Pub Date : 2019-10-01DOI: 10.1109/ATC.2019.8924562
Kwonyeol Park, J. Rhee, Min-Ho Shin, Woonhaing Hur
The utilization of Unmanned Aerial Vehicles (UAVs) is rapidly growing in a wide range of application due to their ease of deployment, low maintenance cost and high mobility. In particular, these advantages are used more effectively by the UAV when interacting with cellular networks such as 5G and beyond 5G. This system is defined as a cellular-UAV system [1]. In order to implement this system, reliable communication between base station and UAV is required. That is, well-designed CQI feedback mechanism is one of the essential technologies to be equipped. In traditional cellular network, the base station requires Channel Quality Indicator (CQI) feedback from users in order to determine a reasonable Modulation and Coding Scheme (MCS) in multicast system. However, traditional techniques also increase essential feedback as the group size increases and cause more signal overhead. This crucial problem can be equally applied to the cellular-UAV system. To cope with this problem, this paper proposes a new type of CQI feedback mechanism. The proposed schemes are expected not only to reduce signalling overhead but also to increase spectral efficiency, which is further demonstrated by the simulation results.
{"title":"A Novel CQI Feedback Channel for Cellular UAV System","authors":"Kwonyeol Park, J. Rhee, Min-Ho Shin, Woonhaing Hur","doi":"10.1109/ATC.2019.8924562","DOIUrl":"https://doi.org/10.1109/ATC.2019.8924562","url":null,"abstract":"The utilization of Unmanned Aerial Vehicles (UAVs) is rapidly growing in a wide range of application due to their ease of deployment, low maintenance cost and high mobility. In particular, these advantages are used more effectively by the UAV when interacting with cellular networks such as 5G and beyond 5G. This system is defined as a cellular-UAV system [1]. In order to implement this system, reliable communication between base station and UAV is required. That is, well-designed CQI feedback mechanism is one of the essential technologies to be equipped. In traditional cellular network, the base station requires Channel Quality Indicator (CQI) feedback from users in order to determine a reasonable Modulation and Coding Scheme (MCS) in multicast system. However, traditional techniques also increase essential feedback as the group size increases and cause more signal overhead. This crucial problem can be equally applied to the cellular-UAV system. To cope with this problem, this paper proposes a new type of CQI feedback mechanism. The proposed schemes are expected not only to reduce signalling overhead but also to increase spectral efficiency, which is further demonstrated by the simulation results.","PeriodicalId":409591,"journal":{"name":"2019 International Conference on Advanced Technologies for Communications (ATC)","volume":"25 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133830143","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 : 2019-10-01DOI: 10.1109/ATC.2019.8924502
T. Pham, Bang Thanh Le
Similar to previous mobile communication systems, random access (RA) procedure in fifth generation of mobile communication (5G) is used to achieve the uplink synchronization between user equipment (UE) and next generation Node B (gNB) based on the detection of preambles in Physical Random Access Channel (PRACH). A method for detecting preamble in PRACH at 5G base station (gNB) is proposed in this paper. The proposed method uses an enhanced algorithm with multi-detection steps to reject effectively false alarm peaks due to noise and channel condition as multipath fading, Doppler shift, frequency offset and timing offset. Simulation results show that the proposed method with optimized detection thresholds satisfies the requirements of system about detection probability and false alarm probability under a certain SNR level and propagation condition.
与以往的移动通信系统类似，第五代移动通信(5G)中的RA (random access)过程是基于对PRACH (Physical random access Channel)前导的检测，实现用户设备(UE)与下一代Node B (gNB)之间的上行同步。提出了一种5G基站(gNB)中PRACH前导信号的检测方法。该方法采用一种增强的多步检测算法，有效地抑制了由噪声和信道条件引起的多径衰落、多普勒频移、频率偏移和时序偏移等虚警峰。仿真结果表明，在一定信噪比水平和传播条件下，优化检测阈值的方法满足系统对检测概率和虚警概率的要求。
{"title":"A proposed preamble detection algorithm for 5G-PRACH","authors":"T. Pham, Bang Thanh Le","doi":"10.1109/ATC.2019.8924502","DOIUrl":"https://doi.org/10.1109/ATC.2019.8924502","url":null,"abstract":"Similar to previous mobile communication systems, random access (RA) procedure in fifth generation of mobile communication (5G) is used to achieve the uplink synchronization between user equipment (UE) and next generation Node B (gNB) based on the detection of preambles in Physical Random Access Channel (PRACH). A method for detecting preamble in PRACH at 5G base station (gNB) is proposed in this paper. The proposed method uses an enhanced algorithm with multi-detection steps to reject effectively false alarm peaks due to noise and channel condition as multipath fading, Doppler shift, frequency offset and timing offset. Simulation results show that the proposed method with optimized detection thresholds satisfies the requirements of system about detection probability and false alarm probability under a certain SNR level and propagation condition.","PeriodicalId":409591,"journal":{"name":"2019 International Conference on Advanced Technologies for Communications (ATC)","volume":"30 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124579930","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 : 2019-10-01DOI: 10.1109/ATC.2019.8924531
Ngo The Anh, Ha Duy Hung, Tran Trung Duy, Hoang Dang Hai, Nguyen Canh Minh
This paper evaluates trade-off between reliable and secure communication for multi-hop low-energy adaptive clustering hierarchy (LEACH) networks under impact of hardware imperfection. In the proposed scheme, a source communicates with a destination via a multi-hop transmission, where the source, destination and intermediate relay nodes are cluster heads (CHs). To protect the data at each hop, harvest-to-jam and randomize-and-forward methods are employed by CHs and cooperative jammers, respectively. Each jammer which is randomly selected at each cluster harvests energy from the previous CHs to transmit noises to an eavesdropper. We derive closed-form expressions of the end-to-end outage probability (OP) and intercept probability (IP) for the proposed scheme over Rayleigh fading channels. Then, the theoretical derivations are verified by Monte-Carlo simulations.
{"title":"Reliability-Security Analysis for Harvest-to-Jam based Multi-hop LEACH Networks under Impact of Hardware Noises","authors":"Ngo The Anh, Ha Duy Hung, Tran Trung Duy, Hoang Dang Hai, Nguyen Canh Minh","doi":"10.1109/ATC.2019.8924531","DOIUrl":"https://doi.org/10.1109/ATC.2019.8924531","url":null,"abstract":"This paper evaluates trade-off between reliable and secure communication for multi-hop low-energy adaptive clustering hierarchy (LEACH) networks under impact of hardware imperfection. In the proposed scheme, a source communicates with a destination via a multi-hop transmission, where the source, destination and intermediate relay nodes are cluster heads (CHs). To protect the data at each hop, harvest-to-jam and randomize-and-forward methods are employed by CHs and cooperative jammers, respectively. Each jammer which is randomly selected at each cluster harvests energy from the previous CHs to transmit noises to an eavesdropper. We derive closed-form expressions of the end-to-end outage probability (OP) and intercept probability (IP) for the proposed scheme over Rayleigh fading channels. Then, the theoretical derivations are verified by Monte-Carlo simulations.","PeriodicalId":409591,"journal":{"name":"2019 International Conference on Advanced Technologies for Communications (ATC)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129208266","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 : 2019-10-01DOI: 10.1109/ATC.2019.8924491
Ryo Marumo, Naoya Tanuma, K. Maruta, C. Ahn
This paper proposes an improved puncturing scheme exploiting the feature of systematic polar codes and verifies its effectiveness in MIMO-OFDM transmission. Puncturing is the process of removing part of the encoded bits and can realize various coding rates to adopt to the channel condition. However, the puncturing deteriorates BER performance because the removed bits are generally unknown at the receiving side. Systematic polar coding can generate the codeword that has the same value of information bits. Using this characteristic, the transmitting side punctures known bits shared between transmitter and receiver in the codeword. The receiving side then decodes the received signal by setting punctured bits to the known value to assist the decoding capability. Computer simulation presents that the achievable throughput can be improved while maintaining BER performance.
{"title":"Throughput Improvement of Systematic Polar Coded MIMO-OFDM by Puncturing","authors":"Ryo Marumo, Naoya Tanuma, K. Maruta, C. Ahn","doi":"10.1109/ATC.2019.8924491","DOIUrl":"https://doi.org/10.1109/ATC.2019.8924491","url":null,"abstract":"This paper proposes an improved puncturing scheme exploiting the feature of systematic polar codes and verifies its effectiveness in MIMO-OFDM transmission. Puncturing is the process of removing part of the encoded bits and can realize various coding rates to adopt to the channel condition. However, the puncturing deteriorates BER performance because the removed bits are generally unknown at the receiving side. Systematic polar coding can generate the codeword that has the same value of information bits. Using this characteristic, the transmitting side punctures known bits shared between transmitter and receiver in the codeword. The receiving side then decodes the received signal by setting punctured bits to the known value to assist the decoding capability. Computer simulation presents that the achievable throughput can be improved while maintaining BER performance.","PeriodicalId":409591,"journal":{"name":"2019 International Conference on Advanced Technologies for Communications (ATC)","volume":"38 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128767130","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 : 2019-10-01DOI: 10.1109/ATC.2019.8924498
L. X. Truong, Truong Vu Bang Giang, T. M. Tuan
this paper presents an application of Bat optimization algorithm on the pattern nulling technique for imposing single null at side lobes. A linear microstrip antenna array has been proposed to deploy the theory from Bat algorithm. The proposed array consists of 10 printed vertical antenna elements based on RO4003C substrate with the size of 160 x 450 x 1.524 mm3. When the array is fed by an ideal source, the simulated radiation pattern meets the requirement in term of null placement. A full design of the array for imposing a single null at the first side lobe has been proposed and investigated. Amplitude excitation weights are divided by a series feeding network. To improve the gain, a back reflector constructed on Fr-4 substrate with the size of 213 x 503 x 1.6 mm3has been used. The simulation results show that the first side lobe level can be suppressed to -40 dB at the frequency of 3.5 GHz while the maximum gain is 17.7 dBi. The simulated and measured reflection coefficients indicate that S1,1is equal -10 dB in the frequency range of 3.26-3.78 GHz. With these characteristics, the proposed antenna array is a good candidate for wireless systems in the C band.
本文介绍了Bat优化算法在侧瓣施加单零的模式去零技术中的应用。提出了一种线性微带天线阵列来应用Bat算法的理论。该阵列由10个基于RO4003C衬底的印刷垂直天线元件组成，尺寸为160 x 450 x 1.524 mm3。当阵列由理想源馈电时，模拟的辐射方向图在零点位置方面满足要求。提出并研究了在第一副瓣处施加单零的阵列的完整设计。振幅激励权由串联馈电网络划分。为了提高增益，采用了尺寸为213 x 503 x 1.6 mm3的Fr-4基板背反射器。仿真结果表明，在3.5 GHz频率下，第一副瓣电平可被抑制至-40 dB，最大增益为17.7 dBi。模拟和实测的反射系数表明，在3.26 ~ 3.78 GHz频率范围内，S1,1 = -10 dB。由于这些特点，该天线阵列是C波段无线系统的理想选择。
{"title":"Application of Bat Algorithm on the Design of a Linear Microstrip Antenna Array for Pattern Nulling","authors":"L. X. Truong, Truong Vu Bang Giang, T. M. Tuan","doi":"10.1109/ATC.2019.8924498","DOIUrl":"https://doi.org/10.1109/ATC.2019.8924498","url":null,"abstract":"this paper presents an application of Bat optimization algorithm on the pattern nulling technique for imposing single null at side lobes. A linear microstrip antenna array has been proposed to deploy the theory from Bat algorithm. The proposed array consists of 10 printed vertical antenna elements based on RO4003C substrate with the size of 160 x 450 x 1.524 mm3. When the array is fed by an ideal source, the simulated radiation pattern meets the requirement in term of null placement. A full design of the array for imposing a single null at the first side lobe has been proposed and investigated. Amplitude excitation weights are divided by a series feeding network. To improve the gain, a back reflector constructed on Fr-4 substrate with the size of 213 x 503 x 1.6 mm3has been used. The simulation results show that the first side lobe level can be suppressed to -40 dB at the frequency of 3.5 GHz while the maximum gain is 17.7 dBi. The simulated and measured reflection coefficients indicate that S1,1is equal -10 dB in the frequency range of 3.26-3.78 GHz. With these characteristics, the proposed antenna array is a good candidate for wireless systems in the C band.","PeriodicalId":409591,"journal":{"name":"2019 International Conference on Advanced Technologies for Communications (ATC)","volume":"92 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126922650","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 : 2019-10-01DOI: 10.1109/ATC.2019.8924509
Hong Son Vu, K. Truong, L. T. Bang, V. Y. Vu, M. Le
Beamforming and the direction of arrival (DOA) estimation for the massive multi-input multi-output (MIMO) play a significant role in the fifth-generation (5G) cellular networks. Several existing DOA and beamforming algorithms are validated for the MIMO antenna system in 5G gNodeB. The proposed non-blind adaptive beamforming algorithm using Recursive least squares Dolph Chebyshev (RLS-DC) with Uniformly spaced Linear Array (ULA) of 32 elements is presented in this paper. The sidelobe level is suppressed from -14 dB to -30 dB while steering area from -60º to +60º is obtained.
{"title":"An Investigation of Adaptive Digital Beamforming Antenna for gNodeB 5G","authors":"Hong Son Vu, K. Truong, L. T. Bang, V. Y. Vu, M. Le","doi":"10.1109/ATC.2019.8924509","DOIUrl":"https://doi.org/10.1109/ATC.2019.8924509","url":null,"abstract":"Beamforming and the direction of arrival (DOA) estimation for the massive multi-input multi-output (MIMO) play a significant role in the fifth-generation (5G) cellular networks. Several existing DOA and beamforming algorithms are validated for the MIMO antenna system in 5G gNodeB. The proposed non-blind adaptive beamforming algorithm using Recursive least squares Dolph Chebyshev (RLS-DC) with Uniformly spaced Linear Array (ULA) of 32 elements is presented in this paper. The sidelobe level is suppressed from -14 dB to -30 dB while steering area from -60º to +60º is obtained.","PeriodicalId":409591,"journal":{"name":"2019 International Conference on Advanced Technologies for Communications (ATC)","volume":"14 2 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124279509","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 : 2019-10-01DOI: 10.1109/ATC.2019.8924516
Chi Yen Nguyen, H. Tran, Tam Thanh Thi Ninh, Truong Quach Xuan, Q. Pham
A cooperative non-orthogonal multiple access (NOMA) communication is a promising solution to improve both the reliability and the capacity of the NOMA system. However, a relay can be exploited by a cooperative attack, this leads to a degradation of performance and secure of the NOMA system. Therefore, we propose a proactive protection scheme to mitigate the effect of the cooperative attack on the NOMA system. We consider the secrecy outage probability (SOP) of the cooperative NOMA in two cases: (1) the NOMA system has no protected scheme; (2) the NOMA system implements the protected scheme using the proactive attack technique. The results demonstrate that using proposed proactive attack scheme improve the secrecy performance of the system. Monte-clalo simulations are provided to examine our proposed scheme.
{"title":"Security Enhancement in NOMA Cooperative Network with a Proactive Attack Scheme","authors":"Chi Yen Nguyen, H. Tran, Tam Thanh Thi Ninh, Truong Quach Xuan, Q. Pham","doi":"10.1109/ATC.2019.8924516","DOIUrl":"https://doi.org/10.1109/ATC.2019.8924516","url":null,"abstract":"A cooperative non-orthogonal multiple access (NOMA) communication is a promising solution to improve both the reliability and the capacity of the NOMA system. However, a relay can be exploited by a cooperative attack, this leads to a degradation of performance and secure of the NOMA system. Therefore, we propose a proactive protection scheme to mitigate the effect of the cooperative attack on the NOMA system. We consider the secrecy outage probability (SOP) of the cooperative NOMA in two cases: (1) the NOMA system has no protected scheme; (2) the NOMA system implements the protected scheme using the proactive attack technique. The results demonstrate that using proposed proactive attack scheme improve the secrecy performance of the system. Monte-clalo simulations are provided to examine our proposed scheme.","PeriodicalId":409591,"journal":{"name":"2019 International Conference on Advanced Technologies for Communications (ATC)","volume":"275 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123717139","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 : 2019-10-01DOI: 10.1109/ATC.2019.8924559
Thanh-Hai Le, T. Nguyen, H. Phan
This paper introduces a method of determining quickly the direction of incoming signal from a radio radiation source in multi-path environment. In this environment, the signals arriving at the antenna array may come from one or many independent radio sources. Therefore, these signals may be uncorrelated or at high correlation level. To circumvent the signal correlation, the proposed method reconstructs the data vector received by the ULA antenna array into the Hermitian Toeplitz matrix form to expand the size of the noise space. Therefore, the signal space and noise can be evaluated more accurately. MUSIC algorithm is employed to determine the signal power spectrum. Since no forward-backward spatial smoothing technique is used, the computational complexity has been reduced. This proposed method can be applied in real-time applications because there needs to use only one signal pattern. The simulation results demonstrate that the proposed method results in better quality than those using ESPRIT and Matrix Pencil algorithms.
{"title":"Fast 1D Direction Finding Method In Multipath Environment","authors":"Thanh-Hai Le, T. Nguyen, H. Phan","doi":"10.1109/ATC.2019.8924559","DOIUrl":"https://doi.org/10.1109/ATC.2019.8924559","url":null,"abstract":"This paper introduces a method of determining quickly the direction of incoming signal from a radio radiation source in multi-path environment. In this environment, the signals arriving at the antenna array may come from one or many independent radio sources. Therefore, these signals may be uncorrelated or at high correlation level. To circumvent the signal correlation, the proposed method reconstructs the data vector received by the ULA antenna array into the Hermitian Toeplitz matrix form to expand the size of the noise space. Therefore, the signal space and noise can be evaluated more accurately. MUSIC algorithm is employed to determine the signal power spectrum. Since no forward-backward spatial smoothing technique is used, the computational complexity has been reduced. This proposed method can be applied in real-time applications because there needs to use only one signal pattern. The simulation results demonstrate that the proposed method results in better quality than those using ESPRIT and Matrix Pencil algorithms.","PeriodicalId":409591,"journal":{"name":"2019 International Conference on Advanced Technologies for Communications (ATC)","volume":"85 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124993972","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 : 2019-10-01DOI: 10.1109/ATC.2019.8924504
Hanh Phan-Xuan, T. Le-Tien, Thuy Nguyen-Chinh, Thien Do-Tieu, Qui Nguyen-Van, Tuan Nguyen-Thanh
As there are a huge range of powerful tools to edit images now, the need for verifying the authentication of images is more urgent than ever. While forgery methods are increasingly more subtle that even human vision seems hard to recognize these manipulations, conventional algorithms, which try to detect tampering traces, often pre-define assumptions that limit the scope of problem. Therefore, such methods are unable to encounter forgery methods in general applications. In this paper, we propose a framework that utilizes Deep Learning techniques to detect tampered images. Concretely, the MobileNetV2 network in [21] is modified so that it can be consistent to the task of image forgery detection. We argue that by remaining spatial dimension of early layers, the model is likely to learn rich features in these layers, and then following layers are to abstract these rich features for making a decision whether an image is forged. Besides, we also conduct a comprehensive experiment to prove those arguments. Experimental results show that the architecture-modified network achieves a remarkable accuracy of 95.15%, which surpasses others relying on the original architecture by a large margin up to 12.09%.
{"title":"Preserving Spatial Information to Enhance Performance of Image Forgery Classification","authors":"Hanh Phan-Xuan, T. Le-Tien, Thuy Nguyen-Chinh, Thien Do-Tieu, Qui Nguyen-Van, Tuan Nguyen-Thanh","doi":"10.1109/ATC.2019.8924504","DOIUrl":"https://doi.org/10.1109/ATC.2019.8924504","url":null,"abstract":"As there are a huge range of powerful tools to edit images now, the need for verifying the authentication of images is more urgent than ever. While forgery methods are increasingly more subtle that even human vision seems hard to recognize these manipulations, conventional algorithms, which try to detect tampering traces, often pre-define assumptions that limit the scope of problem. Therefore, such methods are unable to encounter forgery methods in general applications. In this paper, we propose a framework that utilizes Deep Learning techniques to detect tampered images. Concretely, the MobileNetV2 network in [21] is modified so that it can be consistent to the task of image forgery detection. We argue that by remaining spatial dimension of early layers, the model is likely to learn rich features in these layers, and then following layers are to abstract these rich features for making a decision whether an image is forged. Besides, we also conduct a comprehensive experiment to prove those arguments. Experimental results show that the architecture-modified network achieves a remarkable accuracy of 95.15%, which surpasses others relying on the original architecture by a large margin up to 12.09%.","PeriodicalId":409591,"journal":{"name":"2019 International Conference on Advanced Technologies for Communications (ATC)","volume":"4 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132184313","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 : 2019-10-01DOI: 10.1109/ATC.2019.8924560
M. Kyselak, F. Dvořak, C. Vlcek
Polarization Division Multiplexing is a promising technique for effectively increasing the capacity of optical routes. Its basic advantage is the possibility of being deployed on existing optical routes without the need to replace existing fibres or cables. The use of two optical fibre polarization axes allows the use of two independent transmission channels in a single optical fibre. The deployment options of Polarization Division Multiplexing can be evaluated using a tolerance field that can be obtained by measuring at the end of the optical path. This article discusses special measurement techniques and a new way of illustrating the Poincaré sphere's tolerance field., which allows evaluating the success of a Polarization Division Multiplexing technology at a glance. A detailed analysis of the tolerance field should simplify the idea of the activity of this type of multiplex and., for its clarity., it is also very suitable for study purposes. Unlike the transmission rate measurement., the measurement of the polarization multiplex tolerance field is a beneficial measurement showing the properties of the entire transmission system.
{"title":"Measurement Techniques for Determining the Polarization Division Multiplexing Tolerance Field","authors":"M. Kyselak, F. Dvořak, C. Vlcek","doi":"10.1109/ATC.2019.8924560","DOIUrl":"https://doi.org/10.1109/ATC.2019.8924560","url":null,"abstract":"Polarization Division Multiplexing is a promising technique for effectively increasing the capacity of optical routes. Its basic advantage is the possibility of being deployed on existing optical routes without the need to replace existing fibres or cables. The use of two optical fibre polarization axes allows the use of two independent transmission channels in a single optical fibre. The deployment options of Polarization Division Multiplexing can be evaluated using a tolerance field that can be obtained by measuring at the end of the optical path. This article discusses special measurement techniques and a new way of illustrating the Poincaré sphere's tolerance field., which allows evaluating the success of a Polarization Division Multiplexing technology at a glance. A detailed analysis of the tolerance field should simplify the idea of the activity of this type of multiplex and., for its clarity., it is also very suitable for study purposes. Unlike the transmission rate measurement., the measurement of the polarization multiplex tolerance field is a beneficial measurement showing the properties of the entire transmission system.","PeriodicalId":409591,"journal":{"name":"2019 International Conference on Advanced Technologies for Communications (ATC)","volume":"59 17","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114048191","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：