We present an Interactive Evolutionary Computation (IEC) system that applies user gaze information. Historically, IEC systems have encountered the problems caused by heavy user evaluation loads. To solve these problems, researchers have employed biologically derived user information, such as heartbeats or brainwaves, to reduce the evaluation load. However, the requirement for users to wear special devices to measure this information has limited the popularity of these systems. Therefore, we applied the user gaze information approach to solve these problems. Gaze information includes the user’s potential preferences, which are derived from various processes. When user gaze information is applied in the evaluation of candidate solutions, IEC systems can obtain user evaluation information while users are viewing multiple candidate solutions. In this paper, we verify the effectiveness of the eye tracking IEC system using evaluation experiments with real users. In the experiment, we use a normal IEC system as a comparison method where users manually evaluate candidate solutions using a 10-stage evaluation process. The experimental results show that the eye tracking IEC method can generate solutions with results equivalent to those of the compared system.
In a treatment process, a doctor has to view a lot of medical data about symptoms, test results, drugs and their dosages in a period of time. It is convenient for the doctor to view and search for any information he/she needs if all the medical data of each patient are visualized appropriately. For that purpose, we propose EMRVisualization, an electronic medical record visualization system, to visualize all the related medical data in an integrative manner. The system provides an interactive visualization with accurate data at different detail levels, quick access and convenience for a doctor to track the progress of each patient over time. Its development is detailed in this paper. Its demonstration with the real data of gastroenterological Vietnamese patients in Thong Nhat Hospital, Ho Chi Minh City, Vietnam, is conducted. It also shows that every interaction of a doctor can be accomplished in at most two steps.
The authors have been conducting research on value-creating communication. It is a process where people embody and clarify their own values and form new values through communication. The authors have observed and modeled consensus building process that has few choice as an example of value-creating communication. Next, the authors observed and modeled consensus building process in case of multiple-choices and compared the process based on quantity of choices. The authors have observed one group that they created the conception through communication and one group that they reached the consensus in terms of a viewpoint. Then, in this paper, the authors classified consensus building process into patterns from two viewpoints. Moreover, the authors classified six cases in case of multiple-choice into patterns and discuss the characteristics. As a result, it was suggested that the time to reach agreement varies depending on the pattern.
Color design is a crucial component in creating an appealing media presentation. Designers always prepare many color themes in their design work, while it is not an easy work for non-designers to obtain suitable colors. In this paper, we propose an approach for automatically creating affective color themes for visual-textual design. Banner design acts as an initial application. First, we create 2 estimation models, one is for affective color theme generation and the other is for legibility of text color on a background color. Then, a recommender system is developed to create banners with different colors corresponding to specified impressions. The mechanism of color unification with input images and text color legibility checker are implemented in the design system. Moreover, we conduct verification experiments to explore the effect of system output.
In order to eliminate mismatches between the intentions of questioners and respondents of Question and Answer (Q&A) sites, nine factors of impressions for Japanese and English statements have experimentally been obtained. Factor scores are then estimated by using the feature values of statements. So far the possibility of searching Japanese respondents capable of giving appropriate answers to a newly posted question has been established. It has been shown that the distance and the number of appearance may help us select users who can give appropriate answers to a question. In the similar fashion, this paper tries to find the possibility of detecting respondents who can appropriately answer a newly posted question at English Q&A sites. As a result of analysis, while there were several users who iteratively gave answer statements for Japanese, there are only a small number of respondents who only posted at most two answers for English.
A lot of supporting tools for vitalizing brainstorming sessions have been proposed. Some of them show the participants hints for discussions, e.g. keywords and images. The author’s research group also has proposed a supporting system for vitalizing brainstorming sessions. In the system, “semi-relevant images,” which are relevant images of the relevant words of words used in created ideas, are shown for participants of a brainstorming as hints. Despite the system works well for vitalizing discussions, the effects of this type of hint had not been investigated. Thus, experiments were conducted to show the effects. In the experiments, effects of three types of hints, (1) relevant keywords; relevant words of the words used in ideas presented in the discussion, (2) relevant images; images retrieved by using words used in ideas presented in the discussion as keywords, and (3) semi-relevant images; images retrieved by using relevant words of the words used in ideas presented in the discussion as keywords, were compared. The results show that the third type of hints can increase number of utterances and diversity of the subjects in discussions.
An education program on amyotrophic lateral sclerosis communication support was conducted for students on medical, nursing, rehabilitation, and clinical psychiatry courses. We investigated how the participants’ knowledge was maintained over time. A pre-/post-test was undertaken to evaluate knowledge acquisition through the program. The primary version consisted of 10 questions developed from 26 items extracted in a textbook (by Imura) and was applied to 23 students attending the same two sessions 6 months apart. The average pre-test score was 6.2 +/-2.1; the post-test score was 7.3 +/-1.6 (p = 0.023). However, no difference was evident in the pre-test and post-test scores between the two sessions. The test appeared able to detect knowledge acquisition following a single session; however, it was difficult for the participants to retain the knowledge acquired from a single session over a period of 6 months.