Pub Date : 2017-10-01DOI: 10.1109/ICSENGT.2017.8123414
H. A. Nugroho, M. Rahmawaty, Yuli Triyani, I. Ardiyanto, L. Choridah, Reni Indrastuti
Ultrasound is one of the imaging modalities commonly used for detecting mass abnormalities of nodule. The observation of ultrasound images is conducted by the radiologists, which tend to be subjective. Therefore, the use of computer aided diagnosis (CADx) system based on image processing can assist the radiologists to give more objective decision-making for detecting the mass abnormalities of nodule. This study proposes an approach to identify echo pattern characteristic of nodule by analysing some extracted texture features. A total of 343 ultrasound images consisting of 191 solid and 152 cystic nodules are used in this study. Three classifiers, namely Naïve Bayes, support vector machine (SVM) and multilayer perceptron (MLP) classifier are involved to measure the performance of proposed approach. Generally, MLP classifier achieves the best performance in classifying nodule with the accuracy of 93.00%, Kappa of 0.86 and AUC of 0.974. These results show that the proposed approach successfully identifies echo pattern characteristic of cystic and solid nodules on the ultrasound images.
{"title":"Texture analysis and classification in ultrasound medical images for determining echo pattern characteristics","authors":"H. A. Nugroho, M. Rahmawaty, Yuli Triyani, I. Ardiyanto, L. Choridah, Reni Indrastuti","doi":"10.1109/ICSENGT.2017.8123414","DOIUrl":"https://doi.org/10.1109/ICSENGT.2017.8123414","url":null,"abstract":"Ultrasound is one of the imaging modalities commonly used for detecting mass abnormalities of nodule. The observation of ultrasound images is conducted by the radiologists, which tend to be subjective. Therefore, the use of computer aided diagnosis (CADx) system based on image processing can assist the radiologists to give more objective decision-making for detecting the mass abnormalities of nodule. This study proposes an approach to identify echo pattern characteristic of nodule by analysing some extracted texture features. A total of 343 ultrasound images consisting of 191 solid and 152 cystic nodules are used in this study. Three classifiers, namely Naïve Bayes, support vector machine (SVM) and multilayer perceptron (MLP) classifier are involved to measure the performance of proposed approach. Generally, MLP classifier achieves the best performance in classifying nodule with the accuracy of 93.00%, Kappa of 0.86 and AUC of 0.974. These results show that the proposed approach successfully identifies echo pattern characteristic of cystic and solid nodules on the ultrasound images.","PeriodicalId":350572,"journal":{"name":"2017 7th IEEE International Conference on System Engineering and Technology (ICSET)","volume":"38 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129818321","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 : 2017-10-01DOI: 10.1109/ICSENGT.2017.8123420
Sohail Sarang, M. Drieberg, A. Awang
Wireless Sensor Networks (WSNs) have gained significant attention due to their wide range of applications. In these networks, the sensor nodes collect different types of data from the surrounding environment. There are many applications that require sensor node to transmit urgent data packets faster than normal data packets. In the literature, most of the available medium access control (MAC) protocols have not considered quality-of-service (QoS) and have not addressed multi-priority of the data packets. In this paper, a multi-priority based MAC protocol is proposed, which provides QoS in WSNs, called MPQ-MAC protocol. In the MPQ-MAC protocol, a novel technique is proposed to reduce the delay and energy consumption in the network. Furthermore, the performance of the MPQ-MAC protocol has been evaluated in terms of average delay for priority data packets, energy consumption per node, packet delay, network throughput and packet delivery ratio using Castalia simulator. Simulation results show that the proposed protocol reduces the delay for priority data packet of up to 46.5% and energy consumption per node of up to 1.7% while maintaining network throughput and packet delivery ratio in the network.
{"title":"Multi-priority based QoS MAC protocol for wireless sensor networks","authors":"Sohail Sarang, M. Drieberg, A. Awang","doi":"10.1109/ICSENGT.2017.8123420","DOIUrl":"https://doi.org/10.1109/ICSENGT.2017.8123420","url":null,"abstract":"Wireless Sensor Networks (WSNs) have gained significant attention due to their wide range of applications. In these networks, the sensor nodes collect different types of data from the surrounding environment. There are many applications that require sensor node to transmit urgent data packets faster than normal data packets. In the literature, most of the available medium access control (MAC) protocols have not considered quality-of-service (QoS) and have not addressed multi-priority of the data packets. In this paper, a multi-priority based MAC protocol is proposed, which provides QoS in WSNs, called MPQ-MAC protocol. In the MPQ-MAC protocol, a novel technique is proposed to reduce the delay and energy consumption in the network. Furthermore, the performance of the MPQ-MAC protocol has been evaluated in terms of average delay for priority data packets, energy consumption per node, packet delay, network throughput and packet delivery ratio using Castalia simulator. Simulation results show that the proposed protocol reduces the delay for priority data packet of up to 46.5% and energy consumption per node of up to 1.7% while maintaining network throughput and packet delivery ratio in the network.","PeriodicalId":350572,"journal":{"name":"2017 7th IEEE International Conference on System Engineering and Technology (ICSET)","volume":"73 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128944037","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 : 2017-10-01DOI: 10.1109/ICSENGT.2017.8123443
Raseeda Hamzah, N. Jamil, K. A. Samah, Nur Nabilah Abu Mangshor, Nurbaity Sabri, Rosniza Roslan
Speech emotion recognition has been widely used in human computer interaction and applications. This paper has classified emotion into two classes: happy and angry. All the speech signal is preprocessed from Malay spoken speech database. Emotional information is obtained by applying two well-established acoustical features that are Mel Frequency Cepstral Coefficients (MFCC) and Short Time Energy (STE). The performance of the classification is done by comparing four types of classifiers which are Naïve Bayes, Multi-Layer Perceptron (MLP), C4.5 and Random Forest. Result shows that Random Forest has achieved the highest accuracy of ∼90% exceeding C4.5, Multilayer Perceptron (MLP) and Naïve Bayes. Naïve Bayes shows the lowest score of ∼76% accuracy.
{"title":"Comparing statistical classifiers for emotion classification","authors":"Raseeda Hamzah, N. Jamil, K. A. Samah, Nur Nabilah Abu Mangshor, Nurbaity Sabri, Rosniza Roslan","doi":"10.1109/ICSENGT.2017.8123443","DOIUrl":"https://doi.org/10.1109/ICSENGT.2017.8123443","url":null,"abstract":"Speech emotion recognition has been widely used in human computer interaction and applications. This paper has classified emotion into two classes: happy and angry. All the speech signal is preprocessed from Malay spoken speech database. Emotional information is obtained by applying two well-established acoustical features that are Mel Frequency Cepstral Coefficients (MFCC) and Short Time Energy (STE). The performance of the classification is done by comparing four types of classifiers which are Naïve Bayes, Multi-Layer Perceptron (MLP), C4.5 and Random Forest. Result shows that Random Forest has achieved the highest accuracy of ∼90% exceeding C4.5, Multilayer Perceptron (MLP) and Naïve Bayes. Naïve Bayes shows the lowest score of ∼76% accuracy.","PeriodicalId":350572,"journal":{"name":"2017 7th IEEE International Conference on System Engineering and Technology (ICSET)","volume":"54 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122051550","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 : 2017-10-01DOI: 10.1109/ICSENGT.2017.8123445
M. A. Nugroho, A. Sepri, R. Benyamin, B. Trilaksono, Agoes Moelyadi
Flapping Wings Micro Aerial Vehicle (FWMAV) is developed from MAV (Micro Aerial Vehicle) technology, which uses flapping wing mechanism to fly rather than rotors. MAV itself is a branch of UAV (Unmanned Aerial Vehicle) technology, and focuses on minimizing size and weight of the aircraft. Ganefly is an FWMAV with capability to fly autonomously based on GPS readings and waypoints input from the user. This autopilot system works in conjunction with other parts of the control systems in Ganefly, which also includes attitude stabilization system. Ganefly uses yaw control loop for horizontal attitude stabilization, because Ganefly does not use aileron to control roll, unlike usual aircrafts. The stabilization system is implemented using standard PID control and Paparazzi UAV firmware, on a Lisa/S autopilot board. Testing for stabilization system was done in Manual and Stabilization mode, and testing for autopilot mode was done in Autopilot mode. Results gathered from testing indicate that Ganefly in its flight is not horizontally stable in both Manual and Stabilization mode, and thus was not able to be tested on Autopilot mode.
{"title":"Design and implementation of attitude stabilization on Ganefly flapping wings micro aerial vehicle using Paparazzi","authors":"M. A. Nugroho, A. Sepri, R. Benyamin, B. Trilaksono, Agoes Moelyadi","doi":"10.1109/ICSENGT.2017.8123445","DOIUrl":"https://doi.org/10.1109/ICSENGT.2017.8123445","url":null,"abstract":"Flapping Wings Micro Aerial Vehicle (FWMAV) is developed from MAV (Micro Aerial Vehicle) technology, which uses flapping wing mechanism to fly rather than rotors. MAV itself is a branch of UAV (Unmanned Aerial Vehicle) technology, and focuses on minimizing size and weight of the aircraft. Ganefly is an FWMAV with capability to fly autonomously based on GPS readings and waypoints input from the user. This autopilot system works in conjunction with other parts of the control systems in Ganefly, which also includes attitude stabilization system. Ganefly uses yaw control loop for horizontal attitude stabilization, because Ganefly does not use aileron to control roll, unlike usual aircrafts. The stabilization system is implemented using standard PID control and Paparazzi UAV firmware, on a Lisa/S autopilot board. Testing for stabilization system was done in Manual and Stabilization mode, and testing for autopilot mode was done in Autopilot mode. Results gathered from testing indicate that Ganefly in its flight is not horizontally stable in both Manual and Stabilization mode, and thus was not able to be tested on Autopilot mode.","PeriodicalId":350572,"journal":{"name":"2017 7th IEEE International Conference on System Engineering and Technology (ICSET)","volume":"10 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124031550","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 : 2017-10-01DOI: 10.1109/ICSENGT.2017.8123449
S. R. Yosafat, C. Machbub, E. Hidayat
This paper presents design and implementation of face tracking system using servo-motor-controlled Pan-Tilt visual system. The objective is to maintain the position of a tracked object at the center of frame window on the screen. A simple camera is used as visual sensor to obtain the face object's actual position. Combination of Viola-Jones and Template Matching algorithms are used for face detection, in which template matching method acts as a back up on the occasion Viola-Jones fails to detect the face object. Object's position on the screen is controlled indirectly through the position of the camera using an Arduino-based controller. Two control methods are implemented to track the object, namely lead-lag compensator and PID control. To obtain proper parameters of the controller, identification of the Pan and Tilt system has been done and validated. Both controller algorithms are then compared and analyzed in accordance with system design specification. Overall, experimental results show that PID has faster transient response than lead-lag either for Pan or Tilt.
{"title":"Design and implementation of Pan-Tilt control for face tracking","authors":"S. R. Yosafat, C. Machbub, E. Hidayat","doi":"10.1109/ICSENGT.2017.8123449","DOIUrl":"https://doi.org/10.1109/ICSENGT.2017.8123449","url":null,"abstract":"This paper presents design and implementation of face tracking system using servo-motor-controlled Pan-Tilt visual system. The objective is to maintain the position of a tracked object at the center of frame window on the screen. A simple camera is used as visual sensor to obtain the face object's actual position. Combination of Viola-Jones and Template Matching algorithms are used for face detection, in which template matching method acts as a back up on the occasion Viola-Jones fails to detect the face object. Object's position on the screen is controlled indirectly through the position of the camera using an Arduino-based controller. Two control methods are implemented to track the object, namely lead-lag compensator and PID control. To obtain proper parameters of the controller, identification of the Pan and Tilt system has been done and validated. Both controller algorithms are then compared and analyzed in accordance with system design specification. Overall, experimental results show that PID has faster transient response than lead-lag either for Pan or Tilt.","PeriodicalId":350572,"journal":{"name":"2017 7th IEEE International Conference on System Engineering and Technology (ICSET)","volume":"75 7 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123300724","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 : 2017-10-01DOI: 10.1109/ICSENGT.2017.8123432
N. Farah, M. Talib, Z. Ibrahim, S. S. M. Isa, J. M. Lazi
One of the most popular and easy to implement control strategy for the inverter in induction motor drive system is the hysteresis current control. The most drawbacks associated with the conventional hysteresis current controller is the variable switching frequency due to the constant hysteresis band. This paper aims to develop variable hysteresis band with fuzzy logic controller which can produce constant switching frequency. Matlab/Simulink environment was utilized to conduct the simulation of induction motor drives with three different configuration of hysteresis control; fixed hysteresis band, variable hysteresis band and fuzzy hysteresis band. The obtained results shows that, fuzzy hysteresis band produce better results than the fixed and variable band in which constant switching frequency, less ripple and reduced harmonics contents in the current waveforms. Hence fuzzy based hysteresis current controller proved to be superior in terms of switching frequency and harmonics contents.
{"title":"Variable hysteresis current controller with fuzzy logic controller based induction motor drives","authors":"N. Farah, M. Talib, Z. Ibrahim, S. S. M. Isa, J. M. Lazi","doi":"10.1109/ICSENGT.2017.8123432","DOIUrl":"https://doi.org/10.1109/ICSENGT.2017.8123432","url":null,"abstract":"One of the most popular and easy to implement control strategy for the inverter in induction motor drive system is the hysteresis current control. The most drawbacks associated with the conventional hysteresis current controller is the variable switching frequency due to the constant hysteresis band. This paper aims to develop variable hysteresis band with fuzzy logic controller which can produce constant switching frequency. Matlab/Simulink environment was utilized to conduct the simulation of induction motor drives with three different configuration of hysteresis control; fixed hysteresis band, variable hysteresis band and fuzzy hysteresis band. The obtained results shows that, fuzzy hysteresis band produce better results than the fixed and variable band in which constant switching frequency, less ripple and reduced harmonics contents in the current waveforms. Hence fuzzy based hysteresis current controller proved to be superior in terms of switching frequency and harmonics contents.","PeriodicalId":350572,"journal":{"name":"2017 7th IEEE International Conference on System Engineering and Technology (ICSET)","volume":"34 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115331818","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 : 2017-10-01DOI: 10.1109/ICSENGT.2017.8123447
Mohammad Syahmi Rosli, Nur Nabilah Abu Mangshor, Nurbaity Sabri, Z. Ibrahim
Learning natural disaster safety is important to equip human with awareness and preparedness if the disaster happens. Hurricane is an extreme and dangerous natural disaster which can cause loss of property and life. However, the disaster safety learning in Malaysia only covers flood, earthquake and fire. There is no safety learning to teach hurricane in Malaysia yet. Due to that, Malaysians are still lack in preparedness for emergencies and natural disaster, especially in hurricane since only few games are available. In addition, the development and research of the instructional games based on natural disaster are still lacking. Hence, this study proposes the development of learning hurricane safety using game-based learning technique. The methodology uses Game Development Life Cycle (GDLC). A usability testing and functionality testing has conducted to test the usability and functionality of the game. Results indicate that 90% of the game participants are able to learn hurricane disaster safety effectively.
{"title":"Educational game as interactive learning for hurricane safety","authors":"Mohammad Syahmi Rosli, Nur Nabilah Abu Mangshor, Nurbaity Sabri, Z. Ibrahim","doi":"10.1109/ICSENGT.2017.8123447","DOIUrl":"https://doi.org/10.1109/ICSENGT.2017.8123447","url":null,"abstract":"Learning natural disaster safety is important to equip human with awareness and preparedness if the disaster happens. Hurricane is an extreme and dangerous natural disaster which can cause loss of property and life. However, the disaster safety learning in Malaysia only covers flood, earthquake and fire. There is no safety learning to teach hurricane in Malaysia yet. Due to that, Malaysians are still lack in preparedness for emergencies and natural disaster, especially in hurricane since only few games are available. In addition, the development and research of the instructional games based on natural disaster are still lacking. Hence, this study proposes the development of learning hurricane safety using game-based learning technique. The methodology uses Game Development Life Cycle (GDLC). A usability testing and functionality testing has conducted to test the usability and functionality of the game. Results indicate that 90% of the game participants are able to learn hurricane disaster safety effectively.","PeriodicalId":350572,"journal":{"name":"2017 7th IEEE International Conference on System Engineering and Technology (ICSET)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130114984","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 : 2017-10-01DOI: 10.1109/ICSENGT.2017.8123411
A. Alsaeedi, M. A. Fattah, Khalid S. Aloufi
For text clustering task, distinctive text features selection is important due to feature space high dimensionality. It is essential to reduce the feature space dimension to increase accuracy and decrease processing time. In this work, for text clustering task, we introduce a novel hybrid feature selection model. This method measures the term importance based on the correlation coefficient among four term weighting techniques. All terms in the feature parameter vector are ranked based on this correlation coefficient score. Then low score terms are filtered out. Clustering technique is applied on the feature parameter vectors after filtering step. The proposed method results show its superiority over the traditional feature selection approaches.
{"title":"A hybrid feature selection model for text clustering","authors":"A. Alsaeedi, M. A. Fattah, Khalid S. Aloufi","doi":"10.1109/ICSENGT.2017.8123411","DOIUrl":"https://doi.org/10.1109/ICSENGT.2017.8123411","url":null,"abstract":"For text clustering task, distinctive text features selection is important due to feature space high dimensionality. It is essential to reduce the feature space dimension to increase accuracy and decrease processing time. In this work, for text clustering task, we introduce a novel hybrid feature selection model. This method measures the term importance based on the correlation coefficient among four term weighting techniques. All terms in the feature parameter vector are ranked based on this correlation coefficient score. Then low score terms are filtered out. Clustering technique is applied on the feature parameter vectors after filtering step. The proposed method results show its superiority over the traditional feature selection approaches.","PeriodicalId":350572,"journal":{"name":"2017 7th IEEE International Conference on System Engineering and Technology (ICSET)","volume":"3 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133549469","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 : 2017-10-01DOI: 10.1109/ICSENGT.2017.8123422
C. Jing, Dwi Pebrianti, Goh Ming Qian, L. Bayuaji
Unmanned Aerial Vehicle (UAV) is being used in a wide range of human life. Researcher preferred quadrotor as it can be brought into the first generation of simulator map of an aircraft. It can be developed into larger manned flight. In this regard, extensive research in Fault detection (FD) is necessary, so that it can enhance its safety features. FD is designed to respond and to exclude the wrong information and to quickly perceive and shoulder important regulation. The proposed method for the fault detection in this study uses hybrid technique which combines the Kalman filter and Artificial Neural Network (ANN). Two classes of approaches are analyzed: the system identification approach using ANN and the observer-based approach using Kalman filter. A representative Artificial Neural Network (ANN) model has been designed and used to simulate the system behaviors under various failure conditions. The Kalman filter recognizes data from sensors and indicates the fault of the system in sensor reading. Error prediction is based on the fault magnitude and the time occurrence of fault. The information will then be fed to ANN, which consists of a bank of parameter estimation that generates failure state. The result of the residual signal before filtered and after filtered showed that Kalman-ANN is able to identify multi fault and immediately correct the system to the normal state. The accuracy of the detection is 85 percent. The proposed method is able to detect fault in a short time with delay of 9.23E-05 seconds.
{"title":"Fault detection in quadrotor MAV","authors":"C. Jing, Dwi Pebrianti, Goh Ming Qian, L. Bayuaji","doi":"10.1109/ICSENGT.2017.8123422","DOIUrl":"https://doi.org/10.1109/ICSENGT.2017.8123422","url":null,"abstract":"Unmanned Aerial Vehicle (UAV) is being used in a wide range of human life. Researcher preferred quadrotor as it can be brought into the first generation of simulator map of an aircraft. It can be developed into larger manned flight. In this regard, extensive research in Fault detection (FD) is necessary, so that it can enhance its safety features. FD is designed to respond and to exclude the wrong information and to quickly perceive and shoulder important regulation. The proposed method for the fault detection in this study uses hybrid technique which combines the Kalman filter and Artificial Neural Network (ANN). Two classes of approaches are analyzed: the system identification approach using ANN and the observer-based approach using Kalman filter. A representative Artificial Neural Network (ANN) model has been designed and used to simulate the system behaviors under various failure conditions. The Kalman filter recognizes data from sensors and indicates the fault of the system in sensor reading. Error prediction is based on the fault magnitude and the time occurrence of fault. The information will then be fed to ANN, which consists of a bank of parameter estimation that generates failure state. The result of the residual signal before filtered and after filtered showed that Kalman-ANN is able to identify multi fault and immediately correct the system to the normal state. The accuracy of the detection is 85 percent. The proposed method is able to detect fault in a short time with delay of 9.23E-05 seconds.","PeriodicalId":350572,"journal":{"name":"2017 7th IEEE International Conference on System Engineering and Technology (ICSET)","volume":"16 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122315947","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 : 2017-10-01DOI: 10.1109/ICSENGT.2017.8123437
M. Aziz, Z. M. Yasin, Z. Zakaria
The electrical system photovoltaic (PV) modules required special design considerations due to unpredictable and sudden changes in weather conditions such as the solar irradiation level as well as the cell operating temperature. Therefore, this study presents a practical and reliable approach for the prediction of PV power output using an intelligent-based technique namely Cuckoo Search Algorithm — Least Square Support Vector Machine (CS-LSSVM). Available historical output power data are analyzed and appropriate features are selected for the model. There are two inputs vectors to the model consists of solar irradiation and ambient temperature. Cuckoo Search Algorithm (CS) is hybrid with LS-SVM in order to optimize the RBF parameters for better prediction performance. The performance of CS-LSSVM is compared with those obtained from LS-SVM using cross-validation technique in terms of accuracy. In this paper, Mean Absolute Percentage Error (MAPE) is used to quantify the performance of the prediction. Besides that, evaluation also carried out by calculating the correlation of determination. The historical PV data is utilized to validate the workability of the proposed technique. The results showed that CS-LSSVM provides better performance in predicting photovoltaic system power output.
{"title":"Prediction of photovoltaic system output using hybrid least square support vector machine","authors":"M. Aziz, Z. M. Yasin, Z. Zakaria","doi":"10.1109/ICSENGT.2017.8123437","DOIUrl":"https://doi.org/10.1109/ICSENGT.2017.8123437","url":null,"abstract":"The electrical system photovoltaic (PV) modules required special design considerations due to unpredictable and sudden changes in weather conditions such as the solar irradiation level as well as the cell operating temperature. Therefore, this study presents a practical and reliable approach for the prediction of PV power output using an intelligent-based technique namely Cuckoo Search Algorithm — Least Square Support Vector Machine (CS-LSSVM). Available historical output power data are analyzed and appropriate features are selected for the model. There are two inputs vectors to the model consists of solar irradiation and ambient temperature. Cuckoo Search Algorithm (CS) is hybrid with LS-SVM in order to optimize the RBF parameters for better prediction performance. The performance of CS-LSSVM is compared with those obtained from LS-SVM using cross-validation technique in terms of accuracy. In this paper, Mean Absolute Percentage Error (MAPE) is used to quantify the performance of the prediction. Besides that, evaluation also carried out by calculating the correlation of determination. The historical PV data is utilized to validate the workability of the proposed technique. The results showed that CS-LSSVM provides better performance in predicting photovoltaic system power output.","PeriodicalId":350572,"journal":{"name":"2017 7th IEEE International Conference on System Engineering and Technology (ICSET)","volume":"3 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132545286","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：