Pub Date : 2018-08-01DOI: 10.1109/ICSGRC.2018.8657574
K. Zainuddin, Z. Majid, Mohd Farid Mohd Ariff, K. M. Idris
The recent development of lightweight and small multispectral cameras has allowed the multispectral imagery acquired from either drone or terrestrial platform. A variety of multispectral sensors in the market are mostly designed for agriculture applications, nevertheless, gives benefits to different field such as cultural heritage which recording and documenting the object in the visible and invisible wavelengths. This paper describes the extraction of the geometric parameters of the lightweight multispectral camera, which calibrated using photogrammetric self-calibration bundle adjustment technique. The results show the variation of calibrated parameters, due to the different wavelengths. The elements of interior orientation parameters across all bands, and the consistency of the radial distortion coefficient also tested with statistics to show the significance of the calibrated parameter for photogrammetric applications.
{"title":"Lightweight Multispectral Camera Calibration for Photogrammetric Applications","authors":"K. Zainuddin, Z. Majid, Mohd Farid Mohd Ariff, K. M. Idris","doi":"10.1109/ICSGRC.2018.8657574","DOIUrl":"https://doi.org/10.1109/ICSGRC.2018.8657574","url":null,"abstract":"The recent development of lightweight and small multispectral cameras has allowed the multispectral imagery acquired from either drone or terrestrial platform. A variety of multispectral sensors in the market are mostly designed for agriculture applications, nevertheless, gives benefits to different field such as cultural heritage which recording and documenting the object in the visible and invisible wavelengths. This paper describes the extraction of the geometric parameters of the lightweight multispectral camera, which calibrated using photogrammetric self-calibration bundle adjustment technique. The results show the variation of calibrated parameters, due to the different wavelengths. The elements of interior orientation parameters across all bands, and the consistency of the radial distortion coefficient also tested with statistics to show the significance of the calibrated parameter for photogrammetric applications.","PeriodicalId":147027,"journal":{"name":"2018 9th IEEE Control and System Graduate Research Colloquium (ICSGRC)","volume":"88 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125087857","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 : 2018-08-01DOI: 10.1109/ICSGRC.2018.8657589
Mohd Firdaus Omar, I. M. Saadon, R. Ghazali, M. Aripin, C. C. Soon
Nowadays the Sport Utility Vehicle (SUV) become more popular than sedan car around the world even in Malaysia. But, these types of vehicles have weaknesses such as higher center of gravity, heavier, side area and wheel base are larger than sedan car that lead to unstable vehicle handling during critical maneuver. Numerous researchers have proposed their control strategy in order to overcome this problem. However, there are less studies about the Linear Quadratic Integral (LQI) controller especially in the Direct Yaw Control (DYC) system. Therefore, in this paper, the development of the LQI controllers implemented in the DYC is researched and compared with Linear Quadratic Regulator (LQR) and Proportional-Integral-Derivative (PID) controller for the performances evaluation. Each controller optimized using Particle Swarm Optimization (PSO) algorithm and tested on lane change maneuver with interference of external disturbance and different road condition. With the help of PSO algorithm, the LQI controllers not only produce significant improvement in the lane change maneuver but the controller is more precise, faster tuning gains, robust against external disturbance and capable to endurance the maneuver with lower Root Mean Square Error (RMSE) compare with two other controllers.
{"title":"Optimal Direct Yaw Control for Sport Utility Vehicle Using PSO","authors":"Mohd Firdaus Omar, I. M. Saadon, R. Ghazali, M. Aripin, C. C. Soon","doi":"10.1109/ICSGRC.2018.8657589","DOIUrl":"https://doi.org/10.1109/ICSGRC.2018.8657589","url":null,"abstract":"Nowadays the Sport Utility Vehicle (SUV) become more popular than sedan car around the world even in Malaysia. But, these types of vehicles have weaknesses such as higher center of gravity, heavier, side area and wheel base are larger than sedan car that lead to unstable vehicle handling during critical maneuver. Numerous researchers have proposed their control strategy in order to overcome this problem. However, there are less studies about the Linear Quadratic Integral (LQI) controller especially in the Direct Yaw Control (DYC) system. Therefore, in this paper, the development of the LQI controllers implemented in the DYC is researched and compared with Linear Quadratic Regulator (LQR) and Proportional-Integral-Derivative (PID) controller for the performances evaluation. Each controller optimized using Particle Swarm Optimization (PSO) algorithm and tested on lane change maneuver with interference of external disturbance and different road condition. With the help of PSO algorithm, the LQI controllers not only produce significant improvement in the lane change maneuver but the controller is more precise, faster tuning gains, robust against external disturbance and capable to endurance the maneuver with lower Root Mean Square Error (RMSE) compare with two other controllers.","PeriodicalId":147027,"journal":{"name":"2018 9th IEEE Control and System Graduate Research Colloquium (ICSGRC)","volume":"270 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115887744","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 : 2018-08-01DOI: 10.1109/ICSGRC.2018.8657494
S. S. Sarnin, M. Yusof, M. Mohamad, W. N. W. Mohamad, N. F. Naim, N. Ya'acob
The project proposal is to support the Mobile Subscribers (MS) demand during the major event held in closed environment such as stadium. As usual, the high data usage is the major contribution to the network congestion for every Mobile Network Operators (MNOs) during high crowd. MNOs have to dimension their network according to their strategy(s) over the Grade of Service (GoS) in order to ensure their MS enjoy their network services. This proposal paper will focus on the providing the best solution for MNOs to ease the high congestion via Multibeam RF Antenna solution. Besides other solutions such as IBC (In-Building Coverage), Small Cells and Wi-Fi, the proposed solution, Multibeam RF Antenna solution is chosen as it is fast in deployment, good network quality and cost effective compared to others. The statistics analysis, coverage prediction studies, combining method and cost efficiency studies will be the main focus to ensure the effectiveness of the proposed solution.
{"title":"Multibeam RF Antenna Solution for Capacity Enhancement in Stadium Shah Alam","authors":"S. S. Sarnin, M. Yusof, M. Mohamad, W. N. W. Mohamad, N. F. Naim, N. Ya'acob","doi":"10.1109/ICSGRC.2018.8657494","DOIUrl":"https://doi.org/10.1109/ICSGRC.2018.8657494","url":null,"abstract":"The project proposal is to support the Mobile Subscribers (MS) demand during the major event held in closed environment such as stadium. As usual, the high data usage is the major contribution to the network congestion for every Mobile Network Operators (MNOs) during high crowd. MNOs have to dimension their network according to their strategy(s) over the Grade of Service (GoS) in order to ensure their MS enjoy their network services. This proposal paper will focus on the providing the best solution for MNOs to ease the high congestion via Multibeam RF Antenna solution. Besides other solutions such as IBC (In-Building Coverage), Small Cells and Wi-Fi, the proposed solution, Multibeam RF Antenna solution is chosen as it is fast in deployment, good network quality and cost effective compared to others. The statistics analysis, coverage prediction studies, combining method and cost efficiency studies will be the main focus to ensure the effectiveness of the proposed solution.","PeriodicalId":147027,"journal":{"name":"2018 9th IEEE Control and System Graduate Research Colloquium (ICSGRC)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125505689","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 : 2018-08-01DOI: 10.1109/ICSGRC.2018.8657627
Suhaizal Hashim, Mohd Erfy Ismail, A. Masek, Affero Ismail, Nizamuddin Razali
Ergonomic interpreted as a discipline in science and technology that aims to alter the use of work equipment, the design of the workplace, the environment and ways of working in accordance with the limits as well as physical and mental capabilities of the workers. Recently, many studies mentioned that improper habit of computer usage causes problems such as a repetitive strain injury (RSI). Thus, this study is about a survey on the level of teacher knowledge about ergonomics and negative effects faced by students for those who were using computers in school computer laboratory. Questionnaires were used as a research instrument. This study involved 30 subjects consist of teachers who were using computer labs for teaching and learning from several schools in Johor Bahru, Malaysia. Data were analyzed using mean, frequencies and percentages. The result shows that these teachers have a high level of ergonomics knowledge about computer workstation in the school computer lab and a moderate level of knowledge about the physical ergonomic position while using the computer. Also, the study identified the average level of negative effects faced by students while using computers in school computer laboratory.
{"title":"Ergonomics in School Computer Lab: A Malaysian Teachers' Perspective","authors":"Suhaizal Hashim, Mohd Erfy Ismail, A. Masek, Affero Ismail, Nizamuddin Razali","doi":"10.1109/ICSGRC.2018.8657627","DOIUrl":"https://doi.org/10.1109/ICSGRC.2018.8657627","url":null,"abstract":"Ergonomic interpreted as a discipline in science and technology that aims to alter the use of work equipment, the design of the workplace, the environment and ways of working in accordance with the limits as well as physical and mental capabilities of the workers. Recently, many studies mentioned that improper habit of computer usage causes problems such as a repetitive strain injury (RSI). Thus, this study is about a survey on the level of teacher knowledge about ergonomics and negative effects faced by students for those who were using computers in school computer laboratory. Questionnaires were used as a research instrument. This study involved 30 subjects consist of teachers who were using computer labs for teaching and learning from several schools in Johor Bahru, Malaysia. Data were analyzed using mean, frequencies and percentages. The result shows that these teachers have a high level of ergonomics knowledge about computer workstation in the school computer lab and a moderate level of knowledge about the physical ergonomic position while using the computer. Also, the study identified the average level of negative effects faced by students while using computers in school computer laboratory.","PeriodicalId":147027,"journal":{"name":"2018 9th IEEE Control and System Graduate Research Colloquium (ICSGRC)","volume":"34 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121669605","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 : 2018-08-01DOI: 10.1109/ICSGRC.2018.8657514
N. Razali, N. Abdul Ghani, N. F. Jamin, M. Masrom
Existing control techniques of mobile robot specifically for four to two wheeled wheelchair transformation are lack of adequate mobility, comfort and independence for their users due to highly nonlinear and complex system. This paper presents a four to two wheeled wheelchair transformation system that based on the fundamental of double-link inverted pendulum. SimWise 4D CAD software is used to model and visualize the system movement while evaluating Matlab. This CAD software is integrated with Matlab/Simulink for designing control algorithm. In this work, the controller used to perform transformation and balancing the wheelchair is IT2FLC. It shows that IT2FLC produce better result in terms of lifting and stabilizing the wheelchair in an upright position compared to previous Fuzzy Logic Type-l control.
{"title":"Stability Control of Wheelchair System Using Interval Type-2 Fuzzy Logic Control (IT2FLC)","authors":"N. Razali, N. Abdul Ghani, N. F. Jamin, M. Masrom","doi":"10.1109/ICSGRC.2018.8657514","DOIUrl":"https://doi.org/10.1109/ICSGRC.2018.8657514","url":null,"abstract":"Existing control techniques of mobile robot specifically for four to two wheeled wheelchair transformation are lack of adequate mobility, comfort and independence for their users due to highly nonlinear and complex system. This paper presents a four to two wheeled wheelchair transformation system that based on the fundamental of double-link inverted pendulum. SimWise 4D CAD software is used to model and visualize the system movement while evaluating Matlab. This CAD software is integrated with Matlab/Simulink for designing control algorithm. In this work, the controller used to perform transformation and balancing the wheelchair is IT2FLC. It shows that IT2FLC produce better result in terms of lifting and stabilizing the wheelchair in an upright position compared to previous Fuzzy Logic Type-l control.","PeriodicalId":147027,"journal":{"name":"2018 9th IEEE Control and System Graduate Research Colloquium (ICSGRC)","volume":"3 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127224641","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 : 2018-08-01DOI: 10.1109/ICSGRC.2018.8657603
Norfarahin Mohd Yusoff, Ili Shairah Abdul Halim, N. E. Abdullah, A'zraa Afhzan Ab. Rahim
Real-time image processing is related with typical frame rate that required processing all the frames as soon as the image is captured. Fast processing time is required for edge detection since it is needed to be carry out in a real time. This paper proposes a real-time edge detection technique for identifying Hevea leaves diseases (rubber tree leaves) in images and its hardware implementation. Three major Hevea leaves diseases which are Corynespora Leaf Spot, Bird's Eye Leaf Spot and Collectotrichum Leaf Disease used in this study for image comparison. The disease on the leaves can be detected through edge detection by using Sobel edge detection algorithm. The realtime edge detection result generated by FPGA Cyclone IV E which is displayed through a monitor is compared to Sobel edge detection algorithm that is generated with MATLAB. The algorithm has been implemented on FPGA and the image results on the VGA monitor are similar as the simulation on the MATLAB.
实时图像处理与典型的帧率有关，它要求在捕获图像后立即处理所有帧。由于边缘检测需要实时进行，因此需要快速的处理时间。提出了一种橡胶树叶片病害图像的实时边缘检测技术及其硬件实现。本研究采用三种主要的橡胶树叶片病害Corynespora叶斑病、Bird’s Eye叶斑病和Collectotrichum叶斑病进行图像比较。利用Sobel边缘检测算法，通过边缘检测来检测叶片上的病害。将FPGA Cyclone IV E生成的实时边缘检测结果通过显示器显示，与MATLAB生成的Sobel边缘检测算法进行比较。该算法已在FPGA上实现，VGA显示器上的图像结果与MATLAB仿真结果相似。
{"title":"Real-time Hevea Leaves Diseases Identification using Sobel Edge Algorithm on FPGA: A Preliminary Study","authors":"Norfarahin Mohd Yusoff, Ili Shairah Abdul Halim, N. E. Abdullah, A'zraa Afhzan Ab. Rahim","doi":"10.1109/ICSGRC.2018.8657603","DOIUrl":"https://doi.org/10.1109/ICSGRC.2018.8657603","url":null,"abstract":"Real-time image processing is related with typical frame rate that required processing all the frames as soon as the image is captured. Fast processing time is required for edge detection since it is needed to be carry out in a real time. This paper proposes a real-time edge detection technique for identifying Hevea leaves diseases (rubber tree leaves) in images and its hardware implementation. Three major Hevea leaves diseases which are Corynespora Leaf Spot, Bird's Eye Leaf Spot and Collectotrichum Leaf Disease used in this study for image comparison. The disease on the leaves can be detected through edge detection by using Sobel edge detection algorithm. The realtime edge detection result generated by FPGA Cyclone IV E which is displayed through a monitor is compared to Sobel edge detection algorithm that is generated with MATLAB. The algorithm has been implemented on FPGA and the image results on the VGA monitor are similar as the simulation on the MATLAB.","PeriodicalId":147027,"journal":{"name":"2018 9th IEEE Control and System Graduate Research Colloquium (ICSGRC)","volume":"5 3 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127452694","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 : 2018-08-01DOI: 10.1109/ICSGRC.2018.8657592
Nurbaity Sabri, Joveni Henry, Z. Ibrahim, Nurulhuda Ghazali, N. N. Abu Mangshor, Nur Farahin Mohd Johari, Shafaf Ibrahim
Due to the increasing crime rate in Malaysia, the safety and security need to be robust from the intruders. Numerous biometric-based technologies are offered but they are not friendly and less accurate. Among the available biometric technology, face recognition is the friendliest among all the technology. Hence, the aim of this research is to identify the best classifier for face recognition using facial geometry distance measure. A comparison between Support Vector Machine (SVM), Multi Linear Perceptron (MLP) and Naïve Bayes classifiers is conducted in classifying human face using facial geometry distance measures features. Experimental result shows Naïve Bayes obtained the high accuracy with 93.16% with less build time compared to MLP and SVM classifier. For future work, more person face images will be added into database for face recognition using the highest classifier achieves in this research.
{"title":"A Comparison of Face Detection Classifier using Facial Geometry Distance Measure","authors":"Nurbaity Sabri, Joveni Henry, Z. Ibrahim, Nurulhuda Ghazali, N. N. Abu Mangshor, Nur Farahin Mohd Johari, Shafaf Ibrahim","doi":"10.1109/ICSGRC.2018.8657592","DOIUrl":"https://doi.org/10.1109/ICSGRC.2018.8657592","url":null,"abstract":"Due to the increasing crime rate in Malaysia, the safety and security need to be robust from the intruders. Numerous biometric-based technologies are offered but they are not friendly and less accurate. Among the available biometric technology, face recognition is the friendliest among all the technology. Hence, the aim of this research is to identify the best classifier for face recognition using facial geometry distance measure. A comparison between Support Vector Machine (SVM), Multi Linear Perceptron (MLP) and Naïve Bayes classifiers is conducted in classifying human face using facial geometry distance measures features. Experimental result shows Naïve Bayes obtained the high accuracy with 93.16% with less build time compared to MLP and SVM classifier. For future work, more person face images will be added into database for face recognition using the highest classifier achieves in this research.","PeriodicalId":147027,"journal":{"name":"2018 9th IEEE Control and System Graduate Research Colloquium (ICSGRC)","volume":"58 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133214998","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 : 2018-08-01DOI: 10.1109/ICSGRC.2018.8657542
Mohammed Sultan Mohammed, J. Tang, Ab Al-Hadi Ab Rahman, Norlina Paraman, M. N. Marsono
Most existing works on application mapping for Multiprocessor System-on-Chip (MPSoC) use either simulation or analytical modeling to evaluate their mapping solutions. However, the use of these evaluation approaches is not as accurate as prototyping on a real MPSoC system. Rapid prototyping on a reconfigurable logic platform for design space exploration is also not trivial as tasks have to be developed ground-up. This paper proposes a development environment for fast NoC-based MPSoC application prototyping. A conversion method called CAL2NoC is proposed to convert a high-level dataflow model of real-world applications to multiple executable C codes (tasks). These application tasks are executed on emulated Network-on-Chip (NoC) based MPSoC platform and run-time performance traces are collected. CAL2NoC facilitates prototype-based design space exploration for real-world applications using emulated MPSoC platform for practical performance evaluation. As a proof-of-concept, JPEG encoder is profiled using the proposed method. It has been shown that the proposed method facilitates a rapid development of emulated MPSoC for accurate application mapping evaluation.
{"title":"Rapid Prototyping of NoC-based MPSoC Based on Dataflow Modeling of Real-World Applications","authors":"Mohammed Sultan Mohammed, J. Tang, Ab Al-Hadi Ab Rahman, Norlina Paraman, M. N. Marsono","doi":"10.1109/ICSGRC.2018.8657542","DOIUrl":"https://doi.org/10.1109/ICSGRC.2018.8657542","url":null,"abstract":"Most existing works on application mapping for Multiprocessor System-on-Chip (MPSoC) use either simulation or analytical modeling to evaluate their mapping solutions. However, the use of these evaluation approaches is not as accurate as prototyping on a real MPSoC system. Rapid prototyping on a reconfigurable logic platform for design space exploration is also not trivial as tasks have to be developed ground-up. This paper proposes a development environment for fast NoC-based MPSoC application prototyping. A conversion method called CAL2NoC is proposed to convert a high-level dataflow model of real-world applications to multiple executable C codes (tasks). These application tasks are executed on emulated Network-on-Chip (NoC) based MPSoC platform and run-time performance traces are collected. CAL2NoC facilitates prototype-based design space exploration for real-world applications using emulated MPSoC platform for practical performance evaluation. As a proof-of-concept, JPEG encoder is profiled using the proposed method. It has been shown that the proposed method facilitates a rapid development of emulated MPSoC for accurate application mapping evaluation.","PeriodicalId":147027,"journal":{"name":"2018 9th IEEE Control and System Graduate Research Colloquium (ICSGRC)","volume":"40 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131024733","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 : 2018-08-01DOI: 10.1109/ICSGRC.2018.8657634
N. Jamal, M. Sulaiman, O. Aliman, Z. Mustaffa, M. Mustafa
Recently, nature inspired algorithms (NIA) have been implemented to various fields of optimization problem such as biomedical engineering, electrical engineering, computer science and etc. The achievement of NIA in solving optimization in these fields becoming the motivation to apply one of the NIA namely Grey Wolf Optimizer (GWO) into overcurrent relay coordination problem. However, the current state of GWO suffers lack of exploration problem. Hence, the improvement of GWO has been proposed in this paper to enhance the exploration of original GWO. The improvement of GWO (IGWO) is implemented in finding the the optimal value of the Time Multiplier Setting (TMS) and Plug Setting (PS) in order to minimize the primary relays' operating time at the near end fault. Comprehensive simulation studies have been performed to demonstrate the reliability and efficiency of the proposed modification technique compared to the original GWO. The generated results have confirmed the proposed IGWO is able to improve the objective function of the overcurrent relay coordination problem.
{"title":"Improved Grey Wolf Optimization Algorithm for Overcurrent Relays Coordination","authors":"N. Jamal, M. Sulaiman, O. Aliman, Z. Mustaffa, M. Mustafa","doi":"10.1109/ICSGRC.2018.8657634","DOIUrl":"https://doi.org/10.1109/ICSGRC.2018.8657634","url":null,"abstract":"Recently, nature inspired algorithms (NIA) have been implemented to various fields of optimization problem such as biomedical engineering, electrical engineering, computer science and etc. The achievement of NIA in solving optimization in these fields becoming the motivation to apply one of the NIA namely Grey Wolf Optimizer (GWO) into overcurrent relay coordination problem. However, the current state of GWO suffers lack of exploration problem. Hence, the improvement of GWO has been proposed in this paper to enhance the exploration of original GWO. The improvement of GWO (IGWO) is implemented in finding the the optimal value of the Time Multiplier Setting (TMS) and Plug Setting (PS) in order to minimize the primary relays' operating time at the near end fault. Comprehensive simulation studies have been performed to demonstrate the reliability and efficiency of the proposed modification technique compared to the original GWO. The generated results have confirmed the proposed IGWO is able to improve the objective function of the overcurrent relay coordination problem.","PeriodicalId":147027,"journal":{"name":"2018 9th IEEE Control and System Graduate Research Colloquium (ICSGRC)","volume":"64 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115580584","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 : 2018-08-01DOI: 10.1109/ICSGRC.2018.8657535
M. Lim, Joon Huang Chuah
Fruit or plant recognition is a very pragmatic and specific application of deep-learning technique. As compared to conventional method, the technique requires a larger quantity of data for training while at the same time promises a higher level of accuracy. Among various classes of neural network, convolutional neural network (CNN) is arguably the most commonly used method in image classification. The aim of this research work is to develop an effective method to classify the various cultivars of Durio zibethinus (or commonly known as durian) based on the crop's visual features via the application of CNN to improve the accuracy and speed of the cultivars recognition. Meanwhile, a reliable database consisting of labelled durian cultivars has been created. A total of 800 images consisting of the bottom view of 3 classes of cultivars and non-durian images are used during the training process of the neural network. The research work starts with the pre-processing and conversion of the images then followed by one-hot labelling of the data, construction of the network architecture, training and validation of the model then lastly exporting the trained model for general application. Important system parameters and prediction accuracy are obtained, including the graphs of loss function and accuracy against the number of epochs, confusion matrix, miss-classified images, the effect of network architecture on prediction performance, etc. The prediction accuracy of the trained model on the perfect bottom-view images of Durio zibethinus is 82.50%. With the addition of non-durian images, the prediction accuracy is slightly dropped to 81.25%.
{"title":"Durian Types Recognition Using Deep Learning Techniques","authors":"M. Lim, Joon Huang Chuah","doi":"10.1109/ICSGRC.2018.8657535","DOIUrl":"https://doi.org/10.1109/ICSGRC.2018.8657535","url":null,"abstract":"Fruit or plant recognition is a very pragmatic and specific application of deep-learning technique. As compared to conventional method, the technique requires a larger quantity of data for training while at the same time promises a higher level of accuracy. Among various classes of neural network, convolutional neural network (CNN) is arguably the most commonly used method in image classification. The aim of this research work is to develop an effective method to classify the various cultivars of Durio zibethinus (or commonly known as durian) based on the crop's visual features via the application of CNN to improve the accuracy and speed of the cultivars recognition. Meanwhile, a reliable database consisting of labelled durian cultivars has been created. A total of 800 images consisting of the bottom view of 3 classes of cultivars and non-durian images are used during the training process of the neural network. The research work starts with the pre-processing and conversion of the images then followed by one-hot labelling of the data, construction of the network architecture, training and validation of the model then lastly exporting the trained model for general application. Important system parameters and prediction accuracy are obtained, including the graphs of loss function and accuracy against the number of epochs, confusion matrix, miss-classified images, the effect of network architecture on prediction performance, etc. The prediction accuracy of the trained model on the perfect bottom-view images of Durio zibethinus is 82.50%. With the addition of non-durian images, the prediction accuracy is slightly dropped to 81.25%.","PeriodicalId":147027,"journal":{"name":"2018 9th IEEE Control and System Graduate Research Colloquium (ICSGRC)","volume":"113 ","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"120979845","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：