{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,1]],"date-time":"2026-03-01T08:57:24Z","timestamp":1772355444688,"version":"3.50.1"},"reference-count":32,"publisher":"Springer Science and Business Media LLC","issue":"3","license":[{"start":{"date-parts":[[2021,9,11]],"date-time":"2021-09-11T00:00:00Z","timestamp":1631318400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2021,9,11]],"date-time":"2021-09-11T00:00:00Z","timestamp":1631318400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Complex Intell. Syst."],"published-print":{"date-parts":[[2022,6]]},"abstract":"<jats:title>Abstract<\/jats:title><jats:p>Autoencoder has been widely used as a feature learning technique. In many works of autoencoder, the features of the original input are usually extracted layer by layer using multi-layer nonlinear mapping, and only the features of the last layer are used for classification or regression. Therefore, the features of the previous layer aren\u2019t used explicitly. The loss of information and waste of computation is obvious. In addition, faster training and reasoning speed is generally required in the Internet of Things applications. But the stacked autoencoders model is usually trained by the BP algorithm, which has the problem of slow convergence. To solve the above two problems, the paper proposes a dense connection pseudoinverse learning autoencoder (DensePILAE) from reuse perspective. Pseudoinverse learning autoencoder (PILAE) can extract features in the form of analytic solution, without multiple iterations. Therefore, the time cost can be greatly reduced. At the same time, the features of all the previous layers in stacked PILAE are combined as the input of next layer. In this way, the information of all the previous layers not only has no loss, but also can be strengthened and refined, so that better features could be learned. The experimental results in 8 data sets of different domains show that the proposed DensePILAE is effective.<\/jats:p>","DOI":"10.1007\/s40747-021-00516-5","type":"journal-article","created":{"date-parts":[[2021,9,11]],"date-time":"2021-09-11T02:02:20Z","timestamp":1631325740000},"page":"2039-2049","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":8,"title":["DensePILAE: a feature reuse pseudoinverse learning algorithm for deep stacked autoencoder"],"prefix":"10.1007","volume":"8","author":[{"given":"Jue","family":"Wang","sequence":"first","affiliation":[]},{"given":"Ping","family":"Guo","sequence":"additional","affiliation":[]},{"given":"Yanjun","family":"Li","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2021,9,11]]},"reference":[{"issue":"8","key":"516_CR1","doi-asserted-by":"publisher","first-page":"1798","DOI":"10.1109\/TPAMI.2013.50","volume":"35","author":"Y Bengio","year":"2013","unstructured":"Bengio Y, Courville A, Vincent P (2013) Representation learning: a review and new perspectives. IEEE Transactions on Pattern Analysis & Machine Intelligence 35(8):1798\u20131828","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"key":"516_CR2","doi-asserted-by":"crossref","unstructured":"Chang CC, Lin CJ (2011) LIBSVM: a library for support vector machines. ACM Trans Intell Syst Technol 2(3):1\u201327","DOI":"10.1145\/1961189.1961199"},{"key":"516_CR3","doi-asserted-by":"crossref","unstructured":"Deng L, Yu D, Platt J (2012) Scalable stacking and learning for building deep architectures. In: IEEE international conference on acoustics, speech and signal processing, pp 2133 \u2013 2136","DOI":"10.1109\/ICASSP.2012.6288333"},{"key":"516_CR4","doi-asserted-by":"publisher","unstructured":"Divya R, Peter JD (2021) Smart healthcare system-a brain-like computing approach for analyzing the performance of detectron2 and PoseNet models for anomalous action detection in aged people with movement impairments. Complex Intell Syst. https:\/\/doi.org\/10.1007\/s40747-021-00319-8","DOI":"10.1007\/s40747-021-00319-8"},{"key":"516_CR5","doi-asserted-by":"crossref","unstructured":"Gong D, Liu L, Le V, Saha B, Mansour MR, Venkatesh S, Hengel AVD (2019) Memorizing normality to detect anomaly: memory-augmented deep autoencoder for unsupervised anomaly detection. In: 2019 IEEE\/CVF international conference on computer vision (ICCV)","DOI":"10.1109\/ICCV.2019.00179"},{"key":"516_CR6","unstructured":"Guo P, Chen CLP, Sun Y (1995) A exact supervised learning for a three-layer supervised neural network. In: Proceedings of 1995 international conference on neural information processing"},{"key":"516_CR7","unstructured":"Guo P, Lyu MR (2001) Pseudoinverse learning algorithm for feedforward neural networks. In: Advances in neural networks and applications, pp 321\u2013326"},{"key":"516_CR8","doi-asserted-by":"crossref","unstructured":"Guo, P., Lyu, M.R.: A pseudoinverse learning algorithm for feedforward neural networks with stacked generalization applications to software reliability growth data. Neurocomputing 56(1), 101\u2013121 (2004)","DOI":"10.1016\/S0925-2312(03)00385-0"},{"key":"516_CR9","doi-asserted-by":"publisher","first-page":"27","DOI":"10.1016\/j.neucom.2015.09.116","volume":"187","author":"Y Guo","year":"2016","unstructured":"Guo Y, Liu Y, Oerlemans A, Lao S, Wu S, Lew MS (2016) Deep learning for visual understanding: A review. Neurocomputing 187:27\u201348","journal-title":"Neurocomputing"},{"key":"516_CR10","doi-asserted-by":"crossref","unstructured":"He K, Zhang X, Ren S, Sun J (2016) Deep residual learning for image recognition. In: Proceedings of the IEEE conference on computer vision and pattern recognition","DOI":"10.1109\/CVPR.2016.90"},{"key":"516_CR11","doi-asserted-by":"crossref","unstructured":"Henriquez PA, Ruz GA (2018) Twitter sentiment classification based on deep random vector functional link. In: 2018 international joint conference on neural networks (IJCNN). IEEE, Rio de Janeiro","DOI":"10.1109\/IJCNN.2018.8489703"},{"issue":"5786","key":"516_CR12","doi-asserted-by":"publisher","first-page":"504","DOI":"10.1126\/science.1127647","volume":"313","author":"GE Hinton","year":"2006","unstructured":"Hinton GE (2006) Reducing the Dimensionality of Data with Neural Networks. Science 313(5786):504\u2013507","journal-title":"Science"},{"key":"516_CR13","doi-asserted-by":"crossref","unstructured":"Huang G, Liu Z, Weinberger KQ, van\u00a0der Maaten L (2017) Densely connected convolutional networks. In: Proceedings of the IEEE conference on computer vision and pattern recognition","DOI":"10.1109\/CVPR.2017.243"},{"key":"516_CR14","unstructured":"Katuwal R, Suganthan PN, Tanveer M (2019) Random vector functional link neural network based ensemble deep learning. arXiv:1907.00350"},{"issue":"2","key":"516_CR15","doi-asserted-by":"publisher","first-page":"249","DOI":"10.1109\/TSC.2017.2662008","volume":"11","author":"C Liu","year":"2018","unstructured":"Liu C, Cao Y, Luo Y, Chen G, Vokkarane V, Yunsheng M, Chen S, Hou P (2018) A New Deep Learning-Based Food Recognition System for Dietary Assessment on An Edge Computing Service Infrastructure. Ieee Transactions on Services Computing 11(2):249\u2013261","journal-title":"IEEE Trans Serv Comput"},{"key":"516_CR16","doi-asserted-by":"crossref","unstructured":"Liu R, Tang F, Wang Y, Zheng S (2021) A modified NK algorithm based on BP neural network and DEMATEL for evolution path optimization of urban innovation ecosystem. Complex Intell Syst","DOI":"10.1007\/s40747-021-00284-2"},{"issue":"2","key":"516_CR17","doi-asserted-by":"publisher","first-page":"94","DOI":"10.1109\/MCOM.2018.1700298","volume":"56","author":"M Mohammadi","year":"2018","unstructured":"Mohammadi M, Alfuqaha A (2018) Enabling Cognitive Smart Cities Using Big Data and Machine Learning: Approaches and Challenges. IEEE Communications Magazine 56(2):94\u2013101","journal-title":"IEEE Commun Mag"},{"key":"516_CR18","doi-asserted-by":"publisher","first-page":"76","DOI":"10.1109\/2.144401","volume":"5","author":"YH Pao","year":"1992","unstructured":"Pao YH, Takefuji Y (1992) Functional-link net computing: theory, system architecture, and functionalities. IEEE Computer 5:76\u201379","journal-title":"IEEE Comput"},{"issue":"1","key":"516_CR19","doi-asserted-by":"publisher","first-page":"679","DOI":"10.1109\/JIOT.2018.2853663","volume":"6","author":"X Sun","year":"2019","unstructured":"Sun X, Gui G, Li Y, Liu RP, An Y (2019) ResInNet: A Novel Deep Neural Network With Feature Reuse for Internet of Things. IEEE Internet of Things Journal 6(1):679\u2013691","journal-title":"IEEE Internet Things J"},{"key":"516_CR20","doi-asserted-by":"crossref","unstructured":"Tian Y, Li P (2015) Predicting short-term traffic flow by long short-term memory recurrent neural network. In: IEEE international conference on smart city\/socialcom\/sustaincom","DOI":"10.1109\/SmartCity.2015.63"},{"key":"516_CR21","doi-asserted-by":"crossref","unstructured":"Vincent P, Larochelle H, Bengio Y, Manzagol PA (2008) Extracting and composing robust features with denoising autoencoders. In: Proceedings of the 25th international conference on machine learning. ACM Press, Helsinki","DOI":"10.1145\/1390156.1390294"},{"key":"516_CR22","doi-asserted-by":"crossref","unstructured":"Wang J, Guo P, Xin X (2018) Review of pseudoinverse learning algorithm for multilayer neural networks and applications. In: International symposium on neural networks. Springer, pp 99\u2013106","DOI":"10.1007\/978-3-319-92537-0_12"},{"issue":"6","key":"516_CR23","doi-asserted-by":"publisher","first-page":"3303","DOI":"10.1109\/TITS.2020.2980555","volume":"22","author":"K Wang","year":"2021","unstructured":"Wang K, Guo P (2021) An ensemble classification model with unsupervised representation learning for driving stress recognition using physiological signals. IEEE Transactions on Intelligent Transportation Systems 22(6):3303\u20133315","journal-title":"IEEE Trans Intell Transp Syst"},{"issue":"3","key":"516_CR24","doi-asserted-by":"publisher","first-page":"724","DOI":"10.1007\/s12559-021-09853-6","volume":"13","author":"K Wang","year":"2021","unstructured":"Wang K, Guo P (2021) A Robust Automated Machine Learning System with Pseudoinverse Learning. Cognitive Computation 13(3):724\u2013735","journal-title":"Cogn Comput"},{"issue":"4","key":"516_CR25","doi-asserted-by":"publisher","first-page":"4311","DOI":"10.1093\/mnras\/stw2894","volume":"465","author":"K Wang","year":"2016","unstructured":"Wang K, Guo P, Luo AL (2016) A new automated spectral feature extraction method and its application in spectral classification and defective spectra recovery. Monthly Notices of the Royal Astronomical Society 465(4):4311\u20134324","journal-title":"Mon Not R Astron Soc"},{"key":"516_CR26","doi-asserted-by":"crossref","unstructured":"Wang K, Guo P, Xin X, Ye Z (2017) Autoencoder, low rank approximation and pseudoinverse learning algorithm. In: 2017 IEEE international conference on systems, man, and cybernetics. IEEE Press, pp 948\u2013953","DOI":"10.1109\/SMC.2017.8122732"},{"key":"516_CR27","doi-asserted-by":"crossref","unstructured":"Wei X, Li J, Yuan Q, Chen K, Zhou A, Yang F (2019) Predicting fine-grained traffic conditions via spatio-temporal LSTM. Wirel Commun Mob Comput","DOI":"10.1155\/2019\/9242598"},{"key":"516_CR28","doi-asserted-by":"crossref","unstructured":"Yu F, Wang D, Shelhamer E, Darrell T (2018) Deep layer aggregation. In: 2018 IEEE\/CVF conference on computer vision and pattern recognition. IEEE, Salt Lake City, UT","DOI":"10.1109\/CVPR.2018.00255"},{"key":"516_CR29","first-page":"177","volume":"9","author":"F Zhang","year":"2018","unstructured":"Zhang F, Mao ZJ, Huang Y, Xu L, Ding G (2018) Deep learning models for EEG-based rapid serial visual presentation event classification. Journal of Information Hiding and Multimedia Signal Processing 9:177\u2013187","journal-title":"J Inf Hiding Multim Signal Process"},{"key":"516_CR30","doi-asserted-by":"crossref","unstructured":"Zhang L, Jiao L, Ma W, Duan Y, Zhang D (2019) PolSAR image classification based on multi-scale stacked sparse autoencoder. Neurocomputing 351:167\u2013179","DOI":"10.1016\/j.neucom.2019.03.024"},{"key":"516_CR31","doi-asserted-by":"crossref","unstructured":"Zhang R, Isola P, Efros AA (2017) Split-brain autoencoders: unsupervised learning by cross-channel prediction. In: 2017 IEEE conference on computer vision and pattern recognition (CVPR). IEEE, Honolulu, HI","DOI":"10.1109\/CVPR.2017.76"},{"key":"516_CR32","doi-asserted-by":"publisher","first-page":"85","DOI":"10.1016\/j.neunet.2019.01.007","volume":"112","author":"Y Zhang","year":"2019","unstructured":"Zhang Y, Wu J, Cai Z, Du B, Yu PS (2019) An unsupervised parameter learning model for RVFL neural network. Neural Networks 112:85\u201397","journal-title":"Neural Netw"}],"container-title":["Complex &amp; Intelligent Systems"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s40747-021-00516-5.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s40747-021-00516-5\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s40747-021-00516-5.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,5,30]],"date-time":"2022-05-30T01:11:01Z","timestamp":1653873061000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s40747-021-00516-5"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,9,11]]},"references-count":32,"journal-issue":{"issue":"3","published-print":{"date-parts":[[2022,6]]}},"alternative-id":["516"],"URL":"https:\/\/doi.org\/10.1007\/s40747-021-00516-5","relation":{},"ISSN":["2199-4536","2198-6053"],"issn-type":[{"value":"2199-4536","type":"print"},{"value":"2198-6053","type":"electronic"}],"subject":[],"published":{"date-parts":[[2021,9,11]]},"assertion":[{"value":"15 May 2021","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"26 August 2021","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"11 September 2021","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"The authors declare that there is no conflict of interest in this paper.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of interest"}}]}}