{"title":"Text-Guided Image Inpainting","authors":"Ying Gao, Qing Zhu","doi":"10.1109/ITOEC53115.2022.9734369","DOIUrl":"https://doi.org/10.1109/ITOEC53115.2022.9734369","url":null,"abstract":"Given a corrupted image, image inpainting aims to complete the image and outputs a plausible result. When we complete the missing region, we always borrow the information from a known area, which is aimless and causes unsatisfactory results. In our daily life, some other information is often used for corrupted images, such as text descriptions. Therefore, we introduce the use of text information to guide image inpainting. To fulfill this task, We introduce an inpainting model named TGNet (Text-Guided Inpainting Network). We provide a text-image gated feature fusion module to fuse text feature and image feature deeply. A mask attention module is proposed to enhance the consistency of known areas and the repaired area. Extensive quantitative and qualitative experiments on three public datasets with captions demonstrate the effectiveness of our method.","PeriodicalId":127300,"journal":{"name":"2022 IEEE 6th Information Technology and Mechatronics Engineering Conference (ITOEC)","volume":"109 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-03-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122696111","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":"Application research of IEEE Std.1459–20 10 in three-phase three-wire system","authors":"Shangshu Guan, S. Tao, Yidan Song","doi":"10.1109/ITOEC53115.2022.9734577","DOIUrl":"https://doi.org/10.1109/ITOEC53115.2022.9734577","url":null,"abstract":"At present, different kinds of power theories are relatively uniform in the definition of reactive power, which has clear physical significance, but the understanding of non-reactive power (power other than reactive power) varies considerably. On the basis of the IEEE Std.1459-2010 standard, this paper studies three-phase balance, load asymmetry, load nonlinearity, power supply distortion and asymmetry in three-phase three-wire circuits, employs this power theory to break down and calculate each power component, and designs reasonable parameters for power compensation. In the end, the simulation circuits are built by PSCAD/EMTDC to verify the accuracy of theoretical calculation and the effectiveness of compensation.","PeriodicalId":127300,"journal":{"name":"2022 IEEE 6th Information Technology and Mechatronics Engineering Conference (ITOEC)","volume":"51 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-03-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122622569","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 new integrated network management system based on SDN","authors":"Hailong Wang, Zhang Hongwei, Wenxuan Chen, Xia Cai, Yu-hua Guo, Wen Zhang","doi":"10.1109/ITOEC53115.2022.9734613","DOIUrl":"https://doi.org/10.1109/ITOEC53115.2022.9734613","url":null,"abstract":"Power communication integrated network management system plays a significant role in the planning, design and maintenance of the whole power communication network. This paper analyzes the characteristics of the current power communication network and the corresponding integrated network management system, and improves the design of the existing power communication network integrated network management according to Sdn. This network management system can be used as a supplementary system for the current power system integrated network management function, realizes the global visualization of the power communication network, and provides a strong support for the operation and maintenance of the power communication network. The test running environment is built in the laboratory to realize the mapping of physical route and logical link. The preliminary verification test of the new network management system based on openflow technology is carried out, and the key design methods and ideas of the system are given.","PeriodicalId":127300,"journal":{"name":"2022 IEEE 6th Information Technology and Mechatronics Engineering Conference (ITOEC)","volume":"11 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-03-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129528632","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 Target Recognition Method of Tunnel Lining Image Based on Deep Learning","authors":"Chengjun Li, Linhui Cai, Li Guo, Dejun Chen","doi":"10.1109/ITOEC53115.2022.9734634","DOIUrl":"https://doi.org/10.1109/ITOEC53115.2022.9734634","url":null,"abstract":"Aiming at the complexity and diversity of ground-penetrating radar-based tunnel disease target imaging, as well as the relatively complex disease image identification process, low recognition rate, and the inability to achieve end-to-end identification, this paper proposes an improved Faster-R-CNN method for tunnel lining image target identification. The method can quickly and accurately determine the location of the disease images and classify them. The effectiveness of this method is verified by taking the common disease images such as steel arch and uncompactness in tunnel lining structure as the real measurement recognition objects, which provides a new method for automatic ground-penetrating radar image interpretation.","PeriodicalId":127300,"journal":{"name":"2022 IEEE 6th Information Technology and Mechatronics Engineering Conference (ITOEC)","volume":"6 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-03-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129830287","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}
Xin Xue, Hairan Shi, Tao Jiang, Yunzhong Han, Guoping Zhi
{"title":"Design of a Low-Profile Polarization Tracking Active Phased Array Antenna for Satcom On the Move","authors":"Xin Xue, Hairan Shi, Tao Jiang, Yunzhong Han, Guoping Zhi","doi":"10.1109/ITOEC53115.2022.9734657","DOIUrl":"https://doi.org/10.1109/ITOEC53115.2022.9734657","url":null,"abstract":"Design method and key technologies of a Ku band low profile Active Phased Array Antenna (APAA) with polarization tracking for satcom on the move (SOTM) system are given. The approach presented here realizes polarization tracking and wide-angle beam tracking simultaneously comparing with traditional antennas. To be adequate for wide-angle beam scanning, the microstrip patch array antennas are presented. The choke groove is also adopted to improve the isolation between the transmitting and receiving antenna under the condition of limited size. Finally, a low profile active phased array antenna has been developed successfully. The test result shows arbitrary linear polarization and wide-angle beam tracking can be obtained from different phase setting. There is enough isolation between transmitting and receiving antennas to ensure that the performance of receiving antenna will not deteriorate.","PeriodicalId":127300,"journal":{"name":"2022 IEEE 6th Information Technology and Mechatronics Engineering Conference (ITOEC)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-03-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128695556","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 Cross-Camera Pedestrian Retrieval Study","authors":"Ya-Li Liu, Jinghua Wu","doi":"10.1109/ITOEC53115.2022.9734367","DOIUrl":"https://doi.org/10.1109/ITOEC53115.2022.9734367","url":null,"abstract":"Existing pedestrian retrieval algorithms have many problems, and we explore and optimize the algorithms. Pedestrian retrieval is the process of combining pedestrian detection and pedestrian re-identification. The existing algorithms are designed with an end-to-end framework, and we train pedestrian detection and pedestrian re-identification separately to improve the accuracy of the algorithms separately, and then do the combination during testing. In addition, global features are used to achieve advanced results rather than local features, which are slower to train. And a lightweight pedestrian detector is created, which helps the model to run and compute efficiently. Our approach is evaluated on publicly available datasets, and the results on single-domain and cross-domain scenarios demonstrate the effectiveness of our approach.","PeriodicalId":127300,"journal":{"name":"2022 IEEE 6th Information Technology and Mechatronics Engineering Conference (ITOEC)","volume":"79 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-03-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128293765","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}
Jun Wang, Fujun Qi, Guilong Lv, Chao Su, Haijuan Zhang, Wei Pang
{"title":"Static Voltage Assessment based on Electro-thermal coupling V-Q Sensitivity Analysis","authors":"Jun Wang, Fujun Qi, Guilong Lv, Chao Su, Haijuan Zhang, Wei Pang","doi":"10.1109/ITOEC53115.2022.9734608","DOIUrl":"https://doi.org/10.1109/ITOEC53115.2022.9734608","url":null,"abstract":"Although the traditional V-Q sensitivity can quickly determine the stability of the system bus voltage, its mathematical model only considers the electrical model of the line and ignores the electro-thermal coupling relationship of the line under actual conditions. Therefore, the use of traditional model calculation results as a reference for the actual bus voltage stability judgment has a large deviation. With this as a background, this paper establishes an electro-thermal coupled power flow model, which is based on the IEEE standard heat balance equation and regards the transmission line resistance as the state variable of the power flow. Then, based on the expansion of the Jacobian matrix in the improved power flow model, a V-Q sensitivity analysis method considering the electro-thermal coupling is proposed, and the calculation example is compared and analyzed with the traditional model in different seasons. The results show that the traditional model ignores the influence of the line temperature and resistance due to the electric and heat balance, which will introduce certain errors in the calculation results for different seasons.","PeriodicalId":127300,"journal":{"name":"2022 IEEE 6th Information Technology and Mechatronics Engineering Conference (ITOEC)","volume":"58 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-03-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128643084","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 High-speed Maglev Energy-saving Driving Control","authors":"Hongkai Wang","doi":"10.1109/ITOEC53115.2022.9734598","DOIUrl":"https://doi.org/10.1109/ITOEC53115.2022.9734598","url":null,"abstract":"Maglev train, as a new transportation mode, has the advantages of strong environmental adaptability, convenience and swiftness, and has a vast development prospect in the future rail transit field. The driving control strategy of the maglev train mainly focuses on obtaining the shortest running time and the lowest energy consumption. In this paper, the force of the maglev train is analyzed at first, and then, considering the ramp, line speed limit, traction, and braking force constraints, the energy-saving model of the maglev train with time constraint are established. Based on the above model, a pseudo-spectral method is designed to solve the optimization problems. First of all, we preprocess the ramp and speed data. Then we use the pseudo-spectral method to solve the model. Finally, we obtain the shortest running time driving curve, optimal energy-saving driving curve with the time constraint and optimal train running time allocation energy-saving driving curve. The simulation results show that the proposed algorithm has an obvious energy-saving effect.","PeriodicalId":127300,"journal":{"name":"2022 IEEE 6th Information Technology and Mechatronics Engineering Conference (ITOEC)","volume":"8 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-03-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129841950","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}
Huihui Song, Jianping Li, Zhiping Xia, Zongping Yang, Xiao Du
{"title":"Multimodal Sentiment Analysis Based on Pre-LN Transformer Interaction","authors":"Huihui Song, Jianping Li, Zhiping Xia, Zongping Yang, Xiao Du","doi":"10.1109/ITOEC53115.2022.9734328","DOIUrl":"https://doi.org/10.1109/ITOEC53115.2022.9734328","url":null,"abstract":"Multimodal sentiment analysis aims to extract and integrate semantic information collected from multimodal data to identify the information and emotions expressed in multimodal data. The main focus of this area of research is to develop an extraordinary fusion solution that can extract and integrate key information from a variety of patterns. In view of the problems of the existing model, such as weak parallel computing ability and insufficient remote dependence processing, this paper proposes a cross-modal contextual interaction model (CMCI-PLNT) based on Pre-LN Transformer to carry out the information interaction between language, audio and video, and uses the self-attention module to filter redundant information. Finally, the residual network was used to fuse the information and perform emotion analysis. The core of the model is directed pairwise cross-modal attention, which focuses on the interaction between multi-modal sequences at different time steps. Our model achieves 81.2% accuracy on the MOSI dataset and 81.5% accuracy on the MOSEI dataset, The experiment shows the feasibility and effectiveness of the model in this paper.","PeriodicalId":127300,"journal":{"name":"2022 IEEE 6th Information Technology and Mechatronics Engineering Conference (ITOEC)","volume":"13 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-03-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123944347","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 Target Location Algorithm Based on Millimeter Wave Radar","authors":"Wen Dong, Tianren Sun, Jiahao Tian, Jingyi Wang, Zhi-yong Song, Q. Fu","doi":"10.1109/ITOEC53115.2022.9734670","DOIUrl":"https://doi.org/10.1109/ITOEC53115.2022.9734670","url":null,"abstract":"How to find the trapped rescue workers in the fire disaster is the first problem to be solved. This paper designs the signal waveform, receives the echo data based on the AWR1642 millimeter wave radar sensor produced by TI company. The radar has high speed resolution, is prone to Across Doppler Unit (ADU) phenomenon, and the target signal-to-noise ratio and signal-to-clutter ratio are small in the fire environment, so it is difficult to realize the focus detection of the target. In addition, the radar has low angular resolution and is difficult to achieve accurate target positioning. The range and velocity of the target are estimated through signal processing processes such as Moving Target Indication (MTI), Radon-Fourier Transform (RFT) focusing and cell average constant false alarm rate (CA-CFAR) detection, and then obtains the angle information through multiple signal classification (MUSIC) algorithm processing to complete the target positioning.","PeriodicalId":127300,"journal":{"name":"2022 IEEE 6th Information Technology and Mechatronics Engineering Conference (ITOEC)","volume":"328 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-03-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123403578","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}