FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W2886643713> ?p ?o ?g. }

• W2886643713 abstract "Abstract Objective To provide a parsimonious clustering pipeline that provides comparable performance to deep learning-based clustering methods, but without using deep learning algorithms, such as autoencoders. Materials and methods Clustering was performed on six benchmark datasets, consisting of five image datasets used in object, face, digit recognition tasks (COIL20, COIL100, CMU-PIE, USPS, and MNIST) and one text document dataset (REUTERS-10K) used in topic recognition. K-means, spectral clustering, Graph Regularized Non-negative Matrix Factorization, and K-means with principal components analysis algorithms were used for clustering. For each clustering algorithm, blind source separation (BSS) using Independent Component Analysis (ICA) was applied. Unsupervised feature learning (UFL) using reconstruction cost ICA (RICA) and sparse filtering (SFT) was also performed for feature extraction prior to the cluster algorithms. Clustering performance was assessed using the normalized mutual information and unsupervised clustering accuracy metrics. Results Performing, ICA BSS after the initial matrix factorization step provided the maximum clustering performance in four out of six datasets (COIL100, CMU-PIE, MNIST, and REUTERS-10K). Applying UFL as an initial processing component helped to provide the maximum performance in three out of six datasets (USPS, COIL20, and COIL100). Compared to state-of-the-art non-deep learning clustering methods, ICA BSS and/or UFL with graph-based clustering algorithms outperformed all other methods. With respect to deep learning-based clustering algorithms, the new methodology presented here obtained the following rankings: COIL20, 2nd out of 5; COIL100, 2nd out of 5; CMU-PIE, 2nd out of 5; USPS, 3rd out of 9; MNIST, 8th out of 15; and REUTERS-10K, 4th out of 5. Discussion By using only ICA BSS and UFL using RICA and SFT, clustering accuracy that is better or on par with many deep learning-based clustering algorithms was achieved. For instance, by applying ICA BSS to spectral clustering on the MNIST dataset, we obtained an accuracy of 0.882. This is better than the well-known Deep Embedded Clustering algorithm that had obtained an accuracy of 0.818 using stacked denoising autoencoders in its model. Conclusion Using the new clustering pipeline presented here, effective clustering performance can be obtained without employing deep clustering algorithms and their accompanying hyper-parameter tuning procedure." @default.
• W2886643713 created "2018-08-22" @default.
• W2886643713 creator A5078722503 @default.
• W2886643713 creator A5081476817 @default.
• W2886643713 date "2018-08-23" @default.
• W2886643713 modified "2023-10-06" @default.
• W2886643713 title "Improving clustering performance using independent component analysis and unsupervised feature learning" @default.
• W2886643713 cites W1488854477 @default.
• W2886643713 cites W180242331 @default.
• W2886643713 cites W1902027874 @default.
• W2886643713 cites W1967678928 @default.
• W2886643713 cites W1972322883 @default.
• W2886643713 cites W1985327120 @default.
• W2886643713 cites W2097922870 @default.
• W2886643713 cites W2098693229 @default.
• W2886643713 cites W2100220027 @default.
• W2886643713 cites W2100495367 @default.
• W2886643713 cites W2103402739 @default.
• W2886643713 cites W2108119513 @default.
• W2886643713 cites W2108598243 @default.
• W2886643713 cites W2117539524 @default.
• W2886643713 cites W2120303002 @default.
• W2886643713 cites W2121947440 @default.
• W2886643713 cites W2123649031 @default.
• W2886643713 cites W2128495200 @default.
• W2886643713 cites W2129793592 @default.
• W2886643713 cites W2131828344 @default.
• W2886643713 cites W2132914434 @default.
• W2886643713 cites W2135674549 @default.
• W2886643713 cites W2140499889 @default.
• W2886643713 cites W2142638745 @default.
• W2886643713 cites W2146474141 @default.
• W2886643713 cites W2147152072 @default.
• W2886643713 cites W2155759509 @default.
• W2886643713 cites W2164136210 @default.
• W2886643713 cites W2222512263 @default.
• W2886643713 cites W2386997096 @default.
• W2886643713 cites W2405933695 @default.
• W2886643713 cites W2498260651 @default.
• W2886643713 cites W2603986758 @default.
• W2886643713 cites W2608862709 @default.
• W2886643713 cites W2730106296 @default.
• W2886643713 cites W2736070576 @default.
• W2886643713 cites W2765741717 @default.
• W2886643713 cites W2777073510 @default.
• W2886643713 cites W2962852342 @default.
• W2886643713 cites W2964010455 @default.
• W2886643713 cites W3102431071 @default.
• W2886643713 cites W3105352569 @default.
• W2886643713 cites W4205778870 @default.
• W2886643713 cites W4246180809 @default.
• W2886643713 cites W4298304654 @default.
• W2886643713 cites W4300601563 @default.
• W2886643713 cites W5731987 @default.
• W2886643713 cites W82771173 @default.
• W2886643713 cites W1965566905 @default.
• W2886643713 doi "https://doi.org/10.1186/s13673-018-0148-3" @default.
• W2886643713 hasPublicationYear "2018" @default.
• W2886643713 type Work @default.
• W2886643713 sameAs 2886643713 @default.
• W2886643713 citedByCount "23" @default.
• W2886643713 countsByYear W28866437132019 @default.
• W2886643713 countsByYear W28866437132020 @default.
• W2886643713 countsByYear W28866437132021 @default.
• W2886643713 countsByYear W28866437132022 @default.
• W2886643713 countsByYear W28866437132023 @default.
• W2886643713 crossrefType "journal-article" @default.
• W2886643713 hasAuthorship W2886643713A5078722503 @default.
• W2886643713 hasAuthorship W2886643713A5081476817 @default.
• W2886643713 hasBestOaLocation W28866437131 @default.
• W2886643713 hasConcept C108583219 @default.
• W2886643713 hasConcept C138885662 @default.
• W2886643713 hasConcept C153180895 @default.
• W2886643713 hasConcept C154945302 @default.
• W2886643713 hasConcept C190502265 @default.
• W2886643713 hasConcept C27438332 @default.
• W2886643713 hasConcept C2776401178 @default.
• W2886643713 hasConcept C41008148 @default.
• W2886643713 hasConcept C41895202 @default.
• W2886643713 hasConcept C51432778 @default.
• W2886643713 hasConcept C52622490 @default.
• W2886643713 hasConcept C73555534 @default.
• W2886643713 hasConcept C8038995 @default.
• W2886643713 hasConcept C94641424 @default.
• W2886643713 hasConceptScore W2886643713C108583219 @default.
• W2886643713 hasConceptScore W2886643713C138885662 @default.
• W2886643713 hasConceptScore W2886643713C153180895 @default.
• W2886643713 hasConceptScore W2886643713C154945302 @default.
• W2886643713 hasConceptScore W2886643713C190502265 @default.
• W2886643713 hasConceptScore W2886643713C27438332 @default.
• W2886643713 hasConceptScore W2886643713C2776401178 @default.
• W2886643713 hasConceptScore W2886643713C41008148 @default.
• W2886643713 hasConceptScore W2886643713C41895202 @default.
• W2886643713 hasConceptScore W2886643713C51432778 @default.
• W2886643713 hasConceptScore W2886643713C52622490 @default.
• W2886643713 hasConceptScore W2886643713C73555534 @default.
• W2886643713 hasConceptScore W2886643713C8038995 @default.
• W2886643713 hasConceptScore W2886643713C94641424 @default.
• W2886643713 hasFunder F4320334593 @default.
• W2886643713 hasIssue "1" @default.

• next