Filters








439,066 Hits in 5.1 sec

A Feature Selection Algorithm Performance Metric for Comparative Analysis

Werner Mostert, Katherine M. Malan, Andries P. Engelbrecht
2021 Algorithms  
This study presents a novel performance metric for feature selection algorithms that is unbiased and can be used for comparative analysis across feature selection problems.  ...  The BFI measure can be used to compare the performance of feature selection algorithms across datasets by measuring the change in classifier performance as a result of feature selection, with respect to  ...  Conclusions The goal of this study was to propose a novel performance metric: the baseline fitness improvement (BFI) measure for feature selection algorithms, which is unbiased and can be used for comparative  ... 
doi:10.3390/a14030100 fatcat:h3yen7sb55futo3yuxvspo7c6i

Comparisons of Filter, Wrapper and Embedded-Based Feature Selection Techniques for Consistency of Software Metrics Analysis

Shamsuddeen Muhammad Abubakar, Department of Computer Science, Faculty of Computing Federal University Dutse, Jigawa State., Zahraddeen Sufyanu, Department of Computer Science, Faculty of Computing Federal University Dutse, Jigawa State.
2022 SLU Journal of Science and Technology  
techniques as compared with counterpart filter and wrapper-based feature selection techniques  ...  Identifying and selecting the most consistent subset of metrics which improves the performance of software defect prediction model is paramount but challenging problem as it receives little attention in  ...  The research proposed using Embedded Feature Selection techniques for correlation of a subset of software metrics analysis.  ... 
doi:10.56471/slujst.v4i.238 fatcat:72wqt2eynzb65dwfo2xqswfc3u

A machine learning approach for feature selection traffic classification using security analysis

Muhammad Shafiq, Xiangzhan Yu, Ali Kashif Bashir, Hassan Nazeer Chaudhry, Dawei Wang
2018 Journal of Supercomputing  
2018)A machine learning approach for feature selection traffic classification using security analysis.  ...  These metrics select effective features from a traffic flow. However, in order to select robust features from the selected features, we proposed robust features selection algorithm.  ...  In the second step (line 13-26), WMI_AUC algorithm selects effective features with AUC metric for a particular ML classifier.  ... 
doi:10.1007/s11227-018-2263-3 fatcat:tcy2un6yzfdnfcknz3w26ls4fu

Hybrid Optimization Driven RideNN for Software Reusability Estimation

Ramu Vankudoth, Research Scholar (Ph.D.), Department of Computer Science, Kakatiya University, Vidyaranyapuri, Warangal, Telangana 506009, Dr.Shireesha P, Assistant Professor, Department of Computer Science and Engineering, Kakatiya Institute of Technology and Science, Bheemaram, Hanamkonda, Telangana 506015
2020 Maǧallaẗ al-abḥāṯ al-handasiyyaẗ  
Then, a holoentropy based log function identifies the normalized metric function and provides it to the proposed Cat Swarm Rider Optimization based Neural Network (C-RideNN) algorithm for the software  ...  The simulation results reveal that the proposed C-RideNN algorithm has improved performance with 0.0570 as MAE, 0.0145 as MMRE, and 0.6133 as SEM.  ...  Comparative analysis for the Holoentropy = 4 based on (a) MAE, (b) MMRE, and (c) SEM. Figure 4 . 4 Comparative analysis for the Holoentropy = 5 based on (a) MAE, (b) MMRE, and (c) SEM.  ... 
doi:10.36909/jer.v8i4.7881 fatcat:3zrymogtkjcqrbmyis4evllvxe

Majority vote feature selection algorithm in software fault prediction

Emin Borandag, Akin Ozcift, Deniz Kilinc, Fatih Yucalar
2019 Computer Science and Information Systems  
The aim of this research is to develop a Majority Vote based Feature Selection algorithm (MVFS) to identify the most valuable software metrics.  ...  Furthermore, the performance of the algorithms is closely related to determine the most valuable software metrics.  ...  Another recent work makes use of a hybrid feature selection to improve fault prediction performance of machine learning algorithms [24] .  ... 
doi:10.2298/csis180312039b fatcat:cvglwd6xnnacbbmypwy3flw4ja

The ability to classify patients based on gene-expression data varies by algorithm and performance metric

Stephen R. Piccolo, Avery Mecham, Nathan P. Golightly, Jérémie L. Johnson, Dustin B. Miller, Xing Chen
2022 PLoS Computational Biology  
Hyperparameter optimization and feature selection typically improved predictive performance, and univariate feature-selection algorithms typically outperformed more sophisticated methods.  ...  Together, our findings illustrate that algorithm performance varies considerably when other factors are held constant and thus that algorithm selection is a critical step in biomarker studies.  ...  We thank the Fulton Supercomputing Laboratory at Brigham Young University for providing computational facilities.  ... 
doi:10.1371/journal.pcbi.1009926 pmid:35275931 pmcid:PMC8942277 fatcat:wg7ryefkg5dalpfbmdodtxgkue

Empirical Study on Filter based Feature Selection Methods for Text Classification

Subhajit DeySarakar, Saptarsi Goswami
2013 International Journal of Computer Applications  
This paper presents an empirical study comparing performance of few feature selection techniques (Chi-squared, Information Gain, Mutual Information and Symmetrical Uncertainty) employed with different  ...  The study further allows comparing the relative performance of the classifiers and the methods.  ...  Figure-5 shows the improvement rate of the different classification algorithms using feature selection metrics and figure-6 shows the performance rate of different feature selection metrics.  ... 
doi:10.5120/14018-2173 fatcat:2wcmeve6yfgmtkxg4tzmxji5tu

Towards a software defect proneness model: feature selection

Vitaliy S. Yakovyna, Побудова моделі дефектності програм:вибір метрик, Ivan I. Symets
2021 Applied Aspects of Information Technology  
Feature Selection, Random Forest Importance, LightGBM Importance, Genetic Algorithms, Principal Component Analysis, Xverse python.  ...  procedure for predicting software defects based on metric datasets that contain a significant number of highly correlated software code metrics.  ...  However, because different projects have been used for research, and software code metrics are widely accepted and widely used in software engineering, the authors believe that the code metrics they have  ... 
doi:10.15276/aait.04.2021.5 fatcat:khzta3sz3nejtjhe3rk623gwaa

A Study of Feature Selection and Extraction Algorithms for Cancer Subtype Prediction [article]

Vaibhav Sinha, Siladitya Dash, Nazma Naskar, Sk Md Mosaddek Hossain
2021 arXiv   pre-print
In this work, we study and analyze different feature selection algorithms that can be used to classify cancer subtypes in case of highly varying high-dimensional data.  ...  Instead, we apply these algorithms sequentially which helps in lowering the computational cost and improving the predictive performance.  ...  In order to understand and compare the effects of common feature selection algorithms for predicting cancer subtypes, we aim to present a comparative study of how the effectiveness of these algorithms  ... 
arXiv:2109.14648v1 fatcat:dwcx23atnrgq3eqyrltoxk3p4m

Stochastic Embedded Probit Regressive Reweight Boost Classifier for Software Quality Examination

2019 International journal of recent technology and engineering  
The SGNE-PRRBC technique considers the number of program files as input for software quality analysis through feature selection and classification.  ...  In software development, Software quality analysis plays a considerable process. Through the software testing, the quality analysis is performed for efficient prediction of defects in the code.  ...  The designed technique performs feature selection for software quality analysis.  ... 
doi:10.35940/ijrte.c1040.1183s319 fatcat:liqdj52u2zb4zgpxsmokxkhuxa

Classification algorithms using multiple MRI features in mild traumatic brain injury

Y. W. Lui, Y. Xue, D. Kenul, Y. Ge, R. I. Grossman, Y. Wang
2014 Neurology  
Feature selection was performed using minimal-redundancy maximal-relevance.  ...  Conclusion: Multifeature analysis using diffusion-weighted imaging, MFC, fMRI, and volumetrics may aid in the classification of patients with mTBI compared with controls based on optimal feature selection  ...  In the machine learning community, it is well known that using multiple features can improve classification performance compared with a single feature alone.  ... 
doi:10.1212/wnl.0000000000000834 pmid:25171930 pmcid:PMC4180485 fatcat:vklpg6mjubexlgjr3u7mw6ub2m

STREAMLINE: A Simple, Transparent, End-To-End Automated Machine Learning Pipeline Facilitating Data Analysis and Algorithm Comparison [article]

Ryan J. Urbanowicz, Robert Zhang, Yuhan Cui, Pranshu Suri
2022 arXiv   pre-print
STREAMLINE is specifically designed to compare performance between datasets, ML algorithms, and other AutoML tools.  ...  ' hyperparameter optimization across 15 established algorithms (including less well-known Genetic Programming and rule-based ML), (8) evaluation across 16 classification metrics, (9) model feature importance  ...  We also thank the following collaborators for their feedback on application of the pipeline during development: Shannon  ... 
arXiv:2206.12002v1 fatcat:selkn3u5evhcdlmvxprstxzr4u

ANALYSIS OF SINGLE AND ENSEMBLE MACHINE LEARNING CLASSIFIERS FOR PHISHING ATTACKS DETECTION

Oyelakin A. M, Alimi O. M, Mustapha I. O, Ajiboye I. K
2021 International Journal of Software Engineering and Computer Systems  
This study carried out performance analysis of selected single and ensemble machine learning (ML) classifiers in phishing classification.The focus is to investigate how these algorithms behave in the classification  ...  Accuracy, Precision, Recall and F1-score were used as performance metrics. Logistic Regression algorithm recorded 0.86 as accuracy, 0.89 as precision, 0.87 as recall and 0.81 as F1-score.  ...  ACKNOWLEDGEMENT The authors would like to thank the anonymous reviewers for their comments which helped in improving the article.  ... 
doi:10.15282/ijsecs.7.2.2021.5.0088 fatcat:24lhlzko5vhxfntg2rwba6ygyi

A Comparative Study of Different Source Code Metrics and Machine Learning Algorithms for Predicting Change Proneness of Object Oriented Systems [article]

Lov Kumar, Ashish Sureka
2017 arXiv   pre-print
Experimental results demonstrate that the model based on selected set of source code metrics after applying feature selection techniques achieves better results as compared to the model using all source  ...  In this paper, twenty one source code metrics are computed to develop a statistical model for predicting change-proneness modules.  ...  and in the combine basis for change-proneness prediction and select a metric or group of metrics, whomsoever perform better.  ... 
arXiv:1712.07944v1 fatcat:rknexr7lcraprhiqufkm7cwe24

Artificial Intelligence for Creating Low Latency and Predictive Intrusion Detection with Security Enhancement in Power Systems

Robin Singh Bhadoria, Naman Bhoj, Hatim G. Zaini, Vivek Bisht, Md. Manzar Nezami, Ahmed Althobaiti, Sherif S. M. Ghoneim
2021 Applied Sciences  
In our research we first create a benchmark model for detecting intrusions and then employ various combinations of feature selection techniques based upon ensemble machine learning algorithms to improve  ...  The performance of our model was investigated using three evaluation metrics namely: elimination time, accuracy and F1-score.  ...  A comparative analysis of feature selection techniques was presented using elimination time as the metric.  ... 
doi:10.3390/app112411988 fatcat:brvgfr3oibffnjubo5ceea7s3m
« Previous Showing results 1 — 15 out of 439,066 results