Pub Date : 2020-10-05DOI: 10.1109/SIU49456.2020.9302168
Beyhan Adanur, Burcu Bakir-Güngör, Ahmet Soran
Recently, the use of blockchain technology in the field of healthcare has increased. Although blockchain technology brought several innovations to healthcare, still there are problems waiting to be resolved. In order to provide alternative solutions to these problems, the use of fog computing together with blockchain technology has been proposed. In this study, the applications of blockchain based fog computing technology in healthcare are investigated. The aim of this study is to provide the readers an idea about the interactive use of blockchain and fog computing in the field of healthcare. For this purpose, firstly, fog computing and blockchain technologies are introduced. Afterwards, the integration of these areas, the advantages and disadvantages of using these technologies in the field of healthcare is discussed and a new system architecture is proposed.
{"title":"Blockchain-based Fog Computing Applications in Healthcare","authors":"Beyhan Adanur, Burcu Bakir-Güngör, Ahmet Soran","doi":"10.1109/SIU49456.2020.9302168","DOIUrl":"https://doi.org/10.1109/SIU49456.2020.9302168","url":null,"abstract":"Recently, the use of blockchain technology in the field of healthcare has increased. Although blockchain technology brought several innovations to healthcare, still there are problems waiting to be resolved. In order to provide alternative solutions to these problems, the use of fog computing together with blockchain technology has been proposed. In this study, the applications of blockchain based fog computing technology in healthcare are investigated. The aim of this study is to provide the readers an idea about the interactive use of blockchain and fog computing in the field of healthcare. For this purpose, firstly, fog computing and blockchain technologies are introduced. Afterwards, the integration of these areas, the advantages and disadvantages of using these technologies in the field of healthcare is discussed and a new system architecture is proposed.","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":"115692910","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/SIU49456.2020.9302178
Kaan Karaman, Ibrahim Batuhan Akkaya, A. Alatan
Metric learning is a frequently utilized method that can be applied to many different computer vision problems and; thus, facilitates these problems. In this paper, the proposed method for manipulating the feature space with the help of quadruplets, which is one of the metric learning methods, is explained with details, and the results obtained by using it are shown. Many methods used in the field of metric learning, have been developed on the Siamese and triplet structures and satisfactory results have been obtained by them. Similarly, the quadruplet structure is still being studied and different approaches are proposed in the literature. How to select four elements for generating a quadruplet is not standardized at present. However, by looking at the mining methods of Siamese and triplet samples, it can be concluded that each sample in the dataset that is trained with quadruplet samples, must have at least two hierarchical labels. This makes it possible to train the quadruplet structure only on certain datasets that have the hierarchical labels. In this paper, an unsupervised method is proposed to use the quadruplet structure in datasets that do not have a hierarchical label structure. Besides, the performances of three different quadruplet mining methods are compared and an ablation study is conducted by discussing the advantages and disadvantages of the proposed method.
{"title":"Metric Learning with Quadruplets on Non-Hierarchical Labeled Datasets","authors":"Kaan Karaman, Ibrahim Batuhan Akkaya, A. Alatan","doi":"10.1109/SIU49456.2020.9302178","DOIUrl":"https://doi.org/10.1109/SIU49456.2020.9302178","url":null,"abstract":"Metric learning is a frequently utilized method that can be applied to many different computer vision problems and; thus, facilitates these problems. In this paper, the proposed method for manipulating the feature space with the help of quadruplets, which is one of the metric learning methods, is explained with details, and the results obtained by using it are shown. Many methods used in the field of metric learning, have been developed on the Siamese and triplet structures and satisfactory results have been obtained by them. Similarly, the quadruplet structure is still being studied and different approaches are proposed in the literature. How to select four elements for generating a quadruplet is not standardized at present. However, by looking at the mining methods of Siamese and triplet samples, it can be concluded that each sample in the dataset that is trained with quadruplet samples, must have at least two hierarchical labels. This makes it possible to train the quadruplet structure only on certain datasets that have the hierarchical labels. In this paper, an unsupervised method is proposed to use the quadruplet structure in datasets that do not have a hierarchical label structure. Besides, the performances of three different quadruplet mining methods are compared and an ablation study is conducted by discussing the advantages and disadvantages of the proposed method.","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":"114469934","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/SIU49456.2020.9302437
Umuralp Kaytaz, Seyhan Uçar, S. Coleri
Single-radio multi-channel Medium Access Control (MAC) protocols aim to transmit in parallel on distinct channels while reducing the hardware cost. Although a variety of MAC protocols have been proposed in this context, no detailed classification and performance comparison is available. In this paper, we first classify previous efforts by their rendezvous characteristics as singleand multi-rendezvous protocols. Multirendezvous protocols have the capability of supporting simultaneous handshaking on different channels whereas with single-rendezvous protocols only asynchronous channel negotiations are allowed. Then, we further classify these protocols according to their spectrum decision mechanisms. We demonstrate the functionality of singleand multi-rendezvous protocols under different scenarios via extensive simulations. Our findings show that multi-rendezvous protocol performs better when the transmission range is low and less number of channels is available. Single-rendezvous protocols, on the other hand, are more suitable for networks with larger traffic loads due to their slot-based decision-making schemes. Keywords— medium access control (MAC), multi-channel, ad hoc network. I. G R Günümüzde kullan lan kablosuz a teknolojisinin büyük bir k sm , IEEE 802.11 standard na dayanmaktad r. IEEE 802.11'de bulunan Da t lm Koordinasyon Fonksiyonu (DCF), MAC katman nda tek bir kanal kullan r. Bundan dolay , tek bir kanaldaki a trafi i yükü, yüksek oranda paket çarp mas na ve performans n dü mesine neden olmaktad r. Çok kanall yap n n telsizlerin kanal de i tirme özelli i ile birlikte kullan lmas , farkl kanallarda e zamanl aktar m sa lamak için yayg n bir yakla md r. Bu nedenle, çok kanall yap daki ileti im, daha az kar l kl giri im, daha yüksek mekânsal yeniden kullan m ve geli mi a verimlili i ile sonuçlanmaktad r. Çok kanall ileti imde i levselli i artt rmak için birçok çal ma önerilmi tir [1]. Bu yakla mlar, al c say s na ve/veya tokala ma yöntemlerine göre kategorize edilebilirler. Çok al c vericinin etkin oldu u çok kanall MAC protokolleri daha güvenilir olsa da, her bir dü üm için birden fazla radyo sa lamak donan m maliyetini art rmaktad r. Güvenilir ileti imi minimum maliyet gözeterek ara t rmak için, bu çal mam zda yaln zca tek telsiz çok kanall MAC protokollerini incelemekteyiz. Tek telsiz çok-kanall MAC protokollerinin s n fland r lmas , Tablo I de gösterildi i gibidir. Tek telsiz çok kanall MAC protokolleri, kabul edilen el s k ma prosedürüne ba l olarak tek veya çok randevulu olarak s n fland r labilirler [12]. Tek randevulu MAC için yakla mlardan biri, veri kanal anla malar için kaynak ve var (S-D) çiftleri aras nda ortak bir kontrol kanal n n kullan lmas d r [13]. Atanm Kontrol Kanal (DCC) protokolleri, tokala ma amac yla ortak bir kontrol kanal , iletimler için ise çoklu veri kanallar n kullanmaktad rlar. Tek bir telsiz ile ortak bir kontrol kanal n n kullan lmas kanalda sadece bir S-D çiftinin tokala abilmesine sebep olmaktad r. E zama
{"title":"A Performance Comparison of Single-Radio MultiChannel Medium Access Control Protocols","authors":"Umuralp Kaytaz, Seyhan Uçar, S. Coleri","doi":"10.1109/SIU49456.2020.9302437","DOIUrl":"https://doi.org/10.1109/SIU49456.2020.9302437","url":null,"abstract":"Single-radio multi-channel Medium Access Control (MAC) protocols aim to transmit in parallel on distinct channels while reducing the hardware cost. Although a variety of MAC protocols have been proposed in this context, no detailed classification and performance comparison is available. In this paper, we first classify previous efforts by their rendezvous characteristics as singleand multi-rendezvous protocols. Multirendezvous protocols have the capability of supporting simultaneous handshaking on different channels whereas with single-rendezvous protocols only asynchronous channel negotiations are allowed. Then, we further classify these protocols according to their spectrum decision mechanisms. We demonstrate the functionality of singleand multi-rendezvous protocols under different scenarios via extensive simulations. Our findings show that multi-rendezvous protocol performs better when the transmission range is low and less number of channels is available. Single-rendezvous protocols, on the other hand, are more suitable for networks with larger traffic loads due to their slot-based decision-making schemes. Keywords— medium access control (MAC), multi-channel, ad hoc network. I. G R Günümüzde kullan lan kablosuz a teknolojisinin büyük bir k sm , IEEE 802.11 standard na dayanmaktad r. IEEE 802.11'de bulunan Da t lm Koordinasyon Fonksiyonu (DCF), MAC katman nda tek bir kanal kullan r. Bundan dolay , tek bir kanaldaki a trafi i yükü, yüksek oranda paket çarp mas na ve performans n dü mesine neden olmaktad r. Çok kanall yap n n telsizlerin kanal de i tirme özelli i ile birlikte kullan lmas , farkl kanallarda e zamanl aktar m sa lamak için yayg n bir yakla md r. Bu nedenle, çok kanall yap daki ileti im, daha az kar l kl giri im, daha yüksek mekânsal yeniden kullan m ve geli mi a verimlili i ile sonuçlanmaktad r. Çok kanall ileti imde i levselli i artt rmak için birçok çal ma önerilmi tir [1]. Bu yakla mlar, al c say s na ve/veya tokala ma yöntemlerine göre kategorize edilebilirler. Çok al c vericinin etkin oldu u çok kanall MAC protokolleri daha güvenilir olsa da, her bir dü üm için birden fazla radyo sa lamak donan m maliyetini art rmaktad r. Güvenilir ileti imi minimum maliyet gözeterek ara t rmak için, bu çal mam zda yaln zca tek telsiz çok kanall MAC protokollerini incelemekteyiz. Tek telsiz çok-kanall MAC protokollerinin s n fland r lmas , Tablo I de gösterildi i gibidir. Tek telsiz çok kanall MAC protokolleri, kabul edilen el s k ma prosedürüne ba l olarak tek veya çok randevulu olarak s n fland r labilirler [12]. Tek randevulu MAC için yakla mlardan biri, veri kanal anla malar için kaynak ve var (S-D) çiftleri aras nda ortak bir kontrol kanal n n kullan lmas d r [13]. Atanm Kontrol Kanal (DCC) protokolleri, tokala ma amac yla ortak bir kontrol kanal , iletimler için ise çoklu veri kanallar n kullanmaktad rlar. Tek bir telsiz ile ortak bir kontrol kanal n n kullan lmas kanalda sadece bir S-D çiftinin tokala abilmesine sebep olmaktad r. E zama","PeriodicalId":312627,"journal":{"name":"2020 28th Signal Processing and Communications Applications Conference (SIU)","volume":"52 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":"114492224","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/SIU49456.2020.9302459
M. Imamoglu, F. Kahraman, Z. Çakır, F. B. Sanli
Surface deformations in Bolvadin town without any devastating earthquakes have been observed in the last 10 years. In this study, ground deformation analysis of Bolvadin region was performed by Sentinel-1 synthetic aperture radar (SAR) data and multi-temporal SAR interferometry (InSAR) method. Sentinel-1 images obtained between October 2014 and October 2018 in ascending and descending orbits were processed with SNAP and StaMPS softwares. Deformation velocity maps and vertical displacement time series were produced and compared with geology and groundwater level of the region. Deformation velocity maps show significant subsidence in the region. The most severe subsidence, up to 35 mm/year, was found in the southern part of Bolvadin which is characterized by the presence of soft alluvial deposits. Both in long and short term, there was a strong correlation between the subsidence and the groundwater level. As a result, the high correlation of the vertical deformation velocity with lithological units and groundwater level indicates that subsidence in the region is probably due to the excessive use of groundwater.
{"title":"Bolvadin Subsidence Analysis with Multi-Temporal InSAR Technique and Sentinel-1 Data","authors":"M. Imamoglu, F. Kahraman, Z. Çakır, F. B. Sanli","doi":"10.1109/SIU49456.2020.9302459","DOIUrl":"https://doi.org/10.1109/SIU49456.2020.9302459","url":null,"abstract":"Surface deformations in Bolvadin town without any devastating earthquakes have been observed in the last 10 years. In this study, ground deformation analysis of Bolvadin region was performed by Sentinel-1 synthetic aperture radar (SAR) data and multi-temporal SAR interferometry (InSAR) method. Sentinel-1 images obtained between October 2014 and October 2018 in ascending and descending orbits were processed with SNAP and StaMPS softwares. Deformation velocity maps and vertical displacement time series were produced and compared with geology and groundwater level of the region. Deformation velocity maps show significant subsidence in the region. The most severe subsidence, up to 35 mm/year, was found in the southern part of Bolvadin which is characterized by the presence of soft alluvial deposits. Both in long and short term, there was a strong correlation between the subsidence and the groundwater level. As a result, the high correlation of the vertical deformation velocity with lithological units and groundwater level indicates that subsidence in the region is probably due to the excessive use of groundwater.","PeriodicalId":312627,"journal":{"name":"2020 28th Signal Processing and Communications Applications Conference (SIU)","volume":"34 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":"114762344","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/SIU49456.2020.9302079
Altuğ Kaya, G. M. Güvensen
Realizable root-raised cosine (RRC) filters have finite length. When these filters are used in transmitter and receiver side, frequency response of the effective filter does not have flat fading characteristic and it results two-sided intersymbol interference (ISI). In addition, relatively low up sampling factors result in synchronization errors and thus, two-sided ISI. Consequently, impulse response of the effective filter becomes noncausal. Moreover, nonlinearities in transmitter and receiver chains strengthen ISI. Such a channel-like behaviour of the noncausal effective filter can be overcome by conventional Half-Duplex systems where it should be avoided by In-Band Full-Duplex and higher order constellation systems due to being vulnerable to even low powered effects. In this article, we are providing a new cyclic postamble structure, namely Cyclic Suffix (CS), for constructing circularly symmetric convolution matrices for noncausal channels. CS provides the utilization of frequency domain equalization (FDE) in a low complex manner for cancelling the effects of such noncausal channels.
{"title":"A Circular Postamble Structure Enabling Low Complexity Equalization in Frequency Domain for Noncausal Channels: Cyclic Suffix","authors":"Altuğ Kaya, G. M. Güvensen","doi":"10.1109/SIU49456.2020.9302079","DOIUrl":"https://doi.org/10.1109/SIU49456.2020.9302079","url":null,"abstract":"Realizable root-raised cosine (RRC) filters have finite length. When these filters are used in transmitter and receiver side, frequency response of the effective filter does not have flat fading characteristic and it results two-sided intersymbol interference (ISI). In addition, relatively low up sampling factors result in synchronization errors and thus, two-sided ISI. Consequently, impulse response of the effective filter becomes noncausal. Moreover, nonlinearities in transmitter and receiver chains strengthen ISI. Such a channel-like behaviour of the noncausal effective filter can be overcome by conventional Half-Duplex systems where it should be avoided by In-Band Full-Duplex and higher order constellation systems due to being vulnerable to even low powered effects. In this article, we are providing a new cyclic postamble structure, namely Cyclic Suffix (CS), for constructing circularly symmetric convolution matrices for noncausal channels. CS provides the utilization of frequency domain equalization (FDE) in a low complex manner for cancelling the effects of such noncausal channels.","PeriodicalId":312627,"journal":{"name":"2020 28th Signal Processing and Communications Applications Conference (SIU)","volume":"132 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":"115059007","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/SIU49456.2020.9302149
Waris Gill, Öznur Özkasap, Attila Gürsoy
To enable intelligent decisions at the network edge, supervised and unsupervised machine learning techniques and their variations are highly utilized in recent research studies. These include techniques and the corresponding applications such as detecting manufacturing faults in a smart factory setting, monitoring patient activities and health problems in smart health systems, detecting security attacks on the Internet of Things devices, and finding the rare events in the audio signals. In this paper, we present an extensive review of state-of-the-art techniques and applications of intelligent edge computing and provide classification and discussion of various approaches in this field.
{"title":"Intelligent Edge Computing: State-of-the-art Techniques and Applications","authors":"Waris Gill, Öznur Özkasap, Attila Gürsoy","doi":"10.1109/SIU49456.2020.9302149","DOIUrl":"https://doi.org/10.1109/SIU49456.2020.9302149","url":null,"abstract":"To enable intelligent decisions at the network edge, supervised and unsupervised machine learning techniques and their variations are highly utilized in recent research studies. These include techniques and the corresponding applications such as detecting manufacturing faults in a smart factory setting, monitoring patient activities and health problems in smart health systems, detecting security attacks on the Internet of Things devices, and finding the rare events in the audio signals. In this paper, we present an extensive review of state-of-the-art techniques and applications of intelligent edge computing and provide classification and discussion of various approaches in this field.","PeriodicalId":312627,"journal":{"name":"2020 28th Signal Processing and Communications Applications Conference (SIU)","volume":"17 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":"115061386","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/SIU49456.2020.9302378
Mehmet Zahid Kartal, A. Coşkun, Veyis Solak, H. Ilhan
In this paper, the average bit error rates of nonorthogonal multiple access (NOMA)schemes employing Alamouti space-time block coding (STBC) combined with different transmit antenna selection (TAS) strategies are investigated. With this purpose, the selection criteria that have been proposed for multiple-antenna schemes such as the conventional TAS (CTAS) scheme which relies on determining the antenna with the highest channel gain, TAS-maj scheme which is based on majority voting, and, AIA and A schemes which respectively activates the antenna that maximizes the users with the worst and best channel conditions, have been considered. Within this examination, the antenna selection strategies that are proposed for single TAS case (i.e., TAS-maj, AIA and A) are adapted to the case of determining two transmit antennas which would perform Alamouti codeword transmission. By using the Monte Carlo simulation method, the average bit error rate (BER) performance of each user at the downlink phase is examined for Rayleigh fading channels. After demonstrating the simulation results corresponding to the case of no antenna selection and the introduced TAS strategies, their advantages in terms of the average signal-to-noise ratio enhancements are exhibited. Keywords—Transmit Antenna Selection; Alamouti Space-Time Block Code; Non-Orthogonal Multiple Access; Bit Error Rate.
{"title":"Performance of Alamouti STBC-NOMA Scheme Employing Different Transmit Antenna Selection Strategies","authors":"Mehmet Zahid Kartal, A. Coşkun, Veyis Solak, H. Ilhan","doi":"10.1109/SIU49456.2020.9302378","DOIUrl":"https://doi.org/10.1109/SIU49456.2020.9302378","url":null,"abstract":"In this paper, the average bit error rates of nonorthogonal multiple access (NOMA)schemes employing Alamouti space-time block coding (STBC) combined with different transmit antenna selection (TAS) strategies are investigated. With this purpose, the selection criteria that have been proposed for multiple-antenna schemes such as the conventional TAS (CTAS) scheme which relies on determining the antenna with the highest channel gain, TAS-maj scheme which is based on majority voting, and, AIA and A schemes which respectively activates the antenna that maximizes the users with the worst and best channel conditions, have been considered. Within this examination, the antenna selection strategies that are proposed for single TAS case (i.e., TAS-maj, AIA and A) are adapted to the case of determining two transmit antennas which would perform Alamouti codeword transmission. By using the Monte Carlo simulation method, the average bit error rate (BER) performance of each user at the downlink phase is examined for Rayleigh fading channels. After demonstrating the simulation results corresponding to the case of no antenna selection and the introduced TAS strategies, their advantages in terms of the average signal-to-noise ratio enhancements are exhibited. Keywords—Transmit Antenna Selection; Alamouti Space-Time Block Code; Non-Orthogonal Multiple Access; Bit Error Rate.","PeriodicalId":312627,"journal":{"name":"2020 28th Signal Processing and Communications Applications Conference (SIU)","volume":"13 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":"115098384","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/SIU49456.2020.9302502
Durmuş Özkan Şahin, Oğuz Emre Kural, S. Akleylek, E. Kılıç
In this study, applications developed for Android platforms are tested by static analysis based on machine learning. Permissions that have an important place in the security of the Android operating system are used as attributes. Using the regression techniques, which are among the types of machine learning, the applications are tested. Four different regression techniques are used in this study. These are linear regression, multilayered neural network, additive regression and regression techniques based on sequential minimal optimization. As a result of 10 cross-validations, the best result is obtained by linear regression, while the worst result is obtained by regression techniques based on sequential minimal optimization. The result obtained from linear regression is 0:8655 according to the Pearson correlation coefficient.
{"title":"Comparison of Regression Methods in Permission Based Android Malware Detection","authors":"Durmuş Özkan Şahin, Oğuz Emre Kural, S. Akleylek, E. Kılıç","doi":"10.1109/SIU49456.2020.9302502","DOIUrl":"https://doi.org/10.1109/SIU49456.2020.9302502","url":null,"abstract":"In this study, applications developed for Android platforms are tested by static analysis based on machine learning. Permissions that have an important place in the security of the Android operating system are used as attributes. Using the regression techniques, which are among the types of machine learning, the applications are tested. Four different regression techniques are used in this study. These are linear regression, multilayered neural network, additive regression and regression techniques based on sequential minimal optimization. As a result of 10 cross-validations, the best result is obtained by linear regression, while the worst result is obtained by regression techniques based on sequential minimal optimization. The result obtained from linear regression is 0:8655 according to the Pearson correlation coefficient.","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":"117029973","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/SIU49456.2020.9302452
F. E. Durak, Ş. A. Sadık, K. Boumediene, M. Khelladi, A. Altuncu
This study presents the characterization of four wave mixing (FWM) effect in dense wavelength division multiplexing (DWDM) systems with two different types of optical fibers which are standard single mode fiber (S-SMF, G.652.D) and nonzero dispersion shifted fiber (NZDSF, G.655.C), respectively. The experimental observation of FWM effect at the received signal spectrum have shown that the increase in channel spacing reduces the power of FWM tone signals. Also, we have compared FWM penalty of DWDM signals transmitted in S-SMF and NZDSF by calculating FWM efficiency affected by the channel spacing. It was shown that when the channel spacing is smaller than 0.5 nm, the FWM efficiency in NZDSF is almost 15 dB higher than the FWM efficiency obtained in S-SMF. Moreover, the results have shown that for 10, 20, 30 km of NZDSF, the FWM efficiency tends to increase with optical fiber length.
{"title":"Characterization of Four Wave Mixing Effect in Dense Wavelength Division Multiplexing Systems","authors":"F. E. Durak, Ş. A. Sadık, K. Boumediene, M. Khelladi, A. Altuncu","doi":"10.1109/SIU49456.2020.9302452","DOIUrl":"https://doi.org/10.1109/SIU49456.2020.9302452","url":null,"abstract":"This study presents the characterization of four wave mixing (FWM) effect in dense wavelength division multiplexing (DWDM) systems with two different types of optical fibers which are standard single mode fiber (S-SMF, G.652.D) and nonzero dispersion shifted fiber (NZDSF, G.655.C), respectively. The experimental observation of FWM effect at the received signal spectrum have shown that the increase in channel spacing reduces the power of FWM tone signals. Also, we have compared FWM penalty of DWDM signals transmitted in S-SMF and NZDSF by calculating FWM efficiency affected by the channel spacing. It was shown that when the channel spacing is smaller than 0.5 nm, the FWM efficiency in NZDSF is almost 15 dB higher than the FWM efficiency obtained in S-SMF. Moreover, the results have shown that for 10, 20, 30 km of NZDSF, the FWM efficiency tends to increase with optical fiber length.","PeriodicalId":312627,"journal":{"name":"2020 28th Signal Processing and Communications Applications Conference (SIU)","volume":"6 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":"115993572","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/SIU49456.2020.9302150
Tansel Akgül, Nurullah Çalık, B. U. Töreyin
The successful results of the deep learning models in many areas have been the exit gateway to the problems faced in the challenging conditions of underwater studies. One of these problems is the detection of fish in images with a high turbid and background noise. Therefore, the detection of fish in turbid and background noisy water is an important threshold to be overcome to classify them and track their paths. In this study, videos were taken from the reservoir basin in Kahramanmaraş Ceyhan region with two different cameras. Then, a novel data set is presented which contains 400 images for the detection of fish in the wild. By using these data set, the state-of-the-art detection models, YOLO-V2, YOLO-V3, YOLO-V3 Tiny and MobileNet-SSD networks are trained with fine-tuning strategy, and then they are compared over the precision, recall and mean Average Precision (mAP) performances.
{"title":"Deep Learning-Based Fish Detection in Turbid Underwater Images","authors":"Tansel Akgül, Nurullah Çalık, B. U. Töreyin","doi":"10.1109/SIU49456.2020.9302150","DOIUrl":"https://doi.org/10.1109/SIU49456.2020.9302150","url":null,"abstract":"The successful results of the deep learning models in many areas have been the exit gateway to the problems faced in the challenging conditions of underwater studies. One of these problems is the detection of fish in images with a high turbid and background noise. Therefore, the detection of fish in turbid and background noisy water is an important threshold to be overcome to classify them and track their paths. In this study, videos were taken from the reservoir basin in Kahramanmaraş Ceyhan region with two different cameras. Then, a novel data set is presented which contains 400 images for the detection of fish in the wild. By using these data set, the state-of-the-art detection models, YOLO-V2, YOLO-V3, YOLO-V3 Tiny and MobileNet-SSD networks are trained with fine-tuning strategy, and then they are compared over the precision, recall and mean Average Precision (mAP) performances.","PeriodicalId":312627,"journal":{"name":"2020 28th Signal Processing and Communications Applications Conference (SIU)","volume":"28 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":"122047672","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：