Pub Date : 2020-09-27DOI: 10.1109/SCOReD50371.2020.9383181
Avinash Krishnan Raghunath, Srimathi Chandrasekaran, R. Doss, M. A. Saleem Durai
Liquefied Petroleum Gas (LPG) gas is the most commonly used gas for cooking in India and it is considered highly flammable since it is a combination of hydrocarbon gases such as Propane (C3H8), N-butane and Isobutane (C4H10). These elements contribute to its high density and long-distance travelling capabilities. This results in an extensive gas outspread during leakage with multiple avenues for ignition, primarily due to the electric circuitry at home. The primary focus of our project is to simulate a network map of a gas leakage warning system so as to showcase its implementation in an apartment-based setup. The network map can be scaled up for implementation in residential sectors, petroleum and oil fields, sewage lines, etc. based on our proof of concept. In our use case, we would implement LPG Gas Sensors to Microcontroller for providing a logical binary output of fire warning indication.
{"title":"Gas Leakage Warning System","authors":"Avinash Krishnan Raghunath, Srimathi Chandrasekaran, R. Doss, M. A. Saleem Durai","doi":"10.1109/SCOReD50371.2020.9383181","DOIUrl":"https://doi.org/10.1109/SCOReD50371.2020.9383181","url":null,"abstract":"Liquefied Petroleum Gas (LPG) gas is the most commonly used gas for cooking in India and it is considered highly flammable since it is a combination of hydrocarbon gases such as Propane (C3H8), N-butane and Isobutane (C4H10). These elements contribute to its high density and long-distance travelling capabilities. This results in an extensive gas outspread during leakage with multiple avenues for ignition, primarily due to the electric circuitry at home. The primary focus of our project is to simulate a network map of a gas leakage warning system so as to showcase its implementation in an apartment-based setup. The network map can be scaled up for implementation in residential sectors, petroleum and oil fields, sewage lines, etc. based on our proof of concept. In our use case, we would implement LPG Gas Sensors to Microcontroller for providing a logical binary output of fire warning indication.","PeriodicalId":142867,"journal":{"name":"2020 IEEE Student Conference on Research and Development (SCOReD)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2020-09-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131124091","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 : 2020-09-27DOI: 10.1109/scored50371.2020.9251008
Nurul Ashikin Mohamad, N. M. B. Sham, M. S. Kamarudin, N. Jamail, R. Abd-Rahman, M. Yousof
In the evolution of the electrical systems in the smart grid context, the amount of data available is increasing considerably. Data-driven solutions are emerging as alternatives to model-based approaches. New tools are being developed to handle the flow of data gathered during time from different sources. The presentation highlights various aspects referring to data-driven approaches, from consistency of the data to the challenging task of transforming data into knowledge. Specific focus is set on the nature and quality of the data, the role of data uncertainty, and the role of the expert of the domain in verifying the meaningfulness of the available data and in identifying the most effective usage of the data in the smart grid applications. Biography: Gianfranco Chicco holds a PhD in Electrotechnics Engineering and is a Full Professor of Power and Energy Systems at Politecnico di Torino (POLITO) in Torino, Italy. He is a Fellow of the IEEE (Power and Energy Society). He received the title of “Doctor Honoris Causa” from the University Politehnica of Bucharest (Romania) and from the Technical University “Gheorghe Asachi” of Iasi (Romania) in 2017 and 2018, respectively. He is the vice-Chair of the IEEE Italy Section. More information about Prof. Gianfranco Chicco, please visit: http://icpse.org/keynote.html . Keynote Speaker October 22 | 11:20-12:00(GMT+3) Prof. Bikash Pal, IEEE Fellow, Imperial College London, UK Vice President of Publications, IEEE Power and Energy Society Editor-in-Chief of IEEE Transactions on Sustainable Energy (2012-2017) Editor-in-Chief of IET Generation, Transmission and Distribution (2005-2012) Speech Title: Robust Volt-Var Control in Power Distribution Abstract: Electrical generation, transmission and distribution systems all over the world have entered a period of significant renewal and technological change. There have been phenomenal changes/deployments in technology of generation driven by the worldwide emphasis on energy from wind and solar as a sustainable solution to our energy need. Increasingly energy demand from heating and transportation are being met by electricity. These changes have significantly influenced the planning, design, operation and control of the power distribution system. Accommodating uncertainties in renewable generation and demand forecast in a cost-effective manner is now a very complex optimization problem. This talk will share our recent research efforts Volt/VAr control (VVC) strategy in distribution systems to address the uncertainties. Efficient chance constrained conic optimisation technique accelerated through scenario reduction approach will be discussed to demonstrate the significant reduction of voltage violations when compared with the deterministic cases while not relaxing the conservativeness of the final solutions. It will also touch upon treatment of certain types of load characteristic in the proposed solution framework. Future research challenges and opportunities will be hi
在智能电网背景下电力系统的发展过程中,可用的数据量正在显著增加。数据驱动的解决方案正在成为基于模型的方法的替代方案。正在开发新的工具来处理在一段时间内从不同来源收集的数据流。该演讲强调了涉及数据驱动方法的各个方面,从数据的一致性到将数据转换为知识的挑战性任务。具体重点放在数据的性质和质量,数据不确定性的作用,以及领域专家在验证可用数据的意义和确定智能电网应用中数据的最有效使用方面的作用。简介:Gianfranco Chicco拥有电气工程博士学位,是意大利都灵理工大学(Politecnico di Torino)电力与能源系统专业的正教授。他是IEEE(电力与能源学会)的会员。他分别于2017年和2018年获得布加勒斯特Politehnica大学(罗马尼亚)和Iasi“Gheorghe Asachi”技术大学(罗马尼亚)的荣誉博士称号。他是IEEE意大利分会的副主席。更多关于Gianfranco Chicco教授的信息,请访问:http://icpse.org/keynote.html。Bikash Pal教授,IEEE Fellow, Imperial College London,英国,IEEE出版副总裁,IEEE Power and Energy Society, IEEE Transactions on Sustainable Energy主编(2012-2017),IET Generation,输配电总编辑(2005-2012),演讲主题:配电中的鲁棒电压无功控制全世界的发电、输电和配电系统都进入了一个重大更新和技术变革的时期。由于全世界都强调风能和太阳能是满足我们能源需求的可持续解决方案,因此发电技术已经发生了显著的变化/部署。电力越来越多地满足了供暖和运输的能源需求。这些变化对配电系统的规划、设计、运行和控制产生了重大影响。以经济有效的方式适应可再生能源发电和需求预测的不确定性是一个非常复杂的优化问题。本次演讲将分享我们最近在配电系统中伏/无功控制(VVC)策略方面的研究成果,以解决不确定性。将讨论通过情景约简方法加速的有效机会约束圆锥优化技术,以证明与确定性情况相比,电压违规的显著减少,同时不会放松最终解决方案的保守性。它还将涉及在建议的解决方案框架中处理某些类型的负载特性。强调未来研究的挑战和机遇。全世界的发电、输电和配电系统都进入了一个重大更新和技术变革的时期。由于全世界都强调风能和太阳能是满足我们能源需求的可持续解决方案,因此发电技术已经发生了显著的变化/部署。电力越来越多地满足了供暖和运输的能源需求。这些变化对配电系统的规划、设计、运行和控制产生了重大影响。以经济有效的方式适应可再生能源发电和需求预测的不确定性是一个非常复杂的优化问题。本次演讲将分享我们最近在配电系统中伏/无功控制(VVC)策略方面的研究成果,以解决不确定性。将讨论通过情景约简方法加速的有效机会约束圆锥优化技术,以证明与确定性情况相比,电压违规的显著减少,同时不会放松最终解决方案的保守性。它还将涉及在建议的解决方案框架中处理某些类型的负载特性。强调未来研究的挑战和机遇。
{"title":"Welcome Message","authors":"Nurul Ashikin Mohamad, N. M. B. Sham, M. S. Kamarudin, N. Jamail, R. Abd-Rahman, M. Yousof","doi":"10.1109/scored50371.2020.9251008","DOIUrl":"https://doi.org/10.1109/scored50371.2020.9251008","url":null,"abstract":"In the evolution of the electrical systems in the smart grid context, the amount of data available is increasing considerably. Data-driven solutions are emerging as alternatives to model-based approaches. New tools are being developed to handle the flow of data gathered during time from different sources. The presentation highlights various aspects referring to data-driven approaches, from consistency of the data to the challenging task of transforming data into knowledge. Specific focus is set on the nature and quality of the data, the role of data uncertainty, and the role of the expert of the domain in verifying the meaningfulness of the available data and in identifying the most effective usage of the data in the smart grid applications. Biography: Gianfranco Chicco holds a PhD in Electrotechnics Engineering and is a Full Professor of Power and Energy Systems at Politecnico di Torino (POLITO) in Torino, Italy. He is a Fellow of the IEEE (Power and Energy Society). He received the title of “Doctor Honoris Causa” from the University Politehnica of Bucharest (Romania) and from the Technical University “Gheorghe Asachi” of Iasi (Romania) in 2017 and 2018, respectively. He is the vice-Chair of the IEEE Italy Section. More information about Prof. Gianfranco Chicco, please visit: http://icpse.org/keynote.html . Keynote Speaker October 22 | 11:20-12:00(GMT+3) Prof. Bikash Pal, IEEE Fellow, Imperial College London, UK Vice President of Publications, IEEE Power and Energy Society Editor-in-Chief of IEEE Transactions on Sustainable Energy (2012-2017) Editor-in-Chief of IET Generation, Transmission and Distribution (2005-2012) Speech Title: Robust Volt-Var Control in Power Distribution Abstract: Electrical generation, transmission and distribution systems all over the world have entered a period of significant renewal and technological change. There have been phenomenal changes/deployments in technology of generation driven by the worldwide emphasis on energy from wind and solar as a sustainable solution to our energy need. Increasingly energy demand from heating and transportation are being met by electricity. These changes have significantly influenced the planning, design, operation and control of the power distribution system. Accommodating uncertainties in renewable generation and demand forecast in a cost-effective manner is now a very complex optimization problem. This talk will share our recent research efforts Volt/VAr control (VVC) strategy in distribution systems to address the uncertainties. Efficient chance constrained conic optimisation technique accelerated through scenario reduction approach will be discussed to demonstrate the significant reduction of voltage violations when compared with the deterministic cases while not relaxing the conservativeness of the final solutions. It will also touch upon treatment of certain types of load characteristic in the proposed solution framework. Future research challenges and opportunities will be hi","PeriodicalId":142867,"journal":{"name":"2020 IEEE Student Conference on Research and Development (SCOReD)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2020-09-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134645247","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 : 2020-09-27DOI: 10.1109/SCOReD50371.2020.9251038
Sia Hee Nee, Hermawan Nugroho
Advancements in deep neural networks has led to the extensive implementation of machine learning models for inferencing and analytics on data especially in smart city projects. Object detection algorithm is one of well-known application of deep neural network. Given how computationally expensive these operations are, there is a growing need for methods to reduce the effort of running these complex algorithms on resource-constrained embedded devices which are typically used in IoT applications. Recently, a computing paradigm called fog computing which extends the cloud computing paradigm to the network edge has captured the attention of researchers and industrial organizations alike. This paper investigates the possibilities of implementing Fog Computing using a novel layer-wise partitioning scheme as a solution to reduce the effort of running deep inferencing for object detection algorithms on embedded IoT devices. Results show that the proposed solution is potential in comparison with cloud and single node based system.
{"title":"Task Distribution of Object Detection Algorithms in Fog-Computing Framework","authors":"Sia Hee Nee, Hermawan Nugroho","doi":"10.1109/SCOReD50371.2020.9251038","DOIUrl":"https://doi.org/10.1109/SCOReD50371.2020.9251038","url":null,"abstract":"Advancements in deep neural networks has led to the extensive implementation of machine learning models for inferencing and analytics on data especially in smart city projects. Object detection algorithm is one of well-known application of deep neural network. Given how computationally expensive these operations are, there is a growing need for methods to reduce the effort of running these complex algorithms on resource-constrained embedded devices which are typically used in IoT applications. Recently, a computing paradigm called fog computing which extends the cloud computing paradigm to the network edge has captured the attention of researchers and industrial organizations alike. This paper investigates the possibilities of implementing Fog Computing using a novel layer-wise partitioning scheme as a solution to reduce the effort of running deep inferencing for object detection algorithms on embedded IoT devices. Results show that the proposed solution is potential in comparison with cloud and single node based system.","PeriodicalId":142867,"journal":{"name":"2020 IEEE Student Conference on Research and Development (SCOReD)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2020-09-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133750177","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 : 2020-09-27DOI: 10.1109/SCOReD50371.2020.9250984
Win Adiyansyah Indha, Nur Syahirah Zamzam, A. Saptari, J. Alsayaydeh, N. Hassim
This paper developed security system prototype using motion sensor powered by Radio Frequency Energy Harvesting, one form of energy harvesting that regardless its lowest output power among other energy harvesting forms, its all the time availability, batteryless and readiness everywhere make its own advantages no other type of energy harvesting have. Motion sensor acts as a shield to detect movement as to detect crime. In this project, there are two security system by using motion sensor. First stage of security system which in outdoor, operated as the sensor detect motion, the bulb will light up. Second stage security system which in indoor, operated as the sensor detect motion, it will trigger the dial speed key of the GSM and send an alarm call to user. The RF to DC energy will stored in the LiPO battery to power up the operation of motion sensor. Together with data and analysis measured, the RF energy harvesting able to generate voltage and current which can operate the low power consumption of the PIR sensor.A 3 Watt stand-alone power transmitter at frequency 915 Mhz used to test the prototype to replace the ambient available radio frequency resources. The results showed the security system prototype using motion sensor works properly, able send alarm to owner.
{"title":"Development of Security System Using Motion Sensor Powered by RF Energy Harvesting","authors":"Win Adiyansyah Indha, Nur Syahirah Zamzam, A. Saptari, J. Alsayaydeh, N. Hassim","doi":"10.1109/SCOReD50371.2020.9250984","DOIUrl":"https://doi.org/10.1109/SCOReD50371.2020.9250984","url":null,"abstract":"This paper developed security system prototype using motion sensor powered by Radio Frequency Energy Harvesting, one form of energy harvesting that regardless its lowest output power among other energy harvesting forms, its all the time availability, batteryless and readiness everywhere make its own advantages no other type of energy harvesting have. Motion sensor acts as a shield to detect movement as to detect crime. In this project, there are two security system by using motion sensor. First stage of security system which in outdoor, operated as the sensor detect motion, the bulb will light up. Second stage security system which in indoor, operated as the sensor detect motion, it will trigger the dial speed key of the GSM and send an alarm call to user. The RF to DC energy will stored in the LiPO battery to power up the operation of motion sensor. Together with data and analysis measured, the RF energy harvesting able to generate voltage and current which can operate the low power consumption of the PIR sensor.A 3 Watt stand-alone power transmitter at frequency 915 Mhz used to test the prototype to replace the ambient available radio frequency resources. The results showed the security system prototype using motion sensor works properly, able send alarm to owner.","PeriodicalId":142867,"journal":{"name":"2020 IEEE Student Conference on Research and Development (SCOReD)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2020-09-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134062863","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}
Waste-the abandon things are a big concern for every country. A new day comes with several million tons of wastes. These wastes are not only filling this world lands but also contributing to global climate change. The adverse effect of climate change is happening on human and other living creatures. According to a report from the World Health Organisation (WHO), 4.2 million people have been dying every year because of outdoor pollution. Unfortunately, very few countries are conscious of this serious issue and trying to manage and recycle wastes. In this paper, we have proposed a waste recycling system thinking researchers will implement it in real-time and contribute toward a green and healthy living world. The input of the proposed system will be a mixture of wastes. The system will separate solid wastes like a bottle, wood pieces, brick pieces and other materials which can be reused or used raw material for the Solid Fuel Recover (SRF) system. The outcomes of the system will be biogas and bio-fertiliser. These resources can be used directly in household and industrial purposes and to fertile agricultural lands. Alternatively, these resources can contribute to generating electricity and transportation refuelling. Thus, it is expected, the proposed waste recycling system will add a new dimension in waste management and renewable energy sector.
{"title":"A Waste Recycling System for a Better Living World","authors":"Md. Atiqul Islam, Md. Abdur Rahman, An-Nazmus Sakib","doi":"10.1109/SCOReD50371.2020.9251023","DOIUrl":"https://doi.org/10.1109/SCOReD50371.2020.9251023","url":null,"abstract":"Waste-the abandon things are a big concern for every country. A new day comes with several million tons of wastes. These wastes are not only filling this world lands but also contributing to global climate change. The adverse effect of climate change is happening on human and other living creatures. According to a report from the World Health Organisation (WHO), 4.2 million people have been dying every year because of outdoor pollution. Unfortunately, very few countries are conscious of this serious issue and trying to manage and recycle wastes. In this paper, we have proposed a waste recycling system thinking researchers will implement it in real-time and contribute toward a green and healthy living world. The input of the proposed system will be a mixture of wastes. The system will separate solid wastes like a bottle, wood pieces, brick pieces and other materials which can be reused or used raw material for the Solid Fuel Recover (SRF) system. The outcomes of the system will be biogas and bio-fertiliser. These resources can be used directly in household and industrial purposes and to fertile agricultural lands. Alternatively, these resources can contribute to generating electricity and transportation refuelling. Thus, it is expected, the proposed waste recycling system will add a new dimension in waste management and renewable energy sector.","PeriodicalId":142867,"journal":{"name":"2020 IEEE Student Conference on Research and Development (SCOReD)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2020-09-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114506470","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 : 2020-09-27DOI: 10.1109/SCOReD50371.2020.9250937
Edgar Zhe Qian Koh, Abakar Yousif Abdalla, Hermawan Nugroho
Recently, perception system for autonomous vehicle has seen a tremendous growth. Most of the recent works employ sensor fusion with complementary properties to produce a robust and accurate perceptive system for vehicle. However, this comes at a high price, requires high computing power and consumes more energy. In this study a perceptive system is designed to tackle the above issues while maintaining its accuracy and robustness. The proposed perceptive system is using only a pair of vision sensors. A Convolution Neural Network is used to detect and identify objects in the field of vision. A pair of cameras are then used to form a stereovision which is used to measure the distance of the objects detected. A disparity map from stereovision images was constructed first, then from the region of interest, a single disparity value was extracted to calculate the distance. The system is employed on a single board computer system StereoPi with the help of Intel Neural Compute Stick 2 to run deep neural network inference. An experiment was then conducted to test the perceptive system’s robustness, accuracy, and runtime. Results show that the proposed system is capable of a detection accuracy of 71.7% with an average error of 0.37% up to a distance of 1.3m.
{"title":"Visual Computing-based Perception System for Small Autonomous Vehicles: Development on a Lighter Computing Platform","authors":"Edgar Zhe Qian Koh, Abakar Yousif Abdalla, Hermawan Nugroho","doi":"10.1109/SCOReD50371.2020.9250937","DOIUrl":"https://doi.org/10.1109/SCOReD50371.2020.9250937","url":null,"abstract":"Recently, perception system for autonomous vehicle has seen a tremendous growth. Most of the recent works employ sensor fusion with complementary properties to produce a robust and accurate perceptive system for vehicle. However, this comes at a high price, requires high computing power and consumes more energy. In this study a perceptive system is designed to tackle the above issues while maintaining its accuracy and robustness. The proposed perceptive system is using only a pair of vision sensors. A Convolution Neural Network is used to detect and identify objects in the field of vision. A pair of cameras are then used to form a stereovision which is used to measure the distance of the objects detected. A disparity map from stereovision images was constructed first, then from the region of interest, a single disparity value was extracted to calculate the distance. The system is employed on a single board computer system StereoPi with the help of Intel Neural Compute Stick 2 to run deep neural network inference. An experiment was then conducted to test the perceptive system’s robustness, accuracy, and runtime. Results show that the proposed system is capable of a detection accuracy of 71.7% with an average error of 0.37% up to a distance of 1.3m.","PeriodicalId":142867,"journal":{"name":"2020 IEEE Student Conference on Research and Development (SCOReD)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2020-09-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124757171","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 : 2020-09-27DOI: 10.1109/SCOReD50371.2020.9250977
Jianwen Hoon, R. Tan
This paper aims to develop a charge & discharge controller for 700kWh/540kW Battery Energy Storage System (BESS) with and its integration with Grid-connected 3MWp Solar PV Plant. The BESS plays its very important role to store surplus solar PV power and to perform functions such as load shifting for the economic benefits of electricity consumers. The BESS Charge Discharge Control Strategy serves the purpose to allow battery charging operation when surplus PV power presents after supplying to the load demand and consistently charging during off-peak hours with lower electricity cost compared of peak hours. Similarly, the control system operates discharging operation when PV power does not meet the load demand while being within the peak hours defined by the electricity provider. The integration of functions of load Shifting of the BESS, together with the Solar PV plant will be able to reduce the campus load consumption from the power grid significantly while being cost-effective. The obtained results based on the proposed control strategy demonstrate that minimum energy cost can be saved from this BESS is $ 14.25/day regardless any weather conditions, $ 81.12/day during high variability day, and $ 53.41/day during clear sky day; with the constraints of not considering maximum demand cost and fit-in tariff.
{"title":"Grid-Connected Solar PV Plant Surplus Energy Utilization Using Battery Energy Storage System","authors":"Jianwen Hoon, R. Tan","doi":"10.1109/SCOReD50371.2020.9250977","DOIUrl":"https://doi.org/10.1109/SCOReD50371.2020.9250977","url":null,"abstract":"This paper aims to develop a charge & discharge controller for 700kWh/540kW Battery Energy Storage System (BESS) with and its integration with Grid-connected 3MWp Solar PV Plant. The BESS plays its very important role to store surplus solar PV power and to perform functions such as load shifting for the economic benefits of electricity consumers. The BESS Charge Discharge Control Strategy serves the purpose to allow battery charging operation when surplus PV power presents after supplying to the load demand and consistently charging during off-peak hours with lower electricity cost compared of peak hours. Similarly, the control system operates discharging operation when PV power does not meet the load demand while being within the peak hours defined by the electricity provider. The integration of functions of load Shifting of the BESS, together with the Solar PV plant will be able to reduce the campus load consumption from the power grid significantly while being cost-effective. The obtained results based on the proposed control strategy demonstrate that minimum energy cost can be saved from this BESS is $ 14.25/day regardless any weather conditions, $ 81.12/day during high variability day, and $ 53.41/day during clear sky day; with the constraints of not considering maximum demand cost and fit-in tariff.","PeriodicalId":142867,"journal":{"name":"2020 IEEE Student Conference on Research and Development (SCOReD)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2020-09-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124761869","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 : 2020-09-27DOI: 10.1109/SCOReD50371.2020.9250928
Nur Ayuni Mohamed, M. A. Zulkifley, Siti Raihanah Abdani
Disease screening through the fundus image is one of the hottest research topics in biomedical engineering. There are various diseases that can be screened through human retinal information, which include glaucoma, myopia, macular degeneration, diabetic retinopathy, and cataracts. Hence, an automated system to screen all these diseases will be beneficial to health practitioners. Previously, each of the disease features needs to be designed by hand if the traditional machine learning approach is used. It is hard to process various diseases as a single system through this approach, especially if a new disease that needs to be added to the system does not fit well with the handcrafted features. Thus, a deep learning approach that utilizes learned features is the better alternative as the model can be updated easily if a new disease wants to be added to the system. This paper proposes a modified MobileNet architecture by replacing the top layers with a spatial pyramid pooling module. Three parallel flows of max-pooling operation through kernel sizes of $times$$,times$, and $times$ are implemented to improve the algorithm robustness towards multi-scale input. Atrous convolution is also employed by adding the dilation rate to each of the pointwise convolution operators. The results show that a dilation rate of 4 produces the best mean accuracy of 0.7433 for the 5-fold cross-validation test. The algorithm retains its lightweight nature where the total number of parameters used is around 3 million. The model can be trained better if the number of data among the classes is more or less the same, which will reduce the training bias.
{"title":"Spatial Pyramid Pooling with Atrous Convolutional for MobileNet","authors":"Nur Ayuni Mohamed, M. A. Zulkifley, Siti Raihanah Abdani","doi":"10.1109/SCOReD50371.2020.9250928","DOIUrl":"https://doi.org/10.1109/SCOReD50371.2020.9250928","url":null,"abstract":"Disease screening through the fundus image is one of the hottest research topics in biomedical engineering. There are various diseases that can be screened through human retinal information, which include glaucoma, myopia, macular degeneration, diabetic retinopathy, and cataracts. Hence, an automated system to screen all these diseases will be beneficial to health practitioners. Previously, each of the disease features needs to be designed by hand if the traditional machine learning approach is used. It is hard to process various diseases as a single system through this approach, especially if a new disease that needs to be added to the system does not fit well with the handcrafted features. Thus, a deep learning approach that utilizes learned features is the better alternative as the model can be updated easily if a new disease wants to be added to the system. This paper proposes a modified MobileNet architecture by replacing the top layers with a spatial pyramid pooling module. Three parallel flows of max-pooling operation through kernel sizes of $times$$,times$, and $times$ are implemented to improve the algorithm robustness towards multi-scale input. Atrous convolution is also employed by adding the dilation rate to each of the pointwise convolution operators. The results show that a dilation rate of 4 produces the best mean accuracy of 0.7433 for the 5-fold cross-validation test. The algorithm retains its lightweight nature where the total number of parameters used is around 3 million. The model can be trained better if the number of data among the classes is more or less the same, which will reduce the training bias.","PeriodicalId":142867,"journal":{"name":"2020 IEEE Student Conference on Research and Development (SCOReD)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2020-09-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129382867","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 : 2020-09-27DOI: 10.1109/SCOReD50371.2020.9250931
Denesh Sooriamoorthy, Audrey Li-Huey Wee, Anandan S. Shanmugam, Khor Jeen Ghee, P. Ooi, Marwan Nafea
Zero-dimensional (OD) models are simplified representations of the components of the cardiovascular system which aids in a strong understanding of the cardiovascular circulatory system. The zero-dimensional model provides a concise way to evaluate the dynamics of the blood flow interactions with the cardiovascular organs. The purpose of cardiovascular circulatory system modeling and simulation is to understand the fundamental parameters underlying the heart circulation system. The numerical change in the parameters represents the effects of pulse wave transmission in the arterial network. This paper studies 36 different dynamic parameters of the zero-dimension cardiovascular model by Vincent Rideout that consists of 16 resistance parameters, 12 compliance parameters, and 8 inductance parameters. The main aim of this research is to determine which parameters primarily affect the aortic wave signal of the Vincent Rideout model. An iterative study of the parameters was conducted to study the relationship between each parameter and its response to the aortic waveform. This investigation is focused on the second peak of PA1 because the first peak only quantifies the first pump of blood flow out of the heart. The time was kept constant while each parameter was varied from 0.25 to 1.75 times its default value. The results are analyzed, and 9 prominent parameters and 7 less prominent parameters were identified, which will affect the aortic waveform of the Vincent Rideout cardiovascular model. These prominent and less prominent parameters would be crucial parameters for the detection of cardiovascular diseases and monitoring the condition of the heart of the person.
{"title":"A Study on the Effect of Electrical Parameters of Zero-Dimensional Cardiovascular System on Aortic Waveform","authors":"Denesh Sooriamoorthy, Audrey Li-Huey Wee, Anandan S. Shanmugam, Khor Jeen Ghee, P. Ooi, Marwan Nafea","doi":"10.1109/SCOReD50371.2020.9250931","DOIUrl":"https://doi.org/10.1109/SCOReD50371.2020.9250931","url":null,"abstract":"Zero-dimensional (OD) models are simplified representations of the components of the cardiovascular system which aids in a strong understanding of the cardiovascular circulatory system. The zero-dimensional model provides a concise way to evaluate the dynamics of the blood flow interactions with the cardiovascular organs. The purpose of cardiovascular circulatory system modeling and simulation is to understand the fundamental parameters underlying the heart circulation system. The numerical change in the parameters represents the effects of pulse wave transmission in the arterial network. This paper studies 36 different dynamic parameters of the zero-dimension cardiovascular model by Vincent Rideout that consists of 16 resistance parameters, 12 compliance parameters, and 8 inductance parameters. The main aim of this research is to determine which parameters primarily affect the aortic wave signal of the Vincent Rideout model. An iterative study of the parameters was conducted to study the relationship between each parameter and its response to the aortic waveform. This investigation is focused on the second peak of PA1 because the first peak only quantifies the first pump of blood flow out of the heart. The time was kept constant while each parameter was varied from 0.25 to 1.75 times its default value. The results are analyzed, and 9 prominent parameters and 7 less prominent parameters were identified, which will affect the aortic waveform of the Vincent Rideout cardiovascular model. These prominent and less prominent parameters would be crucial parameters for the detection of cardiovascular diseases and monitoring the condition of the heart of the person.","PeriodicalId":142867,"journal":{"name":"2020 IEEE Student Conference on Research and Development (SCOReD)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2020-09-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116696287","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 : 2020-09-27DOI: 10.1109/SCOReD50371.2020.9250940
Amirul S. Bin Ibrahin, Othman O. Khalifa, D. E. M. Ahmed
Plagiarism is when someone takes another author’s works, thoughts, ideas, etc. without proper referencing and claim it as his/her own works. Plagiarism detection is the process to find the plagiarism within a work or documents. With the advance of modern technology, it makes it easier for people to search for information and plagiarize the work of others. Although the effort and ideas for an image-based plagiarism detection has been increasing over the years, flaws are still presence in the current systems. This paper proposes a new system that can cover those flaws. It consists three stages: the pre-processing, feature extraction and comparison stage. The results showed in an ascending order of similarity index and true and false. However, the accuracy is 100% in case of unedited images and variated in other operations such as flipped, rotated, greyscales and cropped
{"title":"Plagiarism Detection of Images","authors":"Amirul S. Bin Ibrahin, Othman O. Khalifa, D. E. M. Ahmed","doi":"10.1109/SCOReD50371.2020.9250940","DOIUrl":"https://doi.org/10.1109/SCOReD50371.2020.9250940","url":null,"abstract":"Plagiarism is when someone takes another author’s works, thoughts, ideas, etc. without proper referencing and claim it as his/her own works. Plagiarism detection is the process to find the plagiarism within a work or documents. With the advance of modern technology, it makes it easier for people to search for information and plagiarize the work of others. Although the effort and ideas for an image-based plagiarism detection has been increasing over the years, flaws are still presence in the current systems. This paper proposes a new system that can cover those flaws. It consists three stages: the pre-processing, feature extraction and comparison stage. The results showed in an ascending order of similarity index and true and false. However, the accuracy is 100% in case of unedited images and variated in other operations such as flipped, rotated, greyscales and cropped","PeriodicalId":142867,"journal":{"name":"2020 IEEE Student Conference on Research and Development (SCOReD)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2020-09-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126583909","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}