As real-time data sources expand, the need for detecting anomalies in streaming data becomes increasingly critical for cutting edge data-driven applications. Real-time anomaly detection faces various challenges, requiring automated systems that adapt continuously to evolving data patterns due to the impracticality of human intervention. This study focuses on energy systems (ES), critical infrastructures vulnerable to disruptions from natural disasters, cyber attacks, equipment failures, or human errors, leading to power outages, financial losses, and risks to other sectors. Early anomaly detection ensures energy supply continuity, minimizing disruption impacts, an enhancing system resilience against cyber threats. A systematic literature review (SLR) is conducted to answer 5 essential research questions in anomaly detection due to the lack of standardized knowledge and the rapid evolution of emerging technologies replacing conventional methods. A detailed review of selected literature, extracting insights and synthesizing results has been conducted in order to explore anomaly types that can be detected using Machine Learning algorithms in the scope of Energy Systems, the factors influencing this detection success, the deployment algorithms and security measurement to take in to consideration. This paper provides a comprehensive review and listing of advanced machine learning models, methods to enhance detection performance, methodologies, tools, and enabling technologies for real-time implementation. Furthermore, the study outlines future research directions to improve anomaly detection in smart energy systems.

Multiple Sclerosis (MS) is a chronic neuroinflammatory disease of the Central Nervous System (CNS) in which the body's immune system attacks and destroys the myelin sheath that protects nerve fibers, leading to a wide range of debilitating symptoms and causing disruption of axonal signal transmission. Accurate prediction, diagnosis, monitoring and treatment (PDMT) of MS are essential to improve patient outcomes. Recent advances in neuroimaging technologies, particularly electroencephalography (EEG), combined with machine learning (ML) techniques - including Deep Learning (DL) models - offer promising avenues for enhancing MS management. This systematic review synthesizes existing research on the application of ML and DL models to EEG data for MS. It explores the methodologies used, with a focus on DL architectures such as Convolutional Neural Networks (CNNs) and hybrid models, and highlights recent advancements in ML techniques and EEG technologies that have significantly improved MS diagnosis and monitoring. The review addresses the challenges and potential biases in using ML-based EEG analysis for MS. Strategies to mitigate these challenges, including advanced preprocessing techniques, diverse training datasets, cross-validation methods, and explainable Artificial Intelligence (AI), are discussed. Finally, the paper outlines potential future applications and trends in ML for MS management. This review underscores the transformative potential of ML-enhanced EEG analysis in improving MS management, providing insights into future research directions to overcome existing limitations and further improve clinical practice.

This study explores the use of deep learning techniques for classifying EEG signals in the context of Alzheimer’s disease (AD) and frontotemporal dementia (FTD). We propose a novel classification pipeline that combines autoencoders for feature extraction and bidirectional long short-term memory (Bi-LSTM) networks for analyzing patterns over time in EEG data. Given the complexity and high dimensionality of EEG signals, we employed an autoencoder to reduce data dimensionality while preserving key diagnostic features. The Bi-LSTM model effectively identified subtle temporal patterns in brain activity that are indicative of AD and FTD. To enhance interpretability, we applied SHapley Additive exPlanations (SHAP), providing insights into how individual features contribute to the model’s predictions. We evaluated our approach on a publicly available EEG dataset from OpenNeuro, which includes resting-state EEG recordings from 88 elderly participants—36 with AD, 23 with FTD, and 29 cognitively normal controls. EEG provides a non-invasive, cost-effective tool for brain monitoring, but presents challenges such as noise sensitivity and inter-subject variability. Despite these challenges, our approach achieved 98% accuracy while maintaining transparency, making it a promising tool for clinical applications in the diagnosis of neurodegenerative diseases.