Rathawut Lertsuksakda, P. Netisopakul, Kitsuchart Pasupa
{"title":"Thai sentiment terms construction using the Hourglass of Emotions","authors":"Rathawut Lertsuksakda, P. Netisopakul, Kitsuchart Pasupa","doi":"10.1109/KST.2014.6775392","DOIUrl":"https://doi.org/10.1109/KST.2014.6775392","url":null,"abstract":"Most of the current sentiment analysis techniques classifies emotions into two classes which are positive and negative. Some works classify them as positive, negative and objective (neutral). In fact, there are many kinds of emotions in human mind. Recently, psychological viewpoints have influenced most of the works in sentiment analysis. This psychology perspective was adopted to classify human emotions into a wider range, and in a more accurate manner. This paper reviews the adopted computational representation of emotions the so-called Hourglass of Emotion. This paper also proposes a construction of Thai sentiment resource based on such representation for Thai sentiment term tagging. A preliminary sentiment text tagging result shows that the resource as an ontology can be successfully used to tag sentiment text in Thai children stories.","PeriodicalId":427079,"journal":{"name":"2014 6th International Conference on Knowledge and Smart Technology (KST)","volume":"37 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2014-03-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126319940","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}
D. Matsuyoshi, Kana Kuraguchi, H. Ashida, Katsumi Watanabe
{"title":"Interhemispheric differences in the perception of human gaze direction","authors":"D. Matsuyoshi, Kana Kuraguchi, H. Ashida, Katsumi Watanabe","doi":"10.1109/KST.2014.6775406","DOIUrl":"https://doi.org/10.1109/KST.2014.6775406","url":null,"abstract":"Some human brain functions are known to be lateralized to the left or right hemisphere. Although the perception of face has been shown to be mediated by the right hemisphere, whether the discrimination of eye gaze is also mediated by the right hemisphere remains uncertain. In the present study, we attempt to investigate whether the discrimination of human gaze direction is different between the left and right hemispheres. Participants performed a discrimination task using face images in which the face image with gaze was briefly displayed either in the left or right visual hemifield. We found that the discrimination performance of direct gaze was superior to that of averted gaze in the right hemifield when the face image without gaze (control stimulus) was presented in the opposite hemifield. However, the discrimination performance of direct and averted gaze was comparable in the left hemifield. Our findings may reflect a humans' implicit expectation that gaze is directed toward them when the perception of gaze is difficult, which stems from relative difficulty in processing gaze in the non-dominant left hemisphere.","PeriodicalId":427079,"journal":{"name":"2014 6th International Conference on Knowledge and Smart Technology (KST)","volume":"28 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2014-03-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124527687","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 missing values imputation in collaborative filtering with user-preference genre and singular value decomposition","authors":"Wanapol Insuwan, U. Suksawatchon, J. Suksawatchon","doi":"10.1109/KST.2014.6775399","DOIUrl":"https://doi.org/10.1109/KST.2014.6775399","url":null,"abstract":"One of the major concerns in collaborative filtering is sensitive to data sparsity. The other word, missing values are occurred when the customers rate to a few products or services, which bring about to less accuracy of the recommendation. Although the centroid of cluster and SVD are able to solve Sparsity problem, their drawbacks are 1) imputed mean is not derived from user preference and 2) imputed mean does not reflect to the real distribution since imputed mean comes from the average. Therefore, we propose “SVDUPMedianCF” in order to solve the defect of the traditional approach which is an imputation missing value by filling the missing values for each customer with the cluster centroid, obtained from K-means algorithm, of such customer along with singular value decomposition (SVD) in collaborative filtering. According to the experimental evaluation based on MovieLens dataset by using 5-fold cross validation, it has found that imputing missing values with the proposed model presents the lowest mean absolute error when comparison with traditional approach significantly. From the experimental result, the proposed model can improve the quality of recommendation results with significant difference (p<;0.05).","PeriodicalId":427079,"journal":{"name":"2014 6th International Conference on Knowledge and Smart Technology (KST)","volume":"26 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2014-03-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123411828","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":"Fault localization in all-optical linear networks","authors":"M. L. Ali, P. Ho, János Tapolcai","doi":"10.1109/KST.2014.6775400","DOIUrl":"https://doi.org/10.1109/KST.2014.6775400","url":null,"abstract":"The paper investigates single-link fault localization in all-optical networks in a line topology in which a single monitoring node (MN) can localize shared risk link group (SRLG) faults by inspecting the optical bursts traversing through it. We investigate relevant problems in the proposed fault monitoring approach, including m-trail allocation, burst launching time scheduling, and node switch fabric configuration, where constructions are developed to derive optimal solutions and are further examined in numerical experiments.","PeriodicalId":427079,"journal":{"name":"2014 6th International Conference on Knowledge and Smart Technology (KST)","volume":"126 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2014-03-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123110552","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}
Nont Kanungsukkasem, P. Netisopakul, Teerapong Leelanupab
{"title":"Recognition of NASDAQ stock symbols in Tweets","authors":"Nont Kanungsukkasem, P. Netisopakul, Teerapong Leelanupab","doi":"10.1109/KST.2014.6775386","DOIUrl":"https://doi.org/10.1109/KST.2014.6775386","url":null,"abstract":"The massive volume of Twitter data has attracted much attention of researchers to study their correlation with stock market. Tweets with stock symbols can be identified by the prefix with dollar sign or by using some complex techniques. In this paper, we focus on discovering NASDAQ stock symbols in a stream of tweets. We propose a simple but effective methodology to recognize the stock symbols. Stock symbols from NASDAQ company list, WordNet, Wikipedia and sample tweets, as well as a classic method of collocation discovery are employed to filter stock-related tweets. Experimental evaluations show that our methodology outperforms the baseline approach for recognizing NASDAQ stock symbols.","PeriodicalId":427079,"journal":{"name":"2014 6th International Conference on Knowledge and Smart Technology (KST)","volume":"38 6 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2014-03-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126093176","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":"Multi-label classification with extreme learning machine","authors":"Yanika Kongsorot, Punyaphol Horata","doi":"10.1109/KST.2014.6775398","DOIUrl":"https://doi.org/10.1109/KST.2014.6775398","url":null,"abstract":"Extreme learning machine (ELM) is a well-known algorithm for single layer feedforward neural networks (SLFNs) and their learning speed is faster than traditional gradient-based neural networks. However, many of the tasks that ELM focuses on are single-label, where an instance of the input set is associated with one label. This paper proposes a new method for training ELM that will be capable of multi-label classification using the Canonical Correlation Analysis (CCA). The new method is named CCA-ELM. There are 4 steps in the training process: the first step is to compute any correlations between the input features and the set of labels using CCA, the second step maps the input space and label space to the new space, the third step uses ELM to classify and the last step is to map to the original input space. The experimental results show that CCA-ELM can improve ELM for classification on multi-label learning and its recognition performances are better than the other comparative algorithms that use the same standard CCA.","PeriodicalId":427079,"journal":{"name":"2014 6th International Conference on Knowledge and Smart Technology (KST)","volume":"19 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2014-03-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133034676","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}
Mohammad Zuberul Islam, M. Hossain, S. Haque, Jutheka Lahiry, Shyam Akhter Bonny, Mohammed Nazim Uddin
{"title":"User-agent based access control for DLNA devices","authors":"Mohammad Zuberul Islam, M. Hossain, S. Haque, Jutheka Lahiry, Shyam Akhter Bonny, Mohammed Nazim Uddin","doi":"10.1109/KST.2014.6775385","DOIUrl":"https://doi.org/10.1109/KST.2014.6775385","url":null,"abstract":"DLNA based media sharing is very popular nowadays. In current DLNA specification, a DLNA device advertises its presence to everyone in the network. Any control point application receiving the advertisement can access/control the device. However, with increasing popularity and availability of public Wi-Fi hotspots, it is necessary for devices to have some sort of access control. DLNA specification has no mandatory authentication procedure. So a device receiving a request from any unwanted control point cannot block/verify its access. The UPnP recommended authentication procedure is computationally expensive and complex for most personal devices. So, in this paper we propose a simple User-Agent based access control system that is effective to protect devices from unwanted control point applications.","PeriodicalId":427079,"journal":{"name":"2014 6th International Conference on Knowledge and Smart Technology (KST)","volume":"97 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2014-03-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131464280","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":"Cognitive characteristics of human vision: A tutorial","authors":"Katsumi Watanabe","doi":"10.1109/KST.2014.6775382","DOIUrl":"https://doi.org/10.1109/KST.2014.6775382","url":null,"abstract":"Summary form only given. Human vision is composed of numerous functions at multiple levels and complex interactions among them. In this tutorial talk, I will introduce several perspectives to characterize human vision. In particular, distinctions and interactions are discussed between bottom-up versus top-down processes, between perception versus action, between conscious and unconscious processes, all of which lead to variety of “seeing”. Through these examples, I would like to emphasize how the richness of our visual perception depends on many automatic, unconscious processes.","PeriodicalId":427079,"journal":{"name":"2014 6th International Conference on Knowledge and Smart Technology (KST)","volume":"128 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2014-03-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128120923","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":"Single wiper blade with new single link arm mechanism design using fuzzy-PID control system","authors":"S. Kantawong, Nontawat Janepumisart","doi":"10.1109/KST.2014.6775395","DOIUrl":"https://doi.org/10.1109/KST.2014.6775395","url":null,"abstract":"This paper present the new design concept of single wiper blade with single link arm (SBSA) systems that it is controlled by fuzzy proportional plus derivative plus integral controllers (F-PID) and will apply for wiper blade innovation system in the final purpose. A conventional wiper blade system is suitable for some windshield glass conditions because of its influenced not only by the quality of the wiper blade system, but also by the shape of the windshield glass size. The proposed of SBSA has taken an advantage of single link wiper arm to gain the geometrical criteria which a larger wipe area while still maintain wiper period and can be reduce the complexity of multilink arms mechanism as in the previous design concept. The multi-criteria objectives are not only considered for wipe quality but also constraints by windshield glass feasibility and respect of wiper blade standards. When the direct derivation of the objective functions is not available appeared and some mathematical models that are applied to control the speed regulation of a wiper motor are not precise for more complexes and have some vague systems, so the F-PID controllers can be used to solve this kind of problems that the main advantage of fuzzy logic is that no mathematical modeling is required but can be achieved higher performance with effective tuning methods of the initial setting parameters. By applying the proposed system, performance has been improved by mathematical analysis and simulation programs which indicated by a larger wipe area and reach to the optimum interval wipe period time for more precise of wiper blade's positions in the steady state response and can be reduced the transient state errors that come from any instantaneous disturbances such as instant winding or raining effect and finally for the vehicle drive safety.","PeriodicalId":427079,"journal":{"name":"2014 6th International Conference on Knowledge and Smart Technology (KST)","volume":"93 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2014-03-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121918518","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":"Product discovery via recommendation based on user comments","authors":"Walailak Kamlor, K. Cosh","doi":"10.1109/KST.2014.6775391","DOIUrl":"https://doi.org/10.1109/KST.2014.6775391","url":null,"abstract":"Recommendation systems on E-commerce websites help consumers to find products. A recommendation system learns consumer behavior in order to suggest products to those consumers. Recommendation systems allow consumers to have new experiences discovering new products rather than needing to search for them. When making purchase decisions consumers often use the comments left by previous buyers to help them. This paper presents how recommendation systems help E-commerce websites to recommend products, analyzes the recommendations used on some example sites and presents a new technique for recommendations based on the analysis of user comments and then analyzes the results of the new technique. The new techniques include parsing the text in comments to generate a word cloud based on the log likelihood of word frequencies, and then compares products using the RV Coefficient. Our approach automatically identifies similar products for recommendation, and based on the results of our experiment, the recommendations closely match those that would be manually chosen.","PeriodicalId":427079,"journal":{"name":"2014 6th International Conference on Knowledge and Smart Technology (KST)","volume":"95 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2014-03-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134415751","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}