Pub Date : 2020-10-05DOI: 10.1109/SIU49456.2020.9302166
Berrak Ozturk Simsek, A. Akan
In this study, a new method is proposed for predominant audio melody extraction in monophonic Turkish maqam music works. The music signals are decomposed using the Improved Variable Mode Decomposition Method and the fundamental frequencies are obtained by calculation of center frequencies on each mode. In order to estimate and selection of predominant melody line some parameters are determined from the different number of frequency information in each window. The obtained results are compared to YIN and MELODIA which are the signal processing algorithms used for western music. MIREX criterias are used in the evaluation step, adhering to international standards. Simulation results have shown that Improved Variable Mode Decomposition Method gives more successful results than other methods used in comparison.
{"title":"Audio Melody Extraction from Monophonic Turkish Maqam Music","authors":"Berrak Ozturk Simsek, A. Akan","doi":"10.1109/SIU49456.2020.9302166","DOIUrl":"https://doi.org/10.1109/SIU49456.2020.9302166","url":null,"abstract":"In this study, a new method is proposed for predominant audio melody extraction in monophonic Turkish maqam music works. The music signals are decomposed using the Improved Variable Mode Decomposition Method and the fundamental frequencies are obtained by calculation of center frequencies on each mode. In order to estimate and selection of predominant melody line some parameters are determined from the different number of frequency information in each window. The obtained results are compared to YIN and MELODIA which are the signal processing algorithms used for western music. MIREX criterias are used in the evaluation step, adhering to international standards. Simulation results have shown that Improved Variable Mode Decomposition Method gives more successful results than other methods used in comparison.","PeriodicalId":312627,"journal":{"name":"2020 28th Signal Processing and Communications Applications Conference (SIU)","volume":"9 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":"122240161","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/SIU49456.2020.9302169
Fatih Ilhan, S. Tekin, Bilgin Aksoy
In this paper, we propose a new deep learning based model that uses convolutional neural networks for spatiotemporal crime prediction. To learn the temporal pattern of crime events, we employ a temporally hierarchical structure that branches along the temporal dimension. In addition, channel projection is applied to capture the separate influences of crime events over future crime risk. In the results section, our model is compared with classical methods and the performance is analyzed on publicly available Chicago and Los Angeles crime datasets. The proposed model significantly improves the performance compared to the traditional methods.
{"title":"Spatio-Temporal Crime Prediction with Temporally Hierarchical Convolutional Neural Networks","authors":"Fatih Ilhan, S. Tekin, Bilgin Aksoy","doi":"10.1109/SIU49456.2020.9302169","DOIUrl":"https://doi.org/10.1109/SIU49456.2020.9302169","url":null,"abstract":"In this paper, we propose a new deep learning based model that uses convolutional neural networks for spatiotemporal crime prediction. To learn the temporal pattern of crime events, we employ a temporally hierarchical structure that branches along the temporal dimension. In addition, channel projection is applied to capture the separate influences of crime events over future crime risk. In the results section, our model is compared with classical methods and the performance is analyzed on publicly available Chicago and Los Angeles crime datasets. The proposed model significantly improves the performance compared to the traditional methods.","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":"122256552","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/SIU49456.2020.9302518
Yılmaz Bayindir, Yakup S. Özkazanç
LPI radar is a special kind of radar which incorporates some features and techniques to avoid being detected. Because of their advantages, FMCW waveform is often used in LPI emitters. In this work, an original method based on hidden Markov model is suggested for the detection of FMCW. The suggested method is composed of learning and decoding layers. As a result of the simulations, it is observed that several simultaneous LPI emitters having low SNR can be detected in a wide dynamic range.
{"title":"LPI Emitter Detection Based on Hidden Markov Model","authors":"Yılmaz Bayindir, Yakup S. Özkazanç","doi":"10.1109/SIU49456.2020.9302518","DOIUrl":"https://doi.org/10.1109/SIU49456.2020.9302518","url":null,"abstract":"LPI radar is a special kind of radar which incorporates some features and techniques to avoid being detected. Because of their advantages, FMCW waveform is often used in LPI emitters. In this work, an original method based on hidden Markov model is suggested for the detection of FMCW. The suggested method is composed of learning and decoding layers. As a result of the simulations, it is observed that several simultaneous LPI emitters having low SNR can be detected in a wide dynamic range.","PeriodicalId":312627,"journal":{"name":"2020 28th Signal Processing and Communications Applications Conference (SIU)","volume":"98 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":"126097757","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/SIU49456.2020.9302423
Utku Ozmat, M. Demirkol, Nuran Demirci, Mehmet Akif Yazici
Physical layer security has gained importance with the widespread use of wireless communication systems. Multiantenna systems and multi-point transmission techniques in 5G and beyond are promising techniques not only for enhancing data rates, but also physical layer security. Coordinated multipoint transmission is used for enhancing the service quality and decreasing inter-cell interference especially for cell-edge users. In this study, analysis of physical layer security enhancement via multi-antenna technologies and coordinated multi-point for 5G and beyond networks is provided. The proposed scheme is evaluated on calculations from real-life mobile network topologies. As a figure of performance, the secure and successful detection probability is computed with varying antenna array size, number of coordinated transmission points, and different service requirements. Keywords—physical layer security, coordinated multi-point, 5G, mMIMO.
随着无线通信系统的广泛应用，物理层安全变得越来越重要。5G及以后的多天线系统和多点传输技术不仅可以提高数据速率，还可以提高物理层的安全性。为了提高服务质量，减少小区间干扰，特别是小区边缘用户的干扰，采用了协调多点传输。在本研究中，通过多天线技术和协调多点技术对5G及以上网络的物理层安全性进行了分析。该方案通过实际移动网络拓扑计算进行了评估。作为一种性能指标，在不同的天线阵列尺寸、协调发射点数量和不同的业务需求下，计算安全成功的检测概率。关键词:物理层安全，协同多点，5G, mimo
{"title":"Enhancing Physical Layer Security with Coordinated Multi-Point Transmission in 5G and Beyond Networks","authors":"Utku Ozmat, M. Demirkol, Nuran Demirci, Mehmet Akif Yazici","doi":"10.1109/SIU49456.2020.9302423","DOIUrl":"https://doi.org/10.1109/SIU49456.2020.9302423","url":null,"abstract":"Physical layer security has gained importance with the widespread use of wireless communication systems. Multiantenna systems and multi-point transmission techniques in 5G and beyond are promising techniques not only for enhancing data rates, but also physical layer security. Coordinated multipoint transmission is used for enhancing the service quality and decreasing inter-cell interference especially for cell-edge users. In this study, analysis of physical layer security enhancement via multi-antenna technologies and coordinated multi-point for 5G and beyond networks is provided. The proposed scheme is evaluated on calculations from real-life mobile network topologies. As a figure of performance, the secure and successful detection probability is computed with varying antenna array size, number of coordinated transmission points, and different service requirements. Keywords—physical layer security, coordinated multi-point, 5G, mMIMO.","PeriodicalId":312627,"journal":{"name":"2020 28th Signal Processing and Communications Applications Conference (SIU)","volume":"469 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":"115323969","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/SIU49456.2020.9302203
Y. K. Alp, Gokhan Gok
In this work, a simple method for improving the performance of three DFT coefficients based fine frequency estimators is proposed. The computational complexity of the proposed method is quite low that it requires only a few additional multiplications and additions. Conducted simulations implies that the estimator improved by the proposed method has lower bias error, shows a better RMS error performance at all SNR levels and achieves the CRLB as the SNR increases.
{"title":"A Simple Method for Improving the Performance of Three DFT Coefficients Based Frequency Estimators","authors":"Y. K. Alp, Gokhan Gok","doi":"10.1109/SIU49456.2020.9302203","DOIUrl":"https://doi.org/10.1109/SIU49456.2020.9302203","url":null,"abstract":"In this work, a simple method for improving the performance of three DFT coefficients based fine frequency estimators is proposed. The computational complexity of the proposed method is quite low that it requires only a few additional multiplications and additions. Conducted simulations implies that the estimator improved by the proposed method has lower bias error, shows a better RMS error performance at all SNR levels and achieves the CRLB as the SNR increases.","PeriodicalId":312627,"journal":{"name":"2020 28th Signal Processing and Communications Applications Conference (SIU)","volume":"19 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":"116701098","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/SIU49456.2020.9302279
A. Yasli, H. Ademgil
In this study, symmetrical D-shaped PCF-SPR based sensor has been designed for multi analyte sensing purposes. The structure consists of hexagonally arranged air holes on silica background, where gold used as plasmonic material. Double analyte channels have been used with respect to sensing multi refractive index variations. Full Vectorial-Finite Element Method has been employed for numerically analysing the magnetic field distributions, the effective refractive index changes and the confinement losses for proposed sensor. The spectral interrogation method has been also employed for analysing the sensitivities and resolutions of proposed sensor. When the refractive index changes from 1:33 to 1:35, 2300nm=RIU spectral sensitivity obtained with 4.3 × 10-5 RIU resolution.
{"title":"Symmetric D-Shaped PCF-SPR Sensor Based on Multi Analyte Sensing Purposes","authors":"A. Yasli, H. Ademgil","doi":"10.1109/SIU49456.2020.9302279","DOIUrl":"https://doi.org/10.1109/SIU49456.2020.9302279","url":null,"abstract":"In this study, symmetrical D-shaped PCF-SPR based sensor has been designed for multi analyte sensing purposes. The structure consists of hexagonally arranged air holes on silica background, where gold used as plasmonic material. Double analyte channels have been used with respect to sensing multi refractive index variations. Full Vectorial-Finite Element Method has been employed for numerically analysing the magnetic field distributions, the effective refractive index changes and the confinement losses for proposed sensor. The spectral interrogation method has been also employed for analysing the sensitivities and resolutions of proposed sensor. When the refractive index changes from 1:33 to 1:35, 2300nm=RIU spectral sensitivity obtained with 4.3 × 10-5 RIU resolution.","PeriodicalId":312627,"journal":{"name":"2020 28th Signal Processing and Communications Applications Conference (SIU)","volume":"69 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":"122743659","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/SIU49456.2020.9302477
Hasan Öztürk, Alperen Değirmenci, Onur Güngör, Suzan Üsküdarli
One of the most common spelling errors in Turkish is regarding the clitic ‘de/da’. People often misspell the ‘de/da’ either by treating it as a suffix inappropriately when it should not, or by spelling it seperately when it should be a suffix. Since Turkish is a morphologically rich agglutinative language, detecting and identifying such errors are difficult. As such, many widely used spell correction tools do not handle such mistakes well. In this work, we show that a sequence tagger model that employs BERT model which produces word embeddings that consider the context of a word obtains higher performance compared to using non-contextual word embeddings instead. Training and evaluation tasks were performed with a dataset that was derived from a Turkish corpus using a special process in addition to a manually curated one. The contextual word embeddings obtained during this task are publicly shared with the research community.
{"title":"The Role of Contextual Word Embeddings in Correcting the ‘de/da’ Clitic Errors in Turkish","authors":"Hasan Öztürk, Alperen Değirmenci, Onur Güngör, Suzan Üsküdarli","doi":"10.1109/SIU49456.2020.9302477","DOIUrl":"https://doi.org/10.1109/SIU49456.2020.9302477","url":null,"abstract":"One of the most common spelling errors in Turkish is regarding the clitic ‘de/da’. People often misspell the ‘de/da’ either by treating it as a suffix inappropriately when it should not, or by spelling it seperately when it should be a suffix. Since Turkish is a morphologically rich agglutinative language, detecting and identifying such errors are difficult. As such, many widely used spell correction tools do not handle such mistakes well. In this work, we show that a sequence tagger model that employs BERT model which produces word embeddings that consider the context of a word obtains higher performance compared to using non-contextual word embeddings instead. Training and evaluation tasks were performed with a dataset that was derived from a Turkish corpus using a special process in addition to a manually curated one. The contextual word embeddings obtained during this task are publicly shared with the research community.","PeriodicalId":312627,"journal":{"name":"2020 28th Signal Processing and Communications Applications Conference (SIU)","volume":"16 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":"122860159","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/SIU49456.2020.9302411
Metehan Yildirim, E. Anarim
Adding valid safety measures to security layers can be achieved by behavioural biometrics. In this period in which big data solutions are improved and marketable, it can be a logical choice to identify users with big data consisting of their behaviours in addition to other security layers. For this reason, a self-supervised model has been proposed with the Balabit Dataset. This self-supervised model is created with autoencoders and it is demonstrated that the model performance outperforms the previously proposed self-supervised methods. Generally, the model performance was evaluated under the Area Under Curve and Equal Error Rate (EER) evaluations. Comprehensive experiments show that our model’s performance is comparable with the models based on supervised methods. Keywords—Balabit Dataset, intrusion detection, mouse dynamics, self-supervised learning
行为生物识别技术可以为安全层增加有效的安全措施。在这个大数据解决方案不断完善和市场化的时期，除了其他安全层之外，用由用户行为组成的大数据来识别用户可能是一个合乎逻辑的选择。为此，我们提出了一个基于Balabit数据集的自监督模型。该自监督模型是用自编码器创建的，并证明了该模型的性能优于先前提出的自监督方法。一般采用曲线下面积(Area under Curve)和等错误率(Equal Error Rate, EER)评价模型的性能。综合实验表明，该模型的性能与基于监督方法的模型相当。关键词:balabit数据集，入侵检测，鼠标动态，自监督学习
{"title":"Intrusion Detection with Mouse Movements and Self-Supervised Learning","authors":"Metehan Yildirim, E. Anarim","doi":"10.1109/SIU49456.2020.9302411","DOIUrl":"https://doi.org/10.1109/SIU49456.2020.9302411","url":null,"abstract":"Adding valid safety measures to security layers can be achieved by behavioural biometrics. In this period in which big data solutions are improved and marketable, it can be a logical choice to identify users with big data consisting of their behaviours in addition to other security layers. For this reason, a self-supervised model has been proposed with the Balabit Dataset. This self-supervised model is created with autoencoders and it is demonstrated that the model performance outperforms the previously proposed self-supervised methods. Generally, the model performance was evaluated under the Area Under Curve and Equal Error Rate (EER) evaluations. Comprehensive experiments show that our model’s performance is comparable with the models based on supervised methods. Keywords—Balabit Dataset, intrusion detection, mouse dynamics, self-supervised learning","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":"131577899","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/SIU49456.2020.9302124
H. A. Yildiz
A CMOS Gaussian function generator circuit suitable for the implementation of analog neural networks is proposed. For this purpose, it is considered the polynomial approximation of the Gaussian function. The proposed circuit realizes the Gaussian function characteristic inherently, that is without requiring any accurate tuning or adjustment of the circuit parameters. In order to show the usefulness of the proposed circuit, simulation results obtained using Spectre Simulation tool in Cadence design environment are provided. These results show the validity of the theoretical analysis and feasibility of the proposed structure.
{"title":"Gaussian Activation Function Realization with Application to the Neural Network Implementations","authors":"H. A. Yildiz","doi":"10.1109/SIU49456.2020.9302124","DOIUrl":"https://doi.org/10.1109/SIU49456.2020.9302124","url":null,"abstract":"A CMOS Gaussian function generator circuit suitable for the implementation of analog neural networks is proposed. For this purpose, it is considered the polynomial approximation of the Gaussian function. The proposed circuit realizes the Gaussian function characteristic inherently, that is without requiring any accurate tuning or adjustment of the circuit parameters. In order to show the usefulness of the proposed circuit, simulation results obtained using Spectre Simulation tool in Cadence design environment are provided. These results show the validity of the theoretical analysis and feasibility of the proposed structure.","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":"126990413","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：