Ippei Torii

Augmentative and alternative communication with digital assistant for autistic children

“Lets Talk!” is a new AAC (Augmentative and Alternative Communication) application for personal digital assistant for autistic children. This new and remarkable application has many particular advantages comparing to existing AAC. We especially focused on an easy and simple manipulation. By tapping a symbol on a screen of a PDA with this application, a user can show his/her thoughts with pictures and sounds to others easily. There are 2 modes which can be switched depending on different situations of users. It has 120 symbols based on daily life and a user can also create the original page with new icons made by pictures or sound. The operation of “Lets Talk!” is simple and easy. When a user chooses one from 12 categories on the top page, more specific symbols will be appeared and voice sound will come out by touching a symbol. For example, if a user chooses “Eat” category and “bread” for a symbol, the voice will say “I want to eat bread.” There are 2 modes which can be switched depending on different situations of users. On “Supportive Mode”, a supporter shows the application to a user. On Self-use Mode, a user can tell what he/she wants directly with categories and symbols. It is possible to make original icons with a camera or a voice recorder in PDA. A user also can customize an original page by arranging icons he made or existing symbols.

Modified Reduct: Nearest Neighbor Classification

Dimension reduction of data is an important theme as in the data processing and on the web to represent and manipulate higher dimensional data. Rough set developed is fundamental and useful to process higher dimensional data. Reduct in the rough set is a minimal subset of features, which has almost the same discernible power as the entire features in the higher dimensional scheme. Then, there are relations between reducts and their classification classes. Here, we develop a method which connects reducts and the nearest neighbor method to classify data with higher classification accuracy. To improve the classification ability of reducts, we propose a new modified reduct and its optimization method for the classification with higher accuracy. Then, it is shown that the modified reduct improves the classification accuracy, which is followed by the optimized nearest neighbor classification.

Development and Study of Support Applications for Autistic Children

We developed a new VOCA (Voice Output Communication Aid) application for personal digital assistant (PDA), “Lets Talk!” for autistic children. This application has many particular advantages comparing to existing VOCA. We especially focused on an easy and simple manipulation. By tapping a symbol on a screen of a PDA with this application, a user can show his/her thoughts with pictures and sounds to others easily. There are 2 modes that can be switched depending on different situations of users. It has 120 symbols based on daily life and a user can also create the original page with new icons made by pictures or sound. A user also can customize an original page by arranging icons he made or existing symbols. On the newest version of this application, we added Task Schedule System to stimulate motivations of children to do something by them. On the last part of this study, we show some case studies. We introduced this application to students in a school for handicapped children and collected data.

Classification on nonlinear mapping of reducts based on nearest neighbor relation

Dimension reduction of data is an important theme in the data processing and on the web to represent and manipulate higher dimensional data. Rough set is fundamental and useful to process higher dimensional data. Reduct in the rough set is a minimal subset of features, which has the same discernible power as the entire features in the higher dimensional scheme. It is shown that nearest neighbor relation with minimal distance introduced here has a basic information for classification. In this paper, a new reduct generation method based on the nearest neighbor relation with minimal distance is proposed. To improve the classification accuracy of reducts, we develop a nonlinear mapping method on the nearest neighbor relation, which makes vector data relation among neighbor data and preserves data ordering.

Study and Development of Support Tool with Blinks for Physically Handicapped Children

In this study, we try to develop a new application for physically handicapped children to communicate with others by a blink. Because of limited body movements and mental disorders, many of them cannot communicate with their families or caregivers. We think if they can use application in smart phones by a blink, it will be big help for them to tell caregivers what they really need or want to tell. First, we try to detect an eye area by using OpenCv. Then we develop the way to detect opening and closing of eyes. We combine the method using situation and using complexity of image to get more accurate results to detect a blink. The level of handicapped is very varied in children. So we will try to develop the application to be able to customize depends on the situation of users. And also, we will try to reduce the error to detect a blink and pursue the high precision of the eye chased program.

Detecting Eye-Direction Using Afterimage and Ocular Movement

A support application for physically handicapped children to communicate with others by blinks is studied in this paper. OpenCv was used to detect an eye area. The method using saturation and using complexity of image are combined to get more accurate results to detect blinks. The technique is developed into a communication application that has the accurate and high precision blink determination system to detect letters. This devise can also put the words into sound. This blink detection method is used to develop the non-contact communication support tool that judges the eye direction by ocular movement. Combination of blink determination and detecting gaze detraction made it possible to choose letters remarkably fast and acclate. Furthermore, the vibration of the center point of the eyes is digitized by the comparison with the afterimage and middle point of the amount of change with scatter diagram is replaced to distinguish the state of an user. In future study, association with fatigue degree, sleep shortage and an intensive degree and the blurring of the eyeball vibration of right and left can be found using neural network.

Development of Support Applications for Elderly and Handicapped People with ICT Infrastructure

We work on studying and developing support applications for aged and handicapped people. First, we developed a new communication assistant application for autistic children, ”Let’s Talk!”. We especially focused on an easy and simple manipulation. We also developed a to-do application for kids, “Hanamaru” and a scheduler application for elderly people, “Anshin”. We used ICT infrastructure, especially computer network systems such as SNS (Twitter, Facebook), e-mail, Skype, Line, and a message board on the web site, to collect the requests and opinions of users, and tried to feed it back to improve the applications.

Study and Application of Detecting Blinks for Communication Assistant Tool

Abstract We try to develop a support application for physically handicapped children to communicate with others by blinks. Because of limited body movements and mental disorders, many of them cannot communicate with their families or caregivers. If they can use applications in smart phones by blinks, they will be able to tell what they really need or want. Fist, we try to detect an eye area by using OpenCv. Then we develop the way to detect opening and closing of eyes. We combine the method using saturation and using complexity of image to get more accurate results to detect blinks. Then we develop the technique into a communication application that has the accurate and high-precision blink determination system to detect letters and put them into sound.

Generation and Nonlinear Mapping of Reducts—Nearest Neighbor Classification

Dimension reduction of data is an important theme in data processing. Reduct in the rough set is useful since it has the same discernible power as the entire features in the higher dimensional scheme. But, classification with higher accuracy is not obtained in the reduct followed by nearest neighbor processing. To deal with the problem, it is shown that nearest neighbor relation with minimal distance introduced here has a basic piece of information for classification. In this paper, a new reduct generation method based on the nearest neighbor relation with minimal distance is proposed. To improve the classification accuracy of reducts, we develop a nonlinear mapping and embedding methods on the nearest neighbor relation, which also adjust vector data relation and preserve data ordering to cope with noise in classification.

Generation and Mapping of Multi-Reducts Based on Nearest Neighbor Relation

Dimension reduction of data is an important theme in the data processing to represent and manipulate higher dimensional data. Rough set is fundamental and useful to process higher dimensional data. Reduct in the rough set is a minimal subset of features, which has almost the same discernible power as the entire features in the higher dimensional scheme. Combination of multi-reducts is effective for parallel processing of the classification. Nearest neighbor relation between different classes has a b asic information for classification. We propose here a multireduct parallel processing classification scheme with efficient and higher accuracy by using nearest neighbor relation. To improve the classification ability of reducts, we develop a generation method of reducts and its graph mapping method by using the nearest neighbor relation, which is based on characteristics of the weighted reducts for the classification. Further, a dependency relation and an embedding of nearest neighbor relation are proposed to improve the classification accuracy.