In recent years, machine learning has become increasingly important in everyday voice commands and predictions. Instead, it provides a safer auto system and better customer assistance. As a result of all that has been demonstrated, ML is a technology that is becoming more and more popular in a range of industries. To gauge changes in house values, the House Price Index is frequently employed (HPI). Due to the substantial correlation that exists between property prices and other variables, such as location, region, and population, the HPI on its own is not sufficient to accurately forecast a person's house price. Some studies have successfully predicted house prices using conventional machine learning techniques, but they seldom evaluate the efficacy of different models and ignore the more complicated but less well-known models. We proposed Modified Extreme Gradient Boosting as our model in this study due to its adaptive and probabilistic model selection process. Feature engineering, hyperparameter training and optimization, model interpretation, and model selection and evaluation are all steps in the process. Home price indices, which are frequently used to support real estate policy initiatives and estimate housing costs. In this project, models for forecasting changes in home prices are developed using machine learning methods.
Predicting_housing_prices_using_advanced.pdfAyesha Lata
This document discusses various regression techniques that can be used to predict housing prices based on different housing characteristics and features. It first provides background on housing price prediction and factors that influence prices. Then it describes several regression algorithms (hedonic pricing model, artificial neural networks, lasso regression, XGBoost) that can be used to predict prices. The document uses the Ames Housing dataset to test a lasso regression model and analyze impact of features like size, bedrooms, location on prices. The goal is to determine the most accurate advanced methodology for housing price prediction.
Review on House Price Prediction through Regression TechniquesIRJET Journal
This document discusses and compares various machine learning regression techniques for predicting house prices, including linear regression, decision tree regression, random forest regression, and support vector regression. It finds that random forest regression generally provides the most accurate predictions while being able to handle both continuous and categorical variables. However, linear regression is simpler to implement and understand. The document evaluates the techniques based on features, advantages, disadvantages, training speed, prediction speed, and understandability to determine the best algorithm for house price prediction.
House Price Prediction Using Machine LearningIRJET Journal
This document discusses predicting house prices using machine learning algorithms. It begins with an abstract that outlines using machine learning concepts to accurately predict real estate prices based on current market factors. The document then provides details on the proposed system, which uses machine learning models and algorithms like linear regression, Lasso, and decision trees to analyze historical housing data and predict future property prices in India with high accuracy. It aims to help buyers, investors and builders by evaluating market trends and identifying affordable properties. The system is demonstrated on housing data from Bangalore, India.
Housing Price Prediction using Machine LearningIRJET Journal
This document discusses using machine learning algorithms to predict housing prices. It first outlines factors that influence housing prices, such as location, structural characteristics, and neighborhood quality. It then evaluates several machine learning algorithms for predicting prices, including multiple linear regression, decision tree regression, and evaluating their respective accuracies. Specifically, decision tree regression achieved the highest accuracy of 84.64% on a Boston housing dataset. Overall, the document examines how machine learning can accurately predict housing prices based on relevant attributes.
House Price Estimates Based on Machine Learning Algorithmijtsrd
Housing prices are increasing every year, necessitating the creation of a long term housing price strategy. Predicting a homes price will assist a developer in determining a homes purchase price, as well as a consumer in determining the best time to buy a home. The sale price of real estate in major cities depends on the specific circumstances. Housing prices are constantly changing from day to day and are sometimes fired rather than based on estimates. Predicting real estate prices by real factors is a key element as part of our analysis. We want to make our test dependent on all of the simple metrics that are taken into account when deciding the significance. In this research we use linear regression techniques pathway and our results are not self inflicted process rather is a weighted method of various techniques to give the most accurate results. There are fifteen features in the data collection. In this research. There has been an effort to build a forecasting model for determining the price based on the variables that influence the price.The results have proven to be effective lower error and higher accuracy than individual algorithms are used. Jakir Khan | Dr. Ganesh D "House Price Estimates Based on Machine Learning Algorithm" Published in International Journal of Trend in Scientific Research and Development (ijtsrd), ISSN: 2456-6470, Volume-5 | Issue-4 , June 2021, URL: https://www.ijtsrd.compapers/ijtsrd42367.pdf Paper URL: https://www.ijtsrd.comcomputer-science/other/42367/house-price-estimates-based-on-machine-learning-algorithm/jakir-khan
Application of cost effective technology in low cost housing and their propag...Alexander Decker
This document summarizes a study on the application and propagation of cost-effective technologies in low-cost housing in Kerala, India. It describes how the study assessed the economics of various cost-effective building materials and methods compared to conventional techniques. A questionnaire survey was conducted among various income groups to evaluate awareness of cost-effective technologies. The results of the survey were analyzed using statistical tools. Various tables in the results section compare different factors like house ownership, construction materials used, and awareness of organizations promoting low-cost housing techniques. The study concluded the educational qualifications and awareness of groups like Nirmithi Kendra influence the selection and use of cost-effective building methods.
This document discusses predicting real estate prices using machine learning algorithms. It first provides background on the importance of accurately predicting housing prices. It then describes collecting real estate data and analyzing it to gain insights. Various machine learning regression algorithms (linear regression, decision tree regression, gradient boosting, random forest regression) are applied to the data and their results are compared to determine the most accurate algorithm. Visualizations of the data are also created to understand correlations between attributes. The experimental results show the predicted output after entering property inputs into the selected algorithm. In conclusion, a flexible real estate price prediction solution is presented and different technologies are evaluated for feasibility.
House Price Prediction Using Machine Learning Via Data AnalysisIRJET Journal
This document discusses using machine learning models to predict house prices based on various attributes. It describes collecting data on house sales from real estate websites, cleaning the data, and analyzing it. Various regression and classification algorithms are then trained on the data, including decision trees, random forests, and SVMs. The most accurate model was able to predict house prices with over 85% accuracy. A web app was also created using Flask to integrate the trained machine learning model and allow users to get predictions. The goal is to help buyers, sellers, and developers understand house pricing trends and make more informed decisions.
Predicting_housing_prices_using_advanced.pdfAyesha Lata
This document discusses various regression techniques that can be used to predict housing prices based on different housing characteristics and features. It first provides background on housing price prediction and factors that influence prices. Then it describes several regression algorithms (hedonic pricing model, artificial neural networks, lasso regression, XGBoost) that can be used to predict prices. The document uses the Ames Housing dataset to test a lasso regression model and analyze impact of features like size, bedrooms, location on prices. The goal is to determine the most accurate advanced methodology for housing price prediction.
Review on House Price Prediction through Regression TechniquesIRJET Journal
This document discusses and compares various machine learning regression techniques for predicting house prices, including linear regression, decision tree regression, random forest regression, and support vector regression. It finds that random forest regression generally provides the most accurate predictions while being able to handle both continuous and categorical variables. However, linear regression is simpler to implement and understand. The document evaluates the techniques based on features, advantages, disadvantages, training speed, prediction speed, and understandability to determine the best algorithm for house price prediction.
House Price Prediction Using Machine LearningIRJET Journal
This document discusses predicting house prices using machine learning algorithms. It begins with an abstract that outlines using machine learning concepts to accurately predict real estate prices based on current market factors. The document then provides details on the proposed system, which uses machine learning models and algorithms like linear regression, Lasso, and decision trees to analyze historical housing data and predict future property prices in India with high accuracy. It aims to help buyers, investors and builders by evaluating market trends and identifying affordable properties. The system is demonstrated on housing data from Bangalore, India.
Housing Price Prediction using Machine LearningIRJET Journal
This document discusses using machine learning algorithms to predict housing prices. It first outlines factors that influence housing prices, such as location, structural characteristics, and neighborhood quality. It then evaluates several machine learning algorithms for predicting prices, including multiple linear regression, decision tree regression, and evaluating their respective accuracies. Specifically, decision tree regression achieved the highest accuracy of 84.64% on a Boston housing dataset. Overall, the document examines how machine learning can accurately predict housing prices based on relevant attributes.
House Price Estimates Based on Machine Learning Algorithmijtsrd
Housing prices are increasing every year, necessitating the creation of a long term housing price strategy. Predicting a homes price will assist a developer in determining a homes purchase price, as well as a consumer in determining the best time to buy a home. The sale price of real estate in major cities depends on the specific circumstances. Housing prices are constantly changing from day to day and are sometimes fired rather than based on estimates. Predicting real estate prices by real factors is a key element as part of our analysis. We want to make our test dependent on all of the simple metrics that are taken into account when deciding the significance. In this research we use linear regression techniques pathway and our results are not self inflicted process rather is a weighted method of various techniques to give the most accurate results. There are fifteen features in the data collection. In this research. There has been an effort to build a forecasting model for determining the price based on the variables that influence the price.The results have proven to be effective lower error and higher accuracy than individual algorithms are used. Jakir Khan | Dr. Ganesh D "House Price Estimates Based on Machine Learning Algorithm" Published in International Journal of Trend in Scientific Research and Development (ijtsrd), ISSN: 2456-6470, Volume-5 | Issue-4 , June 2021, URL: https://www.ijtsrd.compapers/ijtsrd42367.pdf Paper URL: https://www.ijtsrd.comcomputer-science/other/42367/house-price-estimates-based-on-machine-learning-algorithm/jakir-khan
Application of cost effective technology in low cost housing and their propag...Alexander Decker
This document summarizes a study on the application and propagation of cost-effective technologies in low-cost housing in Kerala, India. It describes how the study assessed the economics of various cost-effective building materials and methods compared to conventional techniques. A questionnaire survey was conducted among various income groups to evaluate awareness of cost-effective technologies. The results of the survey were analyzed using statistical tools. Various tables in the results section compare different factors like house ownership, construction materials used, and awareness of organizations promoting low-cost housing techniques. The study concluded the educational qualifications and awareness of groups like Nirmithi Kendra influence the selection and use of cost-effective building methods.
This document discusses predicting real estate prices using machine learning algorithms. It first provides background on the importance of accurately predicting housing prices. It then describes collecting real estate data and analyzing it to gain insights. Various machine learning regression algorithms (linear regression, decision tree regression, gradient boosting, random forest regression) are applied to the data and their results are compared to determine the most accurate algorithm. Visualizations of the data are also created to understand correlations between attributes. The experimental results show the predicted output after entering property inputs into the selected algorithm. In conclusion, a flexible real estate price prediction solution is presented and different technologies are evaluated for feasibility.
House Price Prediction Using Machine Learning Via Data AnalysisIRJET Journal
This document discusses using machine learning models to predict house prices based on various attributes. It describes collecting data on house sales from real estate websites, cleaning the data, and analyzing it. Various regression and classification algorithms are then trained on the data, including decision trees, random forests, and SVMs. The most accurate model was able to predict house prices with over 85% accuracy. A web app was also created using Flask to integrate the trained machine learning model and allow users to get predictions. The goal is to help buyers, sellers, and developers understand house pricing trends and make more informed decisions.
House Price Anticipation with Machine LearningIRJET Journal
This document provides an overview of a study that uses artificial neural networks to predict house prices. The study utilizes a dataset containing house attributes like square footage and location. These features are preprocessed to address issues like missing values. The neural network is trained on historical housing data and undergoes backpropagation to minimize prediction error. Hyperparameter tuning is performed to optimize model performance. The trained ANN can predict house prices with high accuracy, outperforming traditional regression models. Model performance is evaluated using metrics like mean absolute error and R-squared. The study aims to develop a robust methodology for accurate house price prediction that can benefit various stakeholders in the real estate industry.
This document is a seminar report submitted by a student named Shahbaz Khan to Visvesvaraya Technological University in partial fulfillment of a bachelor's degree in electronics and communication engineering. The report describes a project to predict house prices in Mumbai using machine learning models. It explores a dataset of Mumbai house listings, applies techniques like data visualization, transformation and several regression models to predict prices. It finds that linear regression has the best performance and can be used to build a house price prediction application.
Unveiling Patterns in European Airbnb Prices: A Comprehensive Analytical Stud...IRJET Journal
This study analyzes factors influencing Airbnb pricing in major European cities using machine learning techniques. Regression and random forest models are applied to a dataset of over 50,000 European Airbnb listings. Key findings include: location is a significant pricing determinant, with proximity to city centers and attractions linked to higher prices; entire home rentals generally cost more than private or shared rooms; property features like size and amenities also impact price. The random forest model best captures non-linear relationships and predicts pricing compared to linear regression models. This research provides insights into Airbnb pricing dynamics across Europe.
This document describes a system for predicting house prices using data mining and linear regression. It analyzes past housing market trends and prices to predict future prices. The system accepts a customer's specifications and uses a linear regression algorithm to search for matching properties and forecast prices. This helps customers invest without an agent and reduces risks. It describes the linear regression algorithm used to analyze past price data and generate equations to predict future prices based on quarterly data. The system works by accepting customer inputs, searching data, returning results, and allowing customers to request future price predictions.
The role of neural network for estimating real estate prices value in post C...IJECEIAES
The main goal of this paper was to explore the use of an artificial neural network (ANN) model in predicting real estate prices in the Middle East market. Although conventional modeling approaches such as regression can be used in prediction, they have a weakness of a predetermined relationship between input and output. In this regard, using the ANN model was expected to reduce the bias and ensure non-linear relationships are also covered in the prediction process for more accurate results. The ANN model was created using Python v.3.10 program. The model exhibited a high correlation between predicted and actual house price data (R=0.658). In this respect, it was realized that the model could be effectively used in appraising real estate by investors. However, a major limitation of the model was realized to be a limited dataset for large and luxurious houses, which were not accurately predicted as data distribution between actual and predicted values became sparse for high house prices. A key recommendation made is that future research should include more variables related to luxurious houses and macroeconomic factors to increase the ANN model accuracy.
With China’s rapid economic growth in recent years and the acceleration of urbanization, the real estate price has
also shown a substantial increase, especially the housing prices have always been high in first-tier cities. This paper
systematically combs the research on the factors affecting house price and the forecasting method of house price at
home and abroad, and puts forward some suggestions on the regulation and control of real estate price in our
country. It also points out the deficiency of data statistics and research perspective in empirical research. On this
basis, it is proposed that we should strengthen the scientificalness and comprehensiveness of the empirical data, put
forward a reasonable and appropriate hierarchical classification method for influencing factors, make clear the
importance and coupling mechanism of each level, and excavate the dominant influencing factors.
IRJET- Valuation of Real Estate in Karad CityIRJET Journal
This document discusses valuation of real estate properties in Karad City, India. It aims to develop a model using fuzzy logic to accurately predict residential property prices. Accurate property valuation is important for real estate investors and markets. Currently, property valuation considers various qualitative characteristics but predicting prices precisely is complex due to different location and use factors. The document reviews the need for accurate valuation and challenges in the valuation process. It also provides an overview of fuzzy logic systems and their use in applications like real estate valuation to account for various intrinsic and extrinsic pricing factors. The overall goal is to help investors value properties at precise rates.
“Analysis & Critical study of Impacts of RERA Act, 2016 on Housing Projects i...IRJET Journal
This document summarizes research analyzing the impacts of India's Real Estate Regulation and Development Act (RERA) of 2016 on housing projects in Kolhapur. It begins with an abstract describing the study's focus on Kolhapur City and investigation of RERA's impact on India's construction industry through questionnaires using a Likert scale. Key findings include that RERA has positively impacted the industry by increasing transparency, accountability, and protections for home buyers, but has also increased project costs and registration fees. The document then provides an in-depth literature review of previous research analyzing various factors of delays in construction projects and RERA's effects. It concludes with suggestions that while RERA has improved commitments to buyers,
“Analysis & Critical study of Impacts of RERA Act, 2016 on Housing Projects i...IRJET Journal
This document summarizes research analyzing the impacts of India's Real Estate Regulation and Development Act (RERA) of 2016 on housing projects in Kolhapur. It begins with an abstract describing the study's focus on Kolhapur City and investigation of RERA's impact on India's construction industry through questionnaires using a Likert scale. Key findings include that RERA has positively impacted the industry by increasing transparency, accountability, and protections for home buyers, but has also increased project costs and registration fees. The document then provides an in-depth literature review of previous research analyzing various factors of delays in construction projects and RERA's effects. It concludes with suggestions that while RERA has improved commitments to buyers,
Factors influencing the rise of house price in klang valleyeSAT Journals
Abstract
There is an increase of house price radically in Klang Valley that affect to Malaysian house buyer. House price is the value to be paid for the dealing of buying a residential property. House price rises continuously respecting few factors and had impacting house buyer in decision to buy their house. This study becomes necessary since there is less research that gives information in the factors influencing the rise of house price. The factors are found out through detailed literature reviews and information from pilot study. Pilot study is conducted through interviewing representative from National House Buyer Association, pioneer in solving house related problem, to provide legal suggestion and etc. The data is collected via questionnaire survey form distributed to respondents in sample area. The sample area is Klang Valley region, 10 municipal districts including Kuala Lumpur, the Capital City. In result and analysis stages, the factors had to be refined by analyzing the data using statistical tests. Every single factors are calculated its average index respect to few level of influence under respondents’ opinion. The index will then treated as influencing level of the factors. Based on the study, fluctuation in housing market, increasing in construction cost, population growth and increasing demand are factors which give major influence to rise of house price. The study also identified housing criteria to be considered during setup of house selling price and also preference among house buyer nowadays. This study also identified cost contributors in construction being foresees as control measure concerned in respect to respondents point of view.
Keywords: House price, affordable, and construction cost
1) The document discusses factors that influence the rise of house prices in the Klang Valley region of Malaysia.
2) It identifies key factors like fluctuations in the housing market, increasing construction costs, population growth, and increasing demand as major influences on increasing house prices.
3) The study found that a lack of responsive housing supply to growing demand, high material and land costs, and a shortage of skilled labor in the construction sector contributed to increased construction costs and limited affordable housing options, exacerbating the rise in house prices.
A Model Proposed for the Prediction of Future Sustainable Residence Specifica...IEREK Press
In Egypt, people are unable to determine the qualities of appropriate residence that achieves quality and occupant satisfaction, and contributes to sustainability of residential conglomerations. In general, developing countries lack housing information which can be used to enhance quality of residence. Also, the methods of assessing and identifying the appropriate criteria for future residence quality remain traditional ones that cannot address the multiple, conflicting, overlapping aspects to reach a good decision. This calls for using the Analytical Network Process (ANP), an effective tool for specifying the relativeimportance of all factors impacting a specific issue for making an appropriate residential decision. In addition, this method provides results for the decision element impacts network within the decision structure; thus contributing to more understanding of the mechanisms and requirements of residence selection. The proposed decision structure comprises a two-level network: main clusters, main elements, and sub-elements included in the demographic characteristics group, the residence criteria group, the demand parameters group, the supply parameters group, the residence specifications group, and the alternatives group which representing, in total, the decision and specifying the percentage needed for each housing level. Results of the model showed complete capacity in smoothly addressing complexities and overlapping in the decision structure. The decision structure showed that 52% chose luxury residence, 28% chose middle-class residence, and 19.5% chose the economic residence. Mechanisms of decision making were analyzed; particularly in terms of relationship to demographic characteristics and residence specifications. Also, the importance and impact of demand / supply parameters in reaching decision were analyzed.
A Model Proposed for the Prediction of Future Sustainable Residence Specifica...IEREK Press
In Egypt, people are unable to determine the qualities of appropriate residence that achieves quality and occupant satisfaction, and contributes to sustainability of residential conglomerations. In general, developing countries lack housing information which can be used to enhance quality of residence. Also, the methods of assessing and identifying the appropriate criteria for future residence quality remain traditional ones that cannot address the multiple, conflicting, overlapping aspects to reach a good decision. This calls for using the Analytical Network Process (ANP), an effective tool for specifying the relative importance of all factors impacting a specific issue for making an appropriate residential decision. In addition, this method provides results for the decision element impacts network within the decision structure; thus contributing to more understanding of the mechanisms and requirements of residence selection. The proposed decision structure comprises a two-level network: main clusters, main elements, and sub-elements included in the demographic characteristics group, the residence criteria group, the demand parameters group, the supply parameters group, the residence specifications group, and the alternatives group which representing, in total, the decision and specifying the percentage needed for each housing level. Results of the model showed complete capacity in smoothly addressing complexities and overlapping in the decision structure. The decision structure showed that 52% chose luxury residence, 28% chose middle-class residence, and 19.5% chose the economic residence. Mechanisms of decision making were analyzed; particularly in terms of relationship to demographic characteristics and residence specifications. Also, the importance and impact of demand / supply parameters in reaching decision were analyzed
The determinants of terrace housing rates in malaysiaLdyn Jfr
- The document discusses a study on the determinants of terrace housing rates in Malaysia. It aims to examine the relationship between housing rates and factors like foreign direct investment, inflation rate, and population growth rate.
- The study uses secondary data from 2006 to 2013 and multiple regression analysis to analyze the impact of the independent variables on terrace housing rates. It finds that the data meets the assumptions of no multicollinearity and serially independent errors based on statistical tests.
IRJET- House Cost Prediction using Data Science and Machine LearningIRJET Journal
This document discusses using machine learning techniques to predict housing prices based on collected data. Specifically, it uses regression methods like linear regression, multiple linear regression, and polynomial regression to model housing prices based on features like number of bedrooms, bathrooms, square footage, and year built. It first explores the dataset to understand relationships between variables, then splits the data into training and test sets to build models and evaluate their predictive performance using metrics like RMSE and R-squared. The goal is to determine which regression technique most accurately predicts housing cost to help buyers, sellers, and developers. Future work could involve applying additional algorithms to larger datasets for potentially better results.
Cost Control on Construction with Maximum Usage of Ecofriendly MaterialsIRJET Journal
This paper analyzes cost control methods in construction using ecofriendly materials. A survey was conducted among the public and construction professionals to understand housing costs and identify more affordable alternatives. Common building materials and their costs were examined along with potential substitute ecofriendly materials. Techniques like using fly ash cement, recycled steel, and precast concrete could reduce construction costs by around 10%. The study found that implementing alternative materials and construction methods could lower costs by up to 20% compared to traditional approaches. The paper concludes that widespread use of local, natural materials and low-cost technologies could help address India's shortage of affordable housing.
IRJET- Stock Market Prediction using Financial News ArticlesIRJET Journal
This document presents a system for predicting stock prices using financial news articles and machine learning. It first extracts data from trusted news sources and cleans it using natural language processing. Sentiment analysis determines if the news is positive or negative. This polarity is input to a machine learning model, which uses an algorithm like linear regression to predict if a stock's price will increase in the next 10 minutes. The system was tested on a dataset divided into 70% for training and 30% for testing. Accuracy, specificity and precision metrics showed the system could successfully predict stock price movements based on analyzing financial news sentiment.
The usage of Neural network s has determined a variegated area of packages in the present world. This has caused the
improvement of various fashions for economic markets and funding. This paper represents the idea the way to predict share
market fee the use of artificial Neural community with a given enter parameters of share marketplace. The proportion
marketplace is dynamic in nature approach to expect percentage fee could be very complex method by using trendy prediction
or computation method. Its predominant motive is that there is no linear relationship between market parameters and target last
price. Since there is no linear relationship between input patterns and corresponding output patterns, so use of neural network is
a desire of hobby for share market prediction.
An empirical study to Understand the Factors that Influences Consumer Buying ...scmsnoida5
Indian housing sector is growing at a very rapid
rate. There is a great demand for organized
houses. This study takes up the question of buying
behavior and the reason for the preference of
Housing Projects in a wide context. It tries
to identify the existing market structure for
the product and the factors influencing the
customers to buy Housing projects as well as to
analyze the purchase behavior of customers in
preferring the choice of a House. To prepare an
effective marketing strategy, a company must do
competitor analysis, pest analysis, value chain
analysis, swot analysis as well as its potential and
prospect customer. This is especially necessary in a
developing economy because sales can be gained
only by winning them away from competitor’s
offerings. The marketing activities through
sales promotion and social media tactics has
increased significantly in promoting sales and
preparing the ground for future expansion. The
use of social media sites as part of a company’s marketing strategy has increased significantly in
the past couple of years. The study has used the
primary data to analyze the significant factors
through ANOVA, and Factor analysis which
differ across different demographic variables such
as age, income, education, occupation, gender &
lifestyle.
Analysis of Artificial Intelligence Techniques for Network Intrusion Detectio...IIJSRJournal
With the rapid advancement of computer technology during the last couple of decades. Computer systems are commonly used in manufacturing, corporate, as well as other aspects of human living. As a result, constructing dependable infrastructures is a major challenge for IT managers. On the contrary side, this same rapid advancement of technology has created numerous difficulties in building reliable networks which are challenging tasks. There seem to be numerous varieties of attacks that affect the accessibility, authenticity, as well as secrecy of communications systems. In this paper, an in-depth and all-inclusive description of artificial intelligence methods used for the detection of network intrusions is discussed in detail.
Methodologies for Enhancing Data Integrity and Security in Distributed Cloud ...IIJSRJournal
Usually, cloud infrastructure is used individually by businesses, whereas the hybrid cloud would be a blend of two or many kinds of clouds. Because as clouds become increasingly common, safety issues also expanding. Because of such cybersecurity threats, numerous experts suggested procedures as well as ways to assure internet confidentiality. Providers of cloud-based services were accountable for the complete safety of cloud information. Nevertheless, since the clouds are accessible (easily accessible over the World wide web), much research has been conducted on cloud storage cybersecurity. This paper describes methods for enhancing security and reliability in decentralized cloud-based solutions, as well as suggests a few security solution methods of implementation.
More Related Content
Similar to Machine Learning Based House Price Prediction Using Modified Extreme Boosting
House Price Anticipation with Machine LearningIRJET Journal
This document provides an overview of a study that uses artificial neural networks to predict house prices. The study utilizes a dataset containing house attributes like square footage and location. These features are preprocessed to address issues like missing values. The neural network is trained on historical housing data and undergoes backpropagation to minimize prediction error. Hyperparameter tuning is performed to optimize model performance. The trained ANN can predict house prices with high accuracy, outperforming traditional regression models. Model performance is evaluated using metrics like mean absolute error and R-squared. The study aims to develop a robust methodology for accurate house price prediction that can benefit various stakeholders in the real estate industry.
This document is a seminar report submitted by a student named Shahbaz Khan to Visvesvaraya Technological University in partial fulfillment of a bachelor's degree in electronics and communication engineering. The report describes a project to predict house prices in Mumbai using machine learning models. It explores a dataset of Mumbai house listings, applies techniques like data visualization, transformation and several regression models to predict prices. It finds that linear regression has the best performance and can be used to build a house price prediction application.
Unveiling Patterns in European Airbnb Prices: A Comprehensive Analytical Stud...IRJET Journal
This study analyzes factors influencing Airbnb pricing in major European cities using machine learning techniques. Regression and random forest models are applied to a dataset of over 50,000 European Airbnb listings. Key findings include: location is a significant pricing determinant, with proximity to city centers and attractions linked to higher prices; entire home rentals generally cost more than private or shared rooms; property features like size and amenities also impact price. The random forest model best captures non-linear relationships and predicts pricing compared to linear regression models. This research provides insights into Airbnb pricing dynamics across Europe.
This document describes a system for predicting house prices using data mining and linear regression. It analyzes past housing market trends and prices to predict future prices. The system accepts a customer's specifications and uses a linear regression algorithm to search for matching properties and forecast prices. This helps customers invest without an agent and reduces risks. It describes the linear regression algorithm used to analyze past price data and generate equations to predict future prices based on quarterly data. The system works by accepting customer inputs, searching data, returning results, and allowing customers to request future price predictions.
The role of neural network for estimating real estate prices value in post C...IJECEIAES
The main goal of this paper was to explore the use of an artificial neural network (ANN) model in predicting real estate prices in the Middle East market. Although conventional modeling approaches such as regression can be used in prediction, they have a weakness of a predetermined relationship between input and output. In this regard, using the ANN model was expected to reduce the bias and ensure non-linear relationships are also covered in the prediction process for more accurate results. The ANN model was created using Python v.3.10 program. The model exhibited a high correlation between predicted and actual house price data (R=0.658). In this respect, it was realized that the model could be effectively used in appraising real estate by investors. However, a major limitation of the model was realized to be a limited dataset for large and luxurious houses, which were not accurately predicted as data distribution between actual and predicted values became sparse for high house prices. A key recommendation made is that future research should include more variables related to luxurious houses and macroeconomic factors to increase the ANN model accuracy.
With China’s rapid economic growth in recent years and the acceleration of urbanization, the real estate price has
also shown a substantial increase, especially the housing prices have always been high in first-tier cities. This paper
systematically combs the research on the factors affecting house price and the forecasting method of house price at
home and abroad, and puts forward some suggestions on the regulation and control of real estate price in our
country. It also points out the deficiency of data statistics and research perspective in empirical research. On this
basis, it is proposed that we should strengthen the scientificalness and comprehensiveness of the empirical data, put
forward a reasonable and appropriate hierarchical classification method for influencing factors, make clear the
importance and coupling mechanism of each level, and excavate the dominant influencing factors.
IRJET- Valuation of Real Estate in Karad CityIRJET Journal
This document discusses valuation of real estate properties in Karad City, India. It aims to develop a model using fuzzy logic to accurately predict residential property prices. Accurate property valuation is important for real estate investors and markets. Currently, property valuation considers various qualitative characteristics but predicting prices precisely is complex due to different location and use factors. The document reviews the need for accurate valuation and challenges in the valuation process. It also provides an overview of fuzzy logic systems and their use in applications like real estate valuation to account for various intrinsic and extrinsic pricing factors. The overall goal is to help investors value properties at precise rates.
“Analysis & Critical study of Impacts of RERA Act, 2016 on Housing Projects i...IRJET Journal
This document summarizes research analyzing the impacts of India's Real Estate Regulation and Development Act (RERA) of 2016 on housing projects in Kolhapur. It begins with an abstract describing the study's focus on Kolhapur City and investigation of RERA's impact on India's construction industry through questionnaires using a Likert scale. Key findings include that RERA has positively impacted the industry by increasing transparency, accountability, and protections for home buyers, but has also increased project costs and registration fees. The document then provides an in-depth literature review of previous research analyzing various factors of delays in construction projects and RERA's effects. It concludes with suggestions that while RERA has improved commitments to buyers,
“Analysis & Critical study of Impacts of RERA Act, 2016 on Housing Projects i...IRJET Journal
This document summarizes research analyzing the impacts of India's Real Estate Regulation and Development Act (RERA) of 2016 on housing projects in Kolhapur. It begins with an abstract describing the study's focus on Kolhapur City and investigation of RERA's impact on India's construction industry through questionnaires using a Likert scale. Key findings include that RERA has positively impacted the industry by increasing transparency, accountability, and protections for home buyers, but has also increased project costs and registration fees. The document then provides an in-depth literature review of previous research analyzing various factors of delays in construction projects and RERA's effects. It concludes with suggestions that while RERA has improved commitments to buyers,
Factors influencing the rise of house price in klang valleyeSAT Journals
Abstract
There is an increase of house price radically in Klang Valley that affect to Malaysian house buyer. House price is the value to be paid for the dealing of buying a residential property. House price rises continuously respecting few factors and had impacting house buyer in decision to buy their house. This study becomes necessary since there is less research that gives information in the factors influencing the rise of house price. The factors are found out through detailed literature reviews and information from pilot study. Pilot study is conducted through interviewing representative from National House Buyer Association, pioneer in solving house related problem, to provide legal suggestion and etc. The data is collected via questionnaire survey form distributed to respondents in sample area. The sample area is Klang Valley region, 10 municipal districts including Kuala Lumpur, the Capital City. In result and analysis stages, the factors had to be refined by analyzing the data using statistical tests. Every single factors are calculated its average index respect to few level of influence under respondents’ opinion. The index will then treated as influencing level of the factors. Based on the study, fluctuation in housing market, increasing in construction cost, population growth and increasing demand are factors which give major influence to rise of house price. The study also identified housing criteria to be considered during setup of house selling price and also preference among house buyer nowadays. This study also identified cost contributors in construction being foresees as control measure concerned in respect to respondents point of view.
Keywords: House price, affordable, and construction cost
1) The document discusses factors that influence the rise of house prices in the Klang Valley region of Malaysia.
2) It identifies key factors like fluctuations in the housing market, increasing construction costs, population growth, and increasing demand as major influences on increasing house prices.
3) The study found that a lack of responsive housing supply to growing demand, high material and land costs, and a shortage of skilled labor in the construction sector contributed to increased construction costs and limited affordable housing options, exacerbating the rise in house prices.
A Model Proposed for the Prediction of Future Sustainable Residence Specifica...IEREK Press
In Egypt, people are unable to determine the qualities of appropriate residence that achieves quality and occupant satisfaction, and contributes to sustainability of residential conglomerations. In general, developing countries lack housing information which can be used to enhance quality of residence. Also, the methods of assessing and identifying the appropriate criteria for future residence quality remain traditional ones that cannot address the multiple, conflicting, overlapping aspects to reach a good decision. This calls for using the Analytical Network Process (ANP), an effective tool for specifying the relativeimportance of all factors impacting a specific issue for making an appropriate residential decision. In addition, this method provides results for the decision element impacts network within the decision structure; thus contributing to more understanding of the mechanisms and requirements of residence selection. The proposed decision structure comprises a two-level network: main clusters, main elements, and sub-elements included in the demographic characteristics group, the residence criteria group, the demand parameters group, the supply parameters group, the residence specifications group, and the alternatives group which representing, in total, the decision and specifying the percentage needed for each housing level. Results of the model showed complete capacity in smoothly addressing complexities and overlapping in the decision structure. The decision structure showed that 52% chose luxury residence, 28% chose middle-class residence, and 19.5% chose the economic residence. Mechanisms of decision making were analyzed; particularly in terms of relationship to demographic characteristics and residence specifications. Also, the importance and impact of demand / supply parameters in reaching decision were analyzed.
A Model Proposed for the Prediction of Future Sustainable Residence Specifica...IEREK Press
In Egypt, people are unable to determine the qualities of appropriate residence that achieves quality and occupant satisfaction, and contributes to sustainability of residential conglomerations. In general, developing countries lack housing information which can be used to enhance quality of residence. Also, the methods of assessing and identifying the appropriate criteria for future residence quality remain traditional ones that cannot address the multiple, conflicting, overlapping aspects to reach a good decision. This calls for using the Analytical Network Process (ANP), an effective tool for specifying the relative importance of all factors impacting a specific issue for making an appropriate residential decision. In addition, this method provides results for the decision element impacts network within the decision structure; thus contributing to more understanding of the mechanisms and requirements of residence selection. The proposed decision structure comprises a two-level network: main clusters, main elements, and sub-elements included in the demographic characteristics group, the residence criteria group, the demand parameters group, the supply parameters group, the residence specifications group, and the alternatives group which representing, in total, the decision and specifying the percentage needed for each housing level. Results of the model showed complete capacity in smoothly addressing complexities and overlapping in the decision structure. The decision structure showed that 52% chose luxury residence, 28% chose middle-class residence, and 19.5% chose the economic residence. Mechanisms of decision making were analyzed; particularly in terms of relationship to demographic characteristics and residence specifications. Also, the importance and impact of demand / supply parameters in reaching decision were analyzed
The determinants of terrace housing rates in malaysiaLdyn Jfr
- The document discusses a study on the determinants of terrace housing rates in Malaysia. It aims to examine the relationship between housing rates and factors like foreign direct investment, inflation rate, and population growth rate.
- The study uses secondary data from 2006 to 2013 and multiple regression analysis to analyze the impact of the independent variables on terrace housing rates. It finds that the data meets the assumptions of no multicollinearity and serially independent errors based on statistical tests.
IRJET- House Cost Prediction using Data Science and Machine LearningIRJET Journal
This document discusses using machine learning techniques to predict housing prices based on collected data. Specifically, it uses regression methods like linear regression, multiple linear regression, and polynomial regression to model housing prices based on features like number of bedrooms, bathrooms, square footage, and year built. It first explores the dataset to understand relationships between variables, then splits the data into training and test sets to build models and evaluate their predictive performance using metrics like RMSE and R-squared. The goal is to determine which regression technique most accurately predicts housing cost to help buyers, sellers, and developers. Future work could involve applying additional algorithms to larger datasets for potentially better results.
Cost Control on Construction with Maximum Usage of Ecofriendly MaterialsIRJET Journal
This paper analyzes cost control methods in construction using ecofriendly materials. A survey was conducted among the public and construction professionals to understand housing costs and identify more affordable alternatives. Common building materials and their costs were examined along with potential substitute ecofriendly materials. Techniques like using fly ash cement, recycled steel, and precast concrete could reduce construction costs by around 10%. The study found that implementing alternative materials and construction methods could lower costs by up to 20% compared to traditional approaches. The paper concludes that widespread use of local, natural materials and low-cost technologies could help address India's shortage of affordable housing.
IRJET- Stock Market Prediction using Financial News ArticlesIRJET Journal
This document presents a system for predicting stock prices using financial news articles and machine learning. It first extracts data from trusted news sources and cleans it using natural language processing. Sentiment analysis determines if the news is positive or negative. This polarity is input to a machine learning model, which uses an algorithm like linear regression to predict if a stock's price will increase in the next 10 minutes. The system was tested on a dataset divided into 70% for training and 30% for testing. Accuracy, specificity and precision metrics showed the system could successfully predict stock price movements based on analyzing financial news sentiment.
The usage of Neural network s has determined a variegated area of packages in the present world. This has caused the
improvement of various fashions for economic markets and funding. This paper represents the idea the way to predict share
market fee the use of artificial Neural community with a given enter parameters of share marketplace. The proportion
marketplace is dynamic in nature approach to expect percentage fee could be very complex method by using trendy prediction
or computation method. Its predominant motive is that there is no linear relationship between market parameters and target last
price. Since there is no linear relationship between input patterns and corresponding output patterns, so use of neural network is
a desire of hobby for share market prediction.
An empirical study to Understand the Factors that Influences Consumer Buying ...scmsnoida5
Indian housing sector is growing at a very rapid
rate. There is a great demand for organized
houses. This study takes up the question of buying
behavior and the reason for the preference of
Housing Projects in a wide context. It tries
to identify the existing market structure for
the product and the factors influencing the
customers to buy Housing projects as well as to
analyze the purchase behavior of customers in
preferring the choice of a House. To prepare an
effective marketing strategy, a company must do
competitor analysis, pest analysis, value chain
analysis, swot analysis as well as its potential and
prospect customer. This is especially necessary in a
developing economy because sales can be gained
only by winning them away from competitor’s
offerings. The marketing activities through
sales promotion and social media tactics has
increased significantly in promoting sales and
preparing the ground for future expansion. The
use of social media sites as part of a company’s marketing strategy has increased significantly in
the past couple of years. The study has used the
primary data to analyze the significant factors
through ANOVA, and Factor analysis which
differ across different demographic variables such
as age, income, education, occupation, gender &
lifestyle.
Similar to Machine Learning Based House Price Prediction Using Modified Extreme Boosting (20)
Analysis of Artificial Intelligence Techniques for Network Intrusion Detectio...IIJSRJournal
With the rapid advancement of computer technology during the last couple of decades. Computer systems are commonly used in manufacturing, corporate, as well as other aspects of human living. As a result, constructing dependable infrastructures is a major challenge for IT managers. On the contrary side, this same rapid advancement of technology has created numerous difficulties in building reliable networks which are challenging tasks. There seem to be numerous varieties of attacks that affect the accessibility, authenticity, as well as secrecy of communications systems. In this paper, an in-depth and all-inclusive description of artificial intelligence methods used for the detection of network intrusions is discussed in detail.
Methodologies for Enhancing Data Integrity and Security in Distributed Cloud ...IIJSRJournal
Usually, cloud infrastructure is used individually by businesses, whereas the hybrid cloud would be a blend of two or many kinds of clouds. Because as clouds become increasingly common, safety issues also expanding. Because of such cybersecurity threats, numerous experts suggested procedures as well as ways to assure internet confidentiality. Providers of cloud-based services were accountable for the complete safety of cloud information. Nevertheless, since the clouds are accessible (easily accessible over the World wide web), much research has been conducted on cloud storage cybersecurity. This paper describes methods for enhancing security and reliability in decentralized cloud-based solutions, as well as suggests a few security solution methods of implementation.
Agriculture in Indian Economy and Contribution of Science and Technology IIJSRJournal
One of the oldest occupations in history, agriculture has benefited much from innovation throughout the years. Since then, science has played a significant role in agricultural innovation and quality assurance. We have listed a few of the factors that were mentioned in the introduction section if you'd want to understand more about the significance of science and technology in agriculture. Encouraging the use of science and technology is the cornerstone for improving agriculture's productivity, quality, efficiency, and competitiveness, which also contributes to the modernization of agriculture and rural areas, ensures food security, social security, and increases the income of agricultural producers and traders.
The Effect of Kronecker Tensor Product Values on ECG Rates: A Study on Savitz...IIJSRJournal
This article presents a study on ECG signal filtering algorithms to denoise signals corrupted by various types of noise sources. The study also examines the effect of Kronecker tensor product values on ECG rates. The study is conducted in a Matlab environment, and the results demonstrate that a constant number for the respective codes can effectively denoise ECG signals without any trouble. These findings have significant implications for diagnosing abnormal heart rhythms and investigating chest pains. The present study is novel in that it explores the relationship between ECG rate and Kronecker delta values across different age groups, which has not been extensively studied in previous literature. The study's unique contribution is the determination of age-specific values of the constant K required to represent this relationship accurately in different populations, which could inform the development of more effective algorithms for denoising ECG signals in clinical settings. Additionally, this study's finding of an inverse relationship between ECG rate and Kronecker delta values could have broader implications for understanding the physiological factors that contribute to variability in ECG measurements. The study provides valuable insights into ECG signal processing and suggests that the implemented techniques can improve the accuracy of ECG signal analysis in real-time clinical settings. Overall, the manuscript is a valuable contribution to the field of biomedical signal processing and provides important information for researchers and healthcare professionals.
Basic Criteria for Building the Third Renaissance in Uzbekistan IIJSRJournal
On the occasion of the 29th anniversary of the independence of the Republic of Uzbekistan, President Shavkat Mirziyoyev emphasized that the goal of our development should be the Third Renaissance. This strategic idea, in its grandeur, shows the need to aim for a common goal in all aspects of national development. In practice, the head of state expressed the new and clarified content of the national idea of Uzbekistan at the current stage of development. This article analyzes the important role of literature, theater and art in establishing the Third Renaissance in Uzbekistan.
Assessment of Neglected and Under-Utilized Crop Species of African Horned Mel...IIJSRJournal
This document summarizes a research article that assesses the economic and nutritional value of the neglected and underutilized crop species African horned melon in Zambia. Through a literature review and analysis of secondary data sources, the study finds that African horned melon has numerous health benefits as it contains many vitamins and antioxidants. It can help address issues of food insecurity, malnutrition, and support climate-resilient agriculture in Zambia. However, more needs to be done to promote the domestication, production, processing and marketing of this crop to help boost its utilization.
Prevalence of Trichomonas Vaginalis Infection Among Married Pregnant Women in...IIJSRJournal
A cross-sectional survey of Trichomonas vaginalis infection has been conducted among married pregnant women attending antenatal clinics, for the first time in pregnancy, the direct microscopy technique was adopted. Of the 120 pregnant women studied, 4(3.3%) were infected with T. vaginalis. Individuals age 20-25 years were most infected (3.7%). Women in their third trimester of pregnancy were significantly more infected (1.1%), than those in their second trimester (1.6%) and first trimester (2.3%). Despite reporting a low prevalence of T. vaginalis among pregnant women in the study, this does not imply completely ruling out the presence of T. vaginalis among pregnant women due to the diagnostic technique and also that even the low occurrence among pregnant women in the hospitals cannot totally explain general occurrence. T. vaginalis infection can be dangerous and poses serious threat to the health. Hence, the need for prevention of T. vaginalis and that efforts for prevention of T. vaginalis infection should be targeted at all women of child bearing age. Since T. vaginalis is primarily sexually transmitted, educational efforts must be aimed at high risk groups including women without any formal education and must be explicit regarding the behaviours that leads to the spread of T. vaginalis, and other sexually transmitted infections. There is also the need for proper counseling and education on sexual behaviour and genital hygiene which would greatly help in the prevention of the infection.
Factors Influencing Professional Project Management Ethical Practices in Buil...IIJSRJournal
This document discusses factors that influence ethical practices in project management for building construction. It identifies several factors at different levels - organizational, project, and individual professional.
At the organizational level, factors include project environment/culture, stakeholder impacts, and organizational culture. At the project level, key factors are project scope/complexity, financing, risks, and stakeholders. Individual professional factors center on technical skills, qualifications, and personal values of project managers.
Upholding ethical standards is important for quality and avoiding building failures. However, many Nigerian building projects have faced issues due to non-adherence to standards. The document examines this problem by identifying specific influencing factors at different levels to help advance sustainable project management
Assessment of Water Occupancy Rates of the Çamlıgöze Dam Lake between 2010-20...IIJSRJournal
This document analyzes the water occupancy rates of Çamlıgöze Dam Lake in Turkey between 2010-2021. It finds that the annual average water occupancy rate was 69.55% during this period, indicating the lake was approximately 70% full on average. The highest rate was 95.6% in 2021 and the lowest was 55% in 2015 and 2019. This shows that the lake's water levels have remained generally stable with no serious decreases in occupancy rates over the past decade. The lake provides important benefits like energy production and fishing.
Sustainability of Pod Yields of Groundnut through Crop Seasonal Rainfall, Len...IIJSRJournal
A study was conducted with the objective of assessing the effect of crop seasonal rainfall and length of growing period on the sustainability of pod yields of groundnut attained in 31 mandals under arid Alfisols of Anantapur in Andhra Pradesh. We have considered the variability of mandals with regard to (i) crop seasonal rainfall (mm) and (ii) pod yield of groundnut (kg/ha) during 2001 to 2020; (iii) extent of crop area (ha) during 2009 to 2020; and (iv) length of growing period (days). Based on the mean and standard deviation (SD) of each parameter, the mandals were classified into 5 groups viz., (i) G1: Less than (Mean–2SD); (ii) G2: (Mean–2SD) to (Mean–SD); (iii) G3: (Mean–SD) to (Mean+SD); (iv) G4: (Mean+SD) to (Mean+2SD); and (v) G5: More than (Mean+2SD). Out of 31 mandals, 22 mandals for area and crop seasonal rainfall, 20 mandals for LGP and 18 mandals for yield have fallen in G3. Estimates of correlation were derived between groundnut area, crop seasonal rainfall and yield for each mandal over years and tested for significance to assess the superiority of mandals. Significant correlation of yield and crop seasonal rainfall was observed which ranged from 0.433 at Kalyandurg to 0.765 at Putlur. Similarly, significant correlation between yield and area of groundnut was observed in Kalyandurg (-0.764), Brahmasamudram (-0.674) and Rapthadu (-0.584) mandals. The predictability of yield and prediction error were derived based on a regression model of yield calibrated through the crop seasonal rainfall, LGP and crop area in different mandals. The model gave significant predictability (R2) value of 0.46 with prediction error of 90.9 kg/ha and indicated negative effect of area, positive effect of crop seasonal rainfall and LGP on yield. The sustainability yield index ranged from 26.6% (Kambadur) to 87.5% (Peddavadagur) with mean of 53.9% (CV of 30.1%) over years. Ranks were assigned to the mean and variation of area, crop seasonal rainfall, yield, LGP and SYI of each mandal and rank sums were derived. Guntakal, Gooty and Vidapanakal were superior with rank sums of 30, 38 and 70 respectively. Guntakal was superior with an area of 16570 ha (CV of 17.3%), crop seasonal rainfall of 436.1 mm (CV of 33.4%), LGP of 140 days, yield of 644 kg/ha (CV of 70.9%) and SYI of 76.5%, while Gooty was superior with area of 14146 ha (CV of 14.6%), crop seasonal rainfall of 429.6 mm (CV of 42.4%), LGP of 140 days, yield of 663 kg/ha (CV of 69.1%) and SYI of 79.1%. Similarly, Vidapanakal was superior with area of 5077 ha (CV of 31.1%), crop seasonal rainfall of 403.2 mm (CV of 47.4%), LGP of 140 days, yield of 654 kg/ha (CV of 49.5%) and SYI of 77.9%. Due to maximum LGP and crop seasonal rainfall, we recommend that the farmers of these mandals could enhance the area of groundnut and attain maximum sustainable yields under arid Alfisols.
On the Modulation of Biocompatibility of Hydrogels with Collagen and Guar Gum...IIJSRJournal
In this work, we report the synthesis of molybdenum metal-organic frameworks (Mo-MOFs) using 1,3,5-benzenetricarboxylic acid and the amino acids L-phenylalanine, L- tryptophan, and L-histidine as ligands. They were incorporated in hydrogel matrixes comprised of collagen and guar gum to obtain composite hydrogels. The effect of chemical structure of Mo-MOFs on the structure, physicochemical properties and in vitro biocompatibility of hydrogels was studied. These biomaterials showed a super absorbent performance (higher than 2000 ± 169%) and a high degree of reticulation (higher than 75 ± 6%). The microstructure of the composites showed a granular morphology with some porosity. These composites were degraded entirely by hydrolysis at pH 5 and pH 7 at room temperature in time lapses shorter than 15 days. Also, they were biocompatible with porcine dermis fibroblasts not showing cytotoxic effects up to 48 h of incubation allowing its proliferation, and it was observed that the MOF containing L-tryptophan improved notably the biocompatibility of the collagen/guar gum matrix. Finally, the matrixes were tested as vehicles for cell encapsulation and release. The slow-release rates show that fibroblasts tend to remain inside the hydrogel matrixes. Thus, these materials are more suitable for cell scaffolds and tissue engineering applications such as wound healing dressings.
Incorporation of Se (IV) Complexes based on Amino Acids in Biomatrixes in Hyd...IIJSRJournal
Selenium is a non-metal that shows biological interest since it is responsible for modulating various proteins at the micronutrient level in living beings. In this work, new complexes based on the Se (IV) ion with amino acids such as phenylalanine (Se-F), histidine (Se-H) and tryptophan (Se-T) were hydrothermally synthesized and characterized. These were incorporated into biomatrixes based on semi-interpenetrated polymeric networks (Semi-IPN) of collagen-polyurethane-guar gum (CPGG) by the microemulsion process using a mass ratio of 1 wt.% with respect to collagen. The structural and crystalline characteristics that the selenium-amino acid complexes show a performance in modulating the properties of the biomatrixes under study. The results indicate that the incorporation of the complex decreases the crosslinking of the hydrogel, generating granular surfaces with porosity dependent on the type of amino acid. The CPGG Se-T biomatrix shows a swelling capacity of 10200 ± 1100 higher than the CPGG base matrix; while the CPGG Se-F and CPGG Se-T biomatrixes present slow degradation at both physiological and acidic pH. Interestingly, the matrix that includes the Se-F complex significantly stimulates the metabolic activity of L929 fibroblasts for up to 48 h, stimulating their proliferation. The fibroblasts encapsulated on these novel biomatrixes show recurrent release capacity for up to 7 days, where the structure of the CPGG Se-H biomatrix exhibits greater release from the encapsulated cells. These results demonstrate that these innovative biomatrixes could be used in biomedical applications such as dermal tissue regeneration and cell release for a specific biological fate.
Preliminary Evaluation on Vegetative of Rambutan (Nephelium lappaceum) in San...IIJSRJournal
The study was initiated to evaluate the early performance of rambutan (Nephelium lappaceum) vegetative planted on marginal sandy tin-tailing soil. The experiment was carried out for one year in a plot of 4-year-old rambutan cultivar at MARDI Kundang, Rawang, Selangor, Malaysia. Varieties of Mutiara Merah and Mutiara Wangi were used. Data from the plants as a measurement of vegetative growth was recorded. Mutiara Merah proved that it can be well-grown and cultivated on sandy tin-tailing soil. The plant height of Mutiara Merah indicated the highest significant reading. The parameter of canopy width showed the same variety contributed to the highest record. Nevertheless, Mutiara Merah contributed to the highest significant reading on stem diameter and perimeter respectively. Chlorophyll content in leaves of the plant of the same variety recorded the highest SPAD reading. Further field evaluations are needed to determine the relationship of fertilizer level with the different varieties in inducing the growth and yield of rambutan planted in marginal soil.
Analysis of Physicochemical and Microbiological Parameters of Wine Produced f...IIJSRJournal
Wine is a fermented drink made by the controlled culture of yeasts on fruit juices. This study was undertaken to produce acceptable wines from blends of banana and pineapple by the fermentative action of Meyerozyma guilliermondii strain 1621 and Pichia guilliermondii strain PAX-PAT 18S. The fermentation process lasted for a period of 28 days and, the aging process was for 2 months. The fermentation process comprised two set ups- one was fermented by Meyerozyma guilliermondii strain 1621 and the other was fermented by Pichia guilliermondii strain PAX-PAT 18S. The process was monitored and controlled by carrying out physicochemical analysis (pH, temperature, specific gravity, total titratable acidity, and alcohol content) and yeast count using standard methods. There was a decrease in the pH for both wines and an increase in the total titratable acidity. The temperature was between 17 and 27 0C for both wines. The specific gravity of the wines decreased during the fermentation leading to an increase in alcohol production. There was an increase in yeast count from 6.7×107 sfu/ml to 1.8×108 sfu/ml between days 1 and 17 and a decrease from 1.8×108 sfu/ml to 0 sfu/ml between days 17 to 85 for Meyerozyma guilliermondii; also an increase from 5.1×107 sfu/ml to 1.7×108 sfu/ml from day 1 to 17, and a decrease from 1.7×108 sfu/ml to 0 sfu/ml between day 17 to 85 for Pichia guilliermondii. Statistically, there was no significant difference between the yeast counts, temperature, pH, total titratable acidity, and specific gravity but there was signa ificant difference between the alcohol production for both wines. This study shows that wines can be successfully produced using Meyerozyma guilliermondii strain 1621 and Pichia guilliermondii strain PAX-PAT 18S.
Cohesive and Thermal Properties of Sodium Cyanide-Halide Mixed Crystals IIJSRJournal
In order to analyse the cohesive and thermal properties of sodium cyanide-halide mixed crystals an Extended Three Body Force Shell Model (ETSM) has been applied by incorporating the effect of translational-rotational (TR) coupling. We have conducted theoretical research on cohesive and thermal properties, such as cohesive energy (, molecular force constant (f), compressibility (), Restrahlen frequency (, Debye temperature (D), Gruneisen parameter (), Moelwyn Hughes constants (F1) and the ratio of volume thermal expansion coefficient (v) to volume specific heat (Cv), as a function of temperature within the temperature range 50K T 300K at concentration x=0, 0.27, 0.58 and 1. The current model computations and the findings of the available experiments are in good agreement. The ETSM is a sufficiently realistic model and may be applied to a variety of other mixed crystals in this family.
Discussion on Analysis of Effects of Short-Form Video Advertising on the Purc...IIJSRJournal
The purpose of this study is to investigate the impact of informativeness, entertainment, credibility, social interaction, incentives, and irritation of short-form video advertising on social media on the purchase intention of Gen Z in Vietnam through user attitude and advertising value. The methodology is conducting a survey by collecting responses from 1257 respondents who are Gen Z and familiar with social media, which was later analysed using SmartPLS. The main findings are advertising value and user attitude significantly affect customers’ purchase intention; advertising value is directly affected by informativeness, entertainment, and credibility; user attitude is directly affected by social interaction, incentives, and irritation. Finally, the research team proposes some solutions for businesses to increase the purchase intention of Gen Z in Vietnam through short-form video advertising on social media.
Comparison of Glucose in Urine with Likening of Pigeons as Pets IIJSRJournal
If someone is liking pigeons as pets, this may be due to their intelligent, effortless, and loving nature. The chief objectives of this study were to relate pigeon lovers as a pet with the level of glucose in their urine. Around 100 students of Bahauddin Zakariya University Multan Pakistan were participants of this study. Pee has glucose that is measured for measuring the glucose in urine. If glucose is not present in the urine it shows the kidney is working well. There is no major effect of glucose in urine with the love of a pigeon as a pet.
Non-unique Fixed Points of Self Mappings in Bi-metric Spaces IIJSRJournal
In this paper, we prove a few non-unique fixed-point results of mapping on a set with bi-metrics using θ – contraction. We also give an example that justifies our results. In the literature, our result generalized many results.
Research on the Impact of Short-Form Video Advertising on Social Media on the...IIJSRJournal
In recent years, short-form video has become a popular form of advertising on social media. The way consumers make decisions to purchase has changed owing to this new marketing method. This study aims to investigate the impact of informativeness, entertainment, credibility, social interaction, incentives and irritation of short-form video advertising on social media on the purchase intention of Gen Z in Vietnam through user attitude and advertising value. A survey was conducted by collecting responses from 1257 respondents who are Gen Z and familiar with social media, which was later analysed using SmartPLS. The findings revealed that advertising value and user attitude significantly affect customers’ purchase intention. In addition, advertising value is directly affected by informativeness, entertainment and credibility. Meanwhile, user attitude is directly affected by social interaction, incentives and irritation. Finally, the research team propose some solutions for businesses to increase the purchase intention of Gen Z in Vietnam through short-form video advertising on social media.
Can Perfume Allergy Cause Glycosuria? IIJSRJournal
The main aim of this research is to correlate relation between ornament allergy and glycosuria. Glycosuria is a process in which glucose is removed from urine. The value of glucose in blood must be less than 7 mmol/L. Glycosuria is caused by diabetes, high sugar diet, emotion and liver cirrhosis. Some people are sensitive to some fragrances or ornaments when they come in contact with these ornaments, they show marks of allergy like disease in respiratory track, fever, rashes and headache. The best treatment is to avoid such ornaments having unpleasant sharp smell which cause rashes. 17% males have glucose in urine and show perfume allergy while 1.25% females have glucose in urine and have perfume allergy.
Presentation of IEEE Slovenia CIS (Computational Intelligence Society) Chapte...University of Maribor
Slides from talk presenting:
Aleš Zamuda: Presentation of IEEE Slovenia CIS (Computational Intelligence Society) Chapter and Networking.
Presentation at IcETRAN 2024 session:
"Inter-Society Networking Panel GRSS/MTT-S/CIS
Panel Session: Promoting Connection and Cooperation"
IEEE Slovenia GRSS
IEEE Serbia and Montenegro MTT-S
IEEE Slovenia CIS
11TH INTERNATIONAL CONFERENCE ON ELECTRICAL, ELECTRONIC AND COMPUTING ENGINEERING
3-6 June 2024, Niš, Serbia
Literature Review Basics and Understanding Reference Management.pptxDr Ramhari Poudyal
Three-day training on academic research focuses on analytical tools at United Technical College, supported by the University Grant Commission, Nepal. 24-26 May 2024
Low power architecture of logic gates using adiabatic techniquesnooriasukmaningtyas
The growing significance of portable systems to limit power consumption in ultra-large-scale-integration chips of very high density, has recently led to rapid and inventive progresses in low-power design. The most effective technique is adiabatic logic circuit design in energy-efficient hardware. This paper presents two adiabatic approaches for the design of low power circuits, modified positive feedback adiabatic logic (modified PFAL) and the other is direct current diode based positive feedback adiabatic logic (DC-DB PFAL). Logic gates are the preliminary components in any digital circuit design. By improving the performance of basic gates, one can improvise the whole system performance. In this paper proposed circuit design of the low power architecture of OR/NOR, AND/NAND, and XOR/XNOR gates are presented using the said approaches and their results are analyzed for powerdissipation, delay, power-delay-product and rise time and compared with the other adiabatic techniques along with the conventional complementary metal oxide semiconductor (CMOS) designs reported in the literature. It has been found that the designs with DC-DB PFAL technique outperform with the percentage improvement of 65% for NOR gate and 7% for NAND gate and 34% for XNOR gate over the modified PFAL techniques at 10 MHz respectively.
CHINA’S GEO-ECONOMIC OUTREACH IN CENTRAL ASIAN COUNTRIES AND FUTURE PROSPECTjpsjournal1
The rivalry between prominent international actors for dominance over Central Asia's hydrocarbon
reserves and the ancient silk trade route, along with China's diplomatic endeavours in the area, has been
referred to as the "New Great Game." This research centres on the power struggle, considering
geopolitical, geostrategic, and geoeconomic variables. Topics including trade, political hegemony, oil
politics, and conventional and nontraditional security are all explored and explained by the researcher.
Using Mackinder's Heartland, Spykman Rimland, and Hegemonic Stability theories, examines China's role
in Central Asia. This study adheres to the empirical epistemological method and has taken care of
objectivity. This study analyze primary and secondary research documents critically to elaborate role of
china’s geo economic outreach in central Asian countries and its future prospect. China is thriving in trade,
pipeline politics, and winning states, according to this study, thanks to important instruments like the
Shanghai Cooperation Organisation and the Belt and Road Economic Initiative. According to this study,
China is seeing significant success in commerce, pipeline politics, and gaining influence on other
governments. This success may be attributed to the effective utilisation of key tools such as the Shanghai
Cooperation Organisation and the Belt and Road Economic Initiative.
Introduction- e - waste – definition - sources of e-waste– hazardous substances in e-waste - effects of e-waste on environment and human health- need for e-waste management– e-waste handling rules - waste minimization techniques for managing e-waste – recycling of e-waste - disposal treatment methods of e- waste – mechanism of extraction of precious metal from leaching solution-global Scenario of E-waste – E-waste in India- case studies.
6th International Conference on Machine Learning & Applications (CMLA 2024)ClaraZara1
6th International Conference on Machine Learning & Applications (CMLA 2024) will provide an excellent international forum for sharing knowledge and results in theory, methodology and applications of on Machine Learning & Applications.
2. Asian Journal of Applied Science and Technology (AJAST)
Volume 7, Issue 1, Pages 41-54, January-March 2023
ISSN: 2456-883X
42
widely discussed topics related to real estate has been the methodology behind the pricing of properties. As a direct
result of this matter, a variety of stakeholders, including residential investors, real estate investment trusts,
individual investors, and officials from various government [5] agencies, have been prompted to make projections
regarding the future path of home values. These individuals have employed a large number of different methods in
order to achieve their objective. Since the beginning of the Industrial Revolution, urban populations have increased
at an exponential rate, [6] which has resulted in a severe lack of available housing. This is due to the rapid
urbanisation that is taking place in every region of the world at the present time. As more time has passed, a variety
of facets of this problem have become more apparent. This book investigates the widespread housing problems that
plagued Germany's largest cities in the 1980s, when the nation was still in the process of developing its
infrastructure. During this time period, society as a whole started to come to terms with the housing shortage that
was a direct result of economic inequality, as well as the subsequent requirement for more [7] social housing. These
traits have also been identified as problems in developing countries with a more recent urban population, where
cities are still in their early stages of development.
For example, the issue of housing that is not up to standard in India has been the subject of a number of studies.
While Abhay was presenting data on the number of homes built in Karnataka over the course of the previous
decade, he mentioned that despite the housing shortage problem encouraging the building supply, low-quality
housing is widespread throughout the city (2001-2011). When Abhay was talking about the number of residential
construction projects that took place in Delhi over the course of the examined decade, he brought this up [8]. Many
people point to the disproportionately high number of old houses as a major factor that contributes to the shortage
of housing options. It is challenging to estimate the value of a home because of the intricate connections that exist
between a property's physical characteristics, the neighbourhood, and its location.
In particular, the home price forecast model has received a significantly smaller amount of attention in the existing
body of literature in comparison to more conventional approaches to the solution of this problem. In spite of the fact
that there is widespread consensus that this constitutes an urgent problem that needs to be fixed, this keeps
occurring. Machine learning has emerged as an important prediction method as a result of the rise of Big Data [9].
This has made it possible to make more accurate property price forecasts based solely on features of the property,
rather than on historical data. Although a number of studies have been conducted to investigate this question and
found that machine learning is effective, the vast majority of these studies have merely compared the performances
of different models without taking into consideration how to combine different machine learning models in the
most effective way [10]. A modification of the algorithm known as extreme gradient boosting is used in this
research to perform price forecasting for residential real estate. As a result, becoming more familiar with regression
methods within machine learning is intended to be the end result of this project. In order to achieve optimal
performance, it is necessary to process the datasets that have been provided. Because the value of a house is
determined by the characteristics that are unique to it, [11] we need to first establish which of those characteristics
are essential before we can eliminate the ones that aren't important and arrive at an accurate estimate. The data are
skewed as a result of the fact that not all homes would have access to these upgrades; consequently, the price of
houses would not change in the same way without them.
3. Asian Journal of Applied Science and Technology (AJAST)
Volume 7, Issue 1, Pages 41-54, January-March 2023
ISSN: 2456-883X
43
The main objective of this project is to predict the house price using Modified Extreme Gradient Boosting
algorithm. It is used the predict the price using the area type, location, BHK etc., The Modified XGBoost is
measured for accuracy and performance against several algorithms.
░ 2. Literature Survey
The most precise machine learning (ML) models for predicting property values were studied by Park et al. [4]. For
this, they examined a sample of 5359 Virginian row homes. They employed two methods: the first, the RF
approach, was utilised to address a classification issue, while the second, the nave Bayesian algorithm, addressed a
regression issue. According to the findings, the RIPPER algorithm significantly enhanced price prediction. Several
different approaches to machine learning were investigated by Banerjee et al. [12] for the purpose of predicting
whether future real estate prices will go up or down. The RF method was found to have the greatest amount of
overfitting but was also the method with the highest degree of accuracy. However, the SVM technique was the most
trustworthy because it remained unchanged over the course of the study. Kok et al. [13] investigated the usefulness
of several different machine learning strategies in the context of real estate appraisals. These methods included the
RF approach, and the GBR method. The findings demonstrated that the XGBM algorithm achieved the highest
levels of performance overall. Ceh et al. [14] compared the hedonic price model to the RF algorithm in order to
determine which technique would result in more accurate price forecasts. The authors surveyed a total of 7407
different homes in the Ljubljana area between the years of 2008 and 2013. As (Slovenia). a result of the outcomes,
it was clear that the RF model had a superior performance in terms of prediction 5. Using supervised learning
methods, Hu et al. [15] investigated how accurate it is to predict how much it will cost to rent a house in Shenzhen
(China). The authors used the multilayer perceptron neural network (MLP-NN), the k-NN, the RF, the ETR, the
GBR, and the SVR algorithms in their research. The findings indicated that both the RF and ETR algorithms
operated in a more predictable manner.
S. Lu et al. [16] created a model with improved results for evaluating London's spatial closeness and better estimate
performance for property values. These two geographic traits are two examples of non-linear phenomena that defy
linear quantification. Elham Alzain et al. [17].'s goal is to use an ANN-based prediction model to forecast Saudi
Arabia's future home values. In Riyadh, Jeddah, Dammam, and Al-Khobar, four significant Saudi Arabian cities,
the dataset was gathered from Aqar. The findings indicated that the experimental and projected values had a good
degree of agreement. The employment of ANN in this results in an accuracy of 80%. Classification algorithms
were employed by P. Durganjali et al. [18] to predict the cost of resale properties. The selling price of a property is
predicted in this study using a variety of classification methods, including Leaner regression, Decision Tree,
K-Means, and Random Forest. A home's price is influenced by its physical attributes, its geographic location, and
even the state of the economy. Here, we use these techniques, utilise RMSE as the performance matrix for different
datasets, and find the most accurate model that properly predicts improved results.
A hybrid regression technique was created by Sifei Lu et al. [19] to forecast housing prices. A tiny dataset and data
characteristics are used in this study to test the creative feature engineering approach. Recent Kaggle Competition
"House Price: Advanced Regression 6 Methods" entries adopted the suggested methodology as their fundamental
building block. In view of the readers' financial limitations, the article's goal is to estimate reasonable pricing for
4. Asian Journal of Applied Science and Technology (AJAST)
Volume 7, Issue 1, Pages 41-54, January-March 2023
ISSN: 2456-883X
44
the customers. Fletcher et al. [20] (2000) investigate whether it is preferable to employ aggregate or disaggregated
data when hedonic analysis is used to forecast housing price. It is discovered that several features' hedonic pricing
coefficients vary significantly depending on age, location, and kind of property. However, it is believed that using
an aggregate method, this may be properly simulated. The individual external impacts of factors like environmental
attributes on housing prices have also been estimated using the hedonic price model. For instance, several studies
have used the hedonic price model to measure how much noise and air pollution affect home prices.
2.1. Problem Statement
The current technique can forecast some straightforward and modest homes. It also forecasts the accuracy of
different algorithms. It predicts price using a single parameter. The system as it is now does not benefit from its
current training phase. They are unable to forecast a mansion of luxury. It is unable to suggest the optimal
algorithms [21]. Several parameters cannot be used for prediction. The loss function with regularisation is the
objective function that has to be minimised at iteration t:
The XGBoost goal is obviously a function of functions and "cannot be maximized using typical optimization
methods in Euclidean space," as stated.
From, we get the fundamental linear approximation of the function f(x simplest) as follows:
To represent the initial function, only a function of x may be used:
The initial function can only be expressed as a function of x.
In order to convert a function f(x) into the simplest function of x that can be found near a certain point, use Taylor's
theorem. Prior to the application of the Taylor approximation, the objective function f(x), in which x represented
the sum of the t CART trees, was a function of the currently-selected tree (step t). In this particular scenario, the
anticipated outcome from step t-1 is an, the loss function is denoted by the expression f(x), and the variable x
denotes the additional student who needs to be added in step t.
Given the information that was presented earlier, it is possible to optimise in Euclidean space by defining the
objective (loss) function as a straightforward function of the new learner that was introduced at each iteration [22].
This makes it possible to perform optimization in Euclidean space (t). As was mentioned earlier, the additional
learner that needs to be included in step (t) in order to eagerly reduce the target is a stand for the prediction that was
5. Asian Journal of Applied Science and Technology (AJAST)
Volume 7, Issue 1, Pages 41-54, January-March 2023
ISSN: 2456-883X
45
made in steps (t-1) and (x-a). This step is required in order to eagerly reduce the target. When the Taylor
approximation of the second order is utilised:
XGBoost objective using second-order Taylor approximation-
Where:
The loss function's first and second order gradient statistics-
At least, if we eliminate the constant components, we are left with the simplified objective to minimise at step t as
follows:
XGBoost simplified objective-
Our next objective is to identify a learner that minimises the loss function at iteration t since the aforementioned is
a sum of straightforward quadratic functions of a single variable that can be minimised using well-known methods.
Minimizing a simple quadratic function-
Notice how the following scoring function resembles the "basic quadratic function solution" above when using the
authors' method to "assess the quality of a tree structure q":
The tree learner structure q scoring function
Binary classification using the Cross Entropy loss function, where p stands for the probability score and y for the
actual label, both of which are in the range of 0 to 1 [23]. The total of the CART tree learners makes up the model's
6. Asian Journal of Applied Science and Technology (AJAST)
Volume 7, Issue 1, Pages 41-54, January-March 2023
ISSN: 2456-883X
46
output x. We must ascertain the gradient's and hessian's first and second derivatives with respect to x in order to
minimise the log loss objective function. For example, this post on Stats Stack Exchange may teach you that the
formula for the gradient is (p-y) and the formula for the hessian is (p-*) (1-p).
░ 3. Proposed System
This work is used to predict the house price in safe and secured manner. It can predict the house price for great geo
location. It uses Extreme Gradient Boosting for better accuracy. This algorithm uses linear function, likelihood etc.,
It helps the prediction more accurate and easier.
Figure 1. Flow Diagram
The data is collected from the database and the data is pre-processed such noise reduction, anomaly detection,
missing value finding etc., The pre-processed data is trained using various algorithms and the model is tested using
testing data. Then build the model using modified extreme boosting algorithm. Connect the model with flask and
execute. Get the input from the using in the website and extract the keywords from the input. Then predict the value
for the data given.
3.1. System Architecture
Figure 2. Proposed architecture
7. Asian Journal of Applied Science and Technology (AJAST)
Volume 7, Issue 1, Pages 41-54, January-March 2023
ISSN: 2456-883X
47
Algorithm 1. Modified Extreme Boosting
Initialization:
STEP 1:Given training information from the instance space S = (x1, y1),..., (m, ym) where xi EX and y;
Y = -1,+1.
STEP 2: start the distribution off. D₁(i) =.
Using the algorithm for t = 1,..., T, do
Utilizing the distribution Dt, train a weak learner ht: X R.
Zt is a normalisation factor chosen to create the distribution of Dt+1, and its formula is
Dt+1(i) = Dt(i)e-tyiht(xi) Zt.
f(x) = oatht(x) and H(x) = sign(f(x)) are the final scores.
3.2. Modified Extreme Boosting Algorithm
A. General Parameters
silent: Zero is the default value. For printing running messages, you must specify 0; for silent mode, you must
specify 1.
booster: GBTree is the default selection. The booster to employ must be specified: Tree-based GBTree or linear
GBLinear (linear function).
buffer: It is automatically set by the XGBoost algorithm; user input is not required.
num feature: XGBoost Algorithm sets this value automatically; human input is not required.
B. Booster Parameters
ETA: 0.3 is the default setting. To avoid overfitting, you must specify the step size shrinkage utilised in an update.
You can immediately obtain the weights of new features after each boosting stage. In order to increase the
conservatism of the boosting process, eta actually reduces the feature weights. It ranges from 0 to 1. The model is
more resistant to overfitting if the eta value is low.
GAMMA: A default value of 0 has been set. On a leaf node of the tree, you must indicate the minimal loss
reduction necessary to create another division. The algorithm will be more conservative the larger it is. From 0 to is
the range. The algorithm is more conservative the larger the gamma.
MAX DEPTH: A value of six is used by default. A tree's maximum depth must be specified. 1 to make up the
range.
MIN CHILD WEIGHT: By default, the value is set to 1. The bare minimum instance weight (hessian) required in
a child must be specified. if a leaf node emerges from the tree partitioning step. then with instance weight added
together less than the minimum kid weight. The construction process will then give up on more partitions.
8. Asian Journal of Applied Science and Technology (AJAST)
Volume 7, Issue 1, Pages 41-54, January-March 2023
ISSN: 2456-883X
48
corresponds to the bare minimum of instances required to be in each node in linear regression mode. The algorithm
will be more conservative the larger it is. From 0 to is the range.
MAX DELTA STEP: 0 is the default setting. The largest delta step that can be used to estimate each tree's weight.
There is no constraint if the value is set to 0. It can assist make the update step more cautious if it's set to something
positive. Although it is not typically required, this parameter may be useful in logistic regression. especially when
there is a severe imbalance in the class. Setting it to a number between 1 and 10 could aid in updating control. From
0 to is the range.
SAMPLE: 1 is set as default option. The subsample ratio for the training instance must be given. Half of the data
instances will have been randomly chosen by XGBoost if you set it to 0.5. Overfitting must be prevented by
allowing trees to develop. It is between 0 and 1.
COLSAMPLE BYTREE: The value is set to 1 by default. When building each tree, you must give the subsample
ratio of columns. It ranges from 0 to 1.
C. Linear Booster Specific Parameters
These XGBoost Algorithm Linear Booster Specific Parameters are used.
LAMBDA AND ALPHA: These are terms for weight regularisation. Alpha is supposed to be 0, while lambda's
default value is 1.
LAMBDA BIAS: This term has a default value of 0 and is an L2 regularisation term on bias.
D. Learning Task Parameters
The XGBoost algorithm's learning task parameters are listed below.
BASE SCORE: 0.5 is the default value for this field. The initial prediction score and global bias for each
occurrence must be specified.
OBJECTIVE: Reg: linear is the default value set. You must be clear about the kind of learner you require. This
comprises Poisson and linear regression, among others.
EVAL METRIC: The evaluation metrics for the validation data must be specified. Moreover, a default metric will
be chosen in accordance with the goal.
SEED: In order to reproduce the same set of outputs, you must specify the seed here as usual.
3.3. Model Building
Two datasets are required when building a machine learning model: one for training and one for testing. However,
there is now only one. Let's divide this in two according to an 80:20 ratio. Create two columns for features and
labels in the data frame. Here, the train-test split function from Sklearn was loaded. After that, divide the dataset
using it. Moreover, the dataset is split into two halves with test size = 0.2: 20% for the test and 80% for the train.
Using a random number generator that is seeded by the random state parameter, the dataset is partitioned. The
method returns four datasets. These were designated as test x, test y, train x, and train y. To match the data to
9. Asian Journal of Applied Science and Technology (AJAST)
Volume 7, Issue 1, Pages 41-54, January-March 2023
ISSN: 2456-883X
49
several decision trees, use Modified Extreme Boosting. Finally, tell the fit method to pass trains x and y to train the
model. After training, the model must be tested using test data. One of the most potent techniques used in ML for
regression issues is modified extreme boosting. The supervised algorithm class includes the random forest. This
procedure is run in three stages: the first involves assigning the independent variable weight, the second involves
creating the forest from the provided dataset, and the third involves making predictions from the regressor.
Table 1. Algorithm used and its function
ID Model Function
1 Linear Regression sklearn.linear_model.LinearRegression
2 Random Forest Regressor sklearn.ensemble.RandomForestRegressor
3 Gradient Boosting Regressor sklearn.ensemble.GradientBoostingRegressor
4 Ridge Regression sklearn.linear_model.Ridge
5 Lasso Regression sklearn.linear_model.Lasso
6 Ada Boosting Regression sklearn.ensemble.AdaBoostRegressor
7 Decision Tree Regression sklearn.tree.DecisionTreeRegressor
8 Modified Extreme Boosting XGBRegressor()
░ 4. Result and Discussion
The figure 3 shows the data and parameter present in the dataset. It also shows the columns and the rows in the
csv file.
Figure 3. Dataset Description
10. Asian Journal of Applied Science and Technology (AJAST)
Volume 7, Issue 1, Pages 41-54, January-March 2023
ISSN: 2456-883X
50
The figure 4 shows the graph about the data present in the dataset. The ratio of the data is represented as histograms
and bar graph. The bar graph represents the area_type present in the dataset and its count. The first histogram
represents the sqft_per_bhk and its count and density (The weightage given for that parameter). The second
histogram represents the price_per_sqft. The third histogram represents the sqft present in the dataset. The fourth
histogram represents the total_sqft of the house is the buy. The last histogram represents the price in the dataset.
Figure 4. Data Graph
The figure 5 shows the various algorithm used and its accuracy. The algorithm used for Linear Regression, Ridge
Regression, AdaBoost Regression, Decision Tree Regression, Random Forest Regression, Gradient Boosting
Regression and Modified Extreme Boosting Algorithms are used to compare the accuracy with Modified
XGBoost.
Figure 5. Accuracy
11. Asian Journal of Applied Science and Technology (AJAST)
Volume 7, Issue 1, Pages 41-54, January-March 2023
ISSN: 2456-883X
51
Table 2. Accuracy table
S. No. Algorithm Accuracy
1 Linear Regression 0.78021
2 Ridge Regression 0.79019
3 Lasso Regression 0.76216
4 Decision Tree (DT) 0.74478
5 Random Forest (RF) 0.81065
6 AdaBoost (AB) 0.69240
7 Gradient Boosting Tree (GB) 0.60806
8 Modified Extreme Boosting 0.82912
The figure 6 shows the comparison graph between the algorithms to show the performance and efficiency of the
algorithms and it clearly shows that Modified XGBoost is more efficient than any other algorithms
Figure 6. Accuracy graph
This figure 7 shows that front-end of the application which is running on the server 127.0.01.5000 using flask. It
contains the details such as location, area, availability, square footage, BHK, bathrooms. The input needs to be
entered according the user.
12. Asian Journal of Applied Science and Technology (AJAST)
Volume 7, Issue 1, Pages 41-54, January-March 2023
ISSN: 2456-883X
52
Figure 7. Running website on flask
Figure 8. House price prediction
The figure 8 shows the prediction of house price for the given input.
░ 5. Conclusion
The creation of new jobs is a key factor in the expansion of any economy, which may be aided by the real estate
sector. In this scenario, the roles of property owners and receivers are intertwined. That's why it's so important to
have reliable real estate value forecasts. Property prices are a good barometer of an economy's health, so
homeowners and investors pay close attention to trends in home value. Building a model that can foresee future
housing costs can be a valuable tool for regulating property use and planning financially. Assisting policymakers in
13. Asian Journal of Applied Science and Technology (AJAST)
Volume 7, Issue 1, Pages 41-54, January-March 2023
ISSN: 2456-883X
53
setting appropriate pricing and allowing property owners and brokers to make informed decisions are just two of
the many benefits that come from being able to foresee a piece of real estate's future value. In this analysis, we
compare the predictive efficacy of common regression algorithms to that of Bayesian Regression in predicting
Bangalore home prices. Results were promising because of the abundance of features and high correlation in the
publicly available data. Therefore, additional features, ideally with a high correlation to home price, need to be
added to the local data. However, XGBoost produced the best results. According to the study's findings, Modified
XGBoost outperforms competing prediction algorithms. Including user reviews of the property's attributes, price
data from social media, images from Google Maps, and economic statistics could improve ML forecasts in the
future.
Declarations
Source of Funding
This research work did not receive any grant from funding agencies in the public or not-for-profit sectors.
Competing Interests Statement
Authors have declared no competing interests.
Consent for Publication
The authors declare that they consented to the publication of this research work.
Authors’ Contributions
All authors equally contributed to research and paper drafting.
References
[1] Gallent, Nick, Phoebe Stirling, and Iqbal Hamiduddin. (2022). Pandemic mobility, second homes and housing
market change in a rural amenity area during COVID-19–The Brecon Beacons National Park, Wales. Progress in
Planning, 100731.
[2] Gajalakshmi, R. K., et al. (2020). An Optimized ASM based Routing Algorithm for Cognitive Radio Networks.
International Conference on System, Computation, Automation and Networking (ICSCAN), IEEE.
[3] Padmini, S. V. (2022). Socio-economic conditions of slum dwellers in Karnataka-a case study in Tumkur
district. Archers & Elevators Publishing House.
[4] Raj, S. Gokul, N. Srinath, and T. Ananth Kumar (2019). Real-Time Trespasser Detection Using GPS based
UAV. IEEE International Conference on Innovations in Communication, Computing and Instrumentation (ICCI).
[5] Tokunaga, Robert S. (2010). Following you home from school: A critical review and synthesis of research on
cyberbullying victimization. Computers in Human Behavior, 26(3): 277-287.
[6] Arunmozhiselvi, S., et al. (2022). A Systematic Approach to Agricultural Drones Using a Machine Learning
Model. Machine Learning Approaches and Applications in Applied Intelligence for Healthcare Data Analytics.
CRC Press, Pages 41-60.
14. Asian Journal of Applied Science and Technology (AJAST)
Volume 7, Issue 1, Pages 41-54, January-March 2023
ISSN: 2456-883X
54
[7] Nguyen, Quang Hung, et al. (2021). Influence of data splitting on performance of machine learning models in
prediction of shear strength of soil. Mathematical Problems in Engineering, 2021: 1-15.
[8] Rajmohan, R., et al. (2022). G-Sep: A Deep Learning Algorithm for Detection of Long-Term Sepsis Using
Bidirectional Gated Recurrent Unit.
[9] Ford, Elizabeth, et al. (2019). Identifying undetected dementia in UK primary care patients: a retrospective
case-control study comparing machine-learning and standard epidemiological approaches. BMC Medical
Informatics and Decision Making, 19(1): 1-9.
[10] Muthukumarasamy, Sugumaran, et al. (2020). Machine learning in healthcare diagnosis. Blockchain and
Machine Learning for E-Healthcare Sys., 343.
[11] Mair, Carolyn, et al. (2000). An investigation of machine learning based prediction systems. Journal of
systems and software, 53(1): 23-29.
[12] Saravanan, V., et al. (2023). Design of deep learning model for radio resource allocation in 5G for massive IoT
device. Sustainable Energy Technologies and Assessments, 56: 103054.
[13] Čeh, Marjan, et al. (2018). Estimating the performance of random forest versus multiple regression for
predicting prices of the apartments. ISPRS International Journal of Geo-Information, 7(5): 168.
[14] Hong, Yao, Jianhong Kang, and Ceji Fu. (2022). Rapid prediction of mine tunnel fire smoke movement with
machine learning and supercomputing techniques. Fire Safety Journal, 127: 103492.
[15] Lu, Binbin, et al. (2014). Geographically weighted regression with a non-Euclidean distance metric: a case
study using hedonic house price data. International Journal of Geographical Information Science, 28(4): 660-681.
[16] Alzain, Elham, et al. (2022). Application of Artificial Intelligence for Predicting Real Estate Prices: The Case
of Saudi Arabia. Electronics, 11(21): 3448.
[17] Durganjali, P., and M. Vani Pujitha. (2019). House resale price prediction using classification algorithms.
International Conference on Smart Structures and Systems (ICSSS), IEEE.
[18] Lu, Sifei, et al. (2017). A hybrid regression technique for house prices prediction. International Conference on
Industrial Engineering and Engineering Management (IEEM), IEEE.
[19] Prasanalakshmi, B. (2022). Deep Regression hybridized Neural Network in human stress detection.
International Conference on Smart Technologies and Systems for Next Generation Computing (ICSTSN), IEEE.
[20] Fletcher, Mike, Jean Mangan, and Emily Raeburn. (2004). Comparing hedonic models for estimating and
forecasting house prices. Property Management, (3): 189-200.
[21] Hallegatte, Stéphane, et al. (2012). Investment decision making under deep uncertainty-application to climate
change. World Bank Policy Research Working Paper – 6193.
[22] Sun, Shiliang, et al. (2019). A survey of optimization methods from a machine learning perspective. IEEE
Transactions on Cybernetics, 50(8): 3668-3681.
[23] Coenen, Lize, et al. (2022). Machine learning methods for short-term probability of default: A comparison of
classification, regression and ranking methods. Journal of the Operational Research Society, 73(1): 191-206.