{"title":"Frequency-Difference Matched Field Processing for Broadband Source Localization With One Hydrophone in Shallow Ocean Environment","authors":"Yonggang Lin, Min Zhu, Yanqun Wu, Wen Zhang","doi":"10.1109/ICICSP50920.2020.9232089","DOIUrl":"https://doi.org/10.1109/ICICSP50920.2020.9232089","url":null,"abstract":"Matched field processing (MFP) is appliable to localize tonal sources with arrays and sensitive to the environment mismatch. To localize a broadband source with one hydrophone in shallow water, a new method utilizing frequency-difference autoproduct is proposed in this paper Simulations have been conducted to evaluate the performance of the method. A sea trial data from the SACLAT experiment (1993) is also used to validate it. Comparing to MFP with one hydrophone’s magnitude-only data, the new method is more robust to the environment and has a higher success rate of source localization.","PeriodicalId":117760,"journal":{"name":"2020 IEEE 3rd International Conference on Information Communication and Signal Processing (ICICSP)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2020-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128702525","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}
Shi Wen, Wang Zhengyang, Zhou Shiping, Ling Yunji, Hu Zhe
{"title":"Target Tracking of Radar Seeker Based on Converted Measurement Kalman Filter","authors":"Shi Wen, Wang Zhengyang, Zhou Shiping, Ling Yunji, Hu Zhe","doi":"10.1109/ICICSP50920.2020.9232123","DOIUrl":"https://doi.org/10.1109/ICICSP50920.2020.9232123","url":null,"abstract":"For the requirement of sea-surface target tracking, based on CA motion model, the statistical distribution of the measurement deviation of radar seeker resulting from coordinate transformation and the prediction deviation caused by SIMU error was deduced in this paper. By removing such deviations in the measurement equation and the prediction equation in Kalman filter, the filter is able to converge correctly. Simulation results show the stable target tracking is achieved after a brief convergence by this method.","PeriodicalId":117760,"journal":{"name":"2020 IEEE 3rd International Conference on Information Communication and Signal Processing (ICICSP)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2020-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127340077","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}
{"title":"Facial Expression Recognition Based on Sobel Operator and Improved CNN-SVM","authors":"Sirui Liu, Xiaoyu Tang, Dong Wang","doi":"10.1109/ICICSP50920.2020.9232063","DOIUrl":"https://doi.org/10.1109/ICICSP50920.2020.9232063","url":null,"abstract":"Aiming at the problem that traditional convolutional neural networks (CNN) have incomplete facial expression feature extraction and optimizable recognition accuracy in facial expression recognition (FER), this paper proposes a FER model based on improved CNN for Sobel edge detection and fused support vector machine (SVM). In this model, the VGG11 network is used to realize the feature extraction of facial expressions, and the L2-SVM is used to replace the softmax activation function to realize facial expression classification. This paper has been verified on the CK+ and JAFFE data sets, and the experimental results show that on the CK+ data set, after replacing the softmax activation function with L2-SVM, the accuracy rate has been improved by 3.02%. On this basis, in the image preprocessing stage, after adding Sobel edge detection, the accuracy has been improved by 3.71%. On the JAFFE data set, after using L2-SVM, the accuracy rate has increased by 2.16%, and after adding Sobel edge detection, it has increased by 2.17%.","PeriodicalId":117760,"journal":{"name":"2020 IEEE 3rd International Conference on Information Communication and Signal Processing (ICICSP)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2020-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126840934","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}
{"title":"Analysis of the Boundary Effect on Signal Detection in Unwrapped Phase Noise","authors":"Zhongtao Luo, Yanmei Zhan, Yangyong Zhang","doi":"10.1109/ICICSP50920.2020.9232074","DOIUrl":"https://doi.org/10.1109/ICICSP50920.2020.9232074","url":null,"abstract":"This paper analyzes signal detection in the phase domain and the boundary effect due to the phase noise. Considering the sum of a complex function and additive zero-mean complex Gaussian noise, the phase model is developed under the assumption of perfect phase unwrapping. Then, based on the matched filter, two detectors are proposed, depending on if the phase boundary is employed. The analysis shows that the boundary introduces zero likelihood in the maximum likelihood criterion and so changes the decision rule greatly, resulting in a significant improvement on the detection performance. The binary phase shift keying is analyzed for wireless communication via the phase domain.","PeriodicalId":117760,"journal":{"name":"2020 IEEE 3rd International Conference on Information Communication and Signal Processing (ICICSP)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2020-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126950232","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}
{"title":"Mandarin Singing Synthesis Based on Generative Adversarial Network","authors":"Yun Zhou, Hongwu Yang, Ziyan Chen, Yajing Yan","doi":"10.1109/ICICSP50920.2020.9232118","DOIUrl":"https://doi.org/10.1109/ICICSP50920.2020.9232118","url":null,"abstract":"This paper proposed a method for statistical parametric singing synthesis incorporating GAN (Generative Adversarial Network) that trained acoustic model. In GAN, the acoustic model was trained to minimize the weighted sum of the conventional minimum generation loss and adversarial loss, which was minimizing the distance between the natural and generated samples parameter, thus effectively solved the problem of over-smoothing. In the experimental part, we established a singing voice corpus with 60 songs and divided them that have been recorded and labeled into about 1000 sentences, of which 950 sentences were for training model. Comparing the generated songs of the method proposed in this paper and HMM, through 10 people MOS scores, the score of the former was 3.12 that was better than the latter of 2.81.","PeriodicalId":117760,"journal":{"name":"2020 IEEE 3rd International Conference on Information Communication and Signal Processing (ICICSP)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2020-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129459269","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}
{"title":"ADS-B system Based on SDN and ISIS","authors":"Jun Tao, Z. Yan, Min Du, Yang Shen","doi":"10.1109/ICICSP50920.2020.9232062","DOIUrl":"https://doi.org/10.1109/ICICSP50920.2020.9232062","url":null,"abstract":"ADS-B is an excellent aircraft surveillance system, but there are many deficiencies in RIP protocol and OSPF protocol that traditional ADS-B carrier network relies on. ISIS protocol deployed through SDN has obvious advantages over traditional OSPF and RIP protocols. Based on the simulation experiment, the ADS-B carrier network is reconstructed by using SDN and ISIS protocol, a more efficient ADS-B cooperative work algorithm named Ncoop is proposed. The parameters and operation efficiency of the network system are analyzed in detail, the related results are good and the expected effect is achieved.","PeriodicalId":117760,"journal":{"name":"2020 IEEE 3rd International Conference on Information Communication and Signal Processing (ICICSP)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2020-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121571569","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}
{"title":"Facial expression recognition using convolutional neural network with weighted loss function","authors":"Jiawei Luan","doi":"10.1109/ICICSP50920.2020.9232088","DOIUrl":"https://doi.org/10.1109/ICICSP50920.2020.9232088","url":null,"abstract":"Facial expression is an important content in human communication as it is participating in nearly half of the human interaction. The recognition of facial expression has been applied in security, criminal research, entertainment applications, and other human-computer-interaction fields. Facial expression recognition is being extensively studied in recent years and have reached satisfactory results. However, the type of images of expressions in the commonly used datasets are unbalanced and cause the recognition of one to two facial expressions are harder than others, which affects the accuracy of the whole, Therefore, we create a loss function aim to decrease the effect of this unbalance. With the combination of the state-of-art convolutional neural network and our loss function, the accuracy on the FER-2013 dataset has raised about 2%.","PeriodicalId":117760,"journal":{"name":"2020 IEEE 3rd International Conference on Information Communication and Signal Processing (ICICSP)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2020-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116748069","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}
{"title":"Construction of word level Tibetan Lip Reading Dataset","authors":"Zhenye Gan, Hao Zeng, Hongwu Yang, Shihua Zhou","doi":"10.1109/ICICSP50920.2020.9231973","DOIUrl":"https://doi.org/10.1109/ICICSP50920.2020.9231973","url":null,"abstract":"With the development of deep learning technology, dataset always play an important role in different research fields. Lip reading, which involves image processing and natural language processing, has become one of the most challenging research topics in the field of deep learning. However, the diversity of lip changes and the richness of language itself greatly improve the difficulty of lip reading, which leads to the slow progress of lip reading research. In order to provide a good basis for future Tibetan lip reading, this paper constructs the first Tibetan lip reading dataset, named TLRW-50, which is saved as a series of lip-shaped image sequences after data preprocessing. The complete process and algorithm details of the Tibetan lip reading dataset are proposed and the quality of the lip reading video is evaluated. Six methods of image data expansion are used to expand the lip image frame sequence: color enhancement, Gaussian noise, horizontal image, amplification, rotation and clipping. Ten Tibetan speakers were selected to evaluate the quality of the cut lip reading video before the expansion of the lip image sequence. The MOS score was 3.8.","PeriodicalId":117760,"journal":{"name":"2020 IEEE 3rd International Conference on Information Communication and Signal Processing (ICICSP)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2020-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130003244","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}
{"title":"Anti Spatial Aliasing HOA Encoding Method based on Aliasing Projection Matrix","authors":"Jing Lin, Xihong Wu, T. Qu","doi":"10.1109/ICICSP50920.2020.9232079","DOIUrl":"https://doi.org/10.1109/ICICSP50920.2020.9232079","url":null,"abstract":"Higher order Ambisonics (HOA) is a 3D sound decomposition and reproduction technology that represent 3D sound fields based on a series of spherical harmonic functions. However, practical application of HOA technology is limited by narrow available bandwidth, low-frequency noise pollution and high-frequency spatial aliasing. Inspired by the sparse recovery method, anti-spatial aliasing HOA encoding method which combines aliasing projection matrix and sparse recovery is presented to obtain better high frequency performance. In this work, we explain the causes of spatial aliasing and propose anti-spatial aliasing HOA encoding method. Then a series of simulations were carried out to verify the effectiveness the proposed method.","PeriodicalId":117760,"journal":{"name":"2020 IEEE 3rd International Conference on Information Communication and Signal Processing (ICICSP)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2020-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133505992","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}
Liangling Lai, Jinsong Hu, Youjia Chen, Haifeng Zheng, Nan Yang
{"title":"Directional Modulation-Enabled Secure Transmission with Intelligent Reflecting Surface","authors":"Liangling Lai, Jinsong Hu, Youjia Chen, Haifeng Zheng, Nan Yang","doi":"10.1109/ICICSP50920.2020.9232092","DOIUrl":"https://doi.org/10.1109/ICICSP50920.2020.9232092","url":null,"abstract":"We propose a new secure transmission scheme which uses directional modulation (DM) with artificial noise and is aided by the intelligent reflecting surface (IRS). Specifically, the direct path and IRS-enabled reflect path carry the same confidential signal and thus can be coherently added at the desired position to maximize the total received power, while the received signals at other positions are distorted. We derive a closed-form expression for the secrecy rate achieved by the proposed scheme. Using simulation results, we show that the proposed scheme can achieve two-dimensional secure transmission at a specific position. Also, its performance advantage over the conventional DM scheme becomes more pronounced as the number of reflecting elements at the IRS increases.","PeriodicalId":117760,"journal":{"name":"2020 IEEE 3rd International Conference on Information Communication and Signal Processing (ICICSP)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2020-07-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124954437","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}