Toyohisa Nakada

A support system for finding lost objects using spotlight

We propose a support system for finding lost objects indoors. The system employs active RFID and ultrasonic position detection to detect the position of a lost object. The system illuminates the position by using Movinglight, which is normally employed in stage lighting. From an experiment, the way of notification by light is better than that by sound in some situations.

Notification of dangerous situation for elderly people using visual cues

There are various dangers that could lead to accidents in daily life at home. It is difficult for elderly people to realize these dangers beforehand. In this study, we focus on a method for enhancing the risk perception of elderly people. We have developed a system that enhances the awareness of dangerous situations. It performs the following functions: (1) it recognizes the behavior and situation of the elderly person, (2) it estimates the risk, and (3) when the risk is estimated to be high, it notifies the person of the risk by means of visual and audio cues. In this paper, we outline our system and report a user test that evaluates the notification function, particularly the use of visual cues in our experimental living environment. The result is that the visual cues are suitable for elderly rather than healthy people in the environment of a dark room. As a future work, we will investigate the effects of visual and audio cues as notifications of danger for elderly people.

A Support System for Context Awareness in a Group Home Using Sound Cues

Objectives: In a group home, caregivers should be aware of the inhabitant’s real-time situation. The aim of our study is to facilitate the awareness of an inhabitant’s situation by means of enhanced sound cues. Methods: We propose an audio notification system that indicates the real-time situation of persons in a group home environment using sound cues instead of visual surveillance. The notification system comprises a prediction and a notification function. The prediction function estimates a person’s real-time situation using a Bayesian network and sensed information; the notification function informs recipients of the predicted situation and the confidence level of the prediction by means of sound cues. We use natural sounds as sound cues. Results: As a first step to examine our system in a group home, we conducted operation and performance tests of each unit under a simple test environment. The correct prediction of the subject’s situation is approximately 90%; further, it is shown that the sound cues should be selected according to their environmental dependence. Conclusions: The results show that the method is useful for monitoring persons. As future study, we will conduct a field test on an implemented system and improve it for practical use in a group home.

Subgroup Discovery among Personal Homepages

This paper discusses our algorithm for finding subgroups among personal homepages. Assuming that personal homepages usually carry personal information, we have developed an algorithm that allows us to automatically find potential patterns from them. For example, when the algorithm is applied to personal homepages at some school, we can approximate the ratio between the number of students interested in information science and that of students interested in social science. In the experiment, we successfully created subgroups that showed characteristics of the school. Also, we found relations between subgroups that are important for enhancing human activity.

Robust free-space optical communication for indoor information environment

The purpose of our study is to establish a robust communication, while keeping security and privacy, between a handheld communicator and the surrounding information environment. From the viewpoint of low power consumption, we have been developing a reflectivity modulating communication module composed of a liquid crystal light modulator and a corner-reflecting mirror sheet. We installed a corner-reflecting sheet instead of light scattering sheet in a handheld videogame machine with a display screen with a reflection-type liquid crystal. Infrared (IR) LED illuminator attached next to the IR camera of a base station illuminates all the room, and the terminal send their data to the base station by switching ON and OFF of the reflected IR beam. Intensity of reflected light differs with the position and the direction of the terminal, and sometimes the intensity of OFF signal at a certain condition is brighter than that of ON signal at another condition. To improve the communication quality, use of machine learning technique is a possibility of the solution. In this paper, we compare various machine learning techniques for the purpose of free space optical communication, and propose a new algorithm that improves the robustness of the data link. Evaluation using an actual free-space communication system is also described.