This paper presents the first part-of-speech (POS) tagging research for Tigrinya (Semitic language) from the newly constructed Nagaoka Tigrinya Corpus. The raw text was extracted from a newspaper published in Eritrea in the Tigrinya language. This initial corpus was cleaned and formatted in plaintext and the Text Encoding Initiative (TEI) XML format. A tagset of 73 tags was designed, and the corpus for POS was manually annotated. This tagset encompasses three levels of grammatical information, which are the main POS categories, subcategories, and POS clitics. The POS tagged corpus contains 72,080 tokens. Tigrinya has a unique pattern of root-template morphology that can be utilized to infer POS categories. Subsequently, a supervised learning approach based on conditional random fields (CRFs) and support vector machines (SVMs) was applied, trained over contextual features of words and POS tags, morphological patterns, and affixes. A rigorous parameter optimization was performed and different combinations of features, data size, and tagsets were experimented upon to boost the overall accuracy, and particularly the prediction of POS for unknown words. For a reduced tagset of 20 tags, an overall accuracy of 90.89% was obtained on a stratified 10-fold cross validation. Enriching contextual features with morphological and affix features improved performance up to 41.01 percentage point, which is significant. General Termsnatural language processing, part-of-speech tagging

Product appearance has become a more important influence on customers' preference in regards to product purchase. Not only do customers take into account functionality and cost, but also on aesthetic and affection value. Kansei engineering (KE) utilizes a product design methodology which translates a customers' perception regarding feeling and emotion on appearance of a product into a product's design parameters. This study applied KE methodology to determine customer emotion on the shape of wine glasses and the optimal precise design parameters to obtain customer satisfaction. This study was performed using a four-factor and three-level Box-Behnken design under response surface methodology (RSM). The data obtained from the experiments were analyzed by analysis of variance. Furthermore, the data was fitted to a second-order polynomial equation using multiple regression analysis. The effects of four parameters of wine glass, namely the rim's width (A), the bowl's width (B), the bowl's height (C) and the stem's height (D) on the surface potential of five Kansei words, namely modern, quality, durable, ease of drinking and ease of handle were examined. The optimal model of wine glass design was controlled at A=90 mm, B=61.82 mm, C=126.67 mm and D=61.97 mm, respectively. The results of RSM indicate that the proposed shape design models can interpret all of customers' emotion about a product which in this case is a wine glass. Finally, this study provides useful understanding for shape parameter design and this method can be applied to a variety of design cases.

This study examines a model to evaluate the probability of choosing the mode of public transport with finding most significant aspects related to the characteristic of the journey, characteristic of the traveler and the personal behavior of the traveler. The study area was focused on eleven Divisional Secretariat Divisions of the Colombo Metropolitan Area in the Western Province of Sri Lanka. This area has the most economically advanced functions as the commercial capital of Sri Lanka. The current transportation sector in the focusing area has impact of increasing vehicle ownership and serious inadequacies in the road network such as traffic congestions, shortfall of road capacity and low speed level on road. Hence this study attempts to encourage people for the public transport by focusing about their perception related to the mode choice as a solution for the above issues. The results showed that "Number of Earning Members", "Vehicle Ownership", "Education", "Age", "Gender", "Occupation", "Trip Distance.", "Trip Time", "Total Cost" and "Safety" of the mode were the most significant factors for affecting to choose the public transport. The obtained logistic model with the significant variables had the 78.4% of accuracy for the prediction of probability in using public transport.

No abstract

Ceramic is one of Thai products that are always changing to meet customer's requirements. Knowing customer's need is the target of designers as well as developing a product that must satisfy customers. This research applies Affective Engineering and Fuzzy Analytic Hierarchy Process (FAHP) approach into the customer-driven product design process. Affective Engineering serves to analyze the relationships between customer's perceptions and design characteristics. Six factors were retrieved: attractive, easy to drink, easy to handle, quality, modern and durable. Quantification Theory type 1 was applied to map the relationships between physical attributes and affective values. FAHP method was used to evaluate and to identify design characteristics that were compared and ranked to determine the most suitable design characteristics for a recommended design alternative. Afterward, based on all findings, some candidate samples were designed. The result of this study shows that these techniques can be applied to ceramic design in Thai manufacturing.