Pub Date : 2018-08-01DOI: 10.1109/ISITIA.2018.8710890
D. Setiawan, H. Suryoatmojo, M. Ashari
This paper is dealing with innovative control strategy of a four-leg voltage source inverter (FLVSI) which is implemented in unbalanced condition. The proposed method is aimed to maintain the balancing of voltage and current distribution system due to unbalance capacity of DG connection and unbalanced load. These unbalance condition can affect the transformer performance which is essentially designed to supply a balanced voltage. For solving the problem, the unbalance voltage and current transformer signals are decomposed to its symmetrical components: positive, negative, and zero sequence. Each results of the decomposition are transformed into a synchronous reference frame (dq coordinate) and controlled by ANFIS controller. Based on the simulation results with Matlab/Simulink, current unbalance of transformer is decreased from 48.44% to 15.15% and voltage unbalance is decreased from 5.09% to 2.46%.
{"title":"Four-leg Voltage Source Inverter for Voltage and Current Balancing of Distribution Transformer with Distributed Generations","authors":"D. Setiawan, H. Suryoatmojo, M. Ashari","doi":"10.1109/ISITIA.2018.8710890","DOIUrl":"https://doi.org/10.1109/ISITIA.2018.8710890","url":null,"abstract":"This paper is dealing with innovative control strategy of a four-leg voltage source inverter (FLVSI) which is implemented in unbalanced condition. The proposed method is aimed to maintain the balancing of voltage and current distribution system due to unbalance capacity of DG connection and unbalanced load. These unbalance condition can affect the transformer performance which is essentially designed to supply a balanced voltage. For solving the problem, the unbalance voltage and current transformer signals are decomposed to its symmetrical components: positive, negative, and zero sequence. Each results of the decomposition are transformed into a synchronous reference frame (dq coordinate) and controlled by ANFIS controller. Based on the simulation results with Matlab/Simulink, current unbalance of transformer is decreased from 48.44% to 15.15% and voltage unbalance is decreased from 5.09% to 2.46%.","PeriodicalId":388463,"journal":{"name":"2018 International Seminar on Intelligent Technology and Its Applications (ISITIA)","volume":"16 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":"122481505","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/ISITIA.2018.8710799
Wildan Arif Febrianto, Indrawan Gunartono, O. Penangsang, R. S. Wibowo
Fault in the power distribution system causes protection system tripped and the electrical supply disturbed. The electrical fault occurred by lightning, strong wind, wood cutting, then the aging and an inadequate network component maintenance. It certainly leads to the poor power quality and voltage sag as well. An assessment power quality is an essential thing for utility and the energy supplier to identify and fix a critical area up. The fault location program has an important role in short-term planning operation of electric distribution network to reduce downtime and improve system reliability. A network modelling and faults simulation has been done to obtain voltage sag and current information. Then, the voltage sag at measurement point will be purposed to identify and classify a fault by using K-Means Clustering. Fault location estimation used by technician to repair electrical supply in real system, Kupang substation.
{"title":"Fault Location and Voltage Sag Analysis in Electric Distribution Network","authors":"Wildan Arif Febrianto, Indrawan Gunartono, O. Penangsang, R. S. Wibowo","doi":"10.1109/ISITIA.2018.8710799","DOIUrl":"https://doi.org/10.1109/ISITIA.2018.8710799","url":null,"abstract":"Fault in the power distribution system causes protection system tripped and the electrical supply disturbed. The electrical fault occurred by lightning, strong wind, wood cutting, then the aging and an inadequate network component maintenance. It certainly leads to the poor power quality and voltage sag as well. An assessment power quality is an essential thing for utility and the energy supplier to identify and fix a critical area up. The fault location program has an important role in short-term planning operation of electric distribution network to reduce downtime and improve system reliability. A network modelling and faults simulation has been done to obtain voltage sag and current information. Then, the voltage sag at measurement point will be purposed to identify and classify a fault by using K-Means Clustering. Fault location estimation used by technician to repair electrical supply in real system, Kupang substation.","PeriodicalId":388463,"journal":{"name":"2018 International Seminar on Intelligent Technology and Its Applications (ISITIA)","volume":"218 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":"121035109","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/ISITIA.2018.8710786
Fransisca Margaret Pasalbessy, K. Anwar
The Internet-of-Things (IoT) is estimated to be deployed to serve billions of devices constructing super-dense networks, of which the performances are depending on the multiuser detection (MUD) capabilities to support more devices. This paper analyzes the decoding behaviour of Narrowband IoT (NB-IoT) and Single Carrier IoT (SC-IoT) networks using extrinsic information transfer (EXIT) chart to observe their throughput performances in low and high volume traffics. NB-IoT uses slotted ALOHA as its multiple access technique that discards collided packets, while SC-IoT uses coded random access (CRA) scheme, where the collided packets are to be resolved using successive interference cancellation technique, which is equivalent to peeling decoding at packet level. We also analyze network performances in terms of packet-loss-rate (PLR) and throughput using a series of computer simulations. Our results confirmed that SC-IoT using CRA has better performance than NB-IoT in terms of PLR, throughput, and gap of EXIT chart indicating that SC-IoT based on CRA scheme is a promising scheme for future IoT to serve massive number of users or devices.
{"title":"Analysis of Internet of Things (IoT) Networks Using Extrinsic Information Transfer (EXIT) Chart","authors":"Fransisca Margaret Pasalbessy, K. Anwar","doi":"10.1109/ISITIA.2018.8710786","DOIUrl":"https://doi.org/10.1109/ISITIA.2018.8710786","url":null,"abstract":"The Internet-of-Things (IoT) is estimated to be deployed to serve billions of devices constructing super-dense networks, of which the performances are depending on the multiuser detection (MUD) capabilities to support more devices. This paper analyzes the decoding behaviour of Narrowband IoT (NB-IoT) and Single Carrier IoT (SC-IoT) networks using extrinsic information transfer (EXIT) chart to observe their throughput performances in low and high volume traffics. NB-IoT uses slotted ALOHA as its multiple access technique that discards collided packets, while SC-IoT uses coded random access (CRA) scheme, where the collided packets are to be resolved using successive interference cancellation technique, which is equivalent to peeling decoding at packet level. We also analyze network performances in terms of packet-loss-rate (PLR) and throughput using a series of computer simulations. Our results confirmed that SC-IoT using CRA has better performance than NB-IoT in terms of PLR, throughput, and gap of EXIT chart indicating that SC-IoT based on CRA scheme is a promising scheme for future IoT to serve massive number of users or devices.","PeriodicalId":388463,"journal":{"name":"2018 International Seminar on Intelligent Technology and Its Applications (ISITIA)","volume":"50 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":"121255029","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/ISITIA.2018.8711344
Tirta Samuel Mehang, D. Riawan, Vita Lystianingrum B. Putri
Photovoltaic (PV) systems are nowadays one of the most wide-spread renewable energy systems in the network or grid with one purpose to improve the reliability of the grid. However, PV systems in the network also contribute a negative impact as well; when the main grid fails to supply the load and there is a part of the load energized by the PV systems while being isolated. This case is defined as islanding. If this condition cannot be detected, the load bus will experience voltage disturbance and power quality problem. This paper presents an islanding detection using Artificial Neural Network method (ANN). ANN learning data are generated from simulations under three main scenarios: power match, overvoltage, and undervoltage, with varying power factor (cos phi). Voltage signal at PCC node in load bus is classified to identify if system is in islanding condition or not. The simulation results shows that the built ANN is capable to detect both islanding and non-islanding mode.
{"title":"Islanding Detection in Grid-Connected Distributed Photovoltaic Generation Using Artificial Neural Network","authors":"Tirta Samuel Mehang, D. Riawan, Vita Lystianingrum B. Putri","doi":"10.1109/ISITIA.2018.8711344","DOIUrl":"https://doi.org/10.1109/ISITIA.2018.8711344","url":null,"abstract":"Photovoltaic (PV) systems are nowadays one of the most wide-spread renewable energy systems in the network or grid with one purpose to improve the reliability of the grid. However, PV systems in the network also contribute a negative impact as well; when the main grid fails to supply the load and there is a part of the load energized by the PV systems while being isolated. This case is defined as islanding. If this condition cannot be detected, the load bus will experience voltage disturbance and power quality problem. This paper presents an islanding detection using Artificial Neural Network method (ANN). ANN learning data are generated from simulations under three main scenarios: power match, overvoltage, and undervoltage, with varying power factor (cos phi). Voltage signal at PCC node in load bus is classified to identify if system is in islanding condition or not. The simulation results shows that the built ANN is capable to detect both islanding and non-islanding mode.","PeriodicalId":388463,"journal":{"name":"2018 International Seminar on Intelligent Technology and Its Applications (ISITIA)","volume":"110 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":"129595852","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/ISITIA.2018.8711302
D. A. Asfani, D. Fahmi, I. M. Yulistya Negara, Agung Brastama, F. Kurniawan, I. Ramadhan
In this paper, a web-based online monitoring system of low voltage series arcing was designed. Furthermore, the line impedance was anayzed. The method of arc detection was done by peak thresholding and peak counting of the current signal that were previously processed by a digital high pass filter in LabViewprogram. The algorithm in detection system was designed to recognize three common cases in a circuit, namely normal condition, load switching condition, and series arcing condition. The LabViewprogram was employed to communicate with a MySQL database that was located on a webhost server in internet network by sending the arcing detection log. The results showed that the proposed system could distinguish the arcing condition from the other cases and send this information to the web. In addition, the line impedance affected the sensitivity of arcing detection system since it attenuated the arcing signal.
{"title":"Web-based Online Monitoring of Low Voltage Series Arcing with Line Impedance Analysis","authors":"D. A. Asfani, D. Fahmi, I. M. Yulistya Negara, Agung Brastama, F. Kurniawan, I. Ramadhan","doi":"10.1109/ISITIA.2018.8711302","DOIUrl":"https://doi.org/10.1109/ISITIA.2018.8711302","url":null,"abstract":"In this paper, a web-based online monitoring system of low voltage series arcing was designed. Furthermore, the line impedance was anayzed. The method of arc detection was done by peak thresholding and peak counting of the current signal that were previously processed by a digital high pass filter in LabViewprogram. The algorithm in detection system was designed to recognize three common cases in a circuit, namely normal condition, load switching condition, and series arcing condition. The LabViewprogram was employed to communicate with a MySQL database that was located on a webhost server in internet network by sending the arcing detection log. The results showed that the proposed system could distinguish the arcing condition from the other cases and send this information to the web. In addition, the line impedance affected the sensitivity of arcing detection system since it attenuated the arcing signal.","PeriodicalId":388463,"journal":{"name":"2018 International Seminar on Intelligent Technology and Its Applications (ISITIA)","volume":"79 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":"127124722","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/ISITIA.2018.8711296
Anggarjuna Puncak Pujiputra, Hendra Kusuma, T. A. Sardjono
A good accuracy and certainty paper currency recognition has a great signification for banking system as well as for vending machines. In this paper we propose an ultraviolet (UV) Rupiah paper currency image recognition by implementing Gabor wavelet feature extraction. The UV image is used to distinguish between a genuine and a fake paper image currency, since under UV light a different visual in specific areas of the real banknote will glow and show hidden patterns. To have a high accuracy as well as efficiency, we use 3 scales and 8 orientations Gabor bank and subspace-LDA classifier in recognition process. The proposed Gabor method has advantages of easiness and high accuracy. The experimental results demonstrate that this method is quite reasonable in terms of preciseness, with 98.5% overall average recognition rate are obtained for the data of 160 UV Rupiah paper currency images.
{"title":"Ultraviolet Rupiah Currency Image Recognition using Gabor Wavelet","authors":"Anggarjuna Puncak Pujiputra, Hendra Kusuma, T. A. Sardjono","doi":"10.1109/ISITIA.2018.8711296","DOIUrl":"https://doi.org/10.1109/ISITIA.2018.8711296","url":null,"abstract":"A good accuracy and certainty paper currency recognition has a great signification for banking system as well as for vending machines. In this paper we propose an ultraviolet (UV) Rupiah paper currency image recognition by implementing Gabor wavelet feature extraction. The UV image is used to distinguish between a genuine and a fake paper image currency, since under UV light a different visual in specific areas of the real banknote will glow and show hidden patterns. To have a high accuracy as well as efficiency, we use 3 scales and 8 orientations Gabor bank and subspace-LDA classifier in recognition process. The proposed Gabor method has advantages of easiness and high accuracy. The experimental results demonstrate that this method is quite reasonable in terms of preciseness, with 98.5% overall average recognition rate are obtained for the data of 160 UV Rupiah paper currency images.","PeriodicalId":388463,"journal":{"name":"2018 International Seminar on Intelligent Technology and Its Applications (ISITIA)","volume":"45 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":"129665221","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/isitia.2018.8710967
M. Afandi, Hendra Kusuma, T. A. Sardjono
A pair of blood vessels inside of the human neck that serves to deliver blood to the brain is called carotid artery. Cholesterol in human body can form plaque, causes blockage to carotid artery that evoke atherosclerosis, stroke and heart disease which is a dangerous disease that can lead to death. If in certain long time it is not discovered, carotid artery will rupture. In clinical practice, the availability of ultrasound is wide also it is a low cost method to observe plaque in carotid artery. Unfortunately, ultrasound plaque images in carotid artery is diverse, noisy and not easy to be identified. It is also hard to develop computational techniques for recognizing plaque from ultrasound images. Therefore, it is a challenge to develop an optimal method that can be implemented in computer system to recognize plaque from ultrasound images. One method from many techniques available in pattern recognition is a feature extraction which can be obtained from various ways. In this work, A Gabor wavelet which is one of the powerful method in feature extraction is applied to recognize plaque characteristics. However a Gabor wavelet feature extraction will result a huge data, therefore to reduce the data dimension, the Principal Component Analysis (PCA) is applied to reduce such huge data. The result of this method for recognize plaque in carotid artery is satisfied with 100% recognition rate by using 8 orientations and 3 scales bank of Gabor with 100% eigenvectors configuration. In this research we used 24 carotid artery training images.
{"title":"Carotid Artery Plaque Image Recognition Using Gabor Wavelet and Principal Component Analysis","authors":"M. Afandi, Hendra Kusuma, T. A. Sardjono","doi":"10.1109/isitia.2018.8710967","DOIUrl":"https://doi.org/10.1109/isitia.2018.8710967","url":null,"abstract":"A pair of blood vessels inside of the human neck that serves to deliver blood to the brain is called carotid artery. Cholesterol in human body can form plaque, causes blockage to carotid artery that evoke atherosclerosis, stroke and heart disease which is a dangerous disease that can lead to death. If in certain long time it is not discovered, carotid artery will rupture. In clinical practice, the availability of ultrasound is wide also it is a low cost method to observe plaque in carotid artery. Unfortunately, ultrasound plaque images in carotid artery is diverse, noisy and not easy to be identified. It is also hard to develop computational techniques for recognizing plaque from ultrasound images. Therefore, it is a challenge to develop an optimal method that can be implemented in computer system to recognize plaque from ultrasound images. One method from many techniques available in pattern recognition is a feature extraction which can be obtained from various ways. In this work, A Gabor wavelet which is one of the powerful method in feature extraction is applied to recognize plaque characteristics. However a Gabor wavelet feature extraction will result a huge data, therefore to reduce the data dimension, the Principal Component Analysis (PCA) is applied to reduce such huge data. The result of this method for recognize plaque in carotid artery is satisfied with 100% recognition rate by using 8 orientations and 3 scales bank of Gabor with 100% eigenvectors configuration. In this research we used 24 carotid artery training images.","PeriodicalId":388463,"journal":{"name":"2018 International Seminar on Intelligent Technology and Its Applications (ISITIA)","volume":"76 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":"126109746","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/ISITIA.2018.8710975
M. Attamimi, R. Mardiyanto, A. N. Irfansyah
In general, aerial mapping is an image registration problem, i.e., the problem of transforming different sets of images into one coordinate system. Aerial mapping is one of the important capability of an unmanned aerial vehicle (UAV). Here, the images processed by the registration system is strongly influenced by the quality of the image captured by the UAV. To select the image that will be processed efficiently is not easy considering the ground truth in the mapping process is not given before the UAV flies and captures the image. On the other hand, generally, UAV will fly and take the image in sequence regardless of the quality. These will result in several issues, such as: 1) the quality of mapping results becomes bad, and 2) the computational cost of registration process becomes high. To tackle such issues, therefore, we need a recognition system that is able to recognize images that should be excluded from the registration process. In this paper, we define such image as an “inclined image,” i.e., images captured by UAV not perpendicular with the ground. Although we can calculate the inclination angle using a gyroscope attached to the UAV, our interest here is to recognize the images without the use of such sensor like human do. To realize that, we utilize a deep learning method to build an inclined image recognition system. We tested our proposed system with images captured by UAV. The results showed that the proposed system yielded accuracy rate of 86.4%.
{"title":"Inclined Image Recognition for Aerial Mapping by Unmanned Aerial Vehicles","authors":"M. Attamimi, R. Mardiyanto, A. N. Irfansyah","doi":"10.1109/ISITIA.2018.8710975","DOIUrl":"https://doi.org/10.1109/ISITIA.2018.8710975","url":null,"abstract":"In general, aerial mapping is an image registration problem, i.e., the problem of transforming different sets of images into one coordinate system. Aerial mapping is one of the important capability of an unmanned aerial vehicle (UAV). Here, the images processed by the registration system is strongly influenced by the quality of the image captured by the UAV. To select the image that will be processed efficiently is not easy considering the ground truth in the mapping process is not given before the UAV flies and captures the image. On the other hand, generally, UAV will fly and take the image in sequence regardless of the quality. These will result in several issues, such as: 1) the quality of mapping results becomes bad, and 2) the computational cost of registration process becomes high. To tackle such issues, therefore, we need a recognition system that is able to recognize images that should be excluded from the registration process. In this paper, we define such image as an “inclined image,” i.e., images captured by UAV not perpendicular with the ground. Although we can calculate the inclination angle using a gyroscope attached to the UAV, our interest here is to recognize the images without the use of such sensor like human do. To realize that, we utilize a deep learning method to build an inclined image recognition system. We tested our proposed system with images captured by UAV. The results showed that the proposed system yielded accuracy rate of 86.4%.","PeriodicalId":388463,"journal":{"name":"2018 International Seminar on Intelligent Technology and Its Applications (ISITIA)","volume":"22 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":"122338573","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/ISITIA.2018.8711115
Eko Prasetyo, R. Adityo, N. Suciati, C. Fatichah
The previous research in mango leaf classification which used 270 features consisted of 256 texture features, 2 color features, and 2 shape features, could not achieve high classification performance. In this study, we conduct improvement by combining the previous features with the Boundary Moments of Centroid Contour Distance (CCD) and classify the combination features using Support Vector Machine with Linear and RBF kernels. The experiment results show that the combination features achieve higher classification performance compared to the previous features.
{"title":"Mango Leaf Classification with Boundary Moments of Centroid Contour Distances as Shape Features","authors":"Eko Prasetyo, R. Adityo, N. Suciati, C. Fatichah","doi":"10.1109/ISITIA.2018.8711115","DOIUrl":"https://doi.org/10.1109/ISITIA.2018.8711115","url":null,"abstract":"The previous research in mango leaf classification which used 270 features consisted of 256 texture features, 2 color features, and 2 shape features, could not achieve high classification performance. In this study, we conduct improvement by combining the previous features with the Boundary Moments of Centroid Contour Distance (CCD) and classify the combination features using Support Vector Machine with Linear and RBF kernels. The experiment results show that the combination features achieve higher classification performance compared to the previous features.","PeriodicalId":388463,"journal":{"name":"2018 International Seminar on Intelligent Technology and Its Applications (ISITIA)","volume":"42 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":"133029095","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/ISITIA.2018.8710837
Miftah Rahmalia Arivati, A. Nasution
Studies on the classification of heart rhythms from Electrocardiogram (ECG) signal interpretation have been widely reported. Several techniques for recognizing the abnormalities on left bundle branch (LBBB), right bundle branch (RBBB) and premature ventricular contraction (PVC) using the Taguchi optimization method and the Naïve Bayes classification method have been reported. Unfortunately results from the Naïve Bayes classification method are not as good as those using method such as SVM classification method. In the paper we propose a Hybrid PSO-Neural Network (NN) as a classification method and a Neural Independent Component Analysis (Neural-ICA) as a filter method. Neural ICA aims to separate the original signal and the noise signal on the ECG signal record. In this research the ICA method implements the Neural algorithm for the process of updating the weights after filter process. The Hybrid PSO-Neural Network is a Neural Network method that optimized by PSO to optimize the classification result. Hybrid PSO-NN method can improve the classification accuracy up to 2%, i.e. 99% accuracy, in comparison to NN method 98% accuracy and SVM method 96% accuracy, respectively.
{"title":"Heart Rhythm Classification from Electrocardiogram Signals Using Hybrid PSO-Neural Network Method and Neural ICA","authors":"Miftah Rahmalia Arivati, A. Nasution","doi":"10.1109/ISITIA.2018.8710837","DOIUrl":"https://doi.org/10.1109/ISITIA.2018.8710837","url":null,"abstract":"Studies on the classification of heart rhythms from Electrocardiogram (ECG) signal interpretation have been widely reported. Several techniques for recognizing the abnormalities on left bundle branch (LBBB), right bundle branch (RBBB) and premature ventricular contraction (PVC) using the Taguchi optimization method and the Naïve Bayes classification method have been reported. Unfortunately results from the Naïve Bayes classification method are not as good as those using method such as SVM classification method. In the paper we propose a Hybrid PSO-Neural Network (NN) as a classification method and a Neural Independent Component Analysis (Neural-ICA) as a filter method. Neural ICA aims to separate the original signal and the noise signal on the ECG signal record. In this research the ICA method implements the Neural algorithm for the process of updating the weights after filter process. The Hybrid PSO-Neural Network is a Neural Network method that optimized by PSO to optimize the classification result. Hybrid PSO-NN method can improve the classification accuracy up to 2%, i.e. 99% accuracy, in comparison to NN method 98% accuracy and SVM method 96% accuracy, respectively.","PeriodicalId":388463,"journal":{"name":"2018 International Seminar on Intelligent Technology and Its Applications (ISITIA)","volume":"11 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":"131502407","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：