Pub Date : 2018-05-01DOI: 10.1109/ICEEE2.2018.8391387
Bouaraba Azzedine, Rekioua Badreddine
Synthetic Aperture Radar (SAR) images can be used in various applications such as Digital Elevation Model (DEM) generation, ground deformation monitoring, and detection of natural and man-made fine scale changes. After scanning the imaged scene, focusing algorithm is applied on raw radar data to obtain exploitable SAR images. With the availability of high resolution radar images, there is a real opportunity for studying the new applications of the SAR images. It is in this context that the present work was developed with a main objective of providing a further analysis of Range Doppler focusing algorithm. We are also interested by the use of the obtained SAR images in the application of change detection based on coherence estimation.
{"title":"SAR image formation and exploitation using high resolution radar data","authors":"Bouaraba Azzedine, Rekioua Badreddine","doi":"10.1109/ICEEE2.2018.8391387","DOIUrl":"https://doi.org/10.1109/ICEEE2.2018.8391387","url":null,"abstract":"Synthetic Aperture Radar (SAR) images can be used in various applications such as Digital Elevation Model (DEM) generation, ground deformation monitoring, and detection of natural and man-made fine scale changes. After scanning the imaged scene, focusing algorithm is applied on raw radar data to obtain exploitable SAR images. With the availability of high resolution radar images, there is a real opportunity for studying the new applications of the SAR images. It is in this context that the present work was developed with a main objective of providing a further analysis of Range Doppler focusing algorithm. We are also interested by the use of the obtained SAR images in the application of change detection based on coherence estimation.","PeriodicalId":6482,"journal":{"name":"2018 5th International Conference on Electrical and Electronic Engineering (ICEEE)","volume":"14 1","pages":"488-491"},"PeriodicalIF":0.0,"publicationDate":"2018-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"84850458","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 : 2018-05-01DOI: 10.1109/ICEEE2.2018.8391339
Ö. Farsakoğlu, Necati Aksoy, H. Y. Hasirci, Adil Alahmad
This paper presents the design, simulation, development, testing, and performance appraisal of solar Dish- Gamma type Stirling system. The study provides a theoretical guidance for researcher who want to improve the performance of a solar dish-Stirling system using a mathematical model. It also studies the possibilities of generating electricity by using small scale solar Stirling system in TURKEY. The system is designed and set up in KILIS city. The power output of the system is measured midday in mid-August, and it is in a good agreement with the MATLAB model. The maximum solar Stirling system output power estimation is 250 W with an improved concentration ratio of 94 times. It generates electricity near to 408.07 kWh/year of electricity under KILIS climate condition. The total efficiency of designed system is 17 % Moreover, the solar collector is manufactured by using satellite dish antenna fitted with polished sheets of aluminum. The 3D model of solar tracking mechanism is prepared in solid work before starting the manufacturing and calculations.
{"title":"Design and application of solar dish-gamma type stirling system","authors":"Ö. Farsakoğlu, Necati Aksoy, H. Y. Hasirci, Adil Alahmad","doi":"10.1109/ICEEE2.2018.8391339","DOIUrl":"https://doi.org/10.1109/ICEEE2.2018.8391339","url":null,"abstract":"This paper presents the design, simulation, development, testing, and performance appraisal of solar Dish- Gamma type Stirling system. The study provides a theoretical guidance for researcher who want to improve the performance of a solar dish-Stirling system using a mathematical model. It also studies the possibilities of generating electricity by using small scale solar Stirling system in TURKEY. The system is designed and set up in KILIS city. The power output of the system is measured midday in mid-August, and it is in a good agreement with the MATLAB model. The maximum solar Stirling system output power estimation is 250 W with an improved concentration ratio of 94 times. It generates electricity near to 408.07 kWh/year of electricity under KILIS climate condition. The total efficiency of designed system is 17 % Moreover, the solar collector is manufactured by using satellite dish antenna fitted with polished sheets of aluminum. The 3D model of solar tracking mechanism is prepared in solid work before starting the manufacturing and calculations.","PeriodicalId":6482,"journal":{"name":"2018 5th International Conference on Electrical and Electronic Engineering (ICEEE)","volume":"2674 1","pages":"242-246"},"PeriodicalIF":0.0,"publicationDate":"2018-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"79695463","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 : 2018-05-01DOI: 10.1109/ICEEE2.2018.8391315
Khalid Yahya, M. Z. Bilgin, Tank Erfidan, B. Çakır
In this paper, perturb and observe (P&O) algorithm is presented to grab the maximum power point from Thermoelectric Generator (TEG) sources. The main contribution of this study relies on estimating the output power of TEG by using Kalman filter to readjust the characteristics of TEG with respect to operating conditions. In the real applications, there is a disturbance appears on the power curve due to the heat distribution on the TEG surfaces. For smooth implementation of the maximum power point tracking (MPPT) algorithm and to overcome the disturbance, Kalman filter is used. It is estimate the output power curve which paves the way for MPPT to be implemented easily in the microcontroller. The feasibility of the proposed harvesting system verified experimentally.
{"title":"Improving the performance of the MPPT for thermoelectric generator system by using Kalman filter","authors":"Khalid Yahya, M. Z. Bilgin, Tank Erfidan, B. Çakır","doi":"10.1109/ICEEE2.2018.8391315","DOIUrl":"https://doi.org/10.1109/ICEEE2.2018.8391315","url":null,"abstract":"In this paper, perturb and observe (P&O) algorithm is presented to grab the maximum power point from Thermoelectric Generator (TEG) sources. The main contribution of this study relies on estimating the output power of TEG by using Kalman filter to readjust the characteristics of TEG with respect to operating conditions. In the real applications, there is a disturbance appears on the power curve due to the heat distribution on the TEG surfaces. For smooth implementation of the maximum power point tracking (MPPT) algorithm and to overcome the disturbance, Kalman filter is used. It is estimate the output power curve which paves the way for MPPT to be implemented easily in the microcontroller. The feasibility of the proposed harvesting system verified experimentally.","PeriodicalId":6482,"journal":{"name":"2018 5th International Conference on Electrical and Electronic Engineering (ICEEE)","volume":"8 1","pages":"129-132"},"PeriodicalIF":0.0,"publicationDate":"2018-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"84195203","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 : 2018-05-01DOI: 10.1109/ICEEE2.2018.8391332
Mahmoud Bagheritabar, Hamed Bagheitabar, Mohammad Mansour Riahi Kashani, N. S. Khodashenas
Regarding the fact that huge amount of non-renewable energy is extracted, distributed, converted and consumed for electrical demands in the Building-Integrated Photovoltaic systems, using the rotational photovoltaic panels as a source of energy would be more convenient. Optimization of this system which harvests outdoor natural light and indoor artificial light is an enormous need to maximize the solar panel efficiency. In this paper to achieve the main purpose, an experimental attempt has been made to model the wall and window built PV system as economical as possible. The performance of this model is carried out on the facade of buildings with a Manual switch for rotation. The result of this experiment has shown that the system is more efficient.
{"title":"Photovoltaic systems with rotational panels to harvest natural and artificial light for electrical production","authors":"Mahmoud Bagheritabar, Hamed Bagheitabar, Mohammad Mansour Riahi Kashani, N. S. Khodashenas","doi":"10.1109/ICEEE2.2018.8391332","DOIUrl":"https://doi.org/10.1109/ICEEE2.2018.8391332","url":null,"abstract":"Regarding the fact that huge amount of non-renewable energy is extracted, distributed, converted and consumed for electrical demands in the Building-Integrated Photovoltaic systems, using the rotational photovoltaic panels as a source of energy would be more convenient. Optimization of this system which harvests outdoor natural light and indoor artificial light is an enormous need to maximize the solar panel efficiency. In this paper to achieve the main purpose, an experimental attempt has been made to model the wall and window built PV system as economical as possible. The performance of this model is carried out on the facade of buildings with a Manual switch for rotation. The result of this experiment has shown that the system is more efficient.","PeriodicalId":6482,"journal":{"name":"2018 5th International Conference on Electrical and Electronic Engineering (ICEEE)","volume":"29 1","pages":"211-214"},"PeriodicalIF":0.0,"publicationDate":"2018-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"89852132","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 : 2018-05-01DOI: 10.1109/ICEEE2.2018.8391316
S. Ozden, G. Manav, M. Dursun
In this study, ANN based magnetic field modeling has been experimentally achieved for Double Sided Linear Switched Reluctance Motor (DLSRM) with 6/4 poles, 3 phases, 250W. Inductance modeling profile overlaps magnetic field data was obtained from hall-effect sensor. It is important that estimation inductance value against phase current and motor position due to main factors of the propulsion force. The precise inductance modeling helps to overcome DLSRM nonlinearity characteristic. In addition, the model is useful for controlling motor such as adaptive control methods, new developed force control methods, position control without sensor to be able removing some parts and becoming simplicity of control algorithms.
{"title":"ANN based magnetic field and inductance modeling of double sided linear switched reluctance motor","authors":"S. Ozden, G. Manav, M. Dursun","doi":"10.1109/ICEEE2.2018.8391316","DOIUrl":"https://doi.org/10.1109/ICEEE2.2018.8391316","url":null,"abstract":"In this study, ANN based magnetic field modeling has been experimentally achieved for Double Sided Linear Switched Reluctance Motor (DLSRM) with 6/4 poles, 3 phases, 250W. Inductance modeling profile overlaps magnetic field data was obtained from hall-effect sensor. It is important that estimation inductance value against phase current and motor position due to main factors of the propulsion force. The precise inductance modeling helps to overcome DLSRM nonlinearity characteristic. In addition, the model is useful for controlling motor such as adaptive control methods, new developed force control methods, position control without sensor to be able removing some parts and becoming simplicity of control algorithms.","PeriodicalId":6482,"journal":{"name":"2018 5th International Conference on Electrical and Electronic Engineering (ICEEE)","volume":"45 1","pages":"133-137"},"PeriodicalIF":0.0,"publicationDate":"2018-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"73754715","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 : 2018-05-01DOI: 10.1109/ICEEE2.2018.8391367
Sinem Aybüke Şakaci, S. Ertürk
In this paper, superpixel based spectral classification of hyperspectral images are compared using different spaces. In conventional pixel-wise HSI classification systems only use spectral information. Unlike conventional pixel-wised HSI classification, superpixel based HSI classification consider both spectral and spatial information of HSI. Support vector machine (SVM) is used as the classification method. Simple Linear Iterative Clustering (SLIC) superpixel algorithm is used to segment hyperspectral dataset into superpixels. Classification performance of hyperspectral data is compared in RGB space, LAB space, PCA space, Spectral space, and SVM. The classification performances of the methods used are tested for two different sets of data and the classification performance results are compared. It is shown that superpixel based spectral classification in PCA space and LAB space gives better classification accuracy.
{"title":"Superpixel based spectral classification of hyperspectral images in different spaces","authors":"Sinem Aybüke Şakaci, S. Ertürk","doi":"10.1109/ICEEE2.2018.8391367","DOIUrl":"https://doi.org/10.1109/ICEEE2.2018.8391367","url":null,"abstract":"In this paper, superpixel based spectral classification of hyperspectral images are compared using different spaces. In conventional pixel-wise HSI classification systems only use spectral information. Unlike conventional pixel-wised HSI classification, superpixel based HSI classification consider both spectral and spatial information of HSI. Support vector machine (SVM) is used as the classification method. Simple Linear Iterative Clustering (SLIC) superpixel algorithm is used to segment hyperspectral dataset into superpixels. Classification performance of hyperspectral data is compared in RGB space, LAB space, PCA space, Spectral space, and SVM. The classification performances of the methods used are tested for two different sets of data and the classification performance results are compared. It is shown that superpixel based spectral classification in PCA space and LAB space gives better classification accuracy.","PeriodicalId":6482,"journal":{"name":"2018 5th International Conference on Electrical and Electronic Engineering (ICEEE)","volume":"44 1","pages":"384-388"},"PeriodicalIF":0.0,"publicationDate":"2018-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"75661664","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 : 2018-05-01DOI: 10.1109/ICEEE2.2018.8391353
M. Tayel, T. Abouelnaga, A. F. Desouky
Microwave breast cancer detection has become an attractive method for cancer early detection process. These systems uses directional and efficient antenna for transmitting and receiving signals. This paper is focused on the implementation of ultra-wideband, high gain, and directional microstrip antenna array for breast cancer detection system. Metamaterial cells are used for antenna gain enhancement purpose. Permeability and permittivity of metamaterial unit cell are obtained all over the operating bandwidth. Based on the metamaterial cell performance its geometry is altered to enhance the antenna gain at specific frequency band. Ultra wide band (UWB) unequal power divider is used to feed the proposed four elements antenna array based on Chebyshev excitation method. The proposed antenna has reasonable 3 dB beamwidth (3dBBW) and gain of 17.7 degrees and 14.5 dB at 4.12 GHz, respectively. The operating bandwidth (BW) which extends from 5.6 GHz to 10.9 GHz. The proposed antenna is fabricated, measured, and good agreement is obtained between simulated and measured results. Simulated specific absorption rate SAR is obtained and investigated for breast phantom where a small tumor is placed. The SAR results show clearly the tumor location in breast tissues which ensures the suitability of the proposed antenna array for cancer detection system.
{"title":"UWB high gain antenna array for SAR based breast cancer detection system","authors":"M. Tayel, T. Abouelnaga, A. F. Desouky","doi":"10.1109/ICEEE2.2018.8391353","DOIUrl":"https://doi.org/10.1109/ICEEE2.2018.8391353","url":null,"abstract":"Microwave breast cancer detection has become an attractive method for cancer early detection process. These systems uses directional and efficient antenna for transmitting and receiving signals. This paper is focused on the implementation of ultra-wideband, high gain, and directional microstrip antenna array for breast cancer detection system. Metamaterial cells are used for antenna gain enhancement purpose. Permeability and permittivity of metamaterial unit cell are obtained all over the operating bandwidth. Based on the metamaterial cell performance its geometry is altered to enhance the antenna gain at specific frequency band. Ultra wide band (UWB) unequal power divider is used to feed the proposed four elements antenna array based on Chebyshev excitation method. The proposed antenna has reasonable 3 dB beamwidth (3dBBW) and gain of 17.7 degrees and 14.5 dB at 4.12 GHz, respectively. The operating bandwidth (BW) which extends from 5.6 GHz to 10.9 GHz. The proposed antenna is fabricated, measured, and good agreement is obtained between simulated and measured results. Simulated specific absorption rate SAR is obtained and investigated for breast phantom where a small tumor is placed. The SAR results show clearly the tumor location in breast tissues which ensures the suitability of the proposed antenna array for cancer detection system.","PeriodicalId":6482,"journal":{"name":"2018 5th International Conference on Electrical and Electronic Engineering (ICEEE)","volume":"62 1","pages":"311-316"},"PeriodicalIF":0.0,"publicationDate":"2018-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"75032356","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 : 2018-05-01DOI: 10.1109/ICEEE2.2018.8391384
Ahmed Ghareeb, Maan Tamimi, Mahmoud Jaber, Saif Jaradat, T. Khatib
This paper presents a new I-V curve prediction method using Artificial Neural Networks (ANNs), based on two ANNs, Generalized Regression Neural Network (GRNN) and cascaded forward neural network (CFNN).Solar radiation, ambient temperature, and the specification of PV module (open circuit voltage and short circuit current at STC) are inputs for this method. This method has a high accuracy in predicting I-V curves with average Mean Absolute Percentage Error (MAPE), Mean Bias Error (MBE) and Root Mean Square Error (RMSE) are 1.09%, 0.0229(A) and 0.0336(A) respectively for the validation data.
{"title":"A new method for extracting I-V characteristic curve for photovoltaic modules using artificial neural networks","authors":"Ahmed Ghareeb, Maan Tamimi, Mahmoud Jaber, Saif Jaradat, T. Khatib","doi":"10.1109/ICEEE2.2018.8391384","DOIUrl":"https://doi.org/10.1109/ICEEE2.2018.8391384","url":null,"abstract":"This paper presents a new I-V curve prediction method using Artificial Neural Networks (ANNs), based on two ANNs, Generalized Regression Neural Network (GRNN) and cascaded forward neural network (CFNN).Solar radiation, ambient temperature, and the specification of PV module (open circuit voltage and short circuit current at STC) are inputs for this method. This method has a high accuracy in predicting I-V curves with average Mean Absolute Percentage Error (MAPE), Mean Bias Error (MBE) and Root Mean Square Error (RMSE) are 1.09%, 0.0229(A) and 0.0336(A) respectively for the validation data.","PeriodicalId":6482,"journal":{"name":"2018 5th International Conference on Electrical and Electronic Engineering (ICEEE)","volume":"17 1","pages":"473-476"},"PeriodicalIF":0.0,"publicationDate":"2018-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"80176169","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 : 2018-05-01DOI: 10.1109/ICEEE2.2018.8391356
Taehoon Kim, Hyunmyoung Kim, Yeonbae Chung
With scaling of CMOS technology, data stability of SRAM at ultra-low supply voltage has become a critical issue for wearable system applications. In this paper, we present an advanced 8T SRAM which can operate properly in subthreshold voltage regime. The bit-cell utilizes a differential swing in the read and write path, and allows an efficient column-interleaving structure. In the read operation, a column-wise assistline scheme of the cell leads to the cell being unaffected by the read disturbance. In addition, the bit-cell keeps the noise-vulnerable data 'low' node voltage close to the ground level during the dummy-read operation, thus producing near-ideal voltage transfer characteristics essential for robust SRAM functionality. In the write access, the boosted wordline facilitates to change the contents of the memory bit. Implementation results with 180 nm CMOS technology exhibit that the proposed SRAM remains unaffected by the read disturbance, while achieves 59.8 % higher dummy-read stability and 3.7 times better write-ability at a subthreshold supply voltage compared to the conventional 6T SRAM.
{"title":"Design of advanced subthreshold SRAM array for ultra-low power technology","authors":"Taehoon Kim, Hyunmyoung Kim, Yeonbae Chung","doi":"10.1109/ICEEE2.2018.8391356","DOIUrl":"https://doi.org/10.1109/ICEEE2.2018.8391356","url":null,"abstract":"With scaling of CMOS technology, data stability of SRAM at ultra-low supply voltage has become a critical issue for wearable system applications. In this paper, we present an advanced 8T SRAM which can operate properly in subthreshold voltage regime. The bit-cell utilizes a differential swing in the read and write path, and allows an efficient column-interleaving structure. In the read operation, a column-wise assistline scheme of the cell leads to the cell being unaffected by the read disturbance. In addition, the bit-cell keeps the noise-vulnerable data 'low' node voltage close to the ground level during the dummy-read operation, thus producing near-ideal voltage transfer characteristics essential for robust SRAM functionality. In the write access, the boosted wordline facilitates to change the contents of the memory bit. Implementation results with 180 nm CMOS technology exhibit that the proposed SRAM remains unaffected by the read disturbance, while achieves 59.8 % higher dummy-read stability and 3.7 times better write-ability at a subthreshold supply voltage compared to the conventional 6T SRAM.","PeriodicalId":6482,"journal":{"name":"2018 5th International Conference on Electrical and Electronic Engineering (ICEEE)","volume":"41 1","pages":"329-333"},"PeriodicalIF":0.0,"publicationDate":"2018-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"84554174","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 : 2018-05-01DOI: 10.1109/ICEEE2.2018.8391386
Sait Melih Doğan, Özgül Salor
Separating the vocal and background parts of a piece of music is a very difficult task. In the literature, the process of separating vocal and background parts from musical pieces usually utilizes music repetition feature. In both Repeating Pattern Extraction Technique (REPET) and Robust Principal Component Analysis (RPCA) methods, which are among the leading studies in this field, musical pieces are separated as vocal and background music by using repetition feature of the background music. In this paper, a research study is carried out combining REPET and RPCA algorithms in order to improve the separation performance of the REPET algorithm. In order to compare performances of the proposed method with REPET and RPCA, two different tests have been carried out with selected audio tracks from the MIR-1K dataset. It has been shown by both tests that the performance of the proposed method is much better than other two methods.
{"title":"Music/singing voice separation based on repeating pattern extraction technique and robust principal component analysis","authors":"Sait Melih Doğan, Özgül Salor","doi":"10.1109/ICEEE2.2018.8391386","DOIUrl":"https://doi.org/10.1109/ICEEE2.2018.8391386","url":null,"abstract":"Separating the vocal and background parts of a piece of music is a very difficult task. In the literature, the process of separating vocal and background parts from musical pieces usually utilizes music repetition feature. In both Repeating Pattern Extraction Technique (REPET) and Robust Principal Component Analysis (RPCA) methods, which are among the leading studies in this field, musical pieces are separated as vocal and background music by using repetition feature of the background music. In this paper, a research study is carried out combining REPET and RPCA algorithms in order to improve the separation performance of the REPET algorithm. In order to compare performances of the proposed method with REPET and RPCA, two different tests have been carried out with selected audio tracks from the MIR-1K dataset. It has been shown by both tests that the performance of the proposed method is much better than other two methods.","PeriodicalId":6482,"journal":{"name":"2018 5th International Conference on Electrical and Electronic Engineering (ICEEE)","volume":"2022 1","pages":"482-487"},"PeriodicalIF":0.0,"publicationDate":"2018-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"86837606","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：