Pub Date : 2018-12-01DOI: 10.1109/ICCEREC.2018.8712093
Reza Noval Pahlevy, Agus Dwi Prasetyo, Edwar
Automatic Dependent Surveillance-Broadcast (ADS-B) is a surveillance technology applied to aircrafts for air traffic control with GPS and satellite based. ADS-B worked by receive messages from the aircraft which sends information periodically. At this moment, not all areas are covered by ADS-B. To obtain ADS-B data from the aircraft required a device consisting of a computer, a radio receiver and an antenna to obtain some real time flight information. This project is about designing a prototype for the nanosatellite that acts as a receiver of ADS- B messages that transmitted by the aircraft with a working frequency of 1090MHz and using RTL-SDR RTL2832U as the receiver and Raspberry Pi 3 Model B as On Board Data Handling (OBDH). In this paper, the prototype of ADS- B payload has been successfully designed and implemented. ADS-B payload have a success rate of 91.3% and an accuracy rate of 98.45% in the area of Telkom University. For measurements in the Ciburial area, Bandung, it have a success rate of 90.62% and an accuracy rate of 99.25%. The farthest distance obtained by the payload is 85.30 Km. The payload successfully storing data with. txt file extension format on 0.868 seconds/message.
{"title":"Nanosatellite ADS-B Receiver Prototype for Commercial Aircraft Detection","authors":"Reza Noval Pahlevy, Agus Dwi Prasetyo, Edwar","doi":"10.1109/ICCEREC.2018.8712093","DOIUrl":"https://doi.org/10.1109/ICCEREC.2018.8712093","url":null,"abstract":"Automatic Dependent Surveillance-Broadcast (ADS-B) is a surveillance technology applied to aircrafts for air traffic control with GPS and satellite based. ADS-B worked by receive messages from the aircraft which sends information periodically. At this moment, not all areas are covered by ADS-B. To obtain ADS-B data from the aircraft required a device consisting of a computer, a radio receiver and an antenna to obtain some real time flight information. This project is about designing a prototype for the nanosatellite that acts as a receiver of ADS- B messages that transmitted by the aircraft with a working frequency of 1090MHz and using RTL-SDR RTL2832U as the receiver and Raspberry Pi 3 Model B as On Board Data Handling (OBDH). In this paper, the prototype of ADS- B payload has been successfully designed and implemented. ADS-B payload have a success rate of 91.3% and an accuracy rate of 98.45% in the area of Telkom University. For measurements in the Ciburial area, Bandung, it have a success rate of 90.62% and an accuracy rate of 99.25%. The farthest distance obtained by the payload is 85.30 Km. The payload successfully storing data with. txt file extension format on 0.868 seconds/message.","PeriodicalId":250054,"journal":{"name":"2018 International Conference on Control, Electronics, Renewable Energy and Communications (ICCEREC)","volume":"35 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121899895","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 : 2018-12-01DOI: 10.1109/ICCEREC.2018.8712100
Fariz Henzal Bafadhal, B. S. Nugroho, H. Wijanto
Designing antenna for CubeSat on Inter-Satellite Link (ISL) system is very challenging by considering the tumbling scenario when satellite orbiting. Microstrip antenna is a type of lightweight antenna with a small dimension that meet the requirements of a CubeSat. Its simple configuration simplifies the assembly and adjustment process with the condition of the CubeSat. The propose ISL systems will orbiting on LEO orbits (600–1000 km). On the LEO orbits often occurs an ionic rotation that commonly referred as faraday rotational effect and it can cause Polarization Loss Factor (PLF). The antenna Design use truncated patch to produce circular polarization. Electromagnetic Band Gap (EBG) is placed under the antenna to suppress the surface current and reduce the side lobe and back lobe. Electromagnetic Band Gap (EBG) will increase the gain and widen the bandwidth of the antenna. The satellite prototype is a 3U satellite consist of three CubeSat made of steel alloy. The tumbling simulation produce the minimum HPBW and gain required for the tumbling scheme.
{"title":"Microstrip Antenna and Tumbling Simulation for CubeSat on Inter-Satellite Link (ISL) System","authors":"Fariz Henzal Bafadhal, B. S. Nugroho, H. Wijanto","doi":"10.1109/ICCEREC.2018.8712100","DOIUrl":"https://doi.org/10.1109/ICCEREC.2018.8712100","url":null,"abstract":"Designing antenna for CubeSat on Inter-Satellite Link (ISL) system is very challenging by considering the tumbling scenario when satellite orbiting. Microstrip antenna is a type of lightweight antenna with a small dimension that meet the requirements of a CubeSat. Its simple configuration simplifies the assembly and adjustment process with the condition of the CubeSat. The propose ISL systems will orbiting on LEO orbits (600–1000 km). On the LEO orbits often occurs an ionic rotation that commonly referred as faraday rotational effect and it can cause Polarization Loss Factor (PLF). The antenna Design use truncated patch to produce circular polarization. Electromagnetic Band Gap (EBG) is placed under the antenna to suppress the surface current and reduce the side lobe and back lobe. Electromagnetic Band Gap (EBG) will increase the gain and widen the bandwidth of the antenna. The satellite prototype is a 3U satellite consist of three CubeSat made of steel alloy. The tumbling simulation produce the minimum HPBW and gain required for the tumbling scheme.","PeriodicalId":250054,"journal":{"name":"2018 International Conference on Control, Electronics, Renewable Energy and Communications (ICCEREC)","volume":"24 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115134287","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 : 2018-12-01DOI: 10.1109/ICCEREC.2018.8711994
Yassine Gangat, D. Grondin, Taher Issoufaly, Nicolas Coquillas, M. Benne, J. Chabriat
Energy management has become a very popular topic in the past few years, especially with the protection of the environment. The use and management of renewable energy sources (RES) has therefore become a necessity. In this context, innovative EMSs (Energy Management Systems) are required to bring a new way to monitor energy flows in micro grids. The interaction between physical and digital elements is relying on the use of Information and Communication Technologies (ICTs). A side effect is the appearance of Multi-Agent System (MAS) whose aim is to manage efficiently energy flows to reduce consumer bills, to minimize the use of fossil fuel in favor of RES. In this paper, we introduce “GYSOMATE”, a simulation platform to test different management strategies, with the implementation of predictive tools and MAS to improve the EMS.
{"title":"Simulation & Emulation platform for smart grid technologies","authors":"Yassine Gangat, D. Grondin, Taher Issoufaly, Nicolas Coquillas, M. Benne, J. Chabriat","doi":"10.1109/ICCEREC.2018.8711994","DOIUrl":"https://doi.org/10.1109/ICCEREC.2018.8711994","url":null,"abstract":"Energy management has become a very popular topic in the past few years, especially with the protection of the environment. The use and management of renewable energy sources (RES) has therefore become a necessity. In this context, innovative EMSs (Energy Management Systems) are required to bring a new way to monitor energy flows in micro grids. The interaction between physical and digital elements is relying on the use of Information and Communication Technologies (ICTs). A side effect is the appearance of Multi-Agent System (MAS) whose aim is to manage efficiently energy flows to reduce consumer bills, to minimize the use of fossil fuel in favor of RES. In this paper, we introduce “GYSOMATE”, a simulation platform to test different management strategies, with the implementation of predictive tools and MAS to improve the EMS.","PeriodicalId":250054,"journal":{"name":"2018 International Conference on Control, Electronics, Renewable Energy and Communications (ICCEREC)","volume":"9 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116383709","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 : 2018-12-01DOI: 10.1109/iccerec.2018.8712000
Marcel
Network virtualization allow us to integrate network functional at the level of virtualization together with the virtual machines. While VMware platform provide network virtualization built-in on its hypervisor (VMware ESXi) but with limited function at layer 2 of OSI layer. Additional solutions were offered but targeted for advanced environment, arising a question for a solution targeted at small-scale. The experimental tests performed showed that Mikrotik-based virtual machine can be used to leverage the network virtualization function for layer 3 and layer 4 of OSI layers. The throughput-rate tests were compared physical-routing with virtual-routing solution. The tests also reveal that virtual-routing solution has higher throughput-rate compared with physical-routing, this happen because the end-to-end data transmission was processed virtually at the hypervisor level. This design also has a limitation, since VMware only allows up to 10 virtual network per virtual machine, which means only up to 10 network addresses supported per Mikrotik-based virtual machine.
{"title":"Performance Evaluation of MikroTik-based Virtual Machine for Small-Scale Network Virtualization on VMware Platform","authors":"Marcel","doi":"10.1109/iccerec.2018.8712000","DOIUrl":"https://doi.org/10.1109/iccerec.2018.8712000","url":null,"abstract":"Network virtualization allow us to integrate network functional at the level of virtualization together with the virtual machines. While VMware platform provide network virtualization built-in on its hypervisor (VMware ESXi) but with limited function at layer 2 of OSI layer. Additional solutions were offered but targeted for advanced environment, arising a question for a solution targeted at small-scale. The experimental tests performed showed that Mikrotik-based virtual machine can be used to leverage the network virtualization function for layer 3 and layer 4 of OSI layers. The throughput-rate tests were compared physical-routing with virtual-routing solution. The tests also reveal that virtual-routing solution has higher throughput-rate compared with physical-routing, this happen because the end-to-end data transmission was processed virtually at the hypervisor level. This design also has a limitation, since VMware only allows up to 10 virtual network per virtual machine, which means only up to 10 network addresses supported per Mikrotik-based virtual machine.","PeriodicalId":250054,"journal":{"name":"2018 International Conference on Control, Electronics, Renewable Energy and Communications (ICCEREC)","volume":"14 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124113026","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 : 2018-12-01DOI: 10.1109/ICCEREC.2018.8712003
Giva Andriana Mutiara, Gita Hapsari, Aris Pujud
The increasing number of transportations, need a good maintenance management parking place. Smart Parking System (SPS) is an smart parking system that has been implemented in various places. However, some of the SPS has not provided an information that allows the driver to find an empty parking space easily. In this research, we design an SPS that applies using geeknesia's Application Programming Interface (API) as a centralized IoT server for the embedded system. This system is embedded with the integrated internet-based monitoring system that utilizes server geeknesia.com and a monitoring application parking space on the smartphone. We create the API form in geeknesia.com that will save any changes from the signal sensor as the information of empty space. The testing system is performed with 10 samples parking space area with attached ultrasonic sensor devices. This system is tested to check the correctness of changing data which is generated by the sensor based on the real condition in the parking lot and to see whether the system works. The result showed that the system can read the changes of the sensor, precisely and the changes of the sensor can give the information to the user whether the slot is reserved or empty
{"title":"Centralized Control Parking System using API Geeknesia","authors":"Giva Andriana Mutiara, Gita Hapsari, Aris Pujud","doi":"10.1109/ICCEREC.2018.8712003","DOIUrl":"https://doi.org/10.1109/ICCEREC.2018.8712003","url":null,"abstract":"The increasing number of transportations, need a good maintenance management parking place. Smart Parking System (SPS) is an smart parking system that has been implemented in various places. However, some of the SPS has not provided an information that allows the driver to find an empty parking space easily. In this research, we design an SPS that applies using geeknesia's Application Programming Interface (API) as a centralized IoT server for the embedded system. This system is embedded with the integrated internet-based monitoring system that utilizes server geeknesia.com and a monitoring application parking space on the smartphone. We create the API form in geeknesia.com that will save any changes from the signal sensor as the information of empty space. The testing system is performed with 10 samples parking space area with attached ultrasonic sensor devices. This system is tested to check the correctness of changing data which is generated by the sensor based on the real condition in the parking lot and to see whether the system works. The result showed that the system can read the changes of the sensor, precisely and the changes of the sensor can give the information to the user whether the slot is reserved or empty","PeriodicalId":250054,"journal":{"name":"2018 International Conference on Control, Electronics, Renewable Energy and Communications (ICCEREC)","volume":"21 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132346787","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 : 2018-12-01DOI: 10.1109/ICCEREC.2018.8712001
Gelar Budiman, A. B. Suksmono, D. Danudirdjo
A digital copyright on an audio needs a special protection to prevent it from illegal distribution. Hiding a copyright into an audio is a solution for securing its ownership. In this paper, we propose an audio watermarking using combination method of Lifting Wavelet Transform (LWT), Discrete Sine Transform (DST), Singular Value Decomposition (SVD), and Cartesian Polar Transform (CPT) using Quantization Index Modulation (QIM). A host audio is first decomposed by LWT. Next, a subband is selected then transformed by DST. Then, DST selected coefficients are decomposed into U, S and V matrices by SVD. S matrix is then selected. S elements in position (1,1) and (2,2) are converted by CPT to magnitude and phase coefficients. The phase coefficient is finally used for embedding a bit of watermark by QIM. The simulation result shows that the proposed method offers very high watermark capacity with good imperceptibility and robustness.
{"title":"CPT-Based Data Hiding in Selected Subband Using Combined Transform and Decomposition Method","authors":"Gelar Budiman, A. B. Suksmono, D. Danudirdjo","doi":"10.1109/ICCEREC.2018.8712001","DOIUrl":"https://doi.org/10.1109/ICCEREC.2018.8712001","url":null,"abstract":"A digital copyright on an audio needs a special protection to prevent it from illegal distribution. Hiding a copyright into an audio is a solution for securing its ownership. In this paper, we propose an audio watermarking using combination method of Lifting Wavelet Transform (LWT), Discrete Sine Transform (DST), Singular Value Decomposition (SVD), and Cartesian Polar Transform (CPT) using Quantization Index Modulation (QIM). A host audio is first decomposed by LWT. Next, a subband is selected then transformed by DST. Then, DST selected coefficients are decomposed into U, S and V matrices by SVD. S matrix is then selected. S elements in position (1,1) and (2,2) are converted by CPT to magnitude and phase coefficients. The phase coefficient is finally used for embedding a bit of watermark by QIM. The simulation result shows that the proposed method offers very high watermark capacity with good imperceptibility and robustness.","PeriodicalId":250054,"journal":{"name":"2018 International Conference on Control, Electronics, Renewable Energy and Communications (ICCEREC)","volume":"36 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125340811","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 : 2018-12-01DOI: 10.1109/ICCEREC.2018.8712085
Irvan Ragil Boesandi, Irma Safitri, E. Suhartono
In this study, we propose Huffman coding and compressive sensing (CS) for medical image watermarking. The methods used are Huffman coding, CS, discrete wavelet transform (DWT) and singular value decomposition (SVD). Experiment results show that images can be compressed generally above 50% and are lossless at the time of decompression by having the SSIM value of 1. Our system have the best MSE value of 0.23 and the best PSNR value of 56.5 dB.
{"title":"Compressive Sensing in the Huffman Coding DWT SVD Medical Image Watermarking","authors":"Irvan Ragil Boesandi, Irma Safitri, E. Suhartono","doi":"10.1109/ICCEREC.2018.8712085","DOIUrl":"https://doi.org/10.1109/ICCEREC.2018.8712085","url":null,"abstract":"In this study, we propose Huffman coding and compressive sensing (CS) for medical image watermarking. The methods used are Huffman coding, CS, discrete wavelet transform (DWT) and singular value decomposition (SVD). Experiment results show that images can be compressed generally above 50% and are lossless at the time of decompression by having the SSIM value of 1. Our system have the best MSE value of 0.23 and the best PSNR value of 56.5 dB.","PeriodicalId":250054,"journal":{"name":"2018 International Conference on Control, Electronics, Renewable Energy and Communications (ICCEREC)","volume":"85 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122576943","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 : 2018-12-01DOI: 10.1109/ICCEREC.2018.8711999
Dinah Pearl Madelo, Angeline Tayros, Rochelle M. Sabarillo, A. Lowaton, J. Hora
The trend of faster microprocessors at lower supply voltages demanded the need for a stable and less power consuming SRAM. This study answered these issues by implementing a 12T Power Gated Schmitt Trigger SRAM implemented in Full Custom 65nm CMOS technology. The read and write stability was accomplished without extra peripheral circuitry with more control signals per cell. The design schematic, layout, and results were obtained using SYNOPSYS Custom Designer. The Full Custom design resulted to 1.25 sq. mm. chip area, 2.43 mW power consumption, and 31.45 ns slack time. Results also show that most power consumption from the Full Custom design come from the banking and row decoders. The memory array has a 16-bit addressable word line, 512 byte memory capacity, simulated with 25–200 MHz operating frequency and under 1V supply voltage.
{"title":"Design of Low Power P-Gated Schmitt Trigger SRAM in 65nm CMOS Technology","authors":"Dinah Pearl Madelo, Angeline Tayros, Rochelle M. Sabarillo, A. Lowaton, J. Hora","doi":"10.1109/ICCEREC.2018.8711999","DOIUrl":"https://doi.org/10.1109/ICCEREC.2018.8711999","url":null,"abstract":"The trend of faster microprocessors at lower supply voltages demanded the need for a stable and less power consuming SRAM. This study answered these issues by implementing a 12T Power Gated Schmitt Trigger SRAM implemented in Full Custom 65nm CMOS technology. The read and write stability was accomplished without extra peripheral circuitry with more control signals per cell. The design schematic, layout, and results were obtained using SYNOPSYS Custom Designer. The Full Custom design resulted to 1.25 sq. mm. chip area, 2.43 mW power consumption, and 31.45 ns slack time. Results also show that most power consumption from the Full Custom design come from the banking and row decoders. The memory array has a 16-bit addressable word line, 512 byte memory capacity, simulated with 25–200 MHz operating frequency and under 1V supply voltage.","PeriodicalId":250054,"journal":{"name":"2018 International Conference on Control, Electronics, Renewable Energy and Communications (ICCEREC)","volume":"69 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122964958","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 : 2018-12-01DOI: 10.1109/ICCEREC.2018.8712092
Afif Hijra Ferdinan, Andrew Brian Osmond, C. Setianingsih
Every human being is naturally experiences various emotions. Emotion is a person's feelings into something that affect person's behavior itself. Emotion is subjective and temporary that occurred or triggered by a stimulus such as experience from other people around him and the environment. One of the environment that can trigger someone's emotion is from the song being listened to. Songs are music that consists of a regular arrangement of tones and there are lyrics inside. Song lyrics are parts that can build emotions. Choosing the right words for lyrics are very important because it will create the right emotion. Then, choosing the right songs to listen is also important. k-NN algorithm is one of classification algorithm that will count nearest neighbor of k variable. The results in this study show average accuracy 75%.
{"title":"Emotion Classification in Song Lyrics Using K-Nearest Neighbor Method","authors":"Afif Hijra Ferdinan, Andrew Brian Osmond, C. Setianingsih","doi":"10.1109/ICCEREC.2018.8712092","DOIUrl":"https://doi.org/10.1109/ICCEREC.2018.8712092","url":null,"abstract":"Every human being is naturally experiences various emotions. Emotion is a person's feelings into something that affect person's behavior itself. Emotion is subjective and temporary that occurred or triggered by a stimulus such as experience from other people around him and the environment. One of the environment that can trigger someone's emotion is from the song being listened to. Songs are music that consists of a regular arrangement of tones and there are lyrics inside. Song lyrics are parts that can build emotions. Choosing the right words for lyrics are very important because it will create the right emotion. Then, choosing the right songs to listen is also important. k-NN algorithm is one of classification algorithm that will count nearest neighbor of k variable. The results in this study show average accuracy 75%.","PeriodicalId":250054,"journal":{"name":"2018 International Conference on Control, Electronics, Renewable Energy and Communications (ICCEREC)","volume":"64 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134550567","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 : 2018-12-01DOI: 10.1109/ICCEREC.2018.8711995
Hilman Fauzi, M. I. Shapiai, Shahrum Shah Abdullah, Z. Ibrahim
This paper presents an automatic selected channel method for improving brain-computer interface (BCI) performance. Finding an effective channel composition in a BCI system is important for parsing the complexity of these systems. In this study, several statistical methods based on an energy extraction method were used to automatically detect the composition of selected channels. We introduce four techniques for automatic channel selection to optimize the energy extraction method, such as mean, high mean, box, and high in box. The performance of all of the proposed techniques was evaluated based on performance accuracy, compression ratio, and channel mapping on a brain scalp. The performance of the proposed BCI framework was compared against a BCI framework that used a manual technique as the energy extraction method. The proposed BCI framework system used a conventional common spatial pattern (CSP) to extract features from two-class motor imagery EEG signals before employing extreme learning machine (ELM) to classify the features of the EEG signal. As a result, the proposed automatic channel selection methods were found effective in finding optimal channels and provided better performance accuracy. In general, the proposed method improved the conventional BCI performance by up to 16% accuracy and 87% channel compression size. Besides that, the automatic technique also yielded better BCI performance accuracy of up to 5% compared to the BCI system that used the manual technique of energy extraction as its EEG channel selection method.
{"title":"Automatic Energy Extraction Methods for EEG Channel Selection","authors":"Hilman Fauzi, M. I. Shapiai, Shahrum Shah Abdullah, Z. Ibrahim","doi":"10.1109/ICCEREC.2018.8711995","DOIUrl":"https://doi.org/10.1109/ICCEREC.2018.8711995","url":null,"abstract":"This paper presents an automatic selected channel method for improving brain-computer interface (BCI) performance. Finding an effective channel composition in a BCI system is important for parsing the complexity of these systems. In this study, several statistical methods based on an energy extraction method were used to automatically detect the composition of selected channels. We introduce four techniques for automatic channel selection to optimize the energy extraction method, such as mean, high mean, box, and high in box. The performance of all of the proposed techniques was evaluated based on performance accuracy, compression ratio, and channel mapping on a brain scalp. The performance of the proposed BCI framework was compared against a BCI framework that used a manual technique as the energy extraction method. The proposed BCI framework system used a conventional common spatial pattern (CSP) to extract features from two-class motor imagery EEG signals before employing extreme learning machine (ELM) to classify the features of the EEG signal. As a result, the proposed automatic channel selection methods were found effective in finding optimal channels and provided better performance accuracy. In general, the proposed method improved the conventional BCI performance by up to 16% accuracy and 87% channel compression size. Besides that, the automatic technique also yielded better BCI performance accuracy of up to 5% compared to the BCI system that used the manual technique of energy extraction as its EEG channel selection method.","PeriodicalId":250054,"journal":{"name":"2018 International Conference on Control, Electronics, Renewable Energy and Communications (ICCEREC)","volume":"14 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132380173","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：