Air quality monitoring is a critical component of environmental management, especially in developing countries where pollution levels are a growing concern. This review systematically analyzes recent advances in Internet-of-Things (IoT)-based air quality monitoring systems and highlights the impact of artificial intelligence (AI) technologies. A comprehensive selection process was used to identify 220 relevant studies using databases such as Google Scholar, Scopus, and ResearchRabbit. Following a selection process based on specific eligibility criteria, a total of 147 studies were chosen for a detailed analysis. These studies present notable advances in the application of artificial intelligence to improve data accuracy, predictive capabilities, and real-time analysis in air quality monitoring systems. A key contribution of this review is the proposal of a classification framework for AI techniques in air quality monitoring, organized into five main application areas: data imputation, sensor calibration, anomaly detection, air quality index (AQI) estimation, and short-term forecasting. The review takes an in-depth look at the different uses of these technologies in both urban and industrial settings, presenting successful case studies that showcase their effectiveness in addressing pressing air quality issues. Additionally, the paper identifies research gaps in the literature, particularly related to data quality, system scalability, and integration challenges in AI-driven IoT systems. The insights provided aim to guide researchers and practitioners in selecting appropriate AI techniques and system architectures, inform the design of more reliable and scalable air quality monitoring frameworks, and support future efforts to mitigate air pollution through data-driven decision-making.

For a significant number of people with visual impairments, public transport plays an important role in productivity, community participation, and independence, since it may be the only feasible mobility option to participate in their education, work, medical care, food, and to attend many other places in their community. To use the public bus system safely, effectively, and autonomously, these people need to collect information about their physical environment and visible information at stops and terminals, such as timetables, routes, etc. Unfortunately, most people who are blind or visually impaired experience difficulties in getting on the right bus or getting off at the right destination. These situations usually force them to depend on other people that assist them in activities close to their homes, or settle for simpler jobs, or simply stay at home. Therefore, our efforts should aim to develop a system where technology is used to empower people with visual disabilities, allowing them to navigate autonomously in the public transport system. This paper presents a system based on radio frequency (RF) communication proposed within the framework of the MOVIDIS (Mobility for Visually Disabled People) research project (funded by the National Secretariat of Science, Technology and Innovation-SENACYT, under Grants No. 109-2015-4-FID14-073 and No. 99-2018-4-FID17-031), which provides an alternative to assist people with visual disabilities with their mobility in the public transport system. The various modules of this system communicate with each other by means of radio frequency and allow users to interact with buses and their respective stops. The first experimental results show that RF communication represents a viable option to help people with visual disabilities in public transport services.

This paper presents a study of the main contributions, in terms of the development of electronics and RFID technologies, to assist people with visual disabilities in their mobilization in indoor spaces. The main aspects taken into consideration when designing an assistive system for people with visual impairments for planning and execution of a movement from one place to another and/or for exploration of a site of interest autonomously are included. This study is important to identify the main technologies based on circuits and systems, electronics, ICT, and RF communication that have been proposed to help people with this type of disability in their indoor mobilization, as well as the techniques of location, navigation, orientation, and detection of objects, among other important functionalities for this type of systems. This work allowed us to propose the conceptual design of a novel system based on RFID and electronics technologies to help visually impaired people in their navigation in indoor environments, which will contribute to their social inclusion.

An accurate, economical, and reliable device for detecting falls in persons ambulating with the assistance of an orthopedic walker is crucially important for the elderly and patients with limited mobility. Existing wearable devices, such as wristbands, are not designed for walker users, and patients may not wear them at all times. This research proposes a novel idea of attaching an internet-of-things (IoT) device with an inertial measurement unit (IMU) sensor directly to an orthopedic walker to perform real-time fall detection and activity logging. A dataset is collected and labeled for walker users in four activities, including idle, motion, step, and fall. Classic machine learning algorithms are evaluated using the dataset by comparing their classification performance. Deep learning with a convolutional neural network (CNN) is also explored. Furthermore, the hardware prototype is designed by integrating a low-power microcontroller for onboard machine learning, an IMU sensor, a rechargeable battery, and Bluetooth wireless connectivity. The research results show the promise of improved safety and well-being of walker users.

Parkinson’s disease (PD) is a progressive neurodegenerative disorder characterized by motor symptoms, with tremors being one of the most prominent. Traditional assessment methods, such as the Unified Parkinson’s Disease Rating Scale (UPDRS), rely on subjective, intermittent evaluations, which can miss symptom fluctuations. This study presents the development and validation of the ELENA system, an IoT-based wearable device designed for the continuous monitoring of tremors in PD patients and medication tracking in PD patients. Named in honor of a 67-year-old woman who has lived with Parkinson’s since 2011 and inspired the project, the ELENA system integrates an MPU6050 accelerometer, an ESP32 microcontroller, and cloud-based data analysis and MATLAB. The ELENA system was calibrated and validated against an Apple Watch, demonstrating high accuracy with frequency deviations under 0.5% and an average percentage error of −0.37%. Unlike commercial devices, ELENA offers a clinical-grade solution with customizable data access and visualization tailored for healthcare providers. Participants, including PD patients and a non-PD control group, completed a series of clinical tasks to evaluate tremor monitoring capabilities. The results showed that the system effectively captured tremor frequency and amplitude, enabling the analysis of resting, action, and postural tremors. This study highlights the ELENA system’s potential to enhance PD management by providing real-time, remote monitoring of tremors. The scalable, cost-effective solution supports healthcare professionals in tracking disease progression and optimizing treatment plans, paving the way for improved patient outcomes.