Catálogo de publicaciones - libros

The chronological scenarios of individual patients of hepatitis C are understood, from the double helix process of chance discovery. Here, first the internal data is obtained from the thought of user who is non-expert of hepatitis, having learned premature knowledge about hepatitis from preceding communications with hepatologists and overviewed the output the KeyGraph applied to blood test data of an individual hepatitis patient. This internal data was visualized and fed back to user’s own awareness about the significance of a certain set of blood attributes. The individual patient data got in parallel visualized with DSV, tool for visualizing a scenario flow, and the awareness of the user above was used to annotate on the output of DSV. This clarified the complex scenario of each patient, and lead hepatic doctors to proposing suitable treatments.

The mapping method between the graph generated by KeyGraph and the scenario drawn up by a user is proposed for supporting chance discovery process. Although KeyGraph is widely known as one of the effective tools that support the process of chance discovery, further improvement seems to be required, concerning the ambiguity involved in user’s interpretation of the graph. The mapping found by the proposed algorithm is used for extracting the data referred to in the scenario and for annotating those in the original data file. The annotated data files are expected to be used for further data analysis as well as for supporting group discussion. The preliminary experimental result shows how the algorithm works.

Data mining is one of the methods to extract some knowledge from large amount of data and KeyGraph is one of the unique methods for data mining. The result of KeyGraph analysis is shown like network diagrams; the analyst tries to understand the meaning of links and make reasonable scenarios. In this process, the more complex the link structure is, the more difficult to understand its meaning. For this difficulty, we developed a preprocessing method enabling to generate simpler link structure at first and also generate more complex structure gradually. By this method, we could obtain more detailed and various scenarios.

By modifying a format of data inputted, KeyGraph can visualize a virtual small world structure among respondents of an empirical survey with ease. This article aims at examining a major question in the small world problem: searchability by the new utilization of KeyGraph. Authors found the clear difference of a potential connector and a substantial connector among clusters of human network, and this difference implies a significant nature of our social network, which tends to be overlooked under the strong influence of the Power Law theory.

The aim of this paper is to propose a new system for the strategic use of customer data that includes and integrates such differing data sources as company databases, mobile telephone networks and Internet data and is a consumer research support system for the discovery of new marketing opportunities. This system, called CODIRO, will be discussed in this paper using a case study of the effects on sales of processed food product television commercials. A system for verifying the validity of consumer behavior models will also be described and discussed. Use of the CODIRO analysis system makes it easy to introduce, into the analytic model, consumer attitude changes and in-store data of many types that have not been used to measure advertising and promotional activity effectiveness in the past.

The purpose of this paper is to study the process of discovering problems with activities of salespeople by visualizing the salespeople’s activities from the data of sales reports, written in natural language. A framework was constructed on the basis of the doulble-helix model in which human and data-mining tools are used for spiralled progression toward creative reconstruction of ideas. One of the subjects found that the focus of salespeople’s activities failed to align with his instructions due to the influence of the timing and content of new brochure release.

It has been said that there is something deeply touching about creating something and then having a with it. Machines in general, and more specifically computers, are not the exception to that tendency. In this paper, the introductory idea of considering human chat as a critically self-organized interaction is presented, being its structure pondered as the basis to modeling computer chat.

In the paper, we first present an approach to extract social networks from message boards on the Internet. Then we measure structural features of 3,000 social networks extracted from 3,000 message boards from 15 categories in Yahoo!Japan Message Boards to prove the relationships between the features and the categories. Using hierarchical cluster analysis, we show three types of social networks.

Cognitive science has revealed that the feature of human thinking is not fully logical but symbolic looking. Brain science has clarified that human brain can selectively activate its neural networks. Brain activates and combines proper functional neural areas dynamically in response to various types of problem. Based on this understanding, we have proposed functional parts combination (FPC) model. In this paper, we describe a possible computational modeling of discrete optimization processing in brain by computationally remodeling the FPC model.

Technostress is the general term of the malfunction condition which treating the information management system accompanied by VDTs (Visual Display Terminals). The applied technology of ubiquitous computing will enhance the affinity between a computer and person. However, continuous use of VDTs sometimes causes technostress to us. The purpose of this study was to establish the method of reducing the visual fatigue during VDT work. In order to obtain a better reasoning result, it is necessary to deal with environmental information, VDT information and user information such as both psychological and physiological information, comprehensively. We, then, represent the causal association of visual fatigue using Bayesian network. Result showed the causal relationship between visual fatigue and VDT work factors visually.