DeepWear: Adaptive Local Offloading for On-Wearable Deep Learning
Open accessThe DOI matches its Crossref record; 50 of the 51 references it cites were found in a registry or an index.
Abstract
Due to their on-body and ubiquitous nature, wearables can generate a wide range of unique sensor data creating countless opportunities for deep learning tasks. We propose DeepWear, a deep learning (DL) framework for wearable devices to improve the performance and reduce the energy footprint. DeepWear strategically offloads DL tasks from a wearable device to its paired handheld device through local network connectivity such as Bluetooth. Compared to the remote-cloud-based offloading, DeepWear requires no Internet connectivity, consumes less energy, and is robust to privacy breach. DeepWear provides various novel techniques such as context-aware offloading, strategic model partition, and pipelining support to efficiently utilize the processing capacity from nearby paired handhelds. Deployed as a user-space library, DeepWear offers developer-friendly APIs that are as simple as those in traditional DL libraries such as TensorFlow. We have implemented DeepWear on the Android OS and evaluated it on COTS smartphones and smartwatches with real DL models. DeepWear brings up to 5.08× and 23.0× execution speedup, as well as 53.5 and 85.5 percent energy saving compared to wearable-only and handheld-only strategies, respectively.
Overview
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
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?
In the citing paper
“In this manner, the complex DAG can be transformed into a linear and much simpler one, thus enabling a linear complexity solution for selecting the optimal partition to offload.”
From Convergence of Edge Computing and Deep Learning: A Comprehensive Survey (2020) · cites this paper as [174]
Citations
Cites
Going deeper with convolutions
Szegedy, C., Liu, W., Jia, Y., Sermanet, P., Reed, S., Anguelov, D., Erhan, D., Vanhoucke, V., & Rabinovich, A. (2015) · 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2015.7298594 · Cited by 48,562
MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications
Howard, A. G., Zhu, M., Chen, B., Kalenichenko, D., Wang, W., Weyand, T., Andreetto, M., & Adam, H. (2017) · arXiv · doi:10.48550/arxiv.1704.04861 · Cited by 19,015 · cited 7×
“MNIST [41] digit recognition grayscale image 15M MobileNet [30] image classification rgb image 580M GoogLeNet [42] image classification rgb image 2G LSTM-HAR [43] activity recognition mobile sensor 180M DeepSense [44] activity recognition mobile sensor 550M TextRNN [45] document classification word vectors 11M DeepEar…”
BackgroundInfluentialSelf-citationSequence to Sequence Learning with Neural Networks
Sutskever, I., Vinyals, O., & Le, Q. V. (2014) · arXiv · doi:10.48550/arxiv.1409.3215 · Cited by 17,766 · cited 1×
“For example, the LSTM model used for language modeling can also be applied to problems such as machine translation [47], question answering [48], and handwriting generation [49].”
MethodWaveNet: a generative model for raw audio
Oord, A. V. D., Dieleman, S., Zen, H., Simonyan, K., Vinyals, O., Graves, A., Kalchbrenner, N., Senior, A., & Kavukcuoglu, K. (2016) · arXiv · doi:10.48550/arxiv.1609.03499 · Cited by 4,911 · cited 1×
“…[42] image classification rgb image 2G LSTM-HAR [43] activity recognition mobile sensor 180M DeepSense [44] activity recognition mobile sensor 550M TextRNN [45] document classification word vectors 11M DeepEar [6] emotion recognition raw sound 9M WaveNet [46] speech recognition mfcc features 3.8G 1.”
BackgroundGenerating Sequences With Recurrent Neural Networks
Graves, A. (2013) · arXiv · doi:10.48550/arxiv.1308.0850 · Cited by 2,894 · cited 1×
“For example, the LSTM model used for language modeling can also be applied to problems such as machine translation [47], question answering [48], and handwriting generation [49].”
MethodMAUI: making smartphones last longer with code offload
Cuervo, E., Balasubramanian, A., Cho, D.-K., Wolman, A., Saroiu, S., Chandra, R., & Bahl, P. (2010) · Proceedings of the 8th international conference on Mobile systems, applications, and services · doi:10.1145/1814433.1814441 · Cited by 2,281 · cited 4×
“MAUI [13] designs an enhanced offloading decision mechanism that makes predictions for every single function invocation separately and considers the entire application when choosing which function to offload.”
BackgroundInfluentialOptimizing FPGA-based Accelerator Design for Deep Convolutional Neural Networks
Zhang, C., Li, P., Sun, G., Guan, Y., Xiao, B., & Cong, J. (2015) · Proceedings of the 2015 ACM/SIGDA International Symposium on Field-Programmable Gate Arrays · doi:10.1145/2684746.2689060 · Cited by 2,158 · cited 1×
“Some other efforts such as [31], [32], [33], [34] aimed at building customized hardware accelerators for DL or other machine learning tasks.”
BackgroundEIE: efficient inference engine on compressed deep neural network
Han, S., Liu, X., Mao, H., Pu, J., Pedram, A., Horowitz, M. A., & Dally, W. J. (2016) · ACM SIGARCH Computer Architecture News · doi:10.1145/3007787.3001163 · Cited by 1,937 · cited 1×
“Some other efforts such as [31], [32], [33], [34] aimed at building customized hardware accelerators for DL or other machine learning tasks.”
BackgroundSelf-citation(2011) · doi:10.1145/1966445.1966473 · Cited by 1,870
Exploiting Linear Structure Within Convolutional Networks for Efficient Evaluation
Denton, R., Zaremba, W., Bruna, J., LeCun, Y., & Fergus, R. (2014) · arXiv · doi:10.48550/arxiv.1404.0736 · Cited by 1,414 · cited 2×
“Besides, various model compression techniques [35], [3], [17], [18], [19], [36] have been proposed for accelerating the DL task and reducing its energy consumption.”
BackgroundMethod
Cited by
Items 101–167 of 167
Hyperion: A Generic and Distributed Mobile Offloading Framework on OpenCL
Fu, Z., Ren, J., Liu, Y., Cao, T., Zhang, D., Zhou, Y., & Zhang, Y. (2022) · ACM Conference on Embedded Networked Sensor Systems (SenSys) · doi:10.1145/3560905.3568511 · Cited by 5
“detection, and the work [51] for wearable devices.”
BackgroundDeep action: A mobile action recognition framework using edge offloading
Zhang, D., Zhang, H., Duan, S., Luo, Y., Jia, F., & Liu, F. (2021) · Peer-to-Peer Networking and Applications · doi:10.1007/s12083-021-01232-0 · Cited by 5
“Besides, multiple lightweight CNN models, such as MobileNet [34], SqueezeNet [35], ShuffleNet [36], provide promising performance for object detection on mobile devices.”
MethodShi, L., Xu, Z., Shi, Y., Fan, Y., Ding, X., & Sun, Y. (2021) · Lecture notes of the Institute for Computer Sciences, Social Informatics and Telecommunications Engineering · doi:10.1007/978-3-030-67537-0_15 · Cited by 5
Operating Systems for Resource-adaptive Intelligent Software: Challenges and Opportunities
Liu, X., Wang, S., Ma, Y., Zhang, Y., Mei, Q., Liu, Y., & Huang, G. (2021) · ACM Transactions on Internet Technology · doi:10.1145/3425866 · Cited by 5
Self-citationEdge Computing for Artificial Intelligence
Wang, X., Han, Y., Leung, V. C. M., Niyato, D. T., Yan, X., & Chen, X. (2020) · Springer eBooks · doi:10.1007/978-981-15-6186-3_7 · Cited by 5
Multitemporal Sampling Module for Real-Time Human Activity Recognition
Park, J., Lim, W.-S., Kim, D., & Lee, J. (2022) · IEEE Access · doi:10.1109/access.2022.3176606 · Cited by 5
“A straightforward solution to solve this issue is to allow CNNs to consider multiple sampling intervals simultaneously, yet the stride of pooling is fixed and the pooling is applied after the vanilla convolutions have already consumed a significant computational cost [14], [15].”
BackgroundYao, Y., Wang, Z., Luo, P., Cheng, Y., Hou, J., & Li, X. (2025) · IEEE Transactions on Mobile Computing · doi:10.1109/tmc.2025.3607483 · Cited by 4
“DeepWear [36] works as a variation of DADS.”
QoE-Aware User Allocation in NOMA-Enabled MEC Systems: A Distributed Game-Theoretical Approach
Yang, Y., Chen, Y., Hu, J., Cui, Z., Huang, J., & Zhao, L. Y. (2025) · IEEE Transactions on Vehicular Technology · doi:10.1109/tvt.2025.3605977 · Cited by 4
“Through task offloading, applications can delegate partial workloads to edge servers, [9].”
Seo, W., Kim, S., & Hong, S. (2024) · IEEE International Conference on Distributed Computing Systems (ICDCS) · doi:10.1109/icdcs60910.2024.00156 · Cited by 4
“Many optimal DNN partitioning algorithms that maximize the throughput of DNN inference have been actively investigated in [1], [2], but they have high time complexity due to their reliance on brute-force algorithms.”
BackgroundContext-aware adaptation of deep learning models for IoT devices
Wang, H., Xingshe, Z. H. O. U., Yu, Z., Sicong, L. I. U., Guo, B., Wu, Y., Liu, J., & Wang, H. (2020) · Scientia Sinica Informationis · doi:10.1360/ssi-2020-0067 · Cited by 4
Tian, X., Xu, P., Hui, G., & Meng, H. (2023) · Wireless Communications and Mobile Computing · doi:10.1155/2023/3835297 · Cited by 4
A Novel Adaptive Computation Offloading Strategy for Collaborative DNN Inference over Edge Devices
Zhang, Y., Liu, X., Jia, X., Yuan, D., & Li, X. (2022) · IEEE International Symposium on Parallel and Distributed Processing with Applications (ISPA) · doi:10.1109/ispa-bdcloud-socialcom-sustaincom57177.2022.00055 · Cited by 4
“In addition, CoDNN does not modify the DNN models, so the prediction accuracy will not be sacrificed [7].”
MethodInfluentialSelf-citationBenchmarking the speed–accuracy tradeoff in object recognition by humans and neural networks
Subramanian, A., Price, S., Kumbhar, O. S., Sizikova, E., Majaj, N. J., & Pelli, D. G. (2025) · Journal of Vision · doi:10.1167/jov.25.1.4 · Cited by 3
“Previous work has revealed applications of such networks in resource-sensitive applications such as analysis during autonomous driving (Yang et al., 2019) and mobile health sensors (Xu et al., 2019).”
Autonomous Learning System Towards Mobile Intelligence
Xu, M., Liu, Y., Huang, K., Liu, X., & Huang, G. (2021) · International Journal of Software and Informatics · doi:10.21655/ijsi.1673-7288.00247 · Cited by 3
“…accuracy of a model, which is measured by the validation set; Resource is used to calculate the resource consumption of a model (such as delay, energy consumption, and memory usage), which can be obtained by modeling according to the model structure [24,25] , or by prototype measurement [26,27] .”
Self-citation$C^3DRec$: Cloud-Client Cooperative Deep Learning for Temporal Recommendation in the Post-GDPR EraPreprint
Han, J., & Ma, Y. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2101.05641 · Cited by 3
“DeepType [44, 45, 47] made an effort to solve this dilemma between accuracy and privacy concerns by training a global model on the cloud using massive public corpora, and then incrementally customizing the global model with data on individual devices.”
MethodSubramanian, A., Price, S., Kumbhar, O. S., Sizikova, E., Majaj, N. J., & Pelli, D. G. (2022) · arXiv (Cornell University) · doi:10.48550/arxiv.2206.08427 · Cited by 3
“Previous work has revealed applications of such networks in resource-sensitive applications such as analysis during autonomous driving [24] and mobile health sensors [25] are time-sensitive.”
Edge AI on Constrained Devices: A Survey of Deployment, Optimization, and Lifecycle Management
Passarotto, M., Abdesslem, F. B., Eriksson, J., & Voigt, T. (2026) · ACM Transactions on Embedded Computing Systems · doi:10.1145/3827611 · Cited by 2
“DeepWear, a runtime framework that partitions workloads between wearables and smartphones, adapts decisions at runtime and delivers up to 5 × faster inference with 85% energy savings relative to wearable-only execution [268].”
Managing Edge Offloading for Stochastic Workloads with Deadlines
Bari, A., Veciana, G. A. D., Johnsson, K., & Pyattaev, A. (2023) · ACM International Conference on Modeling, Analysis and Simulation of Wireless and Mobile Systems (MSWiM) · doi:10.1145/3616388.3617515 · Cited by 2
“There are several works [5–7, 11, 15] in the literature that embrace the linear DAG model as an e � ective abstraction/approximation of jobs that might particularly bene � t from o � oading.”
BackgroundQUDOS: quorum-based cloud-edge distributed DNNs for security enhanced industry 4.0
Wallis, K., Reich, C., Varghese, B., & Schindelhauer, C. (2021) · IEEE/ACM International Conference on Utility and Cloud Computing (UCC) · doi:10.1145/3468737.3494094 · Cited by 2
Decision Early-Exit: An Efficient Approach to Hasten Offloading in BranchyNets
Barbosa, M. S. M., Pacheco, R. G., Couto, R. S., Medeiros, D. S. V., & Campista, M. E. M. (2022) · IEEE Latin-American Conference on Communications · doi:10.1109/latincom56090.2022.10000430 · Cited by 2
“Hence, both the latency and the energy consumption are important metrics to take into account when evaluating deep-learning-based solutions for time-critical applications, such as Intelligent Transport System (ITS) [1], or industrial networks [2], which require low response time [3] and energy cost [4].”
BackgroundAdapCP: Collaborative Inference with Adaptive CNN Partition on Distributed Edge Servers
Zhao, S., Yao, D., Wan, Y., Wu, G., & Jin, H. (2025) · ACM Transactions on Autonomous and Adaptive Systems · doi:10.1145/3765961 · Cited by 2
“For example, the work [12, 13] has investigated the splitting of the CNN into two partitions at the layer level for offloading via wireless networks.”
Imperio: Cyber Foraging Framework for On-Device Inference based Mobile Applications
Wijayasekara, V. A., & Vekneswaran, P. (2021) · International Conference on Information and Automation for Sustainability (ICIAfS) · doi:10.1109/iciafs52090.2021.9605965 · Cited by 1
Study and Analysis of IoT-Based Telemedicine and Remote Patient Monitoring
Kumar, R. K., & Sobin, C. C. (2024) · Advances in IT standards and standardization research (AISSR) book series/Advances in IT standards and standardization research series · doi:10.4018/979-8-3693-1686-3.ch005 · Cited by 1
FT-DAG: An Efficient Full-Topology DAG Generator with Controllable Parameters
Fang, Y., Yang, L., Liu, W., Zhang, G., Gu, Y., Xiao, X., Qin, W., Ouyang, X., & Chang, W. (2025) · ACM Transactions on Embedded Computing Systems · doi:10.1145/3760781 · Cited by 1
“In particular, for AI workloads and DL computations, DeepWear [10] abstracts a DL/AI model as a DAG, where each node represents a layer and each edge denotes the data flow between layers.”
Cross-technology cloud offloading model
Al‐Ahmad, A., Shrestha, A., Ali, O., & Kahtan, H. (2025) · Journal of Cloud Computing Advances Systems and Applications · doi:10.1186/s13677-025-00819-9 · Cited by 1
“DeepWear [84] is another context-aware model that uses wearable device sensors, such as pairing data and proximity from the connected device, to inform offloading decisions.”
PIDC: Padding-Aware IoT Device Collaboration for Accelerating DNN Inference
Jiang, W., Han, H., Qian, L. P., Wei, F., Qin, S., & Feng, G. (2025) · IEEE Transactions on Mobile Computing · doi:10.1109/tmc.2025.3633269 · Cited by 1
“In [29], the authors proposed a deep learning framework for wearable devices that strategically offloads computation to paired handheld devices via local connections, employing context-aware offloading, model partitioning, and pipelining for significant energy savings.”
Peak-memory-aware partitioning and scheduling for multi-tenant DNN model inference
Lee, J., Lee, J. M., Jeong, H. K., Kwon, H., Kim, Y., Park, Y., & Kim, H. (2026) · Journal of Systems Architecture · doi:10.1016/j.sysarc.2026.103696 · Cited by 1
Understanding the Predictability of Smartwatch Usage
Yao, Y., Liu, X., & Qian, F. (2019) · doi:10.1145/3325424.3329661 · Cited by 1
“For example, researchers have developed a wide spectrum of novel applications that fully exploit watches’ potentials, such as deep learning [19], sign language translation [10], and drinking activity monitoring [8].”
BackgroundSelf-citationIntroduzindo a qualidade de imagem como uma nova condição de particionamento de DNN na borda
Pacheco, R. G., & Couto, R. S. (2020) · doi:10.5753/sbrc.2020.12272 · Cited by 1
Online Task Scheduling for DNN-Based Applications over Cloud, Edge and End Devices
Zhong, L., Shi, J., Shi, L., Xu, J., Fan, Y., & Xu, Z. (2021) · Lecture notes in computer science · doi:10.1007/978-3-030-86137-7_20 · Cited by 1
Demonstrating the Feasibility of Subepidermal Image Sensing for Hand Posture and Gesture Recognition
Chacon, D. A., Shinoda, K., Yokota, T., & Yatani, K. (2022) · IEEE Sensors Letters · doi:10.1109/lsens.2022.3209074 · Cited by 1
“We chose this platform because of its adaptability for implementation in mobile and low-cost devices without affecting real-time performance, which is suitable for wearable sensors [25], [26].”
Multi-tier Edge Computing for Partitioned Neural Network
Ren, T.-F., & Zhou, M. (2022) · IEEE International Conference on Industrial Technology (ICIT) · doi:10.1109/icit48603.2022.10002820 · Cited by 1
“Some scholars [9][10] investigates how the neural network can be partitioned and deployed among multiple devices, and proposes the concept of streaming processing.”
BackgroundCollaborative Mobile Edge Computing Through UPF Selection
Li, Y., Zhou, A., Ma, X., & Wang, S. (2022) · Lecture notes of the Institute for Computer Sciences, Social Informatics and Telecommunications Engineering · doi:10.1007/978-3-031-24386-8_19 · Cited by 1
Dynamic Offloading for Compute Adaptive Jobs
Bari, A., Veciana, G. A. D., Johnsson, K., & Pyattaev, A. (2023) · IEEE Consumer Communications and Networking Conference · doi:10.1109/ccnc51644.2023.10059859 · Cited by 1
“, [8], [5], [9], [10], [11]) on DNN-based applications have explored the advantages of partial offloading, i.”
Background2020 Index IEEE Transactions on Mobile Computing Vol. 19
(2020) · IEEE Transactions on Mobile Computing · doi:10.1109/tmc.2020.3036773 · Cited by 1
Experience-driven Control For Networking And Computing
Xu, Z. (2021) · Syracuse University Libraries (Syracuse University)
JointCS: Joint Search for Deep Model Compression and Segmentation on Heterogeneous IoT Devices
Li, X., Guo, B., Liu, S., Qiu, C., Liang, Y., & Yu, Z. (2021) · IEEE International Conference on Parallel and Distributed Systems (ICPADS) · doi:10.1109/icpads53394.2021.00059
Flexible collaborative inference for computer vision
Assine, J. S. (2022) · doi:10.47749/t/unicamp.2022.1251262
DeepSlicing: Collaborative and Adaptive CNN Inference With Low Latency
Zhang, S., Chen, Y., Zhang, S., & Chen, Z. (2023) · Advances in computational intelligence and robotics book series · doi:10.4018/979-8-3693-0230-9.ch006
FairMS: Fair DNN Model Selection Algorithm for Collaborative Edge Intelligence
Xu, A., Hu, Z., Zheng, M., Chen, B., Xiao, H., Zheng, H., & Liang, Y. (2025) · Lecture notes in computer science · doi:10.1007/978-981-96-9914-8_3
AI in Wearable Imaging Devices
Adebayo, P. O., Aremu, I. B., & Babatunde, A. J. (2025) · Advances in computational intelligence and robotics book series · doi:10.4018/979-8-3373-0903-3.ch006
New preprint survey on energy-aware deep learning on embedded hardware
Madhavapeddy, A. (2025) · doi:10.59350/g39bb-tw087
Reinforcement Learning-based Task Offloading in the Internet of Wearable ThingsPreprint
Qaim, W. B., Ometov, A., Campolo, C., Molinaro, A., Lohan, E. S., & Nurmi, J. (2025) · arXiv (Cornell University) · doi:10.48550/arxiv.2510.07487
“For example, Xu et al. propose DeepWear [31], a deep learning-based framework designed for wearable devices to offload computationally intensive deep learning tasks to their paired handheld devices.”
Directed Acyclic Graph Topology Generators: A Survey
Fang, Y., Li, H., & Chang, W. (2025) · ACM Transactions on Embedded Computing Systems · doi:10.1145/3778862
PaPro: Parallel Processing Mechanism in In-Network Computing for Multi-Stage Applications
Zhang, J., & Guan, J. (2025) · IEEE International Symposium on Parallel and Distributed Processing with Applications (ISPA) · doi:10.1109/ispa67752.2025.00010
“…the above computing paradigms, when computing tasks are migrated from local devices to edge servers, cloud servers, or other nodes, the granularity of computation offloading can be divided into three methods: full offloading, stage or component offloading, and micro-batch-level offloading [15, 16].”
Online Learning for Orchestrating Deep Learning Inference at Edge
Shahhosseini, S. (2023) · eScholarship (California Digital Library)
COINS '19 Proceedings of the International Conference on Omni-Layer Intelligent Systems
Nakhkash, M., Gia, T., Azimi, I., Anzanpour, A., Rahmani, A. M., & Liljeberg, P. (2022) · UTUPub (University of Turku)
Dynamic Workflow Partitioning via Reinforcement Learning for Edge-Cloud Heterogeneous Systems
Zhang, Y., & Morris, C. (2025) · Frontiers in Artificial Intelligence Research · doi:10.71465/fair455
Modeling and Optimizing Data Reduction Strategies for Wearable Ultrasound System
Lalichetti, H., & Li, W. (2025) · IEEE Biomedical Circuits and Systems Conference (BioCAS) · doi:10.1109/biocas67066.2025.00098
“Thus, our studies consider connected wearable ultrasound systems that resolve some of these constraints by distributing functionalities and computational tasks across multiple hardware platforms [22].”
Singh, H., & Chaurasia, S. N. (2026) · Lecture notes in computer science · doi:10.1007/978-3-032-18477-1_57
Kim, R., Yoo, H., Kim, S., & Kim, Y. (2026) · IEEE Transactions on Green Communications and Networking · doi:10.1109/tgcn.2026.3686316
“Xu et al. [25] developed DeepWear , an adaptive framework for wearable devices that splits DNN workloads between the wearable and a paired smartphone over Bluetooth to balance the trade-off between latency and energy consumption.”
End-Edge-Cloud Orchestration for Video Analytics
Bai, T. (2025) · Textbooks in telecommunication engineering · doi:10.1007/978-3-032-14764-6_6
The Role of IoT in Wearable Devices
Saxena, C., & Verma, V. (2026) · Health informatics · doi:10.1007/978-3-032-23933-4_11
Sazonov, E. E., Hossain, D., Fard, S. E., Hossain, M. B., McCrory, M. A., Higgins, J., & Thomas, J. G. (2026) · IEEE Middle East and North Africa Communications Conference (MENACOMM) · doi:10.1109/menacomm69507.2026.11532882
“This architecture, often called Split Computing, allows the wearable to remain lightweight and long-lasting while leveraging the remote computational power to drive the JITAI logic [25], [26].”
Dynamic task offloading for sports training monitoring in MEC-assisted smart wearable device systems
Zhang, Y., & Zhang, D. (2026) · Scientific Reports · doi:10.1038/s41598-026-56003-9
“Various studies have been conducted to address energy efficiency issues in SWDs. M. Xu et al. 21 proposed a deep learning framework for wearable devices that strategically offloads DL tasks to other devices to reduce computation energy consumption while preserving user privacy.”
EnSplit: Dynamic DRL Energy-Aware Split Inference for AI-Based UE Apps in 6G Networks
Majumdar, S., Samikwa, E., Samdanis, K., Pateromichelakis, E., Nezhad, E. H., & Braun, T. I. (2026) · IEEE International Conference on Network Softwarization (NetSoft) · doi:10.1109/netsoft70012.2026.11603456
“Early work on split inference focused on static, benchmarking-driven partitioning of DNNs. DeepWear [13] and Scission [14] estimate optimal partitions based on profiling target hardware during installation.”
Yao, G., Hu, L., Guo, Y., Wang, X., Chen, X. W., Liu, L., Tang, J., Li, Y., Cheng, C., Wang, C.-P., et al. (2026) · IEEE Transactions on Consumer Electronics · doi:10.1109/tce.2026.3714729
Jyothy, A. (2026) · i-manager s Journal on Augmented & Virtual Reality · doi:10.26634/javr.4.1.1116
Sun, M., Qi, M., Xu, Y., You, D., & Chen, Z. (2026) · IEEE Internet of Things Journal · doi:10.1109/jiot.2026.3718480
Zhang, S., Ma, J., Chi, K., Liu, J., & Shi, Z. (2026) · ACM Transactions on Sensor Networks · doi:10.1145/3838798
Joint Optimization of Multi-DNN Partitioning and Scheduling in IoT Edge Computing
Lin, Y., Fan, F., Yu, Z., & Huang, F. (2026) · Communications in computer and information science · doi:10.1007/978-981-92-3994-8_11
Self-citationMobility-aware Lyapunov-guided deep reinforcement offloading for wearable edge computing
Zhu, X., Liu, R., Wen, Z., & Wang, J. (2026) · Scientific Reports · doi:10.1038/s41598-026-71423-3
COINS '19 Proceedings of the International Conference on Omni-Layer Intelligent Systems
Nakhkash, M., Gia, T., Azimi, I., Anzanpour, A., Rahmani, A. M., & Liljeberg, P. (2022) · UTUPub (University of Turku)
Abbas, S. F., Ahmed, M., Almashfi, N., Bakhshi, A., Aamir, S., Humayun, M., & Almufareh, M. F. (2026) · Research Square · doi:10.21203/rs.3.rs-10516053/v1
An adaptive spatio-temporal framework for carbon-aware and privacy-preserving DNN partitioning
GOEL, S., & Veeragandham, S. (2026) · Frontiers in Artificial Intelligence · doi:10.3389/frai.2026.1961682
Metadata
- Authors
- Xu, M., Qian, F., Zhu, M., Huang, F., Pushp, S., & Liu, X.
- Affiliations
- Peking University (CN)
- University of Minnesota (US)
- Korea Advanced Institute of Science and Technology (KR)
- Venue
- IEEE Transactions on Mobile Computing
- Published
- 2020-02-01
- Volume
- 19
- Issue
- 2
- Pages
- 314-330
- ISSN
- 1536-1233 (ISSN-L)
- 1558-0660
- 2161-9875
- OpenAlex
- W2909099954
- Cited by
- 138
- References
- 51
- Citations by year
- 2026: 10 · 2025: 22 · 2024: 13 · 2023: 17 · 2022: 24 · 2021: 33 · 2020: 14
- FWCI
- 10.40
- Type
- journal article
- Language
- en
- Open access
- green
- arxiv.org
- Licence
- Locations
- IEEE Transactions on Mobile Computing (publishedVersion)
- arXiv (Cornell University) (submittedVersion)
- arXiv (Cornell University)
- Funders
- National Key R&D Program (2018YFB1004800)
- National Natural Science Foundation of China (61725201)
- NSF (CCF-1629347)
- Basic Science Research Program (2017R1A2B3010504)
- Next-Generation Information Computing Development Program (2017M3C4A7065963)
- National Research Foundation of Korea
- Ministry of Science, ICT and Future Planning
- Topics
- Physical Sciences › Computer Science › Computer Networks and Communications › IoT and Edge/Fog Computing
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Context-Aware Activity Recognition Systems
- Physical Sciences › Engineering › Electrical and Electronic Engineering › Green IT and Sustainability
- Keywords
- wearable computing, model partitioning, pipelining, Bluetooth, energy efficiency, privacy preservation, smartwatches, smartphones, Android
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.