7 Hits in 1.3 sec

DeepWear: Adaptive Local Offloading for On-Wearable Deep Learning [article]

Mengwei Xu, Feng Qian, Mengze Zhu, Feifan Huang, Saumay Pushp, Xuanzhe Liu
2021 arXiv   pre-print
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.  ...  For the cloud offloading, we measure only the energy consumption on the wearable. Fig. 14 : 14 Compare DeepWear to cloud offloading TABLE 1 : 1 8 deep learning models used in this work.  ... 
arXiv:1712.03073v3 fatcat:6zgkveypofeuvblm6oj5g32tni

Computation offloading technique for energy efficiency of smart devices

Jaejun Ko, Young-June Choi, Rajib Paul
2021 Journal of Cloud Computing: Advances, Systems and Applications  
AbstractThe substantial number of wearable devices in the healthcare industry and the continuous growth of the market procreates the demand for computational offloading.  ...  In this paper, we focus on the fact that most smart wearable devices have Bluetooth pairing with smartphones, and Bluetooth communication is significantly energy-efficient compare to 3G/LTE or Wi-Fi.  ...  DeepWear, a deep learning framework was proposed in [27] to improve the performance and reduce energy consumption.  ... 
doi:10.1186/s13677-021-00260-8 fatcat:pzd5e6bw5vci5atseot4b6hxmy


Zheng Yang, Xiaowu He, Jiaxing Wu, Xu Wang, Yi Zhao
2021 Scientia Sinica Informationis  
Deep learning with edge computing: a review. Proc IEEE, 2019, 107: 1655-1674 7 Mach P, Becvar Z. Mobile edge computing: a survey on architecture and computation offloading.  ...  " mechanism • Reduce deadline miss rate • Increase GPU utilization • Only works on single GPU [153] N/A Controlled spatial-multiplexing; Self-learning adaptive batching • Design for GPU cluster  ... 
doi:10.1360/ssi-2021-0133 fatcat:qs7jnvnknjhdrhfrru6rfbwuge

2020 Index IEEE Transactions on Mobile Computing Vol. 19

2021 IEEE Transactions on Mobile Computing  
., +, TMC April 2020 752-768 DeepWear: Adaptive Local Offloading for On-Wearable Deep Learning.  ...  Huang, H., +, TMC Dec. 2020 2743-2760 DeepWear: Adaptive Local Offloading for On-Wearable Deep Learning.  ... 
doi:10.1109/tmc.2020.3036773 fatcat:6puiux5lp5bfvjo47ey7ycwyfu

Convergence of Edge Computing and Deep Learning: A Comprehensive Survey [article]

Xiaofei Wang and Yiwen Han and Victor C.M. Leung and Dusit Niyato and Xueqiang Yan and Xu Chen
2019 arXiv   pre-print
As an important enabler broadly changing people's lives, from face recognition to ambitious smart factories and cities, developments of artificial intelligence (especially deep learning, DL) based applications  ...  In addition, DL, as the representative technique of artificial intelligence, can be integrated into edge computing frameworks to build intelligent edge for dynamic, adaptive edge maintenance and management  ...  for deep analysis are hosted on the cloud.  ... 
arXiv:1907.08349v2 fatcat:4hfqgdto4fhvlguwfjxuz3ik5q

C^3DRec: Cloud-Client Cooperative Deep Learning for Temporal Recommendation in the Post-GDPR Era [article]

Jialiang Han, Yun Ma
2021 arXiv   pre-print
To realize the temporal recommendation in the post-GDPR era, this paper proposes C^3DRec, a cloud-client cooperative deep learning framework of mining interaction behaviors for recommendation while preserving  ...  output of the local model is pushed onto the server and combined with candidate items to get recommended ones.  ...  Deepwear: Adaptive local offloading for on-wearable deep learning.  ... 
arXiv:2101.05641v1 fatcat:c2j5dhunubblrb3cocgvrcr4ay

Learning-in-the-Fog (LiFo): Deep Learning meets Fog Computing for the Minimum-Energy Distributed Early-Exit of Inference in delay-critical IoT realms

Enzo Baccarelli, Michele Scarpiniti, Alireza Momenzadeh, Sima Sarv Ahrabi
2021 IEEE Access  
For this purpose, DeepWear in [17] dynamically offloads DL tasks from a wearable device to its paired handheld device over short-range (typically, Bluetoothbased) connections.  ...  First, Federated Learning (FL) is emerging as an interesting paradigm for training complex Deep Neural Networks on the basis of heterogeneous data-sets generated on-line by spatially-distributed IoT devices  ...  : f jk ,f jk , R k for k ≥ m + 1.  ... 
doi:10.1109/access.2021.3058021 fatcat:bi5gawvuubbcto7es7sxg5cd5e