Power requirements for vibrotactile piezo-electric and electromechanical transducers.

Human-machine information transfer through tactile excitation has addressed new applications in virtual reality, robotics, telesurgery, sensory substitution and rehabilitation for the handicapped in the past few years. Power consumption is an important factor in the design of vibrotactile displays, because it affects energy needs and the size, weight, heat dissipation and cost of the associated electronics. An experimental study is presented on the power required to reach tactile thresholds in electromechanical and piezo-electric transducers. Three different waveforms are considered, with an excitatory period formed by a burst of rectangular 50% duty cycle pulses (R50), rectangular low duty cycle pulses (RLO) and sinusoidal pulses (SIN). Ten different pulse repetition periods (RPs) were considered in the range 1/550-1/25 s. The voltage and current waveforms applied to the transducers at sensation thresholds in a group of 12 healthy subjects were sampled and stored in a digital oscilloscope. The average power was determined for each subject, and differences of two orders of magnitude were measured between the electromechanical and the piezo-electric transducer power consumption. Results show that, for the electromechanical transducer, a smaller power consumption of 25 microW was determined for RP = 1/25 s and the RLO waveform. In the case of the piezo-electric transducer, power of 0.21 microW was determined for SIN excitation and RP = 1/250 s. These results show the advantages of reducing power requirements for vibrotactile displays, which can be optimised by the choice of appropriate types of transducer, excitatory waveforms and pulse repetition periods.

Polysomnographic pattern recognition for automated classification of sleep-waking states in infants.

A robust, automated pattern recognition system for polysomnography data targeted to the sleep-waking state and stage identification is presented. Five patterns were searched for: slow-delta and theta wave predominance in the background electro-encephalogram (EEG) activity; presence of sleep spindles in the EEG; presence of rapid eye movements in an electro-oculogram; and presence of muscle tone in an electromyogram. The performance of the automated system was measured indirectly by evaluating sleep staging, based on the experts' accepted methodology, to relate the detected patterns in infants over four months of post-term age. The set of sleep-waking classes included wakefulness, REM sleep and non-REM sleep stages I, II, and III-IV. Several noise and artifact rejection methods were implemented, including filters, fuzzy quality indices, windows of variable sizes and detectors of limb movements and wakefulness. Eleven polysomnographic recordings of healthy infants were studied. The ages of the subjects ranged from 6 to 13 months old. Six recordings counting 2665 epochs were included in the training set. Results on a test set (2,369 epochs from five recordings) show an overall agreement of 87.7% (kappa 0.840) between the automated system and the human expert. These results show significant improvements compared with previous work.

Genetic design of biologically inspired receptive fields for neural pattern recognition.

This paper proposes a new method for the design, through simulated evolution, of biologically inspired receptive fields in feedforward neural networks (NNs). The method is intended to enhance pattern recognition performance by creating new neural architectures specifically tuned for a particular pattern recognition problem. It proposes a combined neural architecture composed of two networks in cascade: a feature extraction network (FEN) followed by a neural classifier. The FEN is composed of several layers with receptive fields constructed by additive superposition of excitatory and inhibitory fields. A genetic algorithm (GA) is used to select receptive field parameters to improve classification performance. The parameters are receptive field size, orientation, and bias as well as the number of different receptive fields in each layer. Based on a random initial population where each individual represents a different neural architecture, the GA creates new enhanced individuals. The method is applied to handwritten digit classification and face recognition. In both problems, results show strong dependency between NN classification performance and receptive field architecture. GA selected parameters of the receptive fields produced improvements in the classification performance on the test set up to 90.8% for the problem of handwritten digit classification and up to 84.2% for the face recognition problem. On the same test sets, results were compared advantageously to standard feedforward multilayer perceptron (MLP) NNs where receptive fields are not explicitly defined. The MLP reached a maximum classification performance of 84.9% and 77.5% in both problems, respectively.

Dynamical properties of min-max networks.

In this paper we study the dynamical behavior of a class of neural networks where the local transition rules are max or min functions. We prove that sequential updates define dynamics which reach the equilibrium in O(n2) steps, where n is the size of the network. For synchronous updates the equilibrium is reached in O(n) steps. It is shown that the number of fixed points of the sequential update is at most n. Moreover, given a set of p < or = n vectors, we show how to build a network of size n such that all these vectors are fixed points.

Single trial P300 detection in children using expert knowledge and SOM.

Preliminary results of an automatic system for single trial P300 visual evoked potential events detection are presented. For each single trial P300, several candidate events were generated, and then filtered, using 3 wave features. The surviving candidate events were fed into a SOM-based classifier. A context filter was applied before the final output. No stationary condition of the P300 is involved in the algorithms. Recordings of 27 assessment sessions, each with 120 trials, were visually inspected by experts to identify and mark the P300 events, which was accomplished in about one third of the trials. The dataset was divided in training (18) and testing (9) subsets. The system identifies the initial and end times of the P300; it obtained a sensitivity of 53.9%, a specificity of 64.0% and an accuracy of 61.2% in the testing dataset.

A balanced sleep/wakefulness classification method based on actigraphic data in adolescents.

Several research groups have developed automated sleep-wakefulness classifiers for night wrist actigraphic (ACT) data. These classifiers tend to be unbalanced, with a tendency to overestimate the detection of sleep, at the expense of poorer detection of wakefulness. The reason for this is that the measure of success in previous works was the maximization of the overall accuracy, disregarding the balance between sensitivity and specificity. The databases were usually sleep recordings, hence the over-representation of sleep samples. In this work an Artificial Neural Network (ANN), sleep-wakefulness classifier is presented. ACT data was collected every minute. An 11-min moving window was used as observing frame for data analysis, as applied in previous sleep ACT studies. However, our feature set adds new variables such as the time of the day, the median and the median absolute deviation. Sleep and Wakefulness data were balanced to improve the system training. A comparison with previous studies can still be done, by choosing the point in the ROC curve associated with the corresponding data balance. Our results are compared with a polysomnogram-based hypnogram as golden standard, rendering an accuracy of 92.8%, a sensitivity of 97.6% and a specificity of 73.4%. Geometric mean between sensitivity and specificity is 84.9%.