This study aimed to develop an advanced ensemble approach for automated classification of mental health disorders in social media posts. The research question was: can an ensemble of fine‐tuned transformer models (XLNet, RoBERTa, and ELECTRA) with Bayesian hyperparameter optimization improve the accuracy of mental health disorder classification in social media text. Three transformer models (XLNet, RoBERTa, and ELECTRA) were fine‐tuned on a dataset of social media posts labelled with 15 distinct mental health disorders. Bayesian optimization was employed for hyperparameter tuning, optimizing learning rate, number of epochs, gradient accumulation steps, and weight decay. A voting ensemble approach was then implemented to combine the predictions of the individual models. The proposed voting ensemble achieved the highest accuracy of 0.780, outperforming the individual models: XLNet (0.767), RoBERTa (0.775), and ELECTRA (0.755). The proposed ensemble approach, integrating XLNet, RoBERTa, and ELECTRA with Bayesian hyperparameter optimization, demonstrated improved accuracy in classifying mental health disorders from social media posts. This method shows promise for enhancing digital mental health research and potentially aiding in early detection and intervention strategies. Future work should focus on expanding the dataset, exploring additional ensemble techniques, and investigating the model's performance across different social media platforms and languages.

A Tenant Virtual Machine (TVM) user in the cloud may misuse its computing power to launch malware attack against other tenant VMs, Host OS, Hypervisor, or any other computing devices/resources inside the cloud environment of a Cloud Service Provider. The security solutions deployed within the TVM may not be reliable, as malware can disable them or remain undetected due to its hidden nature. Therefore, security solutions deployed outside the virtual machine are necessary. This research proposes deploying an Intrusion Detection System (IDS) at the Hypervisor layer, utilizing time series system call data and employing a Convolutional Neural Network (CNN) model to accurately detect the presence of malicious (malware) computer programs within virtual machines. The raw VMM system call traces are transformed into novel Time Series System Call patterns and utilized by a deep learning algorithm for training and building the classifier model. A deep learning model, CNN, is used to build the classifier model for detecting intrusions with high accuracy. It is capable of detecting both known and unknown malware. The CNN model is compared with machine learning algorithms for the results and discussions, and it outperforms ML algorithms in terms of intrusion detection accuracy when utilizing novel time series system call data..

Alzheimer's disease (AD) is a degenerative neurological disease that progresses over time, making early detection crucial for effective intervention and better patient prognosis. Traditional diagnostic methods such as cognitive assessments, neuroimaging, and biomarker analysis can be time-consuming, costly, and inconsistent. We introduce AlzStack, a soft voting ensemble model to classify AD from a richly detailed dataset containing 2149 patients across demographic, medical, lifestyle, and cognitive variables. To resolve class imbalance, we implemented a pipeline 5-fold cross-validation, randomized search for hyper parameter tuning and advanced resampling methods such as SMOTE (Synthetic Minority Oversampling Technique), ADASYN, BorderlineSMOTE, and SVMSMOTE. Soft Vote Classifier surpassed both stacking ensembles and hard voting with an AUC value of 94.27 %, accuracy of 93.26 %, precision of 89.17 %, a recall of 92.11 %, and F1-score value of 90.61 %.A secondary experiment with only resampling methods applied to data to all base models served as a baseline for comparison confirming the superior performance of cross-validation AlzStack configuration. To improve interpretability, we utilized a wide range of Explainable Artificial Intelligence (XAI methods) and these approaches yielded global and local explanations about model behavior, emphasizing key features like MMSE scores, functional measures, and behavioral markers. Combining robust predictive performance with explainable decision-making makes AlzStack is a healthcare decision-support algorithm for the early detection of AD.

This research proposes a hybrid approach combining deep learning models with the Squirrel Search Algorithm (SSA) for early heart disease prediction. Integrating Internet of Things (IoT) devices for real-time health monitoring enhances predictive capability and provides continuous patient data. The proposed model optimizes feature selection using SSA, ensuring that the most relevant and impactful features are used for prediction, which improves the accuracy and efficiency of the deep learning models. This study aims to provide a robust, real-time heart disease prediction system that can be seamlessly integrated into modern healthcare infrastructures.

The rising prevalence of diabetes and hypertension among children calls for innovative solutions to enhance health management. This study introduces a novel pediatric health monitoring system integrating real-time data acquisition, automated alerts, voice-assisted interventions, and gamified educational elements to engage young users. The system demonstrated a rapid response time of 1.8 seconds to abnormal readings, a socket latency of 2.6 seconds, and achieved an accuracy of 98.7% in detecting critical health anomalies, ensuring timely interventions and reliable monitoring. By combining automated real-time monitoring with a gamified experience, the system empowers caregivers to act swiftly, enhances user engagement, and improves health outcomes for children. This work lays the groundwork for advancements in telemedicine, personalized healthcare, and child-centric digital health solutions.