{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,20]],"date-time":"2026-07-20T19:22:39Z","timestamp":1784575359881,"version":"3.55.0"},"reference-count":107,"publisher":"MDPI AG","issue":"3","license":[{"start":{"date-parts":[[2023,1,22]],"date-time":"2023-01-22T00:00:00Z","timestamp":1674345600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Sensors"],"abstract":"<jats:p>Artificial Intelligence (Al) models are being produced and used to solve a variety of current and future business and technical problems. Therefore, AI model engineering processes, platforms, and products are acquiring special significance across industry verticals. For achieving deeper automation, the number of data features being used while generating highly promising and productive AI models is numerous, and hence the resulting AI models are bulky. Such heavyweight models consume a lot of computation, storage, networking, and energy resources. On the other side, increasingly, AI models are being deployed in IoT devices to ensure real-time knowledge discovery and dissemination. Real-time insights are of paramount importance in producing and releasing real-time and intelligent services and applications. Thus, edge intelligence through on-device data processing has laid down a stimulating foundation for real-time intelligent enterprises and environments. With these emerging requirements, the focus turned towards unearthing competent and cognitive techniques for maximally compressing huge AI models without sacrificing AI model performance. Therefore, AI researchers have come up with a number of powerful optimization techniques and tools to optimize AI models. This paper is to dig deep and describe all kinds of model optimization at different levels and layers. Having learned the optimization methods, this work has highlighted the importance of having an enabling AI model optimization framework.<\/jats:p>","DOI":"10.3390\/s23031279","type":"journal-article","created":{"date-parts":[[2023,1,23]],"date-time":"2023-01-23T01:36:26Z","timestamp":1674437786000},"page":"1279","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":122,"title":["A Survey on Optimization Techniques for Edge Artificial Intelligence (AI)"],"prefix":"10.3390","volume":"23","author":[{"given":"Chellammal","family":"Surianarayanan","sequence":"first","affiliation":[{"name":"Centre for Distance and Online Education, Bharathidasan University, Tiruchirappalli 620024, Tamilnadu, India"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"John Jeyasekaran","family":"Lawrence","sequence":"additional","affiliation":[{"name":"Cardiff School of Technologies, Cardiff Metropolitan University, Cardiff CF5 2YB, UK"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5220-0408","authenticated-orcid":false,"given":"Pethuru Raj","family":"Chelliah","sequence":"additional","affiliation":[{"name":"Edge AI Division, Reliance Jio Platforms Ltd., Bangalore 560103, Karnataka, India"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9129-0186","authenticated-orcid":false,"given":"Edmond","family":"Prakash","sequence":"additional","affiliation":[{"name":"Research Center for Creative Arts, University for the Creative Arts (UCA), Farnham GU9 7DS, UK"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7593-6661","authenticated-orcid":false,"given":"Chaminda","family":"Hewage","sequence":"additional","affiliation":[{"name":"Cardiff School of Technologies, Cardiff Metropolitan University, Cardiff CF5 2YB, UK"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1968","published-online":{"date-parts":[[2023,1,22]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","first-page":"112","DOI":"10.1109\/MC.2016.245","article-title":"Fog Computing: Helping the Internet of Things Realize","volume":"49","author":"Buyya","year":"2016","journal-title":"IEEE Comput. Soc."},{"key":"ref_2","doi-asserted-by":"crossref","first-page":"85714","DOI":"10.1109\/ACCESS.2020.2991734","article-title":"An Overview on Edge Computing Research","volume":"8","author":"Cao","year":"2020","journal-title":"IEEE Access"},{"key":"ref_3","doi-asserted-by":"crossref","first-page":"1399","DOI":"10.1007\/s13042-018-0834-5","article-title":"A survey on application of machine learning for Internet of Things","volume":"9","author":"Cui","year":"2018","journal-title":"Int. J. Mach. Learn. Cybern."},{"key":"ref_4","doi-asserted-by":"crossref","unstructured":"Pooyandeh, M., and Sohn, I. (2021). Edge Network Optimization Based on AI Techniques: A Survey. Electronics, 10.","DOI":"10.3390\/electronics10222830"},{"key":"ref_5","doi-asserted-by":"crossref","unstructured":"Kum, S., Oh, S., Yeom, J., and Moon, J. (2022). Optimization of edge resources for deep learning application with batch and model management. Sensors, 22.","DOI":"10.3390\/s22176717"},{"key":"ref_6","doi-asserted-by":"crossref","first-page":"37","DOI":"10.1109\/MDAT.2019.2952350","article-title":"EdgeAI: A vision for deep learning in the IoT era","volume":"38","author":"Bhardwaj","year":"2021","journal-title":"IEEE Des. Test"},{"key":"ref_7","doi-asserted-by":"crossref","unstructured":"Sipola, T., Alatalo, J., Kokkonen, T., and Rantonen, M. (2022, January 27\u201329). Artificial Intelligence in the IoT Era: A Review of Edge AI Hardware and Software. Proceedings of the 2022 31st Conference of Open Innovations Association (FRUCT), Helsinki, Finland.","DOI":"10.23919\/FRUCT54823.2022.9770931"},{"key":"ref_8","doi-asserted-by":"crossref","first-page":"247","DOI":"10.1016\/bs.adcom.2020.07.002","article-title":"Energy-efficient deep learning inference on edge devices","volume":"Volume 122","author":"Kim","year":"2021","journal-title":"Advances in Computers"},{"key":"ref_9","doi-asserted-by":"crossref","first-page":"108186","DOI":"10.1016\/j.comnet.2021.108186","article-title":"Edge intelligence computing for mobile augmented reality with deep reinforcement learning approach","volume":"195","author":"Chen","year":"2021","journal-title":"Comput. Netw."},{"key":"ref_10","doi-asserted-by":"crossref","unstructured":"Buber, E., and Diri, B. (2018, January 25\u201327). Performance Analysis and CPU vs GPU Comparison for Deep Learning. Proceedings of the 2018 6th International Conference on Control Engineering & Information Technology (CEIT), Istanbul, Turkey.","DOI":"10.1109\/CEIT.2018.8751930"},{"key":"ref_11","doi-asserted-by":"crossref","first-page":"225134","DOI":"10.1109\/ACCESS.2020.3039858","article-title":"Hardware and Software Optimizations for Accelerating Deep Neural Networks: Survey of Current Trends, Challenges, and the Road Ahead","volume":"8","author":"Capra","year":"2020","journal-title":"IEEE Access"},{"key":"ref_12","doi-asserted-by":"crossref","unstructured":"Capra, M., Peloso, R., Masera, G., Ruo Roch, M., and Martina, M. (2019). Edge computing: A survey on the hardware requirements in the internet of things world. Future Internet, 11.","DOI":"10.3390\/fi11040100"},{"key":"ref_13","doi-asserted-by":"crossref","unstructured":"Lee, Y.-L., Tsung, P.-K., and Wu, M. (2018, January 16\u201319). Techology trend of edge AI. Proceedings of the 2018 International Symposium on VLSI Design, Automation and Test (VLSI-DAT), Hsinchu, Taiwan.","DOI":"10.1109\/VLSI-DAT.2018.8373244"},{"key":"ref_14","doi-asserted-by":"crossref","unstructured":"Druva Kumar, S., Sharma, P., Prajwal Shenoy, K., Naik, S.S., and Lewis, A.S. (2020, January 13\u201315). Implementation of 16-bit hack CPU on FPGA. Proceedings of the 2020 4th International Conference on Intelligent Computing and Control Systems, ICICCS, Madurai, India.","DOI":"10.1109\/ICICCS48265.2020.9120991"},{"key":"ref_15","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1145\/3357375","article-title":"A survey of coarse-grained reconfigurable architecture and design: Taxonomy, challenges, and applications","volume":"52","author":"Liu","year":"2019","journal-title":"ACM Comput. Surv."},{"key":"ref_16","doi-asserted-by":"crossref","unstructured":"Shahid, A., and Mushtaq, M. (2020, January 5\u20137). A Survey Comparing Specialized Hardware and Evolution in TPUs for Neural Networks. Proceedings of the 2020 IEEE 23rd International Multitopic Conference (INMIC), Bahawalpur, Pakistan.","DOI":"10.1109\/INMIC50486.2020.9318136"},{"key":"ref_17","doi-asserted-by":"crossref","first-page":"217","DOI":"10.1016\/bs.adcom.2020.11.001","article-title":"Architecture of neural processing unit for deep neural networks","volume":"122","author":"Lee","year":"2021","journal-title":"Adv. Comput."},{"key":"ref_18","doi-asserted-by":"crossref","unstructured":"Novac, P.-E., Boukli Hacene, G., Pegatoquet, A., Miramond, B., and Gripon, V. (2021). Quantization and Deployment of Deep Neural Networks on Microcontrollers. Sensors, 21.","DOI":"10.3390\/s21092984"},{"key":"ref_19","doi-asserted-by":"crossref","first-page":"100008","DOI":"10.1016\/j.hcc.2021.100008","article-title":"A survey of federated learning for edge computing: Research problems and solutions","volume":"1","author":"Xia","year":"2021","journal-title":"High-Confid. Comput."},{"key":"ref_20","doi-asserted-by":"crossref","unstructured":"Abreha, H.G., Hayajneh, M., and Serhani, M.A. (2022). Federated Learning in Edge Computing: A Systematic Survey. Sensors, 22.","DOI":"10.3390\/s22020450"},{"key":"ref_21","doi-asserted-by":"crossref","first-page":"1759","DOI":"10.1109\/COMST.2021.3090430","article-title":"Federated Learning for Internet of Things: Recent Advances, Taxonomy, and Open Challenges","volume":"23","author":"Khan","year":"2021","journal-title":"IEEE Commun. Surv. Tutor."},{"key":"ref_22","doi-asserted-by":"crossref","unstructured":"Wink, T., and Nochta, Z. (2021, January 21\u201324). An Approach for Peer-to-Peer Federated Learning. Proceedings of the 2021 51st Annual IEEE\/IFIP International Conference on Dependable Systems and Networks Workshops (DSN-W), Taipei, Taiwan.","DOI":"10.1109\/DSN-W52860.2021.00034"},{"key":"ref_23","unstructured":"Lian, X., Zhang, C., Zhang, H., Hsieh, C.-J., Zhang, W., and Liu, J. (2017, January 4\u20139). Can decentralized algorithms outperform centralized algorithms? A case study for decentralized parallel stochastic gradient descent. Proceedings of the Advances in Neural Information Processing Systems 30: Annual Conference on Neural Information Processing Systems 2017, Long Beach, CA, USA."},{"key":"ref_24","doi-asserted-by":"crossref","first-page":"102402","DOI":"10.1016\/j.cose.2021.102402","article-title":"Privacy preservation in federated learning: An insightful survey from the GDPR perspective","volume":"110","author":"Truong","year":"2021","journal-title":"Comput. Secur."},{"key":"ref_25","doi-asserted-by":"crossref","unstructured":"Brecko, A., Kajati, E., Koziorek, J., and Zolotova, I. (2022). Federated Learning for Edge Computing: A Survey. Appl. Sci., 12.","DOI":"10.3390\/app12189124"},{"key":"ref_26","doi-asserted-by":"crossref","unstructured":"Li, Q., Wen, Z., Wu, Z., Hu, S., Wang, N., Li, Y., Liu, X., and He, B. (2021). A Survey on Federated Learning Systems: Vision, Hype and Reality for Data Privacy and Protection. IEEE Trans. Knowl. Data Eng.","DOI":"10.1109\/TKDE.2021.3124599"},{"key":"ref_27","doi-asserted-by":"crossref","first-page":"21","DOI":"10.1109\/MCE.2020.3048926","article-title":"FedLearnSP: Preserving Privacy and Security Using Federated Learning and Edge Computing","volume":"11","author":"Makkar","year":"2022","journal-title":"IEEE Consum. Electron. Mag."},{"key":"ref_28","doi-asserted-by":"crossref","first-page":"140699","DOI":"10.1109\/ACCESS.2020.3013541","article-title":"Federated Learning: A Survey on Enabling Technologies, Protocols, and Applications","volume":"8","author":"Aledhari","year":"2020","journal-title":"IEEE Access"},{"key":"ref_29","doi-asserted-by":"crossref","first-page":"371","DOI":"10.1016\/j.neucom.2021.07.098","article-title":"Federated Learning on Non-IID Data: A Survey","volume":"465","author":"Zhua","year":"2021","journal-title":"Neurocomputing"},{"key":"ref_30","unstructured":"Hsu, T.M.-H., Qi, H., and Brown, M. (2019). Measuring the effects of nonidentical data distribution for federated visual classification. arXiv."},{"key":"ref_31","doi-asserted-by":"crossref","unstructured":"Kulkarni, V., Kulkarni, M., and Pant, A. (2020, January 27\u201328). Survey of personalization techniques for federated learning. Proceedings of the 2020 Fourth World Conference on Smart Trends in Systems, Security and Sustainability (WorldS4), London, UK.","DOI":"10.1109\/WorldS450073.2020.9210355"},{"key":"ref_32","doi-asserted-by":"crossref","unstructured":"Wu, P., Imbiriba, T., Park, J., Kim, S., and Closas, P. (2021). Personalized Federated Learning over non-IID Data for Indoor Localization. arXiv.","DOI":"10.1109\/SPAWC51858.2021.9593115"},{"key":"ref_33","doi-asserted-by":"crossref","unstructured":"Huang, Y., Chu, L., Zhou, Z., Wang, L., Liu, J., Pei, J., and Zhang, Y. (2021, January 2\u20139). Personalized cross-silo federated learning on non-IID data. Proceedings of the AAAI Conference on Artificial Intelligence, Virtual.","DOI":"10.1609\/aaai.v35i9.16960"},{"key":"ref_34","doi-asserted-by":"crossref","unstructured":"Wang, C.-H., Huang, K.-Y., Chen, J.-C., Shuai, H.-H., and Cheng, W.-H. (2021, January 5\u20139). Heterogeneous Federated Learning Through Multi-Branch Network. Proceedings of the 2021 IEEE International Conference on Multimedia and Expo (ICME), Shenzhen, China.","DOI":"10.1109\/ICME51207.2021.9428189"},{"key":"ref_35","doi-asserted-by":"crossref","unstructured":"Yu, F., Zhang, W., Qin, Z., Xu, Z., Wang, D., Liu, C., Tian, Z., and Chen, X. (2020). Heterogeneous Federated Learning. arXiv.","DOI":"10.1145\/3447548.3467309"},{"key":"ref_36","doi-asserted-by":"crossref","first-page":"101830","DOI":"10.1016\/j.sysarc.2020.101830","article-title":"A Survey on Deep Transfer Learning to Edge Computing for Mitigating the COVID-19 Pandemic","volume":"108","author":"Sufian","year":"2020","journal-title":"J. Syst. Archit."},{"key":"ref_37","doi-asserted-by":"crossref","first-page":"1357","DOI":"10.1109\/TPDS.2019.2962435","article-title":"On-edge multi-task transfer learning: Model and practice with data-driven task allocation","volume":"31","author":"Chen","year":"2020","journal-title":"IEEE Trans. Parallel Distrib. Syst."},{"key":"ref_38","doi-asserted-by":"crossref","first-page":"e474","DOI":"10.7717\/peerj-cs.474","article-title":"Knowledge distillation in deep learning and its applications","volume":"7","author":"Alkhulaifi","year":"2021","journal-title":"PeerJ Comput. Sci."},{"key":"ref_39","doi-asserted-by":"crossref","unstructured":"Heo, B., Kim, J., Yun, S., Park, H., Kwak, N., and Choi, J.Y. (November, January 27). A comprehensive overhaul of feature distillation. Proceedings of the IEEE\/CVF International Conference on Computer Vision (ICCV) 2019, Seoul, Republic of Korea.","DOI":"10.1109\/ICCV.2019.00201"},{"key":"ref_40","doi-asserted-by":"crossref","first-page":"3048","DOI":"10.1109\/TPAMI.2021.3055564","article-title":"Knowledge Distillation and Student-Teacher Learning for Visual Intelligence: A Review and New Outlooks","volume":"44","author":"Wang","year":"2022","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"ref_41","doi-asserted-by":"crossref","unstructured":"Tao, Z., Xia, Q., and Li, Q. (2021, January 25\u201328). Neuron Manifold Distillation for Edge Deep Learning. Proceedings of the 2021 IEEE\/ACM 29th International Symposium on Quality of Service (IWQOS), Tokyo, Japan.","DOI":"10.1109\/IWQOS52092.2021.9521267"},{"key":"ref_42","unstructured":"Li, D., and Wang, J. (2019). FedMD: Heterogenous federated learning via model distillation. arXiv."},{"key":"ref_43","doi-asserted-by":"crossref","unstructured":"Jiang, D., Shan, C., and Zhang, Z. (2020, January 23\u201325). Federated Learning Algorithm Based on Knowledge Distillation. Proceedings of the 2020 International Conference on Artificial Intelligence and Computer Engineering (ICAICE), Beijing, China.","DOI":"10.1109\/ICAICE51518.2020.00038"},{"key":"ref_44","doi-asserted-by":"crossref","first-page":"31","DOI":"10.1186\/s13634-021-00744-4","article-title":"An efficient pruning scheme of deep neural networks for Internet of Things applications","volume":"2021","author":"Qi","year":"2021","journal-title":"EURASIP J. Adv. Signal Process."},{"key":"ref_45","first-page":"1135","article-title":"Learning both weights and connections for efficient neural networks","volume":"Volume 1","author":"Han","year":"2015","journal-title":"Advances in Neural Information Processing Systems 28 (NIPS 2015), Proceedings of the 28th International Conference on Neural Information Processing Systems (NIPS), Montreal, QC, Canada, 7\u201312 December 2015"},{"key":"ref_46","doi-asserted-by":"crossref","first-page":"194","DOI":"10.1587\/transinf.2020EDP7049","article-title":"REAP: A Method for Pruning Convolutional Neural Networks with Performance Preservation","volume":"104","author":"Kamma","year":"2021","journal-title":"IEICE Trans. Inf. Syst."},{"key":"ref_47","doi-asserted-by":"crossref","unstructured":"Luo, J.-H., Wu, J., and Lin, W. (2017, January 22\u201329). ThiNet: A Filter Level Pruning Method for Deep Neural Network Compression. Proceedings of the 2017 IEEE International Conference on Computer Vision (ICCV), Venice, Italy.","DOI":"10.1109\/ICCV.2017.541"},{"key":"ref_48","doi-asserted-by":"crossref","unstructured":"Liu, N., Ma, X., Xu, Z., Wang, Y., Tang, J., and Ye, J. (2019). AutoCompress: An Automatic DNN Structured Pruning Framework for Ultra-High Compression Rates. arXiv.","DOI":"10.1609\/aaai.v34i04.5924"},{"key":"ref_49","doi-asserted-by":"crossref","unstructured":"He, Y., Zhang, X., and Sun, J. (2017, January 22\u201329). Channel pruning for accelerating very deep neural networks. Proceedings of the IEEE International Conference on Computer Vision, Venice, Italy.","DOI":"10.1109\/ICCV.2017.155"},{"key":"ref_50","unstructured":"Gupta, S., Agrawal, A., Gopalakrishnan, K., and Narayanan, P. (2015, January 6\u201311). Deep Learning with Limited Numerical Precision. Proceedings of the 32nd International Conference on International Conference on Machine Learning ICML, Lille, France."},{"key":"ref_51","doi-asserted-by":"crossref","first-page":"141","DOI":"10.1109\/MSP.2012.2211477","article-title":"The MNIST Database of Handwritten Digit Images for Machine Learning Research","volume":"29","author":"Deng","year":"2012","journal-title":"IEEE Signal Process. Mag."},{"key":"ref_52","unstructured":"Cukierski, W. (2022, December 30). CIFAR-10-Object Recognition in Images. Kaggle. Available online: https:\/\/www.kaggle.com\/c\/cifar-10."},{"key":"ref_53","doi-asserted-by":"crossref","unstructured":"Leibe, B., Matas, J., Sebe, N., and Welling, M. (2016). Computer Vision\u2013ECCV 2016, Springer. Lecture Notes in Computer Science.","DOI":"10.1007\/978-3-319-46454-1"},{"key":"ref_54","unstructured":"Courbariaux, M., Hubara, I., Soudry, D., El-Yaniv, R., and Bengio, Y. (2016). Binarized Neural Networks: Training Neural Networks with Weights and Activations Constrained to +1 or \u22121. arXiv."},{"key":"ref_55","unstructured":"Hou, L., and Kwok, J.T.-Y. (May, January 30). Loss-aware weight quantization of deep networks. Proceedings of the ICLR 6th International Conference on Learning Representations, Vancouver, BC, Canada."},{"key":"ref_56","doi-asserted-by":"crossref","unstructured":"Zhou, A., Yao, A., Wang, K., and Chen, Y. (2018, January 18\u201323). Explicit Loss-Error-Aware Quantization for Low-Bit Deep Neural Networks. Proceedings of the 2018 IEEE\/CVF Conference on Computer Vision and Pattern Recognition, Salt Lake City, UT, USA.","DOI":"10.1109\/CVPR.2018.00982"},{"key":"ref_57","unstructured":"Zhou, A., Yao, A., Guo, Y., and Xu, L. (2017, January 24\u201326). Incremental network quantization: Towards lossless CNNs with low-precision weights. Proceedings of the ICLR 5th International Conference on Learning Representations, Toulon, France."},{"key":"ref_58","unstructured":"Burges, C.J., Bottou, L., Welling, M., Ghahramani, Z., and Weinberger, K.Q. (2013). Advances in Neural Information Processing Systems 26 (NIPS 2013), Proceedings of the Advances in Neural Information Processing Systems 26 (NIPS 2013), Lake Tahou, NV, USA, 5\u201310 December 2013, Curran Associates Inc."},{"key":"ref_59","unstructured":"Han, S., Mao, H., and Dally, W.J. (2016, January 2\u20134). Deep compression: Compressing deep neural networks with pruning, trained quantization and Huffman coding. Proceedings of the ICLR 4th International Conference on Learning Representations, San Juan, Puerto Rico."},{"key":"ref_60","unstructured":"Chen, W., Wilson, J.T., Tyree, S., Weinberger, K.Q., and Chen, Y. (2015, January 6\u201311). Compressing Neural Networks with the Hashing Trick. Proceedings of the 32 nd International Conference on Machine Learning, Lille, France."},{"key":"ref_61","doi-asserted-by":"crossref","first-page":"106783","DOI":"10.1016\/j.asoc.2020.106783","article-title":"Re-training and parameter sharing with the Hash trick for compressing convolutional neural networks","volume":"97","author":"Gou","year":"2020","journal-title":"Appl. Soft Comput."},{"key":"ref_62","unstructured":"Van Leeuwen, J. (1976, January 20\u201323). On the construction of huffman trees. Proceedings of the Third International Colloquium on Automata, Languages and Programming, Edinburgh, UK."},{"key":"ref_63","doi-asserted-by":"crossref","unstructured":"Sainath, T., Kingsbury, B., Sindhwani, V., Arisoy, E., and Ramabhadran, B. (2013, January 26\u201331). Low-Rank Matrix Factorization for Deep Neural Network Training with High-Dimensional Output Targets. Proceedings of the IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP), Vancouver, BC, Canada.","DOI":"10.1109\/ICASSP.2013.6638949"},{"key":"ref_64","doi-asserted-by":"crossref","unstructured":"Nakkiran, P., \u00c1lvarez, R., Prabhavalkar, R., and Parada, C. (2015, January 6\u201310). Compressing deep neural networks using a rank-constrained topology. Proceedings of the 16th Annual Conference of the International Speech Communication Association (INTERSPEECH 2015), Dresden, Germany.","DOI":"10.21437\/Interspeech.2015-351"},{"key":"ref_65","doi-asserted-by":"crossref","unstructured":"Merenda, M., Porcaro, C., and Iero, D. (2020). Edge Machine Learning for AI-Enabled IoT Devices: A Review. Sensors, 20.","DOI":"10.3390\/s20092533"},{"key":"ref_66","unstructured":"Sun, X., Wang, N., Chen, C.-y., Ni, J.-M., Agrawal, A., Cui, X., Venkataramani, S., El Maghraoui, K., Srinivasan, V., and Gopalakrishnan, K. (2020, January 6\u201312). Ultra-low precision 4-bit training of deep neural networks. Proceedings of the 34th International Conference on Neural Information Processing Systems, Vancouver, BC, Canada."},{"key":"ref_67","doi-asserted-by":"crossref","unstructured":"Lee, J., Kim, D., and Ham, B. (2021, January 20\u201325). Network Quantization with Element-wise Gradient Scaling. Proceedings of the 2021 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Nashville, TN, USA.","DOI":"10.1109\/CVPR46437.2021.00638"},{"key":"ref_68","doi-asserted-by":"crossref","unstructured":"Hutter, F., Kotthoff, L., and Vanschoren, J. (2019). Automated Machine Learning, Springer.","DOI":"10.1007\/978-3-030-05318-5"},{"key":"ref_69","doi-asserted-by":"crossref","first-page":"1889","DOI":"10.1162\/089976600300015187","article-title":"Gradient-Based Optimization of Hyperparameters","volume":"12","author":"Bengio","year":"2000","journal-title":"Neural Comput."},{"key":"ref_70","doi-asserted-by":"crossref","unstructured":"Li, A., Spyra, O., Perel, S., Dalibard, V., Jaderberg, M., Gu, C., Budden, D., Harley, T., and Gupta, P. (2019, January 4\u20138). A generalized framework for population based training. Proceedings of the 25th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining, Anchorage, AK, USA.","DOI":"10.1145\/3292500.3330649"},{"key":"ref_71","unstructured":"Jaderberg, M., Dalibard, V., Osindero, S., Czarnecki, W.M., Donahue, J., Razavi, A., Vinyals, O., Green, T., Dunning, I., and Simonyan, K. (2017). Population based training of neural networks. arXiv."},{"key":"ref_72","doi-asserted-by":"crossref","unstructured":"Xue, F., and Xin, J. (2021, January 20\u201322). Network Compression via Cooperative Architecture Search and Distillation. Proceedings of the 2021 4th International Conference on Artificial Intelligence for Industries (AI4I), Laguna Hills, CA, USA.","DOI":"10.1109\/AI4I51902.2021.00018"},{"key":"ref_73","doi-asserted-by":"crossref","unstructured":"Geraeinejad, V., Sinaei, S., Modarressi, M., and Daneshtalab, M. (2021, January 18\u201322). RoCo-NAS: Robust and Compact Neural Architecture Search. Proceedings of the 2021 International Joint Conference on Neural Networks (IJCNN), Shenzhen, China.","DOI":"10.1109\/IJCNN52387.2021.9534460"},{"key":"ref_74","doi-asserted-by":"crossref","unstructured":"Hutter, F., Kotthoff, L., and Vanschoren, J. (2019). Automated Machine Learning, Springer.","DOI":"10.1007\/978-3-030-05318-5"},{"key":"ref_75","unstructured":"Bichen, W., Dai, X., Zhang, P., Wang, Y., Sun, F., Wu, Y., Tian, Y., Vajda, P., Jia, Y., and Keutzer, K. (2019, January 15\u201320). Fbnet: Hardware-aware efficient convnet design via differentiable neural architecture search. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Long Beach, CA, USA."},{"key":"ref_76","unstructured":"Hao, C., and Chen, D. (November, January 31). Deep neural network model and FPGA accelerator co-design: Opportunities and challenges. Proceedings of the IEEE International Conference on Solid-State and Integrated Circuit Technology (ICSICT), Qingdao, China."},{"key":"ref_77","first-page":"3064","article-title":"Algorithm\/Accelerator Co-Design and Co-Search for Edge AI","volume":"69","author":"Zhang","year":"2022","journal-title":"IEEE Trans. Circuits Syst. II Express Briefs"},{"key":"ref_78","doi-asserted-by":"crossref","first-page":"2295","DOI":"10.1109\/JPROC.2017.2761740","article-title":"Efficient processing of deep neural networks: A tutorial and survey","volume":"105","author":"Sze","year":"2017","journal-title":"Proc. IEEE"},{"key":"ref_79","doi-asserted-by":"crossref","unstructured":"Li, J., Yan, G., Lu, W., Jiang, S., Gong, S., Wu, J., and Li, X. (2018, January 19\u201323). Smartshuttle: Optimizing off-chip memory accesses for deep learning accelerators. Proceedings of the Design, Automation Test in Europe Conference Exhibition (DATE), Dresden, Germany.","DOI":"10.23919\/DATE.2018.8342033"},{"key":"ref_80","unstructured":"Putra, R.V.W., Hanif, M.A., and Shafique, M. (2020, January 20\u201324). Drmap: A generic DRAM data mapping policy for energy-efficient processing of convolutional neural networks. Proceedings of the 57th ACM\/IEEE Design Automation Conference (DAC), San Francisco, CA, USA."},{"key":"ref_81","doi-asserted-by":"crossref","unstructured":"Kim, Y., Seshadri, V., Lee, D., Liu, J., and Mutlu, O. (2012, January 9\u201313). A case for exploiting subarray-level parallelism (salp) in dram. Proceedings of the 39th Annual International Symposium on Computer Architecture (ISCA), Portland, OR, USA.","DOI":"10.1109\/ISCA.2012.6237032"},{"key":"ref_82","first-page":"702","article-title":"Romanet: Fine grained reuse-driven off-chip memory access management and data organization for deep neural network accelerators","volume":"29","author":"Putra","year":"2021","journal-title":"IEEE TVLSI"},{"key":"ref_83","first-page":"2316","article-title":"Optimizing Off-Chip Memory Access for Deep Neural Network Accelerator","volume":"69","author":"Zheng","year":"2022","journal-title":"IEEE Trans. Circuits Syst. II Express Briefs"},{"key":"ref_84","doi-asserted-by":"crossref","first-page":"012003","DOI":"10.1088\/1757-899X\/495\/1\/012003","article-title":"Review of second-order optimization techniques in artificial neural networks backpropagation","volume":"495","author":"Tan","year":"2019","journal-title":"IOP Conf. Ser. Mater. Sci. Eng."},{"key":"ref_85","doi-asserted-by":"crossref","first-page":"1862","DOI":"10.1109\/TGCN.2022.3173420","article-title":"Communication-Efficient Federated Learning: A Second Order Newton-Type Method With Analog Over-the-Air Aggregation","volume":"6","author":"Krouka","year":"2022","journal-title":"IEEE Trans. Green Commun. Netw."},{"key":"ref_86","doi-asserted-by":"crossref","first-page":"2167","DOI":"10.1109\/COMST.2020.3007787","article-title":"Communication-Efficient Edge AI: Algorithms and Systems","volume":"22","author":"Shi","year":"2020","journal-title":"IEEE Commun. Surv. Tutor."},{"key":"ref_87","doi-asserted-by":"crossref","first-page":"1670","DOI":"10.1109\/TITS.2021.3107527","article-title":"AI Based Energy Efficient Routing Protocol for Intelligent Transportation System","volume":"23","author":"Goswami","year":"2022","journal-title":"IEEE Trans. Intell. Transp. Syst."},{"key":"ref_88","first-page":"5","article-title":"An energy-efficient heuristic based routing protocol in wireless sensor networks","volume":"3","author":"Alkadhmawee","year":"2016","journal-title":"Int. J. Innov. Res. Inf. Secur."},{"key":"ref_89","doi-asserted-by":"crossref","first-page":"30269","DOI":"10.1109\/ACCESS.2018.2833619","article-title":"Performance evaluation of integrated multi-access edge computing and fiber-wireless access networks","volume":"6","author":"Liu","year":"2018","journal-title":"IEEE Access"},{"key":"ref_90","doi-asserted-by":"crossref","unstructured":"Held, I., and Chen, A. (2010, January 16\u201319). Channel Estimation and Equalization Algorithms for Long Range Bluetooth Signal Reception. Proceedings of the IEEE Vehicular Technology Conference, Taipei, Taiwan.","DOI":"10.1109\/VETECS.2010.5493918"},{"key":"ref_91","doi-asserted-by":"crossref","first-page":"144","DOI":"10.1109\/MWC.2014.7000982","article-title":"IEEE 802.11AH: The WiFi approach for M2M communications","volume":"21","author":"Adame","year":"2014","journal-title":"IEEE Wirel. Commun."},{"key":"ref_92","first-page":"337","article-title":"An Evolutionary Secure Energy Efficient Routing Protocol in Internet of Things","volume":"10","author":"Reddy","year":"2017","journal-title":"Int. J. Intell. Eng. Syst."},{"key":"ref_93","unstructured":"Dutta, A., Bergou, E.H., Abdelmoniem, A.M., Yu, H.C., Narayan, S.A., Marco, C., and Panos, K. (2020, January 7\u201312). On the discrepancy between the theoretical analysis and practical implementations of compressed communication for distributed deep learning. Proceedings of the AAAI Conference on Artificial Intelligence, New York, NY, USA."},{"key":"ref_94","doi-asserted-by":"crossref","unstructured":"Guo, B., Liu, Y., and Zhang, C. (2021). A Partition Based Gradient Compression Algorithm for Distributed Training in AIoT. Sensors, 21.","DOI":"10.3390\/s21061943"},{"key":"ref_95","unstructured":"Tsuzuku, Y., Imachi, H., and Akiba, T. (2018). Variance-based Gradient Compression for Efficient Distributed Deep Learning. arXiv."},{"key":"ref_96","unstructured":"Abdelmoniem, A.M., Elzanaty, A., Alouini, M.-S., and Canini, M. (2021). An efficient statistical-based gradient compression technique for distributed training systems. arXiv."},{"key":"ref_97","doi-asserted-by":"crossref","unstructured":"Feng, J., and Huang, D. (2021, January 20\u201325). Optimal Gradient Checkpoint Search for Arbitrary Computation Graphs. Proceedings of the 2021 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Nashville, TN, USA.","DOI":"10.1109\/CVPR46437.2021.01127"},{"key":"ref_98","doi-asserted-by":"crossref","first-page":"1403","DOI":"10.1109\/TCI.2020.3025735","article-title":"Memory-Efficient Learning for Large-Scale Computational Imaging","volume":"6","author":"Kellman","year":"2020","journal-title":"IEEE Trans. Comput. Imaging"},{"key":"ref_99","unstructured":"Pleiss, G., Chen, D., Huang, G., Li, T., van der Maaten, L., and Weinberger, Q. (2017). Memory-Efficient Implementation of DenseNets. arXiv."},{"key":"ref_100","unstructured":"Howard, A.G., Zhu, M., Chen, B., Kalenichenko, D., Wang, W., Weyand, T., Andreetto, M., and Adam, H. (2017). MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications. arXiv."},{"key":"ref_101","doi-asserted-by":"crossref","first-page":"13849","DOI":"10.1109\/JIOT.2021.3088875","article-title":"A Survey of Recent Advances in Edge-Computing-Powered Artificial Intelligence of Things","volume":"8","author":"Chang","year":"2021","journal-title":"IEEE Internet Things J."},{"key":"ref_102","doi-asserted-by":"crossref","first-page":"7457","DOI":"10.1109\/JIOT.2020.2984887","article-title":"Edge Intelligence: The Confluence of Edge Computing and Artificial Intelligence","volume":"7","author":"Deng","year":"2020","journal-title":"IEEE Internet Things J."},{"key":"ref_103","doi-asserted-by":"crossref","first-page":"1738","DOI":"10.1109\/JPROC.2019.2918951","article-title":"Edge Intelligence: Paving the Last Mile of Artificial Intelligence With Edge Computing","volume":"107","author":"Zhou","year":"2019","journal-title":"Proc. IEEE"},{"key":"ref_104","doi-asserted-by":"crossref","unstructured":"Sadatdiynov, K., Cui, L., Zhang, L., Huang, J.Z., Salloum, S., and Mahmud, M.S. (Digit. Commun. Netw., 2022). A review of optimization methods for computation offloading in edge computing networks, Digit. Commun. Netw., in press.","DOI":"10.1016\/j.dcan.2022.03.003"},{"key":"ref_105","doi-asserted-by":"crossref","unstructured":"Umair, M., Cheema, M.A., Cheema, O., Li, H., and Lu, H. (2021). Impact of COVID-19 on IoT Adoption in Healthcare, Smart Homes, Smart Buildings, Smart Cities, Transportation and Industrial IoT. Sensors, 21.","DOI":"10.3390\/s21113838"},{"key":"ref_106","doi-asserted-by":"crossref","first-page":"527","DOI":"10.1049\/iet-com.2017.0619","article-title":"Blockchain-based efficient privacy preserving and data sharing scheme of content-centric network in 5G","volume":"12","author":"Fan","year":"2017","journal-title":"IET Commun."},{"key":"ref_107","doi-asserted-by":"crossref","unstructured":"Nayak, S., Patgiri, R., Waikhom, L., and Ahmed, A. (Digit. Commun. Netw., 2022). A review on edge analytics: Issues, challenges, opportunities, promises, future directions, and applications, Digit. Commun. Netw., in press.","DOI":"10.1016\/j.dcan.2022.10.016"}],"container-title":["Sensors"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/1424-8220\/23\/3\/1279\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,10]],"date-time":"2025-10-10T18:13:43Z","timestamp":1760120023000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/1424-8220\/23\/3\/1279"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,1,22]]},"references-count":107,"journal-issue":{"issue":"3","published-online":{"date-parts":[[2023,2]]}},"alternative-id":["s23031279"],"URL":"https:\/\/doi.org\/10.3390\/s23031279","relation":{},"ISSN":["1424-8220"],"issn-type":[{"value":"1424-8220","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,1,22]]}}}