Proceedings of the 27th Annual International Conference on Mobile Computing and Networking最新文献_第5页

LegoDNN: block-grained scaling of deep neural networks for mobile vision LegoDNN:用于移动视觉的深度神经网络的块粒度缩放

Proceedings of the 27th Annual International Conference on Mobile Computing and Networking Pub Date : 2021-10-19 DOI: 10.1145/3447993.3483249

Rui Han, Qinglong Zhang, C. Liu, Guoren Wang, Jian Tang, L. Chen

{"title":"LegoDNN: block-grained scaling of deep neural networks for mobile vision","authors":"Rui Han, Qinglong Zhang, C. Liu, Guoren Wang, Jian Tang, L. Chen","doi":"10.1145/3447993.3483249","DOIUrl":"https://doi.org/10.1145/3447993.3483249","url":null,"abstract":"Deep neural networks (DNNs) have become ubiquitous techniques in mobile and embedded systems for applications such as image/object recognition and classification. The trend of executing multiple DNNs simultaneously exacerbate the existing limitations of meeting stringent latency/accuracy requirements on resource constrained mobile devices. The prior art sheds light on exploring the accuracy-resource tradeoff by scaling the model sizes in accordance to resource dynamics. However, such model scaling approaches face to imminent challenges: (i) large space exploration of model sizes, and (ii) prohibitively long training time for different model combinations. In this paper, we present LegoDNN, a lightweight, block-grained scaling solution for running multi-DNN workloads in mobile vision systems. LegoDNN guarantees short model training times by only extracting and training a small number of common blocks (e.g. 5 in VGG and 8 in ResNet) in a DNN. At run-time, LegoDNN optimally combines the descendant models of these blocks to maximize accuracy under specific resources and latency constraints, while reducing switching overhead via smart block-level scaling of the DNN. We implement LegoDNN in TensorFlow Lite and extensively evaluate it against state-of-the-art techniques (FLOP scaling, knowledge distillation and model compression) using a set of 12 popular DNN models. Evaluation results show that LegoDNN provides 1,296x to 279,936x more options in model sizes without increasing training time, thus achieving as much as 31.74% improvement in inference accuracy and 71.07% reduction in scaling energy consumptions.","PeriodicalId":177431,"journal":{"name":"Proceedings of the 27th Annual International Conference on Mobile Computing and Networking","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-10-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128716238","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 23

Flexible high-resolution object detection on edge devices with tunable latency 具有可调延迟的边缘设备上灵活的高分辨率对象检测

Proceedings of the 27th Annual International Conference on Mobile Computing and Networking Pub Date : 2021-10-19 DOI: 10.1145/3447993.3483274

Shiqi Jiang, Zhiqi Lin, Yuanchun Li, Yuanchao Shu, Yunxin Liu

{"title":"Flexible high-resolution object detection on edge devices with tunable latency","authors":"Shiqi Jiang, Zhiqi Lin, Yuanchun Li, Yuanchao Shu, Yunxin Liu","doi":"10.1145/3447993.3483274","DOIUrl":"https://doi.org/10.1145/3447993.3483274","url":null,"abstract":"Object detection is a fundamental building block of video analytics applications. While Neural Networks (NNs)-based object detection models have shown excellent accuracy on benchmark datasets, they are not well positioned for high-resolution images inference on resource-constrained edge devices. Common approaches, including down-sampling inputs and scaling up neural networks, fall short of adapting to video content changes and various latency requirements. This paper presents Remix, a flexible framework for high-resolution object detection on edge devices. Remix takes as input a latency budget, and come up with an image partition and model execution plan which runs off-the-shelf neural networks on non-uniformly partitioned image blocks. As a result, it maximizes the overall detection accuracy by allocating various amount of compute power onto different areas of an image. We evaluate Remix on public dataset as well as real-world videos collected by ourselves. Experimental results show that Remix can either improve the detection accuracy by 18%-120% for a given latency budget, or achieve up to 8.1× inference speedup with accuracy on par with the state-of-the-art NNs.","PeriodicalId":177431,"journal":{"name":"Proceedings of the 27th Annual International Conference on Mobile Computing and Networking","volume":"14 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-10-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125347123","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 43

Tracking free-form activity using wifi signals 使用wifi信号追踪自由活动

Proceedings of the 27th Annual International Conference on Mobile Computing and Networking Pub Date : 2021-10-19 DOI: 10.1145/3447993.3482857

Yili Ren, Zi Wang, Sheng Tan, Yingying Chen, Jie Yang

引用次数: 9

Design and implementation of a generic 5G user plane function development framework 通用5G用户平面功能开发框架的设计与实现

Proceedings of the 27th Annual International Conference on Mobile Computing and Networking Pub Date : 2021-10-19 DOI: 10.1145/3447993.3482867

Cheng-Ying Hsieh, Yao-Wen Chang, Chien-Chia Chen, Jyh-cheng Chen

引用次数: 4

An aerodynamic, computer vision, and network simulator for networked drone applications 一个空气动力学、计算机视觉和网络模拟器，用于联网无人机应用

Proceedings of the 27th Annual International Conference on Mobile Computing and Networking Pub Date : 2021-10-19 DOI: 10.1145/3447993.3482862

Shengkun Tang, Cheng-Hsin Hsu, Zhigang Tian, Xin Su

引用次数: 2

Heart rate trend forecasting during high-intensity interval training using consumer wearable devices 使用消费者可穿戴设备预测高强度间歇训练期间的心率趋势

Proceedings of the 27th Annual International Conference on Mobile Computing and Networking Pub Date : 2021-10-19 DOI: 10.1145/3447993.3482870

Illia Fedorin, Kostyantyn Slyusarenko, V. Pohribnyi, JongSeok Yoon, Gunguk Park, Hyunsu Kim

{"title":"Heart rate trend forecasting during high-intensity interval training using consumer wearable devices","authors":"Illia Fedorin, Kostyantyn Slyusarenko, V. Pohribnyi, JongSeok Yoon, Gunguk Park, Hyunsu Kim","doi":"10.1145/3447993.3482870","DOIUrl":"https://doi.org/10.1145/3447993.3482870","url":null,"abstract":"High-Intensity Interval Training is one of the most popular and dynamically developing fitness innovations in recent years. Professional runners have used interval training for a long time, alternating between high intensity sprints and low intensity jogging intervals to improve their overall performance. During such exercises, the accurate monitoring and prediction of heart rate dynamics is of particular importance to control the physiological state of a person and prevent possible pathological consequences. At the same time, heart rate estimation using very popular nowadays wearable devices (like smartwatches, fitness belts, etc.) during high-intensity exercises can be quite inaccurate. This inaccuracy mostly happens since the heart rate sensors (photoplethysmogram (PPG) and electrocardiogram (ECG)) are exposed to noises due to motion artifacts. PPG sensor suffers from periodic ambient light saturation due to intensive hand motions. ECG is noisy due to electrode contact area changes by body deformation. To solve the mentioned problem, in the current paper a deep learning framework for motion resistive heart rate estimation is developed. The system combines signal processing approaches for the raw sensor data processing and a deep learning architectures (convolutional and recurrent neural networks) for a real-time heart rate measurements and forecasting future heart rate dynamics.","PeriodicalId":177431,"journal":{"name":"Proceedings of the 27th Annual International Conference on Mobile Computing and Networking","volume":"35 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-10-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122304595","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 4

Detection of evil flies: securing air-ground aviation communication 侦测恶蝇:确保空中-地面航空通讯

Proceedings of the 27th Annual International Conference on Mobile Computing and Networking Pub Date : 2021-10-19 DOI: 10.1145/3447993.3482869

Suleman Khan, Pardeep Kumar, An Braeken, A. Gurtov

引用次数: 1

Nuberu: reliable RAN virtualization in shared platforms Nuberu:可靠的共享平台RAN虚拟化

Proceedings of the 27th Annual International Conference on Mobile Computing and Networking Pub Date : 2021-10-19 DOI: 10.1145/3447993.3483266

Gines Garcia-Aviles, Andres Garcia-Saavedra, M. Gramaglia, X. Costa, P. Serrano, A. Banchs

{"title":"Nuberu: reliable RAN virtualization in shared platforms","authors":"Gines Garcia-Aviles, Andres Garcia-Saavedra, M. Gramaglia, X. Costa, P. Serrano, A. Banchs","doi":"10.1145/3447993.3483266","DOIUrl":"https://doi.org/10.1145/3447993.3483266","url":null,"abstract":"RAN virtualization will become a key technology for the last mile of next-generation mobile networks driven by initiatives such as the O-RAN alliance. However, due to the computing fluctuations inherent to wireless dynamics and resource contention in shared computing infrastructure, the price to migrate from dedicated to shared platforms may be too high. Indeed, we show in this paper that the baseline architecture of a base station's distributed unit (DU) collapses upon moments of deficit in computing capacity. Recent solutions to accelerate some signal processing tasks certainly help but do not tackle the core problem: a DU pipeline that requires predictable computing to provide carrier-grade reliability. We present Nuberu, a novel pipeline architecture for 4G/5G DUs specifically engineered for non-deterministic computing platforms. Our design has one key objective to attain reliability: to guarantee a minimum set of signals that preserve synchronization between the DU and its users during computing capacity shortages and, provided this, maximize network throughput. To this end, we use techniques such as tight deadline control, jitter-absorbing buffers, predictive HARQ, and congestion control. Using an experimental prototype, we show that Nuberu attains >95% of the theoretical spectrum efficiency in hostile environments, where state-of-art approaches lose connectivity, and at least 80% resource savings.","PeriodicalId":177431,"journal":{"name":"Proceedings of the 27th Annual International Conference on Mobile Computing and Networking","volume":"63 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-10-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115115089","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 24

Octopus 章鱼

Proceedings of the 27th Annual International Conference on Mobile Computing and Networking Pub Date : 2021-10-19 DOI: 10.2307/j.ctt1ffjdz1.28

Zhe Chen, Tianyue Zheng, Jun Luo

引用次数: 0

PassiveLiFi

Proceedings of the 27th Annual International Conference on Mobile Computing and Networking Pub Date : 2021-10-19 DOI: 10.1145/3447993.3483262

M. Mir, Borja Genovés Guzmán, Ambuj Varshney, D. Giustiniano

引用次数: 8