The DOI matches its Crossref record; 44 of the 45 references it cites were found in a registry or an index.
Theoretical and Empirical Analysis of ReliefF and RReliefF
Open accessOverview
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Citations
Cites
Classification and Regression Trees.
Gordon, A. D., Breiman, L., Friedman, J. H., Olshen, R. A., & Stone, C. J. (1984) · Biometrics · doi:10.2307/2530946 · Cited by 23,867
(1992) · Cited by 23,431
Quinlan, J. R. (1986) · Machine Learning · doi:10.1007/bf00116251 · Cited by 21,439
Classification and Regression Trees.
Ryzin, J. V., Breiman, L., Friedman, J. H., Olshen, R. A., & Stone, C. J. (1986) · Journal of the American Statistical Association · doi:10.2307/2288003 · Cited by 21,030
Classification And Regression Trees
Breiman, L., Friedman, J. H., Olshen, R. A., & Stone, C. J. (2017) · doi:10.1201/9781315139470 · Cited by 11,417
Multidimensional binary search trees used for associative searching
Bentley, J. L. (1975) · Communications of the ACM · doi:10.1145/361002.361007 · Cited by 7,498
A Practical Approach to Feature Selection
Kira, K., & Rendell, L. A. (1992) · Elsevier eBooks · doi:10.1016/b978-1-55860-247-2.50037-1 · Cited by 3,090
Estimating attributes: Analysis and extensions of RELIEF
Kononenko, I. (1994) · Lecture notes in computer science · doi:10.1007/3-540-57868-4_57 · Cited by 3,062
Self-citationAn Algorithm for Finding Best Matches in Logarithmic Expected Time
Friedman, J. H., Bentley, J. L., & Finkel, R. A. (1977) · ACM Transactions on Mathematical Software · doi:10.1145/355744.355745 · Cited by 2,802
The feature selection problem: traditional methods and a new algorithm
Kira, K., & Rendell, L. A. (1992) · National Conference on Artificial Intelligence · Cited by 1,828
Research works printed but not linked: 6
- Dietterich, T. G. (1997). Machine learning research: Four current directions. AI Magazine, 18:4, 97-136.
- Jovanoski, V., & Lavrač, N. (1999). Feature subset selection in association rules learning systems. In M. Grobelnik, & D. Mladenič (Eds.), Prooceedings of the Conference Analysis, Warehousing and Mining the Data (AWAMIDA'99) (pp. 74-77).
- Robnik, M. (1995). Constructive induction in machine learning. Electrotehnical Review, 62:1, 43-49. (in Slovene).
- Robnik Šikonja, M. (1998). Speeding up relief algorithm with k-d trees. In Proceedings of Electrotehnical and Computer Science Conference (ERK'98) (pp. B:137-140). Portorož, Slovenia.
- Robnik Šikonja, M., & Kononenko, I. (1996). Context sensitive attribute estimation in regression. In M. Kubat, & G. Widmer (Eds.), Proceedings of ICML'96 Workshop on Learning in Context Sensitive Domains (pp. 43-52). Morgan Kaufmann.
- Vilalta, R. (1999). Understanding accuracy performance through concept characterization and algorithm analysis. In Proceedings of the ICML-99 Workshop on Recent Advances in Meta-Learning and Future Work (pp. 3-9).
Cited by
Sorted by citations
Items 101–200 of 1,004
Li, A., Xue, B., & Zhang, M. (2021) · Applied Soft Computing · doi:10.1016/j.asoc.2021.107302 · Cited by 190
A Hybrid Classification System for Heart Disease Diagnosis Based on the RFRS Method
Liu, X., Wang, X., Su, Q., Zhang, M., Zhu, Y., Wang, Q., & Wang, Q. (2017) · Computational and Mathematical Methods in Medicine · doi:10.1155/2017/8272091 · Cited by 181
Jiao, R., Nguyen, B. H., Xue, B., & Zhang, M. (2023) · IEEE Transactions on Evolutionary Computation · doi:10.1109/tevc.2023.3292527 · Cited by 197
“In order to find neighboring feature subsets with better classification performance than the current one, in [83], after mutation and crossover operations, three local search operators of insertion, deletion, and swap are proposed under the guidance of the ReliefF indicator [84].”
MethodStable feature selection via dense feature groups
Lei, Y., Ding, C. H. Q., & Loscalzo, S. (2008) · ACM SIGKDD Conference on Knowledge Discovery and Data Mining (KDD) · doi:10.1145/1401890.1401986 · Cited by 181
Hu, Q., Lei Zhang, A., Zhang, D. D., Pan, W., An, S., & Pedrycz, W. (2011) · Expert Systems with Applications · doi:10.1016/j.eswa.2011.01.023 · Cited by 179
“…1995; Pawlak & Rauszer, 1985) and fuzzy dependency in the rough set theory (Hu, Xie, & Yu, 2007), consistency in feature subset selection (Dash & Liu, 2003), Chi2 for feature selection and discretization (Liu & Setiono, 1997), Relief and ReliefF to estimate attributes (Sikonja & Kononenko, 2003).”
BackgroundOn Robust Fuzzy Rough Set Models
Hu, Q., Lei Zhang, A., An, S., et al. (2011) · IEEE Transactions on Fuzzy Systems · doi:10.1109/tfuzz.2011.2181180 · Cited by 179
“In Relief-based feature evaluation [41], the algorithm searches two nearest neighbors of each sample x: one from the same class, called nearest hit, which is denoted by NH(x), and the other from the different classes, called nearest miss, which is denoted by NM(x).”
MethodTuning ReliefF for Genome-Wide Genetic Analysis
Moore, J. H., & White, B. C. (2007) · Springer eBooks · doi:10.1007/978-3-540-71783-6_16 · Cited by 177
“For example, RReliefF [13] was developed specifically for regression problems.”
BackgroundMethodDimensionality reduction of medical big data using neural-fuzzy classifier
Azar, A. T., & Hassanien, A. E. (2014) · Soft Computing · doi:10.1007/s00500-014-1327-4 · Cited by 177
“Therefore, feature selection is an active area of research in pattern recognition (Mitra et al. 2002), machine learning (Robnik-Sikonja and Kononenko 2003), image processing (Assad et al. 2014; Inbarani et al. 2013) data mining (Gheyas and Smith 2010; Ruiz et al. 2012; Dash and Liu 2003), medical…”
BackgroundTuncer, T., Doğan, Ş., & Özyurt, F. (2020) · Chemometrics and Intelligent Laboratory Systems · doi:10.1016/j.chemolab.2020.104054 · Cited by 177
“Step 1: Calculate ReliefF weights of the features. where w R is ReliefF weights and ReliefF ð :;:;: Þ is weight calculation function of the ReliefF.”
InfluentialA selective sampling approach to active feature selection
Liu, H., Motoda, H., & Yu, L. (2004) · Artificial Intelligence · doi:10.1016/j.artint.2004.05.009 · Cited by 176
“There has been substantial research on the Relief family of algorithms (Relief, ReliefF, and RReliefF) [25, 28, 32, 33, 45, 46, 47, 48 ].”
BackgroundInfluentialReliefF-Based EEG Sensor Selection Methods for Emotion Recognition
Zhang, J., Chen, M., Zhao, S., Hu, S., Shi, Z., & Cao, Y. (2016) · Sensors · doi:10.3390/s16101558 · Cited by 177
“where, the nearby neighbor’s number k is 10, which is safe for most purposes [17] and the prior probability of class C is P(C) (estimated by the channel-selection sets).”
BackgroundMethodFeature selection and classification model construction on type 2 diabetic patients’ data
Huang, Y., McCullagh, P. J., Black, N. D., & Harper, R. (2007) · Artificial Intelligence in Medicine · doi:10.1016/j.artmed.2007.07.002 · Cited by 174
Zhang, Y., Xu, Y. H., Dong, Z. Y., & Zhang, R. (2018) · IEEE Transactions on Industrial Informatics · doi:10.1109/tii.2018.2829818 · Cited by 175
“The feature selection algorithm used in this paper is RELIEFF [32], [33] which is a distance-based algorithm recognizing fea-”
MethodEffective Discriminative Feature Selection With Nontrivial Solution
Tao, H., Hou, C., Nie, F., et al. (2015) · IEEE Transactions on Neural Networks and Learning Systems · doi:10.1109/tnnls.2015.2424721 · Cited by 173
Novel Audio Features for Music Emotion Recognition
Panda, R., Malheiro, R., & Paiva, R. P. (2018) · IEEE Transactions on Affective Computing · doi:10.1109/taffc.2018.2820691 · Cited by 186
A decision tree-based attribute weighting filter for naive Bayes
Hall, M. (2006) · Knowledge-Based Systems · doi:10.1016/j.knosys.2006.11.008 · Cited by 171
“of the former include Salzberg’s EACH system [23], Aha’s IB4 [1], The Relief system and its extensions [14, 22] and the DIET scheme [16] (which, unlike the other methods, restricts the weight space to a small user-selectable set of discrete values).”
MethodMachine Learning Based on Attribute Interactions
Jakulin, A. (2005) · Repository of the University of Ljubljana (University of Ljubljana) · Cited by 182
Feature Selection by Maximizing Independent Classification Information
Wang, J., Wei, J., Yang, Z., et al. (2017) · IEEE Transactions on Knowledge and Data Engineering · doi:10.1109/tkde.2017.2650906 · Cited by 170
“In this section, MRI is compared with several popular nonmutual-information-based feature selection approaches, i.e., Laplacian Score [30], Inf-FS [31], ReliefF [32], SPEC [33], and SPFS [34].”
MethodInfluentialA Novel Approach to Monitor Rehabilitation Outcomes in Stroke Survivors Using Wearable Technology
Patel, S., Hughes, R., Hester, T., Stein, J., Akay, M., Dy, J. G., & Bonato, P. (2010) · Proceedings of the IEEE · doi:10.1109/jproc.2009.2038727 · Cited by 170
“First, we used the ReliefF [ 27 ] algorithm which ranks the features in decreasing order of importance.”
MethodImproving EEG-Based Emotion Classification Using Conditional Transfer Learning
Lin, Y., & Jung, T. (2017) · Frontiers in Human Neuroscience · doi:10.3389/fnhum.2017.00334 · Cited by 168
“Using 15 training trials to form the TS’s feature space using ReliefF and calculating correlation coefficient values between this space to the space of each of n SSs ( n = 25 in this study).”
MethodInfluentialSelf-adaptive differential evolution for feature selection in hyperspectral image data
Ghosh, A. K., Datta, A., & Ghosh, S. (2012) · Applied Soft Computing · doi:10.1016/j.asoc.2012.11.042 · Cited by 166
Online feature selection for high-dimensional class-imbalanced data
Zhou, P., Hu, X., Li, P., & Wu, X. (2017) · Knowledge-Based Systems · doi:10.1016/j.knosys.2017.09.006 · Cited by 163
Near real-time wind speed forecast model with bidirectional LSTM networks
Joseph, L. P., Deo, R. C., Prasad, R., Salcedo‐Sanz, S., Raj, N., & Soar, J. (2023) · Renewable Energy · doi:10.1016/j.renene.2022.12.123 · Cited by 172
Feature Selection for High-Dimensional Data — A Pearson Redundancy Based Filter
Biesiada, J., & Duch, W. (2007) · Advances in intelligent and soft computing · doi:10.1007/978-3-540-75175-5_30 · Cited by 161
“The PRBF and the C onnSF [7] algorithms had no problem with this task, but FCBF [6] selected only 3 fea tures, CorrSF [5] selected only first two, and ReliefF [8] left only feature 1 an d 5, giving them both the same weight 0.”
MethodInfluentialDeng, X., Li, M., Deng, S., & Wang, L. (2022) · Medical & Biological Engineering & Computing · doi:10.1007/s11517-021-02476-x · Cited by 161
Memetic feature selection algorithm for multi-label classification
Lee, J., & Kim, D. (2014) · Information Sciences · doi:10.1016/j.ins.2014.09.020 · Cited by 160
“CHI [33], LP + RF [26], ELA + CHI [2] (we represent these methods as problem transformation + score function, for example, the score CHI indicates v2 statistics, and RF represents ReliefF [24]), RFS [20], gMLC [15], GA [34], Estimation of Distribution Algorithm (EDA) [25], and Particle Swarm Optimization (PSO) [31].”
MethodFiltering techniques for channel selection in motor imagery EEG applications: a survey
Baig, M. Z., Aslam, N., & Shum, H. P. H. (2019) · Artificial Intelligence Review · doi:10.1007/s10462-019-09694-8 · Cited by 160
Regularized Machine Learning in the Genetic Prediction of Complex Traits
Okser, S., Pahikkala, T., Airola, A., Salakoski, T., Ripatti, S., & Aittokallio, T. A. (2014) · PLoS Genetics · doi:10.1371/journal.pgen.1004754 · Cited by 158
“Whereas classical, univariate filter methods evaluate the relevance of each genetic feature independently of the others, more advanced multivariate filters have also been proposed, including the Relief family of approaches [101].”
MethodEmotion Recognition From Body Movement
Ahmed, F., Bari, A. S. M. H., & Gavrilova, M. L. (2019) · IEEE Access · doi:10.1109/access.2019.2963113 · Cited by 156
“The closest second algorithmwas ReliefFwith neighbor size 30.”
MethodInfluentialAutomated Action Recognition Using an Accelerometer-Embedded Wristband-Type Activity Tracker
Ryu, J., Seo, J., Jebelli, H., & Lee, S. H. (2018) · Journal of Construction Engineering and Management · doi:10.1061/(asce)co.1943-7862.0001579 · Cited by 156
ARX model based fault detection and diagnosis for chillers using support vector machines
Yan, K., Shen, W., Mulumba, T., et al. (2014) · Energy and Buildings · doi:10.1016/j.enbuild.2014.05.049 · Cited by 154
“(2) Using ReliefF to select most important features, dependent and inde- pendent variables are chosen, respectively.”
MethodInfluentialInstance spaces for machine learning classification
Muñoz, M. A., Villanova, L., Baatar, D., & Smith‐Miles, K. (2017) · Machine Learning · doi:10.1007/s10994-017-5629-5 · Cited by 150
“Concept characterization features were shown to provide much information about the difficulty of problem instances (Vilalta 1999; Robnik-Šikonja and Kononenko 2003).”
BackgroundTowards Effective Bug Triage with Software Data Reduction Techniques
Xuan, J., Jiang, H., Hu, Y., et al. (2014) · IEEE Transactions on Knowledge and Data Engineering · doi:10.1109/tkde.2014.2324590 · Cited by 149
Yan, K., Ji, Z., & Shen, W. (2016) · Neurocomputing · doi:10.1016/j.neucom.2016.09.076 · Cited by 149
“In our previous works [8,22], the ReliefF method [40,41] is employed to select features with maximal information.”
MethodNon-intrusive human activity recognition and abnormal behavior detection on elderly people: a review
Lentzas, A., & Vrakas, D. (2019) · Artificial Intelligence Review · doi:10.1007/s10462-019-09724-5 · Cited by 152
“Some of the feature selection methods used in activity recognition are ReliefF, an algorithm ranking features based on relevance (Robnik-Šikonja and Kononenko 2003) and Correlation based Feature Selection (CFS), a technique using a heuristic evaluation function based on correlation to rank feature…”
BackgroundMethodA survey about methods dedicated to epistasis detection
Niel, C., Sinoquet, C., Christian Dina, C., & Rocheleau, G. (2015) · Frontiers in Genetics · doi:10.3389/fgene.2015.00285 · Cited by 147
“ReliefF approach consists in learning informative features from the dataset without any a priori knowledge (Robnik-Šikonja and Kononenko, 2003).”
MethodDevelopment and evaluation of a comprehensive drought index
Esfahanian, E., Nejadhashemi, A. P., Abouali, M., Adhikari, U., Zhang, Z., Daneshvar, F., & Herman, M. R. (2016) · Journal of Environmental Management · doi:10.1016/j.jenvman.2016.10.050 · Cited by 147
Aniceto, N., Freitas, A. A., Bender, A., & Ghafourian, T. (2016) · Journal of Cheminformatics · doi:10.1186/s13321-016-0182-y · Cited by 151
“ReliefF has been shown to detect relevant features even in very crowded (featurewise) datasets, whilst being resilient to noise [18, 19].”
BackgroundAttribute reduction for multi-label learning with fuzzy rough set
Lin, Y., Li, Y., Wang, C., & Chen, J. (2018) · Knowledge-Based Systems · doi:10.1016/j.knosys.2018.04.004 · Cited by 147
Niu, T., Wang, J., Lu, H., Yang, W., & Du, P. (2020) · Expert Systems with Applications · doi:10.1016/j.eswa.2020.113237 · Cited by 149
Modeling readability to improve unit tests
Daka, E., Campos, J., Fraser, G., Dorn, J. G., & Weimer, W. R. (2015) · ACM Joint European Software Engineering Conference and Symposium on the Foundations of Software Engineering (ESEC/FSE) · doi:10.1145/2786805.2786838 · Cited by 146
“Finally, we also applied the Relief-F method [36], which agrees with the one-feature-at-a-time analysis and is thus omitted for brevity.”
MethodRobust Feature Selection for Microarray Data Based on Multicriterion Fusion
Yang, F., & Mao, K. (2010) · IEEE Transactions on Computational Biology and Bioinformatics · doi:10.1109/tcbb.2010.103 · Cited by 147
“Relief is a weight-based feature ranking method inspired by the instance-based learning [32].”
MethodSpatially Uniform ReliefF (SURF) for computationally-efficient filtering of gene-gene interactions
Greene, C. S., Penrod, N. M., Kiralis, J., & Moore, J. H. (2009) · BioData Mining · doi:10.1186/1756-0381-2-5 · Cited by 147
“With Regression ReliefF (RReliefF), ReliefF is broadened to handle continuous attributes and endpoints [23,24].”
MethodA novel hybrid feature selection method based on dynamic feature importance
Wei, G., Zhao, J., Feng, Y., He, A., & Yu, J. (2020) · Applied Soft Computing · doi:10.1016/j.asoc.2020.106337 · Cited by 150
Feature Selection Based on High Dimensional Model Representation for Hyperspectral Images
Taşkın, G., Kaya, H., & Bruzzone, L. (2017) · IEEE Transactions on Image Processing · doi:10.1109/tip.2017.2687128 · Cited by 142
“The parameters of the SVM-RFE and ReliefF methods are optimally selected based on 5-fold cross validation.”
MethodInfluentialDay-ahead electricity price forecasting by modified relief algorithm and hybrid neural network
Amjady, N., Daraeepour, A., & Keynia, F. (2010) · IET Generation Transmission & Distribution · doi:10.1049/iet-gtd.2009.0297 · Cited by 141
“The original Relief algorithm randomly chooses a number of training samples from the training set (this parameter is user-defined) [21, 24].”
BackgroundHoang, N., Nguyen, Q.-L., & Bui, D. T. (2018) · Journal of Computing in Civil Engineering · doi:10.1061/(asce)cp.1943-5487.0000781 · Cited by 141
Machine learning techniques for quality control in high conformance manufacturing environment
Escobar, C. A., & Morales-Menéndez, R. (2018) · Advances in Mechanical Engineering · doi:10.1177/1687814018755519 · Cited by 140
Sitokonstantinou, V., Papoutsis, I., Kontoes, C., Arnal, A. L., Andrés, A. P. A., & Zurbano, J. A. G. (2018) · Remote Sensing · doi:10.3390/rs10060911 · Cited by 140
“The contribution of all hits and misses is averaged, with a contribution weight for each class of the misses being dependent on the prior probability of that class [39].”
BackgroundSadeghian, Z., Akbari, E., & Nematzadeh, H. (2020) · Engineering Applications of Artificial Intelligence · doi:10.1016/j.engappai.2020.104079 · Cited by 140
Feature Selection with Linked Data in Social Media
Tang, J., & Liu, H. (2012) · SIAM International Conference on Data Mining · doi:10.1137/1.9781611972825.11 · Cited by 138
Local contrast phase descriptor for fingerprint liveness detection
Gragnaniello, D., Poggi, G., Sansone, C., & Verdoliva, L. (2014) · Pattern Recognition · doi:10.1016/j.patcog.2014.05.021 · Cited by 135
“For feature selection we used the ReliefF algorithm [53], which is very simple and effective in problems with strong dependencies between features, while a SVM with a linear kernel and C1⁄41 is used as a classifier.”
MethodMulti-Sensor Fusion Approach for Cuff-Less Blood Pressure Measurement
Miao, F., Liu, Z.-D., Liu, J., Wen, B., He, Q., & Li, Y. (2019) · IEEE Journal of Biomedical and Health Informatics · doi:10.1109/jbhi.2019.2901724 · Cited by 137
“[51] M. Robnik-Šikonja and I. Kononenko, “Theoretical and empirical analysis of ReliefF and RReliefF,” Mach.”
MethodAn Efficient Marine Predators Algorithm for Feature Selection
Elminaam, D. S. A., Nabil, A. M., Ibraheem, S. A. A., & Houssein, E. H. (2021) · IEEE Access · doi:10.1109/access.2021.3073261 · Cited by 139
“Some of the popular filter models include Chi-Square [12], information Gain (IG) [13], Gain Ratio [14], and ReliefF [15].”
MethodAnalysis and comparison of feature selection methods towards performance and stability
Barbieri, M., Grisci, B. I., & Dorn, M. (2024) · Expert Systems with Applications · doi:10.1016/j.eswa.2024.123667 · Cited by 161
Robust model-based fault diagnosis for air handling units
Mulumba, T., Afshari, A., Yan, K., et al. (2014) · Energy and Buildings · doi:10.1016/j.enbuild.2014.10.069 · Cited by 134
Paniri, M., Dowlatshahi, M. B., & Nezamabadi–pour, H. (2021) · Swarm and Evolutionary Computation · doi:10.1016/j.swevo.2021.100892 · Cited by 134
Wu, G., Fang, Y., Jiang, Q., et al. (2022) · Computers and Electronics in Agriculture · doi:10.1016/j.compag.2022.107553 · Cited by 134
Identifying Fake News on Social Networks Based on Natural Language Processing: Trends and Challenges
de Oliveira, N. R., Pisa, P. S., Lopez, M. A., Medeiros, D. S. V., & Mattos, D. M. F. (2021) · Information · doi:10.3390/info12010038 · Cited by 149
“Relief is limited to problems with only two classes, but ReliefF [61] is an improvement on the Relief method that handles multiple classes using the nearest neighboring k technique.”
MethodHoang, N., & Van-Duc, T. (2023) · Automation in Construction · doi:10.1016/j.autcon.2023.104767 · Cited by 154
Nguyen, B. H., Xue, B., Andreae, P. M., Ishibuchi, H., & Zhang, M. (2019) · IEEE Transactions on Evolutionary Computation · doi:10.1109/tevc.2019.2913831 · Cited by 131
“algorithms: 1) mRMR (information-based) [37]; 2) reliefF (similarity-based) [38]; 3) CFS (correlation-based) [39]; and Algorithm 3: Pseudocode of MOEA/D-STAT”
A new time–frequency method for identification and classification of ball bearing faults
Attoui, I., Fergani, N., Boutasseta, N., et al. (2017) · Journal of Sound and Vibration · doi:10.1016/j.jsv.2017.02.041 · Cited by 129
Wieland, M., & Pittore, M. (2014) · Remote Sensing · doi:10.3390/rs6042912 · Cited by 128
“The number of nearest neighbors has been set to k = 10 as suggested in [42] and the number of iterations has been set to m = all instances .”
Ranking-Based Emotion Recognition for Music Organization and Retrieval
Yang, Y., & Chen, H. H. (2010) · IEEE Transactions on Audio Speech and Language Processing · doi:10.1109/tasl.2010.2064164 · Cited by 131
Tuncer, T., Doğan, Ş., Özyurt, F., Belhouari, S. B., & Bensmail, H. (2020) · IEEE Access · doi:10.1109/access.2020.2992641 · Cited by 128
“Similar to ReliefF [42], NCA weights are calculated, sorted by descending order.”
MethodGökalp, O., Taşçı, E., & Uğur, A. (2020) · Expert Systems with Applications · doi:10.1016/j.eswa.2020.113176 · Cited by 127
Wind Power Forecasting Using Neural Network Ensembles With Feature Selection
Song, L., Wang, P., & Goel, L. (2015) · IEEE Transactions on Sustainable Energy · doi:10.1109/tste.2015.2441747 · Cited by 127
“The benchmark methods in Table II include correlation analysis (CA), MI, RReliefF [39], and minimum redundancy maximum relevance (mRMR) [40].”
MethodGeiß, C., Pelizari, P. A., Marconcini, M., Sengara, W., Edwards, M., Lakes, T., & Taubenböck, H. (2014) · ISPRS Journal of Photogrammetry and Remote Sensing · doi:10.1016/j.isprsjprs.2014.07.016 · Cited by 132
“…that useful features should differentiate between instances from different classes and have similar values for instances from the same class, RelF (Kononenko, 1994, Robnik-Šikonja and Kononenko, 2003) ranks features according to their ability to discriminate between neighboring instances.”
BackgroundA comparison of feature ranking techniques for fault diagnosis of ball bearing
Vakharia, V., Gupta, V. K., & Kankar, P. K. (2015) · Soft Computing · doi:10.1007/s00500-015-1608-6 · Cited by 126
Unsupervised Streaming Feature Selection in Social Media
Li, J., Hu, X., Tang, J., & Liu, H. (2015) · ACM International Conference on Information and Knowledge Management (CIKM) · doi:10.1145/2806416.2806501 · Cited by 127
“Filter methods are independent of any learning algorithms and are thereby very efficient, they rely on some data characteristics such as distance, consistency, dependency, information, and correlation to measure the strength of each feature individually [13, 16, 25, 28].”
BackgroundZhang, Y., Xu, Y. H., Dong, Z. Y., Xu, Z., & Wong, K. P. (2017) · IEEE Transactions on Industrial Informatics · doi:10.1109/tii.2017.2676879 · Cited by 126
“The mathematical details of RELIEFF can be found in [16], [31], and [32].”
BackgroundFeature selection based on FDA and F-score for multi-class classification
Song, Q., Jiang, H., & Liu, J. (2017) · Expert Systems with Applications · doi:10.1016/j.eswa.2017.02.049 · Cited by 127
“In filter methods, a number of criteria have been proposed for feature selection, such as, Fisher score (Yjlmaz, 2013), ReliefF(Robnik-Šikonja & Kononenko, 2003), Laplacian score (Wan et al.,2015), F-score (Chen & Lin,2003), among which F-score is one of the simplest criteria.”
MethodAçıkgöz, H. (2021) · Applied Energy · doi:10.1016/j.apenergy.2021.117912 · Cited by 125
Xue, Y., Cai, X., & Neri, F. (2022) · Applied Soft Computing · doi:10.1016/j.asoc.2022.109420 · Cited by 123
Bernardini, M., Romeo, L., Misericordia, P., & Frontoni, E. (2019) · IEEE Journal of Biomedical and Health Informatics · doi:10.1109/jbhi.2019.2899218 · Cited by 126
“Differently the wrapper feature selection approaches [16] can result in an external module with an increment of computational effort (e.g., beam search, sequential forward selection, sequential backward elimination) for the training and validation stage, while the filter methodologies [14]–[17] rely on the evaluation…”
MethodInfluentialBhattacharyya, R. P., Bandyopadhyay, N., Ma, P., Son, S. S., Liu, J., He, L. L., Wu, L., Khafizov, R., Boykin, R., Cerqueira, G. C., et al. (2019) · Nature Medicine · doi:10.1038/s41591-019-0650-9 · Cited by 125
A new matching strategy for content based image retrieval system
ElAlami, M. E. (2013) · Applied Soft Computing · doi:10.1016/j.asoc.2013.10.003 · Cited by 120
Predicting Epileptic Seizures in Advance
Moghim, N., & Corne, D. (2014) · PLoS ONE · doi:10.1371/journal.pone.0099334 · Cited by 128
“The computational complexity of ReliefF is suitable for large datasets, being O(n6f ) [53], where n is the number of data instances and f is the number of features.”
BackgroundMethodWind turbine fault diagnosis based on ReliefF-PCA and DNN
Wen, X., & Xu, Z. (2021) · Expert Systems with Applications · doi:10.1016/j.eswa.2021.115016 · Cited by 120
Detecting user engagement in everyday conversations
Yu, C., Aoki, P. M., & Woodruff, A. (2004) · Interspeech (USB) · doi:10.21437/interspeech.2004-327 · Cited by 120
“We transformed the original feature space into a lower dimensional space by using the RELIEF-F algorithm for feature selection [8].”
MethodSequence dependence of isothermal DNA amplification via EXPAR
Qian, J., Ferguson, T. M., Shinde, D. N., et al. (2012) · Nucleic Acids Research · doi:10.1093/nar/gks230 · Cited by 120
“In the training process, important features were selected from the training set using RELIEF attribute evaluation (51).”
MethodImproving the ranking quality of medical image retrieval using a genetic feature selection method
da Silva, S. F., Ribeiro, M. X., Neto, J. D. E. S. B., Traina, C., & Traina, A. J. M. (2011) · Decision Support Systems · doi:10.1016/j.dss.2011.01.015 · Cited by 116
“ReliefF [27] estimates the quality of a feature set computing how well they discriminate instances that are near to each other.”
BackgroundHuynh‐Thu, V. A., Saeys, Y., Wehenkel, L. A., & Geurts, P. (2012) · Bioinformatics · doi:10.1093/bioinformatics/bts238 · Cited by 124
“Obvious future works include the application of the feature selection methods to other popular machine learning-based ranking methods such as for example Relief (Robnik-Sikonja and Kononenko, 2003).”
MethodA Novel Framework of Reservoir Computing for Deterministic and Probabilistic Wind Power Forecasting
Wang, J., Niu, T., Lu, H., Yang, W., & Du, P. (2019) · IEEE Transactions on Sustainable Energy · doi:10.1109/tste.2019.2890875 · Cited by 119
“In this study, RReliefF algorithm cooperated with GCRT [31] was developed in the feature selection module.”
BackgroundMethodInfluentialA novel multi population based particle swarm optimization for feature selection
Kılıç, F., Kaya, Y., & Yıldırım, S. (2021) · Knowledge-Based Systems · doi:10.1016/j.knosys.2021.106894 · Cited by 117
O'Dwyer, L., Lamberton, F., Bokde, A. L. W., Ewers, M., Faluyi, Y. O., Tanner, C., Mazoyer, B., O'Neill, D., Bartley, M., Collins, D. R., et al. (2012) · PLoS ONE · doi:10.1371/journal.pone.0032441 · Cited by 117
A P2P Botnet detection scheme based on decision tree and adaptive multilayer neural networks
Alauthman, M., Aslam, N., Zhang, L., Alasem, R., & Hossain, M. A. (2016) · Neural Computing and Applications · doi:10.1007/s00521-016-2564-5 · Cited by 117
Why Is the Electronic Health Record So Challenging for Research and Clinical Care?
Holmes, J., Beinlich, J., Boland, M., Bowles, K., Chen, Y., Cook, T., Demiris, G., Draugelis, M., Fluharty, L., Gabriel, P., et al. (2021) · Methods of Information in Medicine · doi:10.1055/s-0041-1731784 · Cited by 115
“95 This is one of many potential sources of bias that can impact ML performance.”
BackgroundStability of Feature Selection Algorithms
Kalousis, A., Prados, J., & Hilario, M. (2006) · Proceedings · doi:10.1109/icdm.2005.135 · Cited by 121
Capdehourat, G., Corez, A., Bazzano, A., et al. (2011) · Pattern Recognition Letters · doi:10.1016/j.patrec.2011.06.015 · Cited by 116
“Feature selection is performed using ReliefF (Robnik-Šikonja and Kononenko, 2003) and CFS algorithms (Hall, 2000).”
MethodShort-term wind power forecasts by a synthetical similar time series data mining method
Sun, G., Jiang, C., Cheng, P., Liu, Y., Wang, X., Fu, Y., & Yang, H. (2017) · Renewable Energy · doi:10.1016/j.renene.2017.08.071 · Cited by 116
Binary Horse herd optimization algorithm with crossover operators for feature selection
Awadallah, M. A., Hammouri, A. I., Al‐Betar, M. A., Braik, M. S., & Elaziz, M. A. (2021) · Computers in Biology and Medicine · doi:10.1016/j.compbiomed.2021.105152 · Cited by 116
Peker, M., Şen, B., & Delen, D. (2015) · Journal of Healthcare Engineering · doi:10.1260/2040-2295.6.3.281 · Cited by 115
“Specifically, this algorithm changes the weight of feature conformity/value using the nearest neighbor algorithm [43].”
MethodBocca, F. F., & Rodrigues, L. H. A. (2016) · Computers and Electronics in Agriculture · doi:10.1016/j.compag.2016.08.015 · Cited by 115
Feature Selection: Filter Methods Performance Challenges
Cherrington, M., Thabtah, F., Lu, J., et al. (2019) · doi:10.1109/iccisci.2019.8716478 · Cited by 115
“Additionally, the number of key features to be chosen is highly dependent on having a sufficient number of examples to sufficiently cover the hypothesis space [14].”
BackgroundMethodInfluentialXia, Y., Xu, Y. H., & Gou, B. (2019) · IEEE Transactions on Industrial Informatics · doi:10.1109/tii.2019.2949344 · Cited by 115
Biomedical Potentials of Crown Ethers: Prospective Antitumor Agents
Kralj, M., Tušek‐Božić, L., & Frkanec, L. (2008) · ChemMedChem · doi:10.1002/cmdc.200800118 · Cited by 115
Choosing Feature Selection and Learning Algorithms in QSAR
Eklund, M., Norinder, U., Boyer, S. K., & Carlsson, L. (2014) · Journal of Chemical Information and Modeling · doi:10.1021/ci400573c · Cited by 113
Pes, B., Dessì, N., & Angioni, M. (2016) · Information Fusion · doi:10.1016/j.inffus.2016.10.001 · Cited by 119
Feature Selection for Dimensionality Reduction
Mladenić, D. (2006) · Lecture notes in computer science · doi:10.1007/11752790_5 · Cited by 114
“Some theoretical and empirical analysis of the algorithm and its extensions is provided in [ 55 ].”
Background
Metadata
- Authors
- Robnik-Šikonja, M., & Kononenko, I.
- Affiliations
- University of Ljubljana (SI)
- ORCID
- Kononenko, Igor
- Venue
- Machine Learning
- Published
- 2003-10
- Volume
- 53
- Issue
- 1-2
- Pages
- 23-69
- ISSN
- 0885-6125 (ISSN-L)
- 1573-0565
- OpenAlex
- W1500895378
- Semantic Scholar
- d398ad942320c1c2cf64da23ba519870f9f1d67d
- Cited by
- 3,025
- References
- 45
- Citations by year
- 2026: 125 · 2025: 186 · 2024: 192 · 2023: 209 · 2022: 223 · 2021: 246 · 2020: 237 · 2019: 212 · 2018: 216 · 2017: 150 · 2016: 158 · 2015: 166 · 2014: 143 · 2013: 91 · 2012: 105
- FWCI
- 44.71
- Type
- journal article
- Language
- en
- Open access
- bronze
- doi.org
- Licence
- Locations
- Machine Learning (publishedVersion)
- Topics
- Physical Sciences › Computer Science › Information Systems › Data Mining Algorithms and Applications
- Physical Sciences › Computer Science › Artificial Intelligence › Machine Learning and Data Classification
- Physical Sciences › Computer Science › Computational Theory and Mathematics › Rough Sets and Fuzzy Logic
- Keywords
- Relief algorithm, RReliefF, feature selection, feature weighting, decision tree splitting, inductive logic programming, noise robustness, scalability, data sampling
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
