Kazuya Matsuo

Determination of locations on a tactile sensor suitable for respiration and heartbeat measurement of a person on a bed.

Sleep monitoring systems that can be used in daily life for the assessment of personal health and early detection of diseases are needed. To this end, we are developing a system for unconstrained measurement of the lying posture, respiration and heartbeat of a person on a soft rubber-based tactile sensor sheet. The respiration and heartbeat signals can be detected from only particular locations on the tactile sensor, and the locations depend on the lying location and posture of the measured person. In this paper, we describe how to determine the measurement locations on the sensor. We also report a realtime program that detects the respiration rate and the heart rate by using this method.

Adaptive user-centered design for safety and comfort of physical human nursing: care robot interaction

Nowadays serving robots are more and more popular in human society. However, most of them are designed for the special people or for the special scenario. There is little robot designed to apply appropriate interface for different people that can accommodate age-related and body-related in physical interaction. We propose that user-centered design should be used in physical Human-robot interaction. In this research, we take a nursing-care robot as an example. Based on the results of the experiment, we proved that the distance between two arms of nursing-care robot, which affected the comfort and safety of patient, should be applied by different patients with different body length. We try to build the adaptive human robot interface based on the physical properties of people, such as body length. This study is an attempt to explore the adaptive human robot interaction and contributes to giving insights and implications for the future design of general serving robot.

Probabilistic Prediction in Multiclass Classification Derived for Flexible Text-Prompted Speaker Verification

So far, we have presented a method for text-prompted multistep speaker verification using GEBI (Gibbs-distribution based extended Bayesian inference) for reducing single-step verification error, where we use thresholds for acceptance and rejection but the tuning is not so easy and affects the performance of verification. To solve the problem of thresholds, this paper presents a method of probabilistic prediction in multiclass classification for solving verification problem. We also present loss functions for evaluating the performance of probabilistic prediction. By means of numerical experiments using recorded real speech data, we examine the properties of the present method using GEBI and BI (Bayesian inference) and show the effectiveness and the risk of probability loss in the present method.

MEASUREMENT OF RESPIRATION AND HEARTBEAT USING A FLEXIBLE TACTILE SENSOR SHEET ON A BED

We describe a measurement method of respiration and heartbeat using a Smart Rubber sensor, a rubber-based flexible tactile sensor sheet that we developed. This method is useful for unconstrained recording of a person sleeping soundly, sleeping lightly, lying down, sitting on a bed, and so on. Our goal is to monitor those who require nursing care. The proposed method measures respiration and heartbeat as follows. First, we measure body pressure by using the Smart Rubber sensor placed on a bed. Then, the method applies a frequency analysis to the time series data of body pressure. Finally, respiration and heartbeat are obtained by extracting suitable frequency bands. In the experiments, we show that respiration and heartbeat are successfully measured.

Probabilistic Prediction of Chaotic Time Series Using Similarity of Attractors and LOOCV Predictable Horizons for Obtaining Plausible Predictions

This paper presents a method for probabilistic prediction of chaotic time series. So far, we have developed several model selection methods for chaotic time series prediction, but the methods cannot estimate the predictable horizon of predicted time series. Instead of using model selection methods employing the estimation of mean square prediction error (MSE), we present a method to obtain a probabilistic prediction which provides a prediction of time series and the estimation of predictable horizon. The method obtains a set of plausible predictions by means of using the similarity of attractors of training time series and the time series predicted by a number of learning machines with different parameter values, and then obtains a smaller set of more plausible predictions with longer predictable horizons estimated by LOOCV (leave-one-out cross-validation) method. The effectiveness and the properties of the present method are shown by means of analyzing the result of numerical experiments.

Performance improvement via bagging in probabilistic prediction of chaotic time series using similarity of attractors and LOOCV predictable horizon

Recently, we have presented a method of probabilistic prediction of chaotic time series. The method employs learning machines involving strong learners capable of making predictions with desirably long predictable horizons, where, however, usual ensemble mean for making representative prediction is not effective when there are predictions with shorter predictable horizons. Thus, the method selects a representative prediction from the predictions generated by a number of learning machines involving strong learners as follows: first, it obtains plausible predictions holding large similarity of attractors with the training time series and then selects the representative prediction with the largest predictable horizon estimated via LOOCV (leave-one-out cross-validation). The method is also capable of providing average and/or safe estimation of predictable horizon of the representative prediction. We have used CAN2s (competitive associative nets) for learning piecewise linear approximation of nonlinear function as strong learners in our previous study, and this paper employs bagging (bootstrap aggregating) to improve the performance, which enables us to analyze the validity and the effectiveness of the method.

Speaker Detection in Audio Stream via Probabilistic Prediction Using Generalized GEBI

This paper presents a method of speaker detection using probabilistic prediction for avoiding the tuning of thresholds to detect a speaker in an audio stream. We introduce g-GEBI (generalized GEBI) as a generalization of BI (Bayesian Inference) and GEBI (Gibbs-distribution-based Extended BI) to execute iterative detection of a speaker in audio stream uttered by more than one speaker. Then, we show a method of probabilistic prediction in multiclass classification to classify the results of speaker detection. By means of numerical experiments using recorded real speech data, we examine the properties and the effectiveness of the present method. Especially, we show that g-GEBI and g-BI (generalized BI) are more effective than the conventional BI and GEBI in incremental speaker detection task.

Entropy Maximization of Occupancy Grid Map for Selecting Good Registration of SLAM Algorithms

This paper analyzes entropy of occupancy grid map (OGM) for evaluating registration performance of SLAM (simultaneous localization and mapping) algorithms. So far, there are a number of SLAM algorithms having been proposed, but we do not have general measure to evaluate the registration performance of point clouds obtained by LRF (laser range finder) for SLAM algorithms. This paper analyzes to show that good registration seems corresponding to large overlap of point clouds in OGM as well as large entropy, large uncertainty and low information of OGM. This analysis indicates a method of entropy maximization of OGM for selecting good registration of SLAM algorithms. By means of executing numerical experiments, we show the validity and the effectiveness of the entropy of OGM to evaluate the registration performance.

Probabilistic Prediction for Text-Prompted Speaker Verification Capable of Accepting Spoken Words with the Same Meaning but Different Pronunciations

So far, we have presented a method of probabilistic prediction using GEBI (Gibbs-distribution based Bayesian inference) for flexible text-prompted speaker verification. For more flexible and practical verification, this paper presents a method of verification capable of accepting spoken words with the same meaning but different pronunciations. For example, Japanese language has different pronunciations for a digit, such as /yon/ and /shi/ for 4, /nana/ and /shichi/ for 7, which are usually uttered via unintentional selection, and then it is a practical problem in speech verification of words involving digits, such as ID numbers. With several assumptions, we present a modification of GEBI for dealing with such words. By means of numerical experiments using recorded real speech data, we examine the properties of the present method and show the validity and the effectiveness.

LYING POSTURE DETECTION FOR UNCONSTRAINED MEASUREMENT OF RESPIRATION AND HEARTBEAT ON A BED

Daily monitoring of respiration and heartbeat while sleeping provides basic data for the assessment of personal health and early detection of diseases. The monitoring should not interfere with natural sleep, and it is desirable that the sensor be imperceptible to the person being measured. We propose a method for non-invasive and unconstrained measurement of the lying posture, respiration and heartbeat of a person on a rubber-based tactile sensor sheet. The tactile sensor is soft, flexible, and thin, and is not uncomfortable for the person lying on it. To extract faint heartbeat signals from pressure changes detected by the sensor, precision measurement based on improvement of the S/N ratio by averaging oversampled data is needed. This process takes some time and can be performed at only a limited number of locations on the sensor. To determine the locations, we detect the lying location and posture of the measured personon thesensor by usingpatternrecognition based on machine learning. In this paper, we describe the measurement method and report the experimental results.