2021 IEEE 6th International Conference on Computer and Communication Systems (ICCCS)最新文献_第3页

Enable Pipeline Processing of DNN Co-inference Tasks In the Mobile-Edge Cloud 在移动边缘云中启用DNN协同推理任务的流水线处理

2021 IEEE 6th International Conference on Computer and Communication Systems (ICCCS) Pub Date : 2021-04-23 DOI: 10.1109/ICCCS52626.2021.9449178

Sheng Hu, Chongwu Dong, Wushao Wen

{"title":"Enable Pipeline Processing of DNN Co-inference Tasks In the Mobile-Edge Cloud","authors":"Sheng Hu, Chongwu Dong, Wushao Wen","doi":"10.1109/ICCCS52626.2021.9449178","DOIUrl":"https://doi.org/10.1109/ICCCS52626.2021.9449178","url":null,"abstract":"Deep Neural Network (DNN) based artificial intelligence help driving the great development of mobile Internet. However, the hardware of a mobile device may not be sufficiently to meet the computational requirements of a DNN inference task. Fortunately, computation offloading to the network edge can mitigate part of computation pressure for mobile devices. In this case, DNN computation in mobile devices can be accelerated by an edge-assistance collaborative inference scheme. Since co-inference tasks with multiple processing stages may continuously arrive at mobile devices, only considering one DNN-based task for acceleration is not practical. To solve the above challenge effectively, we formulate the problem of multiple co-inference tasks acceleration as a pipeline execution model. Based on the model, we design a fine-grained optimizer, which integrates model partition, model early-exit and intermediate data compression, to achieve tradeoff between accuracy and latency. Considering computational characteristics of a pipeline, the goal of the optimizer is designed to ensure the pipeline system's inference rate and single task execution performance. We implement the system prototype and do benchmark tests under a real-life testbed and the results prove the effectiveness of the optimizer.","PeriodicalId":376290,"journal":{"name":"2021 IEEE 6th International Conference on Computer and Communication Systems (ICCCS)","volume":"25 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-04-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130740021","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: 3

Intelligent Fertilization System Based on Image Recognition 基于图像识别的智能施肥系统

2021 IEEE 6th International Conference on Computer and Communication Systems (ICCCS) Pub Date : 2021-04-23 DOI: 10.1109/ICCCS52626.2021.9449144

Zhe Sun, Wei Feng, Jintao Jin, Qujiang Lei, Guangchao Gui, Weijun Wang

引用次数: 0

Identify IoT Devices through Web Interface Characteristics 通过Web接口特征识别物联网设备

2021 IEEE 6th International Conference on Computer and Communication Systems (ICCCS) Pub Date : 2021-04-23 DOI: 10.1109/ICCCS52626.2021.9449258

Hui Cheng, Weiyu Dong, Yan Zheng, Bo Lv

引用次数: 3

Dynamic Power Allocation for Cooperative Multi- Antenna Networks in Presence of Mutual Coupling 相互耦合下协同多天线网络的动态功率分配

2021 IEEE 6th International Conference on Computer and Communication Systems (ICCCS) Pub Date : 2021-04-23 DOI: 10.1109/ICCCS52626.2021.9449251

Emmanuel Ufiteyezu, Yun Li

引用次数: 1

A Fast Image Denoising Method Based on CP Tensor Analysis 基于CP张量分析的快速图像去噪方法

2021 IEEE 6th International Conference on Computer and Communication Systems (ICCCS) Pub Date : 2021-04-23 DOI: 10.1109/ICCCS52626.2021.9449104

Xinhong Pan, Guoyi Zhang, Li Wang, Guangbo Wang, Jingyi Dong, Jiali Cao

引用次数: 0

Considerations on the Model Selection of SDOTN Controller Northbound Interface 关于SDOTN控制器北向接口选型的思考

2021 IEEE 6th International Conference on Computer and Communication Systems (ICCCS) Pub Date : 2021-04-23 DOI: 10.1109/ICCCS52626.2021.9449157

Yanlei Zheng, Yacheng Liu, Guangquan Wang

引用次数: 0

Attention-based Efficient Lightweight Model for Accurate Real-Time Face Verification on Embedded Device 基于注意力的嵌入式设备实时精确人脸验证高效轻量级模型

2021 IEEE 6th International Conference on Computer and Communication Systems (ICCCS) Pub Date : 2021-04-23 DOI: 10.1109/ICCCS52626.2021.9449167

Dongmei Wei, Xingjun Wu, Guoqiang Bai, Linlin Su, Sufen Xu

{"title":"Attention-based Efficient Lightweight Model for Accurate Real-Time Face Verification on Embedded Device","authors":"Dongmei Wei, Xingjun Wu, Guoqiang Bai, Linlin Su, Sufen Xu","doi":"10.1109/ICCCS52626.2021.9449167","DOIUrl":"https://doi.org/10.1109/ICCCS52626.2021.9449167","url":null,"abstract":"With the rapid development of face verification technology, the current face verification has reached a high accuracy rate. However, face verification requires large computing resources and complex model parameters, so it is difficult to be applied in real scenes. The face verification system based on embedded applications can well solve the problems of huge model storage space occupation and high computing resource consumption. The existing mainstream face verification models have reached high accuracy, such as VGG16Net. Although there have been studies trying to design lightweight neural networks, such as MobileFaceNet, etc., there are still shortcomings such as complex structure and high resource consumption, so it is only suitable for mobile devices and other embedded devices, and it is difficult to apply to low power consumption and low performance such as embedded systems. In the device. For embedded systems with limited memory and computing power, a more lightweight neural network model is needed. Therefore, this paper conducts two researches on the problems of model storage requiring a large amount of space and high computational resource consumption. First of all, a lightweight face verification network model MobileFaceNet-v3m based on the attention mechanism is designed to solve the problem of model storage space occupation. Our model has a 15.26% smaller space occupation than MobileFaceNet, which successfully reduces the resource consumption of the model. The accuracy rate can still be maintained at a high level-95.47% of face verification accuracy is achieved on LFW; secondly, We use the learning rate optimization method based on efficient warm restart to train the model, the accuracy of the model is improved faster, and the model is successfully transplanted to the embedded platform, which is another step forward to the real scene application in the future.","PeriodicalId":376290,"journal":{"name":"2021 IEEE 6th International Conference on Computer and Communication Systems (ICCCS)","volume":"9 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-04-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125387481","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: 2

DBF Based Channel Estimation for Self-interference Cancellation in Full-Duplex Communications 全双工通信中基于DBF的自干扰消除信道估计

2021 IEEE 6th International Conference on Computer and Communication Systems (ICCCS) Pub Date : 2021-04-23 DOI: 10.1109/ICCCS52626.2021.9449236

Wei Wang, Zhongshan Zhang

{"title":"DBF Based Channel Estimation for Self-interference Cancellation in Full-Duplex Communications","authors":"Wei Wang, Zhongshan Zhang","doi":"10.1109/ICCCS52626.2021.9449236","DOIUrl":"https://doi.org/10.1109/ICCCS52626.2021.9449236","url":null,"abstract":"The full-duplex technology can achieve higher spectrum utilization than the traditional half-duplex technology, which has attracted widespread attention in both academia and industry. Since the performance of the full-duplex system is severely restricted by the self-interference (SI) signal, the influence of the SI signal must be eliminated to give full play to the advantages of the full-duplex technology. Restricted by device performance and circuit structure, traditional analog domain SI cancellation technology has disadvantages such as low accuracy, poor flexibility, and high hardware overhead. In order to avoid the above-mentioned problems, we investigate the SI cancellation technology in the digital domain, and uses digital beamforming (DBF) algorithm for high-precision SI channel estimation. Relying on the auto-correlation characteristics of spread spectrum sequences, SI channel parameters can be quickly obtained by implementing both amplitude and phase tests. It is shown in both simulation and hardware experiment that the adjustment accuracy of amplitude and phase can be better than 0.05dB and 0.05° which is far better than that of the commonly used 8-bit controlled phase shifter, with the accuracy of 1.4° and adjustable attenuator, with the accuracy of 0.5dB. The improvement of accuracy makes the SI cancellation capability of the proposed algorithm 13.49 dB higher than that of the traditional method. The proposed algorithm can be implemented with high enough accuracy and better performance which has a wide range of applications.","PeriodicalId":376290,"journal":{"name":"2021 IEEE 6th International Conference on Computer and Communication Systems (ICCCS)","volume":"43 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-04-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121226668","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: 1

Lightweight Authenticated Encryption Mode with Enhancing Security Guarantees 增强安全保证的轻量级认证加密模式

2021 IEEE 6th International Conference on Computer and Communication Systems (ICCCS) Pub Date : 2021-04-23 DOI: 10.1109/ICCCS52626.2021.9449205

Ping Zhang, Qian Yuan

{"title":"Lightweight Authenticated Encryption Mode with Enhancing Security Guarantees","authors":"Ping Zhang, Qian Yuan","doi":"10.1109/ICCCS52626.2021.9449205","DOIUrl":"https://doi.org/10.1109/ICCCS52626.2021.9449205","url":null,"abstract":"Under the lightweight setting, the security requirements and the leaking security bits for devices or systems are stricter. This paper focuses on the security of permutation-based lightweight authenticated encryption (LAE) modes, presents a new syntax of LAE, and, on the basis of OPP. proposes an enhanced LAE mode called OPP-plus which supports beyond-birthday-bound (BBB) security and integrity security under the releasing unverified plaintext (INT-RUP). For achieving BBB security, OPP-plus is set up by two-round Even-Mansour ciphers with distinct keys. For ensuring INT-RUP security, the authentication part of OPP-plus utilizes an extra intermediated checksum technique to generate the authentication tag. Then, by using the hybrid argument, we prove that OPP-plus meets our stronger security requirements in the nonce-respecting scenario if the underlying permutation is an ideal random permutation. Finally, we discuss the properties of OPP-plus. OPP-plus is based on a pure-permutation, and supports adaptively block-size and smaller security losses. As OPP-plus does not perform the key expansion algorithm and its parts of combinatorial circuits can be replaced directly by lookup tables, the cost of keys' update is relatively small and the implementation efficiency is relatively high in practice.","PeriodicalId":376290,"journal":{"name":"2021 IEEE 6th International Conference on Computer and Communication Systems (ICCCS)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-04-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133080633","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: 1

A Nameserver Importance Ranking Method Based on Heterogeneous Information Network 基于异构信息网络的域名服务器重要性排序方法

2021 IEEE 6th International Conference on Computer and Communication Systems (ICCCS) Pub Date : 2021-04-23 DOI: 10.1109/ICCCS52626.2021.9449288

Bingyang Guo, M. Zhang, Chengxi Xu, Fan Shi

引用次数: 0