{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,6]],"date-time":"2026-03-06T21:12:05Z","timestamp":1772831525777,"version":"3.50.1"},"reference-count":44,"publisher":"Springer Science and Business Media LLC","issue":"11","license":[{"start":{"date-parts":[[2024,8,16]],"date-time":"2024-08-16T00:00:00Z","timestamp":1723766400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,8,16]],"date-time":"2024-08-16T00:00:00Z","timestamp":1723766400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Computing"],"published-print":{"date-parts":[[2024,11]]},"DOI":"10.1007\/s00607-024-01338-2","type":"journal-article","created":{"date-parts":[[2024,8,16]],"date-time":"2024-08-16T15:02:18Z","timestamp":1723820538000},"page":"3727-3753","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":3,"title":["Data and resource aware incremental ML training in support of pervasive applications"],"prefix":"10.1007","volume":"106","author":[{"given":"Thanasis","family":"Moustakas","sequence":"first","affiliation":[]},{"given":"Athanasios","family":"Tziouvaras","sequence":"additional","affiliation":[]},{"given":"Kostas","family":"Kolomvatsos","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2024,8,16]]},"reference":[{"key":"1338_CR1","doi-asserted-by":"publisher","unstructured":"Kurkovsky S (2007) Pervasive computing: past, present and future. In: 5th ITI international conference on information and communications technology, Cairo, Egypt, 65\u201371. https:\/\/doi.org\/10.1109\/ITICT.2007.4475619","DOI":"10.1109\/ITICT.2007.4475619"},{"key":"1338_CR2","doi-asserted-by":"publisher","first-page":"193","DOI":"10.1016\/j.future.2022.05.018","volume":"136","author":"K Kolomvatsos","year":"2022","unstructured":"Kolomvatsos K (2022) A proactive inference scheme for data-aware decision making in support of pervasive applications. Fut Gener Comput Syst 136:193\u2013204","journal-title":"Fut Gener Comput Syst"},{"key":"1338_CR3","doi-asserted-by":"publisher","first-page":"110","DOI":"10.1109\/MCOM.2018.1700906","volume":"56","author":"S Najam","year":"2018","unstructured":"Najam S et al (2018) The role of edge computing in internet of things. IEEE Commun Mag 56:110\u2013115","journal-title":"IEEE Commun Mag"},{"issue":"3","key":"1338_CR4","first-page":"2231","volume":"2","author":"OM Elzeki","year":"2012","unstructured":"Elzeki OM et al (2012) Overview of scheduling tasks in distributed computing systems. Int J Soft Comput Eng (IJSCE) 2(3):2231\u20132307","journal-title":"Int J Soft Comput Eng (IJSCE)"},{"key":"1338_CR5","doi-asserted-by":"crossref","unstructured":"Hsieh L-TH (2020) Task management for cooperative mobile edge computing. In: 2020 IEEE\/ACM Symposium on edge computing (SEC). San Jose, CA, USA 2020, pp 352\u2013357","DOI":"10.1109\/SEC50012.2020.00051"},{"key":"1338_CR6","doi-asserted-by":"crossref","unstructured":"Karanika A, Oikonomou P, Kolomvatsos K, Loukopoulos T (2020) A demand-driven, proactive tasks management model at the edge. In: IEEE FUZZ-IEEE","DOI":"10.1109\/FUZZ48607.2020.9177653"},{"key":"1338_CR7","doi-asserted-by":"publisher","first-page":"358","DOI":"10.1016\/j.future.2018.10.051","volume":"93","author":"K Kolomvatsos","year":"2019","unstructured":"Kolomvatsos K, Anagnostopoulos A (2019) Multi-criteria optimal task allocation at the edge. Fut Gener Comput Syst 93:358\u2013372","journal-title":"Futur Gener Comput Syst"},{"key":"1338_CR8","doi-asserted-by":"crossref","unstructured":"Bhardwaj K et al (2015) AppSachet: distributed app delivery from the edge cloud. In: International conference on mobile computing, applications, and services, pp 89\u2013106","DOI":"10.1007\/978-3-319-29003-4_6"},{"key":"1338_CR9","doi-asserted-by":"crossref","unstructured":"Simoens P et al (2013) Scalable crowd-sourcing of video from mobile devices. In: 11th international conference on mobile systems, applications, and services, pp 139\u2013152","DOI":"10.1145\/2462456.2464440"},{"key":"1338_CR10","doi-asserted-by":"crossref","unstructured":"Lalanda Philippe et al (2021) Architecture and pervasive platform for machine learning services in Industry 4.0. In: 2021 IEEE international conference on pervasive computing and communications workshops and other affiliated events (PerCom Workshops). IEEE","DOI":"10.1109\/PerComWorkshops51409.2021.9431009"},{"issue":"3","key":"1338_CR11","doi-asserted-by":"publisher","first-page":"921","DOI":"10.1109\/TITS.2018.2791643","volume":"19","author":"D Richardos","year":"2018","unstructured":"Richardos D et al (2018) A gamified flexible transportation service for on-demand public transport. IEEE Trans Intell Transp Syst 19(3):921\u2013933","journal-title":"IEEE Trans Intell Transp Syst"},{"issue":"02","key":"1338_CR12","first-page":"98","volume":"2","author":"S Shakya","year":"2020","unstructured":"Shakya S, Nepal L (2020) Computational enhancements of wearable healthcare devices on pervasive computing system. J Ubiquitous Comput Commun Technol (UCCT) 2(02):98\u2013108","journal-title":"J Ubiquitous Comput Commun Technol (UCCT)"},{"issue":"1","key":"1338_CR13","doi-asserted-by":"publisher","first-page":"183","DOI":"10.1109\/JIOT.2016.2638119","volume":"4","author":"K Kolomvatsos","year":"2017","unstructured":"Kolomvatsos K et al (2017) Distributed localized contextual event reasoning under uncertainty. IEEE Internet Things J 4(1):183\u2013191","journal-title":"IEEE Internet Things J"},{"key":"1338_CR14","doi-asserted-by":"crossref","unstructured":"Anagnostopoulos C, Hadjiefthymiades S, Kolomvatsos K (2016) Accurate, dynamic and distributed localization of phenomena for mobile sensor networks, ACM TOSN, 12(2)","DOI":"10.1145\/2882966"},{"issue":"8","key":"1338_CR15","first-page":"1839","volume":"47","author":"K Kolomvatsos","year":"2016","unstructured":"Kolomvatsos K et al (2016) Data fusion and type-2 fuzzy inference in contextual data stream monitoring. IEEE TSMC Syst 47(8):1839\u20131853","journal-title":"IEEE TSMC Syst"},{"key":"1338_CR16","doi-asserted-by":"crossref","unstructured":"Kolomvatsos K et al (2015) An efficient environmental monitoring system adopting data fusion, prediction, and fuzzy logic. In: 6th IISA","DOI":"10.1109\/IISA.2015.7388070"},{"issue":"2","key":"1338_CR17","doi-asserted-by":"publisher","first-page":"15","DOI":"10.3390\/iot1020015","volume":"1","author":"K Kolomvatsos","year":"2020","unstructured":"Kolomvatsos K, Anagnostopoulos C (2020) A deep learning model for demand-driven, proactive tasks management in pervasive computing. IoT 1(2):15","journal-title":"IoT"},{"issue":"5","key":"1338_CR18","doi-asserted-by":"publisher","first-page":"114","DOI":"10.1109\/MNET.011.2100121","volume":"35","author":"V Balasubramanian","year":"2021","unstructured":"Balasubramanian V et al (2021) Intelligent resource management at the edge for ubiquitous IoT: an SDN-based federated learning approach. IEEE Netw 35(5):114\u2013121","journal-title":"IEEE Netw"},{"key":"1338_CR19","unstructured":"Sannara E K et al (2021) A federated learning aggregation algorithm for pervasive computing: evaluation and comparison. In: 2021 IEEE international conference on pervasive computing and communications (PerCom). IEEE"},{"key":"1338_CR20","doi-asserted-by":"crossref","unstructured":"Lee S, Julien C, Zheng X (2022) Facilitating decentralized and opportunistic learning in pervasive computing. In: 2022 IEEE international conference on pervasive computing and communications workshops and other affiliated events (PerCom Workshops). IEEE","DOI":"10.1109\/PerComWorkshops53856.2022.9767211"},{"key":"1338_CR21","doi-asserted-by":"publisher","first-page":"67","DOI":"10.1016\/j.jpdc.2017.05.007","volume":"118","author":"L Cao","year":"2018","unstructured":"Cao L et al (2018) GCHAR: an efficient group-based context-aware human activity recognition on smartphone. J Parallel Distrib Comput 118:67\u201380","journal-title":"J Parallel Distrib Comput"},{"key":"1338_CR22","doi-asserted-by":"crossref","unstructured":"Wu L et al (2021) Learning fair representations for recommendation: a graph-based perspective. In: Proceedings of the web conference 2021","DOI":"10.1145\/3442381.3450015"},{"key":"1338_CR23","unstructured":"Chen G et al (2019) Rethinking the usage of batch normalization and dropout in the training of deep neural networks. arXiv preprint arXiv:1905.05928 (2019)"},{"key":"1338_CR24","unstructured":"Ioffe S, Szegedy C (2015) Batch normalization: accelerating deep network training by reducing internal covariate shift. In: International conference on machine learning. PMLR"},{"key":"1338_CR25","unstructured":"Inoue H (2019) Multi-sample dropout for accelerated training and better generalization. arXiv preprint arXiv:1905.09788 (2019)"},{"key":"1338_CR26","unstructured":"Jiang AH et al (2019) Accelerating deep learning by focusing on the biggest losers. arXiv preprint arXiv:1910.00762"},{"key":"1338_CR27","doi-asserted-by":"publisher","first-page":"142393","DOI":"10.1109\/ACCESS.2020.3013621","volume":"8","author":"Y Naisen","year":"2020","unstructured":"Naisen Y et al (2020) Accelerating the training process of convolutional neural networks for image classification by dropping training samples out. IEEE Access 8:142393\u2013142403","journal-title":"IEEE Access"},{"key":"1338_CR28","unstructured":"Sun X et al (2017) meprop: sparsified back propagation for accelerated deep learning with reduced overfitting. In: International conference on machine learning. PMLR"},{"key":"1338_CR29","unstructured":"Zhang J., Yu H-F, Dhillon I S (2019) Autoassist: a framework to accelerate training of deep neural networks. In: Advances in neural information processing systems, vol 32"},{"issue":"1","key":"1338_CR30","doi-asserted-by":"publisher","first-page":"111","DOI":"10.1016\/j.gltp.2021.01.015","volume":"2","author":"GS Nandini","year":"2021","unstructured":"Nandini GS, Siva Kumar AP, Chidananda K (2021) Dropout technique for image classification based on extreme learning machine. Global Trans Proc 2(1):111\u2013116","journal-title":"Global Trans Proc"},{"key":"1338_CR31","doi-asserted-by":"crossref","unstructured":"Song Z et al (2019) Approximate random dropout for DNN training acceleration in GPGPU. In: 2019 Design, automation and test in Europe conference and exhibition (DATE). IEEE","DOI":"10.23919\/DATE.2019.8715135"},{"issue":"7","key":"1338_CR32","doi-asserted-by":"publisher","first-page":"2043","DOI":"10.1109\/TNNLS.2018.2876179","volume":"30","author":"S Wu","year":"2018","unstructured":"Wu S et al (2018) $$L1$$-norm batch normalization for efficient training of deep neural networks. IEEE Trans Neural Netw Learn Syst 30(7):2043\u20132051","journal-title":"IEEE Trans Neural Netw Learn Syst"},{"key":"1338_CR33","unstructured":"Katharopoulos A, Fleuret F (2018) Not all samples are created equal: Deep learning with importance sampling. In: International conference on machine learning, PMLR"},{"key":"1338_CR34","doi-asserted-by":"publisher","DOI":"10.1016\/j.ymssp.2020.106684","volume":"140","author":"Z Xiang","year":"2020","unstructured":"Xiang Z et al (2020) An active learning method combining deep neural network and weighted sampling for structural reliability analysis. Mech Syst Signal Process 140:106684","journal-title":"Mech Syst Signal Process"},{"key":"1338_CR35","doi-asserted-by":"crossref","unstructured":"Li D et al (2018) \u2019AdaError: an adaptive learning rate method for matrix approximation-based collaborative filtering. In: Proceedings of the 2018 world wide web conference, pp 741\u2013751","DOI":"10.1145\/3178876.3186155"},{"key":"1338_CR36","doi-asserted-by":"publisher","first-page":"368","DOI":"10.1007\/BF01734359","volume":"17","author":"J Felsenstein","year":"1981","unstructured":"Felsenstein J (1981) Evolutionary trees from DNA sequences: a maximum likelihood approach. J Mol Evol 17:368\u2013376","journal-title":"J Mol Evol"},{"key":"1338_CR37","doi-asserted-by":"publisher","first-page":"457","DOI":"10.2307\/2394164","volume":"23","author":"E Anderson","year":"1936","unstructured":"Anderson E (1936) The species problem in Iris. Ann Mo Bot Gard 23:457\u2013509","journal-title":"Ann Mo Bot Gard"},{"issue":"6","key":"1338_CR38","doi-asserted-by":"publisher","first-page":"141","DOI":"10.1109\/MSP.2012.2211477","volume":"29","author":"L Deng","year":"2012","unstructured":"Deng L (2012) The MNIST database of handwritten digit images for machine learning research [best of the web]. IEEE Signal Process Mag 29(6):141\u2013142. https:\/\/doi.org\/10.1109\/MSP.2012.2211477","journal-title":"IEEE Signal Process Mag"},{"key":"1338_CR39","unstructured":"Simonyan S, Zisserman A (2014) Very deep convolutional networks for large-scale image recognition. arXiv preprint arXiv:1409.1556"},{"key":"1338_CR40","doi-asserted-by":"crossref","unstructured":"Sandler M et al (2018) Mobilenetv2: inverted residuals and linear bottlenecks. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 4510\u20134520","DOI":"10.1109\/CVPR.2018.00474"},{"key":"1338_CR41","doi-asserted-by":"crossref","unstructured":"He K et al (2016) Deep residual learning for image recognition. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 770\u2013778","DOI":"10.1109\/CVPR.2016.90"},{"key":"1338_CR42","doi-asserted-by":"crossref","unstructured":"Huang G et al (2017) Densely connected convolutional networks. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 4700\u20134708","DOI":"10.1109\/CVPR.2017.243"},{"key":"1338_CR43","unstructured":"Krizhevsky A et al. The CIFAR-10 dataset. Available: https:\/\/www.cs.toronto.edu\/~kriz\/cifar.html"},{"key":"1338_CR44","unstructured":"Krizhevsky A (2009) Learning multiple layers of features from tiny images. Technical report TR-2009. University of Toronto, Toronto"}],"container-title":["Computing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00607-024-01338-2.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s00607-024-01338-2\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00607-024-01338-2.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,10,15]],"date-time":"2024-10-15T14:58:58Z","timestamp":1729004338000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s00607-024-01338-2"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,8,16]]},"references-count":44,"journal-issue":{"issue":"11","published-print":{"date-parts":[[2024,11]]}},"alternative-id":["1338"],"URL":"https:\/\/doi.org\/10.1007\/s00607-024-01338-2","relation":{},"ISSN":["0010-485X","1436-5057"],"issn-type":[{"value":"0010-485X","type":"print"},{"value":"1436-5057","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,8,16]]},"assertion":[{"value":"10 August 2023","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"1 August 2024","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"16 August 2024","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}}]}}