Pub Date : 2021-11-06DOI: 10.1109/ICSET53708.2021.9612437
Fatria Jumara Adha, Rusyaizila Ramli, M. H. Alkawaz, M. Johar, Asif Iqbal Hajamydeen
The poultry industry can produce large revenue and plays a huge impact on the country's economy. Day-by-day technology continues to innovate. the industrial 4.0 is a reduced application in the field of farming and managed to automated systems. Every year, it is estimated that poultry production and consumption will rise. This hypothesis can be seen in terms of increasing chicken consumption in the developing country by 3.6 percent. Chickens are very sensitive to temperature, humidity, and ammonia in the chicken coop. Therefore, this paper studies how to build a chicken coop monitoring system with the existing methods from the previous paper. This paper highlighted the method of smart poultry farm monitoring systems with their types such as IoT, wireless sensor, and GPRS. These types have been designed based on their technique. Finally, the previous techniques for smart poultry farm systems have been discussed such as advantages and disadvantages in this paper.
{"title":"Assessment of Conceptual Framework for Monitoring Poultry Farm's Temperature and Humidity","authors":"Fatria Jumara Adha, Rusyaizila Ramli, M. H. Alkawaz, M. Johar, Asif Iqbal Hajamydeen","doi":"10.1109/ICSET53708.2021.9612437","DOIUrl":"https://doi.org/10.1109/ICSET53708.2021.9612437","url":null,"abstract":"The poultry industry can produce large revenue and plays a huge impact on the country's economy. Day-by-day technology continues to innovate. the industrial 4.0 is a reduced application in the field of farming and managed to automated systems. Every year, it is estimated that poultry production and consumption will rise. This hypothesis can be seen in terms of increasing chicken consumption in the developing country by 3.6 percent. Chickens are very sensitive to temperature, humidity, and ammonia in the chicken coop. Therefore, this paper studies how to build a chicken coop monitoring system with the existing methods from the previous paper. This paper highlighted the method of smart poultry farm monitoring systems with their types such as IoT, wireless sensor, and GPRS. These types have been designed based on their technique. Finally, the previous techniques for smart poultry farm systems have been discussed such as advantages and disadvantages in this paper.","PeriodicalId":433197,"journal":{"name":"2021 IEEE 11th International Conference on System Engineering and Technology (ICSET)","volume":"44 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-11-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132145858","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 : 2021-11-06DOI: 10.1109/ICSET53708.2021.9612579
Kaiser Habib, Elson Ee Teng Kai, M. Saad, A. Hussain, A. Ayob, A. Ahmad
The advancement of the Internet of Things (IoT) fortifies intelligent system development for diverse information management in various domains. Information produced from Science, Technology, Engineering, and Mathematics (STEM) fields across the diverse networks, also can be successfully integrated to analyze virtually with the help of IoT. Thus, learning relative IoT technology has to be carried out to achieve the initiative's agenda. However, the current Teaching and Learning (T&L) systems are lacking in smart learning toolkit to equip the students with IoT-based STEM knowledge and skillsets relative to the IoT. The purpose of this study is to develop a smart toolkit in association with a T&L module to expose STEM knowledge to the students. The developed toolkit comprises an Input/output (I/O) test board to carry out both analog and digital data acquisition. Raspberry Pi is the heart of this toolkit that processes and transfers the acquired data to a cloud platform named ThingsSentral™ to structurally store, analyze and represent data graphically. Besides, a T&L module was designed based on this developed toolkit functionalities to expose STEM discipline to the younger generation. Based on the performance observations, the proposed system offers a cost-effective cloud-facilitated solution for the Project-Based Learning (PBL) approach, also exhibits salient suitability to effectively introduce IoT-based STEM knowledge to the students, non-technical personnel, even domain experts at the shortest possible time.
{"title":"Internet of Things (IoT) Enhanced Educational Toolkit for Teaching & Learning of Science, Technology, Engineering and Mathematics (STEM)","authors":"Kaiser Habib, Elson Ee Teng Kai, M. Saad, A. Hussain, A. Ayob, A. Ahmad","doi":"10.1109/ICSET53708.2021.9612579","DOIUrl":"https://doi.org/10.1109/ICSET53708.2021.9612579","url":null,"abstract":"The advancement of the Internet of Things (IoT) fortifies intelligent system development for diverse information management in various domains. Information produced from Science, Technology, Engineering, and Mathematics (STEM) fields across the diverse networks, also can be successfully integrated to analyze virtually with the help of IoT. Thus, learning relative IoT technology has to be carried out to achieve the initiative's agenda. However, the current Teaching and Learning (T&L) systems are lacking in smart learning toolkit to equip the students with IoT-based STEM knowledge and skillsets relative to the IoT. The purpose of this study is to develop a smart toolkit in association with a T&L module to expose STEM knowledge to the students. The developed toolkit comprises an Input/output (I/O) test board to carry out both analog and digital data acquisition. Raspberry Pi is the heart of this toolkit that processes and transfers the acquired data to a cloud platform named ThingsSentral™ to structurally store, analyze and represent data graphically. Besides, a T&L module was designed based on this developed toolkit functionalities to expose STEM discipline to the younger generation. Based on the performance observations, the proposed system offers a cost-effective cloud-facilitated solution for the Project-Based Learning (PBL) approach, also exhibits salient suitability to effectively introduce IoT-based STEM knowledge to the students, non-technical personnel, even domain experts at the shortest possible time.","PeriodicalId":433197,"journal":{"name":"2021 IEEE 11th International Conference on System Engineering and Technology (ICSET)","volume":"4 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-11-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127621811","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 : 2021-11-06DOI: 10.1109/ICSET53708.2021.9612554
Azrai Danial Azhari, N. Sulaiman, M. Kassim
Internet of Things (IoT) communication provides connections of more objects and services to the Internet which involves a Secured Internet Office Network environment. Internet office is an important environment where issues on security have been regularly discussed which impact education, communication, business, government, and others. Recent small internet office network has implemented VLAN, DHCP, Cisco ASA Firewall, wireless access point and registration Server but IoT is enhanced from time to time. This paper presents the implementation of simulation of IoT onto a secured small office network by using the Cisco Packet Tracer a network simulator software. A simulation of Internet office network with IoT systems services on motion detection system, door lock system and smoke detection system were developed. Due to security concerns, several security protocols have been integrated such as SSL VPN, ASA Firewall security level and WPA2-PSK authentication. The result has successfully shown the data for smoke level over time taken and the door lock system's scenarios based on the RFID setup. The implementation of the IoT, network design and configuration and integration of the security protocols have been successfully implemented using the Cisco Packet Tracer.
{"title":"Secured Internet Office Network with the Internet of Things Using Packet Tracer Analysis","authors":"Azrai Danial Azhari, N. Sulaiman, M. Kassim","doi":"10.1109/ICSET53708.2021.9612554","DOIUrl":"https://doi.org/10.1109/ICSET53708.2021.9612554","url":null,"abstract":"Internet of Things (IoT) communication provides connections of more objects and services to the Internet which involves a Secured Internet Office Network environment. Internet office is an important environment where issues on security have been regularly discussed which impact education, communication, business, government, and others. Recent small internet office network has implemented VLAN, DHCP, Cisco ASA Firewall, wireless access point and registration Server but IoT is enhanced from time to time. This paper presents the implementation of simulation of IoT onto a secured small office network by using the Cisco Packet Tracer a network simulator software. A simulation of Internet office network with IoT systems services on motion detection system, door lock system and smoke detection system were developed. Due to security concerns, several security protocols have been integrated such as SSL VPN, ASA Firewall security level and WPA2-PSK authentication. The result has successfully shown the data for smoke level over time taken and the door lock system's scenarios based on the RFID setup. The implementation of the IoT, network design and configuration and integration of the security protocols have been successfully implemented using the Cisco Packet Tracer.","PeriodicalId":433197,"journal":{"name":"2021 IEEE 11th International Conference on System Engineering and Technology (ICSET)","volume":"35 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-11-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125373347","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 : 2021-11-06DOI: 10.1109/ICSET53708.2021.9612569
I. T. Ahmed, B. T. Hammad, N. Jamil
In the last few years, Digital image forgery (DIF) detection has become a prominent subject. Image splicing is a frequent approach for making digital image forgeries. Image splicing creates forged images that are hard to detect immediately. The detection accuracy of most existing image splicing detection algorithms is low, thus there is room for improvement. Therefore, this research provides an image splicing detection (ISD) method based on deep learning. The proposed image splicing detection has three stages: (1) RGB image conversion and image size fitting are examples of image pre-processing. (2) Using the pre-trained CNN AlexNet model, we extract the final discriminative feature for a preprocessed image. (3) Finally, the generated feature representation is used to train a Canonical Correlation Analysis (CCA) classifier for binary classification (authentic/forged). The accuracy of the proposed approach using a pre-trained AlexNet model based deep features with CCA classifier is equal to 98.79 % when evaluated on the CASIA v1.0 splicing image forgery database. In comparison, the proposed surpassed existing methods. In the future, the proposed could be applied to other types of image forgery, such as image retouching.
{"title":"Effective Deep Features for Image Splicing Detection","authors":"I. T. Ahmed, B. T. Hammad, N. Jamil","doi":"10.1109/ICSET53708.2021.9612569","DOIUrl":"https://doi.org/10.1109/ICSET53708.2021.9612569","url":null,"abstract":"In the last few years, Digital image forgery (DIF) detection has become a prominent subject. Image splicing is a frequent approach for making digital image forgeries. Image splicing creates forged images that are hard to detect immediately. The detection accuracy of most existing image splicing detection algorithms is low, thus there is room for improvement. Therefore, this research provides an image splicing detection (ISD) method based on deep learning. The proposed image splicing detection has three stages: (1) RGB image conversion and image size fitting are examples of image pre-processing. (2) Using the pre-trained CNN AlexNet model, we extract the final discriminative feature for a preprocessed image. (3) Finally, the generated feature representation is used to train a Canonical Correlation Analysis (CCA) classifier for binary classification (authentic/forged). The accuracy of the proposed approach using a pre-trained AlexNet model based deep features with CCA classifier is equal to 98.79 % when evaluated on the CASIA v1.0 splicing image forgery database. In comparison, the proposed surpassed existing methods. In the future, the proposed could be applied to other types of image forgery, such as image retouching.","PeriodicalId":433197,"journal":{"name":"2021 IEEE 11th International Conference on System Engineering and Technology (ICSET)","volume":"63 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-11-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126430880","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 : 2021-11-06DOI: 10.1109/ICSET53708.2021.9612564
C. Yahaya, Muhammad Hilal Hidayatullah Rosly, M. H. M. Hamzah, M. Kassim
This paper presents the development of the Internet of Things (IoT) System on Waterfall Water Level Monitoring for Warning Phenomena. It aims to prevent injured visitors at a waterfall which warning will be alerted on the increased water level at the waterfall. The incident happened at the waterfall during high water level occur suddenly, where visitors are unknown in the situations. The design system is based on IoT System for Waterfall Water Level Monitoring where water level sensors are used to detect high-level water. The ultrasonic sensor was used in this system where the minimum time delay of the sensor was detected compared with other sensors. The Arduino microcontroller board was used as an interface from a sensor as input and output for data collections. A DC motor was used as a generator to supply voltage. The result of the developed system was analyzed based on time delay and efficiency of water level. The analysis presents the motor rotations increased when the water speed has increased. The supply voltage also increased when the motor rpm is increased. This research is significant as an alert system to most tourists and visitors to the most beautiful waterfall in Malaysia. The alert system is one advantage to reduce death cases that happened at the waterfall which usually happen after rain in the surrounding waterfall. This helps the tourism sectors in developing more visitors to the waterfall places and keep visitors safe with the help of the recent technology can reduce bad incidence.
{"title":"Automated Waterfall Water Level Monitoring for Warning Phenomena","authors":"C. Yahaya, Muhammad Hilal Hidayatullah Rosly, M. H. M. Hamzah, M. Kassim","doi":"10.1109/ICSET53708.2021.9612564","DOIUrl":"https://doi.org/10.1109/ICSET53708.2021.9612564","url":null,"abstract":"This paper presents the development of the Internet of Things (IoT) System on Waterfall Water Level Monitoring for Warning Phenomena. It aims to prevent injured visitors at a waterfall which warning will be alerted on the increased water level at the waterfall. The incident happened at the waterfall during high water level occur suddenly, where visitors are unknown in the situations. The design system is based on IoT System for Waterfall Water Level Monitoring where water level sensors are used to detect high-level water. The ultrasonic sensor was used in this system where the minimum time delay of the sensor was detected compared with other sensors. The Arduino microcontroller board was used as an interface from a sensor as input and output for data collections. A DC motor was used as a generator to supply voltage. The result of the developed system was analyzed based on time delay and efficiency of water level. The analysis presents the motor rotations increased when the water speed has increased. The supply voltage also increased when the motor rpm is increased. This research is significant as an alert system to most tourists and visitors to the most beautiful waterfall in Malaysia. The alert system is one advantage to reduce death cases that happened at the waterfall which usually happen after rain in the surrounding waterfall. This helps the tourism sectors in developing more visitors to the waterfall places and keep visitors safe with the help of the recent technology can reduce bad incidence.","PeriodicalId":433197,"journal":{"name":"2021 IEEE 11th International Conference on System Engineering and Technology (ICSET)","volume":"23 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-11-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123057163","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 : 2021-11-06DOI: 10.1109/ICSET53708.2021.9612542
Jing Zhi Ooi, Chye Cheah Tan
The increase in use cases of last mile delivery is a by-product from the increase in efficiency of globalized goods transportation, to the point that it is applicable for non-commercial endpoints, e.g., personal accommodation. With the surge in use cases, there is an amplified cost in financial and time resources from both logistic companies and the recipients as the amount of endpoints rise. This paper details the development of a proposed system aimed to alleviate the effect by offering concentrated stopping locations to accommodate for different logistic companies to deposit multiple parcels into while the recipients collect them as needed through the implementation of contactless deposit and withdrawal, as well as a modular style of locker unit deployment in a scalable manner.
{"title":"Smart Modular Parcel Locker System using Internet of Things (IoT)","authors":"Jing Zhi Ooi, Chye Cheah Tan","doi":"10.1109/ICSET53708.2021.9612542","DOIUrl":"https://doi.org/10.1109/ICSET53708.2021.9612542","url":null,"abstract":"The increase in use cases of last mile delivery is a by-product from the increase in efficiency of globalized goods transportation, to the point that it is applicable for non-commercial endpoints, e.g., personal accommodation. With the surge in use cases, there is an amplified cost in financial and time resources from both logistic companies and the recipients as the amount of endpoints rise. This paper details the development of a proposed system aimed to alleviate the effect by offering concentrated stopping locations to accommodate for different logistic companies to deposit multiple parcels into while the recipients collect them as needed through the implementation of contactless deposit and withdrawal, as well as a modular style of locker unit deployment in a scalable manner.","PeriodicalId":433197,"journal":{"name":"2021 IEEE 11th International Conference on System Engineering and Technology (ICSET)","volume":"18 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-11-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116542358","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 : 2021-11-06DOI: 10.1109/ICSET53708.2021.9612432
H. Basiron, Muhammad Azri Azmi, Mohd Juzaila Abd Latif, A. I. Kamaruddin, A. Zaidi, Wan Muhammad Fikri Wan Badrulzaman
In Malaysia, stroke is the third cause of death and disability. Stroke cause significant injury to the brain that may result in long-term problems such as communication, concentration, memory, and executive functions. About one-third of post-stroke patients have speech and communication problems that require to undergo series of one-to-one speech therapy sessions. However, there are only 300 speech therapists in Malaysia which limit the recovery and may not reach to the needed patient. More importantly, frequent therapy conducted could fasten the recovery of the patients' speech. Therefore, this research develops a mobile application to be used as an alternative for speech therapy session. Although there are mobile applications for speech therapy, none of them are in Bahasa Melayu. The mobile application implements an automatic speech recognition technology that accepts the vowel speech sound from a post-stroke patient in Bahasa Melayu. The mobile application will process the sound, evaluate, and provide feedback score for the vowel sound in an accuracy percentage. It is expected that the ASR speech therapy mobile application could help speech disorder post-stroke patients to practice their speech ability at their own time without attending speech therapy sessions.
{"title":"Development of Speech Therapy Mobile Application for Speech Disorder Post-Stroke Patients","authors":"H. Basiron, Muhammad Azri Azmi, Mohd Juzaila Abd Latif, A. I. Kamaruddin, A. Zaidi, Wan Muhammad Fikri Wan Badrulzaman","doi":"10.1109/ICSET53708.2021.9612432","DOIUrl":"https://doi.org/10.1109/ICSET53708.2021.9612432","url":null,"abstract":"In Malaysia, stroke is the third cause of death and disability. Stroke cause significant injury to the brain that may result in long-term problems such as communication, concentration, memory, and executive functions. About one-third of post-stroke patients have speech and communication problems that require to undergo series of one-to-one speech therapy sessions. However, there are only 300 speech therapists in Malaysia which limit the recovery and may not reach to the needed patient. More importantly, frequent therapy conducted could fasten the recovery of the patients' speech. Therefore, this research develops a mobile application to be used as an alternative for speech therapy session. Although there are mobile applications for speech therapy, none of them are in Bahasa Melayu. The mobile application implements an automatic speech recognition technology that accepts the vowel speech sound from a post-stroke patient in Bahasa Melayu. The mobile application will process the sound, evaluate, and provide feedback score for the vowel sound in an accuracy percentage. It is expected that the ASR speech therapy mobile application could help speech disorder post-stroke patients to practice their speech ability at their own time without attending speech therapy sessions.","PeriodicalId":433197,"journal":{"name":"2021 IEEE 11th International Conference on System Engineering and Technology (ICSET)","volume":"46 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-11-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128094050","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 : 2021-11-06DOI: 10.1109/ICSET53708.2021.9612523
Norliyana Nor Hisham Shah, A. A. Razak, N. Razak, A. Ramasamy, Asma’ Abu-Samah, M. S. Hasan
Renal failure in the intensive care unit (ICU) is associated with high morbidity and mortality. The Sequential Organ Failure Assessment (SOFA) score is applied in the ICU to track the progression of organ dysfunction. The renal component of the SOFA score employed serum creatinine and urine output to define the stage of its dysfunction. This study aims to explore the relationship between commonly available variables in the ICU together patients' gender and comorbidities to renal failure employing Bayesian Network. The process of building Bayesian Networks involved variable selection, data discretization, and aggregation before structural learning method. The dataset was discretized using equal distance technique into 3 intervals before it was fed into unsupervised structural classification learning techniques. The highest overall precision of 85.1 % was achieved using the unsupervised learning Taboo Order Bayesian Network. Other than creatinine, heart rate, systolic blood pressure, temperature, diabetes mellitus, and hypertension are directly connected with renal failure in this Bayesian Network.
{"title":"Modeling Dynamic Patients Variables to Renal Failure in the Intensive Care Unit Using Bayesian Networks","authors":"Norliyana Nor Hisham Shah, A. A. Razak, N. Razak, A. Ramasamy, Asma’ Abu-Samah, M. S. Hasan","doi":"10.1109/ICSET53708.2021.9612523","DOIUrl":"https://doi.org/10.1109/ICSET53708.2021.9612523","url":null,"abstract":"Renal failure in the intensive care unit (ICU) is associated with high morbidity and mortality. The Sequential Organ Failure Assessment (SOFA) score is applied in the ICU to track the progression of organ dysfunction. The renal component of the SOFA score employed serum creatinine and urine output to define the stage of its dysfunction. This study aims to explore the relationship between commonly available variables in the ICU together patients' gender and comorbidities to renal failure employing Bayesian Network. The process of building Bayesian Networks involved variable selection, data discretization, and aggregation before structural learning method. The dataset was discretized using equal distance technique into 3 intervals before it was fed into unsupervised structural classification learning techniques. The highest overall precision of 85.1 % was achieved using the unsupervised learning Taboo Order Bayesian Network. Other than creatinine, heart rate, systolic blood pressure, temperature, diabetes mellitus, and hypertension are directly connected with renal failure in this Bayesian Network.","PeriodicalId":433197,"journal":{"name":"2021 IEEE 11th International Conference on System Engineering and Technology (ICSET)","volume":"8 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-11-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132594820","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 : 2021-11-06DOI: 10.1109/ICSET53708.2021.9612578
F. Kinasih, C. Machbub, L. Yulianti, A. Syaichu-Rohman
Recent advancements in object detection methods give us the means to recognize what kind of object is present in the sensor field of view. Though indeed useful, this may not be enough for some specific application in which we need to distinguish an object from another object, that might belong to the same or different class object. This paper will discuss a good option for a high-speed/low computation cost method for ID assignment that can be used even for objects that belong to the same class. Utilizing the Centroid Tracker concept, Rosebrock applies an ID assignment based on distances between objects in the current and previous frame. This method has shown promising success in complement with object detection to help a computer vision system for tracking specific objects of interest.
{"title":"Application of ID Assignment Features in Rosebrocks' Simple Object Tracker","authors":"F. Kinasih, C. Machbub, L. Yulianti, A. Syaichu-Rohman","doi":"10.1109/ICSET53708.2021.9612578","DOIUrl":"https://doi.org/10.1109/ICSET53708.2021.9612578","url":null,"abstract":"Recent advancements in object detection methods give us the means to recognize what kind of object is present in the sensor field of view. Though indeed useful, this may not be enough for some specific application in which we need to distinguish an object from another object, that might belong to the same or different class object. This paper will discuss a good option for a high-speed/low computation cost method for ID assignment that can be used even for objects that belong to the same class. Utilizing the Centroid Tracker concept, Rosebrock applies an ID assignment based on distances between objects in the current and previous frame. This method has shown promising success in complement with object detection to help a computer vision system for tracking specific objects of interest.","PeriodicalId":433197,"journal":{"name":"2021 IEEE 11th International Conference on System Engineering and Technology (ICSET)","volume":"46 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-11-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133190923","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 : 2021-11-06DOI: 10.1109/ICSET53708.2021.9612551
T. Tiong, I. Saad
More computation-intensive and low latency applications are emerging recently, and they are constrained by the computing power and battery life of internet of things (IoT). Simultaneous wireless information and power transfer (SWIPT) with mobile-edge computing (MEC) can improve the data processing capability of energy constrained networks. In this paper, a SWIPT-based MEC system is proposed, comprising a multi-antenna access point (AP), multiple single antenna low power IoT devices and a MEC server. The IoT devices exploit the harvested energy for either locally computing or offloading the tasks to the MEC server. Conventional numerical optimization methods are not able to solve combinatorial problems within the limit of the wireless channel coherence time. Thus, Online Offloading with Deep Reinforcement learning (OODRL) is proposed. The proposed algorithm jointly optimizes the offloading decisions, the time slots devoted to energy harvesting (EH), and local computation/offloading to maximize the MEC computation rate. Deep Q network (DQN) is used to learn the binary offloading decisions from the learning experience. This method no longer needs to solve combinatorial problems. Simulation results are presented to demonstrate that the proposed algorithm is able to approach near-optimal performance and superior in decreasing tasks computation time compared with existing optimization methods, enabling real time optimal resource allocation and offloading achievable in a fast-fading wireless environment.
{"title":"Deep Reinforcement Learning Online Offloading for SWIPT Multiple Access Edge Computing Network","authors":"T. Tiong, I. Saad","doi":"10.1109/ICSET53708.2021.9612551","DOIUrl":"https://doi.org/10.1109/ICSET53708.2021.9612551","url":null,"abstract":"More computation-intensive and low latency applications are emerging recently, and they are constrained by the computing power and battery life of internet of things (IoT). Simultaneous wireless information and power transfer (SWIPT) with mobile-edge computing (MEC) can improve the data processing capability of energy constrained networks. In this paper, a SWIPT-based MEC system is proposed, comprising a multi-antenna access point (AP), multiple single antenna low power IoT devices and a MEC server. The IoT devices exploit the harvested energy for either locally computing or offloading the tasks to the MEC server. Conventional numerical optimization methods are not able to solve combinatorial problems within the limit of the wireless channel coherence time. Thus, Online Offloading with Deep Reinforcement learning (OODRL) is proposed. The proposed algorithm jointly optimizes the offloading decisions, the time slots devoted to energy harvesting (EH), and local computation/offloading to maximize the MEC computation rate. Deep Q network (DQN) is used to learn the binary offloading decisions from the learning experience. This method no longer needs to solve combinatorial problems. Simulation results are presented to demonstrate that the proposed algorithm is able to approach near-optimal performance and superior in decreasing tasks computation time compared with existing optimization methods, enabling real time optimal resource allocation and offloading achievable in a fast-fading wireless environment.","PeriodicalId":433197,"journal":{"name":"2021 IEEE 11th International Conference on System Engineering and Technology (ICSET)","volume":"9 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-11-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131140635","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：