Respiratory Inductance Plethysmography (RIP) is commonly used to detect the respiratory motions of chest and abdomen during sleep. However, this method is not suitable for daily use due to its strong constraints. Many unconstrained methods have been developed but they have a common problem in distinguishing the chest and abdominal motions, which are required for understanding the type of sleep apnea. In this study, we proposed an unconstrained method to distinguish chest and abdominal motions by measuring the pressure fluctuations from the chest and abdomen acting on a mattress. We then investigated the feasibility of detecting respiratory motions by using a flexible tactile sensor array, which was laid on a bed like a bed sheet. Ten healthy subjects (five males and five females) were tested and the results were compared with those measured with RIP band sensors. It was confirmed that the sensor array could measure the motions of the chest and abdomen and obtain the respiratory rate at a high precision. However, the phase of the pressure fluctuations measured with the sensor array might disagree with the outputs of the RIP band sensors, depending on the gender and lying position of the subject. The reason was discussed with a dynamic model, which showed that the disagreement might have been related to the coupling of the chest and abdomen. In addition, the influence of the stiffness of the mattress on the pressure fluctuations was investigated. The results showed that mattress stiffness had little effect on the measurement.

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.

In model-based methods of reinforcement learning (RL), the probabilistic inference for learning control (PILCO) algorithm, which relies on Gaussian process (GP) for building probabilistic dynamics models, requires only a small amount of data, and can learn from scratch in a few trials by using a probabilistic dynamics model, it explicitly incorporating model uncertainty into long-term planning. However, the time complexity of the GP, which is cubic with respect to the number of trials, makes it challenging to scale the framework to high-dimensional observation spaces. Moreover, the cost function of a task is limited as a locally quadratic function for calculating the policy gradient analytically. To solve these problems, we proposed a probabilistic neural network (PNN) to replace the GP when building the probabilistic dynamics models and develop a deterministic control policy by using long-term predictions. In particular, we determined model uncertainty through basic prior knowledge and calculated cumulative cost by sampling from state distributions. This approach can help reduce the influence of model error and time consumption. Compared with state-of-the-art model-based RL, the proposed approach can reconcile data efficiency and speed of learning even in high-dimensional observation spaces.

During laparoscopic surgeries, changing forceps is a relatively simple procedure that requires a nurse or another surgeon; however, most hospitals lack a scrub nurse in the operating room. Therefor...