11 December 2025 in IEEE Open Journal of Instrumentation and Measurement
The rapid expansion of Artificial Intelligence (AI)—based classification and prediction systems has significantly influenced both scientific research and industry. However, ensuring the effectiveness, reliability, and validity of these systems requires rigorous assessment of their measurement uncertainty. A review of current uncertainty evaluation methods and relevant literature reveals a gap in understanding the suitability of Artificial Neural Networks (ANNs) as measurement instruments. This study addresses the key challenges involved by developing an analytical framework that models the internal behavior of the network. The proposed approach enables the propagation of input measurement uncertainty through the network to estimate the corresponding prediction uncertainty, thus providing informed estimates accompanied by measurement uncertainty in accordance with the ISO GUM standard.
27 November 2025 in IEEE Transactions on Instrumentation and Measurement
Modern powered wheelchairs can greatly improve mobility for individuals with severe motor impairments, but conventional control methods are not always suitable for users with advanced disabilities. This work presents a hybrid measurement framework that combines deep learning–based RGB image analysis with LiDAR sensing to estimate, in real time, the distance between a wheelchair and its caregiver. A YOLO (You Only Look Once) object detection network identifies the caregiver’s foot in RGB frames, guiding LiDAR measurements to the precise foot–ground contact point. A gradient-based refinement process further improves distance accuracy by reducing environmental noise. The system was evaluated through static and dynamic tests under realistic conditions, including variations in elevation and approach angle between the caregiver and the wheelchair user. Results demonstrate high measurement accuracy and repeatability, with mean relative errors below 2% in static tests and below 3% in dynamic scenarios. By focusing on the caregiver as a dynamic and reliable reference, the proposed method offers a practical and robust solution for safe, adaptive mobility in complex environments.
8 October 2025 in IEEE Transactions on Instrumentation and Measurement
The widespread use of MEMS-based Inertial Measurement Units (IMUs) in mission-critical applications, such as aerospace, robotics, and autonomous systems, demands rigorous evaluation of their reliability. In particular, aging effects can significantly degrade the metrological performances of the sensor, impacting also the accuracy of positioning algorithms. This paper presents a methodology to assess the influence of IMU aging on orientation estimation, focusing on two widely used algorithms: the Complementary Filter and the Madgwick Attitude and Heading Reference System (AHRS). A six-month Accelerated Life Testing (ALT) campaign was conducted on 25 IMUs to emulate long-term degradation. Results are then expanded into a realistic life cycle using the Arrhenius degradation model. Drift and uncertainty propagation were analyzed in compliance with the ISO Guide to the Expression of Uncertainty in Measurement (GUM). For the Complementary Filter, analytical modeling using the Law of Propagation of Uncertainty (LPU) was performed, while a novel observation-window approach was proposed to evaluate uncertainty in the recursive Madgwick AHRS. Results showed non-linear performance degradation, with a critical mid-life phase characterized by increased drift and uncertainty. Monte Carlo simulations confirmed the validity of the proposed methods. The framework offers a practical tool for monitoring sensor aging and metrological reliability in long-duration IMU-based systems.