This document describes a hybrid intelligent system for forecasting iron prices that integrates web-based text mining, a rule-based expert system, and GMDH neural networks. The system collects relevant information on factors affecting iron prices from the internet using text mining. It extracts rules on the relationship between price movements and influencing factors from historical data using an expert system. Finally, it forecasts future iron prices using the GMDH neural networks model incorporating information from the other modules. The system is tested on daily iron price data from 2009 to 2013 and is found to improve forecasting accuracy over GMDH neural networks alone.
Epic EMR - Root Cause Fault Detection in complex Healthcare Records systemsDennis Redwine
This document discusses the challenges of managing electronic medical record (EMR) systems and proposes using artificial intelligence to help address them. EMR systems are very large and complex with many integrated components supporting critical and diverse medical activities. Outages can put lives at risk. The infrastructure supporting EMR applications is also very complex. AI could help automate monitoring of this infrastructure, identify issues before they impact services, maintain service level agreements, and automate cross-team collaboration to resolve problems. It proposes using narrow AI focused on specific infrastructure elements to provide business impact avoidance, automated expertise, dynamic learning, and end-to-end correlation across the infrastructure.
Useful Techniques in Artificial IntelligenceIla Group
The document discusses artificial intelligence techniques presented by Dr. Will Browne at Cranfield University. It provides examples of applications of AI techniques in various fields such as finance, industry, engineering and control. It then describes common AI techniques such as expert systems, case-based reasoning, genetic algorithms, neural networks, fuzzy logic and cellular automata. The document emphasizes exploring appropriate techniques for problems and avoiding issues like lack of transparency, garbage in-garbage out, and difficulties generalizing from training data.
This document summarizes a presentation on failure analysis basics given to the Huntsville Regional Chapter of the International Council on Systems Engineering on April 26, 2002. The presentation covered the role of failure analysis in design and engineering, concepts and techniques in failure analysis like destructive physical analysis and fault tree analysis, and the future of failure analysis involving multidisciplinary teams. The goal was to develop an understanding of failure and review failure analysis methods.
A Hybrid Model of MEMD and PSO-LSSVR for Steel Price ForecastingDr. Amarjeet Singh
Herein, we propose a novel hybrid method for forecasting steel prices by modeling nonlinearity and time variations together to enhance forecasting adaptability. The multivariate empirical mode decomposition (MEMD)–ensemble-EMD (EEMD) approach was employed for preprocessing to separate the nonlinear and time variation components of a hot-rolled coil (HRC) price return series, and a particle swarm optimization (PSO)-based least squares support vector regression (LSSVR) approach and a generalized autoregressive conditional heteroskedasticity (GARCH) model were applied to capture the nonlinear and time variation characteristics of steel returns, respectively. The empirical results revealed that compared with the traditional models, the proposed hybrid method yields superior forecasting performance for HRC returns. The evidence also suggested that in capturing the price dynamics of HRC during the COVID-19 pandemic period, the asymmetric GARCH model with MEMD–LSSVR outperformed not only standard GARCH models but also the EEMD-LSSVR models. The proposed MEMD–LSSVR–GARCH model for steel price forecasting provides a useful decision support tool for steelmakers and consumers to evaluate steel price trends.
This document describes research on using a Long Short-Term Memory (LSTM) neural network model to predict bitcoin prices over the next 5 days. It discusses collecting bitcoin price data from 2015-2021, cleaning the data, and using features like date, price, high, low to train and test the LSTM model. Lag plots show the data has positive correlation at daily intervals. The model is trained on recent data and tested on past data to predict future prices. Root mean square error is calculated between predicted and actual test prices. The model accurately predicts future prices but could be improved by adding more price-influencing features to the training data.
IRJET- Stock Price Prediction using Long Short Term MemoryIRJET Journal
This document proposes using a Long Short Term Memory (LSTM) recurrent neural network for online stock price prediction. It discusses the limitations of existing batch processing methods and other neural networks in capturing the correlated temporal dependencies in stock price data. The document describes preprocessing stock data and training an LSTM model to predict the end-of-day price. It compares the proposed LSTM approach to other methods and evaluates the predictions against actual prices using metrics like root mean squared error.
Bitcoin Price Prediction using Sentiment and Historical PriceIRJET Journal
1. The document presents a study that uses sentiment analysis and historical price data to predict the price movements of bitcoin.
2. It reviews previous studies that have used machine learning models like LSTM, RNN, and ARIMA with either sentiment data or historical price data to predict bitcoin prices. Accuracy between 40-52% was achieved in previous studies.
3. This study collects sentiment data from investing forums from 2017-2020 and cleans the data. It also collects historical bitcoin price data from 2012-2020. It aims to use both sentiment features and historical price indexes as inputs to deep learning models to improve prediction accuracy.
This document presents a generalized algorithm for optimizing demand prediction of short life cycle products using Markov chains. It begins with an introduction to short life cycle products and issues with demand forecasting for products with very low shelf lives between 1-2 days. It then discusses using Markov chains to model demand as a random variable. An algorithm is developed using Markov chain transition probabilities and steady state probabilities to determine optimal demand forecast. The algorithm is implemented on a baked product to determine optimal demand. It is presented as a novel technique that can improve demand forecasting for short life cycle supply chains.
Epic EMR - Root Cause Fault Detection in complex Healthcare Records systemsDennis Redwine
This document discusses the challenges of managing electronic medical record (EMR) systems and proposes using artificial intelligence to help address them. EMR systems are very large and complex with many integrated components supporting critical and diverse medical activities. Outages can put lives at risk. The infrastructure supporting EMR applications is also very complex. AI could help automate monitoring of this infrastructure, identify issues before they impact services, maintain service level agreements, and automate cross-team collaboration to resolve problems. It proposes using narrow AI focused on specific infrastructure elements to provide business impact avoidance, automated expertise, dynamic learning, and end-to-end correlation across the infrastructure.
Useful Techniques in Artificial IntelligenceIla Group
The document discusses artificial intelligence techniques presented by Dr. Will Browne at Cranfield University. It provides examples of applications of AI techniques in various fields such as finance, industry, engineering and control. It then describes common AI techniques such as expert systems, case-based reasoning, genetic algorithms, neural networks, fuzzy logic and cellular automata. The document emphasizes exploring appropriate techniques for problems and avoiding issues like lack of transparency, garbage in-garbage out, and difficulties generalizing from training data.
This document summarizes a presentation on failure analysis basics given to the Huntsville Regional Chapter of the International Council on Systems Engineering on April 26, 2002. The presentation covered the role of failure analysis in design and engineering, concepts and techniques in failure analysis like destructive physical analysis and fault tree analysis, and the future of failure analysis involving multidisciplinary teams. The goal was to develop an understanding of failure and review failure analysis methods.
A Hybrid Model of MEMD and PSO-LSSVR for Steel Price ForecastingDr. Amarjeet Singh
Herein, we propose a novel hybrid method for forecasting steel prices by modeling nonlinearity and time variations together to enhance forecasting adaptability. The multivariate empirical mode decomposition (MEMD)–ensemble-EMD (EEMD) approach was employed for preprocessing to separate the nonlinear and time variation components of a hot-rolled coil (HRC) price return series, and a particle swarm optimization (PSO)-based least squares support vector regression (LSSVR) approach and a generalized autoregressive conditional heteroskedasticity (GARCH) model were applied to capture the nonlinear and time variation characteristics of steel returns, respectively. The empirical results revealed that compared with the traditional models, the proposed hybrid method yields superior forecasting performance for HRC returns. The evidence also suggested that in capturing the price dynamics of HRC during the COVID-19 pandemic period, the asymmetric GARCH model with MEMD–LSSVR outperformed not only standard GARCH models but also the EEMD-LSSVR models. The proposed MEMD–LSSVR–GARCH model for steel price forecasting provides a useful decision support tool for steelmakers and consumers to evaluate steel price trends.
This document describes research on using a Long Short-Term Memory (LSTM) neural network model to predict bitcoin prices over the next 5 days. It discusses collecting bitcoin price data from 2015-2021, cleaning the data, and using features like date, price, high, low to train and test the LSTM model. Lag plots show the data has positive correlation at daily intervals. The model is trained on recent data and tested on past data to predict future prices. Root mean square error is calculated between predicted and actual test prices. The model accurately predicts future prices but could be improved by adding more price-influencing features to the training data.
IRJET- Stock Price Prediction using Long Short Term MemoryIRJET Journal
This document proposes using a Long Short Term Memory (LSTM) recurrent neural network for online stock price prediction. It discusses the limitations of existing batch processing methods and other neural networks in capturing the correlated temporal dependencies in stock price data. The document describes preprocessing stock data and training an LSTM model to predict the end-of-day price. It compares the proposed LSTM approach to other methods and evaluates the predictions against actual prices using metrics like root mean squared error.
Bitcoin Price Prediction using Sentiment and Historical PriceIRJET Journal
1. The document presents a study that uses sentiment analysis and historical price data to predict the price movements of bitcoin.
2. It reviews previous studies that have used machine learning models like LSTM, RNN, and ARIMA with either sentiment data or historical price data to predict bitcoin prices. Accuracy between 40-52% was achieved in previous studies.
3. This study collects sentiment data from investing forums from 2017-2020 and cleans the data. It also collects historical bitcoin price data from 2012-2020. It aims to use both sentiment features and historical price indexes as inputs to deep learning models to improve prediction accuracy.
This document presents a generalized algorithm for optimizing demand prediction of short life cycle products using Markov chains. It begins with an introduction to short life cycle products and issues with demand forecasting for products with very low shelf lives between 1-2 days. It then discusses using Markov chains to model demand as a random variable. An algorithm is developed using Markov chain transition probabilities and steady state probabilities to determine optimal demand forecast. The algorithm is implemented on a baked product to determine optimal demand. It is presented as a novel technique that can improve demand forecasting for short life cycle supply chains.
Visualizing and Forecasting Stocks Using Machine LearningIRJET Journal
This document discusses using machine learning techniques like regression and LSTM models to predict stock market returns. It first provides background on the challenges of predicting the stock market due to its unpredictable nature. It then describes obtaining stock price data from Yahoo Finance to use as the dataset. The document outlines using regression analysis to build a relationship between stock prices and time and using LSTM due to its ability to learn from sequence data. It then reviews related work applying machine learning like neural networks and genetic algorithms to optimize stock prediction. The methodology section provides more detail on preprocessing the dataset and using regression and LSTM models to make predictions and compare results.
Predicting Stock Market Prices with Sentiment Analysis and Ensemble Learning ...IRJET Journal
The document describes a study that proposes a hybrid approach for predicting stock market prices using sentiment analysis and ensemble learning techniques. The approach involves collecting stock price and social media data, performing sentiment analysis on the text data, combining the datasets, training various machine learning models, and evaluating the models based on metrics like RMSE and R2 score. The results found that the ensemble XGBoost model outperformed individual models like LSTM and linear regression in predicting stock prices of companies, demonstrating the potential of using sentiment analysis and ensemble learning for stock market prediction.
Forecasting Crude Oil Prices by using Deep Learning Based ModelIRJET Journal
This document discusses using deep learning models to forecast crude oil prices. It proposes a new hybrid model that uses deep learning techniques like LSTM, CNN, and RNNs. The model is trained on West Texas Intermediate crude oil market data and shows improved accuracy in price predictions compared to other methods. The document also reviews several other studies applying machine learning and deep learning approaches to crude oil price and energy market forecasting.
Re-Mining Association Mining Results Through Visualization, Data Envelopment ...ertekg
İndirmek için Bağlantı > https://ertekprojects.com/gurdal-ertek-publications/blog/re-mining-association-mining-results-through-visualization-data-envelopment-analysis-and-decision-trees/
Re-mining is a general framework which suggests the execution of additional data mining steps based on the results of an original data mining process. This study investigates the multi-faceted re-mining of association mining results, develops and presents a practical methodology, and shows the applicability of the developed methodology through real world data. The methodology suggests re-mining using data visualization, data envelopment analysis, and decision trees. Six hypotheses, regarding how re-mining can be carried out on association mining results, are answered in the case study through empirical analysis.
Computational Nano Technology and Simulation Techniques Applied to Study Silv...IRJET Journal
This document discusses computational nanotechnology methods for simulating silver nano dots. It describes three types of nanotechnologies: wet, dry, and computational. Computational nanotechnology uses computer algorithms and simulations to model nanostructures and devices. The document focuses on using software tools like Quantum Dot Lab and molecular dynamics simulations to model the structure, properties, and dynamics of silver quantum dots at the nanoscale. These computational methods allow for faster, more accurate analysis compared to experimental techniques alone. The simulations provide insights into the charged states, light emission, and movement of atoms in silver nano dots over time.
REAL TIME ERROR DETECTION IN METAL ARC WELDING PROCESS USING ARTIFICIAL NEURA...IJCI JOURNAL
Quality assurance in production line demands reliable weld joints. Human made errors is a major cause of
faulty production. Promptly Identifying errors in the weld while welding is in progress will decrease the
post inspection cost spent on the welding process. Electrical parameters generated during welding, could
able to characterize the process efficiently. Parameter values are collected using high speed data
acquisition system. Time series analysis tasks such as filtering, pattern recognition etc. are performed over
the collected data. Filtering removes the unwanted noisy signal components and pattern recognition task
segregate error patterns in the time series based upon similarity, which is performed by Self Organized
mapping clustering algorithm. Welder’s quality is thus compared by detecting and counting number of
error patterns appeared in his parametric time series. Moreover, Self Organized mapping algorithm
provides the database in which patterns are segregated into two classes either desirable or undesirable.
Database thus generated is used to train the classification algorithms, and thereby automating the real time
error detection task. Multi Layer Perceptron and Radial basis function are the two classification
algorithms used, and their performance has been compared based on metrics such as specificity, sensitivity,
accuracy and time required in training.
IJERA (International journal of Engineering Research and Applications) is International online, ... peer reviewed journal. For more detail or submit your article, please visit www.ijera.com
Call for Chapters- Edited Book: Artificial Intelligence Applications and Simu...Christo Ananth
Call for Chapters- Edited Book: Artificial Intelligence Applications and Simulation Tools for High Temperature Materials, IGI Global, USA, ISBN 9781668477502
This document explores using XML and style sheets to generate materials test reports. It compares using HTML/Perl and Microsoft InfoPath to create XML documents based on an existing MatML schema for materials properties data. Both methods were able to produce XML documents from user input data, which were then formatted into reports using XSLT and CSS style sheets. The InfoPath method more easily created the forms interface, while the HTML/Perl system provided more flexibility but required more development time. Overall the XML-based approach was found to have benefits for report generation and data interchange.
Combining Neural Network and Firefly Algorithm to Predict Stock Price in Tehr...Editor IJCATR
In the present research, prediction of stock price index in Tehran stock exchange by using neural
networks and firefly algorithm in chaotic behavior of price index stock exchange are studied. Two data sets
are selected for neural network input. Various breaks of index and macro economic factors are considered
as independent variables. Also, firefly algorithm is used to [redict price index in next week. The results of
research show that combining neural networks and firefly optimization algorithm has better performance
than neural network to predict the price index. In addition, acceptable value of error-sequre means for
network error in test data show that there are chaotic mevements in behaviour of price index.
Re-Mining Association Mining Results through Visualization, Data Envelopment ...Gurdal Ertek
Re-mining is a general framework which suggests the execution of additional data mining steps based on the results of an original data mining process. This study investigates the multi-faceted re-mining of association mining results, develops and presents a practical methodology, and shows the applicability of the developed methodology through real world data. The methodology suggests re-mining using data visualization, data envelopment analysis, and decision trees. Six hypotheses, regarding how re-mining can be carried out on association mining results, are answered in the case study through empirical analysis.
http://research.sabanciuniv.edu.
Non linear analysis and optimization of flywheelIRJET Journal
This document discusses the non-linear finite element analysis of a flywheel made of different materials. It begins with an introduction to flywheels and the motivation for performing non-linear analysis. The flywheel model is created in SolidWorks and meshed. Non-linear static analysis is performed in ANSYS considering step loading and centrifugal forces. Various parameters like deformation, stress, and factor of safety are analyzed and compared for aluminum alloy and cast iron flywheel models. Shape optimization is also performed to reduce the flywheel mass by 20%. Experimental validation of deflection values matches well with FEA results, with error within 3-4%. Aluminum alloy is found to have lower stresses compared to cast iron, making it better
Prediction prices of Basrah light oil using artificial neural networks IJECEIAES
The global economy is assured to be very sensitive to the volatility of the oil market. The beneficial of oil price collapse are both consumers and developed countries. Iraq's economy is a one-sided economy that completely depends on oil revenue to charge economic activity. Hence, the current decline in oil prices will produce serious concerns. Some factors stopped most investment projects, rationalize the recurrent outflow, and decreasethe development of the economic activity. The predicate oil prices are considered among the most complex studies because of the different dynamic variables that affect the strategic goods. The subject of forecasting has been extremely developing during recent years and some modern methods have been appeared in this regard, for example, Artificial Neural Networks. In this study, an artificial neural network (RFFNN) is adopted to extractthe complex relationships among divergent parameters that have the abilities to predict oil prices serving as an inputs to the network data collected in this research represent monthly time series data are Oil prices series in (US dollars) over a period of 11 years (2008–2018) in Iraq.
Efficient Mining of Association Rules in Oscillatory-based DataWaqas Tariq
Association rules are one of the most researched areas of data mining. Finding frequent patterns is an important step in association rules mining which is very time consuming and costly. In this paper, an effective method for mining association rules in the data with the oscillatory value (up, down) is presented, such as the stock price variation in stock exchange, which, just a few numbers of the counts of itemsets are searched from the database, and the counts of the rest of itemsets are computed using the relationships that exist between these types of data. Also, the strategy of pruning is used to decrease the searching space and increase the rate of the mining process. Thus, there is no need to investigate the entire frequent patterns from the database. This takes less time to find frequent patterns. By executing the MR-Miner (an acronym for “Math Rules-Miner”) algorithm, its performance on the real stock data is analyzed and shown. Our experiments show that the MR-Miner algorithm can find association rules very efficiently in the data based on Oscillatory value type.
Enhancenig OLSR routing protocol using K-means clustering in MANETs IJECEIAES
The design of robust routing protocol schemes for MANETs is quite complex, due to the characteristics and structural constraints of this network. A numerous variety of protocol schemes have been proposed in literature. Most of them are based on traditional method of routing, which doesn’t guarantee basic levels of Qos, when the network becomes larger, denser and dynamic. To solve this problem we use one of the most popular methods named clustering. In this work we try to improve the Qos in MANETs. We propose an algorithm of clustering based in the new mobility metric and K-Means method to distribute the nodes into several clusters; it is implemented to standard OLSR protocol giving birth a new protocol named OLSR Kmeans-SDE. The simulations showed that the results obtained by OLSR Kmeans-SDE exceed those obtained by standard OLSR Kmeans and OLSR Kmed+ in terms of, traffic Control, delay and packet delivery ratio.
IRJET- Data Visualization and Stock Market and PredictionIRJET Journal
This document discusses using machine learning techniques like LSTM neural networks to predict stock market prices. It summarizes the following:
1) Traditional stock prediction methods like fundamental and statistical analysis have limitations, while machine learning approaches like LSTM networks can better capture long-term temporal dependencies in stock price data.
2) The document outlines collecting stock price history, preprocessing the data, and using an LSTM model in Keras to predict future stock prices based on historical closing prices and trading volumes.
3) The model was able to accurately predict stock prices on unseen Facebook data, demonstrating the robustness of the machine learning approach over traditional methods for this challenging problem.
International Journal of Engineering Research and Applications (IJERA) is a team of researchers not publication services or private publications running the journals for monetary benefits, we are association of scientists and academia who focus only on supporting authors who want to publish their work. The articles published in our journal can be accessed online, all the articles will be archived for real time access.
Our journal system primarily aims to bring out the research talent and the works done by sciaentists, academia, engineers, practitioners, scholars, post graduate students of engineering and science. This journal aims to cover the scientific research in a broader sense and not publishing a niche area of research facilitating researchers from various verticals to publish their papers. It is also aimed to provide a platform for the researchers to publish in a shorter of time, enabling them to continue further All articles published are freely available to scientific researchers in the Government agencies,educators and the general public. We are taking serious efforts to promote our journal across the globe in various ways, we are sure that our journal will act as a scientific platform for all researchers to publish their works online.
Enhancement of Single Moving Average Time Series Model Using Rough k-Means fo...IJERA Editor
This document proposes combining rough k-means clustering with a single moving average time series model to improve network traffic prediction. The document first discusses related work on network traffic prediction using various time series models. It then describes using a single moving average model to initially predict network packet loads, and enhancing this prediction by incorporating clusters identified through rough k-means analysis of the network data. The proposed integrated model is evaluated on real network traffic data and shown to improve prediction accuracy over the conventional single moving average model alone.
The document describes the development of a Bayesian neural network model for predicting ferrite content in stainless steel welds. The model was developed using a database of 1020 datasets on chemical compositions and measured ferrite numbers. It predicts ferrite content more accurately than existing methods like constitution diagrams and other neural network models, with a root mean square error of less than 2. The model reveals the influence of individual alloying elements on ferrite content in stainless steel welds.
This paper applies the Vector Autoregressive (VAR) technique to annual data from 1980 to 2013 to provide empirical evidence on the long-run relationship between export trade and economic growth in Malawi. The export trade in this study is disaggregated into services and goods exports. Thus, the paper estimated two models. The first model deals with the relationship between export of services and growth, and the other one determines the relationship between goods export and growth. While the paper finds no evidence for long-run relationship between export of services and goods on economic growth, the empirical results suggest existence of a short-run nexus between export of goods and economic growth in Malawi. The Granger causality test results have also confirmed existence of a unidirectional causality from goods exports to economic growth and another unidirectional causality from goods exports to service exports.
This document summarizes a study that examines the nonlinear relationship between real exchange rates and bilateral trade balance between South Korea and the United States from 1985 to 2013. The study finds:
1) There is a cointegrating relationship between real exchange rates and bilateral trade balance in both linear and nonlinear models, suggesting a long-run equilibrium relationship.
2) South Korea-U.S. bilateral trade balance exhibited no J-curve effect when the South Korean won depreciated against the U.S. dollar.
3) A performance evaluation found the nonlinear model was better than the linear model at predicting trade balance, indicating depreciation has a limited effect and sharp currency depreciation can hurt a country's
More Related Content
Similar to Forecasting Iron Price by Hybrid Intelligent System
Visualizing and Forecasting Stocks Using Machine LearningIRJET Journal
This document discusses using machine learning techniques like regression and LSTM models to predict stock market returns. It first provides background on the challenges of predicting the stock market due to its unpredictable nature. It then describes obtaining stock price data from Yahoo Finance to use as the dataset. The document outlines using regression analysis to build a relationship between stock prices and time and using LSTM due to its ability to learn from sequence data. It then reviews related work applying machine learning like neural networks and genetic algorithms to optimize stock prediction. The methodology section provides more detail on preprocessing the dataset and using regression and LSTM models to make predictions and compare results.
Predicting Stock Market Prices with Sentiment Analysis and Ensemble Learning ...IRJET Journal
The document describes a study that proposes a hybrid approach for predicting stock market prices using sentiment analysis and ensemble learning techniques. The approach involves collecting stock price and social media data, performing sentiment analysis on the text data, combining the datasets, training various machine learning models, and evaluating the models based on metrics like RMSE and R2 score. The results found that the ensemble XGBoost model outperformed individual models like LSTM and linear regression in predicting stock prices of companies, demonstrating the potential of using sentiment analysis and ensemble learning for stock market prediction.
Forecasting Crude Oil Prices by using Deep Learning Based ModelIRJET Journal
This document discusses using deep learning models to forecast crude oil prices. It proposes a new hybrid model that uses deep learning techniques like LSTM, CNN, and RNNs. The model is trained on West Texas Intermediate crude oil market data and shows improved accuracy in price predictions compared to other methods. The document also reviews several other studies applying machine learning and deep learning approaches to crude oil price and energy market forecasting.
Re-Mining Association Mining Results Through Visualization, Data Envelopment ...ertekg
İndirmek için Bağlantı > https://ertekprojects.com/gurdal-ertek-publications/blog/re-mining-association-mining-results-through-visualization-data-envelopment-analysis-and-decision-trees/
Re-mining is a general framework which suggests the execution of additional data mining steps based on the results of an original data mining process. This study investigates the multi-faceted re-mining of association mining results, develops and presents a practical methodology, and shows the applicability of the developed methodology through real world data. The methodology suggests re-mining using data visualization, data envelopment analysis, and decision trees. Six hypotheses, regarding how re-mining can be carried out on association mining results, are answered in the case study through empirical analysis.
Computational Nano Technology and Simulation Techniques Applied to Study Silv...IRJET Journal
This document discusses computational nanotechnology methods for simulating silver nano dots. It describes three types of nanotechnologies: wet, dry, and computational. Computational nanotechnology uses computer algorithms and simulations to model nanostructures and devices. The document focuses on using software tools like Quantum Dot Lab and molecular dynamics simulations to model the structure, properties, and dynamics of silver quantum dots at the nanoscale. These computational methods allow for faster, more accurate analysis compared to experimental techniques alone. The simulations provide insights into the charged states, light emission, and movement of atoms in silver nano dots over time.
REAL TIME ERROR DETECTION IN METAL ARC WELDING PROCESS USING ARTIFICIAL NEURA...IJCI JOURNAL
Quality assurance in production line demands reliable weld joints. Human made errors is a major cause of
faulty production. Promptly Identifying errors in the weld while welding is in progress will decrease the
post inspection cost spent on the welding process. Electrical parameters generated during welding, could
able to characterize the process efficiently. Parameter values are collected using high speed data
acquisition system. Time series analysis tasks such as filtering, pattern recognition etc. are performed over
the collected data. Filtering removes the unwanted noisy signal components and pattern recognition task
segregate error patterns in the time series based upon similarity, which is performed by Self Organized
mapping clustering algorithm. Welder’s quality is thus compared by detecting and counting number of
error patterns appeared in his parametric time series. Moreover, Self Organized mapping algorithm
provides the database in which patterns are segregated into two classes either desirable or undesirable.
Database thus generated is used to train the classification algorithms, and thereby automating the real time
error detection task. Multi Layer Perceptron and Radial basis function are the two classification
algorithms used, and their performance has been compared based on metrics such as specificity, sensitivity,
accuracy and time required in training.
IJERA (International journal of Engineering Research and Applications) is International online, ... peer reviewed journal. For more detail or submit your article, please visit www.ijera.com
Call for Chapters- Edited Book: Artificial Intelligence Applications and Simu...Christo Ananth
Call for Chapters- Edited Book: Artificial Intelligence Applications and Simulation Tools for High Temperature Materials, IGI Global, USA, ISBN 9781668477502
This document explores using XML and style sheets to generate materials test reports. It compares using HTML/Perl and Microsoft InfoPath to create XML documents based on an existing MatML schema for materials properties data. Both methods were able to produce XML documents from user input data, which were then formatted into reports using XSLT and CSS style sheets. The InfoPath method more easily created the forms interface, while the HTML/Perl system provided more flexibility but required more development time. Overall the XML-based approach was found to have benefits for report generation and data interchange.
Combining Neural Network and Firefly Algorithm to Predict Stock Price in Tehr...Editor IJCATR
In the present research, prediction of stock price index in Tehran stock exchange by using neural
networks and firefly algorithm in chaotic behavior of price index stock exchange are studied. Two data sets
are selected for neural network input. Various breaks of index and macro economic factors are considered
as independent variables. Also, firefly algorithm is used to [redict price index in next week. The results of
research show that combining neural networks and firefly optimization algorithm has better performance
than neural network to predict the price index. In addition, acceptable value of error-sequre means for
network error in test data show that there are chaotic mevements in behaviour of price index.
Re-Mining Association Mining Results through Visualization, Data Envelopment ...Gurdal Ertek
Re-mining is a general framework which suggests the execution of additional data mining steps based on the results of an original data mining process. This study investigates the multi-faceted re-mining of association mining results, develops and presents a practical methodology, and shows the applicability of the developed methodology through real world data. The methodology suggests re-mining using data visualization, data envelopment analysis, and decision trees. Six hypotheses, regarding how re-mining can be carried out on association mining results, are answered in the case study through empirical analysis.
http://research.sabanciuniv.edu.
Non linear analysis and optimization of flywheelIRJET Journal
This document discusses the non-linear finite element analysis of a flywheel made of different materials. It begins with an introduction to flywheels and the motivation for performing non-linear analysis. The flywheel model is created in SolidWorks and meshed. Non-linear static analysis is performed in ANSYS considering step loading and centrifugal forces. Various parameters like deformation, stress, and factor of safety are analyzed and compared for aluminum alloy and cast iron flywheel models. Shape optimization is also performed to reduce the flywheel mass by 20%. Experimental validation of deflection values matches well with FEA results, with error within 3-4%. Aluminum alloy is found to have lower stresses compared to cast iron, making it better
Prediction prices of Basrah light oil using artificial neural networks IJECEIAES
The global economy is assured to be very sensitive to the volatility of the oil market. The beneficial of oil price collapse are both consumers and developed countries. Iraq's economy is a one-sided economy that completely depends on oil revenue to charge economic activity. Hence, the current decline in oil prices will produce serious concerns. Some factors stopped most investment projects, rationalize the recurrent outflow, and decreasethe development of the economic activity. The predicate oil prices are considered among the most complex studies because of the different dynamic variables that affect the strategic goods. The subject of forecasting has been extremely developing during recent years and some modern methods have been appeared in this regard, for example, Artificial Neural Networks. In this study, an artificial neural network (RFFNN) is adopted to extractthe complex relationships among divergent parameters that have the abilities to predict oil prices serving as an inputs to the network data collected in this research represent monthly time series data are Oil prices series in (US dollars) over a period of 11 years (2008–2018) in Iraq.
Efficient Mining of Association Rules in Oscillatory-based DataWaqas Tariq
Association rules are one of the most researched areas of data mining. Finding frequent patterns is an important step in association rules mining which is very time consuming and costly. In this paper, an effective method for mining association rules in the data with the oscillatory value (up, down) is presented, such as the stock price variation in stock exchange, which, just a few numbers of the counts of itemsets are searched from the database, and the counts of the rest of itemsets are computed using the relationships that exist between these types of data. Also, the strategy of pruning is used to decrease the searching space and increase the rate of the mining process. Thus, there is no need to investigate the entire frequent patterns from the database. This takes less time to find frequent patterns. By executing the MR-Miner (an acronym for “Math Rules-Miner”) algorithm, its performance on the real stock data is analyzed and shown. Our experiments show that the MR-Miner algorithm can find association rules very efficiently in the data based on Oscillatory value type.
Enhancenig OLSR routing protocol using K-means clustering in MANETs IJECEIAES
The design of robust routing protocol schemes for MANETs is quite complex, due to the characteristics and structural constraints of this network. A numerous variety of protocol schemes have been proposed in literature. Most of them are based on traditional method of routing, which doesn’t guarantee basic levels of Qos, when the network becomes larger, denser and dynamic. To solve this problem we use one of the most popular methods named clustering. In this work we try to improve the Qos in MANETs. We propose an algorithm of clustering based in the new mobility metric and K-Means method to distribute the nodes into several clusters; it is implemented to standard OLSR protocol giving birth a new protocol named OLSR Kmeans-SDE. The simulations showed that the results obtained by OLSR Kmeans-SDE exceed those obtained by standard OLSR Kmeans and OLSR Kmed+ in terms of, traffic Control, delay and packet delivery ratio.
IRJET- Data Visualization and Stock Market and PredictionIRJET Journal
This document discusses using machine learning techniques like LSTM neural networks to predict stock market prices. It summarizes the following:
1) Traditional stock prediction methods like fundamental and statistical analysis have limitations, while machine learning approaches like LSTM networks can better capture long-term temporal dependencies in stock price data.
2) The document outlines collecting stock price history, preprocessing the data, and using an LSTM model in Keras to predict future stock prices based on historical closing prices and trading volumes.
3) The model was able to accurately predict stock prices on unseen Facebook data, demonstrating the robustness of the machine learning approach over traditional methods for this challenging problem.
International Journal of Engineering Research and Applications (IJERA) is a team of researchers not publication services or private publications running the journals for monetary benefits, we are association of scientists and academia who focus only on supporting authors who want to publish their work. The articles published in our journal can be accessed online, all the articles will be archived for real time access.
Our journal system primarily aims to bring out the research talent and the works done by sciaentists, academia, engineers, practitioners, scholars, post graduate students of engineering and science. This journal aims to cover the scientific research in a broader sense and not publishing a niche area of research facilitating researchers from various verticals to publish their papers. It is also aimed to provide a platform for the researchers to publish in a shorter of time, enabling them to continue further All articles published are freely available to scientific researchers in the Government agencies,educators and the general public. We are taking serious efforts to promote our journal across the globe in various ways, we are sure that our journal will act as a scientific platform for all researchers to publish their works online.
Enhancement of Single Moving Average Time Series Model Using Rough k-Means fo...IJERA Editor
This document proposes combining rough k-means clustering with a single moving average time series model to improve network traffic prediction. The document first discusses related work on network traffic prediction using various time series models. It then describes using a single moving average model to initially predict network packet loads, and enhancing this prediction by incorporating clusters identified through rough k-means analysis of the network data. The proposed integrated model is evaluated on real network traffic data and shown to improve prediction accuracy over the conventional single moving average model alone.
The document describes the development of a Bayesian neural network model for predicting ferrite content in stainless steel welds. The model was developed using a database of 1020 datasets on chemical compositions and measured ferrite numbers. It predicts ferrite content more accurately than existing methods like constitution diagrams and other neural network models, with a root mean square error of less than 2. The model reveals the influence of individual alloying elements on ferrite content in stainless steel welds.
Similar to Forecasting Iron Price by Hybrid Intelligent System (20)
This paper applies the Vector Autoregressive (VAR) technique to annual data from 1980 to 2013 to provide empirical evidence on the long-run relationship between export trade and economic growth in Malawi. The export trade in this study is disaggregated into services and goods exports. Thus, the paper estimated two models. The first model deals with the relationship between export of services and growth, and the other one determines the relationship between goods export and growth. While the paper finds no evidence for long-run relationship between export of services and goods on economic growth, the empirical results suggest existence of a short-run nexus between export of goods and economic growth in Malawi. The Granger causality test results have also confirmed existence of a unidirectional causality from goods exports to economic growth and another unidirectional causality from goods exports to service exports.
This document summarizes a study that examines the nonlinear relationship between real exchange rates and bilateral trade balance between South Korea and the United States from 1985 to 2013. The study finds:
1) There is a cointegrating relationship between real exchange rates and bilateral trade balance in both linear and nonlinear models, suggesting a long-run equilibrium relationship.
2) South Korea-U.S. bilateral trade balance exhibited no J-curve effect when the South Korean won depreciated against the U.S. dollar.
3) A performance evaluation found the nonlinear model was better than the linear model at predicting trade balance, indicating depreciation has a limited effect and sharp currency depreciation can hurt a country's
Mobile banking has grown in Nigeria in recent years as banks offer SMS banking, funds transfers, bill payments, and other services via mobile phones. However, the paper identifies several challenges to the operation of mobile banking in Nigeria, including insecure environments, interoperability issues between different mobile devices, unstable power and network infrastructure, and low financial literacy among many Nigerians. The paper proposes that Nigerian banks adopt a "non-bank led model" of mobile banking to make services more transformational and accessible to the unbanked, rather than just adding a new channel for existing customers. Future research is needed to address challenges like security, scalability, and expanding financial inclusion through mobile banking in Nigeria.
Abstract: The paper examines the impact of public sectoral expenditure on economic growth in Nigeria for the period 1981-2013. It was observed that the growth of government expenditure has not fully felt by the economy. The econometric methodology employed is the ARDL model and results show that while the impact of government expenditure on administration and debt servicing were positive on economic growth in the long and short run, expenditure on economic and social sectors has negative impact. We argue that this may not be unconnected with the high level of corruption prevalent in the public sector where funds that are meant for provision or maintenance of social-economic activities like agriculture, roads, transportations, schools and hospitals are diverted for personal use. The CUSUM and CUSUMSQ test show the model is stable as neither of them cross the 5% boundary. The paper recommended that government should increase expenditure to the social and economic sectors while debts or debt servicing should be reduced. Also, corruption so prevalent in the public sector must be minimized if cannot be eradicated.
This document summarizes a research article that investigates the causal relationship between road transport infrastructure development, economic growth, and poverty level in Nigeria from 1980 to 2012. It finds that road transport infrastructure development and economic growth cause poverty reduction in the long run, but that poverty reduction and economic growth can influence each other in the short run. The document reviews theories and prior empirical research on the relationships between transportation infrastructure, economic growth, and poverty reduction. It finds mixed results from other studies on the direction of causality. The research aims to help inform transport investment decisions in Nigeria by providing more clarity on the links between these important variables.
Abstract: Marketing of crops in Tanzania has been undergoing change. Direct sales from farmers to traders
and delivery to the Primary Cooperative Societies (PCS) were in practice at different points of time. Since 2007,
the warehouse receipt system was introduced in Tanzania. The warehouse operators accept the deposit of crops
in the warehouses and provide a receipt to the farmers through PCS and the farmers receive a part of the
payments through bank financing based on these receipts. This study was conducted to assess whether
Warehouse Receipt System has made any contribution in improving smallholder farmers ‘access to financial
services. The study used cross sectional design where 100 smallholder farmers in Singida Rural district in
Singida region were covered. Quantitative and qualitative techniques were used to analyze the data. The results
showed that the motives that were used to influence smallholder farmers to join WRS included price, access to
credit and access to market, although, most of the farmers participate into WRS to access credit for agricultural
activities. Moreover, level of farming technologies adopted found to have increased significantly after joining
the WRS. Based on these findings, it is recommended to increase sensitization efforts among the smallholder
farmers in order to enable the larger spectrum of the community members becoming aware of the WRS practice.
Also, policy maker should deliberately intervene to strengthen the capacity of WRS.
Abstract: The theoretical relationship of the long-run equilibrium between real exchange rates and interest rate differentials is essentially derived from the Purchasing Power Parity (PPP) and the uncovered interest parity. However, empirical evidence on this long-run relationship has rather been inconclusive. While several authors are able to establish the long-run relationship between real exchange rates and interest rate differentials other could not found this relationship. The reason for lack of relationship in some of the studies is as a result of omitted variables (Meese and Rogoff, 1988). Therefore, attempt is made in this study to evaluate this relationship between real exchange rate and interest rate differential for the case of Nigeria by controlling for foreign exchange reserves. The paper uses monthly data for the period 1993:1-2012:12 and applies Autoregressive Distributed Lags (ARDL) model. The estimates suggest the existence of long-run relationship between real exchange rate, interest rate differential and foreign exchange reserves. In the long run, the exchange rate coefficient has a positive effect on the foreign reserves. However, the effect of interest rate differential is negative and statistically significant. On the short run dynamics, the finding indicates a non-monotonic relationship between real exchange rate, interest rate differential and foreign exchange reserves. The out-of-sample forecast indicates a better forecast using ARMA model as all Theil coefficients are close zero for all the horizons used in the model.
Abstract: Financial is the result of an organized process that is commonly referred to as money management
or financial planning and control. Financial planning is the process of managing money to achieve economic
satisfaction. This planning process allows for controlling financial situation. Every organisation has a unique
financial position, and any financial activity therefore must also be carefully planned to meet specific needs and
goals. A comprehensive financial plan can enhance the quality of organisational life and increase future needs
and resources. The specific advantages of personal financial planning include Increased effectiveness in
obtaining, using, and protecting your financial resources throughout your lifetime The objective of the present
study was to study the financial planning and to analyze the financial control. The tools applied for this study
are Additional Fund Needed, Breakeven Analysis, Index analysis etc, findings reveals that the additional fund
needed was increased during the study period. The company has to reduce the additional fund needed, dividend
payout ratio, plant capacity and in order to increase the retained earnings and profit margin. For most
companies, planning and controlling is a necessary but painful process. Unfortunately, it is often a prolonged
exercise that takes so long that the starting assumptions are virtually meaningless by the time the process is
complete. Add to that the rapidly increasing need for reporting and controls, both from investors and to meet
regulatory requirements. As per the above observations and analysis the company will have to improve its
financial planning and control for the upcoming years.
Abstract: In this paper, we examine the existence of the size effect in the Tunisian stock exchange (TSE) over
the period January 2008 to December 2013 and we test the relationship between size and January effects. The
findings reveal that there is a size effect in the TSE. However, we report that size and January effects are separate
anomalies. More specifically, we document that average returns are found to increase with decreases in size.
However, we find that small firms don’t significantly outperform large firms in January.
More from International Journal of Economics and Financial Research (9)
Independent Study - College of Wooster Research (2023-2024) FDI, Culture, Glo...AntoniaOwensDetwiler
"Does Foreign Direct Investment Negatively Affect Preservation of Culture in the Global South? Case Studies in Thailand and Cambodia."
Do elements of globalization, such as Foreign Direct Investment (FDI), negatively affect the ability of countries in the Global South to preserve their culture? This research aims to answer this question by employing a cross-sectional comparative case study analysis utilizing methods of difference. Thailand and Cambodia are compared as they are in the same region and have a similar culture. The metric of difference between Thailand and Cambodia is their ability to preserve their culture. This ability is operationalized by their respective attitudes towards FDI; Thailand imposes stringent regulations and limitations on FDI while Cambodia does not hesitate to accept most FDI and imposes fewer limitations. The evidence from this study suggests that FDI from globally influential countries with high gross domestic products (GDPs) (e.g. China, U.S.) challenges the ability of countries with lower GDPs (e.g. Cambodia) to protect their culture. Furthermore, the ability, or lack thereof, of the receiving countries to protect their culture is amplified by the existence and implementation of restrictive FDI policies imposed by their governments.
My study abroad in Bali, Indonesia, inspired this research topic as I noticed how globalization is changing the culture of its people. I learned their language and way of life which helped me understand the beauty and importance of cultural preservation. I believe we could all benefit from learning new perspectives as they could help us ideate solutions to contemporary issues and empathize with others.
The Rise of Generative AI in Finance: Reshaping the Industry with Synthetic DataChampak Jhagmag
In this presentation, we will explore the rise of generative AI in finance and its potential to reshape the industry. We will discuss how generative AI can be used to develop new products, combat fraud, and revolutionize risk management. Finally, we will address some of the ethical considerations and challenges associated with this powerful technology.
Seminar: Gender Board Diversity through Ownership NetworksGRAPE
Seminar on gender diversity spillovers through ownership networks at FAME|GRAPE. Presenting novel research. Studies in economics and management using econometrics methods.
5 Tips for Creating Standard Financial ReportsEasyReports
Well-crafted financial reports serve as vital tools for decision-making and transparency within an organization. By following the undermentioned tips, you can create standardized financial reports that effectively communicate your company's financial health and performance to stakeholders.
Vicinity Jobs’ data includes more than three million 2023 OJPs and thousands of skills. Most skills appear in less than 0.02% of job postings, so most postings rely on a small subset of commonly used terms, like teamwork.
Laura Adkins-Hackett, Economist, LMIC, and Sukriti Trehan, Data Scientist, LMIC, presented their research exploring trends in the skills listed in OJPs to develop a deeper understanding of in-demand skills. This research project uses pointwise mutual information and other methods to extract more information about common skills from the relationships between skills, occupations and regions.
OJP data from firms like Vicinity Jobs have emerged as a complement to traditional sources of labour demand data, such as the Job Vacancy and Wages Survey (JVWS). Ibrahim Abuallail, PhD Candidate, University of Ottawa, presented research relating to bias in OJPs and a proposed approach to effectively adjust OJP data to complement existing official data (such as from the JVWS) and improve the measurement of labour demand.
1. Elemental Economics - Introduction to mining.pdfNeal Brewster
After this first you should: Understand the nature of mining; have an awareness of the industry’s boundaries, corporate structure and size; appreciation the complex motivations and objectives of the industries’ various participants; know how mineral reserves are defined and estimated, and how they evolve over time.
Financial Assets: Debit vs Equity Securities.pptxWrito-Finance
financial assets represent claim for future benefit or cash. Financial assets are formed by establishing contracts between participants. These financial assets are used for collection of huge amounts of money for business purposes.
Two major Types: Debt Securities and Equity Securities.
Debt Securities are Also known as fixed-income securities or instruments. The type of assets is formed by establishing contracts between investor and issuer of the asset.
• The first type of Debit securities is BONDS. Bonds are issued by corporations and government (both local and national government).
• The second important type of Debit security is NOTES. Apart from similarities associated with notes and bonds, notes have shorter term maturity.
• The 3rd important type of Debit security is TRESURY BILLS. These securities have short-term ranging from three months, six months, and one year. Issuer of such securities are governments.
• Above discussed debit securities are mostly issued by governments and corporations. CERTIFICATE OF DEPOSITS CDs are issued by Banks and Financial Institutions. Risk factor associated with CDs gets reduced when issued by reputable institutions or Banks.
Following are the risk attached with debt securities: Credit risk, interest rate risk and currency risk
There are no fixed maturity dates in such securities, and asset’s value is determined by company’s performance. There are two major types of equity securities: common stock and preferred stock.
Common Stock: These are simple equity securities and bear no complexities which the preferred stock bears. Holders of such securities or instrument have the voting rights when it comes to select the company’s board of director or the business decisions to be made.
Preferred Stock: Preferred stocks are sometime referred to as hybrid securities, because it contains elements of both debit security and equity security. Preferred stock confers ownership rights to security holder that is why it is equity instrument
<a href="https://www.writofinance.com/equity-securities-features-types-risk/" >Equity securities </a> as a whole is used for capital funding for companies. Companies have multiple expenses to cover. Potential growth of company is required in competitive market. So, these securities are used for capital generation, and then uses it for company’s growth.
Concluding remarks
Both are employed in business. Businesses are often established through debit securities, then what is the need for equity securities. Companies have to cover multiple expenses and expansion of business. They can also use equity instruments for repayment of debits. So, there are multiple uses for securities. As an investor, you need tools for analysis. Investment decisions are made by carefully analyzing the market. For better analysis of the stock market, investors often employ financial analysis of companies.
Solution Manual For Financial Accounting, 8th Canadian Edition 2024, by Libby...Donc Test
Solution Manual For Financial Accounting, 8th Canadian Edition 2024, by Libby, Hodge, Verified Chapters 1 - 13, Complete Newest Version Solution Manual For Financial Accounting, 8th Canadian Edition by Libby, Hodge, Verified Chapters 1 - 13, Complete Newest Version Solution Manual For Financial Accounting 8th Canadian Edition Pdf Chapters Download Stuvia Solution Manual For Financial Accounting 8th Canadian Edition Ebook Download Stuvia Solution Manual For Financial Accounting 8th Canadian Edition Pdf Solution Manual For Financial Accounting 8th Canadian Edition Pdf Download Stuvia Financial Accounting 8th Canadian Edition Pdf Chapters Download Stuvia Financial Accounting 8th Canadian Edition Ebook Download Stuvia Financial Accounting 8th Canadian Edition Pdf Financial Accounting 8th Canadian Edition Pdf Download Stuvia
"Does Foreign Direct Investment Negatively Affect Preservation of Culture in the Global South? Case Studies in Thailand and Cambodia."
Do elements of globalization, such as Foreign Direct Investment (FDI), negatively affect the ability of countries in the Global South to preserve their culture? This research aims to answer this question by employing a cross-sectional comparative case study analysis utilizing methods of difference. Thailand and Cambodia are compared as they are in the same region and have a similar culture. The metric of difference between Thailand and Cambodia is their ability to preserve their culture. This ability is operationalized by their respective attitudes towards FDI; Thailand imposes stringent regulations and limitations on FDI while Cambodia does not hesitate to accept most FDI and imposes fewer limitations. The evidence from this study suggests that FDI from globally influential countries with high gross domestic products (GDPs) (e.g. China, U.S.) challenges the ability of countries with lower GDPs (e.g. Cambodia) to protect their culture. Furthermore, the ability, or lack thereof, of the receiving countries to protect their culture is amplified by the existence and implementation of restrictive FDI policies imposed by their governments.
My study abroad in Bali, Indonesia, inspired this research topic as I noticed how globalization is changing the culture of its people. I learned their language and way of life which helped me understand the beauty and importance of cultural preservation. I believe we could all benefit from learning new perspectives as they could help us ideate solutions to contemporary issues and empathize with others.
Forecasting Iron Price by Hybrid Intelligent System
1. International Journal of Economics
and Financial Research
ISSN: 2411-9407
Vol. 1, No. 1, pp: 6-12, 2015
URL: http://arpgweb.com/?ic=journal&journal=5&info=aims
6
Academic Research Publishing Group
Forecasting Iron Price by Hybrid Intelligent System
Vida Varahrami Assistant Professor of University of Shahid Beheshti, Iran
Contents
1. Introduction................................................................................................................................6
2 .The Hybrid Intelligent System for Iron Price Forecasting ....................................................7
2.1. Web-based Text Mining (WTM) Module.............................................................................................. 7
2.2. Rule-based Expert System (RES) .......................................................................................................... 8
2.3. GMDH Neural Networks....................................................................................................................... 8
2.4. Bases and Bases Management Module................................................................................................ 10
3. Empirical Results.....................................................................................................................10
3.1. Data Description .................................................................................................................................. 10
3.2. A Simulation Study.............................................................................................................................. 11
4. Conclusions...............................................................................................................................11
References.....................................................................................................................................12
Bibliography.................................................................................................................................12
1. Introduction
In Iran, iron is used in manufacture and housing and it's price is so important, because rises in price of iron can
cause to increase house price in Iran.
Iron price is formed by demand and supply forces but influenced by some factors such as iron products
inventory levels, political situation and stock markets activities. So the use of iron price as an economic indicator
drew the attention of many economists. Neural networks, the genetic algorithm and their integration are used for
engineering decision systems, techniques. These systems are used in economics.
Cheng and Titterington (1994) revealed a new neural networks. They showed that in comparison with statistical
techniques neural networks provide a higher degree of robustness. Kuo and Reitsch (1995) revealed that neural
networks provide meaningful predictions, when independent variables are missing. Therefore neural networks
tended view regression analysis in independent variables at presence of obscurity. Then well-trained network is
expected to provide robust predictions. Wong and Yakup (1998) surveyed applications of neural network in finance
and business.
Sarfaraz and Afsar (2005) have done another paper by neuro-fuzzy networks for gold price forecasting in Iran.
Gencay (1996) used technical analysis rules as inputs for neural networks, and nonlinear models with powerful
pattern recognition properties for foreign exchange markets. Gencay (1998a) and Gencay (1999) and Gencay and
Stengos (1998) for both foreign exchange rates revealed simple technical rules improved results of forecast for
current returns.
In this paper a moving average daily Iron price from 2009 to 2013 is used to forecast the iron price and a
GMDH neural networks model, using WTM and RES techniques are used for iron price forecasting. This paper
showed that the hybrid intelligent framework improves the iron price forecasting.
Abstract: Novel hybrid intelligent framework is introduces by integration of GMDH neural networks with Web-
based Text Mining (WTM) and GA and Rule-based Exert System (RES) in this paper for forecast iron price. Our
research reveals that by employing hybrid intelligent framework for iron price forecasting, there is better
forecasting results respect to the GMDH neural networks. Therefore significance of this study is to survey a hybrid
intelligent framework for iron price forecasting.
Keywords: Iron price forecasting; Group Method of Data Handling (GMDH) neural networks; Hybrid Intelligent System;
Rule–based Expert System (RES); Web-based Text Mining (WTM).
2. International Journal of Economics and Financial Research, 2015, 1(1): 6-12
7
In this paper, in section 2 a general discussion of WTM, RES and GMDH neural networks modeling is
introduced. Empirical results and concluding reviews are presented and in Section 3 and Section 4.
2. The Hybrid Intelligent System for Iron Price Forecasting
In this paper we employed a hybrid intelligent system that can forecast iron price in the volatile metal market.
Hybrid intelligent system consists of GMDH based time series forecasting module, RES module, bases and bases
management module and WTM module.
2.1. Web-based Text Mining (WTM) Module1
The iron market is an unstable market with high volatility, and iron prices are often affected by many related
factors. These related factors must be taken in to consideration to improve forecasting accuracy. Therefore we should
collect related information from the Internet and analyze its effects on the iron price. However, to collect the related
knowledge from Internet is too hard and time waste. But WTM is one of the most effective techniques for collecting
this information. (Rajman and Besanon, 1998).
The main goal of the WTM module, in this study, is collected related information affecting iron price variability
from Internet and to provide useful information for the RES forecasting module. The main process of the WTM is
presented in Figure1.
As Figure 1, WTM process can be divided into three phases:
1) Feature Extraction Phase:
The Internet contains an enormous and widely distributed information base and the amount of information
increases. In the information base, some conditions can be obtained by using a search engine. However, the collected
text sets are mainly represented by web pages.
Figure-1.The main processes of a WTM module
2) Structure Analyzing Phase:
Text abstracts can be generated using a text abstract builder based on the results of text structure analyzer. Web
texts contain both pure texts and hyperlinks which reflect relationships in different web pages. Therefore it is
necessary to analyze the text structure. We can judge relationships in different documents by analyzing linkage of
web texts. Finding new knowledge is so important. Therefore we can obtain similar and interconnected material in
different web texts, thus efficiency of information retrieval is increased.
1
Varahrami (2014).
Internet
Word/phase division processing
Feature extraction processing
Phase 1 Feature extraction
phase
Text structure
analyzer
Text abstract builder
Phase 2
Structure
analyzing phase
Text categorization Text clustering
Phase 3
Text classification
phase
3. International Journal of Economics and Financial Research, 2015, 1(1): 6-12
8
3) Text Classification Phase Create:
In data mining, Classification is one of the most important tasks. Main goal of classification is to make retrieval
or query speed faster and make the retrieval more efficient and more precise than before. (Wang et al., 2004)
2.2. Rule-based Expert System (RES)2
In this paper KB is represented by all types of rules from knowledge engineers. The main work of an RES
module is collected and extracted rules or knowledge category from the KB. Our expert system module is used to
extract some rules to judge variability in the iron price by summarizing relationships between iron price fluctuation
and irregular key factors affecting iron price volatility. We use from useful price volatility mechanism to predict iron
price movements; one has to first observe historical price patterns that occur frequently in the iron market.
In this paper, the relationships between the iron price variability and the factors affecting iron price are examined.
(Bauer and Liepins, 1992)
If there are strong connections between price movements and price influencing factors, then factors are selected
from the historical price patterns and a KB for predicting iron price variability can be constructed. Therefore, some
world events such as wars can have an immediate impact on the iron price. Then to represent irregular patterns in a
more organized and systematic way, price patterns are classified into individual patterns and combination patterns.
Individual patterns have simple conditions and attributes are used in defining combination patterns. In this
paper, the pattern can be considered to represent a rule because the conditions of a pattern can be seen as conditions
of a rule. Figures 2 and 3 show how individual patterns and combination patterns. As figure 2. If important events
are matched with the IF condition of a particular pattern, then pattern is identified by the conditions, and the
EXPLANATION part gives information about what the pattern really means. Individual pattern has its own meaning
and can be an important role in predicting iron price volatility. As figure 3, combination patterns integrate several
conditions or patterns to explain a certain sophisticated phenomenon, (Wang et al., 2004)
Figure 2. The syntax of individual pattern. Figure 3 .The syntax of a combination pattern.
2.3. GMDH Neural Networks3
GMDH neural networks are based on concept of pattern recognition. GMDH neural networks are highly
flexible, semi parametric models, have been used in many scientific fields such as engineering.
Neural networks represent an alternative to standard regression techniques and are useful for dealing with non-
linear multivariate relationships, for economists.
By applying GMDH algorithm there can be represented a set of neurons in which different pairs of them in each
and thus produce new neurons in the next layer. The formal definition of identification problem is to find a function
f^ that can be approximately used instead of actual one, f, to predict output y^ for a given input vector X = (x1, x2,
x3, . . . xn) as close as possible to its actual output y. Therefore, given M observation of multi-input-single-output
data pairs:
),...,
3
,
2
,
1
(
in
x
i
x
i
x
i
xf
i
y i=1, 2,…, M (1)
To train a GMDH-type neural network to predict the output values y^i for any given input vector X = (xi1, xi2,
xi3, . . . xin), that is:
),...,
3
,
2
,
1
(ˆˆ
in
x
i
x
i
x
i
xf
i
y i=1, 2,…, M (2)
Now problem is to determine a GMDH-type neural network so that square of difference between the actual
output and the predicted one is minimized, in the form of:
min
2
]),...,
3
,
2
,
1
(ˆ
1
[
i
y
in
x
i
x
i
x
i
xf
M
i
(3)
2
Varahrami (2014).
3
Abishami et al. (2010a).
PATTERN pattern name
IF condition A
(AND condition B)
(OR condition C)
· · ·
THEN PATTERN = pattern name
EXPLANATION = statement A
PATTERN pattern name
IF pattern A
(AND pattern B)
(OR pattern C)
(AND condition A)
(OR condition B)
· · ·
THEN PATTERN = pattern name
4. International Journal of Economics and Financial Research, 2015, 1(1): 6-12
9
General connection between inputs and output variables can express by a complicated discrete form of the
Volterra functional series, which is known as the Kolmogorov–Gabor (Farlow, 1984; Iba et al., 1996; Ivakhnenko,
1971; Nariman-zadeh et al., 2002; Sanchez et al., 1997). :
n= 1, 2,.., N (4)
Full form of mathematical description can be represented by a system of partial quadratic polynomials
consisting of only two neurons in the form of:
2
5
2
43210),(ˆ jxaixajxixajxaixaajxixGy i=1,…,M, j=1, 2,..,N (5)
Therefore, such partial quadratic description is used in a network of connected neurons to build the general
mathematical relation of inputs and output variables given in Eq. (4). The coefficients
i
a in Eq. (5) are calculated
by regression techniques (Farlow, 1984; Nariman-zadeh et al., 2002) so that difference between actual output, y,
and the calculated, y^, for each pair of xi, xj as input variables is minimized. In Eq. (5) coefficients are obtained in a
least-squares sense. In this way, the coefficients of each quadratic function Gi are obtained to fit the output that is:
min1
2)(
M
M
i
i
G
i
y
E (6)
In form of the GMDH algorithm, all two independent variables out of total n input variables are taken in order to
construct the regression polynomial in the form of Eq. (5).
2
)1(
2
nnn
neurons will be built up in the first
hidden layer of the feed forward network from the observations {(yi, xip, xiq); (i = 1,2. . . ,M)} for different p, q
(1, 2, . . . ,n). In other words, it is now possible to construct M data triples in the form:
MMqMp
qp
qp
yxx
yxx
yxx
222
111
. (7)
Using quadratic sub-expression for each row of M data triples, the following matrix equation can be readily obtained
as:
YA a (8)
Where a is the vector of unknown coefficients of the quadratic polynomial in Eq. (5)
},,,,,{ 543210 aaaaaaa (9)
And
T
MyyyyY },...,,,{ 321 is the vector of output’s value from observation:
22
2
2
2
22222
2
1
2
11111
1
1
1
MqMpMqMpMqMp
qpqpqp
qpqpqp
xxxxxx
xxxxxx
xxxxxx
A (10)
The least-squares technique from multiple-regression analysis leads to the solution of the normal equations ac shown
in Eq. (11):
YAAA TT 1
)(
a (11)
We should note that this procedure is repeated for each neuron of next hidden layer according to the
connectivity topology of the network. Recently, for each neuron searching its optimal set of connection with the
preceding layer, genetic algorithms have been used in a feed forward GMDH-type neural network (Nariman-zadeh
et al., 2002).
...
1 1 1 1 11
0
n
i
n
j
n
i
n
j
kxjx
n
k
ixijkajxixijaix
n
i
iaay
5. International Journal of Economics and Financial Research, 2015, 1(1): 6-12
10
2.4. Bases and Bases Management Module4
Bases management module is an important part of our new approach because other modules have a strong
connection with this one.
KB, in the bases management module, is the aggregation of domain materials and rules from knowledge
engineers. Furthermore, KB rules are formulated by extracting information from the DB historical data. KB is
component determining quality of the new approach. In addition, KB is organized and qualified determines strength
over the iron prediction. Databases are collected from real iron prices and iron price predict results from the GMDH
forecasting module. It can be used to fine-tune the knowledge in order to adapt to a dynamic situation. Model bases
are the aggregation of algorithms and models from other modules. This component can also support implementation
of the GMDH forecasting module and WTM module. Therefore in the based management module, knowledge
management and verification (KMV) can add new rules to the KB, edit or adjust existing rules and delete obsolete
rules in the KB. KMV can also verify the KB by checking consistency, completeness and redundancy. There are
hundreds of rules in KB that represent the domain expert’s heuristics and experience. Using the knowledge
acquisition tool, domain experts specify their rules for the KB in the format “IF · · · THEN · · ·”. The knowledge
acquisition automatically converts the rules into an inner encoded form. After new rules have been added, the
knowledge base verifier checks for any inconsistency, incompleteness that might have arisen as a result of adding the
rules (Wang et al., 2004)
3. Empirical Results
In this Section, we first describe the data used in this research in Section 3.1 and then define some evaluation
criteria for prediction purposes. Afterwards, the empirical results and explanations are presented in Section 3.2.
3.1. Data Description
In this paper, daily iron price covering January 1, 2009 through December 31, 2013 separately, are used and
with iron prices, iron contracts obtained from Metal Price5
. We utilize neural networks with two hidden layers and a
direct connection between the lagged moving average and prices. As input variables to the neural networks, 2 lags of
the 5[MA5,MA5(-1),MA5(-2)], 50[MA50,MA50(-1),MA50(-2)], day moving average crossover6
are used. The iron
daily price data used in this study.
It is necessary to introduce a forecasting evaluation criterion to evaluate the prediction performance. In this
study, two main evaluation criteria, root mean square error (RMSE) and direction statistics (Dstat) are introduced.
The RMSE is calculated as: (Berger, 1985; Casella and Lehmann, 1999; Degroot, 1980; Mood et al., 1974).
RMSE =
n
i
ie
n 1
21
(12)
ei denotes the difference between forecasted and realized values and n is the number of evaluation periods. A
change in trend is more important in iron price forecasting, than precision level of goodness of fit from the viewpoint
of practical applications is serious. Then we introduce Dstat. Its equation can be expressed as:
Dstat =
n
i
ie
n 1
1
(13)
Where ei = 1 if (yi+1 − yi) (ˆyi+1 − yi) ≥ 0, and ei = 0 otherwise. As the effects on iron price of irregular events
can be measured in the rational range, then the interval forecasting results can be obtained.
Irregular events and their effects are examined and explored. WTM is used to find the irregular events and RES
is to measure degree of impact of these irregular events.
Table-1. The factor classification
Factors Examples
Speculation 2009: in future market
Dollar s value decline 2009-2013: average decline is 20%
Increasing global iron demand 2009-2010: demand of iron increase in housing
Increasing metal price 2011-2013
Increasing investment in metal 2009 -2013
4
Abishami et al. (2010b).
5
MetalPrices.com
6
Such models are all based on rules using moving averages of recent prices. A typical moving average is simply the sum of the closing prices for
the last n number of days divided by n, where n may be from 1 to 200 days the rules for using these tools are very similar and usually involve
making a decision when a short-term average crosses over a long-term average. For example, the rule may be to buy when the 5-day moving
average exceeds the 50-day moving average and to sell when the 5-day average is below the 50-day average. Gencay (1996).
6. International Journal of Economics and Financial Research, 2015, 1(1): 6-12
11
Table-2.The typical rules in the knowledge bases
Rule NO Condition Direction movements The movements (%)
1 Speculation Increase 12
2 Dollar s value decline Increase 35.94
3 Increasing global iron demand Increase 11
4 Increasing metal price Increase 3
5 Increasing investment in metal Increase 6.2
According to the previous description of WTM, we can find some irregular events that affect the iron price from
Internet. Some main factors are concluded by analyzing past events in Table 1.
Table 2 showed the forecasting rules according to the extraction of historical events affecting the iron price. A
range of price movements can be given by the expert system module, when certain irregular events happen. By help
of this information, by using the WTM and RES modules, we can judge the effect of irregular future events on the
iron price. KB rules should be adjusted with time and events in order to keep the expert system robust.
3.2. A Simulation Study
A simulation experiment for proposed the hybrid intelligent system for iron price forecasting is used. Therefore,
we reveal that forecasting rules from expert system and moving average iron price are modeled by using GMDH
neural networks. We used the Muti-Objective Optimization Program (Atashkari et al., 2007) and Pareto based
multi-objective optimization (Amanifard et al., 2008) which designed with this target: reducing error in modeling
and forecasting that simultaneously increase exactitude of forecasting and the stability of process of measurement
the scale of variables effects in various patterns. The evaluation criteria are RMSE and Dstat.
Table 3 shows results of the simulated experiment. We can see that the hybrid intelligent system outperforms
the individual GMDH method in terms of either RMSE or Dstat. Values of Dstat of our hybrid intelligent forecasting
method for each evaluation period exceed 70%, it indicated that proposed hybrid intelligent forecasting approach has
good performance for the iron price forecasting.
In the case of individual GMDH method, the RMSE indicator, third sub-period 2011 performs the best. While
in the case of the hybrid intelligent method, the results of 2013 outperform those of the other evaluation period. The
main reason is that many important events affecting iron price volatility happened in this year and information of
those important events could be obtained by the WTM technique.
Indicator Dstat is more important than the indicator RMSE, from practitioner's point of view. Because the
former can reflect movement trend of iron price and can help traders to make good trading decisions. For the test
case of our hybrid intelligent approach and from the view of Dstat, the performance of 2013 is much better than
2009, 2010.2011 and 2012 as shown in Table 3.
Table-3. The forecasting results of iron price for period of Jan. 2009 - Dec. 2013
Evaluation Method Full Period
(2009-2013)
Sub Period
I 2009
Sub Period
II 2010
Sub Period
III 2011
Sub Period
IV 2012
Sub Period
V 2013
GMDH:
RMSE 3.475 3.461 3.212 3.023 3.187 3.206
Dstat (%) 60.15 57.24 59.35 62.33 64.42 66.18
Hybrid Intelligent:
RMSE 2.572 2.834 2.765 2.526 2.045 1.912
Dstat (%) 82.29 74.77 77.97 80.53 88.36 94.25
As Table 3, a smaller RMSE does not necessarily mean higher Dstat. For example, for individual GMDH
method, RMSE for 2010 is slightly smaller than for full-period 2009-2013, while the Dstat for period of 2009-2013
is larger than 2010. However, overall prediction performance of the proposed hybrid intelligent approach is sgood
because the RMSE for each evaluation period is smaller than 3.00 and the Dstat for each evaluation period exceeds
70%. This indicates that if traders use the proposed approach to forecast iron price, there are some profit
opportunities. (Wang et al., 2004)
4. Conclusions
In our survey, we find some irregular events that affect iron price and we reveal rules according to events
affecting iron price and we used from a hybrid intelligent framework integrating WTM and RES with GMDH neural
networks for iron price forecasting.
We showed that during the crisis period, when we observed the effects of irregular and infrequent events on iron
price by WTM and RES, better forecasting results respect to the GMDH neural networks are accrued. In our sample,
in 2013 different important events happen, in this year GMDH neural networks can not reveal effects of these events
on forecasting iron price and forecast's results of this methodology are not so well.
Therefore, hybrid intelligent forecasting model can be used as an effective tool for iron price forecasting and can
improve forecasting accuracy.
7. International Journal of Economics and Financial Research, 2015, 1(1): 6-12
12
References
Abishami, H., Mehrara, M., Ahrari, M.and Varahrami, V. (2010a). Gold price forecasting by hybrid intelligent
systems with GARCH Effects. Far East Journal of Experimental and Theoretical Artificial Intelligence, 6:
111-28. http://pphmj.com/journals/fejetai.htm
Abishami, H., Moeini, A., Ahrari, M.and Varahrami, V. (2010b). A Hybrid Intelligent System for forecasting
gasoline price. Iranian Economic Review, 15(27): 20-30.
Amanifard, N., Nariman-Zadeh, N., Borji, M., Khalkhali, A.and Habibdoust, A. (2008). Modeling and Pareto
optimization of heat transfer and flow coefficients in micro channels using GMDH type neural networks
and genetic algorithms. Energy Conversion and Management, 49(2): 311-25.
Atashkari, K., Nariman-Zadeh, N., Gölcü, M., Khalkhali, A.and Jamali, A. (2007). Modeling and multi-objective
optimization of a variable valve-timing spark-ignition engine using polynomial neural networks and
evolutionary algorithms. Energy Conversion and Management, 48(3): 1029-41.
Bauer, R. J. and Liepins, G. E. (1992). Genetic algorithms and computerized trading strategies. D. E. O’Leary and
P. R. Watkins. Elsevier Science Publishers: Expert systems in finance, Amsterdam, The Netherlands.
Berger, J. O. (1985). Statistical decision theory and Bayesian analysis. 2nd edn: Springer-Verlag.
Casella, G. and Lehmann, E. L. (1999). Theory of point estimation. Springer:
Cheng, B. and Titterington, D. (1994). Neural networks: A review from a statistical perspective. Statistical Science,
9(1): 2-30.
Degroot, M. (1980). Probability and Statistics. 2nd edn: Addison-Wesley:
Farlow, S. J. (1984). Self-organizing Method in Modeling, GMDH type algorithm. Marcel Dekker Inc.
Gencay, R. (1996). Non-linear prediction of security returns with moving average rules. Journal of Forecasting,
15(3): 165-74.
Gencay, R. (1998a). The predictability of security returns with simple technical trading rules. Journal of Empirical
Finance, 5(4): 374-59.
Gencay, R. (1999). Linear, non-linear and essential foreign exchange rate prediction with simple technical trading
rules. Journal of International Economics, 47(1): 91-107.
Gencay, R. and Stengos, T. (1998). Moving average rules, volume and the predictability of security returns with feed
forward networks. Journal of Forecasting, 17(5-6): 401-14.
Iba, H., de Garis, H.and Sato, T. (1996). A numerical Approach to Genetic Programming for System Identifications.
Evolutionary Computation, 3(4): 417-52.
Ivakhnenko, A. G. (1971). Polynomial Theory of Complex Systems. IEEE Trans. Syst, Man & Cybern, SMC-1: 364-
78.
Kuo, C. and Reitsch, A. (1995). Neural network vs. Conventional methods of forecasting. The Journal of Business
Forecasting Methods & Systems, 14(4): 17-25.
Mood, A., Graybill, F.and Boes, D. (1974). Introduction to the Theory of Statistics. 3nd edn: McGraw-Hill.
Nariman-zadeh, N., Darvizeh, A., Darvizeh, M.and Gharababaei, H. (2002). Modeling of explosive cutting process
of plates using GMDH-type neural network and singular value decomposition. Journal of Materials
Processing Technology, 128(1-3): 80-87.
Rajman, M. and Besanon, R. (1998).'Text mining –knowledge extraction from unstructured textual data'.The 6th
Conference of International Federation of Classification Societies.Rome.
Sanchez, E., Shibata, T.and Zadeh, L. A. (1997). Genetic Algorithms and Fuzzy Logic Systems. World Scientific.
Sarfaraz, L. and Afsar, A. (2005). A study on the factors affecting gold price and a neuro-fuzzy model of forecast.
Tarbiat Modaress Economic Reasearch Journal, 16: 70-75.
Varahrami, V. (2014). Gas price forecasting by Hybrid intelligent system. International Journal of Management and
Innovation: http://www.readperiodicals.com/201407/3360181631.html
Wang, S., Yu, L.and Lai, K. K. (2004). A Novel Hybrid AI System Framework for Crude Oil Price Forecasting.
Springer –Verlag Heidelberg.
Wong, B. K. and Yakup, S. (1998). Neural network applications in finance, A review and analysis of literature
(1990–1996). Information and Management, 58(5): 129–39.
Bibliography
Akgiray, V., Booth, G., Hatem, J.and Mustafa, C. (1991). Conditional dependence in precious metal prices.
Financial Review, 26: 367-86.
Amanifard, N., Nariman-Zadeh, N., Borji, M., Khalkhali, A.and Habibdoust, A. (2008). Modeling and Pareto
optimization of heat transfer and flow coefficients in micro channels using GMDH type neural networks
and genetic algorithms. Energy Conversion and Management, 49(2): 311-25.
Anonymous 'http://www.metalprices.com'.
Jamali, A., Nariman-zadeh, N.and Atashkari, K. (2006).'Inverse Modeling of Multi-objective Thermodynamically
Optimized Turbojet Engines using GMDH and GA'.14th Annual (International) Mechanical Engineering
Conference.Isfahan University of Technology, Isfahan, Iran
Mehrara, M., Abrishami, H., Ahrari, M.and Varahrami, V. (2013). A hybrid intelligent system for forecasting crude
oil price. International Journal of Economics and Business Research, 5(1): 1-16.