{"title":"Fault Diagnosis Based on Modified BiLSTM Neural Network","authors":"Tianqi Zhang, Qing Fei, Nannan Li, Dailiang Ma","doi":"10.1145/3385209.3385212","DOIUrl":"https://doi.org/10.1145/3385209.3385212","url":null,"abstract":"Fault diagnosis of industrial processes has recently received widespread attention. Some studies applied neural networks to fault classification algorithms, which directly take the raw data as input of the neural network for training, and then use classifier to classify faults. However, the raw data of industrial usually has high dimension and the variables has linear correlations between each other, which may not only lead to higher computational complexity and cause the neural network difficult to converge. In this paper, a fault diagnosis algorithm based on a modified bidirectional long-short term memory network (BiLSTM) is investigated. The proposed method introduces the linear discriminant analysis (LDA) before the architecture of networks to reduce the dimension of input data. Then the LDA-BiLSTM is tested in Tennessee Eastman Process (TEP) platform. Experiment results show that the dimension reduction procedure can speed up the convergence of neural network, and may improve the classification accuracy. Extensive experimental results indicate that developed algorithm provides better diagnosis performance.","PeriodicalId":429673,"journal":{"name":"Proceedings of the 2020 5th International Conference on Intelligent Information Technology","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-02-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125827772","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}
Phuc Quang Tran, Ngoan-Thanh Trieu, H. H. Luong, N. C. Tran, H. Huynh
{"title":"An Affinity Propagation Approach for Entity Clustering with Spark","authors":"Phuc Quang Tran, Ngoan-Thanh Trieu, H. H. Luong, N. C. Tran, H. Huynh","doi":"10.1145/3385209.3385224","DOIUrl":"https://doi.org/10.1145/3385209.3385224","url":null,"abstract":"With the dramatically increasing amount of electronic data, the automatic detection and extraction of information in the text is the first step for all other data analysis activities. Clustering entities is the important methods for discovering knowledge and extracting appropriate data applied in several applications. The clustering methods often need to pre-determine the number of clusters and the initial centers thus the problem of \"initial staring conditions\" usually occurs. In this paper we propose a new approach that overcome this problem for clustering entities without pre-defining the number of clusters with the Affinity Propagation algorithm. The algorithm is built on the Spark platform for speed up the clustering process. The experiments are conducted on different characteristics datasets.","PeriodicalId":429673,"journal":{"name":"Proceedings of the 2020 5th International Conference on Intelligent Information Technology","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-02-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125629517","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":"New Discoveries on Integer Factorization by Valuated Binary Tree","authors":"Xingbo Wang, Cong Zheng","doi":"10.1145/3385209.3385217","DOIUrl":"https://doi.org/10.1145/3385209.3385217","url":null,"abstract":"The paper proves that an odd composite integer N can be factorized in O(logN) time if N's big divisor is in the form 2α u + 1 or 2α u − 1 and its small divisor does not exceed 2α + 1 Theorems and corollaries around the conclusion are proved with detail mathematical reasoning. The results in the paper again demonstrate the significance of applying the valuated binary tree on analyzing the odd integers.","PeriodicalId":429673,"journal":{"name":"Proceedings of the 2020 5th International Conference on Intelligent Information Technology","volume":"44 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-02-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115555364","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":"Industrial Wireless Networked Control System with Dynamically Tuned EWMA Filter","authors":"Tran Duc Chung, R. Ibrahim","doi":"10.1145/3385209.3385215","DOIUrl":"https://doi.org/10.1145/3385209.3385215","url":null,"abstract":"Wireless technology has permitted wireless monitoring and control applications for industrial process plants. Most related works have addressed delay issues in networked control system using common predictive techniques such as Smith predictor, and Kalman filter. However, they are complex and only applicable for high performance controllers. Thus, they are not suitable for implementation at microcontroller-based plant actuators which are normally computationally limited. A suitable approach to overcome this shortcoming is to use exponentially weighted moving average (EWMA) filter which is computationally efficient while still achieving desired control performance. Common practice for design of EWMA filters is to fix the filter weight. The drawback of this approach is that it results in longer time to reach the desired setpoint. Therefore, in this paper, a dynamically tuned EWMA filter is proposed to improve control performance of the process plant. Here, the weight of the filter is tuned adaptively using fuzzy logic technique. From the results obtained, it is shown that the proposed method is robust against time-varying delay and significantly improves the control performance by reducing both settling time and percent overshoot.","PeriodicalId":429673,"journal":{"name":"Proceedings of the 2020 5th International Conference on Intelligent Information Technology","volume":"25 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-02-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123589761","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}
Dohyung Kim, Jonghyeok Mun, Yoosang Park, Jongsun Choi, Jaeyoung Choi
{"title":"Planning System Architecture of Fat-client Management for Customized Healthcare Services in Edge Computing Environment","authors":"Dohyung Kim, Jonghyeok Mun, Yoosang Park, Jongsun Choi, Jaeyoung Choi","doi":"10.1145/3385209.3385222","DOIUrl":"https://doi.org/10.1145/3385209.3385222","url":null,"abstract":"To provide customized healthcare services in edge computing environment, it is necessary to process perspectives related to delivering context information such as procedures of data collection and analysis in various data formats. It is required to have a fat-client concept that performs, data preprocessing and converting data formats where generated data sets have different structure. Furthermore, the fat-client concept has advantages of covering data acquisitions and job allocations in edge computing environment. Once data sets are collected, then users can have healthcare reports, analyzed in a different level. When dealing with procedures of analysis, their models are necessary because data sets have different formats and ranges, moreover models will be required for user customizing it by adjustment the data sets being collected. This paper proposes a method for managing fat-client to provide customized healthcare services in edge computing environment. The proposed method, provides a fat-client profile for managing each fat-client user. The fat-client profile includes information such as sequences of data sources and analysis methods. In the experiment, the fat-client management is demonstrated through data collection and monitoring of instances created by the Fat-Client profile.","PeriodicalId":429673,"journal":{"name":"Proceedings of the 2020 5th International Conference on Intelligent Information Technology","volume":"21 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-02-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124837624","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 Question Detection Algorithm for Text Analysis","authors":"Tran Duc Chung, Ha Hong Son, A. Khalyasmaa","doi":"10.1145/3385209.3385230","DOIUrl":"https://doi.org/10.1145/3385209.3385230","url":null,"abstract":"In this paper, an effective question detection algorithm for Vietnamese text analysis is proposed. The proposed algorithm takes an audio file as input, converts its speech to text, and returns question detection result. This is extremely useful for a text analyzer to determine if a given sentence generated from an audio file is a question or not, particularly in chatbot or voicebot systems where very often there are needs for automatic replies to questions queried by users. The algorithm uses two tiers of question words and a customized question phrases to achieve 88.64 % accuracy on a sub-dataset of 176 questions prepared based on FPT Open Speech Dataset.","PeriodicalId":429673,"journal":{"name":"Proceedings of the 2020 5th International Conference on Intelligent Information Technology","volume":"6 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-02-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132039020","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":"Offshore Development Center Management in Action","authors":"P. D. Hung, Le Gia Cuong, N. L. Bach","doi":"10.1145/3385209.3385214","DOIUrl":"https://doi.org/10.1145/3385209.3385214","url":null,"abstract":"Serving as a virtual extension of the Customer's IT Department, the Offshore Development Center (ODC) model provides certain benefits in comparison with in-house teams including reduced development complexity, reduced operating expense, and access to a larger pool of talents. Nevertheless, ODCs are prone to problems in Scope, Schedule, Quality, Human Resources, and Communication. From the experiences of Project Managers who have worked in Offshore Development Centers set up by FPT Software- a leading IT Outsourcing Service provider, this paper offers a look at actual problems encountered in ODCs. We then provide a reference ODC Management Framework, which consists of Best Practices that we have applied into an ODC serving a Media Industry customer over the last 4 years. The results of applying the model are discussed to prove its effectiveness.","PeriodicalId":429673,"journal":{"name":"Proceedings of the 2020 5th International Conference on Intelligent Information Technology","volume":"17 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-02-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133021842","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":"Estimation of Rotational Eye Movement based on Intensity Gradients in the Eye Images","authors":"K. Hoshino, Yuya Nakai, Yuki Noguchi, Nayuta Ono","doi":"10.1145/3385209.3385234","DOIUrl":"https://doi.org/10.1145/3385209.3385234","url":null,"abstract":"Cycloduction or rotational eye movement is regarded as a rotational movement around the z-axis of the eye. This feature may be caused by physical deconditions, including dizziness, car-sickness, visually induced motion sickness, and nausea. In this study, the authors propose a method that allows rotational eye movement measurement with high accuracy without using blue auxiliary light for users in whom blood vessels in the white part of the eye differ considerably in terms of thickness and density on the image. In the system, to select a template image that includes a thick, dense blood vessel suitable for tracking in the white part of the eye, feature points are first extracted from the white part of the eye on the acquired image based on the intensity gradients. The number of feature points in a candidate template image is counted. Next, from among the candidate template images that include a larger number of feature points, those with a reflection of external light sources are excluded. Lastly, blood vessels with no similar shape nearby are selected as a candidate template image. The results of an evaluation experiment showed that among the methods in which rotational eye movement estimation is performed by tracking a blood vessel in the white part of the eye, the method proposed in this study could, even without blue auxiliary light, reduce the standard deviation of the estimation errors to 56% of that of the conventional method developed by Hoshino et al., which uses a blue auxiliary light to enhance the contrast of blood vessels.","PeriodicalId":429673,"journal":{"name":"Proceedings of the 2020 5th International Conference on Intelligent Information Technology","volume":"8 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-02-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128914545","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":"Applying Code Quality Detection in Online Programming Judge","authors":"Xiao Liu, G. Woo","doi":"10.1145/3385209.3385226","DOIUrl":"https://doi.org/10.1145/3385209.3385226","url":null,"abstract":"This article presents an enhanced programming online judge system that not only evaluates the correctness of the submitted program code but also detects its code quality. Both results of the correctness and quality detection are responded through web once the compilation, the execution and the quality detection of the submitted source code have been finished. We take advantage of SonarQube to provide code quality detection in our online judge system named neoESPA. Comparing with other online judges, our proposed work has significant advantages in helping both the instructor to discover the weaknesses in the lecture and the students to locate their mistakes efficiently.","PeriodicalId":429673,"journal":{"name":"Proceedings of the 2020 5th International Conference on Intelligent Information Technology","volume":"49 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-02-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128120433","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":"Gaze Estimation with Easy Calibration Method","authors":"K. Hoshino, Yuki Noguchi, Yuya Nakai","doi":"10.1145/3385209.3385232","DOIUrl":"https://doi.org/10.1145/3385209.3385232","url":null,"abstract":"In the corneal reflection method for gaze estimation, the user is asked to look at multiple calibration points with known lines of sight, and the central pupil point is captured for each vision angle. Therefore, the center of the eye in the images can be acquired for each known eye rotation angle. However, because the spherical center of the eye is captured in two-dimensional images and because measurement errors are, of course, included, in order to map eye rotation angles from two-dimensional images, normally, the approximate solution is calculated by using the least squares method in the overdetermined system linear equation. Normally, six coefficients are calculated from nine points of regard for calibration. This study proposes a new gaze estimation method that uses fewer calibration points while maintaining accuracy equivalent to using nine points.","PeriodicalId":429673,"journal":{"name":"Proceedings of the 2020 5th International Conference on Intelligent Information Technology","volume":"36 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-02-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129198161","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}