{"title":"End-to-end Spatiotemporal Attention Model for Autonomous Driving","authors":"Ruijie Zhao, Yanxin Zhang, Zhiqing Huang, Chenkun Yin","doi":"10.1109/ITNEC48623.2020.9085185","DOIUrl":"https://doi.org/10.1109/ITNEC48623.2020.9085185","url":null,"abstract":"In recent years, end-to-end autonomous driving has become an emerging research direction in the field of autonomous driving. This method attempts to map the road images collected by the vehicle camera to the decision control of the vehicle. We propose a spatiotemporal neural network model with a visual attention mechanism to predict vehicle decision control in an end-to-end manner. The model is composed of CNN and LSTM and can extract temporal and spatial features from road image sequences. The visual attention mechanism in the model helps the model to focus on important areas in the image. We evaluated the model in the open racing car simulator TORCS, and the experiments showed that our model is better at predicting driving decisions than the simple CNN model. In addition, the visual attention mechanism in the model is conducive to improving the performance of the end-to-end autonomous driving model.","PeriodicalId":235524,"journal":{"name":"2020 IEEE 4th Information Technology, Networking, Electronic and Automation Control Conference (ITNEC)","volume":"14 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134298702","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 High-performance Web Attack Detection Method based on CNN-GRU Model","authors":"Qiangqiang Niu, Xiaoyong Li","doi":"10.1109/ITNEC48623.2020.9085028","DOIUrl":"https://doi.org/10.1109/ITNEC48623.2020.9085028","url":null,"abstract":"WEB attack detection is an important part of WEB security. This paper proposes a web attack detection method based on Convolutional Neural Network (CNN) combined with Gated Recurrent Unit (GRU). In order to improve the detection performance, we extract eight statistical features with good classification effect to augment the original data. In addition, we also pre-trained the word embedding matrix using the word2Vec model, then obtained the input of the CNN-GRU model and classified the final results. The experimental results show that the accuracy of the method in the HTTP CSIC 2010 dataset is 99.00%, the recall rate is 97.74%, the F1 value is 98.77% and the precision is 99.82%. Compared with traditional machine learning methods, this method proposed in this paper has better performance.","PeriodicalId":235524,"journal":{"name":"2020 IEEE 4th Information Technology, Networking, Electronic and Automation Control Conference (ITNEC)","volume":"9 6","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131727683","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}
Z. Dong, Shiyun Wang, Jie Ren, Qingwen Jia, Lu Zhang, Dawei Jin, Jiiayi Ma
{"title":"An Ecological Destruction Evaluation Model in Dike Interference Area Based on Triangular Fuzzy Number","authors":"Z. Dong, Shiyun Wang, Jie Ren, Qingwen Jia, Lu Zhang, Dawei Jin, Jiiayi Ma","doi":"10.1109/ITNEC48623.2020.9085158","DOIUrl":"https://doi.org/10.1109/ITNEC48623.2020.9085158","url":null,"abstract":"Dike engineering is the most effective method for flood prevention. Considering the ecological problems brought by dike construction, it is of great significance to establish an ecological destruction evaluation model in the dike interference area. To solve the uncertainty of the ecological destruction evaluation in dike interference area, triangular fuzzy numbers are introduced into the set pair analysis, so as to obtain the ecological health evaluation level and ecological destruction degree. The application in Amur River validates the validity of the model. This model can provide basis for ecological restoration and dike engineering management.","PeriodicalId":235524,"journal":{"name":"2020 IEEE 4th Information Technology, Networking, Electronic and Automation Control Conference (ITNEC)","volume":"27 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131806104","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 of Monte Carlo Real Option in the Construction of Distributed Power Flow Controller","authors":"Zijue Xie, Qian Yu","doi":"10.1109/ITNEC48623.2020.9084680","DOIUrl":"https://doi.org/10.1109/ITNEC48623.2020.9084680","url":null,"abstract":"Uncertainty in electricity market puts forward high requirements for investors to make efficient and timely investment. In this paper, the generation model and load model in uncertain power market is constructed. Meanwhile, the generation and transmission investment cost model, which considering the installed capacity of distributed power flow controllers, is constructed. And a mathematical description of the benefits of the distributed power flow controller capacity is proposed. The real option method of Monte Carlo is applied to distributed power flow controller investments. Then, the investment model based on Monte Carlo is proposed, and the corresponding option value calculation process is given in detail. And the correctness and effectiveness of the proposed method are analyzed and compared by case study","PeriodicalId":235524,"journal":{"name":"2020 IEEE 4th Information Technology, Networking, Electronic and Automation Control Conference (ITNEC)","volume":"41 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132602854","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":"Multi domain fusion feature extraction and classification of ECG based on PCA-ICA","authors":"Ling Zhao, Juan Li, Huilin Ren","doi":"10.1109/ITNEC48623.2020.9084658","DOIUrl":"https://doi.org/10.1109/ITNEC48623.2020.9084658","url":null,"abstract":"With the rapid development of social economy and information technology, human physiological characteristics such as fingerprints, face, palm print, iris, retina, etc. have been widely used in the field of commercial biometrics. In recent years, the dynamic physiological characteristics of human body, such as ECG, heart sound and voice, have been proved to be applicable to biometrics. This paper mainly studies the feature extraction and classification of ECG signals. First, the ECG signal is periodically segmented to obtain the time-domain feature matrix, and the periodic signal is wavelet-transformed to obtain the frequency-domain feature matrix. Then PCA-ICA is used to perform latitude reduction on the feature matrix. Finally, the parameters of the fuzzy decision tree for modeling are intelligently set by the PSO algorithm. And experimental verification on the MIT-BIH standard ECG database.","PeriodicalId":235524,"journal":{"name":"2020 IEEE 4th Information Technology, Networking, Electronic and Automation Control Conference (ITNEC)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130807912","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":"Protective Effect of Dual-wave and Three-wave Guardrail on Coach Collision","authors":"Wang Jinlun, Ma Zhengwei","doi":"10.1109/ITNEC48623.2020.9085033","DOIUrl":"https://doi.org/10.1109/ITNEC48623.2020.9085033","url":null,"abstract":"In order to study the coach-guardrail collision process, finite element models of a large coach, Q235 dual-wave and three-wave beam guardrails normally utilized on highway were established respectively. Dyna solver was used to simulate the dynamic response process with coach speed 80 km/h and collision angle 20°. The results show: 1) The difference of dual-wave and three-wave guardrails' protective effect on coach collision is obvious; the internal energy absorbed by three-wave beam guardrail is 25.5% higher than the dual-wave guardrail. Therefore, the lost control of the coach can be corrected to normal lane more quickly. Whereas, the protective effect of dual-wave guardrail on the coach is poor, the coach will across the guardrail eventually, which may lead to the occurrence of serious accident. 2) The passenger door and the right side of fuel tank generate quite serious deformation, but will not invade the occupant's survival space. 3) The guardrail absorbs more than 50% of the vehicle initial kinetic energy in collision, which can effectively decrease the impact force transmitted to the occupants and reduce the severity of road accidents.","PeriodicalId":235524,"journal":{"name":"2020 IEEE 4th Information Technology, Networking, Electronic and Automation Control Conference (ITNEC)","volume":"54 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130922674","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":"Event - Based Quadripartite Representation of The Power Operation Text","authors":"Yanyan Xu, Yinan Wu, Peng Peng, Yi Zhang, Jianli Song, Heming Zhang","doi":"10.1109/ITNEC48623.2020.9084761","DOIUrl":"https://doi.org/10.1109/ITNEC48623.2020.9084761","url":null,"abstract":"The growing maturity of the Power Grid industry and the continuous progress of information technology make big data mining in the Power Grid industry possible. There is no standardized requirement for the description of operation and maintenance data in the Power Grid industry, resulting in a large amount of unstructured text data. Aiming at solving this problem, this paper analyzes the characteristics of the unstructured text data and addresses the importance of text framework. Then, the event representation framework and event slot are defined, and the event elements are extracted using the methods of part-of-speech segmentation, semantic dependency analysis and dependency syntactic analysis in natural language processing(NLP). Finally, the event quaternion construction method is given. In this paper, the feature points of operation and maintenance data are found and summarized as ‘two events and four parts'. The event slots and event quaternions are defined to successfully structure the unstructured text. It provides the possibility for operation and maintenance data to be applied to question and answer system, intelligent order distribution, spare parts estimation.","PeriodicalId":235524,"journal":{"name":"2020 IEEE 4th Information Technology, Networking, Electronic and Automation Control Conference (ITNEC)","volume":"27 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132872205","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-juan Huang, Erbo Shang, Jiande Xue, Hongwen Ding, Panpan Li
{"title":"A Multi-feature Fusion-based Deep Learning for Insulator Image Identification and Fault Detection","authors":"Xin-juan Huang, Erbo Shang, Jiande Xue, Hongwen Ding, Panpan Li","doi":"10.1109/ITNEC48623.2020.9085037","DOIUrl":"https://doi.org/10.1109/ITNEC48623.2020.9085037","url":null,"abstract":"Insulators are used as faulty multiple components in transmission lines. Problems such as contamination, cracks and damage will seriously affect the normal operation of transmission lines. Therefore, it is necessary to perform Insulator Image Identification and Fault Detection on the insulator. The traditional method is always affected by the complex background and multi-size of the massive aerial image, causing the image segmentation is difficult, the model calculation is complex, and the fault detection type is single. This paper proposes to combine the insulator multi-fault target detection algorithm (Fast R-CNN) and the deep learning to automatically learn the advanced features of the insulator image of multiple different surface faults, adding the traditional low-level visual features (color feature and texture feature) to more fully extract the effective features of the image, thus improving the accuracy of the recognition. In this paper, the model is trained by the multi-type insulator aerial image, such as normal, dropped, damaged, contamination, cracked and noisy. The multi-class neural network is used to classify the surface fault types of insulators in the end. The results show that the method can detect multiple-faults of Insulator image simultaneously, which improves the accuracy of insulator fault identification.","PeriodicalId":235524,"journal":{"name":"2020 IEEE 4th Information Technology, Networking, Electronic and Automation Control Conference (ITNEC)","volume":"2 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132688553","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":"Single Image Blind Deblurring with Deep Recursive Networks","authors":"Yeyun Wu, Junsheng Wang, Xiaofeng Zhang","doi":"10.1109/ITNEC48623.2020.9084960","DOIUrl":"https://doi.org/10.1109/ITNEC48623.2020.9084960","url":null,"abstract":"Single image deblurring aims to retore the latent sharp images from the corresponding blurred ones, which is a highly ill-posed problem. In this paper, we present a deep recursive network based on generatetive adversarial networks (GANs) that restores sharp images in an end-to-end manner where blur is caused by various sources, our recursive neural network can greatly reduce the computation and complexity of the model. Then we use the least square discriminator to prevent the gradient from disappearing and make the training process more stable. We also add an adversarial loss to make the generated images look more realistic and a perceptual loss to generated better image. Experimental results have shown that our proposed method produces better performance and faster time.","PeriodicalId":235524,"journal":{"name":"2020 IEEE 4th Information Technology, Networking, Electronic and Automation Control Conference (ITNEC)","volume":"33 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133217412","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":"Receiving Technology of Multi-target TT&C Signals Using The Unique PRN Code","authors":"Wenwen Si, H. Huan","doi":"10.1109/ITNEC48623.2020.9084835","DOIUrl":"https://doi.org/10.1109/ITNEC48623.2020.9084835","url":null,"abstract":"Low earth orbit (LEO) satellites have broad application prospects in the 5G / 6G communication era due to their high coverage. From the simulation of a constellation of 2000 LEO satellites, the minimum mean value of passing through the same antenna in one minute is more than 60, which far exceeds the monitoring capabilities of telemetry, track and command (TT&C) stations. Code Division Multiple Access (CDMA) technology wastes a lot of hardware resources, and Frequency Division Multiple Access (FDMA) technology needs frequency band resources, which are not applicable to this scenario. In this paper, we analyze the theoretical equal Eb/N0 of multiple access interference. According to the frequency information of the orbit of LEO satellite, and the characteristics of burst mode and large time slot interval of TT&C signals, we design a scheme of parallel access of multiple signals by using the unique pseudorandom (PRN) code. Under the existing conditions, this solution greatly improves the monitoring capability of the ground station and reduces the hardware resource consumption of the ground station. We analyze access capabilities based on actual application scenarios. Simulation results show that the scheme can save 80% of hardware resources under the same monitoring capability.","PeriodicalId":235524,"journal":{"name":"2020 IEEE 4th Information Technology, Networking, Electronic and Automation Control Conference (ITNEC)","volume":"2 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131410781","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}