Mariana Jacob Rodrigues

The existing portable ECG systems are reliable for continuous monitoring, but they provide output in numerical values and in binary alarms. Herein, a single-lead non-invasive cardiac monitoring system named ‘CorSeg’ is presented, where AI-driven natural language feedback has been integrated. Additionally, HRV features, including RMSSD and SDNN, have been derived from five minutes of ECG recording. The metrics such as RR intervals, HR, and HRV features are combined with contextual data to form a local summary and to feed the AI model (GPT-4.1-Nano) through API invocation. The experiment has been performed with a FLUKE ECG simulator and with limited volunteers to observe the AI feedback.

Urban environments expose individuals to multiple stressors, including air pollution and noise, which significantly impact health by causing cardiovascular and respiratory diseases and sleep disruption. Effective monitoring of these stressors through intelligent sensing technologies can support the mitigation of long-term deterioration in both physical and mental health. In this context, this pilot study presents a multimodal approach that integrates environmental sensing and physiological monitoring to assess stress responses of the human body to urban conditions. Indoor and outdoor air quality were measured using smart sensor nodes that captured particulate matter (PM₁, PM_2.5, PM₄, PM₁₀), air temperature and relative humidity. The physiological response to urban noise exposure was evaluated using electrodermal activity (EDA) and heart rate variability (HRV) acquired via a wearable biomedical device, while sound pressure levels (dBA) were measured using a professional sound level meter. Preliminary results indicate that indoor particulate matter concentrations greatly exceeded outdoor levels, despite outdoor sensors being deployed in a high-traffic urban environment. Physiological analysis revealed increased tonic electrodermal activity under noise exposure, indicating increased sympathetic activation. Complementary HRV analysis showed elevated heart rate (HR), reduced parasympathetic activity, and increased sympathetic dominance under high-noise conditions, confirming a measurable physiological stress response to urban environmental exposure.

This chapter explores strategies to increase well-being and reduce stress by analyzing the effects of external stimuli on physiological responses. It examines musical sound stimulation and its impact on stress and well-being by analyzing heart rate variability (HRV), a key indicator of autonomic nervous system (ANS) balance. It also presents a healthcare-centered Internet of Things (IoT) system for cardiac assessment using photoplethysmography (PPG) and ballistocardiography (BCG). Experimental results from indoor applications evaluate HRV and respiratory patterns under varying temperature and humidity conditions to assess their short-term impact on thermal comfort. In addition, this chapter also presents studies conducted through the implementation of new PPG signal processing algorithms to extract several physiological markers simultaneously, such as heart rate (HR), HRV, respiratory rate (RR) and blood oxygen saturation (SpO2), through the implementation of multichannel detection systems with distributed computing platforms. New models for the classification and quantification of stress levels are also discussed, using artificial intelligence techniques such as fuzzy logic and more complex algorithms. Furthermore, the chapter addresses the development of mobile applications, serving as a patient support tool and also as a way of acquiring important markers, from which it is possible to draw correlations between stress, blood pressure and blood glucose levels. As a way of trying to counteract the effects of stress on patients’ health, studies on alternative techniques for continuous relaxation are also discussed, such as the use of holistic medicine and aromatherapy.

Music sound has shown to affect brain function and cardiac activity. Based on this premise, this study examines the effects of sound stimulation, such as music and stress noise, on the balance of the autonomous nervous system (ANS). To monitor such effects, physiological data was collected from a group of volunteers to analyze pulse rate variability (PRV), as well as electrodermal activity (EDA). The final goals of this study are supported by the possibility of automatically integrating musical stimuli into a smart environment to potentially lower individual’s stress levels, as well as to improve their well-being. To accomplish this objective, this research involved three different phases. The first was based on the development of a biomedical wearable sensor for measuring PRV and its validation using a reference sensing system. Good correlation results were obtained between both devices. The second consisted of a preliminary study of the effects of ambient, classic and metal music on PRV. Significant variations of PRV were measured between the three music genres. Considering the obtained results in the previous phase and overcoming the limitations presented in it, the third phase was based on a more in-depth study of the effects of musical stimuli and noise stress, through PRV analysis and the measurement of galvanic skin response (GSR). The obtained results suggested that noise stress contributes to the increasing of sympathetic activity. In contrast, ambient music proved to be very effective in increasing parasympathetic activity and stabilizing comfort levels.

The achievement of a healthy indoor environment - an indispensable requirement for human well-being - relies on the establishment of good air quality conditions and thermal comfort levels. This study addresses the development of a healthcare-focused Internet of Things (IoT) system for cardiac assessment using photoplethysmography (PPG) and ballistocardiography (BCG) that can be applied in any indoor environment. Results from its experimental application include the analysis of heart rate variability (HRV) and respiratory status from a group of young adults under different thermal conditions and relative humidity levels. The final goal was to investigate the effects of a short-term exposure of different air temperature and humidity conditions on human thermal comfort, based on the analysis of the autonomic nervous system (ANS) activity. The experiment took place in a regular and non-isothermal office environment. Simulations based on computational fluid dynamics (CFD) were conducted to estimate heat distribution and select the optimal locations for the environmental sensor nodes’s placement. Results indicated that an activation of the parasympathetic system was more notable in short-term exposures to environments with different air temperatures (24°C – 30°C) than with different levels of relative humidity (50% - 70%). Changes in ambient air temperature led to the activation of thermal regulatory reflexes and thermal discomfort, perceived by an increase of the ratio of low frequency to high frequency (LF/HF) at higher air temperature exposures. Additionally, HRV parameters were used to train machine learning models on predicting if the user is at a thermally comfortable environment or discomfortable environment (hot or humid), having achieved an 87% average accuracy.

The purpose of this practical approach was to extract the relations between music stimulation and heart rate variability (HRV) in healthy volunteers. Different kinds of music were considered, including ambient, classic, and metal music genres. The study was carried out trying to understand how the integration of this stimulus can be a relevant feature of a smart environment and people wellbeing. The HRV evolution was based on time-domain and frequency-domain analysis. Preliminary results underline significant variations in HRV when the user is listening to ambient music versus classic and metal music. Moreover, a greater variance of the ratio between low frequencies (LF) and high frequencies (HF) values among all participants was more noticeable when listening to ambient music than all the other music genres, which may reflect lack of focus and a higher tendency to mind wander. The study was based on the usage of a developed wearable smart sensor that includes a photoplethysmography (PPG) measurement channel. The validation of this smart sensor for HRV monitoring was done using an additional ECG sensor node, as a reference cardiac activity measurement channel. HRV monitoring using the developed sensor node revealed a good correlation with the values obtained by the ECG node.

The exposure to colored light with different wavelengths has proved to affect the physiological functions of the human body. To test such influence, this work was focused on heart rate variability (HRV) analysis associated with different colored light exposure of healthy volunteers. A Photoplethysmography (PPG) wireless sensor network node was employed to acquire information about the cardiac activity, as it proves to be a more convenient and less intrusive method as electrocardiography (ECG). A small group of healthy volunteers were exposed to 10 minutes of blue and red light, preceded and followed by 5 minutes of dark lighting conditions. HRV was acquired during the last 5 minutes of each colored illumination period. The HRV analysis was based on time-domain variables, frequency-domain variables and fractal (nonlinear) analysis. The experimental results from this study show that PPG can be considered as a reliable method to study HRV. The exposure to different colored light conducted to HRV variations that characterize the autonomous nervous system balance. Experimental results obtained for volunteers exposed to different illumination conditions are also included in the paper.

Healthcare optimization has become increasingly important in the current era, where numerous challenges are posed by population ageing phenomena and the demand for higher quality of the healthcare services. The implementation of Internet of Things (IoT) in the healthcare ecosystem has been one of the best solutions to address these challenges and therefore to prevent and diagnose possible health impairments in people. The remote monitoring of environmental parameters and how they can cause or mediate any disease, and the monitoring of human daily activities and physiological parameters are among the vast applications of IoT in healthcare, which has brought extensive attention of academia and industry. Assisted and smart tailored environments are possible with the implementation of such technologies that bring personal healthcare to any individual, while living in their preferred environments. In this paper we address several requirements for the development of such environments, namely the deployment of physiological signs monitoring systems, daily activity recognition techniques, as well as indoor air quality monitoring solutions. The machine learning methods that are most used in the literature for activity recognition and body motion analysis are also referred. Furthermore, the importance of physical and cognitive training of the elderly population through the implementation of exergames and immersive environments is also addressed.