{"title":"Feature Selection of Input Variables for Diagnosis of Patellofemoral Pain Syndrome based on Random Forest and Multilayer Perceptron","authors":"Wuxiang Shi, Baoping Xiong, Yurong Li, Min Du","doi":"10.1109/CSRSWTC50769.2020.9372597","DOIUrl":"https://doi.org/10.1109/CSRSWTC50769.2020.9372597","url":null,"abstract":"Patellofemoral pain syndrome (PFPS) is a common knee disease in the clinic. Its etiology is various, involving a variety of biomechanical variables of lower limbs. Most of the traditional diagnostic methods are subjective and the diagnostic accuracy mainly depends on the experience of doctors. A machine learning method is proposed in this paper to objectively analyze the related variables of PFPS and classify it to assist doctors in diagnosis. The proposed method was tested on a running data set of forty-one subjects, which included seven surface electromyography (sEMG) and three joint angles. Firstly, the importance of ten biomechanical features related to PFPS was compared by the analysis of variance and mean combined with random forest (RF), and then the six most important features were selected. Finally, the 100-time sampling points of each feature selected were input into the multilayer perceptron (MLP) for classification. The classification accuracy is 75% with a 40% reduction of input variables, which is not much different from the 76% accuracy before feature selection. Compared with previous work, the proposed method explores the importance of features related to PFPS from a new perspective, which can assist doctors in the diagnosis of PFPS.","PeriodicalId":207010,"journal":{"name":"2020 Cross Strait Radio Science & Wireless Technology Conference (CSRSWTC)","volume":"97 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-12-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130597647","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":"Non-Ghosting Stitching for Street-View Image","authors":"Z. Lin, Xiaoying Tang, Hongan Wei","doi":"10.1109/CSRSWTC50769.2020.9372606","DOIUrl":"https://doi.org/10.1109/CSRSWTC50769.2020.9372606","url":null,"abstract":"Parallax, relative camera motion, and illumination changes can cause artifacts in stitched images. For example, we might see ghosting effect on the pedestrian who is located at the overlapping region in a stitched image. Existing techniques struggle at dealing with the artifacts and perspective distortion. We propose an innovative image stitching algorithm which combines portrait segmentation and image inpainting. Images from different cameras are first segmented into the pedestrian plane and the scene plane by portrait segmentation. Then, images in different planes are stitched. Finally, the pedestrian plane and the scene plane are fused by aligning and inpainting. Experiments show that our method can remove ghosting effect in stitched street-view images more effectively than existing meth-ods.","PeriodicalId":207010,"journal":{"name":"2020 Cross Strait Radio Science & Wireless Technology Conference (CSRSWTC)","volume":"11 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-12-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129865181","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}
Zhiying Zhao, Peng Zhao, Shichang Chen, Kuiwen Xu, Bo Yuan, Gaofeng Wang
{"title":"An improved Frequency Sweeping Method for Wide-Band Electromagnetic Analysis","authors":"Zhiying Zhao, Peng Zhao, Shichang Chen, Kuiwen Xu, Bo Yuan, Gaofeng Wang","doi":"10.1109/CSRSWTC50769.2020.9372563","DOIUrl":"https://doi.org/10.1109/CSRSWTC50769.2020.9372563","url":null,"abstract":"This paper proposes an improved adaptive frequency sweeping method for electromagnetic simulation. A new convergence criteria of frequency sweep is defined. In addition, by combining matrix rational interpolation and dichotomy frequency sweep, the number of frequency points required for direct calculation is reduced compared with the traditional interpolation-based method. A numerical example is given to prove the effectiveness of the proposed method.","PeriodicalId":207010,"journal":{"name":"2020 Cross Strait Radio Science & Wireless Technology Conference (CSRSWTC)","volume":"2019 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-12-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128039750","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":"A Method to Improve the Testing Efficiency of ADC and Some RF Chips","authors":"W. Li, C. Wenli, Tao Tequan, Z. Wenjian","doi":"10.1109/CSRSWTC50769.2020.9372695","DOIUrl":"https://doi.org/10.1109/CSRSWTC50769.2020.9372695","url":null,"abstract":"At present, with the development of semiconductor technology, IC test cost accounts for an increasing proportion of the total cost of chip products. How to reduce the cost of IC test has become the focus of the integrated circuit industry. This article proposes a method to improve the testing efficiency based on some dynamic parameters of ADCs and radio frequency chips. Aiming at the characteristic that the traditional sine wave test method can only test one frequency point at a time, this method can realize the test of multiple frequency points at a time, which reduces the chip test time and the test cost.","PeriodicalId":207010,"journal":{"name":"2020 Cross Strait Radio Science & Wireless Technology Conference (CSRSWTC)","volume":"135 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-12-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126463678","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":"Study on Beam Wave Interaction of Terahertz Radiation Source Based on Grating Structure","authors":"Longlong Yang, Wenxin Liu, Zhengyuan Zhao, Yue Ou","doi":"10.1109/CSRSWTC50769.2020.9372534","DOIUrl":"https://doi.org/10.1109/CSRSWTC50769.2020.9372534","url":null,"abstract":"The vacuum electron device (VED) is one of the best devices to generate terahertz wave with its advantages of high power, high frequency and power synthesis. In order to obtain higher power terahertz wave, it is imperative to improve the output power and efficiency of VED. For this aim, we propose a novel THz rectangular grating slow wave structure (SWS). The SWS can make full use of the longitudinal electric field of the slot, so that the electromagnetic wave can interact with the electron beam efficiently, so as to improve the beam-wave interaction efficiency and output power. The field characteristics of the novel SWS are analyzed, and the “cold” dispersion equations are derived by the eigen-function method, and the dispersion characteristics and coupling impedance are calculated. The results show that the grating SWS with double holes embed sheet beams has higher working frequency and coupling impedance than the ordinary grating without any slot. These studies provide theoretical guidance for the design of the grating SWS with double holes embed sheet beams.","PeriodicalId":207010,"journal":{"name":"2020 Cross Strait Radio Science & Wireless Technology Conference (CSRSWTC)","volume":"36 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-12-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125707075","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":"Improving the Signal-to-Noise Ratio on Terahertz Compressive Imaging","authors":"Chungui Xing, F. Qi, Shuxu Guo","doi":"10.1109/CSRSWTC50769.2020.9372714","DOIUrl":"https://doi.org/10.1109/CSRSWTC50769.2020.9372714","url":null,"abstract":"we present a compact terahertz compressive imaging utilizing the vector network analyzer base on the compressive sensing technology. To eliminate the noise from the terahertz imaging system and improve the signal-to-noise ratio of the reconstructed image, we propose a novel compressive sensing methodology, in which the Paley-Hadamard sensing matrix and normalization measurement data algorithm are introduced. From the numerical and experimental results, the anti-noise performance of the proposed methodology is superior to the conventional compressive technology.","PeriodicalId":207010,"journal":{"name":"2020 Cross Strait Radio Science & Wireless Technology Conference (CSRSWTC)","volume":"20 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-12-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126865755","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":"Terahertz Transmitarray Antenna Using Rotated Z-shaped Elements","authors":"Yaohui Yang, Jianqin Deng, Qiantao Cao","doi":"10.1109/CSRSWTC50769.2020.9372493","DOIUrl":"https://doi.org/10.1109/CSRSWTC50769.2020.9372493","url":null,"abstract":"A terahertz transmitarray antenna working at the center frequency of 300 GHz is proposed. The antenna is based on a new-type transmitting element, which is composed of a dual Z-shaped configurations, mirror symmetrically printed on the two layers of a thin quartz substrate. Wide phase modulation coverage is achieved by changing the rotated angle of the Z-shaped element, simultaneously with a small change of the overall size. Phase modulation coverage of 360 degrees is obtained with a stacked four-layer design. The transmitarray element has both wide bandwidth and linear phase response characteristics. The proposed structure is simple and also has a good performance on fabrication tolerance, which makes it suitable for terahertz band designs. A standard WR-2.8 waveguide is used to normally illuminate the stacked four-layer transmitarrays. Simulated results show stable radiation patterns and low sidelobe levels in a wide frequency band. The 3-dB gain bandwidth is 18%, and the cross polarization level is lower than −33 dB.","PeriodicalId":207010,"journal":{"name":"2020 Cross Strait Radio Science & Wireless Technology Conference (CSRSWTC)","volume":"45 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-12-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126880922","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}
Shiyu Wang, Lihua Li, J. Liang, Yukan Liu, Wen-Da Hou, Yong-bin Wang
{"title":"Analysis of Antenna Performance in Complex Sea Conditions Based on Ergodic Algorithm","authors":"Shiyu Wang, Lihua Li, J. Liang, Yukan Liu, Wen-Da Hou, Yong-bin Wang","doi":"10.1109/CSRSWTC50769.2020.9372435","DOIUrl":"https://doi.org/10.1109/CSRSWTC50769.2020.9372435","url":null,"abstract":"To explore the communication performance of the underwater vehicle towing antenna under complex sea conditions, the maximum gain and reflection coefficient of the whole attitude of the half-wave vibrator antenna under complex sea conditions were calculated from the angle of the antenna relative to the horizontal plane and the length beyond the sea surface, combined with the ergodic algorithm and FEKO electromagnetic simulation software. The results show that the gain of the towed antenna is above −46dBi and the reflection coefficient is below 0.5 in 75% of the states.","PeriodicalId":207010,"journal":{"name":"2020 Cross Strait Radio Science & Wireless Technology Conference (CSRSWTC)","volume":"21 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-12-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127225376","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":"Joint Multi-Scale and Dual Attention Gate Network for Pulmonary Vessel Segmentation","authors":"Yuhang She, Jinquan Guo","doi":"10.1109/CSRSWTC50769.2020.9372459","DOIUrl":"https://doi.org/10.1109/CSRSWTC50769.2020.9372459","url":null,"abstract":"Pulmonary vessel segmentation is an important precondition for diagnosis, quantitative analysis and treatment planning of pulmonary diseases. Recently, Convolutional Neural Networks (CNNs) has achieved great success in biomedical image processing. However, due to the complex structure, inter-vessel differences and clinical lesions, pulmonary vessel segmentation still faces great challenges. In this work, we propose a novel end-to-end pulmonary vessel segmentation network named Joint Multi-Scale and Dual Attention Gate Network (JMSDAGNet). The JMSDAGNet aggregate feature maps of different scales, which can effectively improve the segmentation accuracy of thin vessels. To focus on vascular areas and suppress the noise caused by diseases, we introduce attention mechanisms that can adaptively learn local and global information. We trained and validated the proposed JMSDAGNet in a custom dataset. Both quantitative and qualitative results of the comprehensive experiments prove the superiority of our proposed method in comparison with the state-of-the-art methods.","PeriodicalId":207010,"journal":{"name":"2020 Cross Strait Radio Science & Wireless Technology Conference (CSRSWTC)","volume":"13 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-12-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114160511","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}