{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,7,30]],"date-time":"2025-07-30T16:31:30Z","timestamp":1753893090972,"version":"3.41.2"},"reference-count":38,"publisher":"Frontiers Media SA","license":[{"start":{"date-parts":[[2025,1,22]],"date-time":"2025-01-22T00:00:00Z","timestamp":1737504000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":["frontiersin.org"],"crossmark-restriction":true},"short-container-title":["Front. Artif. Intell."],"abstract":"<jats:p>With the increasing integration of machine learning into IoT devices, managing energy consumption and data transmission has become a critical challenge. Many IoT applications depend on complex computations performed on server-side infrastructure, necessitating efficient methods to reduce unnecessary data transmission. One promising solution involves deploying compact machine learning models near sensors, enabling intelligent identification and transmission of only relevant data frames. However, existing near-sensor models lack adaptability, as they require extensive pre-training and are often rigidly configured prior to deployment. This paper proposes a novel framework that fuses online learning, active learning, and knowledge distillation to enable adaptive, resource-efficient near-sensor intelligence. Our approach allows near-sensor models to dynamically fine-tune their parameters post-deployment using online learning, eliminating the need for extensive pre-labeling and training. Through a sequential training and execution process, the framework achieves continuous adaptability without prior knowledge of the deployment environment. To enhance performance while preserving model efficiency, we integrate knowledge distillation, enabling the transfer of critical insights from a larger teacher model to a compact student model. Additionally, active learning reduces the required training data while maintaining competitive performance. We validated our framework on both benchmark data from the MS COCO dataset and in a simulated IoT environment. The results demonstrate significant improvements in energy efficiency and data transmission optimization, highlighting the practical applicability of our method in real-world IoT scenarios.<\/jats:p>","DOI":"10.3389\/frai.2024.1403187","type":"journal-article","created":{"date-parts":[[2025,1,22]],"date-time":"2025-01-22T07:17:18Z","timestamp":1737530238000},"update-policy":"https:\/\/doi.org\/10.3389\/crossmark-policy","source":"Crossref","is-referenced-by-count":1,"title":["Self-trainable and adaptive sensor intelligence for selective data generation"],"prefix":"10.3389","volume":"7","author":[{"given":"Arghavan","family":"Rezvani","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Wenjun","family":"Huang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hanning","family":"Chen","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yang","family":"Ni","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Mohsen","family":"Imani","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"1965","published-online":{"date-parts":[[2025,1,22]]},"reference":[{"key":"B1","doi-asserted-by":"crossref","first-page":"89","DOI":"10.1002\/9781119740780.ch3","article-title":"\u201cMachine learning techniques for Iot data analytics,\u201d","volume-title":"Big Data Analytics for Internet of Things","author":"Afshan","year":"2021"},{"key":"B2","doi-asserted-by":"crossref","first-page":"190","DOI":"10.1109\/ISM.2011.38","article-title":"\u201cAdaptive video compression for video surveillance applications,\u201d","volume-title":"2011 IEEE International Symposium on Multimedia","author":"Bagdanov","year":"2011"},{"key":"B3","doi-asserted-by":"crossref","first-page":"404","DOI":"10.1007\/11744023_32","article-title":"\u201cSurf: speeded up robust features,\u201d","volume-title":"Computer Vision-ECCV 2006: 9th European Conference on Computer Vision, Graz, Austria, May 7-13, 2006. Proceedings, Part I 9","author":"Bay","year":"2006"},{"key":"B4","doi-asserted-by":"publisher","first-page":"8553","DOI":"10.1109\/JIOT.2019.2920283","article-title":"Iot wearable sensor and deep learning: an integrated approach for personalized human activity recognition in a smart home environment","volume":"6","author":"Bianchi","year":"2019","journal-title":"IEEE Internet Things J"},{"key":"B5","doi-asserted-by":"crossref","first-page":"535","DOI":"10.1145\/1150402.1150464","article-title":"\u201cModel compression,\u201d","volume-title":"Proceedings of the 12th ACM SIGKDD international conference on Knowledge discovery and data mining","author":"Bucilu\u01ce","year":"2006"},{"key":"B6","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2403.05763","article-title":"Hdreason: algorithm-hardware codesign for hyperdimensional knowledge graph reasoning","author":"Chen","year":"2024","journal-title":"arXiv"},{"key":"B7","doi-asserted-by":"crossref","first-page":"34","DOI":"10.1109\/FPL60245.2023.00013","article-title":"\u201cHypergraf: Hyperdimensional graph-based reasoning acceleration on fpga,\u201d","volume-title":"2023 33rd International Conference on Field-Programmable Logic and Applications (FPL)","author":"Chen","year":"2023"},{"key":"B8","doi-asserted-by":"publisher","first-page":"16344","DOI":"10.48550\/arXiv.2205.14135","article-title":"Flashattention: fast and memory-efficient exact attention with IO-awareness","volume":"35","author":"Dao","year":"2022","journal-title":"Adv. Neural Inf. Process. Syst"},{"key":"B9","doi-asserted-by":"publisher","first-page":"3587","DOI":"10.1038\/s41467-022-31148-z","article-title":"All-in-one, bio-inspired, and low-power crypto engines for near-sensor security based on two-dimensional memtransistors","volume":"13","author":"Dodda","year":"2022","journal-title":"Nat. Commun"},{"key":"B10","doi-asserted-by":"publisher","first-page":"218","DOI":"10.3390\/fi13080218","article-title":"Iot for smart cities: machine learning approaches in smart healthcare\u2014a review","volume":"13","author":"Ghazal","year":"2021","journal-title":"Future Internet"},{"key":"B11","doi-asserted-by":"publisher","first-page":"1789","DOI":"10.1007\/s11263-021-01453-z","article-title":"Knowledge distillation: a survey","volume":"129","author":"Gou","year":"2021","journal-title":"Int. J. Comput. Vis"},{"key":"B12","doi-asserted-by":"publisher","first-page":"2000063","DOI":"10.1002\/aisy.202000063","article-title":"Machine learning-enabled smart sensor systems","volume":"2","author":"Ha","year":"2020","journal-title":"Adv. Intell. Syst"},{"key":"B13","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1503.02531","article-title":"Distilling the knowledge in a neural network","author":"Hinton","year":"2015","journal-title":"arXiv"},{"key":"B14","doi-asserted-by":"publisher","first-page":"298","DOI":"10.1109\/EMBC46164.2021.9629997","article-title":"\u201cExploration of using a pressure sensitive mat for respiration rate and heart rate estimation,\u201d","author":"Huang","year":"2021","journal-title":"2021 43rd Annual International Conference of the IEEE Engineering in Medicine"},{"key":"B15","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2403.14027","article-title":"Ecosense: energy-efficient intelligent sensing for in-shore ship detection through edge-cloud collaboration","author":"Huang","year":"","journal-title":"arXiv"},{"key":"B16","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2409.02715","article-title":"Recoverable anonymization for pose estimation: a privacy-enhancing approach","author":"Huang","year":"","journal-title":"arXiv"},{"key":"B17","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2402.02043","article-title":"A plug-in tiny AI module for intelligent and selective sensor data transmission","author":"Huang","year":"","journal-title":"arXiv"},{"key":"B18","doi-asserted-by":"crossref","first-page":"892","DOI":"10.1109\/INFCOMW.2019.8845240","article-title":"\u201cDeepar: a hybrid device-edge-cloud execution framework for mobile deep learning applications,\u201d","volume-title":"IEEE INFOCOM 2019-IEEE Conference on Computer Communications Workshops (INFOCOM WKSHPS)","author":"Huang","year":"2019"},{"key":"B19","doi-asserted-by":"publisher","first-page":"159","DOI":"10.1016\/j.future.2017.03.034","article-title":"Smart city and Iot","volume":"76","author":"Kim","year":"2017","journal-title":"Future Gener. Comput. Syst"},{"key":"B20","first-page":"1","article-title":"\u201cComprehensive integration of hyperdimensional computing with deep learning towards neuro-symbolic AI,\u201d","volume-title":"2023 60th ACM\/IEEE Design Automation Conference (DAC)","author":"Lee","year":"2023"},{"key":"B21","doi-asserted-by":"crossref","first-page":"2548","DOI":"10.1109\/ICCV.2011.6126542","article-title":"\u201cBrisk: binary robust invariant scalable keypoints,\u201d","volume-title":"2011 International conference on computer vision","author":"Leutenegger","year":"2011"},{"key":"B22","doi-asserted-by":"publisher","first-page":"568384","DOI":"10.3389\/frai.2021.568384","article-title":"Biologically-inspired pulse signal processing for intelligence at the edge","volume":"4","author":"Li","year":"2021","journal-title":"Front. Artif. Intell"},{"key":"B23","doi-asserted-by":"crossref","first-page":"740","DOI":"10.1007\/978-3-319-10602-1_48","article-title":"\u201cMicrosoft coco: common objects in context,\u201d","volume-title":"Computer Vision-ECCV 2014: 13th European Conference, Zurich, Switzerland, September 6-12, 2014, Proceedings, Part V 13","author":"Lin","year":"2014"},{"key":"B24","doi-asserted-by":"publisher","first-page":"5703","DOI":"10.1109\/TVT.2020.2983143","article-title":"An improved neural network pruning technology for automatic modulation classification in edge devices","volume":"69","author":"Lin","year":"2020","journal-title":"IEEE Trans. Veh. Technol"},{"key":"B25","doi-asserted-by":"publisher","first-page":"91","DOI":"10.1023\/B:VISI.0000029664.99615.94","article-title":"Distinctive image features from scale-invariant keypoints","volume":"60","author":"Lowe","year":"2004","journal-title":"Int. J. Comput. Vis"},{"key":"B26","doi-asserted-by":"crossref","first-page":"105","DOI":"10.1145\/3431920.3439284","article-title":"\u201cDemystifying the memory system of modern datacenter fpgas for software programmers through microbenchmarking,\u201d","volume-title":"The 2021 ACM\/SIGDA International Symposium on Field-Programmable Gate Arrays","author":"Lu","year":"2021"},{"key":"B27","doi-asserted-by":"publisher","first-page":"161","DOI":"10.1016\/j.dcan.2017.10.002","article-title":"Machine learning for internet of things data analysis: a survey","volume":"4","author":"Mahdavinejad","year":"2018","journal-title":"Digit. Commun. Netw"},{"key":"B28","unstructured":"Pytorch: an imperative style, high-performance deep learning library\n          \n          \n            \n              Paszke\n              A.\n            \n            \n              Gross\n              S.\n            \n            \n              Massa\n              F.\n            \n            \n              Lerer\n              A.\n            \n            \n              Bradbury\n              J.\n            \n            \n              Chanan\n              G.\n            \n          \n          Adv. Neural Inf. Process. Syst\n          \n          2019"},{"key":"B29","unstructured":"Internet of things-Iot: definition, characteristics, architecture, enabling technologies, application & future challenges\n          \n          \n            \n              Patel\n              K. K.\n            \n            \n              Patel\n              S. M.\n            \n            \n              Scholar\n              P.\n            \n          \n          Int. J. Eng. Sci. comput\n          \n          2016"},{"key":"B30","doi-asserted-by":"crossref","first-page":"278","DOI":"10.1109\/MMSP.2013.6659301","article-title":"\u201cCompress-then-analyze vs. analyze-then-compress: two paradigms for image analysis in visual sensor networks,\u201d","volume-title":"2013 IEEE 15th International Workshop on Multimedia Signal Processing (MMSP)","author":"Redondi","year":"2013"},{"key":"B31","unstructured":"Active learning literature survey\n          \n          \n            \n              Settles\n              B.\n            \n          \n          Technical Report\n          \n          2009"},{"key":"B32","doi-asserted-by":"publisher","first-page":"713176","DOI":"10.3389\/frai.2021.713176","article-title":"Keep calm and do not carry-forward: toward sensor-data driven ai agent to enhance human learning","volume":"4","author":"Sharma","year":"2022","journal-title":"Front. Artif. Intell"},{"key":"B33","doi-asserted-by":"publisher","first-page":"1063","DOI":"10.1038\/s41598-023-27674-5","article-title":"An intelligent model for supporting edge migration for virtual function chains in next generation internet of things","volume":"13","author":"Tsakanikas","year":"2023","journal-title":"Sci. Rep"},{"key":"B34","doi-asserted-by":"crossref","first-page":"235","DOI":"10.1117\/12.974618","article-title":"\u201cA methodology to evaluate the effect of video compression on the performance of analytics systems,\u201d","volume-title":"Optics and Photonics for Counterterrorism, Crime Fighting, and Defence VIII","author":"Tsifouti","year":"2012"},{"key":"B35","doi-asserted-by":"publisher","first-page":"108146","DOI":"10.1016\/j.patcog.2021.108146","article-title":"Edge computing enabled video segmentation for real-time traffic monitoring in internet of vehicles","volume":"121","author":"Wan","year":"2022","journal-title":"Pattern Recognit"},{"key":"B36","first-page":"4933","article-title":"\u201cDistilling object detectors with fine-grained feature imitation,\u201d","volume-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","author":"Wang","year":"2019"},{"key":"B37","doi-asserted-by":"publisher","first-page":"105366","DOI":"10.1016\/j.engappai.2022.105366","article-title":"Iot data analytics in dynamic environments: from an automated machine learning perspective","volume":"116","author":"Yang","year":"2022","journal-title":"Eng. Appl. Artif. Intell"},{"key":"B38","doi-asserted-by":"publisher","first-page":"1190","DOI":"10.1049\/iet-its.2018.5241","article-title":"Deep learning-based helmet wear analysis of a motorcycle rider for intelligent surveillance system","volume":"13","author":"Yogameena","year":"2019","journal-title":"IET Intell. Transp. Syst"}],"container-title":["Frontiers in Artificial Intelligence"],"original-title":[],"link":[{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/frai.2024.1403187\/full","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,1,22]],"date-time":"2025-01-22T07:17:32Z","timestamp":1737530252000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/frai.2024.1403187\/full"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,1,22]]},"references-count":38,"alternative-id":["10.3389\/frai.2024.1403187"],"URL":"https:\/\/doi.org\/10.3389\/frai.2024.1403187","relation":{},"ISSN":["2624-8212"],"issn-type":[{"type":"electronic","value":"2624-8212"}],"subject":[],"published":{"date-parts":[[2025,1,22]]},"article-number":"1403187"}}