Major depressive disorder (MDD) is a mental ailment marked by a loss of interest in activities, persistent depression, and hopelessness. MDD has been on the rise in society in recent decades for varied reasons and has spurred suicidal tendencies among individuals. Early detection, continuous monitoring, and effective treatment are crucial for its impact on quality of life and society. EEG signal models the brain’s electrical activities and has emerged as a potential tool to assess the depression status of a person. Due to advancements in sensor technology, fast, convenient, and cost-effective EEG acquisition is now possible, resulting in many EEG-based healthcare monitoring applications in recent years. This work proposes an EEG-headset-based smart monitoring system for real-time diagnosis of MDD in the Internet of Medical Things (IoMT) framework. In this study, we proposed a novel Linear Graph Convolution Network-Transformer-based deep learning approach for categorizing MDD through a time-frequency analysis of EEG signals. The Stockwell transform (S-transform) is employed to exploit the spectro-temporal information from the EEG and the resulting 2D representation is then fed into customized Linear Graph Convolution Network for MDD detection. We have utilized theWeighted Focal Binary Hinge Loss function, specifically designed for customized Linear Graph Convolution Network, to improve learning and handle unbalanced input. Subsequently, a novel Transformer model is designed to refine the MDD classification further. The proposed methodology named SLiTRANet, blends spectral analysis with the S-transform, graph-based learning with Linear Graph Convolution Network, and the sequence modeling capability of the Transformer. The proposed SLiTRANet model can be further integrated within an IoMT framework for automated real-time MDD diagnosis using EEG signals. The proposed methodology is evaluated on two publicly available datasets, MODMA and HUSM datasets. The evaluation results demonstrate the superior performance of the proposed SLiTRANet framework against the existing pre-trained and hybrid deep learning models, achieving remarkable accuracy, sensitivity, specificity, and precision rates of 99.92%, 99.90%, 99.95%, and 99.97%, respectively on HUSM dataset followed by an equally good performance on MODMA dataset with an accuracy of 99.68%. The proposed comprehensive approach implemented on two varied datasets highlights significant advancements in depression detection by outperforming state-of-art approaches.

Emotion Recognition is a critical area of research including healthcare, human-computer interaction, and psychology. While traditional methods mainly rely on facial expressions and textual analysis, they also have inherent flaws and cannot be reliable. Facial expression-based emotion recognition assumes that it represents genuine internal emotions that may be inaccurate. Similarly, textual analysis depends on the available data and needs help accurately capturing subtle emotions in text. However, electroencephalography (EEG) has emerged as a rising alternative for objective and real-time emotion recognition. Unlike facial and textual methods, EEG directly measures brain activity and provides a reliable result. To address this researchers have used basic machine learning methods that need manual feature extraction, which might miss essential data and make the process slow and less accurate. In this study, we propose a comprehensive methodology for EEG-based emotion recognition that addresses the limitations of traditional methods and basic machine learning techniques. Our approach involves preprocessing EEG signals using a butter-worth bandpass filter to eliminate noise, followed by feature extraction techniques. We then employ Principal Component Analysis (PCA) for dimensionality reduction, ensuring efficient data representation. To further enhance the model performance we explore machine learning classifiers(GaussianNB, SVM, Random Forest) and proposed an EEG-LSTM and GRU model with an accuracy of 97% and 96% respectively, that gives better results than the basic machine learning models.

Novel coronavirus 2019 has created a pandemic and was first reported in December 2019. It has had very adverse consequences on people's daily life, healthcare, and the world's economy as well. According to the World Health Organization's most recent statistics, COVID-19 has become a worldwide pandemic, and the number of infected persons and fatalities growing at an alarming rate. It is highly required to have an effective system to early detect the COVID-19 patients to curb the further spreading of the virus from the affected person. Therefore, to early identify positive cases in patients and to support radiologists in the automatic diagnosis of COVID-19 from X-ray images, a novel method PCA-IELM is proposed based on principal component analysis (PCA) and incremental extreme learning machine. The suggested method's key addition is that it considers the benefits of PCA and the incremental extreme learning machine. Further, our strategy PCA-IELM reduces the input dimension by extracting the most important information from an image. Consequently, the technique can effectively increase the COVID-19 patient prediction performance. In addition to these, PCA-IELM has a faster training speed than a multi-layer neural network. The proposed approach was tested on a COVID-19 patient’s chest X-ray image dataset. The experimental results indicate that the proposed approach PCA-IELM outperforms PCA-SVM and PCA-ELM in terms of accuracy (98.11%), precision (96.11%), recall (97.50%), F1-score (98.50%), etc., and training speed.

Our research addresses the pressing need to assess biodiversity in the face of increasing habitat destruction and species extinctions. Several researchers have modelled conventional measures to assess biodiversity. Every measure evaluates biodiversity by considering different properties. Among them Simpson and Shannon indices are widely used, they primarily focus on species richness and abundance, overlooking the importance of rare or unique species. This limitation makes it challenging to identify which species drive changes in biodiversity and hampers conservation efforts. Moreover, these measures are sensitive to sample size and biased towards dominant species, leading to inaccurate estimations. To overcome these challenges, we propose a novel mathematical model that provides a comprehensive assessment of biodiversity. Our model accounts for species dominance, addresses sample size sensitivity, and highlights the significance of rare species within a community. By applying our measure to real-time scenarios and comparing it with traditional methods using the same dataset, proposed measure demonstrated its efficacy in capturing biodiversity dynamics over time.

Portfolio theory underpins portfolio management, a much-researched yet uncharted field. Stock market prediction is a challenging and essential endeavour in financial research, owing to the nonlinear, volatile, and stochastic characteristics of financial time series data. Conventional statistical techniques often fall short to encapsulate complex interdependencies, resulting in diminished predictive accuracy. This research proposes an ensemble model that integrates Long Short-Term Memory (LSTM), Convolutional Neural Networks (CNN), and Temporal Convolutional Networks (TCN) for effective stock market prediction. The Nifty 50 index dataset is utilized for the empirical evidences. Wavelet-based denoising is utilised as a preprocessing measure to mitigate the intrinsic noise in stock market data. The model’s efficacy is assessed utilising error metrics, such as Mean Squared Error (MSE), Root Mean Squared Error (RMSE), Mean Absolute Error (MAE), and R-squared (R²). The five-fold cross-validation is utilized to establish the robustness of the models. Furthermore, we ascertain the statistical significance of performance enhancements by parametric t-tests, including normality assessments via the Shapiro-Wilk test. Moreover, current state-of-the-art models advocates in favour of proposed study.