Akihiro Ogino

Consumer-Friendly Shopping Assistance by Personal Behavior Log Analysis on Ubiquitous Shop Space

This paper has proposed a shopping assistance service. We provide consumer-friendly services which based on personal behavior log data. The consumer-friendly services are information service which display through a monitor, robot, sound and music that can attract new consumer. In this paper, we study personal behavior from a log file that has been recorded by RFID and camera sensors in the ubiquitous environment. Utilizing ubiquitous sensors, we apply three types of observation scopes to model each users preference. They are microscopic, mezzoscopic, and macroscopic observation scopes. We have proposed the behavior analysis, algorithms and collaborative filtering to retrieve information. Finally, we will also propose a ubiquitous shop space experiment.

Robot Helps Teachers for Education of the C Language Beginners

In this paper, we propose a learning support framework for teacher and learners that achieves the following three requirements: (A) to use unaware system, (B) to support the teacher for educating learners, and (C) to support learners for solving assignments. Based on the proposed framework, we implemented a system using a robot which supports learners.

A Framework for Programming Process Measurement and Compiling Error Interpretation for Novice Programmers

This paper proposes a framework to support programming education intended for novice programmers at universities. This proposed framework entails a collection of compile errors and source codes of a student at the time such errors occur, as well as storing the learning history of the student. Programming processes can be measured and a degree of understanding can be estimated by retaining the editing history of source codes. Furthermore, the implementation of the proposed framework, which resulted in the early identification of students with problems, is presented and evaluated.

Phynocation: a prototyping of a teaching assistant robot for C language class

This paper shows a system that supports students who learn programing language in a class using a robot. We found out that it would help students to solve the error that the robot talks hints with gestures.

Smart store understanding consumer's preference through behavior logs

This paper presents a smart store that estimates a preference of consumers concerning products from their behaviors. This paper proposes a method, which is a passive observation and an active observation, to observe two behaviors, direct behaviors and indirect behaviors. The passive observation is a method to observe direct behaviors of customers towards real products through ambient sensors. The active observation is a method to observe indirect behaviors of customers towards information of products through ambient displays. This study explains a purchase experiment using a prototype smart store that has installed the ambient shelves and displays. This study estimates the favorite clothes from their direct and indirect behavior using the smart store. The result of estimation of preference shows that accuracy rate is 87% by leaveone-out cross-validation.

Emotion-Based Music Information Retrieval Using Lyrics

In this paper, we present a study on emotion-based music information retrieval using lyrics information. Listeners want to search the lyrics of music suitable for his/her emotion (impression of music), by using an information system from music libraries. As a solution of listeners’ needs, we have designed a system that retrieve the lyrics of music based on the emotion (or the impression) suitable for a listener’s feelings that the listener has selected, from 9 emotions and 9 impressions. We select the words, i.e. verb and adjective, from the bridge part of the lyrics of music that express emotion in lyrics by using natural language processing. We summarize the words into the representative words by using a dictionary of synonyms. We make a model that estimates a listener’s 9 emotion/impression of the representative words by using a machine learning method. And listeners want to understand why the recommended music by a system is suitable for his/her emotion/impression. Therefore, we select the representative words most related to a listener’s emotion/impression and we use the selected words as the explanation of reason to a listener. We have made each model of emotion and impression for 9 subjects and have evaluated the accuracy of the model. We also have investigated the selected representative words related to emotion/impression.

Application of Modeling and Recommendation of Sensitivity to Get Tired

Most previous studies on the recommendation of the rut and sensitivity to aspects will feel tired and if the user continued use of the same systems and services has not taken into account. Continue to get service users continue to use, it is necessary to recommend considering information on their characteristics. This study is intended for planning meals, we propose a model sensitivity people get tired, we have applied to the verification and recommendation. An experiment to compare the results of subjective evaluation of real data and simulation results showed that a mathematical model representing the human feeling of mannerism proposed model. We also implemented the system, we evaluate the actual users, and other relevant planning meals to assist in creating, was found to be very effective considering the recommendation sensibility get tired.

A design support system for indoor design with originality suitable for interior style

This paper proposes a design support system to make a room design with freshness and originality impression suitable for users requirement interior styles. The proposed system supports to create the design plan through two steps: Creation process and Selection process. In the creation process, the system generates various design ideas by using several style furniture. In the selection process, the system selects the idea appropriate for their preference of interior styles by making a design style classifier using Naive Bayes. In this paper, we describe the subjective evaluation to 24 research participants through the application built on the proposed system. We show the proposed system can create the design idea that a user satisfied from the result of subjective evaluation concerning the planned idea by analyzing 659 data collected from the participants.

Impression Evaluation of a Conversational Robot Playing RAKUGO

The purpose of this paper is to detect a comfortable strength and timing of gestures of the robot for people. This paper describes the evaluation of individual impressions concerning RAKUGO of the traditional Japanese comic storytelling that is performed by a conversational robot. This paper shows that the gestures of the robot like professional actor of RAKUGO give smart and mature impressions to people than exaggerated gestures. In order to detect a tendency of impression based on individual personality, this paper also describes a relation between the individual impression to the gesture of the robot and Transactional Analysis that is one of psychology. We detect that there is a correlation between their impression to the gesture and their personality.

Framework for Modelling User Interest using Augmented Shopping Store

Recently, it has become difficult for consumers to find items of interest because there is such a vast range of items in the modern world. Consumers search the internet or use information devices in a shop to find their desired item in this information society. However, consumers with an unclear idea about what they want or consumers who are weak at using devices have difficulty finding the item they desire, quickly and easily. Therefore a system is needed that provides information regarding items of clear or spontaneous interest to consumers without demanding an unreasonable amount of time from the consumer. This paper proposes a framework of individual interest modelling used to provide information to consumer and support consumer purchases in a store using ubiquitous devices, such as cameras, sensors and displays. This framework shows a modelling mechanism concerning individual interest in items based on data collected through ubiquitous devices. This framework offers the suggestion that three observation views, micro, mezzo and macro, can be utilized to look at human actions towards items of interest in a store through ubiquitous devices. This paper also describes a personalized shopping store using this framework to create a human friendly environment.