Hidetoshi Nonaka

Privacy-preserved behavior analysis and fall detection by an infrared ceiling sensor network

An infrared ceiling sensor network system is reported in this study to realize behavior analysis and fall detection of a single person in the home environment. The sensors output multiple binary sequences from which we know the existence/non-existence of persons under the sensors. The short duration averages of the binary responses are shown to be able to be regarded as pixel values of a top-view camera, but more advantageous in the sense of preserving privacy. Using the “pixel values” as features, support vector machine classifiers succeeded in recognizing eight activities (walking, reading, etc.) performed by five subjects at an average recognition rate of 80.65%. In addition, we proposed a martingale framework for detecting falls in this system. The experimental results showed that we attained the best performance of 95.14% (F1 value), the FAR of 7.5% and the FRR of 2.0%. This accuracy is not sufficient in general but surprisingly high with such low-level information. In summary, it is shown that this system has the potential to be used in the home environment to provide personalized services and to detect abnormalities of elders who live alone.

Soft authentication using an infrared ceiling sensor network

Person identification is needed to provide various personalized services at home or at the office. We propose a system for tracking persons identified at the entrance to a room in order to realize “soft authentication.” Our system can be constructed at low cost and works anytime and anywhere in a room. Through experiments, we confirmed that the system could track up to 5 persons with a high probability of correct identification, though precise identification is difficult.

Use of highly accurate GPS in network-based barrier-free street map creation system

This paper presents the general architecture of geographic information systems (GIS) for assisting the users in creating barrier-free street maps by using the Internet and the highly accurate global positioning systems (GPS). The purpose of the system is to provide an effective tool for supporting the creation and the use of network-based barrier-free street maps for physically-handicapped people in wheelchairs. The wheelchairs are equipped with the GPS antenna and the tablet PC for computing the current positions with a cm-class accuracy to navigate the people in the streets. The server collects the positions from the wheelchairs moving around the local service area. The collection of data is stored and shared in the server after it is transformed into useful barrier-free information and integrated into the existing geographic information. To minimize the amount of the input by the users, the system relies on the intelligent information technology to construct the graphical structure of the maps and reason about the street conditions.

Communication Interface with Eye-Gaze and Head Gesture Using Successive DP Matching and Fuzzy Inference

This paper proposes a communication interface with eye-gaze and head gesture. Visual sensorimotor integration with eye-head cooperation is considered, especially head gesture accompanied with vestibulo-ocular reflex is used for selecting object in the screen. Eye-mark recorder and motion tracking system were used to tracking eye movement and head movement, respectively. Nonverbal response animation with eye contact was introduced in the interaction system. In identifying the head gesture, we adopted a modified dynamic programming matching method and fuzzy inference.

Multiperson Locating and Their Soft Tracking in a Binary Infrared Sensor Network

Low-cost sensor networks for multitarget tracking are increasingly becoming important equipment in many applications. A major problem is that these sensors usually provide only a binary response in each epoch, if a target is present or absent. Efficient approaches for realizing the location and tracking of multiple targets are needed. In this paper, we develop a soft tracking system using an infrared ceiling sensor network and propose a novel algorithm for tracking multiple people. In this system, 43 infrared sensors were attached to the ceiling of an office room (15.0 m × 8.5 m). Some pieces of weak evidence such as locations of personal desks, and the moving directions of people, were used for soft tracking. Through experiments, the ability of tracking in different situations was evaluated. The tracking accuracy during a 3 h period was investigated. The results showed that this system was able to track up to eight people simultaneously for hours in an office room. The tracking accuracy was above 90% most of the time, although some identity ambiguities occurred.

Person Authentication and Activities Analysis in an Office Environment Using a Sensor Network

Person authentication and activities analysis are indispensable for providing various personalized services in a smart home/office environment. In this study, we introduce a person localization algorithm using an infrared ceiling sensor network, and realize person authentication anywhere and anytime. The key problem is how to distinguish different persons meeting at the same position. We solve this problem by different moving directions depending on individuals. Furthermore, with the locations and the known identities, multiple persons can be tracked and their interactive behaviors can be analyzed by our system.

Soft authentication and behavior analysis using a chair with sensors attached: hipprint authentication

An authentication system using a chair with sensors attached is described. Pressure distribution (hipprint) measured by network-connected sensors on the chair is used for identifying the person sitting on the chair. Hipprint information is not sufficient for maintaining a high level of security but is sufficient for providing personalized services such as automatic log-in at home or in a small office. In experiments, we obtained correct identification rates of 99.6% for five people and 93.2% for ten people. A false rejection rate of 9.2% and a false acceptance rate of 1.9% were achieved using another group of 20 people. The results also showed that changes in hipprints can be used to estimate what the person sitting on the chair is doing, for example, using a mouse or leaning back.

Architecture for migratory adaptive user interfaces

We propose a new solution named interface client/logic server (ICLS), targeting dialog-based interactive services, supporting user interface (UI) migration, and offering adaptive UIs for devices and services. Constant improvements of technology have brought a large variety of platforms, and that has made userspsila new demands about the services. The first is that the users would like to use services through different devices and modalities depending on their use contexts. The second is that the users would sometimes like to change devices and take their tasks from one to another, which is called UI migration. Our architecture ICLS is designed based on client/server model. In ICLS, we use XML documents written in abstract interaction description language (AIDL) as logical descriptions of UIs, and introduce one of the semantic web technologies adding the function of expressing meanings of interactions.

Recording the Activities of Daily Living based on person localization using an infrared ceiling sensor network

In this study, we introduce two methods for indoor localization of person by using an infrared ceiling sensor network, then the performances of them are compared. Through experiments we see that the nonlinear method for person localization obtains better performance. Based on the nonlinear person localization method, we recorded the Activities of Daily Living (ADLs) of a person successfully. By observing the ADL of the person, we can investigate the transition pattern between activities and the living habits of him/her conveniently.

Flexible Widget Layout Formulated as Fuzzy Constraint Satisfaction Problem

We show an improvement of our previous work, a formulation of the flexible widget layout (FWL) problem as a fuzzy constraint satisfaction problem (FCSP) and a method for solving it. The automation of widget layout is one of the most important challenges for the generation of graphical user interfaces (GUIs). In the field of model-based user interface design, widget layout is more complicated because a layout system needs to select widgets. FWL is the automatic GUI generation requiring (1) deciding which widgets are used and (2) completing the layout immediately. We formulate the desirability of selection as fuzzy constraints; thus, we can utilize existing techniques of FCSP without extending its framework.We divide the layout process into three phases, and realize the automatic layout in feasible time.