Toshiya Arakawa

Automated Estimation of Mouse Social Behaviors Based on a Hidden Markov Model

Recent innovations in sensing and Information and Communication Technology (ICT) have enabled researchers in animal behavior to collect an enormous amount of data. Consequently, the development of an automated system to substitute for some of the observations and analyses that are performed currently by expert researchers is becoming a crucial issue so that the vast amount of accumulated data can be processed efficiently. For this purpose, we introduce a process for the automated classification of the social interactive status of two mice in a square field on the basis of a Hidden Markov model (HMM). We developed two models: one for the classification of two states, namely, indifference and interaction, and the other for three states, namely, indifference, sniffing, and following. The HMM was trained with data from 50 pairs of mice as provided by expert human observers. We measured the performance of the HMM by determining its rate of concordance with human observation. We found that sniffing behavior was segmented well by the HMM; however, following behavior was not segmented well by the HMM in terms of percentage concordance. We also developed software called DuoMouse, an automated system for the classification of social interactive behavior of mice, that was based on the HMM. Finally, we compared two implementations of the HMM that were based on a histogram and a Gaussian mixture model.

Video tracking analysis of behavioral patterns during estrus in goats

Here, we report a new method for measuring behavioral patterns during estrus in goats based on video tracking analysis. Data were collected from cycling goats, which were in estrus (n = 8) or not in estrus (n = 8). An observation pen (2.5 m × 2.5 m) was set up in the corner of the female paddock with one side adjacent to a male paddock. The positions and movements of goats were tracked every 0.5 sec for 10 min by using a video tracking software, and the trajectory data were used for the analysis. There were no significant differences in the durations of standing and walking or the total length of movement. However, the number of approaches to a male and the duration of staying near the male were higher in goats in estrus than in goats not in estrus. The proposed evaluation method may be suitable for detailed monitoring of behavioral changes during estrus in goats.

Recent Research and Developing Trends of Wearable Sensors for Detecting Blood Pressure

Blood pressure is considered an index to measure a person’s health or state. The IEEE published a standard for wearable cuffless blood pressure measuring devices, which was certified as IEEE1708 on 26 August 2014, and, according to this standard, the development of wearable devices based on blood pressure is expected in the future. Considering this, blood pressure should be detectable all the time and everywhere, and this can help improve health consciousness. In this review, we introduce the recent development of wearable blood pressure measuring devices and research trends, and present the future prospects for blood pressure measuring devices.

Probability of driver's state detection based on systolic blood pressure

We attempted to detect a typical drivers surprised state based on blood pressure using a driving simulator. The results show that the drivers systolic blood pressure after a child and a bicycle rushed out on the road is higher than that before child and bicycle rushed out, and these two data are statistically significant. This means that the systolic blood pressure became high when the bicycle rushed out, thus suggesting that the feeling of “traffic near-miss” (surprised) can be detected via blood pressure. In addition that, systolic blood pressure is more adequate index to detect drivers surprised state than LF/HF, which is generally used to detect or estimate drivers surprised state.