Cortical representations of Auditory Perception using Graph Independent Component on EEG

Recent studies indicate that the neurons involved in a cognitive task aren't locally limited but span out to multiple human brain regions. We obtain network components and their locations for the task of listening to music. The recorded EEG data is modeled as a graph, and it is assumed that the overall activity is a contribution of several independent subnetworks. To identify these intrinsic cognitive subnetworks corresponding to music perception, we propose to decompose the whole brain graph-network into multiple subnetworks. We perform this decomposition to a group of brain networks by performing Graph-Independent Component Analysis. Graph-ICA is a variant of ICA that decomposes the measured graph into independent source graphs. Having obtained independent subnetworks, we calculate the electrode positions by computing the local maxima of these subnetwork matrices. We observe that the computed electrodes' location corresponds to the temporal lobes and the Broca's area, which are indeed involved in the task of auditory processing and perception. The computed electrodes also span the brain's frontal lobe, which is involved in attention and generating a stimulus-evoked response. The weight of the subnetwork that corresponds to the aforementioned brain regions increases with the increase in the music recording's tempo. The results suggest that whole-brain networks can be decomposed into independent subnetworks and analyze cognitive responses to music stimulus.

Efficient Coding Approach Towards Non-Linear Spectro-Temporal Receptive Fields

Linear Non-Linear(LN) models are widely used to characterize the receptive fields of early-stage auditory processing. We apply the principle of efficient coding to the LN model of Spectro-Temporal Receptive Fields(STRFs) of the neurons in primary auditory cortex. The Efficient Coding Principle has been previously used to understand early visual receptive fields and linear STRFs in auditory processing. Efficient coding is realized by jointly optimizing the mutual information between stimuli and neural responses subjected to the metabolic cost of firing spikes. We compare the predictions of the efficient coding principle with the physiological observations, which match qualitatively under realistic conditions of noise in stimuli and the spike generation process.

Indoor Distance Estimation using LSTMs over WLAN Network

The Global Navigation Satellite Systems (GNSS) like GPS suffer from accuracy degradation and are almost unavailable in indoor environments. Indoor positioning systems (IPS) based on WiFi signals have been gaining popularity. However, owing to the strong spatial and temporal variations of wireless communication channels in the indoor environment, the achieved accuracy of existing IPS is around several tens of centimeters. We present the detailed design and implementation of a self-adaptive WiFi-based indoor distance estimation system using LSTMs. The system is novel in its method of estimating with high accuracy the distance of an object by overcoming possible causes of channel variations and is self-adaptive to the changing environmental and surrounding conditions. The proposed design has been developed and physically realized over a WiFi network consisting of ESP8266 (NodeMCU) devices. The experiment were conducted in a real indoor environment while changing the surroundings in order to establish the adaptability of the system. We introduce and compare different architectures for this task based on LSTMs, CNNs, and fully connected networks (FCNs). We show that the LSTM based model performs better among all the above-mentioned architectures by achieving an accuracy of 5.85 cm with a confidence interval of 93% on the scale of (4.14 m * 2.86 m). To the best of our knowledge, the proposed method outperforms other methods reported in the literature by a significant margin.