{"title":"Study on Fast Human Activity Recognition Based on Optimized Feature Selection","authors":"Hanyuan Xu, Zhibin Huang, Jue Wang, Zilu Kang","doi":"10.1109/DCABES.2017.31","DOIUrl":"https://doi.org/10.1109/DCABES.2017.31","url":null,"abstract":"Sensor-based human activity recognition has attracted much scholarly attention due to its merit of wide applicability. However, because of such hardware limitations as battery capacity and computing power, most current generation of wearable devices cannot yet benefit from those activity recognition methods based on deep learning theory and high dimension features since implementing these methods are time-consuming and need a relatively large amount of calculation. A solution, therefore, is proposed for this situation, which aims to reduce computational complexity by reducing the feature dimension through analyzing the linear correlation between the features. Based on the support vector machine model of single-layer fully connected network, the training and recognition time are significantly reduced while the recognition accuracy is still ensured. The experiment is based on the public dataset in the UCI Machine Learning Repository, and it uses Caffe, a deep learning framework, to structure the support vector machine model. In the experiment, when the feature dimension is reduced from 561 to 130, the training time can be reduced by 70% while the recognition accuracy is kept at a promising 91%.","PeriodicalId":446641,"journal":{"name":"2017 16th International Symposium on Distributed Computing and Applications to Business, Engineering and Science (DCABES)","volume":"444 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116187478","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":"The Design Model of Freeway Toll Collection","authors":"Jinwei Chang, Kuntao Lai, Baizheng Wang","doi":"10.1109/DCABES.2017.49","DOIUrl":"https://doi.org/10.1109/DCABES.2017.49","url":null,"abstract":"The congestion of toll plaza is an urgent problem in traffic. According to the theory of cellular automata with the consideration of the factors, such as safety precaution and design cost, an asymmetric design model of toll plaza confluence is established, and this model simulates the running of the vehicle at the toll station as well as analyzes the relationships between the vehicle flow, vehicle velocity and traffic density. The result demonstrates that the model can effectively improve the vehicle congestion at the toll station.","PeriodicalId":446641,"journal":{"name":"2017 16th International Symposium on Distributed Computing and Applications to Business, Engineering and Science (DCABES)","volume":"11 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128470715","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 Friction Coefficient Principal Component Algorithm of Water Lubricated Bearing Composite Material","authors":"Guo Panpan, Zhang Shesheng","doi":"10.1109/DCABES.2017.60","DOIUrl":"https://doi.org/10.1109/DCABES.2017.60","url":null,"abstract":"The statistical analysis algorithm of the mixed Nitrile Butadiene Rubber (NBR) bearing (compound bearing) is established based on experimental results measured. The analysis formula of the Nitrile Butadiene Rubber data is derived. According to the experimental results, the main components of the friction coefficient are calculated. The results show that the friction of compound bearing is better than the one of ordinary bearing.","PeriodicalId":446641,"journal":{"name":"2017 16th International Symposium on Distributed Computing and Applications to Business, Engineering and Science (DCABES)","volume":"96 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131404920","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":"Surrogate-Based Multidisciplinary Design Optimization of an Autonomous Underwater Vehicle Hull","authors":"Xu Chen, Peng Wang, Daiyu Zhang","doi":"10.1109/DCABES.2017.48","DOIUrl":"https://doi.org/10.1109/DCABES.2017.48","url":null,"abstract":"This paper performed multidisciplinary design optimization (MDO) of an AUV hull to minimize the energy consumption for sailing. The hull is decomposed into two disciplines and a multidisciplinary optimization problem is built. Multidisciplinary design feasible (MDF) architecture is adopted for optimization. A CFD-based analysis framework is proposed for resistance calculation of sample points in the hydrodynamics discipline and then a Kriging surrogate model is constructed. The optimal design of AUV hull is obtained and the computational cost is quite low with few high-fidelity CFD simulations.","PeriodicalId":446641,"journal":{"name":"2017 16th International Symposium on Distributed Computing and Applications to Business, Engineering and Science (DCABES)","volume":"69 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123651752","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":"Impact and Challenges of Using of Virtual Reality & Artificial Intelligence in Businesses","authors":"J. Kiruthika, S. Khaddaj","doi":"10.1109/DCABES.2017.43","DOIUrl":"https://doi.org/10.1109/DCABES.2017.43","url":null,"abstract":"Virtual Reality (VR) is an emerging technology and is disrupting various parts of the businesses. Combining them with Artificial Intelligence (AI) creates a new dimension to the business and affects crucial decisions for the future continuation of the business. AI's role is more pronounced than the VR aspects as not all the business needs VR but need AI. Determining the areas where VR/AI can impact the business is one of the issues stake holders are interested in. As it is new, the integration of VR and AI opens new possibilities and will provide new range of experiences. Thus, this paper focuses on addressing few of those issues and considers a case study with the need for incorporating recent developments and the challenges that need to be addressed.","PeriodicalId":446641,"journal":{"name":"2017 16th International Symposium on Distributed Computing and Applications to Business, Engineering and Science (DCABES)","volume":"141 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122910085","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":"Mooring System Design Optimization Model","authors":"Zhong Qin, Kuntao Lai, Qiuqun Zheng","doi":"10.1109/DCABES.2017.52","DOIUrl":"https://doi.org/10.1109/DCABES.2017.52","url":null,"abstract":"The design of mooring system is an important research project around the ship design. On the basis of the theory of statics and Pareto optimization, establish anchor static analysis model, Pareto optimization model and double objective optimization model in view of extreme condition, and derive the expression of critical wind speed. By adjusting the weight ball, anchor chain type and length, calculate the draft depth and swimming area of the buoy and the optimal value of the tilt angle of steel drum. The calculation results of living example show that the mooring system design optimization model established in this paper has practical applications.","PeriodicalId":446641,"journal":{"name":"2017 16th International Symposium on Distributed Computing and Applications to Business, Engineering and Science (DCABES)","volume":"27 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125911144","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 Forecast of Shared Bicycle Rental Demand Based on Spark Machine Learning Framework","authors":"Zilu Kang, Yuting Zuo, Zhibin Huang, Feng Zhou, Penghui Chen","doi":"10.1109/DCABES.2017.55","DOIUrl":"https://doi.org/10.1109/DCABES.2017.55","url":null,"abstract":"In recent years, the shared bicycle project has developed rapidly. In use of shared bicycles, a great deal of user riding information is recorded. How to extract effective knowledge from these vast amounts of information, how to use this knowledge to improve the shared bicycle system, and how to improve the user experience, are problems to solve. Citi Bike is selected as the research target. Data on Citi Bike’s user historical behavior, weather information, and holiday information are collected from three different sources, and converted into appropriate formats for model training. Spark MLlib is used to construct three different predictive models, advantages and disadvantages of different forecasting models are compared. Some techniques are used to enhance the accuracy of random forests model. The experimental results show that the root mean square error RMSE of the final model is reduced from 305.458 to 243.346.","PeriodicalId":446641,"journal":{"name":"2017 16th International Symposium on Distributed Computing and Applications to Business, Engineering and Science (DCABES)","volume":"32 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124456209","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 Distributed Storage Technology for Financial Management and Control System in Electric Power System","authors":"Yang Yang, YangXiao Peng, G. Feng, Limin Tian","doi":"10.1109/DCABES.2017.34","DOIUrl":"https://doi.org/10.1109/DCABES.2017.34","url":null,"abstract":"Distributed storage technology adopts an extensible system structure, shares storage load by many storage servers, locates stored information through location servers. Compared with a previous framework that financial management and control system of electric power companies adopted centralized storage servers to store all the data, storage servers are no longer bottleneck of information system performance. The servers not only improve reliability, availability and access efficiency of system, but also are apt to extend.","PeriodicalId":446641,"journal":{"name":"2017 16th International Symposium on Distributed Computing and Applications to Business, Engineering and Science (DCABES)","volume":"70 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123107942","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":"An Algorithm of Functional Gradient Thermal Barrier Coating Material Running on Parallel Computing","authors":"Guo Panpan","doi":"10.1109/DCABES.2017.58","DOIUrl":"https://doi.org/10.1109/DCABES.2017.58","url":null,"abstract":"Based on efficient computation of parallel computer, a parallel algorithm is found for optimization theory of three-dimensional ceramic/metal functionally gradient thermal barrier coating material. The numerical methods of optimization design of inverse heat transfer problems are given. The heat conduction coefficient is given.","PeriodicalId":446641,"journal":{"name":"2017 16th International Symposium on Distributed Computing and Applications to Business, Engineering and Science (DCABES)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115801276","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 Parallel XDraw Algorithm Based on Triangle Region Division","authors":"Yanan Li, W. Dou, Yanli Wang","doi":"10.1109/DCABES.2017.16","DOIUrl":"https://doi.org/10.1109/DCABES.2017.16","url":null,"abstract":"Terrain viewshed analysis is the basis of studying on the terrain applications such as observation point siting and shortest path planning. With the rapid development of digital photogrammetry and remote sensing, at the time of getting large scale terrain data, it also puts forward higher requirements for the efficiency and method of the viewshed calculation. In this paper, a parallel XDraw viewshed analysis algorithm is proposed on the process and level. The algorithm presents a fine-grained data scheduling strategy between different layers. Firstly, it divides DEM terrain data into a lot of triangular regions. Then, the algorithm schedules the data with a triangular region in row or column as a thread and calculates the visibility of each grid unit on a row or column. Experimental results show that the proposed method can greatly improve the computational efficiency comparing with other existing methods.","PeriodicalId":446641,"journal":{"name":"2017 16th International Symposium on Distributed Computing and Applications to Business, Engineering and Science (DCABES)","volume":"34 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129801225","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}