We have developed a noninvasive pneumatics-based system by which to measure heartbeat, respiration, snoring, and body movements of a subject in bed. A thin, air-sealed cushion is placed under the bed mattress of the subject and the small movements attributable to human automatic vital functions are measured as changes in pressure using a pressure sensor having an almost flat frequency response from 0.1 to 5 kHz and a sensitivity of 56 mV/Pa. Using the newly developed system, heartbeat, respiration, apnea, snoring and body movements are clearly measured. In addition, the optimal signal-to-noise (S/N) ratio by which to evaluate the reliability of the heart rate measurement is presented. Heart rates were measured for four different body postures, 13 different subjects, four different bed mattresses, and three different sensor positions. For these measurements, the S/N ratios ranged from 15.9 to 23.5 dB, and so were determined to be reliable.

Gait analysis is a valuable tool for obtaining quantitative information on motor deficits in Parkinson's disease (PD). Since the characteristic gait patterns of PD patients may not be fully identified by brief examination in a clinic, long-term, and unobtrusive monitoring of their activities is essential, especially in a nonclinical setting. This paper describes a single accelerometer-based gait analysis system for the assessment of ambulatory gait properties. Acceleration data were recorded continuously for up to 24 h from normal and PD subjects, from which gait peaks were picked out and the relationship between gait cycle and vertical gait acceleration was evaluated. By fitting a model equation to the relationships, a quantitative index was obtained for characterizing the subjects' walking behavior. The averaged index for PD patients with gait disorder was statistically smaller than the value for normal subjects. The proposed method could be used to evaluate daily gait characteristics and thus contribute to a more refined diagnosis and treatment of the disease.

Gait analysis is widely recognized as a promising tool for obtaining objective information on the walking behavior of Parkinson's disease (PD) patients. It is especially useful in clinical practices if gait properties can be captured with minimal instrumentation that does not interfere with the subject's usual behavioral pattern under ambulatory conditions. In this study, we propose a new gait analysis system based on a trunk-mounted acceleration sensor and automatic gait detection algorithm. The algorithm identifies the acceleration signal with high intensity, periodicity, and biphasicity as a possible gait sequence, from which gait peaks due to stride events are extracted by utilizing the cross-correlation and anisotropy properties of the signal. A total of 11 healthy subjects and 12 PD patients were tested to evaluate the performance of the algorithm. The result indicates that gait peaks can be detected with an accuracy of more than 94%. The proposed method may serve as a practical component in the accelerometry-based assessment of daily gait characteristics.

Artificial neural networks have capacity to learn and store information about process faults via associative memory, and thus have an associative diagnostic ability with respect to faults that occur in a process. Knowledge of the faults to be learned by the network evolves from sets of data, namely values of steady-state process variables collected under normal operating condition and those collected under faulty conditions, together with information about the degree of the faults and their causes.Here, we describe how to apply artificial neural networks to fault diagnosis. A suitable two-stage multilayer neural network is proposed as the network to be used for diagnosis. The first stage of the network discriminates between the causes of faults when fed the noisy process measurements. Once the fault is identified, the second stage of the network estimates the degree of the fault. Thus, the diagnosis of incipient faults becomes possible.

This paper describes a novel method to estimate sleep stage through noninvasive and unrestrained means. The Rechtschaffen and Kales (R-K) method is a standard to estimate sleep stage. However, it involves restraining the examinee and, thus, induces psychological stress. Furthermore, it requires specialists with a high degree of technical expertise and the use of an expensive polygraph. The sleep estimation method presented here is based on the noninvasive and unrestrained pneumatic biomeasurement method presented by the authors. Sleep stage transition in overnight sleep and the relationship between sleep stage and biosignals measured using the pneumatic method was analyzed and from the results, a mathematical model of sleep was created. Based on this model, a sleep stage estimator, including a sleep stage classifier and observer, was designed. The sleep state transition equation was the basis for the design of this observer, while the observed relationships were the basis for designing a classifier. Agreement of the estimated sleep stages with those obtained using the R-K method for the non-REM stage was 82.6%, for the REM stage was 38.3 % and for Wake was 70.5 %, including disagreement. However, the new method might ultimately result in better estimation of sleep stage due to the fact that it does not physically restrain the patient and does not induce psychological stress.