Pub Date : 2020-10-05DOI: 10.1109/SIU49456.2020.9302376
Eylem Tugce Guneyi, Elif Vural
Graphs permit the analysis of the relationships in complex data sets effectively. Stationarity is a feature that facilitates the analysis and processing of random time signals. Since graphs have an irregular structure, the definition of classical stationarity does not apply to graphs. In this study, we study how stationarity is defined for graph random processes and examine the validity of the stationarity assumption with experiments on synthetic and real data sets.
{"title":"Investigation of Stationarity for Graph Time Series Data Sets","authors":"Eylem Tugce Guneyi, Elif Vural","doi":"10.1109/SIU49456.2020.9302376","DOIUrl":"https://doi.org/10.1109/SIU49456.2020.9302376","url":null,"abstract":"Graphs permit the analysis of the relationships in complex data sets effectively. Stationarity is a feature that facilitates the analysis and processing of random time signals. Since graphs have an irregular structure, the definition of classical stationarity does not apply to graphs. In this study, we study how stationarity is defined for graph random processes and examine the validity of the stationarity assumption with experiments on synthetic and real data sets.","PeriodicalId":312627,"journal":{"name":"2020 28th Signal Processing and Communications Applications Conference (SIU)","volume":"14 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-10-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125760616","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 : 2020-10-05DOI: 10.1109/SIU49456.2020.9302310
Nihal Aktaş, Ali Burak Can
In case of any problems in the products and services of the companies, the first person contacted is the customer representative. Customer representatives are the visible face of the companies and they represent the companies directly. Therefore, any kind of innovation that will provide added value to customer service and its representatives will contribute to the company. Before digital media became as widespread as it is today, customers were only served by phone or mail. But nowadays, with the spread of digitalization, many new channels started to be provided, the world of written channels, especially in the customer service sector, now occupies a huge place. Considering that the customer prefers communication through written channels, this leads to extra efforts by the customer representatives. The customer representative, who usually faces similar problems, constantly writes the same things and at some point turns into a robot. At this point, our solution to this problem will be explained in this study. The solution we offer is to classify the most common problems and offer answers to the customer representative if the same issue is encountered again by using natural language.
{"title":"Recommendation System for Customer Service Through Chat Channels","authors":"Nihal Aktaş, Ali Burak Can","doi":"10.1109/SIU49456.2020.9302310","DOIUrl":"https://doi.org/10.1109/SIU49456.2020.9302310","url":null,"abstract":"In case of any problems in the products and services of the companies, the first person contacted is the customer representative. Customer representatives are the visible face of the companies and they represent the companies directly. Therefore, any kind of innovation that will provide added value to customer service and its representatives will contribute to the company. Before digital media became as widespread as it is today, customers were only served by phone or mail. But nowadays, with the spread of digitalization, many new channels started to be provided, the world of written channels, especially in the customer service sector, now occupies a huge place. Considering that the customer prefers communication through written channels, this leads to extra efforts by the customer representatives. The customer representative, who usually faces similar problems, constantly writes the same things and at some point turns into a robot. At this point, our solution to this problem will be explained in this study. The solution we offer is to classify the most common problems and offer answers to the customer representative if the same issue is encountered again by using natural language.","PeriodicalId":312627,"journal":{"name":"2020 28th Signal Processing and Communications Applications Conference (SIU)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-10-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122265468","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 : 2020-10-05DOI: 10.1109/SIU49456.2020.9302473
Kubra Nur Akpinar, O. Ozgonenel, U. Kurt
In this study, Stockwell transform and artificial neural network were used in determining the inrush current and the internal current fault based on the power transformer protection. The S-transform is a robust transform that incorporates the time and frequency characteristics used in the analysis of non-stationary short term transient signals. It is used for pattern recognition for distinction between internal faults and inrush current. Time-frequency images were obtained by using S-transform, and the obtained images were observed to be different in internal faults and inrush current. The feature extraction is based on statistical methods, standard deviation and average value, the classification process was performed with the multilayer feed forward artificial neural network. The classification performance is calculated at a hundred percent accuracy.
{"title":"Transformer Protection Algorithm Based on S-Transform","authors":"Kubra Nur Akpinar, O. Ozgonenel, U. Kurt","doi":"10.1109/SIU49456.2020.9302473","DOIUrl":"https://doi.org/10.1109/SIU49456.2020.9302473","url":null,"abstract":"In this study, Stockwell transform and artificial neural network were used in determining the inrush current and the internal current fault based on the power transformer protection. The S-transform is a robust transform that incorporates the time and frequency characteristics used in the analysis of non-stationary short term transient signals. It is used for pattern recognition for distinction between internal faults and inrush current. Time-frequency images were obtained by using S-transform, and the obtained images were observed to be different in internal faults and inrush current. The feature extraction is based on statistical methods, standard deviation and average value, the classification process was performed with the multilayer feed forward artificial neural network. The classification performance is calculated at a hundred percent accuracy.","PeriodicalId":312627,"journal":{"name":"2020 28th Signal Processing and Communications Applications Conference (SIU)","volume":"67 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-10-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121451276","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 : 2020-10-05DOI: 10.1109/SIU49456.2020.9302445
Burak Tufekci, Bugra Onal, Hamza Dere, H. F. Ugurdag
—This paper presents a high switching frequency FPGA implementation of Maximum Torque Per Ampere (MTPA) and Flux Weakening which are branch of Field Oriented Control (FOC) method for 3-phase machine drives. A common architec-ture has been constructed for both BrushLess DC motors (BLDC) and Permanent Magnet Synchronous Motors (PMSM). For this purpose, the controller module was implemented using Space Vector Modulation (SVM) technique. The user interface module was designed to provide real-time torque-time, speed-time, and current-time plots for the user. This interface runs on the PS part of the FPGA and interacts with the user through a UART. The entire system has been verified through simulation.
{"title":"Hardware Implementation of Field Oriented Control for Three Phase Machine Drives","authors":"Burak Tufekci, Bugra Onal, Hamza Dere, H. F. Ugurdag","doi":"10.1109/SIU49456.2020.9302445","DOIUrl":"https://doi.org/10.1109/SIU49456.2020.9302445","url":null,"abstract":"—This paper presents a high switching frequency FPGA implementation of Maximum Torque Per Ampere (MTPA) and Flux Weakening which are branch of Field Oriented Control (FOC) method for 3-phase machine drives. A common architec-ture has been constructed for both BrushLess DC motors (BLDC) and Permanent Magnet Synchronous Motors (PMSM). For this purpose, the controller module was implemented using Space Vector Modulation (SVM) technique. The user interface module was designed to provide real-time torque-time, speed-time, and current-time plots for the user. This interface runs on the PS part of the FPGA and interacts with the user through a UART. The entire system has been verified through simulation.","PeriodicalId":312627,"journal":{"name":"2020 28th Signal Processing and Communications Applications Conference (SIU)","volume":"102 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-10-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115813898","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 : 2020-10-05DOI: 10.1109/SIU49456.2020.9302097
B. Sezgin, Mustafa Direk, Mert Külte, M. Eskin, M. E. Sudaduran, Emrah Abtioglu, Mustafa Tanış, M. Yalçin
GEZSAN (Real Time Spectrum Analyzer): It covers satellite communication, LTE, 4G, 4.5G, Wi-Fi, GSM and cable and wireless communication systems used in broadcasting. GEZSAN is a system-on-chip that can calculate the frequency spectrum up to 50 MHz in real time and also up to 6 GHz with the help of Fast Fourier Transform (FFT) in broadband. The designed system consists of radio frequency front layer, Field Programmable Gate Array (FPGA) and embedded hardware layers. In this study, GEZSAN design, implementation and tests are presented.
{"title":"GEZSAN — Real Time Spectrum Analyzer","authors":"B. Sezgin, Mustafa Direk, Mert Külte, M. Eskin, M. E. Sudaduran, Emrah Abtioglu, Mustafa Tanış, M. Yalçin","doi":"10.1109/SIU49456.2020.9302097","DOIUrl":"https://doi.org/10.1109/SIU49456.2020.9302097","url":null,"abstract":"GEZSAN (Real Time Spectrum Analyzer): It covers satellite communication, LTE, 4G, 4.5G, Wi-Fi, GSM and cable and wireless communication systems used in broadcasting. GEZSAN is a system-on-chip that can calculate the frequency spectrum up to 50 MHz in real time and also up to 6 GHz with the help of Fast Fourier Transform (FFT) in broadband. The designed system consists of radio frequency front layer, Field Programmable Gate Array (FPGA) and embedded hardware layers. In this study, GEZSAN design, implementation and tests are presented.","PeriodicalId":312627,"journal":{"name":"2020 28th Signal Processing and Communications Applications Conference (SIU)","volume":"35 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-10-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115849732","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 : 2020-10-05DOI: 10.1109/SIU49456.2020.9302158
Hüseyin Özmen, M. B. Kurt
In this study, a microwave imaging system was performed in simulation environment for the detection of breast cancer at an early stage. An ultra wide band, high gain, directional Vivaldi antenna was used as a biomedical sensor. An anatomically and physically realistic homogeneous breast model was created as a hemisphere. Two tumors with a radius of 1mm were placed in different locations. Using the signal processing techniques, these two tumors were successfully imaged in the correct locations.
{"title":"Radar based Microwave Imaging System Simulation for Early Detection of Breast Cancer","authors":"Hüseyin Özmen, M. B. Kurt","doi":"10.1109/SIU49456.2020.9302158","DOIUrl":"https://doi.org/10.1109/SIU49456.2020.9302158","url":null,"abstract":"In this study, a microwave imaging system was performed in simulation environment for the detection of breast cancer at an early stage. An ultra wide band, high gain, directional Vivaldi antenna was used as a biomedical sensor. An anatomically and physically realistic homogeneous breast model was created as a hemisphere. Two tumors with a radius of 1mm were placed in different locations. Using the signal processing techniques, these two tumors were successfully imaged in the correct locations.","PeriodicalId":312627,"journal":{"name":"2020 28th Signal Processing and Communications Applications Conference (SIU)","volume":"617 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-10-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131964484","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 : 2020-10-05DOI: 10.1109/SIU49456.2020.9302467
Mesut Seker, M. S. Özerdem
In this experimental study, an EEG coherence based approach is proposed for diagnosis of schizophrenia (sch). In this sense, coherence values estimated from 6 interhemispheric, 3 of left and right intra-hemispheric electrode pairs selected from 16 EEG channel system were used as feature vectors. Classification algorithms of k-nearest neighbor (k-NN), support vector machine (SVM) and multi-layer perceptron (MLP) were utilized for discrimination of coherences belonging sch and healthy (norm) participants. In proposed study, coherence measurements of sch patients were observed slightly lower according to norm groups over all brain regions. Increasing coherence measurements were observed at higher frequency bands (beta-gamma) for sch patients. While higher amplitude of coherence values are achieved for inter-hemispheric electrode pairs (F3-F4, C3-C4), diagnostic ratio of sch is also concvincing as compare with intra-hemispheric electrodes. High achievement of inter-hemispheric electrode pairs stems from definite distance between two probes located on different hemisphere. Moreover, diagnosis of sch is performed effectively at right hemisphere compared to left. In binary classification of sch and norm, highest accuracy was obtained as 99.22% using k-NN algorithm. Proposed work is thought to generate effective solutions for diagnosis of sch disorder in clinical applications.
{"title":"EEG Coherence as a Neuro-marker for Diagnosis of Schizophrenia","authors":"Mesut Seker, M. S. Özerdem","doi":"10.1109/SIU49456.2020.9302467","DOIUrl":"https://doi.org/10.1109/SIU49456.2020.9302467","url":null,"abstract":"In this experimental study, an EEG coherence based approach is proposed for diagnosis of schizophrenia (sch). In this sense, coherence values estimated from 6 interhemispheric, 3 of left and right intra-hemispheric electrode pairs selected from 16 EEG channel system were used as feature vectors. Classification algorithms of k-nearest neighbor (k-NN), support vector machine (SVM) and multi-layer perceptron (MLP) were utilized for discrimination of coherences belonging sch and healthy (norm) participants. In proposed study, coherence measurements of sch patients were observed slightly lower according to norm groups over all brain regions. Increasing coherence measurements were observed at higher frequency bands (beta-gamma) for sch patients. While higher amplitude of coherence values are achieved for inter-hemispheric electrode pairs (F3-F4, C3-C4), diagnostic ratio of sch is also concvincing as compare with intra-hemispheric electrodes. High achievement of inter-hemispheric electrode pairs stems from definite distance between two probes located on different hemisphere. Moreover, diagnosis of sch is performed effectively at right hemisphere compared to left. In binary classification of sch and norm, highest accuracy was obtained as 99.22% using k-NN algorithm. Proposed work is thought to generate effective solutions for diagnosis of sch disorder in clinical applications.","PeriodicalId":312627,"journal":{"name":"2020 28th Signal Processing and Communications Applications Conference (SIU)","volume":"29 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-10-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132394341","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 : 2020-10-05DOI: 10.1109/SIU49456.2020.9302123
C. Vural, Enver Akbacak
Existing video retrieval studies support single query. To the best of our knowledge, there is no multi-query video retrieval method. In this study, an efficient and fast multi-query video retrieval method is proposed for queries having different semantics. The metod supports unlimited number of queries. Real valued features representing a video are extracted by a deep network and are converted into binary codes. Database items that simultaneously most closely resemble multiple queries are retrieved by Pareto front method. Efficiency of the method is determined by means of a designed graphical user interface.
{"title":"Multi-Query Video Retrieval Based on Deep Learning and Pareto Optimality","authors":"C. Vural, Enver Akbacak","doi":"10.1109/SIU49456.2020.9302123","DOIUrl":"https://doi.org/10.1109/SIU49456.2020.9302123","url":null,"abstract":"Existing video retrieval studies support single query. To the best of our knowledge, there is no multi-query video retrieval method. In this study, an efficient and fast multi-query video retrieval method is proposed for queries having different semantics. The metod supports unlimited number of queries. Real valued features representing a video are extracted by a deep network and are converted into binary codes. Database items that simultaneously most closely resemble multiple queries are retrieved by Pareto front method. Efficiency of the method is determined by means of a designed graphical user interface.","PeriodicalId":312627,"journal":{"name":"2020 28th Signal Processing and Communications Applications Conference (SIU)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-10-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129982814","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 : 2020-10-05DOI: 10.1109/SIU49456.2020.9302250
Onur Karaoglu, H. Ş. Bilge, I. Uluer
Image enhancement aims to obtain a clear image from a noisy image and it also uses for ultrasound images. In the experimental study, unlike classical image enhancement methods, deep learning method was used. Different levels of speckle noise added to the ultrasound images of the brachial plexus, which is known as the large nerve community under the armpit, were tried to be removed with the help of the convolutional denoising autoencoder network, which is one of the deep learning methods. The results obtained from the experimental study were compared with classical methods results and the proposed method was found to be more successful than classical methods.
{"title":"Reducing Speckle Noise from Ultrasound Images Using an Autoencoder Network","authors":"Onur Karaoglu, H. Ş. Bilge, I. Uluer","doi":"10.1109/SIU49456.2020.9302250","DOIUrl":"https://doi.org/10.1109/SIU49456.2020.9302250","url":null,"abstract":"Image enhancement aims to obtain a clear image from a noisy image and it also uses for ultrasound images. In the experimental study, unlike classical image enhancement methods, deep learning method was used. Different levels of speckle noise added to the ultrasound images of the brachial plexus, which is known as the large nerve community under the armpit, were tried to be removed with the help of the convolutional denoising autoencoder network, which is one of the deep learning methods. The results obtained from the experimental study were compared with classical methods results and the proposed method was found to be more successful than classical methods.","PeriodicalId":312627,"journal":{"name":"2020 28th Signal Processing and Communications Applications Conference (SIU)","volume":"10 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-10-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133936415","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 : 2020-10-05DOI: 10.1109/SIU49456.2020.9302160
Umut Can Çabuk, M. Tosun, R. Jacobsen, O. Dagdeviren
Unmanned aerial vehicles (UAV) are being used increasingly more within military campaigns, commercial services, and industrial projects. Though using UAVs on such missions is not a new phenomenon anymore, forming them into autonomous groups (called swarms) to accomplish the missions more efficiently is still a hot topic. To implement smart algorithms efficiently in UAV swarms, it is crucial to consider device capabilities, networking technologies, and environmental conditions. A wireless channel model involving path loss is a fundamental element of designing efficient networking schemes for swarms. This paper presents the adoption of known channel models to air-to-air UAV communication scenarios and discusses the results of an exemplary simulation that reckons a swarm of multi-copter UAVs flying over rugged terrains. Wi-Fi (n/ac) is considered to form an ad-hoc network within the swarm due to the need for high data bandwidth.
{"title":"Path Loss Estimation of Air-to-Air Channels for FANETs over Rugged Terrains","authors":"Umut Can Çabuk, M. Tosun, R. Jacobsen, O. Dagdeviren","doi":"10.1109/SIU49456.2020.9302160","DOIUrl":"https://doi.org/10.1109/SIU49456.2020.9302160","url":null,"abstract":"Unmanned aerial vehicles (UAV) are being used increasingly more within military campaigns, commercial services, and industrial projects. Though using UAVs on such missions is not a new phenomenon anymore, forming them into autonomous groups (called swarms) to accomplish the missions more efficiently is still a hot topic. To implement smart algorithms efficiently in UAV swarms, it is crucial to consider device capabilities, networking technologies, and environmental conditions. A wireless channel model involving path loss is a fundamental element of designing efficient networking schemes for swarms. This paper presents the adoption of known channel models to air-to-air UAV communication scenarios and discusses the results of an exemplary simulation that reckons a swarm of multi-copter UAVs flying over rugged terrains. Wi-Fi (n/ac) is considered to form an ad-hoc network within the swarm due to the need for high data bandwidth.","PeriodicalId":312627,"journal":{"name":"2020 28th Signal Processing and Communications Applications Conference (SIU)","volume":"47 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-10-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133961144","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：