Proceedings of the 10th International Conference on Computer Modeling and Simulation最新文献

{"title":"Research on Defect Detection Technology of Trusted Behavior Decision Tree Based on Intelligent Data Semantic Analysis of Massive Data","authors":"Yidan Ren, Zhengzhou Zhu, Xiangzhou Chen, Huixia Ding, Geng Zhang","doi":"10.1145/3177457.3191709","DOIUrl":"https://doi.org/10.1145/3177457.3191709","url":null,"abstract":"With the rapid development of information technology, software systems' scales and complexity are showing a trend of expansion. The users' needs for the software security, software security reliability and software stability are growing increasingly. At present, the industry has applied machine learning methods to the fields of defect detection to repair and improve software defects through the massive data intelligent semantic analysis or code scanning. The model in machine learning is faced with big difficulty of model building, understanding, and the poor visualization in the field of traditional software defect detection. In view of the above problems, we present a point of view that intelligent semantic analysis technology based on massive data, and using the trusted behavior decision tree model to analyze the soft behavior by layered detection technology. At the same time, it is equipped related test environment to compare the tested software. The result shows that the defect detection technology based on intelligent semantic analysis of massive data is superior to other techniques at the cost of building time and error reported ratio.","PeriodicalId":297531,"journal":{"name":"Proceedings of the 10th International Conference on Computer Modeling and Simulation","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-01-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129251517","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":"Film Cooling Performance on the Trailing Edge Cutback of Turbine Blade with Various Slot Inner Angles","authors":"Mingfeng Chen, Changming Ling, Yuwen Zhang","doi":"10.1145/3177457.3191706","DOIUrl":"https://doi.org/10.1145/3177457.3191706","url":null,"abstract":"In order to study the impact of the slot inner angle on the film cooling performance of the trailing edge cutback for turbine blade, physical model and the three-dimensional mathematical model were established. The temperature distribution on the pressure side close to the wall was obtained through numerical simulation method, and the adiabatic temperature difference ratio and actual temperature difference ratio on the trailing edge cutback with various slot inner angles were analyzed. The results showed that, as slot inner angle increases, the average adiabatic temperature difference ratio on the trailing edge cutback and the effect of thermal insulation of gas film are increased. The impact of actual temperature difference ratio on the trailing edge cutback suffers slot inner angle is small, and it is conducive to lower the wall temperature of trailing edge when reduces the slot inner angle. For the study of film cooling performance on the trailing edge cutback of turbine blade, in addition to evaluate the adiabatic temperature difference ratio, it should also assess the actual temperature difference ratio.","PeriodicalId":297531,"journal":{"name":"Proceedings of the 10th International Conference on Computer Modeling and Simulation","volume":"58 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-01-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125485537","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":"Comparison of the LMS, NLMS, RLS, and QR-RLS algorithms for vehicle noise suppression","authors":"R. Martínek, R. Kahankova, J. Nedoma, M. Fajkus, M. Skacel","doi":"10.1145/3177457.3177502","DOIUrl":"https://doi.org/10.1145/3177457.3177502","url":null,"abstract":"The paper deals with the speech processing and adaptive filtration. For the analysis we used application implemented in both online and offline mode in LabVIEW. The experiments included comparison of the noise caused by electric car and diesel car which was measured and analyzed by means of Microphones NI 9234 and our application. We tested four different adaptive filters to cancel the noise and compared their efficiency. The criterion for comparing the efficiency of individual algorithms is primarily to increase the global signal to noise ratio (GSNR).","PeriodicalId":297531,"journal":{"name":"Proceedings of the 10th International Conference on Computer Modeling and Simulation","volume":"14 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-01-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121704586","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":"Improving Efficiency of TV PCB Assembly Line Using a Discrete Event Simulation Approach: A Case Study","authors":"Mohamed Abdelkhak, S. Salama, A. Eltawil","doi":"10.1145/3177457.3177495","DOIUrl":"https://doi.org/10.1145/3177457.3177495","url":null,"abstract":"In this paper, discrete event simulation was utilized to gain more insight into the behavior of a Television Printed Circuit Board (TV PCB) assembly line in one of the leading companies in the Middle East and Africa. The simulation output shows an imbalance in workload between workstations that hinder any opportunity for improvement. Therefore, many scenarios were proposed for rearranging the resources for the sake of eliminating bottlenecks, and increasing resources utilization by transferring technicians from idle to busy workstations. The proposed configurations have proven their superiority in significantly increasing the throughput and improving workload balance throughout the line. Finally, a cost analysis was carried out to assess the return on investment of each scenario separately in order to elaborate the credibility of these proposals.","PeriodicalId":297531,"journal":{"name":"Proceedings of the 10th International Conference on Computer Modeling and Simulation","volume":"35 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-01-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114280672","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 Computation Modification for Multi-layered Neural Network Using Extended Kalman Filter","authors":"Kyungsup Kim, Hui-Joon Kim, Yu-Jae Won","doi":"10.1145/3177457.3177463","DOIUrl":"https://doi.org/10.1145/3177457.3177463","url":null,"abstract":"A lot of learning algorithms for deep layered network are sincerely suffered from complex computation and slow convergence because of a very large number of free parameters. We need to develop an efficient algorithm for deep neural network. The Kalman filter concept can be applied to parameter estimation of neural network to improve computation performance. The algorithms based extended Kalman filter has a serious drawback in its computational complexity. We discuss how a fast algorithm should be developed for reduction in computation time.","PeriodicalId":297531,"journal":{"name":"Proceedings of the 10th International Conference on Computer Modeling and Simulation","volume":"12 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-01-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128064456","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":"Prediction of Business Process Outcome based on Historical Log","authors":"Qianlan Liu, Budan Wu","doi":"10.1145/3177457.3177465","DOIUrl":"https://doi.org/10.1145/3177457.3177465","url":null,"abstract":"With the development of data mining and machine learning, we can get much useful information from historical data. For a business process system, it maintains large amount of process execution data, especially records of events corresponding to the execution of activities, which can also be called event log. Predictive business process monitoring methods exploit logs of completed cases of a process in order to make predictions and recommendation about current running cases. This paper proposes an improved approach for process outcome prediction and next activity recommendation. It estimates the accuracy that a given goal will be fulfilled upon completion of a current running process case through three different methods. Each method includes both clustering phase and classification phase. However, different levels of historical data (business level and control flow level) in event log are used, and the size of data and number of features also differs. We show our improved approach to deal with historical log, encode each feature vector, train predictive model and how to use trained models for predicting the outcome of current case and recommending the next event. Finally, through a series of experiment, we compare three different method and existing approach.","PeriodicalId":297531,"journal":{"name":"Proceedings of the 10th International Conference on Computer Modeling and Simulation","volume":"688 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-01-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131954441","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":"Simulation model for analysis and management of the no-show in outpatient clinic","authors":"A. Pepino, Ersilia Vallefuoco, P. Cuccaro, G. D'Onofrio","doi":"10.1145/3177457.3177473","DOIUrl":"https://doi.org/10.1145/3177457.3177473","url":null,"abstract":"In outpatient management, the lead-time is a critical issue due to its important negative effect on healthcare quality perception. In particular, it generates the phenomenon of \"no-show\": when patients do not attend their scheduled appointments. In this study, we analyze the process of outpatient booking and its critical issues; in particular, we propose a simulation model to evaluate some different approaches. From our results, the lists cleaning can be considered a good tool to manage and reduce the no-show.","PeriodicalId":297531,"journal":{"name":"Proceedings of the 10th International Conference on Computer Modeling and Simulation","volume":"12 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-01-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133375244","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 Sensor Node Lossless Compression Algorithm based on Linear Fitting Residuals Coding","authors":"Xuejun Ren, Zhongyuan Ren","doi":"10.1145/3177457.3177482","DOIUrl":"https://doi.org/10.1145/3177457.3177482","url":null,"abstract":"According to the theory of linear regression model, this paper designed a sensor data lossless compression algorithm. The algorithm calculates the sensor data's fitting values and fitting residuals, which are input to a content-based entropy coder to perform compression. The algorithm achieves lossless transform by rounding operation, and realizes positive sequence decoding by prediction fitting. The efficient entropy coding is realized by calculating the mean bit number of input data. Compared with the typical lossless compression algorithms, the proposed algorithm indicated better compression ratios with a small computational overhead.","PeriodicalId":297531,"journal":{"name":"Proceedings of the 10th International Conference on Computer Modeling and Simulation","volume":"11 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-01-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129152209","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":"Analyzing Human Visual Perception of Streetscape Elements through Taxonomic Diagrams","authors":"G. Gunawardena","doi":"10.1145/3177457.3177476","DOIUrl":"https://doi.org/10.1145/3177457.3177476","url":null,"abstract":"Any element is made of several sub elements and they have complex connections on the physical world. It shows a hierarchy. The complexity caused due to this hierarchical structure of variety and connections is called structural hierarchical complexity. However, in the visual world, these physical elements will be perceived based on their visual qualities like color, shapes, size, and distance. During the course of visual perception, some elements will be highlighted while some elements will be suppressed. Visual perception has an order of viewing objects. This order of visual perception creates invisible connections among the viewing objects and it leads to have an invisible hierarchical structure of perception. This phenomenon can be explained as structural hierarchical visual perception. Therefore, this research was carried out with the objective of representing this structural hierarchical visual perception as diagrams to show these invisible connections among visual elements in human perception. To achieve this objective, the Gestalt's explanation on figure and background classification was applied. For this analysis, a survey was carried out with 60 subjects. Subjects were asked to travel along 100 streetscapes in Colombo District while explaining the most eye catching elements in an orderly way. The explanations were recorded as video clips. Later those video clips were analyzed and the subjects' explanations were arranged as taxonomic diagrams to display order of visual perception by each subject. The ordering of visual elements by sixty subjects for different streetscapes displayed unique patterns such as residential streetscapes resulted one common pattern and this pattern was different from the viewing pattern of commercial streetscapes. Thus the structural hierarchical visual perception for different streetscapes was different to each streetscape type. The taxonomic diagrams drawn to different streetscape types were varied in their lengths and the widths attesting this difference in visual perception in varied streetscape types. Thus by analyzing taxonomic diagrams, it was very straightforward to understand the structural hierarchical visual complexity on different streetscape types. Thus taxonomic diagrams are a best representation of structural hierarchical visual perception as well as the structural hierarchical complexity.","PeriodicalId":297531,"journal":{"name":"Proceedings of the 10th International Conference on Computer Modeling and Simulation","volume":"101 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-01-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"117332437","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":"Neural Machine Translation Enhancements through Lexical Semantic Network","authors":"Quang-Phuoc Nguyen, Anh-Dung Vo, Joon-Choul Shin, Cheolyoung Ock","doi":"10.1145/3177457.3177461","DOIUrl":"https://doi.org/10.1145/3177457.3177461","url":null,"abstract":"In most languages, many words have multiple senses, thus machine translation systems have to choose between several candidates representing different senses of an input word. Although neural machine translation has recently become a dominant paradigm and achieved great progress, it still has to confront with the challenge of word sense disambiguation. Neural machine translation models are trained to identify the correct sense of a word as part of an end-to-end translation task, and their performances on word sense disambiguation are not satisfactory. This paper presents a case study of machine translation for Korean language. We have manually built a Korean lexical semantic network - UWordMap - as a large-scale lexical semantic knowledge-based in which each sense of every polysemous word is associated with a sense-code constituting a network node. Then, based on UWordMap, we determine the correct sense and tag the appropriated sense-code for polysemous words of the training corpus before training neural machine translation models. Experiments on translation from Korean to English and Vietnamese show that UWordMap can significantly improve quality of Korean neural machine translation systems in terms of BLEU and TER cores.","PeriodicalId":297531,"journal":{"name":"Proceedings of the 10th International Conference on Computer Modeling and Simulation","volume":"90 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-01-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125958317","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}