Post-Stroke Resting-State EEG Connectivity: A Longitudinal Neuro-Rehabilitation Study.

Stroke is a leading cause of permanent disability worldwide. Even after adequate treatment, the majority of patients do not recover fully, making them dependent on others for carrying out Activities of Daily Living (ADL). An improved understanding of the underlying mechanism of plasticity will help us in customizing the translational approach for learning and rehabilitation following a stroke. For this study, a 2-minute resting state EEG data were recorded at 5 time-points for 3-months after stroke onset. Directed Transfer Function (DTF) was used to study neural reorganization for 3 months. DTF for different brain regions and sub-bands was correlated with FMA. The information flow was studied for different brain regions as well as Affected Region (AR). Occipital region showed good correlation (r = 0.45 to 0.47) with FMA. Contra-lesional and ipsi-lesional regions trajectories complement each other during acute and sub-acute phase. The information outflow vs inflow imbalance of AR was restored by the end of 3 months. DTF can be used as biomarker for studying neuroplasticity. Occipital, temporal and motor cortex regions play an important role during neuro-rehabilitation. The information about different regions during rehabilitation will help us in designing subject-specific interventions for better recovery.

Feature Importance Score-Based Functional Link Artificial Neural Networks for Breast Cancer Classification.

Growth of malignant tumors in the breast results in breast cancer. It is a cause of death of many women across the world. As a part of treatment, a woman might have to go through painful surgery and chemotherapy that may further lead to severe side effects. However, it is possible to cure it if it is diagnosed in the initial stage. Recently, many researchers have leveraged machine learning (ML) techniques to classify breast cancer. However, these methods are computationally expensive and prone to the overfitting problem. A simple single-layer neural network, i.e., functional link artificial neural network (FLANN), is proposed to overcome this problem. Further, the F-score is used to reduce the issue of overfitting by selecting features having a higher significance level. In this paper, FLANN is proposed to classify breast cancer using Wisconsin Breast Cancer Dataset (WBCD) (with 699 samples) and Wisconsin Diagnostic Breast Cancer (WDBC) (with 569 samples) datasets. Experimental results reveal that the proposed models can diagnose breast cancer with higher performance. The proposed model can be used in the early breast cancer diagnosis with 99.41% accuracy.

Wavelet and Region-Specific EEG Signal Analysis for Studying Post-Stroke Rehabilitation.

Post-stroke monitoring is a crucial step for properly studying the progress of stroke patients. The rehabilitation process consists of exercise regimes that help in constantly engaging the affected part of the brain leading to faster recovery. The work here studies the effectiveness of the rehabilitation regime by investigating several parameters that can play important role in observing the immediate effect of the exercises. Various parameters from different wavelet coefficients were extracted for monitoring rehabilitation for up to 90 days. Energy and waveform length show maximum variation when monitoring pre and post-exercise changes. The parameters were correlated with clinical(FMA) score. Centroid Index gave high correlation value for beta band (r = -0.559). Alpha band on the other hand showed a good correlation with all the extracted fe atures, maximum being -0.6988 with energy. So for monitoring post-stroke rehabilitation alpha and beta bands should be focused. Region-specific analyses were also done to monitor changes in different parts of the brain.

Functional link convolutional neural network for the classification of diabetes mellitus.

Diabetes is a faction of metabolic ailments distinguished by hyperglycemia which is the consequence of a defect, in the action of insulin, insulin secretion, or both and producing various abnormalities in the human body. In recent years, the utilization of intelligent systems has been expanded in disease classification and numerous researches have been proposed. In this research article, a variant of Convolutional Neural Network (CNN) that is, Functional Link Convolutional Neural Network (FLCNN) is proposed for the diabetes classification. The main goal of this article is to find the potential of a computationally less complex deep learning network like FLCNN and applied the proposed technique on a real dataset of diabetes for classification. This article also presents the comparative studies where various other machine learning techniques are implemented and outcomes are compared with the proposed FLCNN network. The performance of each classification techniques have been evaluated based on standard measures and also validated with a non-parametric statistical test such as Friedman. Data for modeling diabetes classification is collected from Bombay Medical Hall, Upper Bazar, Ranchi, India. Accuracy achieve by the proposed classifier is more than 90% which is closer to the other state-of-the-art implemented classifiers.