arXiv subjects

Kleanthis Malialis

Publications and source records attributed to Kleanthis Malialis.

At least 19 recordsLinked to original sources

arXiv2026

A Comparative Study of Deep Learning Architectures for Multi-Horizon Behavioural Forecasting for Mobile Health

Wearable devices and smartphones generate rich behavioural time series that can support proactive health interventions, yet systematic comparisons of modern forecasting architectures for these data are lacking. In particular, it remains unclear how models generalise across populations, how different architectures respond to participant-level fine-tuning and how forecasting accuracy degrades across multi-day horizons. We benchmark six deep learning architectures, two zero-shot Foundation Models (FM) and statistical baselines on three public datasets encompassing over 800 participants, reporting per-feature metrics for step counts, screen time and sleep duration across 1-8 day horizons. We further conduct a per-feature personalisation study across all six architectures and assess FM transferability across dataset sizes and temporal granularities. Our key findings are: (i) no single architecture dominates, PatchTST leads among trained models while the three runners-up (TCN, MLP, Transformer) show no meaningful performance difference; (ii) the FM TimesFM matches or exceeds trained models zero-shot, especially in low-data regimes and (iii) participant-level fine-tuning reduces per-feature RMSE by 16-60\%, with sleep benefiting most and step counts least. These results provide practical guidance on architecture selection, FM applicability and personalisation strategies for mobile health forecasting. To the best of our knowledge, this is the first study to jointly evaluate modern deep learning, FMs and personalisation for multi-horizon behavioural forecasting from wearables.

cs.LG↗

arXiv2026

A Novel end-to-end Digital Health System Using Deep Learning-based ECG Analysis

This study presents AI-HEART, a cloud-based information system for managing and analysing long-duration ambulatory electrocardiogram (ECG) recordings and supporting clinician decision-making. The platform operationalises an end-to-end pipeline that ingests multi-day three-lead ECGs, normalises inputs, performs signal preprocessing, and applies dedicated deep neural networks for wave delineation, noise/quality detection, and beat- and rhythm-level multi-class arrhythmia classification. To address class imbalance and real-world signal variability, model development combines large clinically annotated datasets with expert-in-the-loop curation and generative augmentation for under-represented rhythms. Empirical evaluation on three-lead ambulatory ECG data shows that delineation accuracy is sufficient for automated interval measurement, noise detection reliably flags poor-quality segments, and arrhythmia classification achieves high specificity with clinically useful macro-averaged performance across common and rarer rhythms. Beyond predictive accuracy, AI-HEART provides a scalable deployment approach for integrating AI into routine ECG services, enabling traceable outputs, audit-friendly storage of recordings and derived annotations, and clinician review/editing that captures feedback for controlled model improvement. The findings demonstrate the technical feasibility and operational value of a noise-aware AI-ECG platform as a digital health information system.

eess.SP↗

arXiv2026

Drift-Aware Variational Autoencoder-based Anomaly Detection with Two-level Ensembling

In today's digital world, the generation of vast amounts of streaming data in various domains has become ubiquitous. However, many of these data are unlabeled, making it challenging to identify events, particularly anomalies. This task becomes even more formidable in nonstationary environments where model performance can deteriorate over time due to concept drift. To address these challenges, this paper presents a novel method, VAE++ESDD, which employs incremental learning and two-level ensembling: an ensemble of Variational AutoEncoder(VAEs) for anomaly prediction, along with an ensemble of concept drift detectors. Each drift detector utilizes a statistical-based concept drift mechanism. To evaluate the effectiveness of VAE++ESDD, we conduct a comprehensive experimental study using real-world and synthetic datasets characterized by severely or extremely low anomalous rates and various drift characteristics. Our study reveals that the proposed method significantly outperforms both strong baselines and state-of-the-art methods.

cs.LG↗

arXiv2026

Resilient Class-Incremental Learning: on the Interplay of Drifting, Unlabelled and Imbalanced Data Streams

In today's connected world, the generation of massive streaming data across diverse domains has become commonplace. In the presence of concept drift, class imbalance, label scarcity, and new class emergence, they jointly degrade representation stability, bias learning toward outdated distributions, and reduce the resilience and reliability of detection in dynamic environments. This paper proposes SCIL (Streaming Class-Incremental Learning) to address these challenges. The SCIL framework integrates an autoencoder (AE) with a multi-layer perceptron for multi-class prediction, uses a dual-loss strategy (classification and reconstruction) for prediction and new class detection, employs corrected pseudo-labels for online training, manages classes with queues, and applies oversampling to handle imbalance. The rationale behind the method's structure is elucidated through ablation studies and a comprehensive experimental evaluation is performed using both real-world and synthetic datasets that feature class imbalance, incremental classes, and concept drifts. Our results demonstrate that SCIL outperforms strong baselines and state-of-the-art methods. Based on our commitment to Open Science, we make our code and datasets available to the community.

cs.LG↗

arXiv2026

Low Rank Transformer for Multivariate Time Series Anomaly Detection and Localization

Multivariate time series (MTS) anomaly diagnosis, which encompasses both anomaly detection and localization, is critical for the safety and reliability of complex, large-scale real-world systems. The vast majority of existing anomaly diagnosis methods offer limited theoretical insights, especially for anomaly localization, which is a vital but largely unexplored area. The aim of this contribution is to study the learning process of a Transformer when applied to MTS by revealing connections to statistical time series methods. Based on these theoretical insights, we propose the Attention Low-Rank Transformer (ALoRa-T) model, which applies low-rank regularization to self-attention, and we introduce the Attention Low-Rank score, effectively capturing the temporal characteristics of anomalies. Finally, to enable anomaly localization, we propose the ALoRa-Loc method, a novel approach that associates anomalies to specific variables by quantifying interrelationships among time series. Extensive experiments and real data analysis, show that the proposed methodology significantly outperforms state-of-the-art methods in both detection and localization tasks.

cs.LG↗

arXiv2026

Cross-Country Learning for National Infectious Disease Forecasting Using European Data

Accurate forecasting of infectious disease incidence is critical for public health planning and timely intervention. While most data-driven forecasting approaches rely primarily on historical data from a single country, such data are often limited in length and variability, restricting the performance of machine learning (ML) models. In this work, we investigate a cross-country learning approach for infectious disease forecasting, in which a single model is trained on time series data from multiple countries and evaluated on a country of interest. This setting enables the model to exploit shared epidemic dynamics across countries and to benefit from an enlarged training set. We examine this approach through a case study on COVID-19 case forecasting in Cyprus, using surveillance data of European countries. We evaluate multiple models and analyse the impact of the lookback window length and cross-country 'data augmentation' on multi-step forecasting performance. The results show that combining data from other countries can lead to consistent improvements over models trained solely on national data. Although the focus is on Cyprus and COVID-19, the framework and findings provide promising insights for infectious disease forecasting in settings with limited national data.

q-bio.PE↗

arXiv2025

Unsupervised Online Detection of Pipe Blockages and Leakages in Water Distribution Networks

Water Distribution Networks (WDNs), critical to public well-being and economic stability, face challenges such as pipe blockages and background leakages, exacerbated by operational constraints such as data non-stationarity and limited labeled data. This paper proposes an unsupervised, online learning framework that aims to detect two types of faults in WDNs: pipe blockages, modeled as collective anomalies, and background leakages, modeled as concept drift. Our approach combines a Long Short-Term Memory Variational Autoencoder (LSTM-VAE) with a dual drift detection mechanism, enabling robust detection and adaptation under non-stationary conditions. Its lightweight, memory-efficient design enables real-time, edge-level monitoring. Experiments on two realistic WDNs show that the proposed approach consistently outperforms strong baselines in detecting anomalies and adapting to recurrent drift, demonstrating its effectiveness in unsupervised event detection for dynamic WDN environments.

cs.LG↗

arXiv2025

Investigating Forecasting Models for Pandemic Infections Using Heterogeneous Data Sources: A 2-year Study with COVID-19

Emerging in December 2019, the COVID-19 pandemic caused widespread health, economic, and social disruptions. Rapid global transmission overwhelmed healthcare systems, resulting in high infection rates, hospitalisations, and fatalities. To minimise the spread, governments implemented several non-pharmaceutical interventions like lockdowns and travel restrictions. While effective in controlling transmission, these measures also posed significant economic and societal challenges. Although the WHO declared COVID-19 no longer a global health emergency in May 2023, its impact persists, shaping public health strategies. The vast amount of data collected during the pandemic offers valuable insights into disease dynamics, transmission, and intervention effectiveness. Leveraging these insights can improve forecasting models, enhancing preparedness and response to future outbreaks while mitigating their social and economic impact. This paper presents a large-scale case study on COVID-19 forecasting in Cyprus, utilising a two-year dataset that integrates epidemiological data, vaccination records, policy measures, and weather conditions. We analyse infection trends, assess forecasting performance, and examine the influence of external factors on disease dynamics. The insights gained contribute to improved pandemic preparedness and response strategies.

q-bio.PE↗

arXiv2025

SiameseDuo++: Active Learning from Data Streams with Dual Augmented Siamese Networks

Data stream mining, also known as stream learning, is a growing area which deals with learning from high-speed arriving data. Its relevance has surged recently due to its wide range of applicability, such as, critical infrastructure monitoring, social media analysis, and recommender systems. The design of stream learning methods faces significant research challenges; from the nonstationary nature of the data (referred to as concept drift) and the fact that data streams are typically not annotated with the ground truth, to the requirement that such methods should process large amounts of data in real-time with limited memory. This work proposes the SiameseDuo++ method, which uses active learning to automatically select instances for a human expert to label according to a budget. Specifically, it incrementally trains two siamese neural networks which operate in synergy, augmented by generated examples. Both the proposed active learning strategy and augmentation operate in the latent space. SiameseDuo++ addresses the aforementioned challenges by operating with limited memory and limited labelling budget. Simulation experiments show that the proposed method outperforms strong baselines and state-of-the-art methods in terms of learning speed and/or performance. To promote open science we publicly release our code and datasets.

cs.LG↗

arXiv2025

Transformer-based Multivariate Time Series Anomaly Localization

With the growing complexity of Cyber-Physical Systems (CPS) and the integration of Internet of Things (IoT), the use of sensors for online monitoring generates large volume of multivariate time series (MTS) data. Consequently, the need for robust anomaly diagnosis in MTS is paramount to maintaining system reliability and safety. While significant advancements have been made in anomaly detection, localization remains a largely underexplored area, though crucial for intelligent decision-making. This paper introduces a novel transformer-based model for unsupervised anomaly diagnosis in MTS, with a focus on improving localization performance, through an in-depth analysis of the self-attention mechanism's learning behavior under both normal and anomalous conditions. We formulate the anomaly localization problem as a three-stage process: time-step, window, and segment-based. This leads to the development of the Space-Time Anomaly Score (STAS), a new metric inspired by the connection between transformer latent representations and space-time statistical models. STAS is designed to capture individual anomaly behaviors and inter-series dependencies, delivering enhanced localization performance. Additionally, the Statistical Feature Anomaly Score (SFAS) complements STAS by analyzing statistical features around anomalies, with their combination helping to reduce false alarms. Experiments on real world and synthetic datasets illustrate the model's superiority over state-of-the-art methods in both detection and localization tasks.

cs.LG↗

arXiv2025

Cooperative Search and Track of Rogue Drones using Multiagent Reinforcement Learning

This work considers the problem of intercepting rogue drones targeting sensitive critical infrastructure facilities. While current interception technologies focus mainly on the jamming/spoofing tasks, the challenges of effectively locating and tracking rogue drones have not received adequate attention. Solving this problem and integrating with recently proposed interception techniques will enable a holistic system that can reliably detect, track, and neutralize rogue drones. Specifically, this work considers a team of pursuer UAVs that can search, detect, and track multiple rogue drones over a sensitive facility. The joint search and track problem is addressed through a novel multiagent reinforcement learning scheme to optimize the agent mobility control actions that maximize the number of rogue drones detected and tracked. The performance of the proposed system is investigated under realistic settings through extensive simulation experiments with varying number of agents demonstrating both its performance and scalability.

cs.MA↗

arXiv2025

Online Detection of Water Contamination Under Concept Drift

Water Distribution Networks (WDNs) are vital infrastructures, and contamination poses serious public health risks. Harmful substances can interact with disinfectants like chlorine, making chlorine monitoring essential for detecting contaminants. However, chlorine sensors often become unreliable and require frequent calibration. This study introduces the Dual-Threshold Anomaly and Drift Detection (AD&DD) method, an unsupervised approach combining a dual-threshold drift detection mechanism with an LSTM-based Variational Autoencoder(LSTM-VAE) for real-time contamination detection. Tested on two realistic WDNs, AD&DD effectively identifies anomalies with sensor offsets as concept drift, and outperforms other methods. A proposed decentralized architecture enables accurate contamination detection and localization by deploying AD&DD on selected nodes.

cs.LG↗

arXiv2024

Urban Water Consumption Forecasting Using Deep Learning and Correlated District Metered Areas

Accurate water consumption forecasting is a crucial tool for water utilities and policymakers, as it helps ensure a reliable supply, optimize operations, and support infrastructure planning. Urban Water Distribution Networks (WDNs) are divided into District Metered Areas (DMAs), where water flow is monitored to efficiently manage resources. This work focuses on short-term forecasting of DMA consumption using deep learning and aims to address two key challenging issues. First, forecasting based solely on a DMA's historical data may lack broader context and provide limited insights. Second, DMAs may experience sensor malfunctions providing incorrect data, or some DMAs may not be monitored at all due to computational costs, complicating accurate forecasting. We propose a novel method that first identifies DMAs with correlated consumption patterns and then uses these patterns, along with the DMA's local data, as input to a deep learning model for forecasting. In a real-world study with data from five DMAs, we show that: i) the deep learning model outperforms a classical statistical model; ii) accurate forecasting can be carried out using only correlated DMAs' consumption patterns; and iii) even when a DMA's local data is available, including correlated DMAs' data improves accuracy.

cs.LG↗

arXiv2024

Incremental Learning with Concept Drift Detection and Prototype-based Embeddings for Graph Stream Classification

Data stream mining aims at extracting meaningful knowledge from continually evolving data streams, addressing the challenges posed by nonstationary environments, particularly, concept drift which refers to a change in the underlying data distribution over time. Graph structures offer a powerful modelling tool to represent complex systems, such as, critical infrastructure systems and social networks. Learning from graph streams becomes a necessity to understand the dynamics of graph structures and to facilitate informed decision-making. This work introduces a novel method for graph stream classification which operates under the general setting where a data generating process produces graphs with varying nodes and edges over time. The method uses incremental learning for continual model adaptation, selecting representative graphs (prototypes) for each class, and creating graph embeddings. Additionally, it incorporates a loss-based concept drift detection mechanism to recalculate graph prototypes when drift is detected.

cs.LG↗

arXiv2024

Unsupervised Incremental Learning with Dual Concept Drift Detection for Identifying Anomalous Sequences

In the contemporary digital landscape, the continuous generation of extensive streaming data across diverse domains has become pervasive. Yet, a significant portion of this data remains unlabeled, posing a challenge in identifying infrequent events such as anomalies. This challenge is further amplified in non-stationary environments, where the performance of models can degrade over time due to concept drift. To address these challenges, this paper introduces a new method referred to as VAE4AS (Variational Autoencoder for Anomalous Sequences). VAE4AS integrates incremental learning with dual drift detection mechanisms, employing both a statistical test and a distance-based test. The anomaly detection is facilitated by a Variational Autoencoder. To gauge the effectiveness of VAE4AS, a comprehensive experimental study is conducted using real-world and synthetic datasets characterized by anomalous rates below 10\% and recurrent drift. The results show that the proposed method surpasses both robust baselines and state-of-the-art techniques, providing compelling evidence for their efficacy in effectively addressing some of the challenges associated with anomalous sequence detection in non-stationary streaming data.

cs.CE↗

arXiv2024

Pandemic infection forecasting through compartmental model and learning-based approaches

The emergence and spread of deadly pandemics has repeatedly occurred throughout history, causing widespread infections and loss of life. The rapid spread of pandemics have made governments across the world adopt a range of actions, including non-pharmaceutical measures to contain its impact. However, the dynamic nature of pandemics makes selecting intervention strategies challenging. Hence, the development of suitable monitoring and forecasting tools for tracking infected cases is crucial for designing and implementing effective measures. Motivated by this, we present a hybrid pandemic infection forecasting methodology that integrates compartmental model and learning-based approaches. In particular, we develop a compartmental model that includes time-varying infection rates, which are the key parameters that determine the pandemic's evolution. To identify the time-dependent infection rates, we establish a hybrid methodology that combines the developed compartmental model and tools from optimization and neural networks. Specifically, the proposed methodology estimates the infection rates by fitting the model to available data, regarding the COVID-19 pandemic in Cyprus, and then predicting their future values through either a) extrapolation, or b) feeding them to neural networks. The developed approach exhibits strong accuracy in predicting infections seven days in advance, achieving low average percentage errors both using the extrapolation (9.90%) and neural network (5.04%) approaches.

q-bio.PE↗

arXiv2023

Unsupervised Unlearning of Concept Drift with Autoencoders

Concept drift refers to a change in the data distribution affecting the data stream of future samples. Consequently, learning models operating on the data stream might become obsolete, and need costly and difficult adjustments such as retraining or adaptation. Existing methods usually implement a local concept drift adaptation scheme, where either incremental learning of the models is used, or the models are completely retrained when a drift detection mechanism triggers an alarm. This paper proposes an alternative approach in which an unsupervised and model-agnostic concept drift adaptation method at the global level is introduced, based on autoencoders. Specifically, the proposed method aims to ``unlearn'' the concept drift without having to retrain or adapt any of the learning models operating on the data. An extensive experimental evaluation is conducted in two application domains. We consider a realistic water distribution network with more than 30 models in-place, from which we create 200 simulated data sets / scenarios. We further consider an image-related task to demonstrate the effectiveness of our method.

cs.LG↗

arXiv2023

A Study of Data-driven Methods for Adaptive Forecasting of COVID-19 Cases

Severe acute respiratory disease SARS-CoV-2 has had a found impact on public health systems and healthcare emergency response especially with respect to making decisions on the most effective measures to be taken at any given time. As demonstrated throughout the last three years with COVID-19, the prediction of the number of positive cases can be an effective way to facilitate decision-making. However, the limited availability of data and the highly dynamic and uncertain nature of the virus transmissibility makes this task very challenging. Aiming at investigating these challenges and in order to address this problem, this work studies data-driven (learning, statistical) methods for incrementally training models to adapt to these nonstationary conditions. An extensive empirical study is conducted to examine various characteristics, such as, performance analysis on a per virus wave basis, feature extraction, "lookback" window size, memory size, all for next-, 7-, and 14-day forecasting tasks. We demonstrate that the incremental learning framework can successfully address the aforementioned challenges and perform well during outbreaks, providing accurate predictions.

cs.LG↗