Constructing Query-Driven Dynamic Machine Learning Model With Application to Protein-Ligand Binding Sites Prediction

•Download as DOCX, PDF•

0 likes•82 views

I3E Technologies, #23/A, 2nd Floor SKS Complex, Opp. Bus Stand, Karur-639 001. IEEE PROJECTS AVAILABLE, NON-IEEE PROJECTS AVAILABLE, APPLICATION BASED PROJECTS AVAILABLE, MINI-PROJECTS AVAILABLE. Mobile : 99436 99916, 99436 99926, 99436 99936 Mail ID: i3eprojectskarur@gmail.com Web: www.i3etechnologies.com, www.i3eprojects.com

Engineering

CONSTRUCTING QUERY-DRIVEN DYNAMIC
MACHINE LEARNING MODEL WITH APPLICATION TO PROTEIN-LIGAND
BINDING SITES PREDICTION
ABSTRACT
We are facing an era with annotated biological data rapidly and continuously generated.
How to effectively incorporate new annotated data into the learning step is crucial for enhancing
the performance of a bioinformatics prediction model. Although machine-learning-based
methods have been extensively used for dealing with various biological problems, existing
approaches usually train static prediction models based on fixed training datasets. The static
approaches are found having several disadvantages such as low scalability and impractical when
training dataset is huge. In view of this, we propose a dynamic learning framework for
constructing query-driven prediction models. The key difference between the proposed
framework and the existing approaches is that the training set for the machine learning algorithm
of the proposed framework is dynamically generated according to the query input, as opposed to
training a general model regardless of queries in traditional static methods. Accordingly, a query-
driven predictor based on the smaller set of data specifically selected from the entire annotated
base dataset will be applied on the query. The new way for constructing the dynamic model
enables us capable of updating the annotated base dataset flexibly and using the most relevant
core subset as the training set makes the constructed model having better generalization ability
on the query, showing “part could be better than all” phenomenon. According to the new
framework, we have implemented a dynamic protein-ligand binding sites predictor called OSML
(On-site model for ligand binding sites prediction). Computer experiments on 10 different ligand
types of three hierarchically organized levels show that OSML outperforms most existing
predictors. The results indicate that the current dynamic framework is a promising future
direction for bridging the gap between the rapidly accumulated annotated biological data and the
effective machine-learning-based predictors

This document proposes an incremental semi-supervised clustering ensemble framework (ISSCE) to address limitations in traditional cluster ensemble approaches for high dimensional data clustering. ISSCE incorporates prior knowledge through constraint propagation, handles high dimensionality using random subspaces, and judiciously removes redundant ensemble members through an incremental selection process. Experiments on 18 real-world datasets, including 6 UCI datasets and 12 cancer gene expression profiles, show that ISSCE performs well on very high dimensional data and outperforms other semi-supervised clustering ensemble approaches.

Transfer learning improves supervised image segmentation across imaging proto...

I3E Technologies

IEEE 2014 JAVA DATA MINING PROJECTS Active learning of constraints for semi s...

IEEEFINALYEARSTUDENTPROJECTS

This document summarizes a paper on active learning for semi-supervised clustering. It introduces a novel approach for computing uncertainty in data points and selecting queries that have the highest information rate. The proposed method trades off uncertainty and query cost to iteratively expand neighborhoods defined by pairwise constraints. Evaluation on benchmark datasets demonstrates substantial improvements over the state of the art.

Remote sensing-ieee-2014-projects

Vijay Karan

Artificial intelligence

Genesis Institute of Pharmacy, Radhanagari.

Myself Omkar B. Tipugade ,M-Pharm Sem II, Department of Pharmaceutics , Today I upload the presentation on Artificial Intelligene , In that I discuss about the definition of AI as well as their important in Pharmaceutical field . Also give brief information about the Neural networking & fuzzy logic with diagrammatic presentation And also application of AI in product formulation. I highlight the important words.

ACTIVE LEARNING FOR RANKING THROUGH EXPECTED LOSS OPTIMIZATION

I3E Technologies

This document proposes an active learning framework called expected loss optimization (ELO) for ranking models. ELO can be used with different ranking functions to select the most informative examples for labeling. The document presents an algorithm called expected discounted cumulative gain loss optimization (ELO-DCG) for selecting examples under this framework. It also describes a two-stage ELO-DCG algorithm that performs both query-level and document-level active learning. Experiments on real-world web search data demonstrated the effectiveness of the proposed framework and algorithms.

Group ppt 8

KarthikKaricheti

This paper aims to provide a methodology for identifying energy consumption patterns in a large dataset of flats using data mining. The authors analyzed energy usage data from over 92,000 flats to classify them and establish rules for decision making. The classifications can help designers and planners identify major causes of high energy consumption and evaluate potential impacts of retrofitting actions. The paper recommends further investigating the dataset to improve classification accuracy and studying how building owner decisions influence applying proposed retrofits.

A reconstruction error based framework for multi label and multi-view learning

ieeepondy

A reconstruction error based framework for multi label and multi-view learning +91-9994232214,8144199666, ieeeprojectchennai@gmail.com, www.projectsieee.com, www.ieee-projects-chennai.com IEEE PROJECTS 2015-2016 ----------------------------------- Contact:+91-9994232214,+91-8144199666 Email:ieeeprojectchennai@gmail.com Support: ------------- Projects Code Documentation PPT Projects Video File Projects Explanation Teamviewer Support

This project aimed to build a predictive model for detecting healthcare fraud using Medicare and payment data from open sources. The data was stored in a Hadoop cluster and preprocessed using Pig scripts. Python was used to implement a data pipeline with scaling and different machine learning models, including logistic regression, Gaussian, random forest, extra trees, and gradient boosting classifiers. The random forest model achieved the best average AUC of 0.69. Feature importance analysis found the custom "drug_score" feature was most important. Future work could include more data sources, additional features, and model blending to improve results.

ChEBI and genome scale metabolic reconstructions

Neil Swainston

1. Genome-scale metabolic reconstructions are network maps of metabolism that are computer-readable and can be used for metabolic engineering, biological discovery, and predicting phenotypic behavior. 2. Standards like SBML and MIRIAM allow sharing, comparing and merging models by providing a common language and requiring annotation of model constituents to external databases. 3. ChEBI is commonly used for annotating metabolites in models due to its comprehensive coverage, fast search capabilities, and web services that enable automation. This allows relating experimental data to models and developing tools for tasks like reaction balancing.

Cbms07 Bratsas

Charalampos Bratsas

Thesis the impact of total preventive maintenance on kanban system to buss...

Su darjo

This document summarizes a research paper titled "The Impact of Total Preventive Maintenance on Kanban system to Bussiness Performance" by Trisakti University student SUDARJO in September 2013. The research aimed to identify the influence of total preventive maintenance on kanban systems and business performance. It used a correlation research design to detect relationships between independent and dependent variables. Data analysis tested hypotheses using SPSS to analyze the impact of preventive maintenance on kanban systems and business performance.

Nataly Zhukova - Conceptual Model for Routine Measurements Analyses in Seman...

AIST

The document presents a conceptual model for processing routine measurements in adaptive intelligent information systems. The model aims to help users solve domain-specific tasks by reducing large amounts of data, linking related pieces of information, and providing machine-based solutions. It is based on the idea that measurements can provide insights into the real world if transformed and analyzed over time. The model represents real-world objects and processes with simpler views and decomposable sub-processes. A case study demonstrates applying the model to process patient measurement data from a medical center over time and link it to medical events and expected outcomes. Future work involves developing a framework for both experts and non-experts to work with the domain models.

Efficient data query in intermittently connected mobile ad hoc social networks

LogicMindtech Nologies

Data Science in Medicine and Health

Steve Tsang

Technology and data-driven approaches are helping advance our understanding of science and medicine. Deep learning algorithms can analyze large amounts of medical data to identify patterns and make diagnoses. One study found that a deep learning system correctly identified the diagnosis of skin lesions 72% of the time, outperforming board-certified dermatologists who were correct 66% of the time. Initiatives like the Cancer Moonshot aim to apply these types of data-driven approaches and machine learning to make breakthroughs in cancer research, with a goal of accelerating progress by 10 years. These new technologies have potential to transform how doctors learn, practice medicine, and improve patient outcomes.

Artificial intelligence in drug discovery

RAVINDRABABUKOPPERA

This document discusses the use of artificial intelligence in drug discovery and development. It begins by defining artificial intelligence, machine learning, and deep learning. It then provides examples of how AI is currently used in various stages of the drug development process, including identifying molecular targets, finding hit compounds, optimizing lead compounds, predicting toxicity, and drug repurposing. It also discusses startups applying AI to drug discovery. Finally, it notes some limitations and drawbacks of using AI, such as potential bias in algorithms.

Crowdsourcing predictors of behavioral outcomes

IEEEFINALYEARPROJECTS

This paper describes a new approach to machine learning that uses crowdsourcing to develop predictive models of behavioral outcomes. Users on a website generate questions to collect data on predictors of an outcome like energy usage or BMI. They also answer questions to provide values for potential predictors. Models are built using this user-generated data to predict individual outcomes. Two experiments successfully built models predicting monthly energy usage and BMI based on questions crowdsourced by users. This demonstrates that non-experts can collectively identify predictive features and provide data to build models of behavioral outcomes through an interactive online process.

Crowdsourcing predictors of behavioral outcomes

JPINFOTECH JAYAPRAKASH

This document describes a new approach to machine learning that harnesses the wisdom of crowds to develop predictive models of behavioral outcomes. The approach uses a web platform where users answer questions to predict an outcome (like electricity usage or BMI) and also generate new questions. As more users contribute data by answering questions, models are developed that can better predict outcomes based on the question responses. Two experiments accurately predicted monthly electricity usage and BMI based on models developed from questions crowdsourced by users. This novel approach may lead to new insights into causal factors of behaviors.

IBMA: An SPM toolbox for Neuroimaging Image-Based Meta-Analysis

Camille Maumet

While most neuroimaging meta-analyses are based on peak coordinate data, the best practice method is an image-based meta-analysis that combines the effect estimates and the standard errors from each study [7]. Various efforts are underway to facilitate sharing of neuroimaging data to make such intensity-based meta-analysis possible (see, e.g. [4]). When image data is available for each study, a number of approaches (see [6] for a review) have been proposed to perform such meta-analysis including combination of standardised statistics, just effect estimates or both effects estimates and their sampling variance. While the latter is the preferred approach in the statistical community [1], often only standardised estimates are shared, reducing the possible meta-analytic approaches. In view of the increasing availability of image data for neuroimaging analyses, we introduce IBMA, a toolbox for SPM [8] providing a set of tools for image-based meta-analysis. The toolbox is freely available at: https://github.com/NeuroimagingMetaAnalysis/ibma.

RELATIONAL COLLABORATIVE TOPIC REGRESSION FOR RECOMMENDER SYSTEMS

I3E Technologies

Role of AI in Drug Discovery and Development

Dr. Manu Kumar Shetty

Genome-Scale Metabolic Models and Systems Medicine of Metabolic Syndrome

Natal van Riel

Research assistant at nus

SrinivasaRaoKaza1

The document describes a job opening for a Research Assistant to work on a disaster management project at the National University of Singapore. The project aims to develop a prescriptive analytics framework to optimize resource deployment during disasters through data integration, simulation modeling, and accounting for human behavior. The research assistant will help investigate the data modeling framework and simulation model, and may collaborate with social science researchers. Candidates should have a computer science degree and experience in data modeling, crisis systems modeling, agent-based simulation, and human behavior models.

UPMCE CMU - Introduction to Data Analysis In Healthcare

Mohinder Dick, PMP

This document discusses machine learning in healthcare. It begins with an overview of key machine learning concepts like supervised learning, linear algorithms, target variables, and features. It then discusses getting started with machine learning, including recommended training resources, available data sources, and popular tools like Spark, Python, and R. The document also presents a healthcare use case example to predict length of stay using patient data like age, gender, and diagnosis. It describes feature extraction and evaluation metrics that could be used to assess the machine learning model's performance.

Introductionedited

Mefratechnologies

This document discusses random forest machine learning algorithms and their use in predictive modeling. It provides context on random forests, including that they perform well for both classification and regression tasks, are less prone to overfitting than decision trees, and provide good predictive accuracy while also being interpretable. The document then discusses preprocessing methods like stemming, removing punctuation and stop words that can be applied before using natural language processing algorithms. It highlights the advantages of random forests, such as their ability to handle different data types, parallelizability, and stability. It also notes limitations like lack of interpretability for some users and potential for overfitting on some data sets.

Paper Explained: RandAugment: Practical automated data augmentation with a re...

Devansh16

Ieee transactions on 2018 knowledge and data engineering topics with abstract .

tsysglobalsolutions

This document contains abstracts from 8 different academic papers. The abstracts discuss various topics related to knowledge and data engineering including traditional Chinese medicine prescriptions, multi-label learning, viral marketing in online social networks, location recommendation, nonnegative matrix factorization, distributed processing of top-k dominating queries, and supervised topic modeling for e-commerce applications. The contact information for TSYS Academic Projects is also provided at the top.

Machine learning - session 4

Luis Borbon

demonstration lecture on Homology modeling

Maharaj Vinayak Global University

This document discusses homology modeling, which is a computational technique used to develop atomic-resolution models of proteins based on their amino acid sequences and known 3D structures of homologous proteins. It describes the key steps in homology modeling as template identification, target-template alignment, model building and refinement, and model validation. The advantages of homology modeling include that it is faster than experimental techniques. However, the accuracy depends on factors like the sequence identity between the target and template.

What's hot

Efficient motif discoveryfor large scale time series in healthcare

I3E Technologies

Medicare fraud detection

Xinyu (Max) Liu

ChEBI and genome scale metabolic reconstructions

Neil Swainston

Cbms07 Bratsas

Charalampos Bratsas

Thesis the impact of total preventive maintenance on kanban system to buss...

Su darjo

Nataly Zhukova - Conceptual Model for Routine Measurements Analyses in Seman...

AIST

Efficient data query in intermittently connected mobile ad hoc social networks

LogicMindtech Nologies

Data Science in Medicine and Health

Steve Tsang

Artificial intelligence in drug discovery

RAVINDRABABUKOPPERA

Crowdsourcing predictors of behavioral outcomes

IEEEFINALYEARPROJECTS

Crowdsourcing predictors of behavioral outcomes

JPINFOTECH JAYAPRAKASH

IBMA: An SPM toolbox for Neuroimaging Image-Based Meta-Analysis

Camille Maumet

RELATIONAL COLLABORATIVE TOPIC REGRESSION FOR RECOMMENDER SYSTEMS

I3E Technologies

Role of AI in Drug Discovery and Development

Dr. Manu Kumar Shetty

Genome-Scale Metabolic Models and Systems Medicine of Metabolic Syndrome

Natal van Riel

Research assistant at nus

SrinivasaRaoKaza1

UPMCE CMU - Introduction to Data Analysis In Healthcare

Mohinder Dick, PMP

Introductionedited

Mefratechnologies

What's hot (18)

Efficient motif discoveryfor large scale time series in healthcare

Medicare fraud detection

ChEBI and genome scale metabolic reconstructions

Cbms07 Bratsas

Thesis the impact of total preventive maintenance on kanban system to buss...

Nataly Zhukova - Conceptual Model for Routine Measurements Analyses in Seman...

Efficient data query in intermittently connected mobile ad hoc social networks

Data Science in Medicine and Health

Artificial intelligence in drug discovery

Crowdsourcing predictors of behavioral outcomes

IBMA: An SPM toolbox for Neuroimaging Image-Based Meta-Analysis

RELATIONAL COLLABORATIVE TOPIC REGRESSION FOR RECOMMENDER SYSTEMS

Role of AI in Drug Discovery and Development

Genome-Scale Metabolic Models and Systems Medicine of Metabolic Syndrome

Research assistant at nus

UPMCE CMU - Introduction to Data Analysis In Healthcare

Introductionedited

Similar to Constructing Query-Driven Dynamic Machine Learning Model With Application to Protein-Ligand Binding Sites Prediction

Paper Explained: RandAugment: Practical automated data augmentation with a re...

Devansh16

Ieee transactions on 2018 knowledge and data engineering topics with abstract .

tsysglobalsolutions

Machine learning - session 4

Luis Borbon

demonstration lecture on Homology modeling

Maharaj Vinayak Global University

Fast and Scalable Semi Supervised Adaptation For Video Action Recognition

IJSRED

This document summarizes a research paper on developing a fast and scalable semi-supervised method for video action recognition using conditional random fields. The proposed method, called semi-supervised virtual evidence boosting (sVEB), simultaneously performs feature selection and semi-supervised training of CRFs using both labeled and unlabeled data. sVEB reduces the amount of labeling required during training while maintaining high accuracy, making it suitable for real-world applications. Experimental results on synthetic and activity recognition tasks demonstrate that sVEB outperforms other training techniques in terms of accuracy while being more computationally efficient.

Semi-supervised learning approach using modified self-training algorithm to c...

IJECEIAES

Burst header packet flooding is an attack on optical burst switching (OBS) network which may cause denial of service. Application of machine learning technique to detect malicious nodes in OBS network is relatively new. As finding sufficient amount of labeled data to perform supervised learning is difficult, semi-supervised method of learning (SSML) can be leveraged. In this paper, we studied the classical self-training algorithm (ST) which uses SSML paradigm. Generally, in ST, the available true-labeled data (L) is used to train a base classifier. Then it predicts the labels of unlabeled data (U). A portion from the newly labeled data is removed from U based on prediction confidence and combined with L. The resulting data is then used to re-train the classifier. This process is repeated until convergence. This paper proposes a modified self-training method (MST). We trained multiple classifiers on L in two stages and leveraged agreement among those classifiers to determine labels. The performance of MST was compared with ST on several datasets and significant improvement was found. We applied the MST on a simulated OBS network dataset and found very high accuracy with a small number of labeled data. Finally we compared this work with some related works.

JAVA 2013 IEEE DATAMINING PROJECT Crowdsourcing predictors of behavioral outc...

IEEEGLOBALSOFTTECHNOLOGIES

This paper describes a new approach to machine learning that uses crowdsourcing to develop predictive models of behavioral outcomes. Users on a website generate questions to collect data on predictors of an outcome like energy usage or BMI. They also answer questions to provide values for potential predictors. Models are built using this user-generated data to predict individual outcomes. Two experiments showed this approach successfully identified predictors of monthly energy consumption and BMI. By outsourcing variable selection and data collection to users, this method develops predictive models without requiring domain expertise.

Spe165 t

Rajesh War

This document discusses techniques for detecting duplicate records from multiple web databases. It begins with an abstract describing an unsupervised approach that uses classifiers like the weighted component similarity summing classifier and support vector machine along with a Gaussian mixture model to iteratively identify duplicate records. The document then provides details on related work, including probabilistic matching models, supervised and unsupervised learning techniques, distance-based techniques, rule-based approaches, and methods for improving efficiency like blocking and the sorted neighborhood approach.

12918 2015 article_144 (1)

Anandsingh06

This document introduces BioPreDyn-bench, a suite of benchmark problems for dynamic modelling in systems biology. The suite contains 6 benchmark problems ranging from medium to large-scale kinetic models of organisms such as E. coli, S. cerevisiae, D. melanogaster, and human cells. For each benchmark, the document provides a description, implementations in various formats, computational results from specific solvers, and analysis. The suite aims to serve as reference test cases to evaluate and compare parameter estimation methods for dynamic models in systems biology.

Neural networks for the prediction and forecasting of water resources variables

Jonathan D'Cruz

This document reviews the use of artificial neural networks (ANNs) for predicting and forecasting water resource variables. It outlines the key steps in developing ANN models, including choosing performance criteria, preprocessing and dividing data, determining appropriate model inputs and network architecture, optimizing connection weights through training, and validating models. Specifically, it focuses on feedforward networks with sigmoid transfer functions, which have been most widely used for predicting water resources variables.

UNCERTAINTY ESTIMATION IN NEURAL NETWORKS THROUGH MULTI-TASK LEARNING

gerogepatton

The impressive predictive performance of deep learning techniques on a wide range of tasks has led to its widespread use. Estimating the confidence of these predictions is paramount for improving the safety and reliability of such systems. However, the uncertainty estimates provided by neural networks (NNs) tend to be overconfident and unreasonable. Previous studies have found out that ensemble of NNs typically produce good predictions and uncertainty estimates. Inspired by these, this paper presents a new framework that can quantitatively estimate the uncertainties by leveraging the advances in multi-task learning through slight modification to the existing training pipelines. This promising algorithm is developed with an intention of deployment in real world problems which already boast a good predictive performance by reusing those pretrained models. The idea is to capture the behavior of the trained NNs for the base task by augmenting it with the uncertainty estimates from a supplementary network. A series of experiments show that the proposed approach produces well calibrated uncertainty estimates with high quality predictions.

UNCERTAINTY ESTIMATION IN NEURAL NETWORKS THROUGH MULTI-TASK LEARNING

ijaia

This summarizes a research paper on using multi-task learning to estimate uncertainty in neural networks. The paper proposes training a base neural network for the main prediction task. It then fine-tunes the base network along with a separate uncertainty estimation network using multi-task learning. The uncertainty network is trained to output predictive variance, allowing the model to estimate aleatoric and epistemic uncertainty. Experiments showed this approach produces well-calibrated uncertainty estimates while maintaining high quality predictions.

Ieee projects 2012 2013 - Bio Informatics

K Sundaresh Ka

ieee projects download, base paper for ieee projects, ieee projects list, ieee projects titles, ieee projects for cse, ieee projects on networking,ieee projects 2012, ieee projects 2013, final year project, computer science final year projects, final year projects for information technology, ieee final year projects, final year students projects, students projects in java, students projects download, students projects in java with source code, students projects architecture, free ieee papers

Predictive Data Mining with Normalized Adaptive Training Method for Neural Ne...

IJERDJOURNAL

Abstract:- Predictive data mining is an upcoming and fast-growing field and offers a competitive edge for the benefit of organization. In recent decades, researchers have developed new techniques and intelligent algorithms for predictive data mining. In this research paper, we have proposed a novel training algorithm for optimizing neural networks for prediction purpose and to utilize it for the development of prediction models. Models developed in MATLAB Neural Network Toolbox have been tested for insurance datasets taken from a live data warehouse. A comparative study of the proposed algorithm with other popular first and second order algorithms has been presented to judge the predictive accuracy of the suggested technique. Various graphs have been presented to analyse the convergence behaviour of different algorithms towards point of minimum error.

An Efficient PSO Based Ensemble Classification Model on High Dimensional Data...

ijsc

This summary provides the high-level information from the document in 3 sentences: The document proposes a Particle Swarm Optimization (PSO) based ensemble classification model to improve classification of high-dimensional biomedical datasets. It develops an optimized PSO technique to select optimal features and initialize weights for base classifiers in the ensemble model. Experimental results on microarray datasets show the proposed model achieves higher accuracy, true positive rate, and lower error rate compared to traditional feature selection based classification models.

AN EFFICIENT PSO BASED ENSEMBLE CLASSIFICATION MODEL ON HIGH DIMENSIONAL DATA...

ijsc

As the size of the biomedical databases are growing day by day, finding an essential features in the disease prediction have become more complex due to high dimensionality and sparsity problems. Also, due to the availability of a large number of micro-array datasets in the biomedical repositories, it is difficult to analyze, predict and interpret the feature information using the traditional feature selection based classification models. Most of the traditional feature selection based classification algorithms have computational issues such as dimension reduction, uncertainty and class imbalance on microarray datasets. Ensemble classifier is one of the scalable models for extreme learning machine due to its high efficiency, the fast processing speed for real-time applications. The main objective of the feature selection based ensemble learning models is to classify the high dimensional data with high computational efficiency and high true positive rate on high dimensional datasets. In this proposed model an optimized Particle swarm optimization (PSO) based Ensemble classification model was developed on high dimensional microarray datasets. Experimental results proved that the proposed model has high computational efficiency compared to the traditional feature selection based classification models in terms of accuracy , true positive rate and error rate are concerned.

An efficient feature selection algorithm for health care data analysis

journalBEEI

Diabete is a silent killer, which will slowly kill the person if it goes undetected. The existing system which uses F-score method and K-means clustering of checking whether a person has diabetes or not are 100% accurate, and anything which isn't a 100% is not acceptable in the medical field, as it could cost the lives of many people. Our proposed system aims at using some of the best features of the existing algorithms to predict diabetes, and combine these and based on these features; This research work turns them into a novel algorithm, which will be 100% accurate in its prediction. With the surge in technological advancements, we can use data mining to predict when a person would be diagnosed with diabetes. Specifically, we analyze the best features of chi-square algorithm and advanced clustering algorithm (ACA). This research work is done using the Pima Indian Diabetes dataset provided by National Institutes of Diabetes and Digestive and Kidney Diseases. Using classification theorems and methods we can consider different factors like age, BMI, blood pressure and the importance given to these attributes overall, and singles these attributes out, and use them for the prediction of diabetes.

Emr a scalable graph based ranking model for content-based image retrieval

Pvrtechnologies Nellore

This document summarizes a research paper that proposes a new scalable graph-based ranking model called Efficient Manifold Ranking (EMR) to address limitations of existing Manifold Ranking (MR) methods for large-scale content-based image retrieval. EMR improves upon MR in two ways: 1) it builds an anchor graph instead of a k-nearest neighbor graph to represent image relationships more efficiently, and 2) it designs a new adjacency matrix formulation to speed up the ranking computation process. The paper presents experimental results demonstrating that EMR enables effective out-of-sample retrieval from large image databases containing over 1 million images, which was previously not possible with MR methods.

Post Graduate Admission Prediction System

IRJET Journal

This document presents a post graduate admission prediction system built using machine learning algorithms. The system analyzes factors like GRE scores, TOEFL scores, undergraduate GPA, research experience etc. to predict the universities a student is likely to get admission in. Various machine learning models like multiple linear regression, random forest regression, support vector machine and logistic regression are implemented and evaluated on an admission prediction dataset. Logistic regression achieved the highest accuracy of 97%. A web application called PostPred is developed using the logistic regression model to help students predict suitable universities to apply to based on their profile.

ON THE PREDICTION ACCURACIES OF THREE MOST KNOWN REGULARIZERS : RIDGE REGRESS...

ijaia

The document compares the prediction accuracies of ridge regression, lasso regression, and elastic net regularization methods on 13 datasets. It finds that the prediction accuracy depends heavily on the nature of the datasets. When using cross-validation, the lasso method worked better than ridge regression and elastic net on two datasets. When using BIC scoring, BIC produced better predictions than cross-validation for 6 datasets, especially favoring ridge regression on highly correlated datasets. Overall, ridge regression, lasso, and elastic net tended to perform similarly except on two datasets where ridge regression outperformed the others.

Similar to Constructing Query-Driven Dynamic Machine Learning Model With Application to Protein-Ligand Binding Sites Prediction (20)

Paper Explained: RandAugment: Practical automated data augmentation with a re...

Ieee transactions on 2018 knowledge and data engineering topics with abstract .

Machine learning - session 4

demonstration lecture on Homology modeling

Fast and Scalable Semi Supervised Adaptation For Video Action Recognition

Semi-supervised learning approach using modified self-training algorithm to c...

JAVA 2013 IEEE DATAMINING PROJECT Crowdsourcing predictors of behavioral outc...

Spe165 t

12918 2015 article_144 (1)

Neural networks for the prediction and forecasting of water resources variables

UNCERTAINTY ESTIMATION IN NEURAL NETWORKS THROUGH MULTI-TASK LEARNING

Ieee projects 2012 2013 - Bio Informatics

Predictive Data Mining with Normalized Adaptive Training Method for Neural Ne...

An Efficient PSO Based Ensemble Classification Model on High Dimensional Data...

AN EFFICIENT PSO BASED ENSEMBLE CLASSIFICATION MODEL ON HIGH DIMENSIONAL DATA...

An efficient feature selection algorithm for health care data analysis

Emr a scalable graph based ranking model for content-based image retrieval

Post Graduate Admission Prediction System

ON THE PREDICTION ACCURACIES OF THREE MOST KNOWN REGULARIZERS : RIDGE REGRESS...

More from I3E Technologies

Add

I3E Technologies

Design of a low voltage low-dropout regulator

I3E Technologies

An efficient constant multiplier architecture based on vertical horizontal bi...

I3E Technologies

Aging aware reliable multiplier design with adaptive hold logic

I3E Technologies

A high performance fir filter architecture for fixed and reconfigurable appli...

I3E Technologies

A generalized algorithm and reconfigurable architecture for efficient and sca...

I3E Technologies

A combined sdc sdf architecture for normal i o pipelined radix-2 fft

I3E Technologies

Reverse converter design via parallel prefix adders novel components, method...

I3E Technologies

Pre encoded multipliers based on non-redundant radix-4 signed-digit encoding

I3E Technologies

Energy optimized subthreshold vlsi logic family with unbalanced pull up down ...

I3E Technologies

Variable form carrier-based pwm for boost-voltage motor driver with a charge-...

I3E Technologies

Ultrasparse ac link converters

I3E Technologies

Single inductor dual-output buck–boost power factor correction converter

I3E Technologies

Ripple minimization through harmonic elimination in asymmetric interleaved mu...

I3E Technologies

Resonance analysis and soft switching design of isolated boost converter with...

I3E Technologies

Reliability evaluation of conventional and interleaved dc–dc boost converters

I3E Technologies

Power factor corrected zeta converter based improved power quality switched m...

I3E Technologies

The document describes a proposed switched mode power supply (SMPS) system that uses a front-end power factor corrected Zeta converter to improve power quality. The front-end converter reduces 100-Hz ripple and improves power factor and voltage regulation. Simulation and testing of a laboratory prototype showed the proposed SMPS enhanced performance under varying input voltages and loading conditions, meeting international power quality standards.

Pfc cuk converter fed bldc motor drive

I3E Technologies

Optimized operation of current fed dual active bridge dc dc converter for pv ...

I3E Technologies

This document discusses optimized operation of a current-fed dual active bridge DC-DC converter for photovoltaic applications. It analyzes the operating principle and soft-switching conditions over a wide operating range with phase shift and duty cycle control. An optimized operating mode is proposed to achieve minimum RMS transformer current and extend the soft-switching region to reduce losses. Experimental results from a 5 kW hardware prototype verify the analysis. Contact and location information is also provided for an organization that develops IEEE software and hardware projects.

Online variable topology type photovoltaic grid-connected inverter

I3E Technologies

More from I3E Technologies (20)