Piyush Swami

Robust expert system design for automated detection of epileptic seizures using SVM classifier

The classification of normal and ailing brain activities through visual inspection proves to be very challenging even for any experienced neurologist. The case is even worse for detection of heterogeneous anomalies like epileptic seizures. Authors have presented robust expert system design for classification of epileptic seizures automatically with an improvement over the existing systems. The developed scheme illustrates selection methodology for feeding energy, entropy and standard deviation feature sets to the support vector classifier. The results display maximum classification rate of 99.53 % with sensitivity and specificity rates above 98.8 %. These results were validated over 10 folds of sub-divisions using rotation estimation technique with minimum computation time noted to be 0.0131 s. Therefore, the expert system developed during this study holds promising grounds for automated clinical diagnosis in real time.

A Low-Noise Low-Cost EEG Amplifier for Neural Recording Applications

The development and testing of a high-precision low-cost biopotential amplifier are presented in this paper. The amplifier consisting of filters and amplifiers operating at a gain of 92 dB over 0.5–45 Hz bandwidth provides very low noise levels for high-quality brain activity recordings. Signals acquired provide state-of-the-art signal–noise tradeoff. The resulting amplifier developed is an eight-channel EEG recording unit capable of recording brain activities and stores the data for research and clinical applications. Preliminary results obtained from experimentation in alpha rhythms and visual evoked potentials in the occipital region corroborate the precision and robustness of the designed amplifier.

Emergence of categorical face perception after extended early-onset blindness

Significance The results of this study help resolve an important open question regarding visual learning: Can the human brain acquire face classification skill late in life, or is such learning limited only to a critical period early in development? Working with a group of congenitally blind children in whom we were able to surgically initiate sight, we tracked their face/nonface categorization ability over several months. The data reveal that although the newly sighted children do not possess innately specified face schemas, they are able to learn this distinction to a high degree of proficiency through natural visual experience. These findings have implications for visual learning, brain plasticity, and prognoses for late treatments of blindness. It is unknown whether the ability to visually distinguish between faces and nonfaces is subject to a critical period during development. Would a congenitally blind child who gains sight several years after birth be able to acquire this skill? This question has remained unanswered because of the rarity of cases of late sight onset. We had the opportunity to work with five early-blind individuals who gained sight late in childhood after treatment for dense bilateral cataracts. We tested their ability to categorize patterns as faces, using natural images that spanned a spectrum of face semblance. The results show that newly sighted individuals are unable to distinguish between faces and nonfaces immediately after sight onset, but improve markedly in the following months. These results demonstrate preserved plasticity for acquiring face/nonface categorization ability even late in life, and set the stage for investigating the informational and neural basis of this skill acquisition.

A novel technique for identifying attentional selection in a dichotic environment

Healthy humans have an innate ability to concentrate on the voice of their choice even in noisy surroundings. But, a complete understanding of the process of segregation and selection of a particular sound in brain is still unclear. Recent studies have successfully demonstrated reconstruction of stimuli speech envelopes through mathematical modeling. In order to determine the attentional focus of the listener in multi-speaker settings, the existing models rely on the correlation between the reconstructed speech signals and the electroencephalogram (EEG) signals acquired while listening to the actual speech. However, realization of these type of models requires substantial time to reconstruct the stimulus and classify the direction of attention. Present study, proposes a novel solution for “cocktail party problem” by using machine learning approach. In this work, classification features viz. standard deviation, mean absolute values, mean absolute deviation and root-mean-square values were extracted from EEG data. The extracted features were fed into the artificial neural network (ANN) model with randomized sub-sampling procedure. The final outcomes showed ceiling level of performance to predict the attentional focus within subjects. These findings attest the robustness of the developed model for auditory stream segregation.

Application of Photoplethysmography for Man- Machine Interface: A Pilot Study

Man-machine interfacing holds the key for developing assistive technology. Moving towards this direction, here we present a simple and novel design that uses photoplethysmography for interfacing application. The intent behind this development was to aid people having disabilities with novel rehabilitation tool. Present research, illustrates a set of pilot experiments that successfully demonstrates its application for real-time implementation.

Detection of ictal patterns in electroencephalogram signals using 3D phase trajectories

Epilepsy is one of the most common brain disorder. Its diagnosis is generally performed using electroencephalography (EEG). But, the process of visually inspecting the EEG signals to trance out the seizure patterns has always been very time consuming and difficult. Researchers have continuously tried to automate the process of recognizing ictal patterns. But, the complexity and high erroneous outcomes from most of the deployed expert systems continues to limit practical realization. In this study, authors have presented a simple yet novel methodology to detect ictal patterns in EEG signals. The proposed model used intrinsic mode functions to plot 3D phase trajectories. The mean values of Euclidean distances calculated from these trajectories were used as input feature vectors to probabilistic neural network classifier. The outcomes from the classifier discriminated between the seizure and seizure-free patterns with ~98 % accuracy. The model achieved similar statistical performance in <; 0.03 s. Thus, attesting the design for application in practical settings.