Michiko Anse

A method for constructing a movie-selection support system based on Kansei engineering

When a person requests, for example, I want to see a bright and exciting movie, the words bright and exciting are called Kansei keywords. With a retrieval system to retrieve recommended movies using these Kansei keywords, a viewer will be able to select movies that fit the Kansei without actually having to view samples or previews of the movies. The purpose of this research is to clarify a method to construct a support system capable of selecting movies that fit the viewers Kansei, and to verify the effectiveness of this method based on Kansei engineering, for the selection of recommended movies. To accomplish this, we extract the features of a movie using factoranalysis from data from a Semantic Differential Gauge questionnaire, then link the viewers Kansei with the features using multiple linear regression analysis. After constructing a prototype ?system to verify the effectiveness, ten examinees viewed a movie selected by the prototype?system. The selected movie fit the Kansei at a level of about 70 percent.

A Prototype Crowdsourcing Approach for Document Summarization Service

This paper proposes a crowdsourcing approach for informative document summarization service. It first captures the task of summarizing a lengthy document as a bi-objective combinatorial optimization problem. One objective function to be minimized is the time to comprehend the summary, and the other one to be maximized is the amount of information content remaining in it. The solution space of the problem is composed of various combinations of candidate condensed elements covering the whole document as a set. Since it is not easy for a computer algorithm to create condensed elements of different lengths which are natural and easy for a human to comprehend, as well as to evaluate the two objective functions for any possible summary, these sub-tasks are crowdsourced to human contributors. The rest of the approach is handled by a computer algorithm. How the approach functions is tested by a laboratory experiment using a pilot system implemented as a web application.

A Prediction Market Game to Route Selection under Uncertainty

This paper addresses a route selection problem under uncertainty. The structure of the problem can be captured as an ordinal shortest path problem of a directed graph. However, the length of each arc of the graph is an uncertain random variable and its probability distribution is unknown to the decision maker; instead, information on the distribution is dispersed among the crowd. Under this set of circumstances, this paper provides a prediction market game for gathering the dispersed information from the crowd and thereby solving the reformulated problem. Further, the proposed gaming approach is applied to a simple real-life problem to understand how it works.

Development of a Coloration Support Tool for Making Web Page Screens User-Friendly for Color Blind

Websites are providing more and more information because of their convenience. Information is often discriminated by color vision ability between individuals. Some people cannot discriminate information depending on the coloration. In these cases, information cannot be correctly discerned. Therefore, the development of a supporting tool for configuring screens is needed.

A Skill Transfer Method for Manual Machine Tool Operation Utilizing Cutting Sound

This study focuses on the inheritance of skills that has faced difficulties through the years in Japan. Sensorimotor knowledge, which is hard to be described by words alone, is often seen in technical skills in a manufacturing environment in Japan. Interpreting sensorimotor knowledge as formal knowledge, attempts have been made to impart technical skills but have faced barriers particularly in lathe processing due to no visual check of finished quality being allowed. Thus, this study suggested training on the inheritance of skills utilizing the level of cutting sound generated in process. Novice workers served as experimental subjects for an experiment to verify the effectiveness of proposed training.

A study of an effective rehearsal method in e-learning

When information is memorized, the brain rehearses it. We can preserve information over a long period of time if this rehearsal is effectively performed in studying. This research aims 1.To clarify the effect of the rehearsal in e-learning, 2. To clarify the effective method for summary-making using a prototype system that studies structure of a stock (equity in a company). For this purpose, we 1.Compare the difference among three rehearsal methods, 2. (From result of 1) compare the results of an experiment of Summarize rehearsal method. As a result we find that the Summarize rehearsal is effective, especially when used for memorization constraints imposed in the number and types words used.

Methodology for constructing a prototype site for finding employment SPI measures using mobile phones

The written examination for job hunters in Japan is an important examination that cannot be skirted as the first step in the hunt for employment. However, there is no environment that can be studied using easy methods (mobile phones, etc.). In this research we clarify a methodology for constructing a prototype system for finding employment SPI measures. After constructing a prototype, we examine the effectiveness of the methodology. We use answer formats to achieve two purposes. (1) We clarified an answer format that can be efficiently studied through an experiment in no space in order to produce a measure site that can be efficiently studied in little time. (2) We constructed a prototype for selecting answer formats in order to examine whether the prototype can be used to select the following two formats on a mobile phone: first, the word, the meaning of the word, and an example of the word in use; second, the word, an explanation of the word, an example of the word in use, and the meaning of the word. (3) The test-takers studied the constructed prototype on mobile phones, then our group examined the effectiveness of the prototype based on the questionnaire results. The results indicate that the form can be efficiently studied. Thus, we can conclude that the prototype constructed can be used to select the following two answer formats: the word, the meaning of the word, and an example of the word in use and the word, an explanation of the word, an example of the word in use, and the meaning of the word.

Evaluation method of e-learning materials by α-wave and β-wave of EEG

The invention concerns a process for producing lactulose from lactose, wherein a saturated aqueous solution of lactose monohydrate is heated under reflux in the presence of an alkaline phosphite. The lactulose present in the solution obtained is purified by passing the solution in succession through a cation exchange resin and an anion exchange resin. The lactose is possibly separated by silica gel chromatography and evaporating the eluate.

A method for generating plans for retail store improvements using text mining and conjoint analysis

Sales at retail stores in Japan have been declining for various reasons. One important factor has been a steady diversification in the lifestyles and needs of customers. If a retail store is to sustain itself and continue developing, it must search for the latent demands of customers and adapt itself to accommodate those demands. A support system for store improvement capable of viewing specific improvement plans will prove useful as a tool for improving stores on a sustainable basis. In this research we develop a method for generating effective store-improvement plans to accommodate actual customer demands. The method employs both Text Mining and Conjoint Analysis techniques. We also demonstrate a sequence and a test run of a prototype.

A change of captain's EEG in a container ship-working in a bridge and resting in a cabin

The authors have experimented to investigate the relation between the electroencephalogram (EEG) and the level of brain activity of a captain in a container ship. The authors object is to show how EEG activity changes when working or when relaxing according to the progress of time. It is concluded that an expert such as the captain can exercise self-control because of duty to safety, that is, the captain can easily switch from a strained working stage to a relaxed resting stage. The characteristic patterns of the captains EEG were components of AR power spectra; active waves appeared dominantly in a strained condition, while inactive waves appeared in a relaxed condition.<<ETX>>