Chirag Kumar

An effective electrode selection strategy is crucial in motor imagery (MI)-based brain–computer interfaces (BCIs) to maintain competitive performance while reducing the number of electrodes and overall computational complexity. This study introduces a novel electrode selection method based on signal power and evaluates its impact on MI task classification using the BCI Competition IV-2a dataset. Electrodes were systematically reduced by selecting those with the highest signal power. The proposed method was evaluated using state-of-the-art deep learning models, EEGNet, ShallowConvNet, and DeepConvNet, with classification accuracy and F1-score as performance metrics. EEGNet, with all electrodes, achieved an average accuracy of 69.30% and an average F1-score of 0.6910. As the number of electrodes was progressively reduced, performance declined gradually, with a noticeable drop observed after a 50% reduction. Notably, even with 50% fewer electrodes, accuracy remained within 8.59% of the full-electrode configuration. Topographic analysis showed that electrodes near the motor cortex, exhibiting higher signal power, were most critical for classification. In contrast, peripheral electrodes with lower signal power were less informative and could be removed, demonstrating the effectiveness of the proposed method. Similar trends were observed for ShallowConvNet and DeepConvNet, further confirming the method’s generalizability. This approach provides a promising direction for developing more practical, faster, cost-effective, and resource-efficient BCI systems.

Motor imagery (MI)-based brain-computer interfaces (BCIs) require efficient electrode selection to reduce cost and computational complexity while preserving their performance. We propose a signal-to-noise ratio (SNR)-based electrode selection strategy and introduce a novel method to calculate SNR from EEG datasets. We further present the Pairwise Difference (PRD) technique for data augmentation to compensate for the accuracy loss resulting from electrode reduction. Using EEGNet, a state-of-the-art deep learning model, we achieved an accuracy of 68.99% and an F1-score of 0.6891 with all 22 electrodes as the baseline. As electrodes were progressively removed, performance declined, with a notable drop after a 50% reduction. However, applying the PRD technique maintained EEGNet's average accuracy within 3.96% of the baseline (66.26%), and F1-score at 0.6587, even with the above reduction. PRD effectively compensated for the loss of information due to electrode reduction. Simulations further validated the generalizability of our approach, demonstrating its effectiveness across other deep learning models, viz., ShallowConvNet and DeepConvNet. This work will help develop cheaper and resource-efficient BCI systems.

The manuscript is about the one of the important challenges which is faced on the daily basis. The problem is of importance but there are multiple issues which should be addressed and are as follows: * Novelty of the work: The novelty of the system...

As machine learning implementations move towards the network edge, distributed optimization algorithms are becoming increasingly relevant. Common approaches build upon the consensus framework to enforce cooperation and consistency among the nodes. In many applications however, the inter-node relationships are better modeled via antagonistic or dissensual constraints. These relationships can generally be incorporated via non-convex constraints or penalty functions, and the resulting formulations are flexible enough to subsume a wide variety of classificaiton and discrimination problems. This work develops a general-purpose ADMM algorithm for distributed optimization with dissensus constraints. The formulation is generalized to incorporate both consensus and dissensus relationships. The non-convex constraints are handled via appropriate first-order approximations and convergence to a stationary point is established. The proposed algorithm is tested on various synthetic as well as real-world data sets. In particular, we focus on the discriminative dictionary learning problem, where the goal is to learn class-specific dictionaries usable for both reconstruction and discrimination tasks. Extensive tests over seizure detection, activity recognition, and indoor localization datasets demonstrate the efficacy of the proposed approach.

Common approaches in distributed optimization build upon the consensus framework to enforce cooperation and consistency among the nodes. In many applications however, the inter-node relationships are better modeled via antagonistic or dissensual constraints. These relationships can generally be incorporated via non-convex constraints or penalty functions, and the resulting formulations are flexible enough to subsume a wide variety of classification and discrimination problems. This work develops a general-purpose ADMM algorithm for distributed optimization with dissensus constraints. The formulation is generalized to incorporate both consensus and dissensus relationships. The non-convex constraints are handled via appropriate first-order approximations. The proposed algorithm is tested on the discriminative dictionary learning problem, where the goal is to learn class-specific dictionaries usable for both reconstruction and discrimination tasks. Extensive tests over human activity recognition dataset demonstrate the efficacy of the proposed approach.

Indoor localization is often challenging due to the non-availability of GPS signals. Recently, various radio frequency fingerprinting techniques have been proposed to identify indoor locations using simply received signal strength (RSS) measurements. In general however, RSS measurements are time-varying and are difficult to model for complex environments. This paper proposes the use of dictionary learning (DL) to generate high quality fingerprints that depend also on the channel characteristics for each location. An enhanced DL algorithm is proposed that utilizes prior information about the channel distribution, and can generate the fingerprints in an online fashion. Simulation results demonstrate the efficacy of the proposed approach.

Mobile Ad-Hoc Network (MANET) is a self-configuring network of mobile nodes connected by wireless links to form an arbitrary topology without the use of existing infrastructure. In order to facilitate communication between a pair of nodes, routing protocols are used. The performance of routing protocols is evaluated using simulation tools such as QUALNET, NS-2 and MATLAB etc. Simulation tool provides researchers with a number of significant benefits, including repeatable scenarios, isolation of parameters, and exploration of a variety of metrics. We wish to make these simulations more realistic for ad hoc network. To do the same different shapes such as square, elliptical, circular and rectangular of the simulation region were taken. In addition to different shapes, we used the concept of obstacle. These obstacles restrict node movement as well as obstruct the communication path between nodes. Simulation results show that for same number of nodes deployed having equal areas and with different shapes the throughput will have inverse relationship with perimeter. The result can be very useful while designing a routing protocol.