{"title":"A fuzzy assessment on customer satisfaction of mobile telecommunication enterprises based on analytic hierarchy process","authors":"Yan-Li Lu, Shu-Shan Li, Bin Zhang","doi":"10.1109/ICMLC.2014.7009692","DOIUrl":"https://doi.org/10.1109/ICMLC.2014.7009692","url":null,"abstract":"This paper describes a customer satisfaction assessment model in mobile telecommunication service industry based on a fuzzy analytic hierarchy process approach. An empirical research is explored in three enterprises in Shijiazhuang. The assessment results show that as a whole the China Mobile's customer satisfaction index evolved to a much higher level, and followed by China Unicom and China Telecom, respectively in the better level and medium level. The results are basically in line with the actual, which proves that this evaluation model proposed in this paper is scientific and effective.","PeriodicalId":335296,"journal":{"name":"2014 International Conference on Machine Learning and Cybernetics","volume":"91 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2014-07-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132314545","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":"High dynamic range intelligent effects","authors":"Wei-Ming Yeh","doi":"10.1109/ICMLC.2014.7009655","DOIUrl":"https://doi.org/10.1109/ICMLC.2014.7009655","url":null,"abstract":"Recently, many mobile electronic devices, such as mobile phones and digital cameras, are equipped with a new function: High dynamic range (HDR), which can take better quality of photos, and create better selling record also. Actually, HDR effects deliver a mixture range of images of the same picture into a new photo. This new technique offers all kinds of photography (still, video, movie), computer graphics and image processing a new vision, which provides a better dynamic luminance range between dark and shining bright, and adding new life to a dull image. We checked every possible point about the advantages and disadvantages for this new function, and possible challenging for different aspect of users. In our experiments we checked this effects by taking trial photos, and phone survey also. We hope to find practical data to different groups of people who have same interests.","PeriodicalId":335296,"journal":{"name":"2014 International Conference on Machine Learning and Cybernetics","volume":"5 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2014-07-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132950244","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 maintenance algorithm of FDS based mathematical expression index","authors":"Song-Qiang Yang, Xue-dong Tian","doi":"10.1109/ICMLC.2014.7009727","DOIUrl":"https://doi.org/10.1109/ICMLC.2014.7009727","url":null,"abstract":"Mathematical expressions have complex two dimensions structure which could not be processed properly by traditional full-text retrieval method. It is necessary for us to research and develop special retrieval theory and technology including the indexing and matching methods of mathematical expressions which fully considers the characteristics of them. In this paper, a maintenance algorithm is designed for the mathematical expression index based on FDS which we given previously. Firstly, the existing achievements about mathematical expression recognition and retrieval are introduced and discussed. Then, the FDS is defined based on formula structural tree and the corresponding mathematical expression index is constructed. Finally, the index maintenance algorithms including the searching, inserting, and deleting operations of index items corresponding to the FDS based index are designed. The experimental result shows that the proposed method is helpful for the mathematical resources management and retrieval.","PeriodicalId":335296,"journal":{"name":"2014 International Conference on Machine Learning and Cybernetics","volume":"46 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2014-07-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116523007","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":"Some topological and measure properties of rough sets","authors":"Qun-Feng Zhang, Tianyi Zhang","doi":"10.1109/ICMLC.2014.7009713","DOIUrl":"https://doi.org/10.1109/ICMLC.2014.7009713","url":null,"abstract":"Since rough set theory was proposed by Pawlak in 1982, it has been investigated extensively and applied in a wide range of research fields such as machine learning and data mining. However, the pure mathematical explorations of rough sets have not been paid sufficient attention. This paper explores rough set theory from the point of view of topology and measure theory, and proves a few propositions about its properties.","PeriodicalId":335296,"journal":{"name":"2014 International Conference on Machine Learning and Cybernetics","volume":"25 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2014-07-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134080510","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":"Speech synthesis using articulatory-knowledge based HMM structure","authors":"H. Gu, Ming-Yen Lai, Wei-Siang Hong","doi":"10.1109/ICMLC.2014.7009144","DOIUrl":"https://doi.org/10.1109/ICMLC.2014.7009144","url":null,"abstract":"In this paper, a different HMM structure is proposed to model the context-dependent spectral characteristics of a speech unit in order to improve synthetic speech fluency. Instead of using decision trees, we reduce the huge amount of context combinations based on the articulatory knowledge of phonemes. To evaluate the proposed HMM structure, three Mandarin speech synthesis systems using different HMM structures are constructed for comparisons. In these systems, prosodic parameters are generated with the same ANN module developed previously but spectral parameters are generated using HMMs. As to the synthesis of signal waveform, the same HNM (harmonic plus noise model) based synthesis module being developed previously is used. According to results of listening tests, the speech signal synthesized by using the proposed HMM structure is significantly more fluent than those synthesized by using other HMM structures. In addition, the average spectral distances measured between recorded and synthetic sentences show that the proposed HMM structure yields a smaller spectral distance as compared with other HMM structures.","PeriodicalId":335296,"journal":{"name":"2014 International Conference on Machine Learning and Cybernetics","volume":"84 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2014-07-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133937292","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":"Machine learning class with automatic learning materials","authors":"L. L. Lai, C. L. Chan","doi":"10.1109/ICMLC.2014.7009127","DOIUrl":"https://doi.org/10.1109/ICMLC.2014.7009127","url":null,"abstract":"In this paper, an experimental class teaching Machine Learning such as Artificial Intelligence is presented. In this class, all teaching materials distributed to students are automatically processed with a set of XML compilers, after being inputted by the teachers with a GUI input tool. The compiler set was designed to generate three different forms of teaching materials from a single file using XML based semantics. Both students and teachers used all three forms in defined stages of learning process. The class activities and its teaching materials are refined by the toolkit in a highly systematic and organized manner, results, in the experimental class, with better initial understanding, less confusion, more active response and better class atmosphere. This leads to a better support form decision making.","PeriodicalId":335296,"journal":{"name":"2014 International Conference on Machine Learning and Cybernetics","volume":"24 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2014-07-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116552965","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":"Temporal prediction using self-organizing multilayer perceptron","authors":"Chengru Wang, Shie-Jue Lee","doi":"10.1109/ICMLC.2014.7009673","DOIUrl":"https://doi.org/10.1109/ICMLC.2014.7009673","url":null,"abstract":"In this paper, we apply the self-organizing multilayer perceptron (SOMLP) architecture proposed by Gas for temporal prediction. Our main idea is to divide a data series into several smaller sub-series which are treated as individual functions or signals. Then we can find the tendencies in detail and perform predictions based on the properties of these signals. By using the SOMLP, signals can be clustered and similar sub-series for the underlying prediction are located. The idea is tested by forecasting the Taiwan Stock Exchange Capitalization Weighted Stock Index (TAIEX) and results are presented.","PeriodicalId":335296,"journal":{"name":"2014 International Conference on Machine Learning and Cybernetics","volume":"13 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2014-07-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121921561","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":"Genetic algorithm based detection of general linear biclusters","authors":"Cuong To, Alan Wee-Chung Liew","doi":"10.1109/ICMLC.2014.7009667","DOIUrl":"https://doi.org/10.1109/ICMLC.2014.7009667","url":null,"abstract":"Clustering methods classify patterns into clusters using the entire set of attributes of patterns in the similarity measurement. In plenty of cases, patterns are similar under a subset of attributes only. The class of methods that cluster patterns based on subsets of attributes is called biclustering. Biclustering simultaneously groups on both rows and columns of a data matrix and has been applied to various fields, especially gene expression data. However, the biclustering problem is inherently intractable and computationally complex. In recent years, several biclustering algorithms which are based on linear coherent model have been proposed. In this paper, we introduce a novel GA-based algorithm that uses hyperplane to describe the linear relationships between rows (genes) in a sub-matrix (bicluster). The performance of our algorithm is tested via simulated data, gene expression data and compared with several other bicluster methods.","PeriodicalId":335296,"journal":{"name":"2014 International Conference on Machine Learning and Cybernetics","volume":"26 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2014-07-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125054374","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":"Value-based distribution systems reliability assessment considering different topologies","authors":"T. Tsao, H. Cheng","doi":"10.1109/ICMLC.2014.7009680","DOIUrl":"https://doi.org/10.1109/ICMLC.2014.7009680","url":null,"abstract":"This paper is concerned with the value based reliability assessment considering different topologies for planning a new distribution system. We will develop a set of reliability evaluation models for five distribution types to calculate load point reliability indices. The reliability worth of the five distribution types are evaluated according to customer interruption costs by using the sector customer damage function (SCDF). The most suitable system design is obtained based on comparison of the distribution system reliability cost/worth analysis for different planning topologies. Four case studies associated with the reliability cost benefit analysis are examined in this paper.","PeriodicalId":335296,"journal":{"name":"2014 International Conference on Machine Learning and Cybernetics","volume":"6 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2014-07-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127844086","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":"Text string detection for the first grade visually impaired pupils “reading mandarin textbooks”","authors":"Ching-Ching Cheng, Teng-Hui Tseng, Chun-Ming Tsai","doi":"10.1109/ICMLC.2014.7009145","DOIUrl":"https://doi.org/10.1109/ICMLC.2014.7009145","url":null,"abstract":"A text string detection method is proposed to help visually impaired first grade pupils read mandarin textbooks. To detect the actual text in view, and recognizing that a textbook is normally held open with both hands, the proposed method sequentially detects seeing a textbook, and then detects skin colors, index fingers and thumbs, text string region, and text strings. Experimental results show that the proposed method performs better than conventional two frame differencing methods. Furthermore, the proposed method reduces time complexity and has 98.5% text string total detection rate for the experimental videos.","PeriodicalId":335296,"journal":{"name":"2014 International Conference on Machine Learning and Cybernetics","volume":"404 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2014-07-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122941176","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}