The present paper proposes a new probabilistic neural network (NN) that can estimate a posteriori probability for a pattern classification problem. The structure of the proposed network is based on a statistical model composed by a mixture of log-linearized Gaussian components. However, the forward calculation and the backward learning rule can be defined in the same manner as the error backpropagation NN. In this paper, the proposed network is applied to the electroencephalogram (EEG) pattern classification problem. In the experiments, two types of a photic stimulation, which are caused by eye opening/closing and artificial light, are used to collect the data to be classified. It is shown that the EEG signals can be classified successfully and that the classification rates change depending on the number of training data and the dimension of the feature vectors.
It has frequently been demonstrated that prior heavy cycling exercise facilitates pulmonarẏ VO 2 kinetics at the onset of subsequent heavy exercise. This might be due to improved muscle perfusion via acidosis-induced vasodilating effects. However, it is difficult to measure the blood flow (BF) to the working muscles (via the femoral artery) during cycling exercise. We therefore selected supine knee extension (KE) exercise as an alternative, and investigated whether the fasterVO 2 kinetics in the 2nd bout was matched by proportionally faster BF kinetics to the exercising muscle. Nine healthy subjects (aged 21-44 years) volunteered to participate in this study. The protocol consisted of two consecutive 6-min KE exercise bouts in a supine position (work rate: 70-75% of peak power) separated by a 6-min baseline rest (EX1 to EX2). During the protocol, a pulsed Doppler ultrasound technique was utilized to continuously measure the BF in the right femoral artery. The protocol was repeated at least 6 times to characterize the precise kinetics. In agreement with previous studies using cycling exercise, theVO 2 kinetics in the 2nd bout were facilitated compared with that in the 1st bout [mean ± S.D. of the 'effective' time constant (τ ): EX1, 68.6 ± 15.9, versus EX2, 58.0 ± 14.4 s. Phase II-τ : EX1, 48.7 ± 9.0, versus EX2, 41.2 ± 13.3 s. Empirical index of the slow component (∆VO 2(6-3) ): EX1, 78 ± 44, versus EX2, 57 ± 36 ml min −1 (P < 0.05)]. However, no substantial difference was observed for the facilitation of the femoral artery BF response to the 1st and 2nd exercise bouts [i.e. the 'effective' τ of the femoral artery BF: EX1, 40.8 ± 16.9, versus EX2, 39.0 ± 17.1 s (P > 0.05)]. It was concluded that the faster pulmonaryVO 2 kinetics during heavy KE exercise following prior heavy exercise was not associated with a similar modulation in the BF to the working muscles.
Abstractc‐Axis oriented aluminum nitride (AlN) thin films are successfully prepared on amorphous polyimide films by radiofrequency magnetron reactive sputtering at room temperature. Structural analysis shows that the AlN films have a wurtzite structure and consist of c‐axis oriented columnar grains about 100 nm wide. The full width at half maximum of the X‐ray diffraction rocking curves and piezoelectric coefficient d33 of the AlN films are 8.3° and 0.56 pC N–1, respectively. The AlN films exhibit a piezoelectric response over a wide temperature range, from –196 to 300 °C, and can measure pressure within a wide range, from pulse waves of hundreds of pascals to 40 MPa. Moreover, the sensitivity of the AlN films increases with the number of times it was folded, suggesting that we can control the sensitivity of the AlN films by changing the geometric form. These results were achieved by a combination of preparing the oriented AlN thin films on polyimide films, and sandwiching the AlN and polymer films between top and bottom electrodes, such as Pt/AlN/polyimide/Pt. They are thin (less than 10 μm), self powered, adaptable to complex contours, and available in a variety of configurations. Although AlN is a piezoelectric ceramic, the AlN films are flexible and excellent in mechanical shock resistance.
Cardio-respiratory monitoring during sleep is one of the basic means for assessment of personal health, and has been widely used in diagnosis of sleep disorders. This paper proposes a novel method for non-invasive and unconstrained measurement of respiration and heartbeat during sleep. A flexible piezoelectric film sensor made of aluminum nitride (AlN) material is used in this study. This sensor measures pressure fluctuation due to respiration and heartbeat on the contact surface when a subject is lying on it. Since the AlN film sensor has good sensitivity, the pressure fluctuation measured can be further separated into signals corresponding to respiration and heartbeat, respectively. In the proposed method, the signal separation is achieved using an algorithm based on empirical mode decomposition (EMD). Experiments have been conducted with three subjects. The experimental results show that respiration and heartbeat signals can be successfully obtained with the proposed method.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.