The integration of IoT and Ambient Assisted Living (AAL) enables discreet real-time health monitoring in home environments, offering significant potential for personalized and preventative care. However, challenges persist in balancing privacy, cost, usability, and system reliability. This paper provides an overview of recent advancements in sensor and IoT technologies for assisted living, with a focus on elderly individuals living independently. It categorizes sensor types and technologies that enhance healthcare delivery and explores an interdisciplinary framework encompassing sensing, communication, and decision-making systems. Through this analysis, this paper highlights current applications, identifies emerging challenges, and pinpoints critical areas for future research. This paper aims to inform ongoing discourse and advocate for interdisciplinary approaches in system design to address existing trade-offs and optimize performance.
Transparency is key to enhancing users’ trust by enabling their judgment on the outcomes and consequences of a system’s operations. This paper presents the transparency engineering methodology (TEM) to generate transparency requirements that enable users’ trust judgement. The idea is to identify where transparency is lacking and to address this through patterns augmenting the specification of data, use case, and process requirements. Due to the complexity of software, it is impossible (and undesirable) to achieve full transparency throughout the system. However, transparency can be improved for selected system aspects. This is demonstrated using the results from an industrial case study with a medical technology company where, with the help of TEM, existing functional requirements were refined, and transparency requirements generated systematically.
This paper introduces a traffic signal control system using deep reinforcement learning to solve the congestion problems at signalized intersections under dynamic traffic conditions. The proposed framework is simulated with the help of MATLAB-SUMO co-simulation framework, the traffic signal control is modeled as a Markov Decision Process (MDP). State space includes traffic density, the queue length, vehicles waiting time, and the actual signal phase whereas the action space comprises of the possible selections of the signal phase. A Deep Q-Network (DQN) is utilized to estimate the optimal state-action value function so that green times can be dynamically allocated based on the changing traffic demand. Multi-objective reward functionality is based on the combined minimization of vehicle delay, queue length, and waiting time and maximization of traffic throughput. Experience replay and target network updates are used to stabilize the learning process. Simulation experiments are conducted in low, medium, and high traffic demand conditions to compare the work of the suggested framework with fixed-time control, actuated control, and classical tabular Q-learning methods. Experimental results demonstrate that the proposed framework reduces average delay by up to 33.9%, decreases queue length by 47.1%, and increases throughput by 25.5% compared to fixed-time control under high-demand conditions. Finally, scalability studies involving networks of up to 16 isolated signalized intersections were conducted to assess computational feasibility and robustness even when the size of the network grows. Comprehensively, the results prove the usefulness of deep reinforcement learning in the creation of intelligent and adaptive traffic signal control services in the city.
The rapid miniaturisation of biosensors, be it wearable health monitors, point-of-care diagnostics, and community-scale environmental sensing, has enabled health data collection at a rapidly increasing and more distributed scale across Low- and Middle-Income Countries (LMICs). This rise in the scale of adoption in LMICs is due to these technologies becoming more feasible, portable, and orientated toward low-resource deployment. Yet the Privacy-Enhancing Technologies (PETs) developed to protect these data were designed and validated in high-income, high-compute contexts. This Perspective argues that deploying next-generation miniaturised biosensors for LMICs without rethinking the PET design agenda risks compounding existing health inequities. Current PET implementations face three structural mismatches with LMIC biosensor deployment: the computational overhead of secure multiparty computation and homomorphic encryption exceeds the resource envelope of low-power edge devices; differential privacy can disproportionately degrade model utility for underrepresented populations when datasets are small, imbalanced, or hard to model, conditions that are endemic to LMIC biosensor cohorts; and regulatory-technical translation remains underdeveloped in the jurisdictions where biosensor rollout is accelerating fastest. We propose a reorientation around three design principles: computational proportionality (matching PET selection to hardware constraints), equity-aware privacy budgeting (calibrating differential privacy parameters to population representation), and community data sovereignty (architecting local governance into federated biosensor networks). We identify five priority research questions that reframe the field’s open challenges through an LMIC lens. The goal is not to caution against biosensor deployment, but to ensure that privacy-by-design is embedded in the next-generation of sensing systems, while accounting for adoption challenges and broader digital transformation in resource-constrained health systems.