Jun Toyama

Multidimensional curve classification using passing—through regions

Abstract A new method is proposed for classifying sets of a variable number of points and curves in a multidimensional space as time series. Almost all classifiers proposed so far assume that there is a constant number of features and they cannot treat a variable number of features. To cope with this difficulty, we examine a fixed number of questions like “how many points are in a certain range of a certain dimension”, and we convert the corresponding answers into a binary vector with a fixed length. These converted binary vectors are used as the basis for our classification. With respect to curve classification, many conventional methods are based on a frequency analysis such as Fourier analysis, a predictive analysis such as auto-regression, or a hidden Markov model. However, their resulting classification rules are difficult to interpret. In addition, they also rely on the global shape of curves and cannot treat cases in which only one part of a curve is important for classification. We propose some methods that are especially effective for such cases and the obtained rule is visualized.

Performance analysis of minimum /spl lscr//sub 1/-norm solutions for underdetermined source separation

Results of the analysis of the performance of minimum /spl lscr//sub 1/-norm solutions in underdetermined blind source separation, that is, separation of n sources from m(<n) linearly mixed observations, are presented in this paper. The minimum /spl lscr//sub 1/-norm solutions are known to be justified as maximum a posteriori probability (MAP) solutions under a Laplacian prior. Previous works have not given much attention to the performance of minimum /spl lscr//sub 1/-norm solutions, despite the need to know about its properties in order to investigate its practical effectiveness. We first derive a probability density of minimum /spl lscr//sub 1/-norm solutions and some properties. We then show that the minimum /spl lscr//sub 1/-norm solutions work best in a case in which the number of simultaneous nonzero source time samples is less than the number of sensors at each time point or in a case in which the source signals have a highly peaked distribution. We also show that when neither of these conditions is satisfied, the performance of minimum /spl lscr//sub 1/-norm solutions is almost the same as that of linear solutions obtained by the Moore-Penrose inverse. Our results show when the minimum /spl lscr//sub 1/-norm solutions are reliable.

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.

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.

On the Minimum ℓ 1 -Norm Signal Recovery in Underdetermined Source Separation

This paper studied the minimum l1-norm signal recovery in underdetermined source separation, which is a problem of separating n sources blindly from m linear mixtures for n>m. Based on our previous result of submatrix representation and decision regions, we describe the property of the minimum l1-norm sequence from the viewpoint of source separation, and discuss how to construct it geometrically from the observed sequence and the mixing matrix, and the unstability for a perturbation of mixing matrix.

A Divergence Criterion for Classifier-Independent Feature Selection

Feature selection aims to find the most important feature subset from a given feature set without degradation of discriminative information. In general, we wish to select a feature subset that is effective for any kind of classifier. Such studies are called Classifier-Independent Feature Selection, and Novovicova et al.s method is one of them. Their method estimates the densities of classes with Gaussian mixture models, and selects a feature subset using Kullback-Leibler divergence between the estimated densities, but there is no indication how to choose the number of features to be selected. Kudo and Sklansky (1997) suggested the selection of a minimal feature subset such that the degree of degradation of performance is guaranteed. In this study, based on their suggestion, we try to find a feature subset that is minimal while maintainig a given Kullback-Leibler divergence.

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.

Spectral properties of Japanese whispered vowels referred to pitch

Whispered speech can communicate the same linguistic information as ordinary speech in spite of the great difference of their respective acoustic characteristics. In this respect, whispering is an interesting object for studying speech perception and recognition. In this study, we investigate the spectral properties of five whispered Japanese vowels uttered in isolation and having different pitch. Pitch of ordinary whispered vowels was measured in terms of the manner in which the talkers were listening to pure tones while uttering and adjusting its frequency so that the pitch matched the utterance. For other samples, talkers changed the pitch of utterances to match the given pure tones. Acoustic analyses were carried out on formant frequencies, a spectral tilt, and a peak frequency of wide‐ranging spectral shape using second‐order LPC method called a global peak. Preliminary results show a tendency of upward shift of F1, F2, and global peaks, and flattened spectral tilts on overall vowels with increasing ...