{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,17]],"date-time":"2026-01-17T01:58:03Z","timestamp":1768615083973,"version":"3.49.0"},"reference-count":31,"publisher":"MDPI AG","issue":"20","license":[{"start":{"date-parts":[[2020,10,14]],"date-time":"2020-10-14T00:00:00Z","timestamp":1602633600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"name":"Fundamental Research Grant Scheme (FRGS) Ministry of Higher Education (MOHE) Malaysia","award":["2019"],"award-info":[{"award-number":["2019"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Sensors"],"abstract":"<jats:p>In the modern era of digitization, the analysis in the Internet of Things (IoT) environment demands a brisk amalgamation of domains such as high-dimension (images) data sensing technologies, robust internet connection (4 G or 5 G) and dynamic (adaptive) deep learning approaches. This is required for a broad range of indispensable intelligent applications, like intelligent healthcare systems. Dynamic image classification is one of the major areas of concern for researchers, which may take place during analysis under the IoT environment. Dynamic image classification is associated with several temporal data perturbations (such as novel class arrival and class evolution issue) which cause a massive classification deterioration in the deployed classification models and make them in-effective. Therefore, this study addresses such temporal inconsistencies (novel class arrival and class evolution issue) and proposes an adapted deep learning framework (ameliorated adaptive convolutional neural network (CNN) ensemble framework), which handles novel class arrival and class evaluation issue during dynamic image classification. The proposed framework is an improved version of previous adaptive CNN ensemble with an additional online training (OT) and online classifier update (OCU) modules. An OT module is a clustering-based approach which uses the Euclidean distance and silhouette method to determine the potential new classes, whereas, the OCU updates the weights of the existing instances of the ensemble with newly arrived samples. The proposed framework showed the desirable classification improvement under non-stationary scenarios for the benchmark (CIFAR10) and real (ISIC 2019: Skin disease) data streams. Also, the proposed framework outperformed against state-of-art shallow learning and deep learning models. The results have shown the effectiveness and proven the diversity of the proposed framework to adapt the new concept changes during dynamic image classification. In future work, the authors of this study aim to develop an IoT-enabled adaptive intelligent dermoscopy device (for dermatologists). Therefore, further improvements in classification accuracy (for real dataset) is the future concern of this study.<\/jats:p>","DOI":"10.3390\/s20205811","type":"journal-article","created":{"date-parts":[[2020,10,14]],"date-time":"2020-10-14T21:24:39Z","timestamp":1602710679000},"page":"5811","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":19,"title":["An Adaptive Deep Learning Framework for Dynamic Image Classification in the Internet of Things Environment"],"prefix":"10.3390","volume":"20","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-7179-8206","authenticated-orcid":false,"given":"Syed Muslim","family":"Jameel","sequence":"first","affiliation":[{"name":"Department of Computer and Information Sciences, Universiti Teknologi PETRONAS (UTP), Seri Iskandar 32610, Malaysia"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6617-8149","authenticated-orcid":false,"given":"Manzoor Ahmed","family":"Hashmani","sequence":"additional","affiliation":[{"name":"Department of Computer and Information Sciences, Universiti Teknologi PETRONAS (UTP), Seri Iskandar 32610, Malaysia"},{"name":"Centre for Research in Data Science (CERDAS), UTP, Perak 32610, Malaysia"},{"name":"High Performance Cloud Computing Centre (HPC3), UTP, Seri Iskandar 32610, Malaysia"},{"name":"Institute of Electrical and Electronics Engineers (IEEE), New Jersey, NY 10016, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1182-2504","authenticated-orcid":false,"given":"Mobashar","family":"Rehman","sequence":"additional","affiliation":[{"name":"Faculty of Information and Communication Technology, Universiti Tunku Abdul Rahman, Kampar 31900, Malaysia"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Arif","family":"Budiman","sequence":"additional","affiliation":[{"name":"Faculty of Computer Science, University of Indonesia, West Java Depok 16424, Indonesia"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"1968","published-online":{"date-parts":[[2020,10,14]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","unstructured":"Tchernykh, A., Babenko, M., Chervyakov, N., Miranda-Lopez, V., Avetisyan, A., Drozdov, A.Y., Rivera-Rodriguez, R., Radchenko, G., and Du, Z. (2020). Scalable Data Storage Design for Non-Stationary IoT Environment with Adaptive Security and Reliability. IEEE Internet Things J., 1.","DOI":"10.1109\/JIOT.2020.2981276"},{"key":"ref_2","first-page":"195","article-title":"Survey of Real-time Processing Technologies of IoT Data Streams","volume":"24","author":"Yasumoto","year":"2016","journal-title":"J. Inf. Process."},{"key":"ref_3","unstructured":"Anwar, M., Khosla, A., and Kapoor, R. (2020, June 25). Handbook of Research on Advanced Concepts in Real-Time Image and Video Processing. IGI Global. Available online: https:\/\/dl.acm.org\/doi\/book\/10.5555\/3164781."},{"key":"ref_4","doi-asserted-by":"crossref","unstructured":"Hadidi, R., Cao, J., Woodward, M., Ryoo, M.S., and Kim, H. (2018, January 1). Real-Time Image Recognition Using Collaborative IoT Devices. Proceedings of the 1st on Reproducible Quality-Efficient Systems Tournament on Co-designing Pareto-efficient Deep Learning (ReQuEST \u201818). Association for Computing Machinery, New York, NY, USA.","DOI":"10.1145\/3229762.3229765"},{"key":"ref_5","doi-asserted-by":"crossref","first-page":"7776","DOI":"10.1109\/ACCESS.2017.2696365","article-title":"Machine Learning With Big Data: Challenges and Approaches","volume":"5","author":"Grolinger","year":"2017","journal-title":"IEEE Access"},{"key":"ref_6","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1145\/2523813","article-title":"A survey on concept drift adaptation","volume":"46","author":"Gama","year":"2014","journal-title":"ACM Comput. Surv."},{"key":"ref_7","unstructured":"Prasad, K.S.N., Rao, A.S., and Ramana, A.V. (2020). Ensemble framework for concept-drift detection in multidimensional streaming data. Int. J. Comput. Appl., 1\u20138."},{"key":"ref_8","doi-asserted-by":"crossref","unstructured":"Guzy, F., and Wozniak, M. (2020, January 19\u201324). Employing Dropout Regularization to Classify Recurring Drifted Data Streams. Proceedings of the 2020 International Joint Conference on Neural Networks, IJCNN 2020, Glasgow, UK.","DOI":"10.1109\/IJCNN48605.2020.9207266"},{"key":"ref_9","doi-asserted-by":"crossref","first-page":"804","DOI":"10.1016\/j.procs.2017.11.440","article-title":"Concept Drift in Streaming Data Classification: Algorithms, Platforms and Issues","volume":"122","author":"Janardan","year":"2007","journal-title":"Procedia Comput. Sci."},{"key":"ref_10","doi-asserted-by":"crossref","unstructured":"Bouguelia, M.R., Belaid, Y., and Belaid, A. (2014, January 24\u201328). Efficient Active Novel Class Detection for Data Stream Classification. Proceedings of the ICPR\u2014International Conference on Pattern Recognition, Stockholm, Sweden.","DOI":"10.1109\/ICPR.2014.487"},{"key":"ref_11","doi-asserted-by":"crossref","unstructured":"Saeed, F., Gazem, N., Mohammed, F., and Busalim, A. (2019). A Fully Adaptive Image Classification Approach for Industrial Revolution 4.0. Recent Trends in Data Science and Soft Computing. IRICT 2018, Springer. Advances in Intelligent Systems and, Computing.","DOI":"10.1007\/978-3-319-99007-1"},{"key":"ref_12","doi-asserted-by":"crossref","unstructured":"Jameel, S.M., Hashmani, M.A., Al Hussain, H., Rehman, M., and Budiman, A. (2019, January 19). Deleterious Effects of Uncertainty in Color Imagery Streams on Classification Models. Proceedings of the 2019 1st International Conference on Artificial Intelligence and Data Sciences (AiDAS), Ipoh, Perak, Malaysia.","DOI":"10.1109\/AiDAS47888.2019.8970757"},{"key":"ref_13","doi-asserted-by":"crossref","unstructured":"Wang, Z., Kong, Z., Changra, S., Tao, H., and Khan, L. (2019, January 8\u201311). Robust High Dimensional Stream Classification with Novel Class Detection. Proceedings of the 2019 IEEE 35th International Conference on Data Engineering (ICDE), Macao, Macao.","DOI":"10.1109\/ICDE.2019.00128"},{"key":"ref_14","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1155\/2020\/8361989","article-title":"Adaptive CNN Ensemble for Complex Multispectral Image Analysis","volume":"2020","author":"Jameel","year":"2020","journal-title":"Complexity"},{"key":"ref_15","doi-asserted-by":"crossref","first-page":"8091267-17","DOI":"10.1155\/2016\/8091267","article-title":"Adaptive Online Sequential ELM for Concept Drift Tackling","volume":"2016","author":"Budiman","year":"2016","journal-title":"Comput. Intell. Neurosci."},{"key":"ref_16","doi-asserted-by":"crossref","first-page":"67","DOI":"10.1016\/j.eswa.2018.03.021","article-title":"Adapting dynamic classifier selection for concept drift","volume":"104","author":"Almeida","year":"2018","journal-title":"Expert Syst. Appl."},{"key":"ref_17","doi-asserted-by":"crossref","unstructured":"Spinosa, E.J., Carvalho, A.P.D.L.F.D., and Gama, J. (2008, January 16\u201320). Cluster-based novel concept detection in data streams applied to intrusion detection in computer networks. Proceedings of the 2008 ACM symposium on Applied computing\u2014SAC \u201908, Cear\u00e1, Brazil.","DOI":"10.1145\/1363686.1363912"},{"key":"ref_18","doi-asserted-by":"crossref","first-page":"859","DOI":"10.1109\/TKDE.2010.61","article-title":"Classification and novel class detection in concept-drifting data streams under time constraints","volume":"23","author":"Masud","year":"2011","journal-title":"IEEE Trans. Knowl. Data Eng."},{"key":"ref_19","doi-asserted-by":"crossref","unstructured":"Haque, A., Khan, L., and Baron, M. (2016, January 12\u201317). Sand: Semi-supervised adaptive novel class detection and classification over the data stream. Proceedings of the AAAI-16: Thirtieth AAAI Conference on Artificial Intelligence, Phoenix, AZ, USA.","DOI":"10.1609\/aaai.v30i1.10283"},{"key":"ref_20","doi-asserted-by":"crossref","unstructured":"Haque, A., Khan, L., Baron, M., Thuraisingham, B., and Aggarwal, C. (2016, January 16\u201320). Efficient handling of concept drift and concept evolution over stream data. Proceedings of the 32nd IEEE International Conference on Data Engineering WorkshopsICDE, Helsinki, Finland.","DOI":"10.1109\/ICDE.2016.7498264"},{"key":"ref_21","doi-asserted-by":"crossref","unstructured":"Mu, X., Zhu, F., Du, J., Lim, E.-P., and Zhou, Z.-H. (2017, January 4\u20139). Streaming classification with emerging new class by class matrix sketching. Proceedings of the Thirty-First AAAI Conference on Artificial Intelligence (AAAI-17), San Francisco, CA, USA.","DOI":"10.1609\/aaai.v31i1.10842"},{"key":"ref_22","unstructured":"Hendrycks, D., and Gimpel, K. (2016, January 2\u20134). A baseline for detecting misclassified and out-of-distribution examples in neural networks. Proceedings of the ICLR, San Juan, Puerto Rico."},{"key":"ref_23","unstructured":"Liang, S., Li, Y., and Srikant, R. (2017, January 24\u201326). Enhancing the reliability of out-of distribution image detection in neural networks. Proceedings of the ICLR, Toulon, France."},{"key":"ref_24","unstructured":"Hinton, G., Vinyals, O., and Dean, J. (2015). Distilling the Knowledge in a Neural Network. arXiv."},{"key":"ref_25","doi-asserted-by":"crossref","unstructured":"Gao, Y., Chandra, S., Wang, Z., and Khan, L. (2018, January 19\u201323). Adaptive image stream classification via the convolutional neural network with intrinsic similarity metrics. Proceedings of the KDD Workshop, London, UK.","DOI":"10.1186\/s13640-018-0329-z"},{"key":"ref_26","unstructured":"Krizhevsky, A., and Hinton, G. (2020, June 15). Learning Multiple Layers of Features from Tiny Images. Available online: http:\/\/citeseerx.ist.psu.edu\/viewdoc\/download?doi=10.1.1.222.9220&rep=rep1&type=pdf."},{"key":"ref_27","doi-asserted-by":"crossref","unstructured":"Parker, B.S., and Khan, L. (2015, January 25\u201330). Detecting and tracking concept class drift and emergence in non-stationary fast data streams. Proceedings of the AAAI15: Twenty-Ninth Conference on Artificial Intelligence, Austin, TX, USA.","DOI":"10.1609\/aaai.v29i1.9588"},{"key":"ref_28","first-page":"281","article-title":"Random search for hyper-parameter optimization","volume":"13","author":"James","year":"2012","journal-title":"J. Mach. Learn. Res."},{"key":"ref_29","doi-asserted-by":"crossref","first-page":"317","DOI":"10.1007\/s10994-012-5320-9","article-title":"On evaluating stream learning algorithms","volume":"90","author":"Gama","year":"2012","journal-title":"Mach. Learn."},{"key":"ref_30","doi-asserted-by":"crossref","first-page":"427","DOI":"10.1016\/j.ipm.2009.03.002","article-title":"A systematic analysis of performance measures for classification tasks","volume":"45","author":"Sokolova","year":"2009","journal-title":"Inf. Process. Manag."},{"key":"ref_31","doi-asserted-by":"crossref","first-page":"1532","DOI":"10.1109\/ACCESS.2018.2886026","article-title":"An Overview on Concept Drift Learning","volume":"7","author":"Iwashita","year":"2018","journal-title":"IEEE Access"}],"container-title":["Sensors"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/1424-8220\/20\/20\/5811\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,11]],"date-time":"2025-10-11T10:21:14Z","timestamp":1760178074000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/1424-8220\/20\/20\/5811"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020,10,14]]},"references-count":31,"journal-issue":{"issue":"20","published-online":{"date-parts":[[2020,10]]}},"alternative-id":["s20205811"],"URL":"https:\/\/doi.org\/10.3390\/s20205811","relation":{},"ISSN":["1424-8220"],"issn-type":[{"value":"1424-8220","type":"electronic"}],"subject":[],"published":{"date-parts":[[2020,10,14]]}}}