Kohei Yamamoto 교수

BackgroundIn 1974, the Acoustical Society of Japan first organizes a research committee to develop a road traffic noise prediction model.This committee has been undertaking research activities since then.As a result of its activities, a prediction model called ASJ Model 1975 was published in 1975, which provided a method of calculating the 50 percentile A-weighted sound pressure level (L A50 ) [1,2].This model was widely accepted and applied to assessments of noise around roads for many years.Af

An Electrocardiogram (ECG) is a typical method used to detect heartbeat, and an ECG signal analysis enables the detection of some heart diseases. However, the ECG-based heartbeat detection requires device attachment, which is not preferred for daily use. A Doppler sensor could be a device used to enable the non-contact heartbeat detection. In this paper, we propose a Doppler sensor-based ECG signal reconstruction method by a hybrid deep learning model with Convolutional Neural Network (CNN) and

Quantizing deep neural networks is an effective method for reducing memory consumption and improving inference speed, and is thus useful for implementation in resource-constrained devices. However, it is still hard for extremely low-bit models to achieve accuracy comparable with that of full-precision models. To address this issue, we propose learnable companding quantization (LCQ) as a novel non-uniform quantization method for 2-, 3-, and 4-bit models. LCQ jointly optimizes model weights and le

Demands for vital sign monitoring are increasing in the field of health care. In particular, the R-R Interval (RRI) estimation has been studied extensively, since the RRI variation is highly related with the stress of a subject. Various Doppler sensor-based-heartbeat detection methods have been proposed so far, thanks to non-contact and non-invasive features of a Doppler sensor. In our previous research, we have proposed a Doppler sensor-based RRI estimation method by a spectrogram. In this meth

Compression techniques for deep neural networks are important for implementing them on small embedded devices. In particular, channel-pruning is a useful technique for realizing compact networks. However, many conventional methods require manual setting of compression ratios in each layer. It is difficult to analyze the relationships between all layers, especially for deeper models. To address these issues, we propose a simple channel-pruning technique based on attention statistics that enables

Heartbeat detection is one of key techniques to monitor our health condition in daily life, and demands for this technique have increased year and year. Thanks to the non-contact and non-invasive features, various Doppler sensor-based detection methods have been investigated so far. However, the heartbeat detection accuracy of the conventional methods could get degraded due to the low SNR (Signal-to-Noise Ratio) of heartbeat components. Thus, even after some signal processing, non-heartbeat comp

Sound propagation over ground from a point source having a typical spectrum of motor vehicle noise was investigated by a computational study using theoretical models. Employing new parameters of an average propagation height and a classified resistivity of ground surface, a practical expression to estimate A-weighted excess attenuation was obtained with some charts for various source and receiver locations. Results of field and scale model experiment show a good agreement with the values estimat

Blink duration is one of the useful indicators to estimate drowsiness and fatigue. A Doppler sensor could be a key device to realize the non-contact blink duration estimation, which is very useful for the drowsiness and fatigue monitoring in real life. However, none of the blink duration estimation methods has been proposed so far. In this paper, we propose a novel Doppler sensor-based blink duration estimation method based on the analysis of eyelids closing and opening behavior on a spectrogram

Heartbeat detection are receiving a lot of attention in the field of health care, since cardiac activity reflects various information of a subject, e.g., the stress. Many Doppler sensor-based heartbeat detection methods have been proposed so far. As one of such methods, the MUSIC (MUltiple SIgnal Classification)-based HR (Heart Rate) estimation method has been proposed. However, the conventional MUSIC-based HR estimation method not only needs a long time window, but also requires to know the num

The authors proposed a propagation model for ground effect of vehicle noise. Since it was given by a simple formula and related charts, rough estimation of vehicle noise level at a road side could be made without any precise computation.

Respiration is known to reflect our health condition, which motivates researchers to develop various radar-based respiration rate estimation methods. However, these conventional methods do not work, when a subject is not right in front of the radar. In this paper, we propose a novel CNN (Convolutional Neural Network)-based respiration rate estimation method in indoor environments via a MIMO (Multiple-Input Multiple-Output) FMCW (Frequency Modulated Continuous Wave) radar. A MIMO FMCW radar can e