Pub Date : 2022-11-24DOI: 10.1109/IoTaIS56727.2022.9975861
Veena Chidurala, Xiaodong Wang, Xinrong Li, Jesse H. Hamner
The sensor systems are growing daily in terms of their complexity and getting more sophisticated from an application perspective. Smart cities and intelligent buildings are critical driving factors in designing and improving sensor systems. However, there is always a big concern about invading people’s privacy and finding the right balance between privacy and sensing accuracy. In our previous work, we demonstrated how thermal imaging sensors could estimate occupancy effectively in a non-intrusive way. This paper presents an efficient sensor system design of a non-intrusive occupancy monitoring system (OMS). It uses state-of-the-art open-source software elements such as the FastAPI web framework, Raspberry Pi, low-resolution IR thermal sensor, temperature, humidity, and motion sensors. We also present our data collection methods in detail and show valuable insights and experimental results to demonstrate that our OMS can accurately estimate the occupancy in a designated area or a room level to meet various demanding real-time occupancy monitoring applications.
{"title":"IoT based Sensor System Design for Real-Time Non-Intrusive Occupancy Monitoring","authors":"Veena Chidurala, Xiaodong Wang, Xinrong Li, Jesse H. Hamner","doi":"10.1109/IoTaIS56727.2022.9975861","DOIUrl":"https://doi.org/10.1109/IoTaIS56727.2022.9975861","url":null,"abstract":"The sensor systems are growing daily in terms of their complexity and getting more sophisticated from an application perspective. Smart cities and intelligent buildings are critical driving factors in designing and improving sensor systems. However, there is always a big concern about invading people’s privacy and finding the right balance between privacy and sensing accuracy. In our previous work, we demonstrated how thermal imaging sensors could estimate occupancy effectively in a non-intrusive way. This paper presents an efficient sensor system design of a non-intrusive occupancy monitoring system (OMS). It uses state-of-the-art open-source software elements such as the FastAPI web framework, Raspberry Pi, low-resolution IR thermal sensor, temperature, humidity, and motion sensors. We also present our data collection methods in detail and show valuable insights and experimental results to demonstrate that our OMS can accurately estimate the occupancy in a designated area or a room level to meet various demanding real-time occupancy monitoring applications.","PeriodicalId":138894,"journal":{"name":"2022 IEEE International Conference on Internet of Things and Intelligence Systems (IoTaIS)","volume":"30 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-11-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126791529","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}
Pub Date : 2022-11-24DOI: 10.1109/IoTaIS56727.2022.9975974
Ravi Shankar, Sasirekha Gvk, Chandrashekar Ramanathan, Jyotsna L. Bapat
The Industry 4.0 initiatives have triggered the concept of Digital Twin (DT). A DT is a virtual replica of any physical object like a machinery, an equipment or a manufacturing process, that accurately reflects the state of the object under observation. In an asset intensive industry like Oil and Gas (O&G), DT provides significant value addition. DT, being a digital representation in the cyber space of the Internet of Things (IoT) ecosystem, enables simulation, experimentation, and personnel training in a safe environment, without disrupting the actual physical process. In this paper, a knowledge based digital twin prototype for the O&G upstream, using generalized IoT stack & schema-based ontologies has been proposed and built. In comparison with the existing systems, the proposed prototype has the advantages of being open sourced, microservice based, context aware, and it supports ontology. The architecture and implementation details, along with the sample test results with real data, showing the working and efficacy of the system are presented. A use case of proactive site visit scheduling, resulting in operational improvement is detailed.
{"title":"Knowledge-based Digital Twin for Oil and Gas 4.0 Upstream Process: A System Prototype","authors":"Ravi Shankar, Sasirekha Gvk, Chandrashekar Ramanathan, Jyotsna L. Bapat","doi":"10.1109/IoTaIS56727.2022.9975974","DOIUrl":"https://doi.org/10.1109/IoTaIS56727.2022.9975974","url":null,"abstract":"The Industry 4.0 initiatives have triggered the concept of Digital Twin (DT). A DT is a virtual replica of any physical object like a machinery, an equipment or a manufacturing process, that accurately reflects the state of the object under observation. In an asset intensive industry like Oil and Gas (O&G), DT provides significant value addition. DT, being a digital representation in the cyber space of the Internet of Things (IoT) ecosystem, enables simulation, experimentation, and personnel training in a safe environment, without disrupting the actual physical process. In this paper, a knowledge based digital twin prototype for the O&G upstream, using generalized IoT stack & schema-based ontologies has been proposed and built. In comparison with the existing systems, the proposed prototype has the advantages of being open sourced, microservice based, context aware, and it supports ontology. The architecture and implementation details, along with the sample test results with real data, showing the working and efficacy of the system are presented. A use case of proactive site visit scheduling, resulting in operational improvement is detailed.","PeriodicalId":138894,"journal":{"name":"2022 IEEE International Conference on Internet of Things and Intelligence Systems (IoTaIS)","volume":"45 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-11-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126793045","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}
Pub Date : 2022-11-24DOI: 10.1109/IoTaIS56727.2022.9975947
Nabil El Hassainate, A. O. Said, Z. Guennoun
This paper reports the study and analysis of the link budget for uplink and downlink communication between the 3U university nano-satellite using Software-defined radio (SDR) and the ground IoT terminals. The aim of such study is to ensure that the playload of the 3U-CubeSat receives and processes correctly data sent by ground IoT terminals. The calculation of the link budget allows the determination of attenuation parameters such as atmospheric losses, free space path losses, antenna polarization losses. The analysis of the link budget enables finding the adequate elevation angle to ensure that the communication link and synchronization can be performed correctly. For this purpose, the link margin for three different elevation angles is calculated. It has been shown that 30° elevation angle is the optimal elevation for a favorable communication link between the 3U university nano-satellite and the ground IoT terminals.The original idea in this work is to provide a detailed overview of the architecture communication between 3U cubesat and ground IoT terminal and to analyze the link budget requirements to successfully establish this communication.
{"title":"Communication Link Budget Estimation between Ground IoT Terminal and Cubesat 3U ’s SDR","authors":"Nabil El Hassainate, A. O. Said, Z. Guennoun","doi":"10.1109/IoTaIS56727.2022.9975947","DOIUrl":"https://doi.org/10.1109/IoTaIS56727.2022.9975947","url":null,"abstract":"This paper reports the study and analysis of the link budget for uplink and downlink communication between the 3U university nano-satellite using Software-defined radio (SDR) and the ground IoT terminals. The aim of such study is to ensure that the playload of the 3U-CubeSat receives and processes correctly data sent by ground IoT terminals. The calculation of the link budget allows the determination of attenuation parameters such as atmospheric losses, free space path losses, antenna polarization losses. The analysis of the link budget enables finding the adequate elevation angle to ensure that the communication link and synchronization can be performed correctly. For this purpose, the link margin for three different elevation angles is calculated. It has been shown that 30° elevation angle is the optimal elevation for a favorable communication link between the 3U university nano-satellite and the ground IoT terminals.The original idea in this work is to provide a detailed overview of the architecture communication between 3U cubesat and ground IoT terminal and to analyze the link budget requirements to successfully establish this communication.","PeriodicalId":138894,"journal":{"name":"2022 IEEE International Conference on Internet of Things and Intelligence Systems (IoTaIS)","volume":"33 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-11-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130313221","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}
Pub Date : 2022-11-24DOI: 10.1109/IoTaIS56727.2022.9975992
Alberto Cruz, Maria Lorena Villena, Ivy Marisse Castro, John Paul Cervantes, Sofia Anne Ondra, Rahino Quijano, John Elbert Veneracion, Melchizedek I. Alipio
Technological advancements in medical field gave birth to smart watches, handheld devices that can read your vital signs real-time. However, home quarantined COVID-19 patients, even with the help of smartwatches, are still needed to be monitored physically by health practitioners, therefore posing a threat of transmission of the virus. This paved the way to the investigation of designing a wearable device that read health vital statistics and the location of home quarantined patients and a system that will remotely monitor it. Thus, this work developed Vitaband, a health-monitoring system made up of a node, gateway, and a web application. The node consists of sensors – pulse meter, oximeter, IR sensor and GPS module – that will read the vital signs of the patient and display it through an OLED screen. Two Raspberry Pico Pi microcontrollers will process the data gathered by these sensors and send them to the gateway through the Lora module. The gateway then, housing the ESP32 microcontroller, will connect to the internet and transmit the received data to the MongoDB database. The web application finally, which is programmed using REACT framework, shall display the data for remote monitoring. Vitaband is tested and evaluated using the ISO/IEC 25010 model. Results revealed that Vitaband received an overall rating of Very Satisfactory from the Bulacan State University Nursing student during their training as the respondents and Excellent from medical professionals which are registered nurses and barangay health workers, respectively.
{"title":"Vitaband: IoT-Driven Health Monitoring System for Home Quarantine COVID-19 Patient Using LoRaWAN","authors":"Alberto Cruz, Maria Lorena Villena, Ivy Marisse Castro, John Paul Cervantes, Sofia Anne Ondra, Rahino Quijano, John Elbert Veneracion, Melchizedek I. Alipio","doi":"10.1109/IoTaIS56727.2022.9975992","DOIUrl":"https://doi.org/10.1109/IoTaIS56727.2022.9975992","url":null,"abstract":"Technological advancements in medical field gave birth to smart watches, handheld devices that can read your vital signs real-time. However, home quarantined COVID-19 patients, even with the help of smartwatches, are still needed to be monitored physically by health practitioners, therefore posing a threat of transmission of the virus. This paved the way to the investigation of designing a wearable device that read health vital statistics and the location of home quarantined patients and a system that will remotely monitor it. Thus, this work developed Vitaband, a health-monitoring system made up of a node, gateway, and a web application. The node consists of sensors – pulse meter, oximeter, IR sensor and GPS module – that will read the vital signs of the patient and display it through an OLED screen. Two Raspberry Pico Pi microcontrollers will process the data gathered by these sensors and send them to the gateway through the Lora module. The gateway then, housing the ESP32 microcontroller, will connect to the internet and transmit the received data to the MongoDB database. The web application finally, which is programmed using REACT framework, shall display the data for remote monitoring. Vitaband is tested and evaluated using the ISO/IEC 25010 model. Results revealed that Vitaband received an overall rating of Very Satisfactory from the Bulacan State University Nursing student during their training as the respondents and Excellent from medical professionals which are registered nurses and barangay health workers, respectively.","PeriodicalId":138894,"journal":{"name":"2022 IEEE International Conference on Internet of Things and Intelligence Systems (IoTaIS)","volume":"36 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-11-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129774229","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}
Pub Date : 2022-11-24DOI: 10.1109/IoTaIS56727.2022.9975909
K. Padmanabh, Ahmad Al-Rubaie, A. Aljasmi
Due to ageing or adverse environment, the sensors of an HVAC system deteriorate progressively and fail to produce the desired output after sometime. Each HVAC system has hundreds of sensors. This paper proposes a generic framework to predict the failures of these sensors in advance. A novel technique has been used to transform the problem domain from prediction to detection where conventional algorithms were used to build classifiers. A number of common features were derived out of the sensor values. These features were subsequently used to define a function to deduce in real time the health of a sensor. A dashboard displays the deterioration of the health of the sensor over the time. Data from hundreds of sensors of more than 60 HVAC systems with hundreds of sensors each were used to build machine learning models. The solution has been deployed to detect failure of these sensors and it was found that this framework was able to model 74% of all sensor faults at least 10 hours in advance. The accuracy of fault prediction has been more than 96%, precision has been more than 74% and recall has been 95%.
{"title":"Health Estimation and Fault Prediction of the Sensors of a HVAC System","authors":"K. Padmanabh, Ahmad Al-Rubaie, A. Aljasmi","doi":"10.1109/IoTaIS56727.2022.9975909","DOIUrl":"https://doi.org/10.1109/IoTaIS56727.2022.9975909","url":null,"abstract":"Due to ageing or adverse environment, the sensors of an HVAC system deteriorate progressively and fail to produce the desired output after sometime. Each HVAC system has hundreds of sensors. This paper proposes a generic framework to predict the failures of these sensors in advance. A novel technique has been used to transform the problem domain from prediction to detection where conventional algorithms were used to build classifiers. A number of common features were derived out of the sensor values. These features were subsequently used to define a function to deduce in real time the health of a sensor. A dashboard displays the deterioration of the health of the sensor over the time. Data from hundreds of sensors of more than 60 HVAC systems with hundreds of sensors each were used to build machine learning models. The solution has been deployed to detect failure of these sensors and it was found that this framework was able to model 74% of all sensor faults at least 10 hours in advance. The accuracy of fault prediction has been more than 96%, precision has been more than 74% and recall has been 95%.","PeriodicalId":138894,"journal":{"name":"2022 IEEE International Conference on Internet of Things and Intelligence Systems (IoTaIS)","volume":"84 16","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-11-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131878826","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}
Pub Date : 2022-11-24DOI: 10.1109/IoTaIS56727.2022.9976010
J. Jason, Anderies, Kay Leonico, Javier Islamey, Irene Anindaputri Iswanto
Object detection is a machine learning task that can detect objects in an image or video. With the rising demand for object detection features, a solution is needed to make it more accessible. This can be solved by integrating an object detection model into Flutter, a framework that can be compiled and used on popular platforms like iOS and Android. We investigated a total of 13 pre-trained models from PyTorch that will be integrated into Flutter. Through our investigation, we found that the YOLOv5 variants provided the best balance between accuracy and speed while boasting a significantly higher accuracy-to-speed ratio compared to the rest. We also found that quantizing the models can reduce their file size and execution time by up to 55% and 26% respectively while retaining comparable accuracies. However, we were not able to integrate them into flutter due to issues that we encountered.
{"title":"Investigating The Best Pre-Trained Object Detection Model for Flutter Framework","authors":"J. Jason, Anderies, Kay Leonico, Javier Islamey, Irene Anindaputri Iswanto","doi":"10.1109/IoTaIS56727.2022.9976010","DOIUrl":"https://doi.org/10.1109/IoTaIS56727.2022.9976010","url":null,"abstract":"Object detection is a machine learning task that can detect objects in an image or video. With the rising demand for object detection features, a solution is needed to make it more accessible. This can be solved by integrating an object detection model into Flutter, a framework that can be compiled and used on popular platforms like iOS and Android. We investigated a total of 13 pre-trained models from PyTorch that will be integrated into Flutter. Through our investigation, we found that the YOLOv5 variants provided the best balance between accuracy and speed while boasting a significantly higher accuracy-to-speed ratio compared to the rest. We also found that quantizing the models can reduce their file size and execution time by up to 55% and 26% respectively while retaining comparable accuracies. However, we were not able to integrate them into flutter due to issues that we encountered.","PeriodicalId":138894,"journal":{"name":"2022 IEEE International Conference on Internet of Things and Intelligence Systems (IoTaIS)","volume":"11 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-11-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134394985","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}
Pub Date : 2022-11-24DOI: 10.1109/IoTaIS56727.2022.9975959
Dana Terrazas-Rodas, Joanna Carrión-Pérez
Currently, disability is a condition in which people are considered to have long-term physical, mental, intellectual, or sensory impairments due to different circumstances or situations, which may be due to an accident, illness, among others. According to the United Nations (UN), approximately 10% of people (650 million approximately) are registered with some type of disability, which is increasing due to population growth worldwide, medical advances and the aging process. Upper limb prostheses are devices that replace parts of the body of a person or user with upper limb disability or amputation, such as the arm, hand, among others. In this review, various Artificial Intelligence (AI) techniques were examined for their applications such as pattern recognition and classification of biosignals in a total of 72 upper limb prostheses in different categories such as the commercial name or main author’s name of the device, the characteristics of the patient-user who will use it, the level of amputation, the mechanism which is the body part that replaces the bionic hand, the control biosignals that activate the operation of the prosthesis, the Artificial Intelligence (AI) methods that have been employed, the applications of AI techniques and the Technology Readiness Level (TRL), which is the level of development of the upper limb prosthesis between the lowest level (1) and the highest level (9).
{"title":"Artificial Intelligence Techniques for Biosignal Pattern Recognition and Classification in Upper-Limb Prostheses: A Review","authors":"Dana Terrazas-Rodas, Joanna Carrión-Pérez","doi":"10.1109/IoTaIS56727.2022.9975959","DOIUrl":"https://doi.org/10.1109/IoTaIS56727.2022.9975959","url":null,"abstract":"Currently, disability is a condition in which people are considered to have long-term physical, mental, intellectual, or sensory impairments due to different circumstances or situations, which may be due to an accident, illness, among others. According to the United Nations (UN), approximately 10% of people (650 million approximately) are registered with some type of disability, which is increasing due to population growth worldwide, medical advances and the aging process. Upper limb prostheses are devices that replace parts of the body of a person or user with upper limb disability or amputation, such as the arm, hand, among others. In this review, various Artificial Intelligence (AI) techniques were examined for their applications such as pattern recognition and classification of biosignals in a total of 72 upper limb prostheses in different categories such as the commercial name or main author’s name of the device, the characteristics of the patient-user who will use it, the level of amputation, the mechanism which is the body part that replaces the bionic hand, the control biosignals that activate the operation of the prosthesis, the Artificial Intelligence (AI) methods that have been employed, the applications of AI techniques and the Technology Readiness Level (TRL), which is the level of development of the upper limb prosthesis between the lowest level (1) and the highest level (9).","PeriodicalId":138894,"journal":{"name":"2022 IEEE International Conference on Internet of Things and Intelligence Systems (IoTaIS)","volume":"24 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-11-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127198374","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}
Pub Date : 2022-11-24DOI: 10.1109/IoTaIS56727.2022.9975982
Adnan Nadeem, David Chatzichristodoulou, Abdul Quddious, N. Shoaib, L. Vassiliou, P. Vryonides, S. Nikolaou
This manuscript presents a novel UHF IoT humidity and temperature sensor module that is powered from an integrated energy harvesting (EH) system. The module is intended for smart agriculture applications. The sensing module is powered from the collected RF energy that is harvested by a meander monopole antenna operating at 915 MHz (US UHF band) and therefore the use of a battery is not required. The rectifying voltage doubler converts the received RF energy into DC while the Power Management Unit (PMU) boosts-up and stores the rectified voltage providing a regulated output voltage of 1.8V to the RFID tag IC (ROCKY100) and 3.3V to the microcontroller unit (MCU) and the humidity and temperature sensor IC. The communication RFID antenna uses the European UHF frequency band centered at 868 MHz. When the RFID tag IC is supplied with 1.8 V from the PMU it operates in semi-passive mode and it effectively increases its communication range. The ROCKY100 is EPC C1G2 compliant and is compatible with power harvesting modules and SPI communication to support external low-power sensors and actuators. In addition, a capacitive digital humidity and temperature sensor (HTS221) is used as the sensing module for soil measurements. The process of measuring the relative humidity and temperature of the soil is controlled with a Texas Instrument mixed signal microcontroller that possesses two SPI interfaces that allows it to communicate with the RFID IC and the sensor in parallel. Upon receiving a SPI directed read request from the RFID reader, the ROCKY100 SPI bridge requests the value of the last measurement from the microcontroller and the humidity and temperature measurements taken by the HTS221 IC are sent to the RFID reader. The use of harvested wireless energy as a power source makes the demonstrated module a potentially batteryless and thus a “Green” sensor.
{"title":"UHF IoT Humidity and Temperature Sensor for Smart Agriculture Applications Powered from an Energy Harvesting System","authors":"Adnan Nadeem, David Chatzichristodoulou, Abdul Quddious, N. Shoaib, L. Vassiliou, P. Vryonides, S. Nikolaou","doi":"10.1109/IoTaIS56727.2022.9975982","DOIUrl":"https://doi.org/10.1109/IoTaIS56727.2022.9975982","url":null,"abstract":"This manuscript presents a novel UHF IoT humidity and temperature sensor module that is powered from an integrated energy harvesting (EH) system. The module is intended for smart agriculture applications. The sensing module is powered from the collected RF energy that is harvested by a meander monopole antenna operating at 915 MHz (US UHF band) and therefore the use of a battery is not required. The rectifying voltage doubler converts the received RF energy into DC while the Power Management Unit (PMU) boosts-up and stores the rectified voltage providing a regulated output voltage of 1.8V to the RFID tag IC (ROCKY100) and 3.3V to the microcontroller unit (MCU) and the humidity and temperature sensor IC. The communication RFID antenna uses the European UHF frequency band centered at 868 MHz. When the RFID tag IC is supplied with 1.8 V from the PMU it operates in semi-passive mode and it effectively increases its communication range. The ROCKY100 is EPC C1G2 compliant and is compatible with power harvesting modules and SPI communication to support external low-power sensors and actuators. In addition, a capacitive digital humidity and temperature sensor (HTS221) is used as the sensing module for soil measurements. The process of measuring the relative humidity and temperature of the soil is controlled with a Texas Instrument mixed signal microcontroller that possesses two SPI interfaces that allows it to communicate with the RFID IC and the sensor in parallel. Upon receiving a SPI directed read request from the RFID reader, the ROCKY100 SPI bridge requests the value of the last measurement from the microcontroller and the humidity and temperature measurements taken by the HTS221 IC are sent to the RFID reader. The use of harvested wireless energy as a power source makes the demonstrated module a potentially batteryless and thus a “Green” sensor.","PeriodicalId":138894,"journal":{"name":"2022 IEEE International Conference on Internet of Things and Intelligence Systems (IoTaIS)","volume":"26 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-11-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125867949","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}
Pub Date : 2022-11-24DOI: 10.1109/IoTaIS56727.2022.9976020
Resy Indira Indah Purnama, Levy Olivia Nur, R. Anwar
Wireless Body Area Network (WBAN) is a wireless communication network designed to monitor the condition of the human body. This monitoring is very important to ensure that the body stay healthy when carrying out daily activities. Antenna is one of the important devices in WBAN communication. This paper focuses on design and realization a textile antenna with patch in the form of Telkom University logo which operates at 2.4 GHz frequency of the ISM (Industrial, Scientific, and Medical) band. This antenna uses trunk cut method on the feed line to widen bandwidth. The result has dimensions (101.49 $times 110.10 times $ 7.6) mm with 1.265 GHz bandwidth when free space and 1.306 GHz bandwidth when on-body. The measurement results obtained 1.16 VSWR when free space and 1.35 VSWR when on-body at 2.428 GHz frequency. The simulation results obtained 7.26 dBi gain when free space and 7.34 dBi when on-body, unidirectional radiation pattern, and SAR 0.715 W/kg.
{"title":"Textile Antenna With Telkom University Logo Patch For WBAN Communication At 2.4 GHz Frequency","authors":"Resy Indira Indah Purnama, Levy Olivia Nur, R. Anwar","doi":"10.1109/IoTaIS56727.2022.9976020","DOIUrl":"https://doi.org/10.1109/IoTaIS56727.2022.9976020","url":null,"abstract":"Wireless Body Area Network (WBAN) is a wireless communication network designed to monitor the condition of the human body. This monitoring is very important to ensure that the body stay healthy when carrying out daily activities. Antenna is one of the important devices in WBAN communication. This paper focuses on design and realization a textile antenna with patch in the form of Telkom University logo which operates at 2.4 GHz frequency of the ISM (Industrial, Scientific, and Medical) band. This antenna uses trunk cut method on the feed line to widen bandwidth. The result has dimensions (101.49 $times 110.10 times $ 7.6) mm with 1.265 GHz bandwidth when free space and 1.306 GHz bandwidth when on-body. The measurement results obtained 1.16 VSWR when free space and 1.35 VSWR when on-body at 2.428 GHz frequency. The simulation results obtained 7.26 dBi gain when free space and 7.34 dBi when on-body, unidirectional radiation pattern, and SAR 0.715 W/kg.","PeriodicalId":138894,"journal":{"name":"2022 IEEE International Conference on Internet of Things and Intelligence Systems (IoTaIS)","volume":"62 3-4","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-11-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132031542","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}
Pub Date : 2022-11-24DOI: 10.1109/IoTaIS56727.2022.9975908
Yash Gupta, Z. Fadlullah, M. Fouda
Recently, Internet of Things (IoT) systems in the network edge with embedded intelligence emerged as a trending research topic. Edge computing offers a significant advantage over the traditional form of sharing personal data with a centralized entity since the latter paradigm may affect the user’s privacy, e.g., due to explicit exchange of sensitive biomedical data. To address this inherent data privacy issue, in this paper, we focus on designing an asynchronously weight updating federated learning algorithm toward the much anticipated AI-on-Edge IoT systems. Among numerous use-cases, we consider the face mask detection problem, which is traditionally considered as a centralized computer vision task. We take a different approach to distribute the learning tasks to the users in a federated learning framework, and then investigate the performance trade-off between synchronous and asynchronously weight updating methods. In our proposed system, the models are penalized by their performance metrics to limit a model’s participation in the aggregation stage. By developing the asynchronously weight updating method for deep learning (e.g., Convolutional Neural Network (CNN)) models, we also investigate its impact on model parameters exchange with the centralized aggregator. Experimental results demonstrate that our proposed asynchronously weight updating method achieves results comparable to those attained with the centralized training and the synchronously weight updating strategy. Also, we provide numerical analysis to demonstrate a significant transmission time overhead with our proposal.
{"title":"Toward Asynchronously Weight Updating Federated Learning for AI-on-Edge IoT Systems","authors":"Yash Gupta, Z. Fadlullah, M. Fouda","doi":"10.1109/IoTaIS56727.2022.9975908","DOIUrl":"https://doi.org/10.1109/IoTaIS56727.2022.9975908","url":null,"abstract":"Recently, Internet of Things (IoT) systems in the network edge with embedded intelligence emerged as a trending research topic. Edge computing offers a significant advantage over the traditional form of sharing personal data with a centralized entity since the latter paradigm may affect the user’s privacy, e.g., due to explicit exchange of sensitive biomedical data. To address this inherent data privacy issue, in this paper, we focus on designing an asynchronously weight updating federated learning algorithm toward the much anticipated AI-on-Edge IoT systems. Among numerous use-cases, we consider the face mask detection problem, which is traditionally considered as a centralized computer vision task. We take a different approach to distribute the learning tasks to the users in a federated learning framework, and then investigate the performance trade-off between synchronous and asynchronously weight updating methods. In our proposed system, the models are penalized by their performance metrics to limit a model’s participation in the aggregation stage. By developing the asynchronously weight updating method for deep learning (e.g., Convolutional Neural Network (CNN)) models, we also investigate its impact on model parameters exchange with the centralized aggregator. Experimental results demonstrate that our proposed asynchronously weight updating method achieves results comparable to those attained with the centralized training and the synchronously weight updating strategy. Also, we provide numerical analysis to demonstrate a significant transmission time overhead with our proposal.","PeriodicalId":138894,"journal":{"name":"2022 IEEE International Conference on Internet of Things and Intelligence Systems (IoTaIS)","volume":"66 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-11-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130302643","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}
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：