Hironobu Satoh

Posture and Face Detection with Dynamic Thumbnail Views for Collaborative Distance Learning

In this paper, we describe the use of a collaborative TERAKOYA learning system developed to help students actively study anywhere on a local area network (LAN) linked to multipoint remote users. In this environment, if many students send questions to a teacher, it is difficult for the teacher to provide answers quickly; furthermore, the teacher is largely unable to determine the degree to which each student has understood the course materials, because he or she cannot observe the students and their reactions in person. In this paper, we discuss a graphical user interface (GUI) system that prioritizes student screens by changing the GUI on the teacher’s computer; more specifically, thumbnails of student screens zoom dynamically in proportion to each student’s understanding level. By sorting these priorities on his or her screen, the teacher can observe each student’s work and support their thinking process at each student’s individual pace.

Development of an Awaking Behavior Detection System with Kinect

The purpose of this study is detecting unsafe behavior of the person lying on the bed and warning caregivers that a person is falling down from the bed.

Implementation of a Learning Style by E-Textbook Contents Reduction Processing

The majority of Japanese classrooms are teacher-centered. Teachers lecture one-sidedly and write explanatory notes on blackboard matching the content of the textbook. The students just listen and copy the content that the teacher wrote on the blackboard.

Noninvasive Estimation of Lumber Disk Load During Motion to Improve the Posture

In order to reduce the load by improving the posture, it is necessary to know the load to the lumbar intervertebral disk when patients are in various motions. In this study, we propose a method to noninvasively estimate the load of the lumbar disc during motion. In the proposed method, we consider that the change in the gap between the vertebrae due to the posture change is determined only by the deformation of the intervertebral disc. And the internal changes are estimated indirectly by measuring the shape of the lumbar part from outside the body. And the deformation of the disc is estimated with this, and it will be evaluated as an intervertebral disc load. In this study, a disc load of sneezing motion was estimated and the load on lumber intervertebral disk during motion could be estimated with the proposed method.

Estimation of Hip Joint Moment by an Inertial Measurement Unit

This research is to estimate the hip joint moment without using a force plate that disturbs the gate. The purpose of this research is to show that with a single leg supporting period, the system is statically fixed, making it possible to derive the hip joint moment from the balance of inertial force and gravity without a force plate. Therefore, in this research, a wearable inertial measurement unit was used to measure the acceleration and angle of five body parts, and the hip joint moment was estimated. The proposed method, which estimated the hip joint moment using the inertial measurement unit, and the conventional method which estimated the hip joint moment using the information of the force plate showed similar results. Thus, the validity of the proposed method was obtained.

Noninvasive Estimation of Lumbar Intervertebral Disk Load Using Multiple Regression Analysis to Consider the Pelvic Tilt

In this study, a noninvasive method to estimate the load on the lumbar disk is proposed. By using the proposed method to evaluate posture, a system that user himself improves bad posture is provided. The load applied to the lumbar is indirectly estimated from the moment about the lumbar vertebra. Assuming the lumbar vertebrae part as a beam, it should consider three elements, the weight of the upper body, the weight of the heavy objects, and the bending of the lumbar part due to the pelvic tilt. In order to examine the validity of this proposal, multiple regression analysis by a simple model was carried out. As results, the tendencies of the proposed method were qualitatively consistent to the tendencies of the conventional method.

A Study for Adapting the Monitoring System in Order to Prevent Fall Down from a Bed

In hospitals, older people often fall down from a bed. This accident causes a decline in the quality of life of due to an injury. Therefore, the researchers develop a monitoring system which avoid falling down from a bed with Deep Belief Network. However, the proposed monitoring system is not able to individual differences. The proposed is a new learning method to adapt the proposed system for individual difference of behaviors. An experiment was conducted to verify the effectiveness of the proposed learning method. From the experimental result, the proposed learning method has the ability of adapting the proposed system to the individual difference of a behavior.

Adaptation Monitoring System Preventing Fall Down from a Bed for Individual Difference of Behavior

Elderly sometime fall down from a bed and fractured their femur. Fall accident must be avoided to improve the quality of life. To solve this problem, we proposed monitoring system preventing fall down using DBN (Deep Belief Network) and Kinect.

Collaborative Tablet PC the System for Self-Active Awareness in a Dormitory Environment

We describe a new interactive system using a social learning platform to provide dormitory students with the ability to communicate with teachers/advisors in a timely manner to promote self-active awareness in the dormitory environment. Our system comprises tablet PCs, cloud computing services, and application and server software to enable collaboration over a high-speed wireless local area network (WLAN) that covers the campus, dormitory, and teachers’ homes.

Interactive Check System for Facilitating Self-awareness of Dorm Students in Upper Secondary Education

We describe a new interactive system using a social learning platform to provide dormitory students with the ability to communicate with teachers/advisors in a timely manner to promote self-active awareness of the dormitory environment. Our system comprises tablet PCs, cloud computing services, and application and server software to enable collaboration over a high-speed wireless local area network that covers the campus, dormitory, and teachers’ homes. The purpose of this system is to facilitate the self-recognition of behavioral problems, raise awareness, and encourage student initiative in a natural manner.