: This thesis applies neural network feature selection techniques to multivariate time series data to improve prediction of a target time series. Two approaches to feature selection are used. First, a subset enumeration method is used to determine which financial indicators are most useful for aiding in prediction of the S&P 500 futures daily price. The candidate indicators evaluated include RSI, Stochastics and several moving averages. Results indicate that the Stochastics and RSI indicators result in better prediction results than the moving averages. The second approach to feature selection is calculation of individual saliency metrics. A new decision boundary-based individual saliency metric, and a classifier independent saliency metric are developed and tested. Ruck's saliency metric, the decision boundary based saliency metric, and the classifier independent saliency metric are compared for a data set consisting of the RSI and Stochastics indicators as well as delayed closing price values. The decision based metric and the Ruck metric results are similar, but the classifier independent metric agrees with neither of the other metrics. The nine most salient features, determined by the decision boundary based metric, are used to train a neural network and the results are presented and compared to other published results. (AN)

/pdf/nonlinear-time-series-analysis-1j3a35n4y3.pdf

Nonlinear Time Series Analysis.

Cours d'economie politique

THE human brain is the instrument of the high powers of intelligence that distinguish man from all other living creatures. The secret of man's most distinctive attribute is hidden in the texture of his brain, and perhaps will never be fully revealed. Yet from time to time, with the growth of knowledge and the discovery of new methods of approach, we can profitably return to this greatest of all biological problems and get new glimpses of the factors that have made man what he is. Two considerations make the present time appropriate for taking stock of the state of our knowledge of these matters. The emergence of a clearer understanding of the sequence of structural changes in the brain and body of man's ancestors enables us to interpret the physiological factors involved in the widening and deepening of the intellectual powers and to appreciate the conditions essential for the attainment of-such mental growth. In the second place, the new points of view regarding the functions of the cerebral cortex that have emerged from Dr. Henry Head's suggestive clinical investigations prompt one to examine the brain anew and endeavour to integrate the results of his brilliant analysis with those revealed in the study of the evolution of the brain. Whether or not it is yet possible fully to correlate the facts and conclusions of these two disciplines into one coherent body of doctrine, it is well worth while to make the attempt to do so, if for no other reason than to direct attention to new problems that call for solution.

The Human Brain

The statistical mechanics of financial markets

We perform an analysis of cardiac data using multiscale entropy as proposed in Costa et al. [Multiscale entropy analysis of complex physiological time series, Phys. Rev. Lett. 89 (2002) 068102]. We reproduce the signatures of the multiscale entropy for the three cases of young healthy hearts, atrial fibrillation and congestive heart failure. We show that one has to be cautious how to interpret these signatures in terms of the underlying dynamics. In particular, we show that different dynamical systems can exhibit the same signatures depending on the sampling time, and that similar systems may have different signatures depending on the time scales involved. Besides the total amount of data we identify the sampling time, the correlation time and the period of possible nonlinear oscillations as important time scales which have to be involved in a detailed analysis of the signatures of multiscale entropies. We illustrate our ideas with the Lorenz equation as a simple deterministic chaotic system.

https://www.maths.usyd.edu.au/u/gottwald/preprints/MultiscaleEntropy.pdf

On multiscale entropy analysis for physiological data

The study compared traditional spectral analysis and a new scale-invariant method, the analysis of the length distribution of low-variability periods (LDLVPs), to distinguish between electro-encephalogram (EEG) signals with and without a weak stressor, a low-level modulated microwave field. During the experiment, 23 healthy volunteers were exposed to a microwave (450 MHz) of 7 Hz frequency on-off modulation. The field power density at the scalp was 0.16 mW cm(-2). The experimental protocol consisted of ten cycles of repetitive microwave exposure. Signals from frontal EEG channels FP1 and FP2 were analysed. Smooth power spectrum and length distribution curves of low-variability periods, as well as probability distribution close to normal, confirmed that stationarity of the EEG signal during recordings was achieved. The quantitative measure of LDLVPs provided a significant detection of the effect of the stressor for the six subjects exposed to the microwave field but for none of the sham recordings. The spectral analysis revealed a significant result for one subject only. A significant effect of the exposure to the EEG signal was detected in 25% of subjects, with microwave exposure increasing EEG variability. The effect was not detectable by power spectral measures.

Non-linear analysis of the electroencephalogram for detecting effects of low-level electromagnetic fields.

It is shown that the distribution of low variability periods in the activity of human heart rate typically follows a multi-scaling Zipf's law. The presence or failure of a power law, as well as the values of the scaling exponents, are personal characteristics depending on the daily habits of the subjects. Meanwhile, the distribution function of the low-variability periods as a whole discriminates efficiently between various heart pathologies. This new technique is also applicable to other non-linear time-series and reflects these aspects of the underlying intermittent dynamics, which are not covered by other methods of linear- and nonlinear analysis.

Zipf's law in human heartbeat dynamics

Effect of 450 MHz Microwave Modulated with 217 Hz on Human EEG in Rest

The aim of this study was to select and evaluate methods sensitive to reveal small hidden changes in the electroencephalographic (EEG) signal. Two original methods were considered. Multifractal method of scaling analysis of the EEG signal based on the length distribution of low variability periods (LDLVP) was developed and adopted for EEG analysis. The LDLVP method provides a simple route to detecting the multifractal characteristics of a time-series and yields somewhat better temporal resolution than the traditional multifractal analysis. The method of modulation with further integration of energy of the recorded signal was applied for EEG analysis. This method uses integration of differences in energy of the EEG segments with and without stressor. Microwave exposure was used as an external stressor to cause hidden changes in the EEG. Both methods were evaluated on the same EEG database. Database consists of resting EEG recordings of 15 subjects without and with low-level microwave exposure (450 MHz modulated at 40 Hz, power density 0.16 mW/cm2). The significant differences between recordings with and without exposure were detected by the LDLVP method for 4 subjects (26.7%) and energy integration method for 2 subjects (13.3%). The results show that small changes in time variability or energy of the EEG signals hidden in visual inspection can be detected by the LDLVP and integration of differences methods.

/pdf/methods-of-electroencephalographic-signal-analysis-for-1m5fc778fa.pdf

Methods of electroencephalographic signal analysis for detection of small hidden changes

Three different methods in combination with integration of differences in signals were applied for EEG analysis to distinguish changes in EEG caused by microwave: S-parameter, power spectral density and length distribution of low variability periods. The experiments on the effect of modulated low-level microwaves on human EEG were carried out on four different groups of healthy volunteers exposed to 450 MHz microwave radiation modulated with 7 Hz, 14 Hz, 21 Hz, 40 Hz, 70 Hz, 217 or 1000 Hz frequencies. The field power density at the scalp was 0.16 mW/cm 2 . The EEG analysis performed for individuals with three different methods showed that statistically significant changes occur in the EEG rhythms energy and dynamics between 12% and 30% of subjects. Our previous studies on detection of the effect of microwave radiation on human EEG showed that some traditional methods for EEG analysis such as weighted spectral intensity, bispectrum or fractal dimension, usually successfully applied, did not provide distinction of small changes caused by microwave in EEG (5, 6). In the case of detection of small changes in stochastic signals the method of modulation with further integration of differences between the segments of signal with and without expected change would be useful. Such approach has been shown to be able to detect significant changes in EEG caused by 7 Hz modulated microwave (7, 8). This study is focused on detection of the effect of microwave radiation modulated with 7, 14, 21, 40, 70, 217 and 1000 Hz frequencies on human EEG rhythms. The on- off switching of the modulated exposure with further integration of differences between the EEG segments with and without exposure was applied. In this paper we present the results of analysis and conclusions about individual sensitivity to microwave based on EEG analysis. The experimental studies with different modulation frequencies were performed on four groups of subjects.

Maksim Säkki

Papers

Non-linear analysis of the electroencephalogram for detecting effects of low-level electromagnetic fields.

Zipf's law in human heartbeat dynamics

Effect of 450 MHz Microwave Modulated with 217 Hz on Human EEG in Rest

Methods of electroencephalographic signal analysis for detection of small hidden changes

Integration of differences in EEG analysis reveals changes in human EEG caused by microwave.