Mototaka Yoshioka

Travel destination prediction using frequent crossing pattern from driving history

The modeling of user behavior patterns for personalized information services in mobile environments has recently become a popular research theme. Most of the research aims at predicting the users future behavior (and/or location) by extracting frequent patterns from the history of location data sequences. However, sometimes user behavior changes according to the external information such as date, time, weather, etc., and we cannot accurately predict it based on the location data sequences alone. In this paper, we propose a new travel destination prediction method including day and time as external information. First, the users travel history information including the location, date and time is stored. Then, from the external information, time/day categories that have correlation to the users destination based on entropy are determined. Finally, using the categories, a destination that depends on the external information can be successfully predicted. An application of the method to data collected from a car navigation system showed possibility for an improved performance comparing to the conventional methods. Higher destination prediction accuracy during the first several minutes after users departure was reported.

Feature-Based Correlation and Topological Similarity for Interbeat Interval Estimation Using Ultrawideband Radar

The objectives of this paper are to propose a method that can accurately estimate the human heart rate (HR) using an ultrawideband (UWB) radar system, and to determine the performance of the proposed method through measurements. The proposed method uses the feature points of a radar signal to estimate the HR efficiently and accurately. Fourier- and periodicity-based methods are inappropriate for estimation of instantaneous HRs in real time because heartbeat waveforms are highly variable, even within the beat-to-beat interval. We define six radar waveform features that enable correlation processing to be performed quickly and accurately. In addition, we propose a feature topology signal that is generated from a feature sequence without using amplitude information. This feature topology signal is used to find unreliable feature points, and thus, to suppress inaccurate HR estimates. Measurements were taken using UWB radar, while simultaneously performing electrocardiography measurements in an experiment that was conducted on nine participants. The proposed method achieved an average root-mean-square error in the interbeat interval of 7.17 ms for the nine participants. The results demonstrate the effectiveness and accuracy of the proposed method. The significance of this study for biomedical research is that the proposed method will be useful in the realization of a remote vital signs monitoring system that enables accurate estimation of HR variability, which has been used in various clinical settings for the treatment of conditions such as diabetes and arterial hypertension.

Accurate heartbeat monitoring using ultra-wideband radar

We demonstrate an accurate remote measurement of heartbeats using an ultra-wideband radar system. Although most conventional systems use either continuous waves or impulse-radio systems for remote vital monitoring, continuous waves suffer from non-stationary clutters, while impulse-radio systems cannot detect heartbeats. Our ultra-wideband radar system has a moderate fractional bandwidth intermediate of these systems, resulting in both the suppression of clutters and high sensitivity in measuring accurate heart rates even in a dynamic environment. A simultaneous measurement of the vital signal of a participant employing the ultra-wideband radar and electrocardiography reveals the high accuracy of the radar system in measuring the heart rate varying over time.

Remote heartbeat monitoring from human soles using 60-GHz ultra-wideband radar

Measurement of heartbeats is essential in cardiovascular magnetic resonance imaging because the measurement must be synchronized with the phase of cardiac cycles. Many existing studies on radar-based heartbeat monitoring have focused on echoes from the torso only, and such monitoring cannot be applied to subjects in magnetic resonance scanners because only the head and soles can be seen from the outside. In this study, we demonstrate the feasibility of the remote monitoring of heartbeats from the subject’s soles using a 60-GHz ultra-wideband radar. The heartbeat intervals measured using the radar are quantitatively compared with those measured using conventional electrocardiography.

Ultrawideband Radar Imaging Using Adaptive Array and Doppler Separation

Ultrawideband Doppler radar interferometry is known as an effective method that enables high-resolution imaging when using a simple antenna array. The technique, however, suffers from image artifacts when multiple moving targets with the similar Doppler velocities are present in the same range bin. To resolve this problem, we combine the Doppler interferometry technique with the Capon methods. Through numerical simulations and experiments, we show the remarkable performance improvement achieved by the proposed method.

Improved human pulse peak estimation using derivative features for noncontact pulse transit time measurements

This paper proposes a method to estimate temporally accurate human pulse peaks for noncontact pulse transit time (PTT) measurements. The PTT is considered as a significant diagnostic index for conditions such as blood pressure and arterial stiffness; however, millisecond-order accuracy is required in the determination of each pulse peak. In this study, human pulse waveforms are obtained from wrist and ankle images taken using a webcam at 90 cm distance. In the proposed method, the waveform is smoothed using finite impulse response low-pass filtering that sustains the shape of the pulse waveform, and the phase delay is compensated. Then, features of the first-order derivative of the filtered waveform are used to estimate the pulse peaks. The interbeat intervals obtained from the peaks estimated by the proposed method closely coincided with those obtained from a contact-type photoplethysmogram sensor, yielding less absolute error than that obtained from a comparative method; thus, this confirms the improved temporal accuracy of the proposed method. The PTTs are calculated from the time differences between the estimated pulse peaks of the wrist and those of the ankle images. The benefit of accurate pulse peak estimation is demonstrated by investigating the relation between the PTT and blood pressure. The PTTs are correlated with blood pressure in ten human participants, and a high correlation coefficient of -0.88 was obtained, indicating a direct relation between these two measures.

Non-contact pulse transit time measurement using imaging camera, and its relation to blood pressure

This study reports pulse transit time (PTT) measurements of two areas of the human body (wrist and ankle) by a single imaging camera. The pulse peaks at both areas were extracted by finite impulse response (FIR) low-pass filtering and phase delay compensation. The interbeat intervals (IBIs) obtained by the camera and a photoplethysmogram sensor were almost identical, confirming the temporal accuracy of the camera-obtained peaks, and suggesting the utility of the camera in noncontact PTT measurements. Next, the PTTs were calculated from the time differences between the pulse peaks of the wrist and ankle images, and correlated with vital parameters such as blood pressure and age in ten subjects. A high correlation coefficient of (-0.88) was obtained between PTT and blood pressure, indicating a direct relationship between these two measures.

Brain signal pattern of engrossed subjects using near infrared spectroscopy (NIRS) and its application to TV commercial evaluation

In this paper, we present near infrared spectroscopy (NIRS) signal patterns of subjects when they are focused on specific tasks. We determined that oxygenated hemoglobin in the frontal cortex decreased when the subjects were engrossed in tasks, and we propose an evaluation method for TV commercials based on the results. TV commercials are produced to be as attractive as possible and can increase consumer awareness of a particular product or its features. Our idea is based on the assumption that the attractiveness of a commercial can be estimated by the extent of decrease in oxygenated hemoglobin using NIRS, and the consumers awareness of the products features in TV commercials can be measured by analyzing the subjects glancing regions using an eye-tracking system. We obtained good agreement between the correlation of awareness and focus, and the possibility of estimating these parameters using NIRS is suggested.

Monitoring of a driver's heart rate using a microwave sensor and template-matching algorithm

A method of monitoring a drivers heart rate using a microwave sensor on a seat backrest is proposed. The heartbeat signal was learned as a template while the car engine idled. This template was used to calculate correlation between observed signals. The proposed method amplifies a weak heartbeat signal and reduces road noise. A basic experiment was conducted on an actual road at low speed. The proposed method detected the heart rate with accuracy exceeding 90% relative to heart rates measured with a contact-based system.

A new approach for non-contact pulse transit time measurement using microwave and image sensors

This study proposes a new approach for non-contact based pulse transit time (PTT) measurement using microwave and image sensors. The microwave sensor detects heartbeats using reflected wave signal from a subjects chest, and the image sensor obtains pulse-arrival times using a subjects face image sequences. By temporally synchronizing these sensors, the proposed system calculates the time difference between a heartbeat and a pulse, thus allowing PTT to be remotely obtained. Using basic experiments conducted on six independent subjects, we were able to physically measure PTT (around 180 ms). Our results strongly indicated the potential viability for widespread use of the proposed method for non-contact-based PTT measurement.