{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,22]],"date-time":"2026-07-22T19:17:31Z","timestamp":1784747851669,"version":"3.55.0"},"reference-count":36,"publisher":"Springer Science and Business Media LLC","issue":"28","license":[{"start":{"date-parts":[[2023,4,25]],"date-time":"2023-04-25T00:00:00Z","timestamp":1682380800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2023,4,25]],"date-time":"2023-04-25T00:00:00Z","timestamp":1682380800000},"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":["Multimed Tools Appl"],"published-print":{"date-parts":[[2023,11]]},"abstract":"<jats:title>Abstract<\/jats:title><jats:p>The correct and robust recognition of traffic signs is indispensable to self-driving vehicles and driver-assistant systems. In this work, we propose and evaluate two network architectures for multi-expert decision systems that we test on a challenging Traffic Sign Recognition Benchmark dataset. The decision systems implement individual experts in the form of deep convolutional neural networks (CNNs). A gating network CNN acts as final decision unit and learns which individual expert CNNs are likely to contribute to an overall meaningful classification of a traffic sign. The gating network then selects the outputs of those individual expert CNNs to be fused to form the final decision. In this work we study the advantages and challenges of the proposed multi-expert architectures that in comparison to other network architectures allow for parallel training of individual experts with reduced datasets. Under the challenging conditions introduced by the benchmark dataset, the demonstrated multi-expert decision systems achieve a recognition performance that is superior to those of humans: with an accuracy of 99.10%, when training experts with the complete dataset and 98.94%, when individual experts are only trained with 36% of the training samples. Overall, our approach ranked fourth on the list of the applied approaches proposed for the German traffic sign Recognition Benchmark (GTSRB) dataset.<\/jats:p>","DOI":"10.1007\/s11042-023-14959-0","type":"journal-article","created":{"date-parts":[[2023,4,25]],"date-time":"2023-04-25T07:02:55Z","timestamp":1682406175000},"page":"43841-43864","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":4,"title":["Switching network for mixing experts with application to traffic sign recognition"],"prefix":"10.1007","volume":"82","author":[{"given":"Amir","family":"Ahangi","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Rico","family":"M\u00f6ckel","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2023,4,25]]},"reference":[{"issue":"5","key":"14959_CR1","doi-asserted-by":"publisher","first-page":"1319","DOI":"10.1007\/s00521-012-1074-3","volume":"23","author":"A Ahangi","year":"2013","unstructured":"Ahangi A, Karamnejad M, Mohammadi N, Ebrahimpour R, Bagheri N (2013) Multiple classifier system for eeg signal classification with application to brain\u2013computer interfaces. Neural Comput Appl 23(5):1319\u20131327. https:\/\/doi.org\/10.1007\/s00521-012-1074-3","journal-title":"Neural Comput Appl"},{"issue":"14","key":"14959_CR2","doi-asserted-by":"publisher","first-page":"20217","DOI":"10.1007\/s11042-019-7391-0","volume":"78","author":"A Ahangi","year":"2019","unstructured":"Ahangi A, Langroudi AF, Yazdanpanah F, Mirroshandel SA (2019) A novel fusion mixture of active experts algorithm for traffic signs recognition. Multimed Tools Appl 78 (14):20217\u201320237. https:\/\/doi.org\/10.1007\/s11042-019-7391-0","journal-title":"Multimed Tools Appl"},{"key":"14959_CR3","doi-asserted-by":"publisher","first-page":"158","DOI":"10.1016\/j.neunet.2018.01.005","volume":"99","author":"\u00c1 Arcos-Garc\u00eda","year":"2018","unstructured":"Arcos-Garc\u00eda \u00c1, \u00c1lvarez-Garc\u00eda JA, Soria-Morillo LM (2018) Deep neural network for traffic sign recognition systems: an analysis of spatial transformers and stochastic optimisation methods. Neural Netw 99:158\u2013165. https:\/\/doi.org\/10.1016\/j.neunet.2018.01.005","journal-title":"Neural Netw"},{"key":"14959_CR4","doi-asserted-by":"publisher","unstructured":"Ciregan D, Meier U, Schmidhuber J (2012) Multi-column deep neural networks for image classification. In: 2012 IEEE Conference on computer vision and pattern recognition, pp 3642\u20133649. https:\/\/doi.org\/10.1109\/CVPR.2012.6248110","DOI":"10.1109\/CVPR.2012.6248110"},{"key":"14959_CR5","doi-asserted-by":"publisher","unstructured":"Ciresan DC, Meier U, Gambardella LM, Schmidhuber J (2011) Convolutional neural network committees for handwritten character classification. In: 2011 International conference on document analysis and recognition, pp 1135\u20131139. https:\/\/doi.org\/10.1109\/ICDAR.2011.229","DOI":"10.1109\/ICDAR.2011.229"},{"key":"14959_CR6","doi-asserted-by":"publisher","first-page":"333","DOI":"10.1016\/j.neunet.2012.02.023","volume":"32","author":"D Cire\u015fan","year":"2012","unstructured":"Cire\u015fan D, Meier U, Masci J, Schmidhuber J (2012) Multi-column deep neural network for traffic sign classification. Neural Netw 32:333\u2013338. https:\/\/doi.org\/10.1016\/j.neunet.2012.02.023. Selected papers from IJCNN 2011","journal-title":"Neural Netw"},{"key":"14959_CR7","unstructured":"Combining pattern classifiers (2014) Methods and algorithms, 2nd edn Wiley Publishing"},{"key":"14959_CR8","doi-asserted-by":"crossref","unstructured":"Deng L, Platt JC (2014) Ensemble deep learning for speech recognition. In: Interspeech","DOI":"10.21437\/Interspeech.2014-433"},{"key":"14959_CR9","doi-asserted-by":"publisher","first-page":"165","DOI":"10.1016\/j.imavis.2016.10.006","volume":"57","author":"B Gecer","year":"2017","unstructured":"Gecer B, Azzopardi G, Petkov N (2017) Color-blob-based cosfire filters for object recognition. Image Vis Comput 57:165\u2013174. https:\/\/doi.org\/10.1016\/j.imavis.2016.10.006","journal-title":"Image Vis Comput"},{"key":"14959_CR10","doi-asserted-by":"publisher","first-page":"144","DOI":"10.4103\/2249-4863.104987","volume":"1","author":"S Gopalakrishnan","year":"2012","unstructured":"Gopalakrishnan S (2012) A public health perspective of road traffi c accidents. J Family Med Primary Care July 2012 1:144","journal-title":"J Family Med Primary Care July 2012"},{"key":"14959_CR11","unstructured":"Haloi M (2015) Traffic sign classification using deep inception based convolutional networks. CoRR arXiv:1511.02992"},{"key":"14959_CR12","doi-asserted-by":"crossref","unstructured":"He K, Zhang X, Ren S, Sun J (2016) Deep residual learning for image recognition. In: The IEEE conference on computer vision and pattern recognition (CVPR)","DOI":"10.1109\/CVPR.2016.90"},{"key":"14959_CR13","doi-asserted-by":"publisher","unstructured":"Huang GB, Lee H, Learned-Miller E (2012) Learning hierarchical representations for face verification with convolutional deep belief networks. In: 2012 IEEE conference on computer vision and pattern recognition, pp 2518\u20132525. https:\/\/doi.org\/10.1109\/CVPR.2012.6247968","DOI":"10.1109\/CVPR.2012.6247968"},{"issue":"1","key":"14959_CR14","doi-asserted-by":"publisher","first-page":"79","DOI":"10.1162\/neco.1991.3.1.79","volume":"3","author":"RA Jacobs","year":"1991","unstructured":"Jacobs RA, Jordan MI, Nowlan SJ, Hinton GE (1991) Adaptive mixtures of local experts. Neural Computat 3(1):79\u201387. https:\/\/doi.org\/10.1162\/neco.1991.3.1.79. PMID: 31141872","journal-title":"Neural Computat"},{"key":"14959_CR15","doi-asserted-by":"crossref","unstructured":"Kuncheva LI (2004) Combining pattern classifiers: methods and algorithms","DOI":"10.1002\/0471660264"},{"key":"14959_CR16","unstructured":"Kuncheva LI, Whitaker CJ (2003) Measures of diversity in classifier ensembles and their relationship with the ensemble accuracy"},{"issue":"7553","key":"14959_CR17","doi-asserted-by":"publisher","first-page":"436","DOI":"10.1038\/nature14539","volume":"521","author":"Y LeCun","year":"2015","unstructured":"LeCun Y, Bengio Y, Hinton G (2015) Deep learning. Nature Cell Biol 521(7553):436\u2013444. https:\/\/doi.org\/10.1038\/nature14539","journal-title":"Nature Cell Biol"},{"issue":"3","key":"14959_CR18","doi-asserted-by":"publisher","first-page":"50","DOI":"10.1109\/MSP.2020.2975749","volume":"37","author":"T Li","year":"2020","unstructured":"Li T, Sahu AK, Talwalkar A, Smith V (2020) Federated learning: challenges, methods, and future directions. IEEE Signal Process Mag 37(3):50\u201360. https:\/\/doi.org\/10.1109\/MSP.2020.2975749","journal-title":"IEEE Signal Process Mag"},{"key":"14959_CR19","unstructured":"Maji D, Santara A, Mitra P, Sheet D (2016) Ensemble of deep convolutional neural networks for learning to detect retinal vessels in fundus images"},{"issue":"2","key":"14959_CR20","doi-asserted-by":"publisher","first-page":"275","DOI":"10.1007\/s10462-012-9338-y","volume":"42","author":"S Masoudnia","year":"2014","unstructured":"Masoudnia S, Ebrahimpour R (2014) Mixture of experts: a literature survey. Artif Intell Rev 42(2): 275\u2013293. https:\/\/doi.org\/10.1007\/s10462-012-9338-y","journal-title":"Artif Intell Rev"},{"issue":"3","key":"14959_CR21","doi-asserted-by":"publisher","first-page":"21","DOI":"10.1109\/MCAS.2006.1688199","volume":"6","author":"R Polikar","year":"2006","unstructured":"Polikar R (2006) Ensemble based systems in decision making. IEEE Circuits Syst Mag 6(3):21\u201345. https:\/\/doi.org\/10.1109\/MCAS.2006.1688199","journal-title":"IEEE Circuits Syst Mag"},{"key":"14959_CR22","unstructured":"Powers DMW (2020) Evaluation: from precision, recall and F-measure to ROC, informedness markedness and correlation"},{"key":"14959_CR23","doi-asserted-by":"publisher","first-page":"242","DOI":"10.1016\/j.neucom.2016.06.014","volume":"214","author":"A Prieto","year":"2016","unstructured":"Prieto A, Prieto B, Ortigosa EM, Ros E, Pelayo F, Ortega J, Rojas I (2016) Neural networks: an overview of early research, current frameworks and new challenges. Neurocomputing 214:242\u2013268. https:\/\/doi.org\/10.1016\/j.neucom.2016.06.014","journal-title":"Neurocomputing"},{"key":"14959_CR24","doi-asserted-by":"publisher","first-page":"381","DOI":"10.1016\/j.patcog.2017.08.004","volume":"72","author":"R Rasti","year":"2017","unstructured":"Rasti R, Teshnehlab M, Phung SL (2017) Breast cancer diagnosis in dce-mri using mixture ensemble of convolutional neural networks. Pattern Recogn 72:381\u2013390. https:\/\/doi.org\/10.1016\/j.patcog.2017.08.004","journal-title":"Pattern Recogn"},{"key":"14959_CR25","doi-asserted-by":"publisher","first-page":"85","DOI":"10.1016\/j.neunet.2014.09.003","volume":"61","author":"J Schmidhuber","year":"2015","unstructured":"Schmidhuber J (2015) Deep learning in neural networks: an overview. Neural Netw 61:85\u2013117. https:\/\/doi.org\/10.1016\/j.neunet.2014.09.003","journal-title":"Neural Netw"},{"key":"14959_CR26","doi-asserted-by":"publisher","unstructured":"Sermanet P, LeCun Y (2011) Traffic sign recognition with multi-scale convolutional networks. In: The 2011 international joint conference on neural networks, pp 2809\u20132813. https:\/\/doi.org\/10.1109\/IJCNN.2011.6033589","DOI":"10.1109\/IJCNN.2011.6033589"},{"key":"14959_CR27","doi-asserted-by":"publisher","unstructured":"Shopa P, Sumitha N, Patra PSK (2015) Traffic sign detection and recognition using opencv. In: 2014 International conference on information communication and embedded systems, ICICES 2014. https:\/\/doi.org\/10.1109\/ICICES.2014.7033810","DOI":"10.1109\/ICICES.2014.7033810"},{"key":"14959_CR28","doi-asserted-by":"publisher","first-page":"323","DOI":"10.1016\/j.neunet.2012.02.016","volume":"32","author":"J Stallkamp","year":"2012","unstructured":"Stallkamp J, Schlipsing M, Salmen J, Igel C (2012) Man vs. computer: benchmarking machine learning algorithms for traffic sign recognition. Neural Netw 32:323\u201332. https:\/\/doi.org\/10.1016\/j.neunet.2012.02.016. Epub 2012 Feb 20. PMID:22394690","journal-title":"Neural Netw"},{"issue":"1","key":"14959_CR29","doi-asserted-by":"publisher","first-page":"77","DOI":"10.1016\/S0034-4257(97)00083-7","volume":"62","author":"SV Stehman","year":"1997","unstructured":"Stehman SV (1997) Selecting and interpreting measures of thematic classification accuracy. Remote Sens Environ 62(1):77\u201389. https:\/\/doi.org\/10.1016\/S0034-4257(97)00083-7","journal-title":"Remote Sens Environ"},{"key":"14959_CR30","doi-asserted-by":"publisher","unstructured":"Sun Z-L, Wang H, Lau W-S, Seet G, Wang D (2013) Application of bw-elm model on traffic sign recognition. Neurocomputing, vol 128. https:\/\/doi.org\/10.1016\/j.neucom.2012.11.057","DOI":"10.1016\/j.neucom.2012.11.057"},{"issue":"10","key":"14959_CR31","doi-asserted-by":"publisher","first-page":"1997","DOI":"10.1109\/TPAMI.2015.2505293","volume":"38","author":"Y Sun","year":"2016","unstructured":"Sun Y, Wang X, Tang X (2016) Hybrid deep learning for face verification. IEEE Trans Pattern Anal Mach Intell 38(10):1997\u20132009. https:\/\/doi.org\/10.1109\/TPAMI.2015.2505293","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"key":"14959_CR32","doi-asserted-by":"publisher","first-page":"56","DOI":"10.1016\/j.apenergy.2016.11.111","volume":"188","author":"H-Z Wang","year":"2017","unstructured":"Wang H-Z, Li G-Q, Wang G-B, Peng J-C, Jiang H, Liu Y-T (2017) Deep learning based ensemble approach for probabilistic wind power forecasting. Appl Energy 188:56\u201370. https:\/\/doi.org\/10.1016\/j.apenergy.2016.11.111","journal-title":"Appl Energy"},{"key":"14959_CR33","doi-asserted-by":"publisher","first-page":"16","DOI":"10.1016\/j.robot.2012.07.019","volume":"62","author":"F Zaklouta","year":"2014","unstructured":"Zaklouta F, Stanciulescu B (2014) Real-time traffic sign recognition in three stages. Robot Auton Syst 62:16\u201324. https:\/\/doi.org\/10.1016\/j.robot.2012.07.019","journal-title":"Robot Auton Syst"},{"key":"14959_CR34","doi-asserted-by":"publisher","unstructured":"Zaklouta F, Stanciulescu B, Hamdoun O (2011) Traffic sign classification using k-d trees and random forests. In: The 2011 international joint conference on neural networks, pp 2151\u20132155. https:\/\/doi.org\/10.1109\/IJCNN.2011.6033494","DOI":"10.1109\/IJCNN.2011.6033494"},{"issue":"5","key":"14959_CR35","doi-asserted-by":"publisher","first-page":"967","DOI":"10.1109\/TASLP.2016.2536478","volume":"24","author":"X Zhang","year":"2016","unstructured":"Zhang X, Wang D (2016) A deep ensemble learning method for monaural speech separation. IEEE\/ACM Trans Audio Speech Lang Process 24(5):967\u2013977. https:\/\/doi.org\/10.1109\/TASLP.2016.2536478","journal-title":"IEEE\/ACM Trans Audio Speech Lang Process"},{"key":"14959_CR36","doi-asserted-by":"crossref","unstructured":"Zhou Z-H (2012) Ensemble methods: foundations and algorithms, 1st edn Chapman & hall\/CRC","DOI":"10.1201\/b12207"}],"container-title":["Multimedia Tools and Applications"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11042-023-14959-0.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s11042-023-14959-0\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11042-023-14959-0.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,10,28]],"date-time":"2023-10-28T06:06:41Z","timestamp":1698473201000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s11042-023-14959-0"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,4,25]]},"references-count":36,"journal-issue":{"issue":"28","published-print":{"date-parts":[[2023,11]]}},"alternative-id":["14959"],"URL":"https:\/\/doi.org\/10.1007\/s11042-023-14959-0","relation":{},"ISSN":["1380-7501","1573-7721"],"issn-type":[{"value":"1380-7501","type":"print"},{"value":"1573-7721","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,4,25]]},"assertion":[{"value":"11 April 2022","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"28 September 2022","order":2,"name":"revised","label":"Revised","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"22 February 2023","order":3,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"25 April 2023","order":4,"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 no conflict of interest.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"<!--Emphasis Type='Bold' removed-->Competing interests"}}]}}