The detection and prevention of workers’ body straining postures and other stressing conditions within the work environment, supports establishing occupational safety and promoting well being and sustainability at work. Developed methods towards this aim typically rely on combining highly ergonomic workplaces and expensive monitoring mechanisms including wearable devices. In this work, we demonstrate how the input from low-cost sensors, specifically, passive camera sensors installed in a real manufacturing workplace, and smartwatches used by the workers can provide useful feedback on the workers’ conditions and can yield key indicators for the prevention of work-related musculo-skeletal disorders (WMSD) and physical fatigue. To this end, we study the ability to assess the risk for physical strain of workers online during work activities based on the classification of ergonomically sub-optimal working postures using visual information, the correlation and fusion of these estimations with synchronous worker heart rate data, as well as the prediction of near-future heart rate using deep learning-based techniques. Moreover, a new multi-modal dataset of video and heart rate data captured in a real manufacturing workplace during car door assembly activities is introduced. The experimental results show the efficiency of the proposed approach that exceeds 70% of classification rate based on the F1 score measure using a set of over 300 annotated video clips of real line workers during work activities. In addition a time lagging correlation between the estimated ergonomic risks for physical strain and high heart rate was assessed using a larger dataset of synchronous visual and heart rate data sequences. The statistical analysis revealed that imposing increased strain to body parts will results in an increase to the heart rate after 100–120 s. This finding is used to improve the short term forecasting of worker’s cardiovascular activity for the next 10 to 30 s by fusing the heart rate data with the estimated ergonomic risks for physical strain and ultimately to train better predictive models for worker fatigue.

The increasing integration of AI-driven interfaces into public service channels has catalyzed a vibrant discourse on the interplay between technological innovation and the traditional values of public governance. This discussion invites a critical exploration of how emerging chatbot architectures can be aligned with ethical principles and resilient public sector practices. While there is research assessing the potential benefits of integrating chatbots in service delivery, existing evaluation approaches often lack specificity to the unique context of public administration, failing to adequately balance technical performance with crucial ethical considerations, safety requirements, and core public service principles like transparency, fairness, and accountability. This research addresses this critical gap by developing and applying a structured evaluation framework specifically designed for assessing diverse chatbot architectures within the public sector. The methodology offers actionable insights to guide the selection and implementation of chatbot solutions that enhance citizen engagement, streamline government services, and uphold key public service values. A key contribution is the introduction of fifteen pre-assessed evaluation criteria, encompassing areas such as input understanding, error handling, legal compliance, safety, and personalization, which are applied to four distinct chatbot architectures. Our findings indicate that while no single architecture is universally optimal, hybrid retrieval-augmented generation (RAG) systems emerge as the most balanced approach, effectively mitigating the risks of pure generative models while retaining their adaptability. Ultimately, this work provides actionable guidance for policymakers and researchers, supporting informed decisions on the responsible use of chatbots and emphasizing the critical balance between innovation and public trust.