Learning IoT in Edge: Deep Learning for the Internet of Things with Edge Computing
Open accessThe DOI matches its Crossref record; 15 of the 15 references it cites were found in a registry or an index.
Abstract
Deep learning is a promising approach for extracting accurate information from raw sensor data from IoT devices deployed in complex environments. Because of its multilayer structure, deep learning is also appropriate for the edge computing environment. Therefore, in this article, we first introduce deep learning for IoTs into the edge computing environment. Since existing edge nodes have limited processing capability, we also design a novel offloading strategy to optimize the performance of IoT deep learning applications with edge computing. In the performance evaluation, we test the performance of executing multiple deep learning tasks in an edge computing environment with our strategy. The evaluation results show that our method outperforms other optimization solutions on deep learning for IoT.
Overview
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
The source backs part of the claim, not all of it — or backs it for a different population, condition or comparison.
In the citing paper
“There are some studies that exist in DTL-EC as in [68] and some related work mentioned in Section 3.”
From A survey on deep transfer learning to edge computing for mitigating the COVID-19 pandemic (2020) · cites this paper as [68]
Experimental — accuracy not yet measuredIn the citing paper
“Traditional centralized machine learning (ML) approaches cannot support such ubiquitous deployments and applications due to infrastructure shortcomings such as limited communication bandwidth, intermittent network connectivity, and strict delay constraints [1].”
From Privacy and Robustness in Federated Learning: Attacks and Defenses (2024) · cites this paper as [1]
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Citations
Cites
Collaborative Mobile Edge Computing in 5G Networks: New Paradigms, Scenarios, and Challenges
Tran, T. X., Hajisami, A., Pandey, P., & Pompili, D. (2017) · IEEE Communications Magazine · doi:10.1109/mcom.2017.1600863 · Cited by 874 · cited 1×
“The other one is, the cloud resources are optimized by enabling edge nodes with computing ability [14].”
BackgroundFadlullah, Z. M., Tang, F., Mao, B., Kato, N., Akashi, O., Inoue, T., & Mizutani, K. (2017) · IEEE Communications Surveys & Tutorials · doi:10.1109/comst.2017.2707140 · Cited by 810 · cited 1×
“I N recent years, deep learning becomes an important methodology in many informatics fields such as vision recognition, natural language processing, and bioinformatics [1] [2].”
BackgroundVerma, S., Kawamoto, Y., Fadlullah, Z. M., Nishiyama, H., & Kato, N. (2017) · IEEE Communications Surveys & Tutorials · doi:10.1109/comst.2017.2694469 · Cited by 422
Serving at the Edge: A Scalable IoT Architecture Based on Transparent Computing
Ren, J., Guo, H., Xu, C., & Zhang, Y. (2017) · IEEE Network · doi:10.1109/mnet.2017.1700030 · Cited by 416 · cited 1×
“Edge computing is another important technology for IoT services [5] [6] [7].”
BackgroundKato, N., Fadlullah, Z. M., Mao, B., Tang, F., Akashi, O., Inoue, T., & Mizutani, K. (2017) · IEEE Wireless Communications · doi:10.1109/mwc.2016.1600317wc · Cited by 400 · cited 1×
“I N recent years, deep learning becomes an important methodology in many informatics fields such as vision recognition, natural language processing, and bioinformatics [1] [2].”
BackgroundRodrigues, T. G., Suto, K., Nishiyama, H., & Kato, N. (2017) · IEEE Transactions on Computers · doi:10.1109/tc.2016.2620469 · Cited by 374 · cited 1×
“Edge computing is another important technology for IoT services [5] [6] [7].”
BackgroundLiu, C., Cao, Y., Luo, Y., Chen, G., Vokkarane, V., Yunsheng, M., Chen, S., & Hou, P. (2018) · IEEE Transactions on Services Computing · doi:10.1109/tsc.2017.2662008 · Cited by 333 · cited 1×
“Liu et al. [15] proposed the first work that introduces deep learning into the edge computing environment.”
BackgroundDeepEar: robust smartphone audio sensing in unconstrained acoustic environments using deep learning
Lane, N. D., Georgiev, P., & Qendro, L. (2015) · Proceedings of the 2015 ACM International Joint Conference on Pervasive and Ubiquitous Computing · doi:10.1145/2750858.2804262 · Cited by 310 · cited 1×
“[10] proposed new acceleration engines, such as DeepEar and DeepX, to support different deep learning applications in latest mobile system-on-chips (SoC).”
MethodMobile big data analytics using deep learning and apache spark
Alsheikh, M. A., Niyato, D., Lin, S., Tan, H.-P., & Han, Z. (2016) · IEEE Network · doi:10.1109/mnet.2016.7474340 · Cited by 272 · cited 1×
“[13] proposed a framework to combine deep learning algorithms and Apache”
MethodBhattacharya, S., & Lane, N. D. (2016) · Proceedings of the 14th ACM Conference on Embedded Networked Sensor Systems CD-ROM · doi:10.1145/2994551.2994564 · Cited by 236
Cited by
Items 101–200 of 1,000
Task Partitioning and Offloading in DNN-Task Enabled Mobile Edge Computing Networks
Gao, M., Shen, R., Shi, L. X., Qi, W., Li, J., & Li, Y. (2021) · IEEE Transactions on Mobile Computing · doi:10.1109/tmc.2021.3114193 · Cited by 175
“…expensive on the side of mobile devices (MDs) because of limited energy and computing capability of MDs. Recently, mobile edge computing (MEC) is a promising technology to meet the high-computation requirements of DNN tasks and relieve the computation burden of MDs [5], [6], [7], [8], [9].”
BackgroundSurvey:Time-series data preprocessing: A survey and an empirical analysis
Tawakuli, A., Havers, B., Gulisano, V. M., Kaiser, D., & Engel, T. (2024) · Journal of Engineering Research · doi:10.1016/j.jer.2024.02.018 · Cited by 173
Gyamfi, E., & Jurcut, A. (2022) · Sensors · doi:10.3390/s22103744 · Cited by 171
“The Internet of Things has experienced tremendous growth in area-specific applications such as healthcare, smart transportation systems, smart agriculture, and industries to improve socio-economic development in recent years [1].”
BackgroundTavana, M., Hajipour, V., & Oveisi, S. (2020) · Internet of Things · doi:10.1016/j.iot.2020.100262 · Cited by 171
Deep Unified Model For Face Recognition Based on Convolution Neural Network and Edge Computing
Khan, M. Z., Harous, S., Hassan, S. U., Ghani Khan, M. U., Iqbal, R., & Mumtaz, S. (2019) · IEEE Access · doi:10.1109/access.2019.2918275 · Cited by 170
“It is also helpful in reducing the response time and data latency and making the data transmission more safe and secure [1], [2].”
BackgroundAHAR: Adaptive CNN for Energy-Efficient Human Activity Recognition in Low-Power Edge Devices
Rashid, N., Demirel, B. U., & Abdullah Al Faruque, M. (2022) · IEEE Internet of Things Journal · doi:10.1109/jiot.2022.3140465 · Cited by 169
AI-Enabled Secure Microservices in Edge Computing: Opportunities and Challenges
Al-Doghman, F., Moustafa, N., Khalil, I., Sohrabi, N., Tari, Z., & Zomaya, A. Y. (2023) · IEEE Transactions on Services Computing · doi:10.1109/tsc.2022.3155447 · Cited by 168
“There is a decrease in the efficiency of the centralised cloud computing paradigms regarding the processing and analysis of big data, because of the difficulties in transferring such data amount, which has limited the performance of edge networks [6].”
BackgroundRETRACTED: Intelligent edge computing based on machine learning for smart city
Lv, Z., Chen, D., Lou, R., & Wang, Q. (2021) · Future Generation Computer Systems · doi:10.1016/j.future.2020.08.037 · Cited by 168
RetractedMijuskovic, A., Chiumento, A., Bemthuis, R., Aldea, A., & Havinga, P. (2021) · Sensors · doi:10.3390/s21051832 · Cited by 133
“In edge computing, data processing is offloaded onto the edge devices [14].”
BackgroundMethodYang, H., Liang, Y., Yuan, J., Yao, Q., Yu, A., & Zhang, J. (2020) · IEEE Transactions on Industrial Informatics · doi:10.1109/tii.2020.2964563 · Cited by 165
“we intercepted with the traffic in an actual multidimensional resource hybrid network model [32], [33], we select to divide”
MethodYang, B., Cao, X., Yuen, C., & Qian, L. (2021) · IEEE Internet of Things Journal · doi:10.1109/jiot.2020.3016694 · Cited by 164
Missing Value Imputation for Industrial IoT Sensor Data With Large Gaps
Liu, Y., Dillon, T. S., Yu, W., Rahayu, W. J., & Mostafa, F. (2020) · IEEE Internet of Things Journal · doi:10.1109/jiot.2020.2970467 · Cited by 164
“…smart healthcare, etc. Recently, edge computing has been proposed to offload computing tasks from the centralized cloud to the edge near IoT devices [12], [13], such as decentralizing data preprocessing at the edge of the network and moving some preprocessing procedures, such as noise detection and…”
Green AI for IIoT: Energy Efficient Intelligent Edge Computing for Industrial Internet of Things
Zhu, S., Ota, K., & Dong, M. (2022) · IEEE Transactions on Green Communications and Networking · doi:10.1109/tgcn.2021.3100622 · Cited by 162
Self-citationLatif, S., Driss, M., Boulila, W., Huma, Z. E., Jamal, S. S., Idrees, Z., & Ahmad, J. (2021) · Sensors · doi:10.3390/s21227518 · Cited by 161
“Some extra efforts are required to address this problem [150].”
BackgroundInternet of Things 2.0: Concepts, Applications, and Future Directions
Zhou, I., Makhdoom, I., Shariati, N., Raza, M. A., Keshavarz, R., Lipman, J., Abolhasan, M., & Jamalipour, A. (2021) · IEEE Access · doi:10.1109/access.2021.3078549 · Cited by 160
“This type of application is defined in this article as process offloading applications [46], [130]–[132].”
BackgroundInfluentialIntelligent Cooperative Edge Computing in Internet of Things
Gong, C., Lin, F., Gong, X., & Lu, Y. (2020) · IEEE Internet of Things Journal · doi:10.1109/jiot.2020.2986015 · Cited by 158
“Therefore, the entire process of AI, including the training process and the inference process, is desired in the edge [14].”
BackgroundA Cloud-Edge Collaboration Framework for Cognitive Service
Ding, C., Zhou, A., Liu, Y., Chang, R. N., Hsu, C.-H., & Wang, S. (2022) · IEEE Transactions on Cloud Computing · doi:10.1109/tcc.2020.2997008 · Cited by 158
“[14] proposed an edge computing structure for Internet of Things (IoT) deep learning tasks.”
BackgroundA survey on deep transfer learning to edge computing for mitigating the COVID-19 pandemic
Sufian, A., Ghosh, A., Sadiq, A. S., & Smarandache, F. (2020) · Journal of Systems Architecture · doi:10.1016/j.sysarc.2020.101830 · Cited by 156
“However, researchers are working hard to cope with the challenges, as results in many computing ideas, optimized model, as well as some computing accelerator devices, comes in picture [70, 71].”
BackgroundMohanty, S. P., Yanambaka, V. P., Kougianos, E., & Puthal, D. (2020) · IEEE Consumer Electronics Magazine · doi:10.1109/mce.2019.2953758 · Cited by 156
“ns of resource constrained and low performance devices [16]. These architectures are finding their way into many mission-critical application scenarios such as military, healthcare, and industrial IoT [17, 18]. Such mission-critical applications also demand the highest reliability, security and privacy. There have been…”
BackgroundVideo Caching, Analytics, and Delivery at the Wireless Edge: A Survey and Future Directions
Jedari, B., Premsankar, G., Illahi, G. K., Francesco, M. D., Mehrabi, A., & Ylä-Jääski, A. (2020) · IEEE Communications Surveys & Tutorials · doi:10.1109/comst.2020.3035427 · Cited by 155
“[162] focus on the latency and bandwidth constraints of video surveillance.”
BackgroundDigital Twins in Unmanned Aerial Vehicles for Rapid Medical Resource Delivery in Epidemics
Lv, Z., Chen, D., Feng, H., Zhu, H., & Lv, H. (2022) · IEEE Transactions on Intelligent Transportation Systems · doi:10.1109/tits.2021.3113787 · Cited by 143
“In this regard, the Online Hard Example Mining (OHEM) strategy [28] is adopted to optimize the network training process.”
MethodEdge Intelligence for Data Handling and Predictive Maintenance in IIOT
Hafeez, T., Xu, L., & McArdle, G. (2021) · IEEE Access · doi:10.1109/access.2021.3069137 · Cited by 156
Accelerating Federated Learning With Cluster Construction and Hierarchical Aggregation
Wang, Z., Xu, H., Liu, J., Xu, Y., Huang, H., & Zhao, Y. (2022) · IEEE Transactions on Mobile Computing · doi:10.1109/tmc.2022.3147792 · Cited by 155
“Since data are generated at the network edge, mobile edge computing (MEC) is a natural alternative[3], [4], which uses the computing and storage resources of devices to perform data processing close to the data generators.”
BackgroundMobile Internet of Things Under Data Physical Fusion Technology
Lv, Z., & Song, H. (2019) · IEEE Internet of Things Journal · doi:10.1109/jiot.2019.2954588 · Cited by 153
“Li et al. (2018) applied the deep learning algorithm to the edge computing environment and designed a new unloading strategy to optimize the performance of the IoT deep learning application with edge computing based on the limited existing edge processing ability.”
MethodResultYu, W., Liu, Y., Dillon, T. S., & Rahayu, W. J. (2022) · IEEE Transactions on Industrial Informatics · doi:10.1109/tii.2022.3178732 · Cited by 153
“Instead of focusing on elaborating the optimized computing of machine learning methods when incorporated with edge computing [15], [16], we introduce an integrated architecture, which demonstrates the overall working principle of edge computing facilitating fault detection in an IoT paradigm.”
BackgroundMethodA survey on machine learning in Internet of Things: Algorithms, strategies, and applications
Messaoud, S., Bradai, A., Bukhari, S. H. R., Quang, P. T. A., Ahmed, O. B., & Atri, M. (2020) · Internet of Things · doi:10.1016/j.iot.2020.100314 · Cited by 151
Badidi, E., Moumane, K., & Ghazi, F. E. (2023) · IEEE Access · doi:10.1109/access.2023.3300658 · Cited by 154
“Increasing computing power at the edge, combined with the ease of using machine learning and deep learning, makes edge devices extremely intelligent [18], [19], [20], [21], [22].”
BackgroundRoldán-Gómez, J., Boubeta-Puig, J., Martínez, J. L., & Ortiz, G. (2020) · Expert Systems with Applications · doi:10.1016/j.eswa.2020.113251 · Cited by 149
A Survey on IoT Big Data: Current Status, 13 V’s Challenges, and Future Directions
Bansal, M., Chana, I., & Clarke, S. (2020) · ACM Computing Surveys · doi:10.1145/3419634 · Cited by 146
“Venue Li et al. 2018 [81] Performed Layered execution of DL model among Edge-Cloud Servers by partial-offloading of layers of DL network among edge-cloud servers based on the computing and communication capacity of edge servers.”
MethodEfficient Resource Allocation for On-Demand Mobile-Edge Cloud Computing
Chen, X., Li, W., Lu, S., Zhou, Z., & Fu, X. (2018) · IEEE Transactions on Vehicular Technology · doi:10.1109/tvt.2018.2846232 · Cited by 145
Nagarajan, S. M., Devarajan, G. G., Chatterjee, P., Alnumay, W. S., & Ghosh, U. (2021) · Sustainable Cities and Society · doi:10.1016/j.scs.2021.102945 · Cited by 144
A survey on deploying mobile deep learning applications: A systemic and technical perspective
Wang, Y., Wang, J., Zhang, W., Zhan, Y., Guo, S., Zheng, Q., & Wang, X. (2022) · Digital Communications and Networks · doi:10.1016/j.dcan.2021.06.001 · Cited by 110
Energy-Aware Application Placement in Mobile Edge Computing: A Stochastic Optimization Approach
Badri, H., Bahreini, T., Grosu, D., & Yang, K. (2020) · IEEE Transactions on Parallel and Distributed Systems · doi:10.1109/tpds.2019.2950937 · Cited by 134
“This has made MEC an attractive infrastructure for many applications, such as machine learning [8], [9], [10], vehicular computing [11], and Internet of Things (IoT) [12], [13].”
BackgroundDave, S., Baghdadi, R., Nowatzki, T., Avancha, S., Shrivastava, A., & Li, B. (2021) · Proceedings of the IEEE · doi:10.1109/jproc.2021.3098483 · Cited by 111
“n [1]–[6] and detection [7]–[13]), media processing [14]–[22] and generation [23], [24], recommendation systems [25], [26], largescale scientific computing [27], embedded systems [28], edge processing [29], and even for optimizing system executions [30], [31] and designing the hardware [32] and software systems [33]. T…”
BackgroundSiddiqui, S., Hameed, S., Shah, S. A., Ahmad, I., Aneiba, A., Draheim, D., & Dustdar, S. (2022) · IEEE Access · doi:10.1109/access.2022.3188311 · Cited by 140
“In combination with edge computing, the emergence of the IoT has recently opened up several possibilities for new applications [225].”
BackgroundDeep Learning-Constructed Joint Transmission-Recognition for Internet of Things
Lee, C.-H., Lin, J.-W., Chen, P.-H., & Chang, Y.-C. (2019) · IEEE Access · doi:10.1109/access.2019.2920929 · Cited by 126
A Survey on Deep Learning Empowered IoT Applications
Ma, X., Yao, T., Hu, M., Dong, Y., Liu, W., Wang, F., & Liu, J. (2019) · IEEE Access · doi:10.1109/access.2019.2958962 · Cited by 138
“The recent breakthroughs in deep learning and hardware design have enabled researchers to train much more powerful models, which highly empower many applications such as crowdsourced delivery [11], network caching [12], energy management [13] and edge computing [14].”
BackgroundGbadamosi, A.-Q., Oyedele, L. O., Delgado, J. M. D., Kusimo, H., Akanbi, L., Olawale, O. A., & Muhammed-Yakubu, N. T. (2020) · Automation in Construction · doi:10.1016/j.autcon.2020.103486 · Cited by 138
IoT Network Security from the Perspective of Adversarial Deep Learning
Sagduyu, Y. E., Shi, Y., & Erpek, T. (2019) · IEEE International Conference on Sensing, Communication, and Networking (SECON) · doi:10.1109/sahcn.2019.8824956 · Cited by 136
“classification, and prediction tasks [3], [4] to learn from and adapt to the underlying spectrum environment characterized by heterogeneous devices, different priorities, channel, interference, and traffic effects.”
BackgroundMachine Learning in Resource-Scarce Embedded Systems, FPGAs, and End-Devices: A Survey
Branco, S., Ferreira, A. G., & Cabral, J. (2019) · Electronics · doi:10.3390/electronics8111289 · Cited by 136
“If the data has to leave the local network, the privacy can be increased with the use of deep neural networks’ (DNN) semantics [28].”
BackgroundRathore, S., & Park, J. H. (2021) · IEEE Transactions on Industrial Informatics · doi:10.1109/tii.2020.3040968 · Cited by 113
“Since the edge server is nearer to the UEs, and only one hop is required in most cases, this leads to the reduction of communication bandwidth and latency [9].”
BackgroundAdaptive parallel execution of deep neural networks on heterogeneous edge devices
Zhou, L., Samavatian, M. H., Bacha, A., Majumdar, S., & Teodorescu, R. (2019) · ACM/IEEE Symposium on Edge Computing (SEC) · doi:10.1145/3318216.3363312 · Cited by 134
“Edge processing has the benefit of keeping data closer to its source to provide real-time responses while protecting the privacy of the end-user [17, 29].”
BackgroundA Stable AI-Based Binary and Multiple Class Heart Disease Prediction Model for IoMT
Yuan, X., Chen, J., Zhang, K., Wu, Y., & Yang, T. (2021) · IEEE Transactions on Industrial Informatics · doi:10.1109/tii.2021.3098306 · Cited by 136
He, W., Guo, S., Guo, S., Qiu, X., & Qi, F. (2020) · IEEE Internet of Things Journal · doi:10.1109/jiot.2020.2981338 · Cited by 133
“As indicated in [13], the average task queueing delay in the M/D/1 queueing model is an improved upper bound over that in the G/D/1 system, especially when the input tasks are lightly loaded.”
BackgroundPain-FL: Personalized Privacy-Preserving Incentive for Federated Learning
Sun, P., Che, H., Wang, Z., Wang, Y., Wang, T., Wu, L., & Shao, H. (2021) · IEEE Journal on Selected Areas in Communications · doi:10.1109/jsac.2021.3118354 · Cited by 133
Bharati, S., & Podder, P. (2022) · Security and Communication Networks · doi:10.1155/2022/8951961 · Cited by 133
“intelligent home, IoT devices automatically talk to each other to form a completely intelligent home [14].”
BackgroundMethodFedASMU: Efficient Asynchronous Federated Learning with Dynamic Staleness-Aware Model Update
Liu, J., Jia, J., Che, T., Huo, C., Ren, J., Zhou, Y., Dai, H., & Dou, D. (2024) · Proceedings of the AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v38i12.29297 · Cited by 131
Wireless Networked Multirobot Systems in Smart Factories
Chen, K., Lin, S., Hsiao, J.-H., Liu, C., Molisch, A. F., & Fettweis, G. P. (2020) · Proceedings of the IEEE · doi:10.1109/jproc.2020.3033753 · Cited by 131
“Recent works in [129]–[132], for example, showed that distributed (deep) learning at the wireless edge can effectively optimize the performances of IIoT systems for various mission-critical applications.”
BackgroundMachine Learning in IoT Security: Current Solutions and Future Challenges
Hussain, F., Hussain, R., Hassan, S. A., & Hossain, E. (2020) · IEEE Communications Surveys & Tutorials · doi:10.1109/comst.2020.2986444 · Cited by 129
“DL is also useful in Edge computing and for scheduling of IoT devices and mobile crowd sensing in Fog computing environment [100], [101].”
MethodZero Knowledge Clustering Based Adversarial Mitigation in Heterogeneous Federated Learning
Chen, Z., Tian, P., Liao, W., & Yu, W. (2021) · IEEE Transactions on Network Science and Engineering · doi:10.1109/tnse.2020.3002796 · Cited by 114
Energy-Aware Analog Aggregation for Federated Learning with Redundant Data
Sun, Y., Zhou, S., & Gunduz, D. (2020) · ICC 2020 - 2020 IEEE International Conference on Communications (ICC) · doi:10.1109/icc40277.2020.9148853 · Cited by 111
Byzantine-Resilient Decentralized Stochastic Gradient Descent
Guo, S., Zhang, T., Yu, H., Xie, X., Ma, L., Xiang, T., & Liu, Y. (2021) · IEEE Transactions on Circuits and Systems for Video Technology · doi:10.1109/tcsvt.2021.3116976 · Cited by 129
“Nowadays, it is a trend to learn and deploy powerful DL models on edge devices [1]–[5] for various AI tasks (e.”
BackgroundEdge AI for Internet of Energy: Challenges and perspectives
Himeur, Y., Sayed, A. N., Alsalemi, A., Bensaali, F., & Amira, A. (2023) · Internet of Things · doi:10.1016/j.iot.2023.101035 · Cited by 130
HERO: Human Emotions Recognition for Realizing Intelligent Internet of Things
Hua, W., Dai, F., Huang, L., Xiong, J., & Gui, G. (2019) · IEEE Access · doi:10.1109/access.2019.2900231 · Cited by 128
“INTRODUCTION Human emotions recognition (HERO) is considered one of important techniques for realizing intelligent Internet of Things (IIoT) which plays the interactive role among humanto-human, human to things [1]– [3] and even security considerations [4]– [7].”
BackgroundEnergy-Aware Inference Offloading for DNN-Driven Applications in Mobile Edge Clouds
Xu, Z., Zhao, L., Liang, W., RANA, O. F., Zhou, P., Xia, Q., Xu, W., & Wu, G. (2020) · IEEE Transactions on Parallel and Distributed Systems · doi:10.1109/tpds.2020.3032443 · Cited by 128
“[27], [28] designed offloading strategies for both IoT applications and mobile crowdsensing applications in edge computing by leveraging deep learning and reinforcement learning techniques.”
BackgroundResource Allocation for Edge Computing in IoT Networks via Reinforcement Learning
Liu, X., Qin, Z., & Gao, Y. (2019) · International Conference on Communications · doi:10.1109/icc.2019.8761385 · Cited by 127
“Deep learning achieves excellent performance with large amount of data generated by IoT applications [15].”
BackgroundDeep Reinforcement Scheduling for Mobile Crowdsensing in Fog Computing
Li, H., Ota, K., & Dong, M. (2019) · ACM Transactions on Internet Technology · doi:10.1145/3234463 · Cited by 126
“provide a hierarchical scheduling for deep learning–based IoT applications in edge computing, which divided deep learning networks into different offloading layers [25].”
BackgroundSelf-citationJoint Source–Channel Coding: Fundamentals and Recent Progress in Practical Designs
Gündüz, D., Wigger, M., Tung, T.-Y., Zhang, P., & Xiao, Y. L. (2024) · Proceedings of the IEEE · doi:10.1109/jproc.2024.3477331 · Cited by 126
“Firstly, as ML tools and applications become increasingly widespread, they are expected to be deployed on mobile edge devices, requiring distributed implementations of training as well as inference tasks [4]–[10].”
CovidSens: a vision on reliable social sensing for COVID-19
Rashid, M. T., & Wang, D. (2020) · Artificial Intelligence Review · doi:10.1007/s10462-020-09852-3 · Cited by 124
“s, MLPs, and RNNs have been originally developed for powerful centralized hardware (e.g., GPU clusters) and are not tailored for resource constrained smart devices residing at the edge of the network [79,80,81]. In particular, current AI algorithms are associated with model update processes that operate in a centraliz…”
BackgroundJin, X., Yang, N.-X., Wang, X., Bai, Y., Su, T., & Kong, J. (2020) · Sensors · doi:10.3390/s20051334 · Cited by 122
“In [59], the performance of IoT deep learning applications was optimized by edge computing.”
MethodZhang, X., Ming, X., Liu, Z., Yin, D., Chen, Z., & Chang, Y. (2018) · The International Journal of Advanced Manufacturing Technology · doi:10.1007/s00170-018-3106-3 · Cited by 121
“The third wave peaks are due to the development of deep learning [5], the development of mobile Internet, and big data.”
BackgroundAnand, A., Rani, S., Anand, D., Aljahdali, H. M., & Kerr, D. (2021) · Sensors · doi:10.3390/s21196346 · Cited by 121
“In [58], a great improvement is being achieved in the performance of DL over ML.”
BackgroundMulti-Agent-Based Unsupervised Detection of Energy Consumption Anomalies on Smart Campus
Weng, Y., Zhang, N., & Xia, C. (2019) · IEEE Access · doi:10.1109/access.2018.2886583 · Cited by 116
“Deep learning is a promising approach to extracting accurate information from raw sensor data that has been deployed in complex environments [2].”
BackgroundBringing Deep Learning at the Edge of Information-Centric Internet of Things
Khelifi, H., Luo, S., Nour, B., Sellami, A., Moungla, H., Ahmed, S. H., & Guizani, M. (2018) · IEEE Communications Letters · doi:10.1109/lcomm.2018.2875978 · Cited by 119
“Deploying DL services closer to consumers [7] with the computation processing enables a fast data processing, and enhances the business control and management.”
BackgroundEnergy-Optimal Dynamic Computation Offloading for Industrial IoT in Fog Computing
Chen, S., Zheng, Y., Lu, W., Varadarajan, V., & Wang, K. (2019) · IEEE Transactions on Green Communications and Networking · doi:10.1109/tgcn.2019.2960767 · Cited by 119
“These properties that inspire the fog computing paradigm can be applied in various fields, such as the IoT [8], vehicular networks [9], and information-centric networks [10].”
BackgroundLow-Cost Automatic Weather Stations in the Internet of Things
Ιωάννου, Κ., Karampatzakis, D., Amanatidis, P., Aggelopoulos, V., & Karmiris, I. (2021) · Information · doi:10.3390/info12040146 · Cited by 119
“In the IoT intermediate layer, DL [34] will play a key role enabling a technology for data processing closer to the data sources and advanced techniques for computational offloading to the edge [35].”
MethodA Systematic Literature Review on Distributed Machine Learning in Edge Computing
Filho, C. P., Marques, E. L., Chang, V. I. C., dos SANTOS, L., Bernardini, F., Pires, P. F., Ochi, L. S., & Delicato, F. C. (2022) · Sensors · doi:10.3390/s22072665 · Cited by 120
“H. Li et al. [35] Model Partitioning They divide the NN layers and deploy the part with the lower ones (closer to the input) into edge servers and the part with higher layers (closer to the output) into the cloud for offloading processing.”
A Deep Learning-Based Intelligent Medicine Recognition System for Chronic Patients
Chang, W., Chen, L.-B., Hsu, C.-H., Lin, C., & Yang, T.-C. (2019) · IEEE Access · doi:10.1109/access.2019.2908843 · Cited by 118
“The proposed system incorporates edge computing [34] capabilities to reduce delay and to make the connected application more sensitive, thus enabling realtime computing capabilities and the performance optimization of applications based on artificial intelligence over the Internet of Things (AIoT).”
MethodWu, J., Xiong, F., & Li, C. (2019) · IEEE Access · doi:10.1109/access.2019.2930637 · Cited by 120
“[7] designed a novel offloading strategy to optimize the performance of IoT deep learning applications.”
BackgroundSun, H., Yu, H., Fan, G., & Chen, L. (2019) · Peer-to-Peer Networking and Applications · doi:10.1007/s12083-019-00783-7 · Cited by 117
“Thus, the approach is described as fog computing (or edge computing) [4].”
BackgroundMethodInfluentialA Tensor-Based Multiattributes Visual Feature Recognition Method for Industrial Intelligence
Wang, X., Yang, L. T., Song, L., Wang, H. H., Ren, L., & Deen, M. J. (2020) · IEEE Transactions on Industrial Informatics · doi:10.1109/tii.2020.2999901 · Cited by 117
“…(IIoT), integrating various kinds of production equipment, mobile intelligent terminals, manufacturing machines, and monitoring devices, combines advanced communication, computational, and intelligent analysis technologies into all aspects of the industrial production process [1]–[3].”
BackgroundMethodZhang, Z., Wang, N., Wu, H., Tang, C., & Li, R. (2021) · IEEE Internet of Things Journal · doi:10.1109/jiot.2021.3126101 · Cited by 117
“Li et al. [23] used the deep learning method to tackle the offloading-decision issue.”
MethodChen, J., Li, K., & Yu, P. S. (2022) · IEEE Transactions on Intelligent Transportation Systems · doi:10.1109/tits.2021.3105682 · Cited by 116
Deep Reinforcement Learning for Load-Balancing Aware Network Control in IoT Edge Systems
Liu, Q., Xia, T., Cheng, L., van Eijk, M., Özçelebi, T., & Mao, Y. (2021) · IEEE Transactions on Parallel and Distributed Systems · doi:10.1109/tpds.2021.3116863 · Cited by 115
“However, it is always hard for them to process the data in an efficient way, due to hardware limitations [19].”
Video Frame Interpolation: A Comprehensive Survey
Dong, J., Ota, K., & Dong, M. (2023) · ACM Transactions on Multimedia Computing Communications and Applications · doi:10.1145/3556544 · Cited by 116
“Meantime, some researchers have focused on applying deep learning in the Internet of Things (IoT) environments, and they propose many optimization algorithms [36, 62, 63, 160], which will inspire designing real-time video frame interpolation algorithms on edge devices.”
BackgroundSelf-citationZhang, W., Zhang, Z., Zeadally, S., Chao, H.-C., & Leung, V. C. M. (2019) · IEEE Transactions on Industrial Informatics · doi:10.1109/tii.2019.2897001 · Cited by 114
“In [26], Li et al.”
Demystifying Why Local Aggregation Helps: Convergence Analysis of Hierarchical SGD
Wang, J., Wang, S., Chen, R., & Ji, M. (2022) · Proceedings of the AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v36i8.20832 · Cited by 115
“In practical scenarios, networks often have a hierarchical structure in nature, such as edge computing systems (Li, Ota, and Dong 2018) and software defined networks (SDN) (Kim and Feamster 2013).”
BackgroundA Review of Artificial Intelligence in Embedded Systems
Zhang, Z., & Li, J. (2023) · Micromachines · doi:10.3390/mi14050897 · Cited by 114
“In reference [5], the authors proposed incorporating deep learning into the edge computing environment to enhance learning performance while reducing network traffic.”
BackgroundMachine Learning and Deep Learning Methods for Intrusion Detection Systems in IoMT: A survey
Rbah, Y., Mahfoudi, M., Balboul, Y., Fattah, M. Y., Mazer, S., Elbekkali, M., & Bernoussi, B. (2022) · International Conference on Innovative Research in Applied Science, Engineering and Technology (IRASET) · doi:10.1109/iraset52964.2022.9738218 · Cited by 113
DeepNap: Data-Driven Base Station Sleeping Operations Through Deep Reinforcement Learning
Liu, J., Krishnamachari, B., Zhou, S., & Niu, Z. (2018) · IEEE Internet of Things Journal · doi:10.1109/jiot.2018.2846694 · Cited by 112
“lenging communications problems [14], [15], [16], [17], [18].”
A Systematic Investigation of the Integration of Machine Learning into Supply Chain Risk Management
Schroeder, M., & Lodemann, S. (2021) · Logistics · doi:10.3390/logistics5030062 · Cited by 112
“Supplementary factors, such as the increased use of Cloud Computing (and thus easier access to powerful computing), software libraries which make it easier to execute ML projects despite the limited number of available skilled ML engineers, and the Internet of Things which provides more data-generating sensors [33], s…”
BackgroundEnforcing security in Internet of Things frameworks: A Systematic Literature Review
Aly, M., Khomh, F., Haoues, M., Quintero, A., & Yacout, S. (2019) · Internet of Things · doi:10.1016/j.iot.2019.100050 · Cited by 98
Sum-Rate Maximization for Intelligent Reflecting Surface Assisted Terahertz Communications
Pan, Y., Wang, K., Pan, C., Zhu, H., & Wang, J. (2022) · IEEE Transactions on Vehicular Technology · doi:10.1109/tvt.2022.3140869 · Cited by 111
Energy-Efficient Artificial Intelligence of Things With Intelligent Edge
Zhu, S., Ota, K., & Dong, M. (2022) · IEEE Internet of Things Journal · doi:10.1109/jiot.2022.3143722 · Cited by 112
Self-citationAn Optimized IoT-Enabled Big Data Analytics Architecture for Edge–Cloud Computing
Babar, M. A., Jan, M. A., He, X., Tariq, M. U., Mastorakis, S., & Alturki, R. (2022) · IEEE Internet of Things Journal · doi:10.1109/jiot.2022.3157552 · Cited by 111
“The idea of edge computing is gaining significant attention with the rise of IoT [2]–[4].”
BackgroundThe Internet of Sounds: Convergent Trends, Insights, and Future Directions
Turchet, L., Lagrange, M., Rottondi, C., Fazekas, G., Peters, N., Østergaard, J., Font, F., Bäckström, T., & Fischione, C. (2023) · IEEE Internet of Things Journal · doi:10.1109/jiot.2023.3253602 · Cited by 111
“Such assumptions challenge the distributed, networked, and real-time nature of the IoS [281].”
BackgroundFederated Feature Selection for Horizontal Federated Learning in IoT Networks
Zhang, X., Mavromatis, A., Vafeas, A., Nejabati, R., & Simeonidou, D. E. (2023) · IEEE Internet of Things Journal · doi:10.1109/jiot.2023.3237032 · Cited by 110
“Data collected by the underlying IoT networks are the foundation of ML [8] methods which often need to learn latent patterns and empirical models from a large amount of data, attempting to give optimal regression or classification results.”
BackgroundLiu, Y., Jiang, L., Qi, Q., & Xie, S. (2022) · IEEE Internet of Things Journal · doi:10.1109/jiot.2022.3220677 · Cited by 108
“In [15] and [16], the artificial intelligence (AI) technologies are used to find optimal computation offloading policies for MEC-driven IoT system.”
MethodZhang, X., Fang, F., & Wang, J. (2020) · IEEE Transactions on Industrial Informatics · doi:10.1109/tii.2020.3035807 · Cited by 107
Machine Learning for Wireless Link Quality Estimation: A Survey
Cerar, G., Yetgin, H., Mohorčič, M., & Fortuna, C. (2021) · IEEE Communications Surveys & Tutorials · doi:10.1109/comst.2021.3053615 · Cited by 107
“Kernel Methods [45] Statistical [45] Anomaly Detection Classification Kernel Methods [46] Service Optimization Classification Deep Learning [47]”
BackgroundShahidinejad, A., & Ghobaei‐Arani, M. (2020) · Software: Practice and Experience · doi:10.1002/spe.2888 · Cited by 79
“Li et al 23 designed an offloading strategy and formulated an elastic scheduling problem to optimize the performance of IoT devices along with introducing multilayer deep learning (DL) into their proposed method to decrease network traffic while increasing learning performance and guaranteeing…”
BackgroundElhanashi, A., Dini, P., Saponara, S., & Zheng, Q. (2023) · Electronics · doi:10.3390/electronics12244925 · Cited by 106
A comprehensive survey of energy-efficient computing to enable sustainable massive IoT networks
Alsharif, M. H., Kelechi, A. H., Jahid, A., Kannadasan, R., Singla, M. K., Gupta, J., & Geem, Z. W. (2024) · Alexandria Engineering Journal · doi:10.1016/j.aej.2024.01.067 · Cited by 107
Information fusion for edge intelligence: A survey
Zhang⋆, Y., Jiang, C., Yue, B., Wan, J., & Guizani, M. (2021) · Information Fusion · doi:10.1016/j.inffus.2021.11.018 · Cited by 105
Dynamic Edge Computation Offloading for Internet of Vehicles With Deep Reinforcement Learning
Yao, L., Xu, X., Bilal, M., & Wang, H. H. (2022) · IEEE Transactions on Intelligent Transportation Systems · doi:10.1109/tits.2022.3178759 · Cited by 105
“EC, as the emerging computing paradigm, is envisioned as a promising technology for soaring computing requirements of ITS environment [18].”
BackgroundBlockDeepNet: A Blockchain-Based Secure Deep Learning for IoT Network
Rathore, S., Pan, Y. F., & Park, J. H. (2019) · Sustainability · doi:10.3390/su11143974 · Cited by 103
“A layered architecture of the IoT network is general as in Li et al. [8], but with a distinct device and edge layer, as shown in Figure 1.”
BackgroundMethodInfluentialScalable edge-based hyperdimensional learning system with brain-like neural adaptation
Zou, Z., Kim, Y., Imani, F., Alimohamadi, H., Cammarota, R., & Imani, M. (2021) · International Conference for High Performance Computing, Networking, Storage and Analysis (SC) · doi:10.1145/3458817.3480958 · Cited by 102
“, Deep Neural Network (DNNs), which require billions of parameters and many hours to train in powerful and reliable computing environment [6, 7].”
BackgroundDeng, C., Fang, X., & Wang, X. (2022) · IEEE Internet of Things Journal · doi:10.1109/jiot.2022.3151619 · Cited by 103
“Fourth, to further improve the model accuracy, for an example, DNN models become deeper and require larger-scale input data [10], [13], [21], which introduces the long processing latency and high energy consumption.”
MethodLiu, Y., Yu, W., Rahayu, W. J., & Dillon, T. S. (2023) · IEEE Internet of Things Journal · doi:10.1109/jiot.2023.3246100 · Cited by 105
“The works in [79] and [80] focus only on resource distribution in the case of convolutional neural networks (CNNs) by designing an offloading strategy to offload the computational burden from the central cloud to the fog nodes.”
BackgroundOmrany, H., Al-Obaidi, K. M., Hossain, M., Alduais, N. A. M., Al-Duais, H. S., & Ghaffarianhoseini, A. (2024) · Discover Cities · doi:10.1007/s44327-024-00002-w · Cited by 103
“Li et al. [92] described deep learning as an ideal method for obtaining precise information from raw IoT data that existed in complex environments.”
Metadata
- Authors
- Li, H., Ota, K., & Dong, M.
- Affiliations
- Muroran Institute of Technology (JP)
- Venue
- IEEE Network
- Published
- 2018-01
- Volume
- 32
- Issue
- 1
- Pages
- 96-101
- ISSN
- 0890-8044 (ISSN-L)
- 1558-156X
- OpenAlex
- W2786070938
- Cited by
- 1,566
- References
- 15
- Citations by year
- 2026: 56 · 2025: 102 · 2024: 121 · 2023: 178 · 2022: 245 · 2021: 322 · 2020: 301 · 2019: 186 · 2018: 55
- FWCI
- 133.84
- Type
- journal article
- Language
- en
- Open access
- Locations
- IEEE Network (publishedVersion)
- Institutional Repositories DataBase (IRDB) (acceptedVersion)
- Muroran Institute of Technology Academic Resources Archieve (Muroran Institute of Technology) (submittedVersion)
- Funders
- Japan Society for the Promotion of Science (17K12669, 16K00117, 15K15976)
- Topics
- Physical Sciences › Computer Science › Computer Networks and Communications › IoT and Edge/Fog Computing
- Physical Sciences › Computer Science › Information Systems › Internet of Things and AI
- Physical Sciences › Computer Science › Hardware and Architecture › Energy Efficiency in Computing
- Keywords
- Internet of Things, edge computing, deep learning, computation offloading, sensor data processing, resource-constrained edge nodes
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.