2020 IEEE International Conference on Internet of Things and Intelligence System (IoTaIS)最新文献

筛选
英文 中文
A Rigorous Analysis of Biomedical Edge Computing: An Arrhythmia Classification Use-Case Leveraging Deep Learning 生物医学边缘计算的严格分析:利用深度学习的心律失常分类用例
2020 IEEE International Conference on Internet of Things and Intelligence System (IoTaIS) Pub Date : 2021-01-27 DOI: 10.1109/IoTaIS50849.2021.9359721
S. Sakib, M. Fouda, Z. Fadlullah
{"title":"A Rigorous Analysis of Biomedical Edge Computing: An Arrhythmia Classification Use-Case Leveraging Deep Learning","authors":"S. Sakib, M. Fouda, Z. Fadlullah","doi":"10.1109/IoTaIS50849.2021.9359721","DOIUrl":"https://doi.org/10.1109/IoTaIS50849.2021.9359721","url":null,"abstract":"Biomedical Edge computing is an exciting area of interdisciplinary research involving the Internet of Medical Things (IoMT) sensors and devices with lightweight Artificial Intelligence (AI) logic. To address the rapidly growing need for smart and portable biomedical devices with localized decision-making capability, we present a proof-of-concept logic-in-sensor design with an arrhythmia analytics use-case. Existing signal processing techniques for arrhythmia analytics such as discrete wave transform (DWT) and non-linear delay differential equation (DDE) lead to high complexity and computational burden on biomedical edge devices due to expensive preprocessing steps. As a solution, we propose a deep learning-based lightweight arrhythmia classification method leveraging a customized one-dimensional (1-D) convolutional neural network (CNN). A rigorous analysis of the proposed method's performances and generalization potential are assessed using four publicly available datasets.","PeriodicalId":409079,"journal":{"name":"2020 IEEE International Conference on Internet of Things and Intelligence System (IoTaIS)","volume":"8 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-01-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133067600","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: 9
IDS Performance Analysis using Anomaly-based Detection Method for DOS Attack 基于异常检测方法的DOS攻击IDS性能分析
2020 IEEE International Conference on Internet of Things and Intelligence System (IoTaIS) Pub Date : 2021-01-27 DOI: 10.1109/IoTaIS50849.2021.9359719
Aghnia Fadhlillah, N. Karna, A. Irawan
{"title":"IDS Performance Analysis using Anomaly-based Detection Method for DOS Attack","authors":"Aghnia Fadhlillah, N. Karna, A. Irawan","doi":"10.1109/IoTaIS50849.2021.9359719","DOIUrl":"https://doi.org/10.1109/IoTaIS50849.2021.9359719","url":null,"abstract":"Intrusion Detection System (IDS) is a system that could detect suspicious activity in a network. Two approaches are known for IDS, namely signature-based and anomaly-based. The anomaly-based detection method was chosen to detect suspicious and abnormal activity for the system that cannot be performed by the signature-based method. In this study, attack testing was carried out using three DoS tools, namely the LOIC, Torshammer, and Xerxes tools, with a test scenario using IDS and without IDS. From the test results that have been carried out, IDS has successfully detected the attacks that were sent, for the delivery of the most consecutive attack packages, namely Torshammer, Xerxes, and LOIC. In the detection of Torshammer attack tools on the target FTP Server, 9421 packages were obtained, for Xerxes tools as many as 10618 packages and LOIC tools as many as 6115 packages. Meanwhile, attacks on the target Web Server for Torshammer tools were 299 packages, for Xerxes tools as many as 530 packages, and for LOIC tools as many as 103 packages. The accuracy of the IDS performance results is 88.66%, the precision is 88.58% and the false positive rate is 63.17%.","PeriodicalId":409079,"journal":{"name":"2020 IEEE International Conference on Internet of Things and Intelligence System (IoTaIS)","volume":"29 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-01-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124002852","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
The Last Mile of M-Connected-Healthcare in the Covid Age: Data Sharing at Large Scale 新冠时代移动互联医疗的最后一英里:大规模数据共享
2020 IEEE International Conference on Internet of Things and Intelligence System (IoTaIS) Pub Date : 2021-01-27 DOI: 10.1109/IoTaIS50849.2021.9359706
A. Faro, D. Giordano, M. Venticinque
{"title":"The Last Mile of M-Connected-Healthcare in the Covid Age: Data Sharing at Large Scale","authors":"A. Faro, D. Giordano, M. Venticinque","doi":"10.1109/IoTaIS50849.2021.9359706","DOIUrl":"https://doi.org/10.1109/IoTaIS50849.2021.9359706","url":null,"abstract":"Aim of the paper is to illustrate a platform for that supports the link between the patient and doctors, family members, clinical laboratories and hospitals, that is a platform that supports the last mile between patients and the entire healthcare network so that the personal data collected by edge devices don't remain confined locally at the patient side but are shared at large scale to aid the patients anywhere and anytime. In particular the paper illustrates from the engineering point of view how implementing the last mile for Covid monitoring and control in practice by means of available Cyber Physical Systems (CPSs), i.e., edge IoT devices provided with communication and computational functions, freeware home control systems and low cost relevant web services available on the market. The key element of our proposal is the one of using a portable BLE/MQTT gateway or to develop DIY MQTT sensors to allow health measurements taken by edge devices to be sent to a remote automated control system supervised by a doctor. A detailed analysis is carried out on the contact and contactless sensors that can be integrated in our platform from the more and more diffused smart bands and ibeacons until the IR thermal cameras. For each considered sensor, the paper discusses its integration it in the platform and the global scenario in which it may be used effectively","PeriodicalId":409079,"journal":{"name":"2020 IEEE International Conference on Internet of Things and Intelligence System (IoTaIS)","volume":"71 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-01-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116351981","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
Network Intrusion Detection System Using Neural Network and Condensed Nearest Neighbors with Selection of NSL-KDD Influencing Features 基于NSL-KDD影响特征选择的神经网络和精简近邻网络入侵检测系统
2020 IEEE International Conference on Internet of Things and Intelligence System (IoTaIS) Pub Date : 2021-01-27 DOI: 10.1109/IoTaIS50849.2021.9359689
Fatima Zohra Belgrana, Nacéra Benamrane, Mohamed Amine Hamaida, Abdellah Mohamed Chaabani, A. Taleb-Ahmed
{"title":"Network Intrusion Detection System Using Neural Network and Condensed Nearest Neighbors with Selection of NSL-KDD Influencing Features","authors":"Fatima Zohra Belgrana, Nacéra Benamrane, Mohamed Amine Hamaida, Abdellah Mohamed Chaabani, A. Taleb-Ahmed","doi":"10.1109/IoTaIS50849.2021.9359689","DOIUrl":"https://doi.org/10.1109/IoTaIS50849.2021.9359689","url":null,"abstract":"The number and severity of cybernetic attacks continue to increase. Thereupon Intrusion Detection Systems (IDSs) have become an integral part of the organization's security infrastructure. Several algorithms have been applied in order to realize the detection of anomalies. They derived mainly from Artificial Intelligence (AI). The main interest is thus to reduce the false-negative and improve the quality of detection. However, it is important to reduce processing time. There are many data sets in literature which can be used for the learning and the test step of the IDS. One of the objectives of this work is to select the most significant characteristics of New Selected Learning-Knowledge Discovery in Databases Data set (NSL- KDD), which influences the result of the detection. Therefore, we will consume the disturbing element of the dataset. To realize our Network IDS (NIDS), we implemented the Condensed Nearest Neighbors (CNN) algorithm as our first approach. A very effective method for classification and regression as it considers the distribution of samples. CNN reduces the data vector dimension which leads in turn to low use of system resources as well as a reduction in processing time while maintaining good detection results. In a second approach, we adopted a Neural Network (NN) with a pre-classification of our learning data set.To prove the efficiency of our approaches, we release a comparison with K Nearest Neighbors (KNN) methods. We also compare our approaches with two other methods from WEKA software. Experiments show that our two proposed approaches of IDS improve the detection rate, decrease missed attacks while reducing processing time.","PeriodicalId":409079,"journal":{"name":"2020 IEEE International Conference on Internet of Things and Intelligence System (IoTaIS)","volume":"157 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-01-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131827566","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
Android-based Disaster Management Application for After-Disaster Rapid Mobile Assessment 基于android的灾后快速移动评估灾害管理应用
2020 IEEE International Conference on Internet of Things and Intelligence System (IoTaIS) Pub Date : 2021-01-27 DOI: 10.1109/IoTaIS50849.2021.9359695
Jason Widagdo, Dicky Dwi Putra, Budi Syihabuddin, T. Juhana, E. Mulyana, A. Munir
{"title":"Android-based Disaster Management Application for After-Disaster Rapid Mobile Assessment","authors":"Jason Widagdo, Dicky Dwi Putra, Budi Syihabuddin, T. Juhana, E. Mulyana, A. Munir","doi":"10.1109/IoTaIS50849.2021.9359695","DOIUrl":"https://doi.org/10.1109/IoTaIS50849.2021.9359695","url":null,"abstract":"As the most disaster-prone countries in the world, Indonesia is facing multiple hazards. However, due to some technical problems such as condition of the hazard level, the performances of disaster management have not yet run optimally. In contributing to the disaster management, this paper proposes the development of after-disaster rapid mobile assessment application using android platform. The application which is a client-server-based system is deployed on a web server for the server side and implemented on a mobile device for the client side. By using the proposed application which then it is named as Mobile Indonesia Damage Data Assessor (MIDDAS), the assessors are allowed to inventory disaster-damaged buildings by uploading the damage data into the rapid damage assessment server to be displayable on the web pages. Based on the data, the decision maker can assess rapidly the essential damage information and calculate the required recovery cost.","PeriodicalId":409079,"journal":{"name":"2020 IEEE International Conference on Internet of Things and Intelligence System (IoTaIS)","volume":"24 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-01-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122027629","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
Finding the Proper Mental Stress Model Depending on Context using Edge Devices and Machine Learning 利用边缘设备和机器学习找到适合上下文的心理压力模型
2020 IEEE International Conference on Internet of Things and Intelligence System (IoTaIS) Pub Date : 2021-01-27 DOI: 10.1109/IoTaIS50849.2021.9359701
A. Faro, D. Giordano, M. Venticinque
{"title":"Finding the Proper Mental Stress Model Depending on Context using Edge Devices and Machine Learning","authors":"A. Faro, D. Giordano, M. Venticinque","doi":"10.1109/IoTaIS50849.2021.9359701","DOIUrl":"https://doi.org/10.1109/IoTaIS50849.2021.9359701","url":null,"abstract":"Aim of the paper is to demonstrate how finding the proper mental stress model and its dependencies on context using Machine Learning technologies resident on edge devices to allow the user and remote medical staff to continuously monitor and control the user stress status. To this aim, the paper first discusses the method used to measure the mental stress inspired by tools available on the market, secondly it illustrates how the sensed bio-data should be preprocessed on an edge device to support the first control actions. Finally it shows how such data may used to derive a stress model of the user using a machine learning algorithm on edge devices and/or computing server. An example illustrates the proposed methodology, how this model can be tuned depending on context using the data collected by the wearable monitoring device, and how the entire system can be implemented on few interconnected micro-boards. A case study demonstrates how deriving the mental stress model of a subject depending on contexts also by using the stress mental model derived from a community of people.","PeriodicalId":409079,"journal":{"name":"2020 IEEE International Conference on Internet of Things and Intelligence System (IoTaIS)","volume":"11 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-01-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125545753","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
Image-based Kinship Verification Using Dual VGG-Face Classifie 基于图像的VGG-Face双分类亲属关系验证
2020 IEEE International Conference on Internet of Things and Intelligence System (IoTaIS) Pub Date : 2021-01-27 DOI: 10.1109/IoTaIS50849.2021.9359720
R. F. Rachmadi, I. Purnama, S. M. S. Nugroho, Y. Suprapto
{"title":"Image-based Kinship Verification Using Dual VGG-Face Classifie","authors":"R. F. Rachmadi, I. Purnama, S. M. S. Nugroho, Y. Suprapto","doi":"10.1109/IoTaIS50849.2021.9359720","DOIUrl":"https://doi.org/10.1109/IoTaIS50849.2021.9359720","url":null,"abstract":"In this paper, we investigated dual VGG-Face convolutional neural network classifier for image-based kinship verification problems. The proposed classifier is formed by paralleling convolutional layers of VGG CNN architecture and combined it with several fully-connected layers. Although the VGG CNN architecture is consists of huge parameters, the number of parameters in the classifier will be reduced by more than 80% by removing the fully-connected layers of the original classifier. We use the multi-task loss function for the training process to ensure that the features learned by the classifier are also can be used for family classification. Experiments on the FIW kinship verification dataset show that dual VGG-Face CNN classifiers can achieve an average accuracy of 64.71% on a single classifier and 65.49% on ensemble configuration. Based on our experiments, the lowest accuracy is produced for second-generation kinship (grandchild - grandparent) which have a low number of examples on FIW kinship.","PeriodicalId":409079,"journal":{"name":"2020 IEEE International Conference on Internet of Things and Intelligence System (IoTaIS)","volume":"24 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-01-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127577644","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
Lightweight Remote Control of Distributed Web-of-Things Platforms: First Prototype 分布式物联网平台的轻量级远程控制:第一个原型
2020 IEEE International Conference on Internet of Things and Intelligence System (IoTaIS) Pub Date : 2021-01-27 DOI: 10.1109/IoTaIS50849.2021.9359718
Allal Tiberkak, A. Hentout, Abdelkader Belkhir
{"title":"Lightweight Remote Control of Distributed Web-of-Things Platforms: First Prototype","authors":"Allal Tiberkak, A. Hentout, Abdelkader Belkhir","doi":"10.1109/IoTaIS50849.2021.9359718","DOIUrl":"https://doi.org/10.1109/IoTaIS50849.2021.9359718","url":null,"abstract":"Web of Things is the concept of controlling smart and communicating systems, Connected Objects (COs), through Web applications. Web technologies offer interoperable and flexible technologies to implement sophisticated GUI to control COs. However, such technologies are very limited in terms of communication protocols. This paper proposes a lightweight platform to control COs via Web applications without adding any extension to the Web browser. For this, only the standardized protocol HTTP is used by exploiting two JavaScript objects: (i) XMLHttpRequest for synchronous communication and (ii) EventSource for CO-to-Web application communication. The proposed platform implements the basic functionalities, inspired from OUPnP/UPNP, for remote monitoring and controlling of COs such as: (a) Discovering to allow COs advertising their presence to Web applications and Web applications to find available COs, (b) Description to know how controlling COs and their services, (c) Controlling to allow Web application invoking COs services, and finally (d) Eventing to allow CO sending notifications to the adequate Web applications. Moreover, this platform allows dynamic incorporation of pre-implemented control panel (fragment of Web page) on the Web application to control COs.","PeriodicalId":409079,"journal":{"name":"2020 IEEE International Conference on Internet of Things and Intelligence System (IoTaIS)","volume":"78 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-01-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123211369","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
Ultra-Low Power Wake-Up for Long-Term Biodiversity Monitorin 生物多样性长期监测的超低功耗唤醒
2020 IEEE International Conference on Internet of Things and Intelligence System (IoTaIS) Pub Date : 2021-01-27 DOI: 10.1109/IoTaIS50849.2021.9359710
Sebastián Marzetti, V. Gies, V. Barchasz, Paul Best, Sébastien Paris, H. Barthélemy, H. Glotin
{"title":"Ultra-Low Power Wake-Up for Long-Term Biodiversity Monitorin","authors":"Sebastián Marzetti, V. Gies, V. Barchasz, Paul Best, Sébastien Paris, H. Barthélemy, H. Glotin","doi":"10.1109/IoTaIS50849.2021.9359710","DOIUrl":"https://doi.org/10.1109/IoTaIS50849.2021.9359710","url":null,"abstract":"This paper presents a mixed analog-digital always-on ultra low-power wake-up based on pulse pattern analysis. It is used for triggering a high performance multi-channel recorder only when necessary. Its architecture makes the most of ultra-low power analog primitives coupled with an embedded digital low power system for fine tuning the pulse detector in order to maximise its efficiency. Such system allows long-term biodiversity study, as most of the bioacoustic energy is pulsed. We illustrate the efficiency of our system with a case study on Sperm Whale biosonar. The architecture and features extraction using analog primitives are first detailed, followed by embedded digital implementation of the automatic gain control for the pulse detector. Always-on current consumption of this intelligent wake-up is 12.5μA, with an area under the ROC curve equal to 75%. This allows an autonomy of 2 years on a single CR2032 battery cell. Finally perspectives towards biodiversity monitoring are discussed.","PeriodicalId":409079,"journal":{"name":"2020 IEEE International Conference on Internet of Things and Intelligence System (IoTaIS)","volume":"96 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-01-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133034702","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
IoTaIS 2021 Cover Page IoTaIS 2021封面页
2020 IEEE International Conference on Internet of Things and Intelligence System (IoTaIS) Pub Date : 2021-01-27 DOI: 10.1109/iotais50849.2021.9359723
{"title":"IoTaIS 2021 Cover Page","authors":"","doi":"10.1109/iotais50849.2021.9359723","DOIUrl":"https://doi.org/10.1109/iotais50849.2021.9359723","url":null,"abstract":"","PeriodicalId":409079,"journal":{"name":"2020 IEEE International Conference on Internet of Things and Intelligence System (IoTaIS)","volume":"487 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-01-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123060335","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
0
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
提示
您的信息不完整,为了账户安全,请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
确定
请完成安全验证×
相关产品
×
本文献相关产品
联系我们:info@booksci.cn Book学术提供免费学术资源搜索服务,方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。 Copyright © 2023 布克学术 All rights reserved.
京ICP备2023020795号-1
ghs 京公网安备 11010802042870号
Book学术文献互助
Book学术文献互助群
群 号:604180095
Book学术官方微信
小红书