Akinori Abe

The role of abduction in chance discovery

Recently, researches on discovery science and knowledge discovery have been carried out in various fields. Basically they are types of learning that learn tendencies from the sets of data of the same or similar categories. In this sense, discovery is to discover the tendencies. As a result, they cannot predict the events that are different from the trend. On the other hand, abduction is thought of as an explanatory reasoning. Indeed, abduction is a reasoning to generate hypotheses to explain an observation. However, the original meaning of abduction was to discover new things that cannot be known in a simple way. In this paper, abduction is defined using the original definition that discovers something that cannot be easily predicted. Then, this paper shows a role of abduction that can suggest or foresee the events that are different from the trend. In fact, Abductive Analogical Reasoning that can generate new hypotheses is adopted to solve the problem.

Curation in Chance Discovery

In this paper, a definition and function of a curation are extended according to the chance discovery aspects. A new definition, function, and effect of a curation in chance discovery are discussed. First, ordinal types of curation are reviewed. Definition by American Association of Museums Curators Committee (AAMCC) and Digital data curation are shown. Especially the latter is not curation in (art) museum but for digital data. In addition, interesting (from the viewpoint of chance discovery) curatorial cases are introduced. Based on those definitions and applications, a new type of curation in chance discovery is discussed. Our previous researches are also discussed from the viewpoint of curation.

Scenario Violation in Nursing Activities: Nursing Risk Management from the Viewpoint of Chance Discovery

This paper introduces scenarios that from a time series of events under a coherent context of performing nursing risk management. First, we describe general nursing risk management procedures. Then we review our previous nursing accident or incident protection model based on abduction. This paper extends the nursing accident or incident protection model by using the concept of scenario. That is, the model introduces chronological information in knowledge presentation. Then this paper regards a set of nursing activities as a scenario and characterizes a (nursing) accident or incident as a scenario violation. The main purpose of this paper is to present nursing risk management from the viewpoint of scenario violation in the context of chance discovery.

Possibility of Integrated Data Mining of Clinical Data

In this paper, we introduce integrated data mining. Because of recent rapid progress in medical science as well as clinical diagnosis and treatment, integrated and cooperative research among medical researchers, biology, engineering, cultural science, and sociology is required. Therefore, we propose a framework called Cyber Integrated Medical Infrastructure (CIMI). Within this framework, we can deal with various types of data and consequently need to integrate those data prior to analysis. In this study, for medical science, we analyze the features and relationships among various types of data and show the possibility of integrated data mining.

E-Nightingale: Crisis Detection in Nursing Activities

Summary. In this chapter, we address the importance of nursing risk management and propose computational models that address it. First, we address the importance and necessity of nursing risk management, then review nursing accidents or incidents from the cognitive aspects of human error. Based on cognitive features, we logically model nursing risk management. In fact, we present an abduction-based model. In the abductive model, nursing risk management is discussed from the viewpoint of Chance Discovery, where we can deal with hidden, rare, or new factors that can be regarded as dynamic risk management.

Exceptions as Chance for Computational Chance Discovery

In this paper, we analyze clinical data to model relationships between clinical data and health levels. During analyses of data, we discovered models which are important for determining health levels but cannot be extracted during machine learning process. We regard such models as chance and propose an interactive determination of such models. The obtained models can be referred to when standard models cannot correctly explain certain individual health levels.

Communication Error Determination System for Multi-layered or Chained Situations

Many medical accidents and incidents occurred due to communication errors. To avoid such incidents, in this paper, we propose a system for determining communication errors. Especially, we propose a model that can be applied to multi-layered or chained situations. First, we provide an overview of communication errors in nursing activities. Then we describe the warp and woof model for nursing task that was proposed by Harada and considers multi-layered or chained situations. Next we describe a system for determining communication errors based on the warp and woof model for nursing task. The system is capable of generating nursing activity diagrams semi-automatically and compiles necessary nursing activities. We also propose a prototype tagging of the nursing corpus for an effective generation of the diagrams. Then we combine the diagram generation with the Kamishibai KeyGraph to determine possible points of the hidden or potential factors of communication errors.

Data mining of multi-categorized data

At the International Research and Educational Institute for Integrated Medical Sciences (IREIIMS) project, we are collecting complete medical data sets to determine relationships between medical data and health status. Since the data include many items which will be categorized differently, it is not easy to generate useful rule sets. Sometimes rare rule combinations are ignored and thus we cannot determine the health status correctly. In this paper, we analyze the features of such complex data, point out the merit of categorized data mining and propose categorized rule generation and health status determination by using combined rule sets.

Cognitive Chance Discovery: From Abduction to Affordance

In this paper, first I review the basic theories- concept and computational realization of abduction. Then I brefly review chance discovery which focuses on rare and novel events. In addition I briefly review the concept of affordance porposed by Gibson. By using the above concepts and techniques, a dementia care system inspired by affordance is proposed and discussed Finally I introduce chance discovery based curation proposed by me. The dementia care system is discussed from the aspect of communication and chance discovery based curation.

Scenario Violation As Gaps Between Activity Patterns

In this paper, we propose interactive and visual discovery method of hidden factors for accidents or incidents. Accidents or incidents tend to occur because of very small differences from an ideal situation. From the above viewpoint, we introduce scenario violation model and regard scenario violation as a gap from the proper scenario. Previously, we proposed abduction-based scenario violation determination strategy, but in this paper, we adopt the Kamishibai-KeyGraph to analyze multiple patterns at the same time. Then, we show a gap discovery procedure by using the Kamishibai-KeyGraph.