In anesthesia automation, one of the main important issues is the availability of a reliable measurement of the depth of consciousness level (hypnosis) of the patient. According to this value, the hypnotic drug dosage can be adequately calculated. One of the most studied hypnosis indexes is the bispectral index (BIS). In this article we analyzed an alternative called patient state index (PSI). The objectives of this study are, first, to validate the accuracy of the PSI describing the hypnosis level during the maintenance phase of general anesthesia, by comparing with the BIS and, second, to model the relationship between propofol infusion rate and PSI values, obtained from a SEDLine monitor. For this, real data from patients undergoing general anesthesia simultaneously monitored with both BIS and PSI signals was used. Results obtained are interesting for a correct interpretation of PSI signal in clinical practice.

No abstract

The Indian stock market is experiencing fast growth and has peculiarities that differentiate it from many other stock markets, particularly those in developed markets. Given the potential size of this stock market and the growing importance of the Indian economy it seemed reasonable to look at what tools provide reasonably accurately stock prices forecast. It is of clear practical and theoretical relevance to determine which type of algorithm to use in order to try to forecast stock market trends. In recent times there has been an increasing interest in applying neural networks to such aim. In this article it is shown that a neural network using as an input the closing price in the previous day and two different learning algorithms produce accurate forecast. This simple but efficient approach generated a one day forecasting accuracy, measured as the mean value of 2 , of [0.9952, 0.9972] for the Levenberg-Marquardt training algorithm and [0.9965, 0.9970] for the Scaled Conjugate learning algorithm. These results were obtained using only 10 neurons in the neural network. Increasing the number of neurons to 500 did not improve the out of sample forecasting accuracy. It actually decreased, for both algorithms. It would seem that at least for the period of time analyzed, from 2010 to 2016, neural networks did a reasonably good job forecasting stock prices.