The world population is ageing. In the aged society, grasping the body condition of the elderly is helpful to choose appropriate rehabilitation. This research focuses on the outdoor walking analysis by use of the simple foot mounted IMU system. The walking feature values are estimated by the algorithm, and they are combined with the GPS data obtained by smartphone to compare the feature values of frail elderly and healthy subject. The differences of walking feature values that are calculated by this system show the usefulness of developed system. The developed system is simple, but useful to grasp the gait features changing of the user.

This study aimed to understand whether and how wearable technologies and mHealth services could be nurtured for self-care at the individual-level. We launched a self-care online survey in 2015, and a total of 188 participants (66% female; mean age = 30 years) completed the survey. Following the survey, we also conducted a qualitative study with 12 Fitbit users. In both studies, we focused on understanding three prerequisite elements for behavior change: mindset, tool set and skill set. The results showed that most people had the mindset that self-care was important for preventing chronic diseases, and their top health concerns were sleep quality, body weight, mood, skin conditions and chronic fatigue. As for tool set, users acknowledge the potentially positive impact and efficacy of the technologies in facilitating self-care. However, current technologies have several usability issues such as low accuracy, low technology transparency, and limited feedback. As for skill set, two major obstacles were identified: difficulty in sustaining the usage of the technologies, and lacking domain knowledge and data analysis skills to gain insights from personal data. Different from existing studies which mainly focused on understanding the tool set, i.e., the technologies and services per se, this study produced new insights on the current landscape of people's mindset and skill set on adopting the technologies for health behavior change. We also summarized the opportunities and challenges to guide researchers in designing new wearable technologies and mHealth services for self-care.

Studies of interactive systems in museums have raised important design considerations, but so far have failed to address sufficiently the particularities of family interaction and co-operation. This paper introduces qualitative video-based observations of Japanese families using an interactive portable guide system in a museum. Results show how unexpected usage can occur through particularities of interaction between family members. The paper highlights the necessity to more fully consider familial relationships in HCI.

To realize accurate tracking of people in the environment, many studies have been proposed using vision sensors, floor sensors, and wearable devices. The problem of using vision sensors is that they do not provide ID information of each people and there are ambiguities when people come across. To solve the problem, we propose to combine acceleration sensors that are attached to the human body. Since the signals from vision sensors and acceleration sensors synchronize when they observe same person who are acting or walking in the environment, these signals are not independent. The correlation between the signals is evaluated based on the canonical correlation analysis. Experimental results are shown to detect gesture and to track people to confirm the effectiveness of the proposed method.

In this paper, we present a method for estimation of objects' positions and orientations in an indoor environment. For ubiquitous computing, it is important to realize provision of a location-aware information service for humans. Especially, orientation information can reflect a more detailed context than that obtained merely according to a location: people standing face-to-face or back-to-back have vastly different contexts. We are tackling indoor location and orientation estimation using a new approach called topological estimation, which specifically examines relative relationships of humans rather than their absolute positions. In the initial implementation of topological estimation, we have used infrared tags as sensors to collect real-world related information. This paper describes an ultrasonic and radio device system to collect objects' local relationships.

"Tabletop Community" is an artwork that records interactions among users around a table. The artwork also visualizes a social network of users from data that show these interactions; the piece can present that network to other users as well. Its theme is self-recognition, which emerges from social interactions with others in a human network. It is intended to offer experiences of looking back at a user's past interactions with others within the perspective of a group (social network) in a visual manner. We have shown the artwork at Ubicomp2005. The paper shows the types of interactions, inferred from collected data and comments from the audience, which have delivered some improvements in the artwork since its original version.

We have undertaken a research project that visualizes a community, especially for events such as academic conferences. As research progresses, we have noticed that small gatherings of a few persons happen during events as a vital component of forming a community. We call these happenings Social Interactions. Typical situations that foster Social Interactions include gathering around a table. Therefore, we think it is possible to visualize larger communities through obtaining and processing Social Interaction data via table-like interfaces.As one part of group research project, here we introduce an art piece, named "Tabletop Community", that enables the visualization of Social Interactions around the table. Through this artwork system, users/participants easily record the state and atmosphere of each Interaction. The system visualizes the state of the entire community as an interactive network visualization. Here we introduce past results along with the current progress of the system.

A social network can become bases for information infrastructure in the future. It is important to extract social networks that are not biased. Providing a simple means for users to register their social relation is also important. We propose a method that combines various approaches to extract social networks. Especially, three kinds of networks are extracted; user-registered Know link network, Web-mined Web link network, and face-to-face Touch link network. In this paper, the combination of social network extraction for communities is described, and the analysis on the extracted social networks is shown.

Social networks play important roles in the Semantic Web: knowledge management, information retrieval, ubiquitous computing, and so on. We propose a social network extraction system called POLYPHONET, which employs several advanced techniques to extract relations of persons, detect groups of persons, and obtain keywords for a person. Search engines, especially Google, are used to measure co-occurrence of information and obtain Web documents.Several studies have used search engines to extract social networks from the Web, but our research advances the following points: First, we reduce the related methods into simple pseudocodes using Google so that we can build up integrated systems. Second, we develop several new algorithms for social networking mining such as those to classify relations into categories, to make extraction scalable, and to obtain and utilize person-to-word relations. Third, every module is implemented in POLYPHONET, which has been used at four academic conferences, each with more than 500 participants. We overview that system. Finally, a novel architecture called Super Social Network Mining is proposed; it utilizes simple modules using Google and is characterized by scalability and Relate-Identify processes: Identification of each entity and extraction of relations are repeated to obtain a more precise social network.

This paper presents a card type battery-less information terminal $CardBIT - and a method of situated interaction that uses single-lens cameras. The CardBIT system provides situated information support at locations such as exhibition halls, train stations and streets. CardBIT can operate without a battery because it utilizes energy from the information car-tier and the user. It realizes location-and-direction-based interaction; a user can get appropriate information for his/her position and direction. The most significant feature of the CardBIT is its high portability because it is easily implanted into widely-used IC cards. Based on information accumulated in the CardBIT, personalized information in the form of sound, such as speech or music, is provided. Furthermore, a user can signal to the interface system and obtain information dynamically. This paper introduces the CardBIT system concept and its implementation using cameras, position estimation, and sign recognition methods. Our experiments show the feasibility of the proposed system.

A retrieval method, called running time interval clustering (Rutic), is proposed. The method detects time sequence intervals similar to the query time sequence in a vast database of time sequences such as video and audio data. Conventional methods, such as RIFCDP, handled queries of any interval lengths, but they require a relatively high computational burden and are not suitable for real-time retrieval from a large database. The Rutic method allows retrieval results to be output for each input frame of the time sequence queries, thus enabling retrieval from a database without segmentation. The computational burden of the Rutic method is so small that it enables the so-called real-time spotting retrieval. This report describes the algorithm of the Rutic method, and verifies its validity through comparison with other methods based on image search experiments.

We develop a technique for robustly positioning and guiding mobile robots in the real world, such as offices and homes, by using topological maps consisting of image sequences capturing the environment. This technique uses reference interval-free continuous dynamic programming (DP) which allows positioning by spotting, but it restricts the direction of mobile robot navigation to the same one as the map creation. We propose to use the nonmonotonic continuous DP for gesture recognition, to allow the positioning of a robot within the same framework even when it navigates backwards or stops. We also propose the use of average values of local features in each section generated by horizontally dividing the omnidirectional view as rotation-invariant features to allow global positioning of a robot regardless of its direction. In addition, we demonstrate the usefulness of this technique through evaluation experiments using mobile robots.

Our purpose is to recognize the human gestures from motion image without using contact type sensors such as data gloves or markers on hands. This paper proposes a method which can extracts good features from a small-sized image of a person and demonstrates the effectiveness using an omni-directional camera which can capture the gestures of more than one person.

We study spotting recognition of human gestures from time-varying images. We propose a feature extraction method and a spotting method. The feature extraction reduces each frame of motion into a frame image of small size, such as 3/spl times/3 pixels. We show that the feature with 3/spl times/3 is the best one to provide robust characteristics to the changes of cloth and background. The spotting recognition rate was about 80% for 8 gesture categories. A new spotting method called non-monotonic continuous DP is proposed for spotting gestures and their variations such as reverse, partial and stop motions. We show the effectiveness of the new spotting method.

We have been developing a localization method for an autonomous robot without using any prior knowledge or assumptions about the environment. The method is general and robust and can be used in real world robot tasks. With a map description based on a reduced image sequence, we detect a frame sequence in the map which matches an input frame sequence, by means of reference interval-free continuous dynamic programming (RIFCDP). The method can cope with changes in the robot's speed because RIFCDP can spot arbitrary frame sequences by nonlinear matching. In this paper, we show a real-time localization system, and we illustrate the effectiveness of our method in the real world by some evaluation experiments.