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

Precision Tuning of an Accelerometer-Based Pedometer Algorithm for IoT Devices 物联网设备中基于加速度计的计步器算法的精确调谐

2020 IEEE International Conference on Internet of Things and Intelligence System (IoTaIS) Pub Date : 2021-01-27 DOI: 10.1109/IoTaIS50849.2021.9359700

Dorra Ben Khalifa, M. Martel

引用次数: 5

Medium Interaction Honeypot Infrastructure on The Internet of Things 物联网媒介交互蜜罐基础设施

2020 IEEE International Conference on Internet of Things and Intelligence System (IoTaIS) Pub Date : 2021-01-27 DOI: 10.1109/IoTaIS50849.2021.9359711

Elang Dwi Saputro, Yudha Purwanto, M. F. Ruriawan

引用次数: 3

Accessibility Support in Urban Space 城市空间的可达性支持

2020 IEEE International Conference on Internet of Things and Intelligence System (IoTaIS) Pub Date : 2021-01-27 DOI: 10.1109/IoTaIS50849.2021.9359691

J. Beingolea, Renato Huallpa, Xiomara Vilca, J. Borja, Jorge Rendulich

引用次数: 1

An AIoT System for Bat Species Classification 蝙蝠物种分类的AIoT系统

2020 IEEE International Conference on Internet of Things and Intelligence System (IoTaIS) Pub Date : 2021-01-27 DOI: 10.1109/IoTaIS50849.2021.9359704

I. Zualkernan, J. Judas, Taslim Mahbub, Azadan Bhagwagar, Priyanka Chand

{"title":"An AIoT System for Bat Species Classification","authors":"I. Zualkernan, J. Judas, Taslim Mahbub, Azadan Bhagwagar, Priyanka Chand","doi":"10.1109/IoTaIS50849.2021.9359704","DOIUrl":"https://doi.org/10.1109/IoTaIS50849.2021.9359704","url":null,"abstract":"Bat species are an integral part of our ecosystem and their monitoring can provide important insights into conservation and tracking viruses like Covid-19. Given the difficulty and high cost of manually monitoring bats in their natural habitats, this paper proposes an Artificially Intelligent Internet of Things (AIoT) system that uses audio-based Convolutional Neural Network (CNN) to monitor bat species using their echolocation calls. The system uses Long Range Wide Area Network (LoRaWAN) to send the classified species to an application server in real-time. The paper compared the performance of three different edge devices, Raspberry Pi Model (RPI) 3B+ (RPi), NVIDIA Jetson Nano, and Google Coral and two deep learning frameworks (TensorFlow Lite and TensorRT). Although all edge devices were able to do the real-time inference (< 0.5 seconds/inference for a 3-second audio segment), Google Coral appears to be the best choice because it was the fastest (0.3917 seconds/audio segment) and required the least resources (maximum %CPU Utilization = 29.2%). However, if cost was a concern then even the RPI was more than adequate for the task.","PeriodicalId":409079,"journal":{"name":"2020 IEEE International Conference on Internet of Things and Intelligence System (IoTaIS)","volume":"25 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":"129315511","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: 14

Optimized Face Detection and Alignment for Low-Cost and Low-Power IoT Systems 优化低成本低功耗物联网系统的人脸检测和对齐

2020 IEEE International Conference on Internet of Things and Intelligence System (IoTaIS) Pub Date : 2021-01-27 DOI: 10.1109/IoTaIS50849.2021.9359713

Kyubaik Choi, G. Sobelman

{"title":"Optimized Face Detection and Alignment for Low-Cost and Low-Power IoT Systems","authors":"Kyubaik Choi, G. Sobelman","doi":"10.1109/IoTaIS50849.2021.9359713","DOIUrl":"https://doi.org/10.1109/IoTaIS50849.2021.9359713","url":null,"abstract":"Face detection and alignment are challenging operations due to variations in image angles, background lighting conditions and intermediate blocking objects. Recent work has shown that these tasks can be improved through the use of a multi-task cascaded convolutional neural network (MTCNN) architecture. However, it is difficult to implement such an approach in a low-end edge AI system because of its high computational complexity. This paper presents the design of an MTCNN based on a low-cost and low-power processor/FPGA system that can be used in IoT applications. First, we analyze the computational requirements of the algorithm. Based on this analysis, we develop an optimized implementation to achieve real-time processing, taking advantage of the available hardware resources. In order to enhance the throughput and reduce the power consumption for AI edge devices, we store all intermediate results in on-chip block RAM. We achieve a frame rate of 15.2 frames per second, which meets the needs of security cameras that are widely used in IoT systems. Furthermore, our approach has a 2.67 times lower power consumption than for a previous MTCNN implementation.","PeriodicalId":409079,"journal":{"name":"2020 IEEE International Conference on Internet of Things and Intelligence System (IoTaIS)","volume":"159 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":"127435955","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

Designing Sigfox Network for Public Internet of Things in Batam Island 巴淡岛公共物联网Sigfox网络设计

2020 IEEE International Conference on Internet of Things and Intelligence System (IoTaIS) Pub Date : 2021-01-27 DOI: 10.1109/IoTaIS50849.2021.9359703

Shelasih Winalisa, M. I. Nashiruddin, M. A. Murti

{"title":"Designing Sigfox Network for Public Internet of Things in Batam Island","authors":"Shelasih Winalisa, M. I. Nashiruddin, M. A. Murti","doi":"10.1109/IoTaIS50849.2021.9359703","DOIUrl":"https://doi.org/10.1109/IoTaIS50849.2021.9359703","url":null,"abstract":"Sigfox Network is one of the most widely used IoT Connectivity technologies for the IoT market, especially for the Public IoT as integrated systems that operate in real-time, track devices, and manage the energy used to help social work. Sigfox uses unlicensed public frequencies, namely Industry frequency, Science, and Medical (ISM), and technology with global reach characteristics, cost-effectiveness, energy efficiency, and simplicity, which is scarce for scholars to explore the Sigfox network for multiple use cases as public IoT. Using Ultra-Narrow Band (UNB) with a total bandwidth of 192 kHz and 100 Hz messages per bandwidth, Sigfox operates globally. This research explored Sigfox network planning and simulation with Batam Island representatives as Urban areas. The method used network planning (coverage and capacity) analysis and simulation using Network Design Software Forsk Atoll 2.3.3. The results of the study stated that 15 gateways needed to cover the area. The simulation was done in two predictions, the coverage or prediction of the received signal level and the predicted Signal to Noise Ratio (SNR). The simulation result shows that almost sufficiently 100% of the area has an acceptable level above -134 dBm and produces an average best signal level of -86.55 dBm. The simulation also provides an average SNR level of 6.1 dB with the highest SNR value of 30 dB to 31 dB can cover an area of 7.81 sq. km.","PeriodicalId":409079,"journal":{"name":"2020 IEEE International Conference on Internet of Things and Intelligence System (IoTaIS)","volume":"15 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":"133274198","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

Phishing Web Page Detection Methods: URL and HTML Features Detection 网络钓鱼网页检测方法:URL和HTML特征检测

2020 IEEE International Conference on Internet of Things and Intelligence System (IoTaIS) Pub Date : 2021-01-27 DOI: 10.1109/IoTaIS50849.2021.9359694

Humam Faris, S. Yazid

引用次数: 6

Energy Management System with IoT Connectivity for Portable Solar Power Plant 便携式太阳能发电厂的物联网连接能源管理系统

2020 IEEE International Conference on Internet of Things and Intelligence System (IoTaIS) Pub Date : 2021-01-27 DOI: 10.1109/IoTaIS50849.2021.9359705

Dicky Dwi Putra, Budi Syihabuddin, Muhammad Alif Mi’raj Jabbar, Abdurrauf Irsal, A. Purwadi, A. Munir

引用次数: 2

Diagnosis and Prognosis of a Cartesian Robot’s Drive Belt Looseness 直角坐标机器人传动带松动的诊断与预测

2020 IEEE International Conference on Internet of Things and Intelligence System (IoTaIS) Pub Date : 2021-01-27 DOI: 10.1109/IoTaIS50849.2021.9359712

P. Pierleoni, Alberto Belli, Lorenzo Palma, Luisiana Sabbatini

引用次数: 4

Comparison of High Availability Performance on OpenDaylight with Corosync Pacemaker and OpenDaylight SDN Controller Platform Clustering OpenDaylight与Corosync起搏器和OpenDaylight SDN控制器平台集群的高可用性性能比较

2020 IEEE International Conference on Internet of Things and Intelligence System (IoTaIS) Pub Date : 2021-01-27 DOI: 10.1109/IoTaIS50849.2021.9359696

Nasikh Parhandhito, R. Negara, Favian Dewanta

{"title":"Comparison of High Availability Performance on OpenDaylight with Corosync Pacemaker and OpenDaylight SDN Controller Platform Clustering","authors":"Nasikh Parhandhito, R. Negara, Favian Dewanta","doi":"10.1109/IoTaIS50849.2021.9359696","DOIUrl":"https://doi.org/10.1109/IoTaIS50849.2021.9359696","url":null,"abstract":"Software Defined Network (SDN) can manage, design, and implement a data flow. Controllers from SDN in a network can control all data flow to make traffic more efficient, but it will be a severe problem if the controller is down. High availability can solve those problems. High Availability controllers divide into Primary and Secondary, and when the Primary Controller is off, the Secondary Controller will detect and replace the Primary Controller function. We can create a High Availability system in various ways. However, in this paper, the High Availability will use the Corosync Pacemaker method to compare it to the OpenDaylight SDN Controller Platform (OSCP) Clustering method. Corosync Pacemaker is a High Availability Proxy application that provides features on the controller that are ready to use and needs to be configured on a cluster system to be connected to the controller used from testing results and analysis. The conclusion is that high availability with the OSCP Clustering method is more stable when it occurs host and switch spikes than the Corosync Pacemaker method. OSCP Clustering is better to implement on a network because the required failover and failback times are relatively stable, and also the resulting QoS parameters have an excellent index.","PeriodicalId":409079,"journal":{"name":"2020 IEEE International Conference on Internet of Things and Intelligence System (IoTaIS)","volume":"33 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":"125868657","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