Tracking the states of a nonlinear and nonstationary system in the weight-space of artificial neural networks

We propose a novel interpretation and usage of Neural Network (NN) in modeling physiological signals, which are allowed to be nonlinear and/or nonstationary. The method consists of training a NN for the k-step prediction of a physiological signal, and then examining the connection-weight-space (CWS) of the NN to extract information about the signal generator mechanism. We de. ne a novel feature, Normalized Vector Separation (gamma(ij)), to measure the separation of two arbitrary states i and j in the CWS and use it to track the state changes of the generating system. The performance of the method is examined via synthetic signals and clinical EEG. Synthetic data indicates that gamma(ij) can track the system down to a SNR of 3.5 dB. Clinical data obtained from three patients undergoing carotid endarterectomy of the brain showed that EEG could be modeled (within a root-means-squared-error of 0.01) by the proposed method, and the blood perfusion state of the brain could be monitored via gamma(ij), with small NNs having no more than 21 connection weight altogether.

Effect of mutual coupling on the interference rejection capabilities of linear and circular arrays in CDMA systems

This paper is concerned with assessing the interference rejection capabilities of linear and circular array of dipoles that can be part of a base station of a code-division multiple-access cellular communication system. The performance criteria for signal-to-interference ratio (SIR) improvement employed in this paper is the spatial interference suppression coefficient. We first derive an expression for this figure of merit and then analyze and compare the SIR performance of the two types of arrays. For a linear array, we quantitatively assess the degradation in SIR performance, as we move from array broadside to array end-fire direction. In addition, the effect of mutual coupling is taken into account.

Skeletal muscle mitochondrial ATP production rate and walking performance in peripheral arterial disease

This study tested the hypotheses that skeletal muscle mitochondrial ATP production rate (MAPR) is impaired in patients with peripheral arterial disease (PAD) and that it relates positively to their walking performances. Seven untrained patients, eight exercise-trained patients and 11 healthy controls completed a maximal walking test and had muscle sampled from the gastrocnemius medialis muscle. Muscle was analysed for its MAPR in the presence of pyruvate, palmitoyl-L-carnitine or both, as well as citrate synthase (CS) activity. MAPRs were not different between untrained PAD and controls. In contrast, MAPRs (pyruvate) were significantly higher in trained PAD vs. controls. MAPR (pyruvate combinations) was also significantly higher in trained than untrained PAD muscle. MAPR and CS activity were highly correlated with walking performance in patients, but not in controls. These data do not support the hypothesis that isolated mitochondria are functionally impaired in PAD and demonstrate that the muscle mitochondrial capacity to oxidize carbohydrate is positively related to walking performance in these patients.