2021 IEEE International Conference on Smart Computing (SMARTCOMP)最新文献_第4页

A Framework for Partitioning Support Vector Machine Models on Edge Architectures 一种基于边缘架构的支持向量机模型划分框架

2021 IEEE International Conference on Smart Computing (SMARTCOMP) Pub Date : 2021-08-01 DOI: 10.1109/SMARTCOMP52413.2021.00062

Mansi Sahi, Md. Al Maruf, Akramul Azim, Nitin Auluck

{"title":"A Framework for Partitioning Support Vector Machine Models on Edge Architectures","authors":"Mansi Sahi, Md. Al Maruf, Akramul Azim, Nitin Auluck","doi":"10.1109/SMARTCOMP52413.2021.00062","DOIUrl":"https://doi.org/10.1109/SMARTCOMP52413.2021.00062","url":null,"abstract":"Current IoT applications generate huge volumes of complex data that requires agile analysis in order to obtain deep insights, often by applying Machine Learning (ML) techniques. Support vector machine (SVM) is one such ML technique that has been used in object detection, image classification, text categorization and Pattern Recognition. However, training even a simple SVM model on big data takes a significant amount of computational time. Due to this, the model is unable to react and adapt in real-time. There is an urgent need to speedup the training process. Since organizations typically use the cloud for this data processing, accelerating the training process has the advantage of bringing down costs. In this paper, we propose a model partitioning approach that partitions the tasks of Stochastic Gradient Descent based Support Vector Machines (SGD-SVM) on various edge devices for concurrent computation, thus reducing the training time significantly. The proposed partitioning mechanism not only brings down the training time but also maintains the approximate accuracy over the centralized cloud approach. With a goal of developing a smart objection detection system, we conduct experiments to evaluate the performance of the proposed method using SGD-SVM on an edge based architecture. The results illustrate that the proposed approach significantly reduces the training time by 47%, while decreasing the accuracy by 2%, and offering an optimal number of partitions.","PeriodicalId":330785,"journal":{"name":"2021 IEEE International Conference on Smart Computing (SMARTCOMP)","volume":"94 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126081505","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: 0

Cloud Computing Management Architecture for Digital Health Remote Patient Monitoring 数字健康远程患者监测的云计算管理架构

2021 IEEE International Conference on Smart Computing (SMARTCOMP) Pub Date : 2021-08-01 DOI: 10.1109/SMARTCOMP52413.2021.00049

Hsuan Su, L. Yao, Dennis Hou, M. Sun, Janpu Hou, Jeffrey Ying, Hsin-Yu Feng, Po-Ying Chen, Raymond Hou

{"title":"Cloud Computing Management Architecture for Digital Health Remote Patient Monitoring","authors":"Hsuan Su, L. Yao, Dennis Hou, M. Sun, Janpu Hou, Jeffrey Ying, Hsin-Yu Feng, Po-Ying Chen, Raymond Hou","doi":"10.1109/SMARTCOMP52413.2021.00049","DOIUrl":"https://doi.org/10.1109/SMARTCOMP52413.2021.00049","url":null,"abstract":"With machine learning, the remote patient monitoring (RPM) devices are no longer just remote data collection devices. In addition to data analytics, data security and systems integration are also core challenges for developers of the next generation of innovative RPM devices. This includes overcoming technological barriers on applying machine learning algorithms to patient data directly on devices and regulatory barriers on patient data privacy. To address these challenges, this study proposed a unified edge-cloud computing architecture to effectively integrate all the RPM devices in use by the individual patient. All the remote patient monitoring data are managed by edge computing, only the latent representations are uploaded to the cloud for AI-assisted decision making. The proposed model has three modules. The edge medical image module used a subspace learning model for anomalies detection and unhealthy signs and symptoms classification. The edge medical time series module used spectral residual for anomalies detection and scattering wavelet network for severity classification. The cloud telehealth management module used convolutional neural network, recurrent neural network and attention model to provide individual patient treatment plan and medicine delivery schedule. The proposed platform has been tested on various RPM devices to provide AI-based anomaly detection and symptoms classifications. The application of the proposed platform has demonstrated that the on-device training model can enable faster and more accurate diagnosis and treatment. For meso-level organizational interoperability on health information exchange, we will only transmit the latent representation instead of the patient’s raw data to reduce cyberattacks and ensure confidentiality of health data.","PeriodicalId":330785,"journal":{"name":"2021 IEEE International Conference on Smart Computing (SMARTCOMP)","volume":"69 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126225595","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: 0

Message from SSC 2021 Workshop Co-Chairs SSC 2021研讨会共同主席致辞

2021 IEEE International Conference on Smart Computing (SMARTCOMP) Pub Date : 2021-08-01 DOI: 10.1109/smartcomp52413.2021.00019

引用次数: 0

Multi-task BERT for Aspect-based Sentiment Analysis 面向面向方面情感分析的多任务BERT

2021 IEEE International Conference on Smart Computing (SMARTCOMP) Pub Date : 2021-08-01 DOI: 10.1109/SMARTCOMP52413.2021.00077

Yuqi Wang, Qi Chen, Wen Wang

引用次数: 5

Blockchain and Self-Sovereign Identity Empowered Cyber Threat Information Sharing Platform 区块链和自主身份授权的网络威胁信息共享平台

2021 IEEE International Conference on Smart Computing (SMARTCOMP) Pub Date : 2021-08-01 DOI: 10.1109/SMARTCOMP52413.2021.00057

Eranga Bandara, Xueping Liang, Peter B. Foytik, S. Shetty

引用次数: 4

PhD Forum Abstract: Efficient Computing and Communication Paradigms for Federated Learning Data Streams 摘要:联邦学习数据流的高效计算和通信范式

2021 IEEE International Conference on Smart Computing (SMARTCOMP) Pub Date : 2021-08-01 DOI: 10.1109/SMARTCOMP52413.2021.00086

S. Bano

引用次数: 0

Smart Oracle Based Building Management System 基于Oracle的智能楼宇管理系统

2021 IEEE International Conference on Smart Computing (SMARTCOMP) Pub Date : 2021-08-01 DOI: 10.1109/SMARTCOMP52413.2021.00029

Angan Mitra, Yanik Ngoko, D. Trystram

{"title":"Smart Oracle Based Building Management System","authors":"Angan Mitra, Yanik Ngoko, D. Trystram","doi":"10.1109/SMARTCOMP52413.2021.00029","DOIUrl":"https://doi.org/10.1109/SMARTCOMP52413.2021.00029","url":null,"abstract":"Buildings in residential and commercial sites consume close to 40 per cent of the world’s total energy produced and is growing at a steady pace. The need to lower the energy footprint is a matter of sustainability and active research for the smart building community. Recent trends in machine learning have led to significant work on occupancy detection in spaces by training isolated or ex-situ models, but with no reliability of performance on unknown spaces. Model applicability becomes questionable when the sensor value distribution is different from training data and in a real-life this is usually the case. Furthermore, analyzing a space on a floor-plan in silo obscures the holistic view of interactivity between building elements. In this paper, we propose the design of a generic building management system that auto-learns occupancy patterns and leverages spatial organization to deliver actionable insights on energy savings. We combine the building information with sensor signals into a Spatio-temporal activity graph, whose edges are dynamically updated based on occupancy. We introduce human-space interaction models to infer the human transmission capacity of each edge and compute an Eigenvalue score for all the spaces to derive automated checkpoints on space-wise appliance monitoring.","PeriodicalId":330785,"journal":{"name":"2021 IEEE International Conference on Smart Computing (SMARTCOMP)","volume":"70 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114836135","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

Birdsong Detection at the Edge with Deep Learning 基于深度学习的边缘鸟鸣检测

2021 IEEE International Conference on Smart Computing (SMARTCOMP) Pub Date : 2021-08-01 DOI: 10.1109/SMARTCOMP52413.2021.00022

Simone Disabato, Giuseppe Canonaco, P. Flikkema, M. Roveri, C. Alippi

{"title":"Birdsong Detection at the Edge with Deep Learning","authors":"Simone Disabato, Giuseppe Canonaco, P. Flikkema, M. Roveri, C. Alippi","doi":"10.1109/SMARTCOMP52413.2021.00022","DOIUrl":"https://doi.org/10.1109/SMARTCOMP52413.2021.00022","url":null,"abstract":"Understanding the distribution of bird species and populations and learning how birds behave and communicate are of great importance in wildlife biology, animal ecology, conservation of ecosystems, and assessing the effects of climate change and urbanization. The temporal and spatial limitations of human observation have motivated significant efforts to develop technology for bird song and vocalization detection and classification. While solutions based on signal processing and machine learning are extant, they are limited in various combinations of speed, computational complexity, and memory use, as well as in detection/classification capability in real-world conditions. This paper introduces ToucaNet, a deep neural network for birdsong detection based on transfer-learning, a deep learning mechanism allowing us to exploit knowledge acquired on various tasks: this enables us to speed up training and shows improved detection accuracy. ToucaNet provides birdsong detection accuracy in line with the best solutions in the literature but with much less computational complexity and memory demand. We also introduce BarbNet, an approximated version of ToucaNet tailored for Internet-of-Things (IoT) units. We show the proposed solution’s effectiveness and efficiency in terms of detection accuracy and the implementation feasibility in real-world IoT devices, with specific results for the STM32 Nucleo H7 board, which is based on an ARM Cortex-M7 processor. To our best knowledge, this is the first birdsong detection algorithm designed to take into account constraints on memory, computational speed, and power usage of embedded devices. Thus, this work points the way to cost-effective IoT technology for at-scale intelligent birdsong data collection and analysis in the field.","PeriodicalId":330785,"journal":{"name":"2021 IEEE International Conference on Smart Computing (SMARTCOMP)","volume":"43 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115080926","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: 7

Message from the BITS 2021 General Chairs and TPC Chairs 2021年BITS总主席和TPC主席致辞

2021 IEEE International Conference on Smart Computing (SMARTCOMP) Pub Date : 2021-08-01 DOI: 10.1109/smartcomp52413.2021.00015

引用次数: 0

Hardware/Software Security Patches for the Internet of Things 物联网硬件/软件安全补丁

2021 IEEE International Conference on Smart Computing (SMARTCOMP) Pub Date : 2021-08-01 DOI: 10.1109/SMARTCOMP52413.2021.00054

J. Stankovic, Tu Le, Abdeltawab M. Hendawi, Yuan Tian

引用次数: 0