Pub Date : 2019-10-01DOI: 10.1109/SCORED.2019.8896253
K. Nurhanim, I. Elamvazuthi, L. I. Izhar, G. Capi
In Human activity recognition (HAR) research study it is a common practice using a wearable sensor to acquire the signal of human daily activities. In this study, database from smartphone inertial sensors is analysed for six different activities recognition. The aim of this paper is to compare different filter method feature selections for multiclass problem based on human daily living activities using the smartphone inertial sensor. Three components for HAR processing stage are involved that comprises of data filtering and segmentation, data feature extraction, feature selection of the data and classification. An ensemble method of Random subspace with Support vector machine is adapted for classification. Model evaluation of holdout and 10-fold cross-validation methods are implemented for classification assessment. The performance of all human daily activities is evaluated according to comparison of overall accuracy for four type filter method feature selection method. From the result findings, the number of features that reduce to 198 feature archived 98.89% compared to 561 numbers of features 98.74% of overall accuracy for holdout method. While using the 10 cross validation method, the numbers of features are reduced to 424 with the overall accuracy 99.28% compared to 561 number of features with 99.22% of overall accuracy.
{"title":"Feature selection of Human Daily Activities using Ensemble method Classification","authors":"K. Nurhanim, I. Elamvazuthi, L. I. Izhar, G. Capi","doi":"10.1109/SCORED.2019.8896253","DOIUrl":"https://doi.org/10.1109/SCORED.2019.8896253","url":null,"abstract":"In Human activity recognition (HAR) research study it is a common practice using a wearable sensor to acquire the signal of human daily activities. In this study, database from smartphone inertial sensors is analysed for six different activities recognition. The aim of this paper is to compare different filter method feature selections for multiclass problem based on human daily living activities using the smartphone inertial sensor. Three components for HAR processing stage are involved that comprises of data filtering and segmentation, data feature extraction, feature selection of the data and classification. An ensemble method of Random subspace with Support vector machine is adapted for classification. Model evaluation of holdout and 10-fold cross-validation methods are implemented for classification assessment. The performance of all human daily activities is evaluated according to comparison of overall accuracy for four type filter method feature selection method. From the result findings, the number of features that reduce to 198 feature archived 98.89% compared to 561 numbers of features 98.74% of overall accuracy for holdout method. While using the 10 cross validation method, the numbers of features are reduced to 424 with the overall accuracy 99.28% compared to 561 number of features with 99.22% of overall accuracy.","PeriodicalId":231004,"journal":{"name":"2019 IEEE Student Conference on Research and Development (SCOReD)","volume":"8 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129556754","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 : 2019-10-01DOI: 10.1109/SCORED.2019.8896309
Fadhil Mukhlif, Kholoud Maswadi, Kamarul Ariffin bin Noordin, Nader ale Ebrahim
The emerging field of green communication has quickly evolved with a geometric growth with respect to the amount of academic publications in this area. This paper aims to conduct an analysis of the green transmission literature in the field of communication during the past ten years through the use of rigorous bibliometric analysis tools. Furthermore, it highlights the future implications and directions for researchers, decision makers, and managers. The bibliometric analysis techniques were adopted for this study. This paper conducted a review of the articles that were published on green communications from the years 2007 to 2017. It determined the authors with the top contributions, as well as the sources and the leading countries that are linked to the field. Furthermore, it identified the main research topics in relation to this field. Academics and researchers were encouraged to explore this topic further. Despite the fact that the focus of this study is only on efficient communication vision in terms of green cooperation, other different aspects of this research area may also be explored by other researchers. Given the best of our knowledge, this study is the first to conduct a review on the available literature for green communication through the use of bibliometric analysis techniques. The study is distinct from others as it spans a prolong time frame of 10 years (2007–2017).
{"title":"Research Direction Based Green Communications for Next Era: A Bibliometric Analysis","authors":"Fadhil Mukhlif, Kholoud Maswadi, Kamarul Ariffin bin Noordin, Nader ale Ebrahim","doi":"10.1109/SCORED.2019.8896309","DOIUrl":"https://doi.org/10.1109/SCORED.2019.8896309","url":null,"abstract":"The emerging field of green communication has quickly evolved with a geometric growth with respect to the amount of academic publications in this area. This paper aims to conduct an analysis of the green transmission literature in the field of communication during the past ten years through the use of rigorous bibliometric analysis tools. Furthermore, it highlights the future implications and directions for researchers, decision makers, and managers. The bibliometric analysis techniques were adopted for this study. This paper conducted a review of the articles that were published on green communications from the years 2007 to 2017. It determined the authors with the top contributions, as well as the sources and the leading countries that are linked to the field. Furthermore, it identified the main research topics in relation to this field. Academics and researchers were encouraged to explore this topic further. Despite the fact that the focus of this study is only on efficient communication vision in terms of green cooperation, other different aspects of this research area may also be explored by other researchers. Given the best of our knowledge, this study is the first to conduct a review on the available literature for green communication through the use of bibliometric analysis techniques. The study is distinct from others as it spans a prolong time frame of 10 years (2007–2017).","PeriodicalId":231004,"journal":{"name":"2019 IEEE Student Conference on Research and Development (SCOReD)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130782846","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 : 2019-10-01DOI: 10.1109/SCORED.2019.8896289
P. Devan, F. Hussin, R. Ibrahim, Kishore Bingi, M. Nagarajapandian
This study was carried out to analyze the variations of hazardous pollutants like Carbon Monoxide (CO), Carbon Oxides (COx) and Nitrogen Oxides (NOx) in Tamil Nadu. The major source of air pollution in urban areas mainly in developing countries like India is due to the transportation sector. Road and Transportation Office (RTO) and Central Pollution Control Board (CPCB) are the monitoring authorities of the emission standards. This paper measures the emissions standards in a real-time process using various sensors namely smoke sensor which is placed at the exhaust of the vehicle. The data collected verifies the standard limits and provides information to the vehicle operator, RTO, and CPCB through the Global System for Mobile Communication (GSM) and the Internet of Things (IoT) for further analysis. The Indian government provides the Fitness Certificate (FC) for every vehicle by monitoring its behaviour. The control strategy coding for calculating the emitted gas limits has been done in PIC Microcontroller which analyzes the data and yields the statistics which are then compared with the standard values. Drivers and nearby control stations are provided with continuous feedback and warnings if the limits are exceeded. The Gas sensor is installed in the proposed control system by indicating the values provided in the Liquid Crystal Display (LCD).
{"title":"IoT Based Vehicle Emission Monitoring and Alerting System","authors":"P. Devan, F. Hussin, R. Ibrahim, Kishore Bingi, M. Nagarajapandian","doi":"10.1109/SCORED.2019.8896289","DOIUrl":"https://doi.org/10.1109/SCORED.2019.8896289","url":null,"abstract":"This study was carried out to analyze the variations of hazardous pollutants like Carbon Monoxide (CO), Carbon Oxides (COx) and Nitrogen Oxides (NOx) in Tamil Nadu. The major source of air pollution in urban areas mainly in developing countries like India is due to the transportation sector. Road and Transportation Office (RTO) and Central Pollution Control Board (CPCB) are the monitoring authorities of the emission standards. This paper measures the emissions standards in a real-time process using various sensors namely smoke sensor which is placed at the exhaust of the vehicle. The data collected verifies the standard limits and provides information to the vehicle operator, RTO, and CPCB through the Global System for Mobile Communication (GSM) and the Internet of Things (IoT) for further analysis. The Indian government provides the Fitness Certificate (FC) for every vehicle by monitoring its behaviour. The control strategy coding for calculating the emitted gas limits has been done in PIC Microcontroller which analyzes the data and yields the statistics which are then compared with the standard values. Drivers and nearby control stations are provided with continuous feedback and warnings if the limits are exceeded. The Gas sensor is installed in the proposed control system by indicating the values provided in the Liquid Crystal Display (LCD).","PeriodicalId":231004,"journal":{"name":"2019 IEEE Student Conference on Research and Development (SCOReD)","volume":"46 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122911330","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 : 2019-10-01DOI: 10.1109/SCORED.2019.8896335
Elango Natarajan, A.R. Venkataramanan, R. Sasikumar, S. Parasuraman, G. Kosalishkwaran
It is important to test all the functional modules of the space systems before it is being launched. The very stringent tests need to be conducted particularly for manned missions. The vibration is one of the most significant phenomena involved in testing of space systems. As the system faces periodic as well as random vibrations containing both high and low frequency components, testing its responses under the same type of vibration will help in making more realistic observations. Stewart-Gough type platform is the predominantly used platform to test space systems. The existing platforms are operated at low frequency and are capable of producing low frequency response only. In this paper, a single compliant leg is introduced in Stewart-Gough type platform. The respective model is developed and analyzed to investigate the effect of leg compliance on the dynamics of platform. It is to understand whether the compliant arrangement in the leg itself will generate required high frequency component along with the low frequency (generated by leg actuator) component or an additional high frequency actuation is required. The result shows that the top platform can generate an extra high frequency response at resonance conditions in addition to the low frequency response corresponding to the input which regarded a significant contribution to the system.
{"title":"Dynamic Analysis of Compliant LEG of a Stewart-Gough Type Parallel Mechanism","authors":"Elango Natarajan, A.R. Venkataramanan, R. Sasikumar, S. Parasuraman, G. Kosalishkwaran","doi":"10.1109/SCORED.2019.8896335","DOIUrl":"https://doi.org/10.1109/SCORED.2019.8896335","url":null,"abstract":"It is important to test all the functional modules of the space systems before it is being launched. The very stringent tests need to be conducted particularly for manned missions. The vibration is one of the most significant phenomena involved in testing of space systems. As the system faces periodic as well as random vibrations containing both high and low frequency components, testing its responses under the same type of vibration will help in making more realistic observations. Stewart-Gough type platform is the predominantly used platform to test space systems. The existing platforms are operated at low frequency and are capable of producing low frequency response only. In this paper, a single compliant leg is introduced in Stewart-Gough type platform. The respective model is developed and analyzed to investigate the effect of leg compliance on the dynamics of platform. It is to understand whether the compliant arrangement in the leg itself will generate required high frequency component along with the low frequency (generated by leg actuator) component or an additional high frequency actuation is required. The result shows that the top platform can generate an extra high frequency response at resonance conditions in addition to the low frequency response corresponding to the input which regarded a significant contribution to the system.","PeriodicalId":231004,"journal":{"name":"2019 IEEE Student Conference on Research and Development (SCOReD)","volume":"44 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122465381","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 : 2019-10-01DOI: 10.1109/SCORED.2019.8896284
A. Reindl, H. Meier, M. Niemetz
Conventional battery management systems typically adopt hierarchical master-slave architectures. With regard to an uninterruptible power supply, the most significant disadvantage of central structures is the dependency of the errorfree function of the superior master board. The decentralized battery management system presented in this paper, consisting of consumers, generators and intelligent battery cells, is controlled without any central coordination authority. For this purpose, an intelligent control algorithm and a leader election algorithm are implemented on the microcontrollers of the battery cells. To test different control and election strategies, a software framework is presented for the complete simulation of the decentralized battery management system consisting of equal participants.
{"title":"Software Framework for the Simulation of a Decentralized Battery Management System Consisting of Intelligent Battery Cells","authors":"A. Reindl, H. Meier, M. Niemetz","doi":"10.1109/SCORED.2019.8896284","DOIUrl":"https://doi.org/10.1109/SCORED.2019.8896284","url":null,"abstract":"Conventional battery management systems typically adopt hierarchical master-slave architectures. With regard to an uninterruptible power supply, the most significant disadvantage of central structures is the dependency of the errorfree function of the superior master board. The decentralized battery management system presented in this paper, consisting of consumers, generators and intelligent battery cells, is controlled without any central coordination authority. For this purpose, an intelligent control algorithm and a leader election algorithm are implemented on the microcontrollers of the battery cells. To test different control and election strategies, a software framework is presented for the complete simulation of the decentralized battery management system consisting of equal participants.","PeriodicalId":231004,"journal":{"name":"2019 IEEE Student Conference on Research and Development (SCOReD)","volume":"9 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123955224","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 : 2019-10-01DOI: 10.1109/SCORED.2019.8896271
N. K. Madzhi, N. E. Abdullah, M. H. bin Harun, Faridatul Aima Ismail
This paper presents an initial preservative latex measurement technique based on optical sensing. The previous technique used is based on laboratory method, which is the sample of latex need to undergo several laboratory experiments to determine the percentage of Dry Rubber Content (DRC) in a 100g sample of latex. Present-day, there is no portable technology available in the market that can be used to differentiate the electrical properties for the different rubber clones based on latex that can be used for in situ testing. By developing a portable device prototype, it will help farmer and agriculture officer to identify latex clone produced by the rubber tree. This project uses Near Infrared of 880nm and phototransistor of 900nm as signal transduction. The output from signal transduction circuit will go through three (3) stage amplification using two (2) types of LM358 and INA122P operational amplifier. After amplification, the signal will enter the Peripheral Interface Controller (PIC) and the output voltage from the testing process will be displayed. The tests conducted to obtained electrical properties of 30ml Latex 2008 sample are divided into three (3); that are initial testing, dilution test, and reproducibility test. The results obtained are tabulated in Microsoft Office Excel and the data produced are analyzed. As the dilution volume increased, the voltage produced decreased.
{"title":"Optical Sensing Technique Investigation for Preservative Latex Measurement","authors":"N. K. Madzhi, N. E. Abdullah, M. H. bin Harun, Faridatul Aima Ismail","doi":"10.1109/SCORED.2019.8896271","DOIUrl":"https://doi.org/10.1109/SCORED.2019.8896271","url":null,"abstract":"This paper presents an initial preservative latex measurement technique based on optical sensing. The previous technique used is based on laboratory method, which is the sample of latex need to undergo several laboratory experiments to determine the percentage of Dry Rubber Content (DRC) in a 100g sample of latex. Present-day, there is no portable technology available in the market that can be used to differentiate the electrical properties for the different rubber clones based on latex that can be used for in situ testing. By developing a portable device prototype, it will help farmer and agriculture officer to identify latex clone produced by the rubber tree. This project uses Near Infrared of 880nm and phototransistor of 900nm as signal transduction. The output from signal transduction circuit will go through three (3) stage amplification using two (2) types of LM358 and INA122P operational amplifier. After amplification, the signal will enter the Peripheral Interface Controller (PIC) and the output voltage from the testing process will be displayed. The tests conducted to obtained electrical properties of 30ml Latex 2008 sample are divided into three (3); that are initial testing, dilution test, and reproducibility test. The results obtained are tabulated in Microsoft Office Excel and the data produced are analyzed. As the dilution volume increased, the voltage produced decreased.","PeriodicalId":231004,"journal":{"name":"2019 IEEE Student Conference on Research and Development (SCOReD)","volume":"15 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125841158","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 : 2019-10-01DOI: 10.1109/SCORED.2019.8896336
M. Nagarajapandian, S. Kanthalakshmi, T. Anitha, P. Devan
In industries most of the process are non-linear in nature. Inorder to overcome this problem most of the industries modify the loop and make it as Single Input and Single Output (SISO) controllers to regulate such processes inorder to obtain the fast and quicker settling. But some processes with numerous variables causes lot of complexities, there is a high demand for designing a multivariable system in process industries. One such multivariable process is the quadruple tank systems which are a multivariable process. It is non-linear and dynamic, but the challenging task is to maintain the level of tanks due to the interaction between the process variable. This paper is based on using LMI (Linear Matrix inequalities) and Model Reference Adaptive control (MRAC) tuned PI controller for controlling the level of the four tanks. All the experimental results for various tanks are obtained using MATLAB software.
{"title":"Linear Matrix Inequality Based Controller used in Multivariable Systems","authors":"M. Nagarajapandian, S. Kanthalakshmi, T. Anitha, P. Devan","doi":"10.1109/SCORED.2019.8896336","DOIUrl":"https://doi.org/10.1109/SCORED.2019.8896336","url":null,"abstract":"In industries most of the process are non-linear in nature. Inorder to overcome this problem most of the industries modify the loop and make it as Single Input and Single Output (SISO) controllers to regulate such processes inorder to obtain the fast and quicker settling. But some processes with numerous variables causes lot of complexities, there is a high demand for designing a multivariable system in process industries. One such multivariable process is the quadruple tank systems which are a multivariable process. It is non-linear and dynamic, but the challenging task is to maintain the level of tanks due to the interaction between the process variable. This paper is based on using LMI (Linear Matrix inequalities) and Model Reference Adaptive control (MRAC) tuned PI controller for controlling the level of the four tanks. All the experimental results for various tanks are obtained using MATLAB software.","PeriodicalId":231004,"journal":{"name":"2019 IEEE Student Conference on Research and Development (SCOReD)","volume":"25 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115998904","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 : 2019-10-01DOI: 10.1109/SCORED.2019.8896244
M. K. Alam, A. Aziz, S. A. Latif, A. Awang
In wireless sensor networks (WSNs), plenty of sensor nodes are typically deployed in the field to provide a long-term monitoring facility. These sensor nodes are usually collect a huge amount of data over time. Transmitting the huge data from the sensor nodes to a sink introduces a big challenge to the network due to energy constraint of the sensor nodes. Therefore, many research efforts have been carried out so far to design efficient data clustering techniques for WSNs. The main purpose of these techniques is to reduce the amount of data over the network while retaining their fundamental properties. This paper aims to develop a Histogram-based Data Clustering (HDC) technique at the cluster-head (CH) for in-network data reduction. The HDC groups the homogeneous data into clusters and then performs in-network data reduction by selecting the central values (instead of all data points) of each cluster. Simulations on real-world sensor data show that the proposed HDC can effectively reduce a significant amount of redundant data and outperform existing techniques.
{"title":"Data Clustering Technique for In-Network Data Reduction in Wireless Sensor Network","authors":"M. K. Alam, A. Aziz, S. A. Latif, A. Awang","doi":"10.1109/SCORED.2019.8896244","DOIUrl":"https://doi.org/10.1109/SCORED.2019.8896244","url":null,"abstract":"In wireless sensor networks (WSNs), plenty of sensor nodes are typically deployed in the field to provide a long-term monitoring facility. These sensor nodes are usually collect a huge amount of data over time. Transmitting the huge data from the sensor nodes to a sink introduces a big challenge to the network due to energy constraint of the sensor nodes. Therefore, many research efforts have been carried out so far to design efficient data clustering techniques for WSNs. The main purpose of these techniques is to reduce the amount of data over the network while retaining their fundamental properties. This paper aims to develop a Histogram-based Data Clustering (HDC) technique at the cluster-head (CH) for in-network data reduction. The HDC groups the homogeneous data into clusters and then performs in-network data reduction by selecting the central values (instead of all data points) of each cluster. Simulations on real-world sensor data show that the proposed HDC can effectively reduce a significant amount of redundant data and outperform existing techniques.","PeriodicalId":231004,"journal":{"name":"2019 IEEE Student Conference on Research and Development (SCOReD)","volume":"73 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130322353","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 : 2019-10-01DOI: 10.1109/SCORED.2019.8896263
A. Yadav, V. Mahajan
As load demand is increasing, the existing power system network has to maintain its reliability. So to make system more reliable, FACTS devices are most commonly used in the system network. Here, Static Synchronous Compensator (STATCOM) load flow modelling is discussed to evaluate the total available capacity with each possible transmission line switching to determine the reliability condition of system network. Capacity outage probability is used to estimate the reliability indices with respect to line switching and switching rate. Individual and cumulative probability are evaluated according to available and unavailable units forced outage rate (FOR). Reliability indices EDNS and LOLP are compared with incorporation of STATCOM with respect to base case. Voltage profile is major concern in power system network. STATCOM is more preferable FACTS device used in the system network buses for improving the voltage profile and making the system more secure. The 24 bus IEEE Reliability Test System (IEEE-RTS-1979) is simulate for evaluation and contrast of the reliability and power flow parameter. Load flow with STATCOM gives better results in terms of improved voltage profile and reduction in loss.
{"title":"Transmission System Reliability Evaluation by Incorporating STATCOM in the System Network","authors":"A. Yadav, V. Mahajan","doi":"10.1109/SCORED.2019.8896263","DOIUrl":"https://doi.org/10.1109/SCORED.2019.8896263","url":null,"abstract":"As load demand is increasing, the existing power system network has to maintain its reliability. So to make system more reliable, FACTS devices are most commonly used in the system network. Here, Static Synchronous Compensator (STATCOM) load flow modelling is discussed to evaluate the total available capacity with each possible transmission line switching to determine the reliability condition of system network. Capacity outage probability is used to estimate the reliability indices with respect to line switching and switching rate. Individual and cumulative probability are evaluated according to available and unavailable units forced outage rate (FOR). Reliability indices EDNS and LOLP are compared with incorporation of STATCOM with respect to base case. Voltage profile is major concern in power system network. STATCOM is more preferable FACTS device used in the system network buses for improving the voltage profile and making the system more secure. The 24 bus IEEE Reliability Test System (IEEE-RTS-1979) is simulate for evaluation and contrast of the reliability and power flow parameter. Load flow with STATCOM gives better results in terms of improved voltage profile and reduction in loss.","PeriodicalId":231004,"journal":{"name":"2019 IEEE Student Conference on Research and Development (SCOReD)","volume":"91 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131192112","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 : 2019-10-01DOI: 10.1109/SCORED.2019.8896246
Al.maamoon Rasool Abdali, R. F. Ghani
The Detection of a fire in surveillance systems is playing a significant role to Reduce material and human losses, the effectiveness of fire detectors measured by the speed of response and the accuracy and the generality over different kinds of video sources with a different format. Several studies worked on fire detection. Also, there is several benchmarking dataset, even though all available datasets are not large enough to build a robust real-world fire detector. In this paper, we proposed a real-time fire detector based on deep-learning, the model consists of Convolutional neural network (CNN) as spatial feature extractor and Long short-term memory (LSTM) as temporal relation learning method with a focus on the three-factor (overall generality - accuracy - fast response time) the proposed model achieved accuracy of 95.39% with a speed of 120 frames/sec based on extended dataset from the available data sets. The accuracy and the speed of the proposed model have been compared to previous works, shows that the proposed model has the highest accuracy and the fastest speed among all the previous works in the field of fire detection.
{"title":"Robust Real-Time Fire Detector Using CNN And LSTM","authors":"Al.maamoon Rasool Abdali, R. F. Ghani","doi":"10.1109/SCORED.2019.8896246","DOIUrl":"https://doi.org/10.1109/SCORED.2019.8896246","url":null,"abstract":"The Detection of a fire in surveillance systems is playing a significant role to Reduce material and human losses, the effectiveness of fire detectors measured by the speed of response and the accuracy and the generality over different kinds of video sources with a different format. Several studies worked on fire detection. Also, there is several benchmarking dataset, even though all available datasets are not large enough to build a robust real-world fire detector. In this paper, we proposed a real-time fire detector based on deep-learning, the model consists of Convolutional neural network (CNN) as spatial feature extractor and Long short-term memory (LSTM) as temporal relation learning method with a focus on the three-factor (overall generality - accuracy - fast response time) the proposed model achieved accuracy of 95.39% with a speed of 120 frames/sec based on extended dataset from the available data sets. The accuracy and the speed of the proposed model have been compared to previous works, shows that the proposed model has the highest accuracy and the fastest speed among all the previous works in the field of fire detection.","PeriodicalId":231004,"journal":{"name":"2019 IEEE Student Conference on Research and Development (SCOReD)","volume":"33 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131537054","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：