{"title":"Image Generation Method Based on Improved Condition GAN","authors":"Qiuzi Jin, Xin Luo, Youqun Shi, K. Kita","doi":"10.1109/ICSAI48974.2019.9010120","DOIUrl":"https://doi.org/10.1109/ICSAI48974.2019.9010120","url":null,"abstract":"The Generated Adversarial Network (GAN) is commonly used to learn to generate a wide variety of images. The Wasserstein GAN improves the stability of GAN, but there are also deficiencies that do not have controllable conditions. This paper proposes an improved GAN network model, which we call CWGAN. CWGAN achieves the goal of improving the training stability and controllability of GAN by adding condition information to WGAN generators and discriminators. The experiment results show that CWGAN improves the training stability, solves the problem of gradient disappearance, and produces images more clearly, and there is no obvious mode collapse problem.","PeriodicalId":270809,"journal":{"name":"2019 6th International Conference on Systems and Informatics (ICSAI)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122758772","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":"Intelligent Fan System Based on Big Data and Artificial Intelligence","authors":"Zhihe Yang, Mingjie Lin","doi":"10.1109/ICSAI48974.2019.9010072","DOIUrl":"https://doi.org/10.1109/ICSAI48974.2019.9010072","url":null,"abstract":"Gearbox is an important component of doubly-fed wind turbines. The maintenance cost of replacing gearbox after serious fault is very high. If the damage of gearbox can be detected as soon as possible and timely maintenance is carried out, it is of great significance to guide the operation of field personnel and realize intelligent operation. This paper presents an intelligent fan system based on large data and artificial intelligence. This system introduces the modeling method of artificial intelligence big data technology. Through the integration and processing of multi-source heterogeneous data, the intelligent decision-making of fan operation system is formed. The decision-making is made by machine rather than by human, which improves the prediction accuracy of decision-making model, reduces the false alarm rate, improves the operation efficiency of fan, and brings real economic value to fan owners.","PeriodicalId":270809,"journal":{"name":"2019 6th International Conference on Systems and Informatics (ICSAI)","volume":"17 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124123612","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":"Parameters Optimization for Catalyst Centrifugal Spray Drying Process Based on BP Neural Network and Genetic Algorithm","authors":"Yunfei Liu, Jingjing Xu, Tianyang Ye","doi":"10.1109/ICSAI48974.2019.9010174","DOIUrl":"https://doi.org/10.1109/ICSAI48974.2019.9010174","url":null,"abstract":"Reasonable and effective process parameters in the catalyst centrifugal spray drying are of significance for the quality and industrial production of the catalyst. The overall desirability of fine powder ratio and water evaporation is defined as the goal and the process parameters are optimized based on BP neural network with genetic algorithm, which obtains the better drying performance. The optimization results provide a basis for setting the process parameters of the industrial production of catalyst centrifugal spray drying and improve the quality of the catalyst product.","PeriodicalId":270809,"journal":{"name":"2019 6th International Conference on Systems and Informatics (ICSAI)","volume":"14 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125126678","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":"Dual Universes Multi-Granulation Covering Rough Sets Model","authors":"Zhijia Wang, Qinghai Wang","doi":"10.1109/ICSAI48974.2019.9010099","DOIUrl":"https://doi.org/10.1109/ICSAI48974.2019.9010099","url":null,"abstract":"The rough set of classical multi-granulation decision theory is in return for the equivalence relation on the universe. But in practical application, the equivalence relation is difficult to be realized because of the incompleteness of information system. In this paper, multi-granulation decision theory and the covering rough sets model is extended to the dual universes model, and the dual universes multi-granulation covering rough sets model is proposed. The minimal covering description is given, in addition, the definition of lower and upper approximation is constructed to deal with knowledge of multiple granularity space of distributed data. The practicability and reliability of this model are proved by introducing the uncertainty measurement of rough entropy and information entropy.","PeriodicalId":270809,"journal":{"name":"2019 6th International Conference on Systems and Informatics (ICSAI)","volume":"29 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126436968","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 Pre-synchronization Method for Grid-connection Based on Virtual Synchronous Generator","authors":"Wenqiao Tang, Jun Liu","doi":"10.1109/ICSAI48974.2019.9010249","DOIUrl":"https://doi.org/10.1109/ICSAI48974.2019.9010249","url":null,"abstract":"The inverter is simulated as a synchronous generator that is friendly to large power grid, which can improve the absorption capacity of distributed power supply. However, when virtual synchronous generator (VSG) is connected to the grid, there will be a large current shock. Therefore, this paper proposes an improved pre-synchronization control strategy without phase-locked loop to realize smooth switching between VSG off-grid and grid-connected. Firstly, the principle of virtual synchronous machine is introduced. Finally, through simulation analysis, it is verified that the proposed pre-synchronization control method can realize the seamless switching of VSG between different modes, and it is simpler than the traditional pre-synchronization control algorithm, which verifies the effectiveness of the proposed control strategy.","PeriodicalId":270809,"journal":{"name":"2019 6th International Conference on Systems and Informatics (ICSAI)","volume":"25 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129802281","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":"Algorithm Research Based on Labels of Scenic Spots","authors":"Jinlong Chen, Junwei Hu, Minghao Yang","doi":"10.1109/ICSAI48974.2019.9010408","DOIUrl":"https://doi.org/10.1109/ICSAI48974.2019.9010408","url":null,"abstract":"In collaborative filtering recommendation algorithm based on user's social relations, sometimes the ratings of target user for the target items can't be predicted. What's more, in traditional item-based collaborative filtering, user ratings for different types of items are not comparable. To handle this problem, two new algorithms of collaborative filtering recommendation were proposed, in which the labels of scenic spot's type were introduced to compute the similarity between two scenic spots. The experimental results on the data set of scenic spot's ratings show that, the accuracy and coverage of collaborative filtering recommendation algorithm based on user's social relations and item labels are improved by 10% and 4% respectively compared with the collaborative filtering recommendation algorithm based on user's social relations, the accuracy of collaborative filtering recommendation algorithm based on items and item labels are improved by 15% compared with the collaborative filtering recommendation algorithm based on items, this indicates that introducing the labels of scenic spot's type can make the computation of the similarity between two scenic spots more accurate.","PeriodicalId":270809,"journal":{"name":"2019 6th International Conference on Systems and Informatics (ICSAI)","volume":"6 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129821871","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":"Hyperspectral Face Recognition Using Block based Convolution Neural Network and AdaBoost Band Selection","authors":"Zhihua Xie, Yi Li, Jieyi Niu, Xinhe Yu, Ling Shi","doi":"10.1109/ICSAI48974.2019.9010511","DOIUrl":"https://doi.org/10.1109/ICSAI48974.2019.9010511","url":null,"abstract":"Hyperspectral imaging, adding discrimination information along spectral dimension, offers a new chance for robust face recognition. To improve the effectiveness of facial feature represented by hyperspectral face data, we proposed a block-based hyperspectral face recognition method using bands selection and convolution neural network (CNN). Firstly, a small convolution neural network is trained to capture discriminative visual information for different blocks in face images. Secondly, an improved AdaBoost algorithm (AdaBoost.MS) is introduced to choose different optimal bands for different blocks. Then, each block label can be determined by the ensemble learning classification. Finally, the recognition result can be gotten by the majority voting principle. The experiment results based on PolyU-HSFD database show that block-level based bands selection can capture the more discriminative spectral features than the method based on image level. The proposed method outperforms the existing state-of-the-art methods.","PeriodicalId":270809,"journal":{"name":"2019 6th International Conference on Systems and Informatics (ICSAI)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130119656","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 Multiple-Phase-Sectionalized- Modulation Based Frequency Shift Jamming Method For Pulse Compression Radar","authors":"Jiawei Jiang, Hongyan Wang, Shuya Kong","doi":"10.1109/ICSAI48974.2019.9010218","DOIUrl":"https://doi.org/10.1109/ICSAI48974.2019.9010218","url":null,"abstract":"In order to expand the jamming range of frequency shift jamming, this paper presents a multiple-phase- sectionalized-modulation (MPSM) based frequency shift jamming method for pulse compression radar. Based on the principle of frequency shift modulation, the jamming position can be controlled. Then, the jamming signal is divided into multiple sections, and modulated with different phases to expand the jamming range, so as to generate the local barrage jamming effect against the pulse compression radar. Theoretical analysis and simulation results show that this method can obtain partial process gain to reduce the need for jamming power effectively, generate local barrage jamming effect with controllable position and jamming range by reasonably choosing jamming parameters.","PeriodicalId":270809,"journal":{"name":"2019 6th International Conference on Systems and Informatics (ICSAI)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129358187","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}
Dexiong Zhang, Yichao Cao, Guangming Zhang, Xiaobo Lu
{"title":"An Attention Convolutional Neural Network for Forest Fire Smoke Recognition","authors":"Dexiong Zhang, Yichao Cao, Guangming Zhang, Xiaobo Lu","doi":"10.1109/ICSAI48974.2019.9010577","DOIUrl":"https://doi.org/10.1109/ICSAI48974.2019.9010577","url":null,"abstract":"In order to find forest fire in time and accurately, the identification of forest fire smoke based on computer vision has become an important research direction. In this paper, a convolutional neural network model based on the attention mechanism is designed for forest fire smoke recognition. By focusing on the regions with obvious discrimination in the image, more precise local features are extracted for fire smoke identification with the auxiliary of backbone network. The performance of network on the unbalanced forest fire dataset is improved by optimizing the cross-entropy loss function with weights. The experimental results show that attention convolutional neural network improves the accuracy of the model which reached 89.3% while reducing false positives and false negatives.","PeriodicalId":270809,"journal":{"name":"2019 6th International Conference on Systems and Informatics (ICSAI)","volume":"11 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128248373","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":"OPC UA PubSub Implementation and Configuration","authors":"Zepeng Liu, Patrick Bellot","doi":"10.1109/ICSAI48974.2019.9010445","DOIUrl":"https://doi.org/10.1109/ICSAI48974.2019.9010445","url":null,"abstract":"OPC UA (Open Platform Communication Unified Architecture) is one of the most widely used specifications for industrial system communication. In the context of increasingly complex technologies of the Industrial Internet of Things (IIoT) and requirements for interoperability of the Industrie 4.0, the specification is extended by adding a new communication architecture named PubSub to provide asynchronous information exchange capability. This paper introduces our OPC UA PubSub and MQTT based configuration tool, and a PubSub implementation that can be easily integrated into other C/C++ OPC UA projects.","PeriodicalId":270809,"journal":{"name":"2019 6th International Conference on Systems and Informatics (ICSAI)","volume":"10 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128430367","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}