Violin is one of the most complex musical instruments to learn. The learning process requires constant training and many hours of exercise and is primarily based on a student-teacher interaction where the latter guides the beginner through verbal instructions, visual demonstrations, and physical guidance. The teacher\'s instruction and practice allow the student to learn gradually how to perform the correct gesture autonomously. Unfortunately, these traditional teaching methods require the constant supervision of a teacher and the interpretation of non-real-time feedback provided after the performance. To address these limitations, this work presents a novel interface (Visual Interface for Bowing Evaluation-VIBE) to facilitate student\'s progression throughout the learning process, even in the absence of direct teacher intervention. The proposed interface allows two key parameters of bowing movements to be monitored, namely, the angle between the bow and the string (i.e., α angle) and the bow tilt (i.e., β angle), providing real-time visual feedback on how to correctly move the bow. Results collected on 24 beginners (12 exposed to visual feedback, 12 in a control group) showed a positive effect of the real-time visual feedback on the improvement of bow control. Moreover, the subjects exposed to visual feedback judged the latter as useful to correct their movement and clear in terms of the presentation of data. Although the task was rated as harder when performed with the additional feedback, the subjects did not perceive the presence of a violin teacher as essential to interpret the feedback.

Human Activity Recognition (HAR) plays an important role in the automation of various tasks related to activity tracking in such areas as healthcare and eldercare (telerehabilitation, telemonitoring), security, ergonomics, entertainment (fitness, sports promotion, human-computer interaction, video games), and intelligent environments. This paper tackles the problem of real-time recognition and repetition counting of 12 types of exercises performed during athletic workouts. Our approach is based on the deep neural network model fed by the signal from a 9-axis motion sensor (IMU) placed on the chest. The model can be run on mobile platforms (iOS, Android). We discuss design requirements for the system and their impact on data collection protocols. We present architecture based on an encoder pretrained with contrastive learning. Compared to end-to-end training, the presented approach significantly improves the developed model\'s quality in terms of accuracy (F1 score, MAPE) and robustness (false-positive rate) during background activity. We make the AIDLAB-HAR dataset publicly available to encourage further research.

Investigating aircraft flight dynamics often requires dynamic wind tunnel testing. This paper proposes a non-contact, off-board instrumentation method using vision-based techniques. The method utilises a sequential process of Harris corner detection, Kanade-Lucas-Tomasi tracking, and quaternions to identify the Euler angles from a pair of cameras, one with a side view and the other with a top view. The method validation involves simulating a 3D CAD model for rotational motion with a single degree-of-freedom. The numerical analysis quantifies the results, while the proposed approach is analysed analytically. This approach results in a 45.41% enhancement in accuracy over an earlier direction cosine matrix method. Specifically, the quaternion-based method achieves root mean square errors of 0.0101 rad/s, 0.0361 rad/s, and 0.0036 rad/s for the dynamic measurements of roll rate, pitch rate, and yaw rate, respectively. Notably, the method exhibits a 98.08% accuracy for the pitch rate. These results highlight the performance of quaternion-based attitude estimation in dynamic wind tunnel testing. Furthermore, an extended Kalman filter is applied to integrate the generated on-board instrumentation data (inertial measurement unit, potentiometer gimbal) and the results of the proposed vision-based method. The extended Kalman filter state estimation achieves root mean square errors of 0.0090 rad/s, 0.0262 rad/s, and 0.0034 rad/s for the dynamic measurements of roll rate, pitch rate, and yaw rate, respectively. This method exhibits an improved accuracy of 98.61% for the estimation of pitch rate, indicating its higher efficiency over the standalone implementation of the direction cosine method for dynamic wind tunnel testing.

With increased age, walking without tripping requires greater cognitive demand. Therefore, it may be beneficial for training interventions to address and incorporate aspects of cognitive load. The purpose of this study was to compare a semi-immersive virtual reality treadmill training (VRTT) and conventional treadmill training (CTT) on obstacle clearance and trip hazard in older adults. Obstacle clearance parameters were measured with foot-mounted inertial measurement units (IMUs) and a Zeno pressure walkway. All data were processed and analyzed through custom Matlab scripts. Obstacle step height mean decreased (p = .003) in the lead limb following both training interventions. Additional significant changes were found in pre- and post-obstacle distance mean following both training interventions. Furthermore, significant correlations were found between demographic, cognitive, and functional mobility assessments and changes in dependent measures. The findings suggest that both the VRTT and CTT interventions may provide a reduction in trip risk in older adults, although through different methods.

The interpretability of gait analysis studies in people with rare diseases, such as those with primary hereditary cerebellar ataxia (pwCA), is frequently limited by the small sample sizes and unbalanced datasets. The purpose of this study was to assess the effectiveness of data balancing and generative artificial intelligence (AI) algorithms in generating synthetic data reflecting the actual gait abnormalities of pwCA. Gait data of 30 pwCA (age: 51.6 ± 12.2 years; 13 females, 17 males) and 100 healthy subjects (age: 57.1 ± 10.4; 60 females, 40 males) were collected at the lumbar level with an inertial measurement unit. Subsampling, oversampling, synthetic minority oversampling, generative adversarial networks, and conditional tabular generative adversarial networks (ctGAN) were applied to generate datasets to be input to a random forest classifier. Consistency and explainability metrics were also calculated to assess the coherence of the generated dataset with known gait abnormalities of pwCA. ctGAN significantly improved the classification performance compared with the original dataset and traditional data augmentation methods. ctGAN are effective methods for balancing tabular datasets from populations with rare diseases, owing to their ability to improve diagnostic models with consistent explainability.

This study focused on developing and evaluating a gyroscope-based step counter algorithm using inertial measurement unit (IMU) readings for precise athletic performance monitoring in soccer. The research aimed to provide reliable step detection and distance estimation tailored to soccer-specific movements, including various running speeds and directional changes. Real-time algorithms utilizing shank angular data from gyroscopes were created. Experiments were conducted on a specially designed soccer-specific testing circuit performed by 15 athletes, simulating a range of locomotion activities such as walking, jogging, and high-intensity actions. The algorithm outcome was compared with manually tagged data from a high-quality video camera-based system for validation, by assessing the agreement between the paired values using limits of agreement, concordance correlation coefficient, and further metrics. Results returned a step detection accuracy of 95.8% and a distance estimation Root Mean Square Error (RMSE) of 17.6 m over about 202 m of track. A sub-sample (N = 6) also wore two pairs of devices concurrently to evaluate inter-unit reliability. The performance analysis suggested that the algorithm was effective and reliable in tracking diverse soccer-specific movements. The proposed algorithm offered a robust and efficient solution for tracking step count and distance covered in soccer, particularly beneficial in indoor environments where global navigation satellite systems are not feasible. This advancement in sports technology widens the spectrum of tools for coaches and athletes in monitoring soccer performance.

This study aims to profile biomechanical abilities during sprint front crawl by identifying technical stroke characteristics, in light of performance level. Ninety-one recreational to world-class swimmers equipped with a sacrum-worn IMU performed 25 m all-out. Intra and inter-cyclic 3D kinematical variabilities were clustered using a functional double partition model. Clusters were analysed according to (1) swimming technique using continuous visualisation and discrete features (standard deviation and jerk cost) and (2) performance regarding speed and competition calibre using respectively one-way ANOVA and Chi-squared test as well as Gamma statistics. Swimmers displayed specific technical profiles of intra-cyclic (smoothy and jerky) and inter-cyclic stroke regulation (low, moderate and high repeatability) significantly discriminated by speed (p < 0.001, η2 = 0.62) and performance calibre (p < 0.001, V = 0.53). We showed that combining high levels of both kinds of variability (jerky + low repeatability) are associated with highest speed (1.86 ± 0.12 m/s) and competition calibre (ℽ = 0.75, p < 0.001). It highlights the crucial importance of variabilities combination. Technical skills might be driven by a specific alignment of stroke pattern and its associated dispersion according to the task constraints. This data-driven approach can assist eyes-based technical evaluation. Targeting the development of an explosive swimming style with a high level of body stability should be considered during training of sprinters.

BACKGROUND: Human behavior patterns involve mutual interactions among psychology, physiology, and stress, which are all associated with gait at different grades.
OBJECTIVE: The study aims to reveal the interrelationship among personality, mental workload, and gait patterns by capturing gait variations using inertial sensors. It also assesses individual personality traits and simulates stress to construct a gait classification model.
METHODS: Sixty participants were instructed to perform regular, low, and high mental workload walking on the corridor to simulate a natural setting walking. Meanwhile inertial measurement units (IMUs) were placed on eight body parts. Mental workload was induced using the auditory n-back task, and their Big Five personality traits were evaluated. Gait data from IMUs were categorized into nine classifications of average, low, and high Big Five Inventory scores with three levels of mental workload walking. Subsequently, the segmentation gait data were used as input features for classifications in deep learning models, employing a sliding window long short-term memory network for nine classifications for different personality dimensions.
RESULTS: The results indicated average accuracies of nine classifications were 83.6 % for Openness, 84.4 % for Conscientiousness, 82.0 % for Extraversion, 85.2 % for Agreeableness, and 84.5 % for Neuroticism across all IMU placements. Remarkably, gait data from the lower back IMU achieved the highest model performance, with an average accuracy of 92.7 %, in classifying the different levels of personality and mental workload walking. In contrast, the left wrist and chest showed several misclassifications among regular, low, and high mental workload walking across personality traits.
CONCLUSIONS: Successful classification can help monitor an individual\'s mental state in real time and analyze personality dimensions, providing feedback and suggestions. The present study demonstrated that gait characteristics can contribute to more profound and personalized health information.

To enhance physical capabilities of workers who regularly perform physically demanding tasks involving heavy lifting and awkward postures, various tools and occupational exoskeletons can be used. Most of the studies aiming to explore the efficiency of these tools and exoskeletons have been performed in confined and controlled laboratory spaces, which do not represent the real-world work environment. This study aimed to compare the outcome of biomechanical assessment of using a back support exoskeleton and assistive tools (Lever and Jake) in the procedure of a high demanding manual material handling task versus the results found by performing the same task in a laboratory. Ten able-bodied participants and ten able-bodied utility workers performed the same manhole removal task in-lab and in-field, respectively, with the aid of an exoskeleton and Lever and Jake tools. Muscle activity and Rapid Entire Body Assessment (REBA) scores were recorded using surface electromyography and inertial measurement units, respectively and compared between in-lab and in-field trials. The field experiments indicated significant differences (p < 0.05) in normalized muscle activity across most muscles when compared to laboratory data. These results revealed how muscle activity is affected by the controlled lab setting compared to real-world field conditions. However, REBA scores indicate similar ergonomic implications regardless of the utilization of exoskeletons or tools. These findings underscore that real-world field assessments are crucial for evaluating ergonomic risks and effects of occupational exoskeletons and tools to account for environmental factors and workers\' skills in ergonomic evaluations of this nature.

The recognition of head movements plays an important role in human-computer interface domains. The data collected with image sensors or inertial measurement unit (IMU) sensors are often used for identifying these types of actions. Compared with image processing methods, a recognition system using an IMU sensor has obvious advantages in terms of complexity, processing speed, and cost. In this paper, an IMU sensor is used to collect head movement data on the legs of glasses, and a new approach for recognizing head movements is proposed by combining activity detection and dynamic time warping (DTW). The activity detection of the time series of head movements is essentially based on the different characteristics exhibited by actions and noises. The DTW method estimates the warp path distances between the time series of the actions and the templates by warping under the time axis. Then, the types of head movements are determined by the minimum of these distances. The results show that a 100% accuracy was achieved in the task of classifying six types of head movements. This method provides a new option for head gesture recognition in current human-computer interfaces.