Andreas Menychtas

Academic stress in higher education is strongly influenced by workload structure and scheduling decisions, yet academic planning sometimes remains static and does not incorporate behavioural or physiological indicators. While existing research focuses on stress measurement and prediction, these approaches are rarely integrated into decision-support mechanisms capable of restructuring academic schedules. This work introduces a Course Digital Twin (CDT) framework that integrates multimodal student data with simulation-based academic planning. The proposed system models course scheduling as a decision-support problem, where alternative configurations are evaluated using a structured stress model combining wearable-derived physiological signals, self-reported stress measures, and contextual academic workload indicators. The framework employs a hybrid approach in which machine learning is used for physiological stress estimation, while schedule adaptation is performed through transparent rule-based mechanisms. The system was implemented as an end-to-end platform including mobile sensing, course configuration interfaces, and instructor analytics dashboards, and was evaluated through a pilot deployment across multiple postgraduate courses. Preliminary results indicate that simulation-based schedule adjustments are associated with reductions in projected peak stress levels and improved workload distribution patterns. The findings demonstrate the feasibility of integrating multimodal stress modelling and Digital Twin simulation into academic planning workflows. The proposed framework provides a foundation for future stress-aware scheduling systems, although further large-scale validation is required to establish its effectiveness and generalizability.

Accurately classifying gait abnormalities is crucial for the effective monitoring and rehabilitation of stroke patients. This study proposed a lightweight machine learning framework for distinguishing healthy from abnormal gait patterns using statistical features extracted from wearable gyroscope data. Statistical z-axis angular velocity values from both limbs were derived and used to evaluate the performance of multiple classifiers, including logistic regression, support vector machines, and ensemble methods. A leave-one-out cross-validation strategy was employed to enhance generalizability across subjects. The results indicated that several classifiers achieve accuracy and area under the curve (AUC) values exceeding 0.95, with random forest and support vector machine-based models demonstrating near-perfect class separability, with an AUC of 0.98. These findings highlighted the effectiveness of using minimal set of biomechanically relevant gyroscope features for gait classification in real-world healthcare applications. The proposed pipeline is computationally efficient, making it well suited for implementing in wearable and remote monitoring systems.

The rapid evolution of Generative AI (GenAI) has created the conditions for developing innovative solutions that disrupt all fields of human-related activities. Within the healthcare sector, numerous AI-driven applications have emerged, offering comprehensive health-related insights and addressing user questions in real time. Nevertheless, most of them use general-purpose Large Language Models (LLMs); consequently, the responses may not be as accurate as required in clinical settings. Therefore, the research community is adopting efficient architectures, such as Multi-Agent Systems (MAS) to optimize task allocation, reasoning processes, and system scalability. Most recently, the Model Context Protocol (MCP) has been introduced; however, very few applications apply this protocol within a healthcare MAS. Furthermore, Retrieval-Augmented Generation (RAG) has proven essential for grounding AI responses in verified clinical literature. This paper proposes a novel architecture that integrates these technologies to create an advanced Agentic Corrective RAG (CRAG) system. Unlike standard approaches, this method incorporates an active evaluation layer that autonomously detects retrieval failures and triggers corrective fallback mechanisms to ensure safety and accuracy. A comparative analysis was conducted for this architecture against Typical RAG and Cache-Augmented Generation (CAG), demonstrating that the proposed solution improves workflow efficiency and enables more accurate, context-aware interventions in healthcare.

Gait analysis is important in understanding human movement and diagnosing various mobility-related disorders. A crucial step in this procedure is the recognition of the different phases of human gait. An innovative, cost-effective prototype of shoe insoles with sensors is presented, designed to capture data which are used for gait phase recognition with the aid of artificial intelligence. Each insole is embedded with capacitive sensors to record measurements and is accompanied by an inertial measurement unit (IMU) that monitors foot motion during walking. Using these prototypes, we collected data from multiple volunteers while they performed simple walking exercises. The collected data, having undergone preprocessing, were used to train a Long Short-Term Memory (LSTM)-based neural network that recognizes the different gait phases during walking. The resulting model can segment a gait session into distinct phases with high accuracy, effectively demonstrating the capability of the prototype pair of insoles to be used as an inexpensive way to record data that can be used for gait analysis. The presented method has potential applications in rehabilitation and the early detection of mobility impairments. The most important benefit of the developed system is that it constitutes an affordable alternative to commercial solutions for patients who require medical care through telemedicine.

The formulation of touristic policies is a time-consuming process that consists of a wide range of steps and procedures. These policies are highly dependent on the number of tourists and visitors to an area to be as effective as possible. The estimation of this number is not always easy to achieve, since there is a lack of the corresponding data (i.e., number of visitors per day). Hence, this estimation must be achieved by utilizing alternative data sources. To this end, in this paper, the authors propose a neural network architecture that is trained on waste management data to estimate the number of visitors and tourists in the highly touristic municipality of Vari-Voula-Vouliagmeni, Greece.