Schizophrenia (SCZ) is a serious mental condition that causes hallucinations, delusions, and disordered thinking. Traditionally, SCZ diagnosis involves the subject's interview by skilled psychiatrist. The process needs time bound to human errors bias. Recently, brain connectivity indices have been used in few pattern recognition methods discriminate neuro-psychiatric patients from healthy subjects. study presents Schizo-Net, novel, highly accurate, reliable model based on late multimodal...

Abstract Considering the prevailing scenario of COVID‐19 pandemic, early detection disease is an important and crucial step in management. Early correct treatment may limit progression to severe levels prevent deaths. In addition, isolation infected patients will lead control transmission rate possibly reduce stress on present healthcare system. Currently, most common reliable testing method available for diagnosis real‐time reverse transcription‐polymerase chain reaction (rRT‐PCR) test....

Effective working of brain computer interface largely depends upon mental state and vigilance level human brain. Electroencephalogram signal undergoes for unpredictable changes when alters widely sometimes cause wrong interpretation by during operation. Hence, needs to investigate subject's alertness frequently avoid false command generation. In present work, an approach feature extraction from electroencephalogram signals using continuous wavelet transform is proposed validated...

This paper presents an S-transform-based Electroencephalogram channel optimization and feature extraction methodology for monitoring mental vigilance level of humans. Vigilance detection consists four steps. In the first stage, two types signals (alert drowsy) are acquired from 30 healthy subjects decomposed into sub-bands using S-transform. second permutation entropy S-transform coefficients is calculated performed. statistical features computed optimized channels, in third stage. fourth...

ABSTRACT The emerging field of brain–computer interface has significantly facilitated the analysis electroencephalogram signals required for motor imagery classification tasks. However, accuracy EEG models been restricted by low signal‐to‐noise ratio, nonlinear nature brain signals, and a lack sufficient data training. To address these challenges, this study proposes new approach that combines time‐frequency with hybrid parallel–series attention‐based deep learning network signal...

Abstract In this research study, a compact dual-polarized co-radiator ultra-wideband (UWB) multiple-input multiple-output (MIMO) antenna with improved impedance bandwidth and isolation is proposed for wireless applications. The designed has an overall area of 0.3 λ o × mm 2 (where, free space wavelength corresponding to the lower cut-off frequency, i.e., 3.1 GHz). resonator comprises hybrid geometry which created combinations circular-shaped patch, square, two rectangular stubs. It centrally...

Abstract Multi‐class MI EEG analysis is an extensively used paradigm in BCI. However, multiple channels lead to redundant information extraction and would reduce the distinction among various tasks. Therefore, optimal channel selection from multi‐channel activity still remains a challenging task. In this study, enhance multi‐class BCI system's performance, novel selection, features optimization methodology have been proposed. First, dataset reduced optimum no. of subset using developed...

Migraine is a prolonged neurovascular illness, which causes outbreaks of severe pain and autonomic nervous system disturbance. The clinical analysis Electroencephalogram signals helps in management prognosis migraine disease. Recent advancement biomedical signal processing field led to generation various techniques for multi-resolution diagnosis diseased condition. In present work, nonlinear parametric approach feature extraction proposed analysed automated database studied study was...

Deep learning-based Computer-Aided Diagnosis has gained immense attention in recent years due to its capability enhance diagnostic performance and elucidate complex clinical tasks. However, conventional supervised deep learning models are incapable of recognizing novel diseases that do not exist the training dataset. Automated early-stage detection infectious can be vital controlling their rapid spread. Moreover, development a CAD model is only possible after disease outbreaks datasets...

Epileptic seizure is the abnormal synchronous neuronal activity that occurs in human brain. The early detection of epileptic helps improving patient's mental health. In this work, an Electroencephalogram based methodology automated using Flexible Analytical Wavelet Transform presented. proposed methodology, signals are decomposed into approximate and detailed wavelet coefficients Transform, initially. statistical features such as mean, kurtosis skewness calculated from selected features....

Abstract The classification of electroencephalograms‐based motor imagery signals poses a significant issue in the design and development brain‐computer interfaces. Neural Networks are observed to be successful brain signals. However, existing data sets limited size suffer from low signal noise ratio. Hence, achieve high performance with small datasets, this paper proposes novel combination time frequency analysis along deep learning network perform task. proposed framework consists two...

Abstract This manuscript presents a 50 Ω microstrip-fed quad-element high isolated ultra-wideband (UWB) multiple-input multiple-output (MIMO) antenna with band-notched characteristics. The overall area of the proposed structure is 0.33 λ o × mm 2 (where depicts free space wavelength corresponding to lower cutoff frequency, i.e. 2.54 GHz), etched on an FR-4 substrate thickness 0.8 mm. top layer has four semicircular disc-shaped radiating elements that are identical and orthogonal obtain...

Electroencephalogram (EEG) signal analysis provides ground for evaluation of various neurological disorders and implementation Brain Computer Interface (BCI) such disabilities. These capabilities BCI system enable patients suffering from severe motor disability to control variety applications by simply generating commands using channel like, brain controlled arm or wheel chair. Successful realization an efficient depends upon accuracy maintained during EEG signals recording, processing,...