Zhikang Wang, Xingjuan Xi, G. Liao, Lan Lan, Hui Chen
{"title":"Refined Modeling and Simulation Method of Raw Signal Returns for Space-based Radar","authors":"Zhikang Wang, Xingjuan Xi, G. Liao, Lan Lan, Hui Chen","doi":"10.1109/ICPECA56706.2023.10076012","DOIUrl":"https://doi.org/10.1109/ICPECA56706.2023.10076012","url":null,"abstract":"Radar echo refinement simulation is an important means to provide data for space-based radar design demonstration. Most of the current simulation methods ignore the real surface topography and complex geomorphic distribution, and the target characteristics are not sufficiently described, resulting in a shortage of refined radar echo data, which is difficult to meet the demonstration requirements of space-based radar early warning detection system. This paper proposes a more refined simulation method for space-based radar echo, mainly from the background clutter and target echo two aspects of fine modeling: Firstly, based on the real ground battlefield environment fluctuation model and complex geomorphic distribution attributes constructed by GIS (Geographic Information System) data, a refined space-time two-dimensional clutter simulation model of space-based radar is constructed which simultaneously includes the characteristics of terrain fluctuation scattering distribution, terrain occlusion and diffraction, earth-sea clutter distribution and earth rotation. Secondly, based on the efficient modeling technology of ray-tracing high-frequency electromagnetic scattering, the target characteristics in the detection scene are finely modeled, which can fully consider the changes of target characteristics under different conditions. Finally, the rationality of space-time two-dimensional echo signal is verified and analyzed by simulation cases. The echo generated by this method is closer to the real situation, and provide support for the research of space-based radar system design and clutter suppression algorithm.","PeriodicalId":247340,"journal":{"name":"2023 IEEE 3rd International Conference on Power, Electronics and Computer Applications (ICPECA)","volume":"56 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-01-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116127833","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}
Zishun Zhou, Yuxiang Liu, Qingzheng Wang, Teoh Teik Toe
{"title":"Detection of Pneumonia Based on ResNet Improved by Attention Mechanism","authors":"Zishun Zhou, Yuxiang Liu, Qingzheng Wang, Teoh Teik Toe","doi":"10.1109/ICPECA56706.2023.10076216","DOIUrl":"https://doi.org/10.1109/ICPECA56706.2023.10076216","url":null,"abstract":"In recent years, Covid-19 is one of the major health challenges facing the human population. Due to the highly infectious nature of Covid-19 and the difficulty of detecting symptoms in the early stages, it is definitely necessary to combine X-ray for the diagnosis of pneumonia. Using traditional neural networks such as VGG, ResNet, and DenseNet to diagnose pneumonia based on X-ray images faces a number of difficulties. These models have insufficient spatial information extraction capability and are prone to overfitting on the training set. The attention mechanism is a means to improve model performance by helping the model better extract channel and spatial features from the feature maps. To identify pneumonia more accurately, we combined the ResNet network and CBAM attention mechanism to design the ResNet101-cbam model with a series of data augmentation methods as well as training strategies. We used the same approach to add attention mechanisms to ResNet50, ResNet101 and ResNet152 and tested their performance. The results show that ResNet101-cbam is the best performing model overall. It achieved a recall of 0.8205, a precision of 0.822, and an accuracy of 0.8285 on the test set, while the original pretrained ResNet101 had a precision of 0.7280 and an accuracy of 0.7644. Its performance were better than the more complex model: ResNet152-cbam, a little bit, but the training speed is improved by more than 25%. More importantly, the model with the added attention mechanism effectively overcomes the effects of positive and negative sample imbalance. The ResNet101-cbam model can be used as a medical aid, which can improve diagnostic efficiency and help us better deal with large-scale pneumonia epidemics.","PeriodicalId":247340,"journal":{"name":"2023 IEEE 3rd International Conference on Power, Electronics and Computer Applications (ICPECA)","volume":"10 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-01-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122362116","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}
Xingjian Jia, Yaoting Zhao, Changbao Chu, Changlin Run, Zhimei Gan
{"title":"Application of millimeter-wave radar in giant-magnetostrictive brake by wire environment perception system","authors":"Xingjian Jia, Yaoting Zhao, Changbao Chu, Changlin Run, Zhimei Gan","doi":"10.1109/ICPECA56706.2023.10076178","DOIUrl":"https://doi.org/10.1109/ICPECA56706.2023.10076178","url":null,"abstract":"Aiming at the problem including insufficient accuracy of the giant-magnetostrictive brake by wire environment perception system in sensing target motion in complex environments and the noise of millimeter-wave radar during data collection, a Kalman filter method is proposed to predict the target distance and speed, and MATLAB simulation has verified its feasibility and effectiveness. The simulation results show that the prediction accuracy of the target through the millimeter-wave radar data can be centimeter level, which improves the perception accuracy of the environment perception system to the target, and it provides a good basis for the date fusion for millimeter-wave radar and other sensors.","PeriodicalId":247340,"journal":{"name":"2023 IEEE 3rd International Conference on Power, Electronics and Computer Applications (ICPECA)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-01-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122558137","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}
Yue Luo, Jiaxin Wu, Zhuhao Zhang, Huaju Zhao, Zhong Shu
{"title":"Design of Facial Expression Recognition Algorithm Based on CNN Model","authors":"Yue Luo, Jiaxin Wu, Zhuhao Zhang, Huaju Zhao, Zhong Shu","doi":"10.1109/ICPECA56706.2023.10075779","DOIUrl":"https://doi.org/10.1109/ICPECA56706.2023.10075779","url":null,"abstract":"This paper proposes an improved CNN model with the main process of face image preprocessing, face image feature extraction, input test sample training, acquisition of test sample features, face image feature classification, restoration of face expression images, and recognition results. In the convolution activation function, the cumulative sum operation is performed on three aspects of facial expression image pixels, the number of convolution operations, and the number of pooling operations, and a highly integrated facial expression image feature extraction is realized. It is merged with the pooling operation. In the classification loss function, two processes of convolution and pooling operations are considered, and the weight and bias updates in the convolution, pooling, and classification loss functions are included. Relevant experiments and experimental statistics show that the classification accuracy of the facial image expression feature extraction algorithm proposed in this paper is about 87%, and the recognition accuracy of the improved CNN facial expression recognition model proposed in this paper is about 88%.","PeriodicalId":247340,"journal":{"name":"2023 IEEE 3rd International Conference on Power, Electronics and Computer Applications (ICPECA)","volume":"14 3","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-01-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114124488","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 Printing Defect Recognition Method Based on Class-imbalanced Learning","authors":"Jing Li, Jie Pan, Qiqi Zhang","doi":"10.1109/ICPECA56706.2023.10075748","DOIUrl":"https://doi.org/10.1109/ICPECA56706.2023.10075748","url":null,"abstract":"Printing product is very common in people's daily life, such as newspapers, books, advertisements, product packaging and even banknotes. Because of various printing defects occurring in printing process, the quality of printing product is directly affected. During the high-speed printing, it is necessary to detect various printing defects quickly and accurately for eliminating defective printing products from qualified ones. The printing defect recognition method based on machine vision is replacing manual defect recognition in printing industry because of its automation, high efficiency and recognition accuracy. We use deep learning method to detect printing defects. The number of printing defects in different categories is often uneven. The quantity of normal samples and dirty points is significantly larger than other defect types. In this paper, a printing defect recognition method based on class-imbalanced learning is proposed. In addition, a warp-based bundled homography model is also proposed to improve the registration accuracy, which is beneficial to improve the efficiency of defect recognition. Experimental results demonstrate that the proposed method can detect printing defects quickly and effectively.","PeriodicalId":247340,"journal":{"name":"2023 IEEE 3rd International Conference on Power, Electronics and Computer Applications (ICPECA)","volume":"29 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-01-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114428673","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":"Research on Detection Algorithms of Weak Electromagnetic Spectrum Signal","authors":"Yanqin Zuo, Chong Cao, Yu Zhu","doi":"10.1109/ICPECA56706.2023.10076138","DOIUrl":"https://doi.org/10.1109/ICPECA56706.2023.10076138","url":null,"abstract":"The weak electromagnetic spectrum signal drowned in the noise is difficult to be detected and identified. To solve this problem, the frequency-domain superposition algorithm and the power-entropy algorithm are proposed respectively. Considering the actual electromagnetic spectrum signals detection scenario, three types of experimental scenarios in which the DS-BPSK signal invades the frequency bands of FM, QPSK and 16QAM signals are simulated. By comparing the advantages and disadvantages of two different algorithms, it is proved that the power-entropy algorithm is much more effective. Even there exists the strong electromagnetic spectrum signal, the weak electromagnetic spectrum signal can be easily distinguished and not be ignored.","PeriodicalId":247340,"journal":{"name":"2023 IEEE 3rd International Conference on Power, Electronics and Computer Applications (ICPECA)","volume":"55 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-01-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114568957","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":"Research on the Dynamic System Faults of Electric Vehicles","authors":"Chenxi Ma","doi":"10.1109/ICPECA56706.2023.10075926","DOIUrl":"https://doi.org/10.1109/ICPECA56706.2023.10075926","url":null,"abstract":"In electric vehicles, the dynamic system is the key to operating stably, and if there is a failure, it will inevitably reduce the safety of running the car. In order to understand the common faults of the electric vehicle dynamic system and grasp the handling methods of different faults, this paper introduces the fault types and causes of the electric vehicle dynamic system directly. After research, it is found that the causes of various types of failures have the characteristics of different failures, so it is necessary to eliminate the causes of the faults. According to the study, this paper believes that in order to prevent and effectively deal with the electric vehicle dynamic system, it is necessary to perform regular maintenance and use appropriate and effective methods to analyze and deal with the causes in order to improve the stability of the electric vehicle dynamic system and meet the basic needs of vehicle operation.","PeriodicalId":247340,"journal":{"name":"2023 IEEE 3rd International Conference on Power, Electronics and Computer Applications (ICPECA)","volume":"88 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-01-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122196921","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":"Electrical lighting design and intelligent control of a industry-education integration building through load calculation","authors":"Yu Qingmin, Chen Peikun","doi":"10.1109/ICPECA56706.2023.10075935","DOIUrl":"https://doi.org/10.1109/ICPECA56706.2023.10075935","url":null,"abstract":"This paper is the electrical design of a general industry-education integration training building - electrical lighting and anti-grounding system design, mainly including two aspects, namely the design of lighting and socket system, and the design of power supply and distribution system. Lighting includes general lighting and emergency lighting, and in the design process usually includes the selection of lighting fixtures and light sources, illuminance calculation and arrangement methods; The design of the socket system is arranged according to the needs of the project and the actual use. In this paper, radial power distribution is used to provide electrical energy, and the appropriate equipment is selected through load calculation. In order to provide reference for the design and construction of similar training buildings.","PeriodicalId":247340,"journal":{"name":"2023 IEEE 3rd International Conference on Power, Electronics and Computer Applications (ICPECA)","volume":"36 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-01-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122233233","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 Acoustic Signal in Switchgear Based on VMD Decomposition Algorithm","authors":"Yan Ying, Cao Hao, Huang Tao, Weihua Cai","doi":"10.1109/ICPECA56706.2023.10076084","DOIUrl":"https://doi.org/10.1109/ICPECA56706.2023.10076084","url":null,"abstract":"The switchgear acoustic signal collected in the field environment is usually non-stationary and nonlinear, with a complex composition, mainly composed of noise, effective sound vibration waveform and harmonic superposition. At the same time, due to the weak energy of the fault feature signal, it is often submerged by the noise, and it is difficult to find and extract the fault signal with periodic and shock characteristics. This paper presents an acoustic vibration signal analysis method based on variational mode decomposition (VMD) to decompose the raw data into narrow-band eigenmode functions to mine fault information. Practical tests show that this method works well.","PeriodicalId":247340,"journal":{"name":"2023 IEEE 3rd International Conference on Power, Electronics and Computer Applications (ICPECA)","volume":"17 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-01-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129880479","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":"Design and Implementation of the Automatic Sorting System Based on PLC","authors":"Lv Huimin","doi":"10.1109/ICPECA56706.2023.10075963","DOIUrl":"https://doi.org/10.1109/ICPECA56706.2023.10075963","url":null,"abstract":"Automatic material sorting is widely used in enterprise automatic production line, product assembly line and automated warehouse. Compared with traditional manual sorting, automatic sorting has the advantages of high efficiency, low error rate, many sorting points, unmanned industrial operation, etc. The control system of automatic sorting device is the core of the sorting device. This paper presents an automatic material sorting system based on PLC and pneumatic control, and completes the design of PLC control system and pneumatic control system. The automatic separation system is controlled by PLC of Mitsubishi FX2N series. The system is mainly composed of material feeding module, material handling module, material conveying module and separation module. The experimental results show that the system has high sorting accuracy, stable operation and meets the design requirements.","PeriodicalId":247340,"journal":{"name":"2023 IEEE 3rd International Conference on Power, Electronics and Computer Applications (ICPECA)","volume":"48 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-01-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128436266","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}