Background/Objectives: Gait analysis, traditionally performed with lab-based optical motion capture systems, offers high accuracy but is costly and impractical for real-world use. Wearable technologies, especially inertial measurement units (IMUs), enable portable and accessible assessments outside the lab, though challenges with sensor placement, signal selection, and algorithm design can affect accuracy. This systematic review aims to bridge the benchmarking gap between IMU-based and traditional systems, validating the use of wearable inertial systems for gait analysis. Methods: This review examined English studies between 2012 and 2023, retrieved from the Scopus database, comparing wearable sensors to optical motion capture systems, focusing on IMU body placement, gait parameters, and validation metrics. Exclusion criteria for the search included conference papers, reviews, unavailable papers, studies without wearable inertial sensors for gait analysis, and those not involving agreement studies or optical motion capture systems. Results: From an initial pool of 479 articles, 32 were selected for full-text screening. Among them, the lower body resulted in the most common site for single IMU placement (in 22 studies), while the most frequently used multi-sensor configuration involved IMU positioning on the lower back, shanks, feet, and thighs (10 studies). Regarding gait parameters, 11 studies out of the 32 included studies focused on spatial-temporal parameters, 12 on joint kinematics, 2 on gait events, and the remainder on a combination of parameters. In terms of validation metrics, 24 studies employed correlation coefficients as the primary measure, while 7 studies used a combination of error metrics, correlation coefficients, and Bland–Altman analysis. Validation metrics revealed that IMUs exhibited good to moderate agreement with optical motion capture systems for kinematic measures. In contrast, spatiotemporal parameters demonstrated greater variability, with agreement ranging from moderate to poor. Conclusions: This review highlighted the transformative potential of wearable IMUs in advancing gait analysis beyond the constraints of traditional laboratory-based systems.

The tumor grading of laryngeal cancer pathological images needs to be accurate and interpretable. The deep learning model based on the attention mechanism-integrated convolution (AMC) block has good inductive bias capability but poor interpretability, whereas the deep learning model based on the vision transformer (ViT) block has good interpretability but weak inductive bias ability. Therefore, we propose an end-to-end ViT-AMC network (ViT-AMCNet) with adaptive model fusion and multiobjective optimization that integrates and fuses the ViT and AMC blocks. However, existing model fusion methods often have negative fusion: 1). There is no guarantee that the ViT and AMC blocks will simultaneously have good feature representation capability. 2). The difference in feature representations learning between the ViT and AMC blocks is not obvious, so there is much redundant information in the two feature representations. Accordingly, we first prove the feasibility of fusing the ViT and AMC blocks based on Hoeffding’s inequality. Then, we propose a multiobjective optimization method to solve the problem that ViT and AMC blocks cannot simultaneously have good feature representation. Finally, an adaptive model fusion method integrating the metrics block and the fusion block is proposed to increase the differences between feature representations and improve the deredundancy capability. Our methods improve the fusion ability of ViT-AMCNet, and experimental results demonstrate that ViT-AMCNet significantly outperforms state-of-the-art methods. Importantly, the visualized interpretive maps are closer to the region of interest of concern by pathologists, and the generalization ability is also excellent. Our code is publicly available at https://github.com/Baron-Huang/ViT-AMCNet.

Modern cars include a huge number of sensors and actuators, which continuously exchange data and control commands. The most used protocol for communication of different components in automotive system is the Controller Area Network (CAN). According to CAN, components communicate by broadcasting messages on a bus. In addition, the standard definition of the protocol does not provide information for authentication, so exposing it to attacks. This paper proposes a method based on deep learning aiming at discovering attacks towards the CAN-bus. In particular, Neural Networks and MultiLayer Perceptrons are the class of networks employed in our approach. We also validate our approach by analysing a real-world dataset with the injection of messages from different types of attacks: denial of service, fuzzy pattern attacks, and attacks against specific components. The obtained results are encouraging and demonstrate the effectiveness of the approach.

Background: Respiratory sound analysis represents a research topic of growing interest in recent times. In fact, in this area, there is the potential to automatically infer the abnormalities in the preliminary stages of a lung dysfunction. Methods: In this paper, we propose a method to analyse respiratory sounds in an automatic way. The aim is to show the effectiveness of machine learning techniques in respiratory sound analysis. A feature vector is gathered directly from breath audio and, thus, by exploiting supervised machine learning techniques, we detect if the feature vector is related to a patient affected by a lung disease. Moreover, the proposed method is able to characterise the lung disease in asthma, bronchiectasis, bronchiolitis, chronic obstructive pulmonary disease, pneumonia, and lower or upper respiratory tract infection. Results: A retrospective experimental analysis on 126 patients with 920 recording sessions showed the effectiveness of the proposed method. Conclusion: The experimental analysis demonstrated that it is possible to detect lung disease by exploiting machine learning techniques. We considered several supervised machine learning algorithms, obtaining the most interesting performance with the neural network model, with an F-Measure of 0.983 in lung disease detection and equal to 0.923 in lung disease characterisation, increasing the state-of-the-art performance.