Development of a speaker recognition system using wavelets and artificial neural networks

This paper addresses the problem of speaker recognition from speech signals. The study focuses on the development of a speaker recognition system comprising two modules: a wavelet-based feature extractor, and a neural-network-based classifier. We have conducted a number of experiments to investigate the applicability of Discrete Wavelet Transform (D WT) in extracting discriminative features from the speech signals, and have examined various models from the Adaptive Resonance Theory (ART) family of neural networks in classijjing the extracted features. The results indicate that DWT could be a potential feature extraction tool for speaker recognition. In addition, the ART-based classijiers have yielded very promising recognition accuracy at more than 81%.

Are voluntary wheel running and open-field behavior correlated in mice? Different answers from comparative and artificial selection approaches

Voluntary wheel running and open-field behavior are probably the two most widely used measures of locomotion in laboratory rodents. We tested whether these two behaviors are correlated in mice using two approaches: the phylogenetic comparative method using inbred strains of mice and an ongoing artificial selection experiment on voluntary wheel running. After taking into account the measurement error and phylogenetic relationships among inbred strains, we obtained a significant positive correlation between distance run on wheels and distance moved in the open-field for both sexes. Thigmotaxis was negatively correlated with distance run on wheels in females but not in males. By contrast, mice from four replicate lines bred for high wheel running did not differ in either distance covered or thigmotaxis in the open field as compared with mice from four non-selected control lines. Overall, results obtained in the selection experiment were generally opposite to those observed among inbred strains. Possible reasons for this discrepancy are discussed.

The pace of life under artificial selection : personality, energy expenditure, and longevity are correlated in domestic dogs

The domestic dog has undergone extensive artificial selection resulting in an extreme diversity in body size, personality, life‐history, and metabolic traits among breeds. Here we tested whether proactive personalities (high levels of activity, boldness, and aggression) are related to a fast “pace of life” (high rates of growth, mortality, and energy expenditure). Data from the literature provide preliminary evidence that artificial selection on dogs (through domestication) generated variations in personality traits that are correlated with life histories and metabolism. We found that obedient (or docile, shy) breeds live longer than disobedient (or bold) ones and that aggressive breeds have higher energy needs than unaggressive ones. These correlations could result from either human preference for particular trait combinations or, more likely, correlated responses to artificial selection on personality. Our results suggest the existence of a general pace‐of‐life syndrome arising from the coevolution of personality, metabolic, and life‐history traits.

Artificial neural network analysis of twin tunnelling-induced ground settlements

In this paper, we apply a computational intelligence method for tunnelling settlement prediction. A supervised feed forward back propagation neural network is used to predict the surface settlement during twin-tunnelling while surface buildings are considered in the models. The performance of the statistical neural network structure is tested on a dataset provided by numerical parametric studies conducted by ABAQUS software based on Shiraz line 1 metro data. Six input variables are fed to neural network model for predicting the surface settlement. These include tunnel center depth, distance between centerlines of twin tunnels, buildings width and building bending stiffness, and building weight and distance to tunnel centerline. Simulation results indicate that the proposed NN models are able to accurately predict the surface settlement.

Artificial ornaments manipulate intrinsic male quality in wild-caught zebra finches (Taeniopygia guttata)

The addition of red and green color bands is a commonly used method for manipulating male attractiveness in the zebra finch (Taeniopygia guttata), providing insight into the study of maternal investment and sexual selection. The addition of artificial ornaments has been assumed to manipulate a females’ perception of the male, rather than affecting intrinsic qualities of the male himself. Here, however, we reveal that the artificial band color worn by a male changes his body mass, condition, and courtship display rate. Males wearing red color bands in aviaries prior to mate-choice trials had a significantly higher song rate during trials than those wearing green color bands, alongside a significant increase in mass change and condition. Male song rate was found to significantly correlate with female preference alongside a female preference for red-banded males. However, male song rate in turn increased when female response was positive, suggesting a social feedback between the interacting birds. Our data suggest the presence of socially mediated feedback mechanisms whereby the artificial increase in attractiveness or dominance of a male directly affects other aspects of his attractiveness. Therefore, housing birds in social groups while manipulating attractiveness can directly influence other male qualities and should be accounted for by future studies.

Artificial Muscles Based on Polypyrrole/Carbon Nanotube Laminates

A novel method for the periodical assembly of laminates of forest-drawn carbon nanotube (CNT) sheets and polypyrrole (PPy) is described. The method produces composite films in which the volume fraction and orientation of CNTs can be controlled. Actuator stroke and strength is increased and work capacity per cycle doubled when nanotube orientation is perpendicular to the actuation direction. Most importantly, these PPy/CNT laminates have dramatically decreased creep during actuation, which has been a major barrier for the application of PPy actuators.