Pub Date : 2019-10-01DOI: 10.1109/icct46805.2019.8947147
{"title":"ICCT 2019 Conference Committee","authors":"","doi":"10.1109/icct46805.2019.8947147","DOIUrl":"https://doi.org/10.1109/icct46805.2019.8947147","url":null,"abstract":"","PeriodicalId":306112,"journal":{"name":"2019 IEEE 19th International Conference on Communication Technology (ICCT)","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":"129307938","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/ICCT46805.2019.8947220
Zeyu Lei, Yan Wang, Yufan Xu, Rui Huang
Predicting depth from an image is an essential problem in the area of computer vision and deep learning shows a great potential in this area. However most deep Convolutional Neural Networks are need to train them using vast amount of manually labelled data, which is difficult or even scarcely possible in some special environment. In this paper, we proposed an unsupervised method based on left-right consistence with multi-loss fusion, which can perform single image depth estimation, despite the absence of ground truth data. We treat the issue as an image reconstruction problem by training our network with a combine of SSIM and Huber loss. To achieve estimation the depth from coarse to fine, we estimate a coarse map in the former layer and using bilinear sample to transmit the map to the latter layer to obtain a fine depth map. Our method achieves more accurate result on KITTI driving dataset.
{"title":"From Coarse to Fine: A Monocular Depth Estimation Model Based on Left-Right Consistency","authors":"Zeyu Lei, Yan Wang, Yufan Xu, Rui Huang","doi":"10.1109/ICCT46805.2019.8947220","DOIUrl":"https://doi.org/10.1109/ICCT46805.2019.8947220","url":null,"abstract":"Predicting depth from an image is an essential problem in the area of computer vision and deep learning shows a great potential in this area. However most deep Convolutional Neural Networks are need to train them using vast amount of manually labelled data, which is difficult or even scarcely possible in some special environment. In this paper, we proposed an unsupervised method based on left-right consistence with multi-loss fusion, which can perform single image depth estimation, despite the absence of ground truth data. We treat the issue as an image reconstruction problem by training our network with a combine of SSIM and Huber loss. To achieve estimation the depth from coarse to fine, we estimate a coarse map in the former layer and using bilinear sample to transmit the map to the latter layer to obtain a fine depth map. Our method achieves more accurate result on KITTI driving dataset.","PeriodicalId":306112,"journal":{"name":"2019 IEEE 19th International Conference on Communication Technology (ICCT)","volume":"116 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":"124606125","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/ICCT46805.2019.8947266
Yuan Zhang, Mingyang Xie
This paper studies the resource scheduling problem for multi-cell cellular edge computing systems. Firstly, the analytical formulas of the communication delay and computing delay in multi-cell cellular edge computing systems are derived and expressed as virtual delay queues. Then, a delay based Lyapunov function is defined and a novel backpressure based subcarrier and virtual machine (VM) scheduling algorithm is proposed which stabilizes the virtual delay queues. Simulation results show that the total delay of the proposed scheduling algorithm is always lower than that of the queue length based traditional scheduling algorithm.
{"title":"Delay Based Subcarrier and VM Scheduling for Multi-cell Cellular Edge Computing Systems","authors":"Yuan Zhang, Mingyang Xie","doi":"10.1109/ICCT46805.2019.8947266","DOIUrl":"https://doi.org/10.1109/ICCT46805.2019.8947266","url":null,"abstract":"This paper studies the resource scheduling problem for multi-cell cellular edge computing systems. Firstly, the analytical formulas of the communication delay and computing delay in multi-cell cellular edge computing systems are derived and expressed as virtual delay queues. Then, a delay based Lyapunov function is defined and a novel backpressure based subcarrier and virtual machine (VM) scheduling algorithm is proposed which stabilizes the virtual delay queues. Simulation results show that the total delay of the proposed scheduling algorithm is always lower than that of the queue length based traditional scheduling algorithm.","PeriodicalId":306112,"journal":{"name":"2019 IEEE 19th International Conference on Communication Technology (ICCT)","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":"130778436","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/ICCT46805.2019.8947219
Xin Lin, Yikang Zhang, Hongmin Li, Gang Li, W. Qiao, Falin Liu
In wide-band digital predistortion linearizers, the number of coefficients of a simplified Volterra polynomial model required to model memory effects can increase dramatically, which causes large computational complexity, ill-conditioning or overfitting problems. We propose a novel digital predistortion (DPD) implementation approach called covariance matrix based independent parameters estimation (CM-IPE) method for a direct learning structure (DLA). In the approach, we use the constant transformation matrix to replace the time-varying transformation matrix because of the stationary and ergodic nature of input signals. And then the principal component analysis (PCA) method is applied for independent parameters estimation. The proposed method can reduce computational complexity. And by utilizing the PCA technique, the coefficients can be estimated independently which, at the same time, can prevent ill-conditioning or overfitting problems. Experimental results demonstrate that the proposed approach realizes the equivalent linearization performance as the traditional DLA method at lower computational complexity.
{"title":"Low Computational Complexity Digital Predistortion Based on Independent Parameters Estimation","authors":"Xin Lin, Yikang Zhang, Hongmin Li, Gang Li, W. Qiao, Falin Liu","doi":"10.1109/ICCT46805.2019.8947219","DOIUrl":"https://doi.org/10.1109/ICCT46805.2019.8947219","url":null,"abstract":"In wide-band digital predistortion linearizers, the number of coefficients of a simplified Volterra polynomial model required to model memory effects can increase dramatically, which causes large computational complexity, ill-conditioning or overfitting problems. We propose a novel digital predistortion (DPD) implementation approach called covariance matrix based independent parameters estimation (CM-IPE) method for a direct learning structure (DLA). In the approach, we use the constant transformation matrix to replace the time-varying transformation matrix because of the stationary and ergodic nature of input signals. And then the principal component analysis (PCA) method is applied for independent parameters estimation. The proposed method can reduce computational complexity. And by utilizing the PCA technique, the coefficients can be estimated independently which, at the same time, can prevent ill-conditioning or overfitting problems. Experimental results demonstrate that the proposed approach realizes the equivalent linearization performance as the traditional DLA method at lower computational complexity.","PeriodicalId":306112,"journal":{"name":"2019 IEEE 19th International Conference on Communication Technology (ICCT)","volume":"81 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":"130886211","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/ICCT46805.2019.8947146
Yueyue Dai, Du Xu, Kecheng Zhang, Yunlong Lu, Sabita Maharjan, Yan Zhang
By extending computation capacity to the edge of wireless networks, edge computing has the potential to enable computation-intensive and delay-sensitive applications in 5G and beyond via computation offloading. However, in multi-user heterogeneous networks, it is challenging to capture complete network information, such as wireless channel state, available bandwidth or computation resources. The strong couplings among devices on application requirements or radio access mode make it more difficult to design an optimal computation offloading scheme. Deep Reinforcement Learning (DRL) is an emerging technique to address such an issue with limited and less accurate network information. In this paper, we utilize DRL to design an optimal computation offloading and resource allocation strategy for minimizing system energy consumption. We first present a multi-user edge computing framework in heterogeneous networks. Then, we formulate the joint computation offloading and resource allocation problem as a DRL form and propose a new DRL-inspired algorithm to minimize system energy consumption. Numerical results based on a realworld dataset demonstrate demonstrate the effectiveness of our proposed algorithm, compared to two benchmark solutions.
{"title":"Deep Reinforcement Learning for Edge Computing and Resource Allocation in 5G Beyond","authors":"Yueyue Dai, Du Xu, Kecheng Zhang, Yunlong Lu, Sabita Maharjan, Yan Zhang","doi":"10.1109/ICCT46805.2019.8947146","DOIUrl":"https://doi.org/10.1109/ICCT46805.2019.8947146","url":null,"abstract":"By extending computation capacity to the edge of wireless networks, edge computing has the potential to enable computation-intensive and delay-sensitive applications in 5G and beyond via computation offloading. However, in multi-user heterogeneous networks, it is challenging to capture complete network information, such as wireless channel state, available bandwidth or computation resources. The strong couplings among devices on application requirements or radio access mode make it more difficult to design an optimal computation offloading scheme. Deep Reinforcement Learning (DRL) is an emerging technique to address such an issue with limited and less accurate network information. In this paper, we utilize DRL to design an optimal computation offloading and resource allocation strategy for minimizing system energy consumption. We first present a multi-user edge computing framework in heterogeneous networks. Then, we formulate the joint computation offloading and resource allocation problem as a DRL form and propose a new DRL-inspired algorithm to minimize system energy consumption. Numerical results based on a realworld dataset demonstrate demonstrate the effectiveness of our proposed algorithm, compared to two benchmark solutions.","PeriodicalId":306112,"journal":{"name":"2019 IEEE 19th International Conference on Communication Technology (ICCT)","volume":"19 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":"129931302","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/ICCT46805.2019.8947238
Heming Ding, Guangming Li, Menghui Xu
The methods of realizing broadband of dipole antenna are summarized and analyzed. Due to the narrow operating frequency band of the dipole antenna, in order to improve the bandwidth of the dipole antenna and improve its spectrum efficiency, the broadband of the dipole antenna is studied. This is also in line with the research trend of broadband antenna. This paper probes into the broadband methods of dipole antenna and analyzes the advantages and disadvantages of each method. It is pointed out that the core problem of broadband antenna is how to compromise the relationship between broadband antenna and other performance changes brought by broadband antenna. We propose that optimization algorithms can be used in antenna design to solve the problems caused by broadband antenna.
{"title":"Overview of Research on Broadband of Dipole Antenna","authors":"Heming Ding, Guangming Li, Menghui Xu","doi":"10.1109/ICCT46805.2019.8947238","DOIUrl":"https://doi.org/10.1109/ICCT46805.2019.8947238","url":null,"abstract":"The methods of realizing broadband of dipole antenna are summarized and analyzed. Due to the narrow operating frequency band of the dipole antenna, in order to improve the bandwidth of the dipole antenna and improve its spectrum efficiency, the broadband of the dipole antenna is studied. This is also in line with the research trend of broadband antenna. This paper probes into the broadband methods of dipole antenna and analyzes the advantages and disadvantages of each method. It is pointed out that the core problem of broadband antenna is how to compromise the relationship between broadband antenna and other performance changes brought by broadband antenna. We propose that optimization algorithms can be used in antenna design to solve the problems caused by broadband antenna.","PeriodicalId":306112,"journal":{"name":"2019 IEEE 19th International Conference on Communication Technology (ICCT)","volume":"36 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":"128865603","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/ICCT46805.2019.8947114
Jichao Liu, Yahong Zhao, Ji Yang, Xiaoke Tang
IEEE 802.15.4g Standard specifies multi-rate and multi-regional orthogonal frequency division multiplexing (MR-OFDM) physical layer, which supports principally outdoor, low-data-rate, wireless, smart metering utility network (SUN). Caused by Doppler frequency shift of fading channel, the inter-channel interference (ICI) arises in MROFDM system. In this paper, the degrading of performance due to ICI for detection of phase shift keying modulation signal is provided. It is derived that non-ideal properties for reception symbols are characterized by sampling offset and phase shift on subcarrier. Furthermore, the influence on data demodulation under different conditions is analyzed in detail. Simulation results are consistent with the theoretical analysis.
{"title":"Performance Analysis of IEEE 802.15.4g MR-OFDM with Frequency Offset","authors":"Jichao Liu, Yahong Zhao, Ji Yang, Xiaoke Tang","doi":"10.1109/ICCT46805.2019.8947114","DOIUrl":"https://doi.org/10.1109/ICCT46805.2019.8947114","url":null,"abstract":"IEEE 802.15.4g Standard specifies multi-rate and multi-regional orthogonal frequency division multiplexing (MR-OFDM) physical layer, which supports principally outdoor, low-data-rate, wireless, smart metering utility network (SUN). Caused by Doppler frequency shift of fading channel, the inter-channel interference (ICI) arises in MROFDM system. In this paper, the degrading of performance due to ICI for detection of phase shift keying modulation signal is provided. It is derived that non-ideal properties for reception symbols are characterized by sampling offset and phase shift on subcarrier. Furthermore, the influence on data demodulation under different conditions is analyzed in detail. Simulation results are consistent with the theoretical analysis.","PeriodicalId":306112,"journal":{"name":"2019 IEEE 19th International Conference on Communication Technology (ICCT)","volume":"16 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":"125624573","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/ICCT46805.2019.8947227
K. Mao, Xianqiang Li, Chen Wei, Zhiyuan Ma, Xixiu Wu
When the high-power VLF (Very Low Frequency) communication system is in operation, dielectric loss and corresponding temperature rising will occur at the terminal of the antenna due to the alternating high electric field intensity environment. Based on the theoretical analysis of dielectric loss and temperature rise, the distribution of electric field intensity at the terminal of antenna and its influencing factors are numerically analyzed by establishing a three-dimensional simulation model. The results show that the electric field intensity varies linearly with the increase of the voltage of the antenna terminal; however, the working frequency has little effect on the electric field intensity. Finally, the reduction effect of a corona ring on the electric field intensity at the antenna terminal is analyzed.
{"title":"Numerical Analysis of Electric Field Distribution at the Terminal of VLF Antenna","authors":"K. Mao, Xianqiang Li, Chen Wei, Zhiyuan Ma, Xixiu Wu","doi":"10.1109/ICCT46805.2019.8947227","DOIUrl":"https://doi.org/10.1109/ICCT46805.2019.8947227","url":null,"abstract":"When the high-power VLF (Very Low Frequency) communication system is in operation, dielectric loss and corresponding temperature rising will occur at the terminal of the antenna due to the alternating high electric field intensity environment. Based on the theoretical analysis of dielectric loss and temperature rise, the distribution of electric field intensity at the terminal of antenna and its influencing factors are numerically analyzed by establishing a three-dimensional simulation model. The results show that the electric field intensity varies linearly with the increase of the voltage of the antenna terminal; however, the working frequency has little effect on the electric field intensity. Finally, the reduction effect of a corona ring on the electric field intensity at the antenna terminal is analyzed.","PeriodicalId":306112,"journal":{"name":"2019 IEEE 19th International Conference on Communication Technology (ICCT)","volume":"46 5","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"120974556","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/ICCT46805.2019.8947132
Juan Yang, Zhiping Shi, Dandi Yang, Chen-Xi Wang
In this paper, we propose an improved belief propagation (BP) decoding algorithm for decoding BATS codes. In the traditional BP decoding, the BP decoder decodes the input packets only when the rank equals to the degree of the efficient matrix for a batch. For improving the decoding performance, our proposed scheme exploits the fact that some packets can be decoded even when the rank is smaller than the degree. We decode these packets in the process of calculating the rank of batch, which will not induce extra computational cost. The simulation results show that the decoding performance of our proposed method is better than the traditional BATS codes.
{"title":"An Improved Belief Propagation Decoding of BATS Codes","authors":"Juan Yang, Zhiping Shi, Dandi Yang, Chen-Xi Wang","doi":"10.1109/ICCT46805.2019.8947132","DOIUrl":"https://doi.org/10.1109/ICCT46805.2019.8947132","url":null,"abstract":"In this paper, we propose an improved belief propagation (BP) decoding algorithm for decoding BATS codes. In the traditional BP decoding, the BP decoder decodes the input packets only when the rank equals to the degree of the efficient matrix for a batch. For improving the decoding performance, our proposed scheme exploits the fact that some packets can be decoded even when the rank is smaller than the degree. We decode these packets in the process of calculating the rank of batch, which will not induce extra computational cost. The simulation results show that the decoding performance of our proposed method is better than the traditional BATS codes.","PeriodicalId":306112,"journal":{"name":"2019 IEEE 19th International Conference on Communication Technology (ICCT)","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":"122327753","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/ICCT46805.2019.8947273
Yan Xu, Yi Zheng, Hao Cui, Yifan Hu, Xiaodong Gong, Hui Liu
Aiming at the problem of One-Side EMD on non-equal modulus composite signal processing, this paper proposes the mechanism and method for phase spectrum decomposition based on spectral component companding. This mechanism proposes the conception of “Hypothesis Equimodular Vector”, designs the phase deflection model to calculate equalmodulus resultant vector through spectral component companding method, constructs equal modulus phase spectrum and its One-Side superposition. The equal modulus phase spectrum has features forOne-Side EMD and could be decomposed. This mechanism and method extend One-Side EMD use field from equal modulus to non-equal, which could gain higher generality and wider application prospect. The simulation testing proves that it could be used in the instantaneous time-frequency analysis for any two frequency components with higher reliability and accuracy.
{"title":"The Research on Phase Spectrum Decomposition Mechanism Based on Spectral Component Companding","authors":"Yan Xu, Yi Zheng, Hao Cui, Yifan Hu, Xiaodong Gong, Hui Liu","doi":"10.1109/ICCT46805.2019.8947273","DOIUrl":"https://doi.org/10.1109/ICCT46805.2019.8947273","url":null,"abstract":"Aiming at the problem of One-Side EMD on non-equal modulus composite signal processing, this paper proposes the mechanism and method for phase spectrum decomposition based on spectral component companding. This mechanism proposes the conception of “Hypothesis Equimodular Vector”, designs the phase deflection model to calculate equalmodulus resultant vector through spectral component companding method, constructs equal modulus phase spectrum and its One-Side superposition. The equal modulus phase spectrum has features forOne-Side EMD and could be decomposed. This mechanism and method extend One-Side EMD use field from equal modulus to non-equal, which could gain higher generality and wider application prospect. The simulation testing proves that it could be used in the instantaneous time-frequency analysis for any two frequency components with higher reliability and accuracy.","PeriodicalId":306112,"journal":{"name":"2019 IEEE 19th International Conference on Communication Technology (ICCT)","volume":"107 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":"116369310","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：