Pub Date : 2020-10-05DOI: 10.1109/SIU49456.2020.9302504
Özge Aslan, A. Yazıcı
This study deals with the problem of conflict-free route planning for multiple autonomous transport vehicles. In this study, an algorithm based on A* algorithm to solve conflict-free routing problems for multiple autonomous transport vehicles, is proposed. While classical A* algorithm plans routes for a single start and end node at the same time, the proposed algorithm plans routes for multiple start and end nodes without conflicts. The proposed algorithm apply waiting or change the route strategies to resolve conflict types. The proposed algorithm has been tested on multiple autonomous transport vehicles having different velocities (heterogeneous). Tests conducted within the scope of the study, show that the proposed algorithm finds effective conflictfree routes.
{"title":"Conflict-Free Route Planning For Autonomous Transport Vehicle","authors":"Özge Aslan, A. Yazıcı","doi":"10.1109/SIU49456.2020.9302504","DOIUrl":"https://doi.org/10.1109/SIU49456.2020.9302504","url":null,"abstract":"This study deals with the problem of conflict-free route planning for multiple autonomous transport vehicles. In this study, an algorithm based on A* algorithm to solve conflict-free routing problems for multiple autonomous transport vehicles, is proposed. While classical A* algorithm plans routes for a single start and end node at the same time, the proposed algorithm plans routes for multiple start and end nodes without conflicts. The proposed algorithm apply waiting or change the route strategies to resolve conflict types. The proposed algorithm has been tested on multiple autonomous transport vehicles having different velocities (heterogeneous). Tests conducted within the scope of the study, show that the proposed algorithm finds effective conflictfree routes.","PeriodicalId":312627,"journal":{"name":"2020 28th Signal Processing and Communications Applications Conference (SIU)","volume":"45 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":"124053251","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/SIU49456.2020.9302484
Yusuf Coşkuner, Yakup Genç
It is very practical to photograph and store documents using mobile phones. However, it is difficult to obtain a quality document image due to creases on the paper and limitations of the camera pose. These produce geometric distortions and irregular shadows on the document image. The rectification of geometric distortions requires an estimate of the 3D shape of the photographed document. In this study, we introduce a new approach that can estimate the 3D shape of the document using artificial neural networks. Neural network models extract geometric information from the context of the image to create a 3D shape. In addition, an adaptive thresholding algorithm was used to correct lighting-related distortions. Data reflecting actual document conditions were used to train the neural networks. Therefore, in addition to previous studies, the method can be applied to photograph samples which creased in many different ways and photographed from varying perspectives. Comparative experiments show that the method works well.
{"title":"Context Driven Geometry Consistent Document Reconstruction from Photographs","authors":"Yusuf Coşkuner, Yakup Genç","doi":"10.1109/SIU49456.2020.9302484","DOIUrl":"https://doi.org/10.1109/SIU49456.2020.9302484","url":null,"abstract":"It is very practical to photograph and store documents using mobile phones. However, it is difficult to obtain a quality document image due to creases on the paper and limitations of the camera pose. These produce geometric distortions and irregular shadows on the document image. The rectification of geometric distortions requires an estimate of the 3D shape of the photographed document. In this study, we introduce a new approach that can estimate the 3D shape of the document using artificial neural networks. Neural network models extract geometric information from the context of the image to create a 3D shape. In addition, an adaptive thresholding algorithm was used to correct lighting-related distortions. Data reflecting actual document conditions were used to train the neural networks. Therefore, in addition to previous studies, the method can be applied to photograph samples which creased in many different ways and photographed from varying perspectives. Comparative experiments show that the method works well.","PeriodicalId":312627,"journal":{"name":"2020 28th Signal Processing and Communications Applications Conference (SIU)","volume":"22 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":"128341341","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/SIU49456.2020.9302276
A. A. Özaslan, M. T. Arslan, E. Saritas
Magnetic Particle Imaging (MPI) is a relatively new biomedical imaging modality that images the spatial distribution of superparamagnetic iron oxide nanoparticles. In MPI, an AC excitation field is applied to induce nanoparticle signal. The magnetization response of nanoparticles to this excitation field is delayed due to the relaxation effect, which in turn can cause a significant level of resolution loss in the MPI image. In this work, a back-and-forth scanning scheme is proposed for non- Cartesian trajectories in MPI to directly estimate the relaxation time constant from the acquired MPI signal. In addition, using the estimated time constant from both scans, deconvolution of relaxation effects from the MPI signal followed by a gridding reconstruction to obtain a Cartesian MPI image is proposed. The simulation results obtained using realistic parameters show that the resolution of the reconstructed MPI image improves significantly with the proposed method, and that the image quality closely matches that of the ideal image without relaxation effects.
{"title":"Image Reconstruction with Relaxation Estimation for Non-Cartesian Magnetic Particle Imaging","authors":"A. A. Özaslan, M. T. Arslan, E. Saritas","doi":"10.1109/SIU49456.2020.9302276","DOIUrl":"https://doi.org/10.1109/SIU49456.2020.9302276","url":null,"abstract":"Magnetic Particle Imaging (MPI) is a relatively new biomedical imaging modality that images the spatial distribution of superparamagnetic iron oxide nanoparticles. In MPI, an AC excitation field is applied to induce nanoparticle signal. The magnetization response of nanoparticles to this excitation field is delayed due to the relaxation effect, which in turn can cause a significant level of resolution loss in the MPI image. In this work, a back-and-forth scanning scheme is proposed for non- Cartesian trajectories in MPI to directly estimate the relaxation time constant from the acquired MPI signal. In addition, using the estimated time constant from both scans, deconvolution of relaxation effects from the MPI signal followed by a gridding reconstruction to obtain a Cartesian MPI image is proposed. The simulation results obtained using realistic parameters show that the resolution of the reconstructed MPI image improves significantly with the proposed method, and that the image quality closely matches that of the ideal image without relaxation effects.","PeriodicalId":312627,"journal":{"name":"2020 28th Signal Processing and Communications Applications Conference (SIU)","volume":"20 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":"129592201","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/SIU49456.2020.9302102
Kenan Serdar Kavlak, M. Çelebi
In non-orthogonal multiple access systems, the problem of resource allocation is generally addressed in two stages. These steps determine a proper power allocation and user pairing method for the system. In this work, optimal fair resource allocation has been proposed as the solution to the resource allocation problem in the literature. This method aims to provide superiority to orthogonal multiple access by providing fairness among users under certain constraints. Firstly, the necessary power allocation coefficients are calculated to maximize the system's achievable data rate by taking into account the quality of service requirements at the power allocation stage. A new algorithm is then proposed to ensure optimal user pairing. In the simulations, it is shown that the proposed method increases the efficiency as much as 35% in terms of sum rate of the system. In addition, the proposed method is compared to another well-known method that also proposes a user pairing algorithm, and better performance is achieved.
{"title":"Optimal Fair Resource Allocation for Downlink NOMA Systems","authors":"Kenan Serdar Kavlak, M. Çelebi","doi":"10.1109/SIU49456.2020.9302102","DOIUrl":"https://doi.org/10.1109/SIU49456.2020.9302102","url":null,"abstract":"In non-orthogonal multiple access systems, the problem of resource allocation is generally addressed in two stages. These steps determine a proper power allocation and user pairing method for the system. In this work, optimal fair resource allocation has been proposed as the solution to the resource allocation problem in the literature. This method aims to provide superiority to orthogonal multiple access by providing fairness among users under certain constraints. Firstly, the necessary power allocation coefficients are calculated to maximize the system's achievable data rate by taking into account the quality of service requirements at the power allocation stage. A new algorithm is then proposed to ensure optimal user pairing. In the simulations, it is shown that the proposed method increases the efficiency as much as 35% in terms of sum rate of the system. In addition, the proposed method is compared to another well-known method that also proposes a user pairing algorithm, and better performance is achieved.","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":"129632193","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/SIU49456.2020.9302368
Muammer Turkoglu, Huseyin Uzen, D. Hanbay
{"title":"A deep feature extractor approach for the recognition of pollen-bearing bees","authors":"Muammer Turkoglu, Huseyin Uzen, D. Hanbay","doi":"10.1109/SIU49456.2020.9302368","DOIUrl":"https://doi.org/10.1109/SIU49456.2020.9302368","url":null,"abstract":"","PeriodicalId":312627,"journal":{"name":"2020 28th Signal Processing and Communications Applications Conference (SIU)","volume":"56 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":"130769616","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/SIU49456.2020.9302063
Mustafa Temiz, Ahmet Soran, Halil Arslan, Hilal Erel
Blockchain is a reliable and transparent structure formed by distributing the data in blocks connected to each other using various cryptography techniques to other points on the network. The difference from the existing database operations is that the authorities and responsibilities do not exist in a single central authority, and that these powers and responsibilities are distributed to the other nodes in the network and the assignment is shared. To provide this, peer to peer network infrastructure is used. However, at this stage, authentication in terms of security is one of the basic security mechanisms. In this study, a user management system which can be integrated with more reliable and current technologies, which is thought to be the solution to speed problems in blockchain, is proposed.
{"title":"Blockchain Based User Management System","authors":"Mustafa Temiz, Ahmet Soran, Halil Arslan, Hilal Erel","doi":"10.1109/SIU49456.2020.9302063","DOIUrl":"https://doi.org/10.1109/SIU49456.2020.9302063","url":null,"abstract":"Blockchain is a reliable and transparent structure formed by distributing the data in blocks connected to each other using various cryptography techniques to other points on the network. The difference from the existing database operations is that the authorities and responsibilities do not exist in a single central authority, and that these powers and responsibilities are distributed to the other nodes in the network and the assignment is shared. To provide this, peer to peer network infrastructure is used. However, at this stage, authentication in terms of security is one of the basic security mechanisms. In this study, a user management system which can be integrated with more reliable and current technologies, which is thought to be the solution to speed problems in blockchain, is proposed.","PeriodicalId":312627,"journal":{"name":"2020 28th Signal Processing and Communications Applications Conference (SIU)","volume":"32 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":"132467788","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/SIU49456.2020.9302182
Aytuğ Onan
In the era of big data, natural language processing becomes an important research discipline, owing to the immense quantity of text documents and the progresses in machine learning. Natural language processing has been succesfully employed in many different areas, including machine translation, search engines, virtual assistants, spam filtering, question answering and sentiment analysis. Recent studies in the field of natural language processing indicate that word embedding based representation, in which words have been represented in dense spaces through fixed length vectors, can yield promising results. In this study, we evaluate the predictive performance of 36 word embedding based representation obtained by three word embedding methods (i.e., word2vec, fastText and DOC2vec), two basic weighting functions (i.e., inverse document frequency and smooth inverse document frequency) and three vector pooling schemes (namely, weighted sum, center based approach and delta rule). Experimental analysis indicates that word2vec based representation in conjunction with inverse document frequency based weighting and center based pooling, yields promising results for sentiment analysis in Turkish.
{"title":"Sentiment Analysis in Turkish Based on Weighted Word Embeddings","authors":"Aytuğ Onan","doi":"10.1109/SIU49456.2020.9302182","DOIUrl":"https://doi.org/10.1109/SIU49456.2020.9302182","url":null,"abstract":"In the era of big data, natural language processing becomes an important research discipline, owing to the immense quantity of text documents and the progresses in machine learning. Natural language processing has been succesfully employed in many different areas, including machine translation, search engines, virtual assistants, spam filtering, question answering and sentiment analysis. Recent studies in the field of natural language processing indicate that word embedding based representation, in which words have been represented in dense spaces through fixed length vectors, can yield promising results. In this study, we evaluate the predictive performance of 36 word embedding based representation obtained by three word embedding methods (i.e., word2vec, fastText and DOC2vec), two basic weighting functions (i.e., inverse document frequency and smooth inverse document frequency) and three vector pooling schemes (namely, weighted sum, center based approach and delta rule). Experimental analysis indicates that word2vec based representation in conjunction with inverse document frequency based weighting and center based pooling, yields promising results for sentiment analysis in Turkish.","PeriodicalId":312627,"journal":{"name":"2020 28th Signal Processing and Communications Applications Conference (SIU)","volume":"32 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":"132894471","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/SIU49456.2020.9302245
I. Altin, Emre Bilican, Özge Özaltın
In this study, we propose a novel Narrowband Internet of Things (NB-IoT) NPUSCH Format 2 receiver with DTX detection. The proposed method uses the channel estimation results to identify the DTX situation. The method performs better than NPUSCH Format 2 requirements identified in the 3GPP standards.
{"title":"A Novel NPUSCH Format 2 Receiver with DTX Detection","authors":"I. Altin, Emre Bilican, Özge Özaltın","doi":"10.1109/SIU49456.2020.9302245","DOIUrl":"https://doi.org/10.1109/SIU49456.2020.9302245","url":null,"abstract":"In this study, we propose a novel Narrowband Internet of Things (NB-IoT) NPUSCH Format 2 receiver with DTX detection. The proposed method uses the channel estimation results to identify the DTX situation. The method performs better than NPUSCH Format 2 requirements identified in the 3GPP standards.","PeriodicalId":312627,"journal":{"name":"2020 28th Signal Processing and Communications Applications Conference (SIU)","volume":"33 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":"132047389","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/SIU49456.2020.9302460
Selim Sahin, Çagri Demir, I. Erer
In this paper we inspect two mine detection algorithms [2,3], suggest modifications and present results on detection of anti-personnel (AP) landmines using methods employing Auto Regressive (AR) modeling algortihms. First method is based on the statistical distance between AR models of the reference and simulated data. In literature, while the statistical distance is calculated only for A-Scan data, in this study we suggest statistical distance to be calculated for both A-Scan and rows of the processed data. The second method is relied on AR modeling of the clutter energy in the B-scan. To decide whether a threat signature is present, it is proposed to utilize the difference between the estimated AR model clutter energy and the energy of real data. It is shown that proposed AR model based algorithms can be utilized to detect threat in GPR data and some advices to improve detection performance are given.
{"title":"Threat Detection In GPR Data Using Autoregressive Modelling","authors":"Selim Sahin, Çagri Demir, I. Erer","doi":"10.1109/SIU49456.2020.9302460","DOIUrl":"https://doi.org/10.1109/SIU49456.2020.9302460","url":null,"abstract":"In this paper we inspect two mine detection algorithms [2,3], suggest modifications and present results on detection of anti-personnel (AP) landmines using methods employing Auto Regressive (AR) modeling algortihms. First method is based on the statistical distance between AR models of the reference and simulated data. In literature, while the statistical distance is calculated only for A-Scan data, in this study we suggest statistical distance to be calculated for both A-Scan and rows of the processed data. The second method is relied on AR modeling of the clutter energy in the B-scan. To decide whether a threat signature is present, it is proposed to utilize the difference between the estimated AR model clutter energy and the energy of real data. It is shown that proposed AR model based algorithms can be utilized to detect threat in GPR data and some advices to improve detection performance are given.","PeriodicalId":312627,"journal":{"name":"2020 28th Signal Processing and Communications Applications Conference (SIU)","volume":"116 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":"132180804","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/SIU49456.2020.9302424
Yasin YenIaydin, Klaus Werner Schmidt
This study proposes a novel lane detection and tracking algorithm. Firstly, feature extraction is performed by convolving a grayscale bird’s eye view image with a 1 dimensional top-hat kernel and applying a histogram computation afterwards. Next, the Hough Transform is applied to detect lines that are then merged based on their geometrical characteristics. Then, the best lane pair is selected based on a custom cost function. Lastly, polynomial lane model parameters are estimated for the best lane pair and tracked by a Kalman Filter. Our computational results show that the proposed method can detect lanes in complex cases and increase the lane detection accuracy. Keywords—lane detection, histogram, hough transform, lane model, top-hat kernel.
{"title":"Lane Detection and Tracking based on Best Pairs of Lane Markings: Method and Evaluation","authors":"Yasin YenIaydin, Klaus Werner Schmidt","doi":"10.1109/SIU49456.2020.9302424","DOIUrl":"https://doi.org/10.1109/SIU49456.2020.9302424","url":null,"abstract":"This study proposes a novel lane detection and tracking algorithm. Firstly, feature extraction is performed by convolving a grayscale bird’s eye view image with a 1 dimensional top-hat kernel and applying a histogram computation afterwards. Next, the Hough Transform is applied to detect lines that are then merged based on their geometrical characteristics. Then, the best lane pair is selected based on a custom cost function. Lastly, polynomial lane model parameters are estimated for the best lane pair and tracked by a Kalman Filter. Our computational results show that the proposed method can detect lanes in complex cases and increase the lane detection accuracy. Keywords—lane detection, histogram, hough transform, lane model, top-hat kernel.","PeriodicalId":312627,"journal":{"name":"2020 28th Signal Processing and Communications Applications Conference (SIU)","volume":"18 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":"131730901","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：