Search Results (172)

The increasing use of AI systems for face, object, action, scene, and emotion recognition raises significant privacy risks, particularly when processing Personally Identifiable Information (PII). Current privacy-preserving methods lack adaptability to users’ preferences and contextual requirements, and obfuscate user faces uniformly. This research proposes a user-centric, context-aware, and ontology-driven privacy protection framework that dynamically adjusts privacy decisions based on user-defined preferences, entity sensitivity, and contextual information. The framework integrates state-of-the-art recognition models for recognising faces, objects, scenes, actions, and emotions in real time on data acquired from vision sensors (e.g., cameras). Privacy decisions are directed by a contextual ontology based in Contextual Integrity theory, which classifies entities into private, semi-private, or public categories. Adaptive privacy levels are enforced through obfuscation techniques and a multi-level privacy model that supports user-defined red lines (e.g., “always hide logos”). The framework also proposes a Re-Identifiability Index (RII) using soft biometric features such as gait, hairstyle, clothing, skin tone, age, and gender, to mitigate identity leakage and to support fallback protection when face recognition fails. The experimental evaluation relied on sensor-captured datasets, which replicate real-world image sensors such as surveillance cameras. User studies confirmed that the framework was effective, with over 85.2% of participants rating the obfuscation operations as highly effective, and the other 14.8% stating that obfuscation was adequately effective. Amongst these, 71.4% considered the balance between privacy protection and usability very satisfactory and 28% found it satisfactory. GPU acceleration was deployed to enable real-time performance of these models by reducing frame processing time from 1200 ms (CPU) to 198 ms. This ontology-driven framework employs user-defined red lines, contextual reasoning, and dual metrics (RII/IVI) to dynamically balance privacy protection with scene intelligibility. Unlike current anonymisation methods, the framework provides a real-time, user-centric, and GDPR-compliant method that operationalises privacy-by-design while preserving scene intelligibility. These features make the framework appropriate to a variety of real-world applications including healthcare, surveillance, and social media. Full article

Background: Muscle health is an emerging concept linked to physical performance and functional independence. However, the term lacks a standardized definition and is often used as a broad muscle-related outcome descriptor. Clinical communication and research would benefit from a conceptual model of muscle health grounded in an established framework. Methods: We conducted systematic search and narrative synthesis to identify multifactorial measurement approaches explicitly described under ‘muscle health’. PubMed and CINAHL were searched for clinical and randomized controlled trials published in the past 5 years (final search: March 2025) that used the term “muscle health.” Studies were reviewed for explicit definitions of “muscle health,” and all identified outcomes (e.g., strength, mass) and measurement tools (e.g., grip strength, ultrasound) were synthesized. This review was retrospectively registered (INPLASY202580069). Results: Of the 65 clinical or randomized controlled trials that met inclusion criteria, 29 provided an operational definition of ‘muscle health’, while 36 inferred measurements without a clear definition. The identified measurements spanned four primary categories, with body composition/muscle mass being the most common (92.3%), followed by muscle performance (78.5%), physical function (63.1%), and tissue composition (30.8%). Most studies included more than one muscle health metric (93.9%). Common assessment methods included DXA (44.6%), grip strength (64.6%), and gait speed (27.7%). Conclusions: While there are common measurement approaches, the definition of muscle health varies widely in the cited works. The framework of the International Classification of Functioning, Disability and Health, was used to identify domains aligned with muscle health components of muscle morphology/morphometry (e.g., mass and composition), functional status (performance-based tasks), and physical capacity (muscle performance). This framework provides a structured basis for evaluating muscle health in research and clinical practice. Consistent use of these domains could enhance assessment and support efforts to standardize testing and interpretation across settings. Full article

Inertial Measurement Units (IMUs) offer promising alternatives to traditional motion capture systems, especially in real-world sports scenarios. Accurate foot contact detection (FCD) is crucial for biomechanical analysis, and since on-the-field force plates are unsuitable, IMU-based FCD algorithms have been extensively investigated. However, sports activities leading to musculoskeletal injuries are multidirectional and high-dynamics in nature and FCD algorithms, which have mostly been studied in gait analysis, might sensibly worsen performance. This systematic review (PROSPERO, ID: CRD420251010584) aimed to evaluate IMU-based FCD algorithms applied to high-dynamics sports tasks, identifying strengths, limitations, and areas for improvement. A multi-database search was conducted until May 2025. Studies were included if they applied IMU-based FCD algorithms in high-dynamic movements. In total, 37 studies evaluating 71 FCD algorithms were included. Most papers focused on running, with only 3 on cut manoeuvres. Almost all studies involved healthy individuals only, and foot linear acceleration was the most inspected FCD metric. FCD algorithms demonstrated high accuracy, though speed variation impacted performance in 23/37 studies. This review highlights the lack of validated IMU-based FCD algorithms for high-dynamic sports movements and emphasizes the need for improved methods to advance sports biomechanics testing in injury prevention. Full article

The acceleration of global population aging has driven a surge in demand for health monitoring among older adults. However, traditional mobility assessment methods mostly rely on invasive measurements or laboratory-grade equipment, making it difficult to achieve continuous monitoring in daily scenarios. This study investigated the correlation between dynamic gait characteristics and static body metrics to enhance the understanding of elderly mobility and overall health. A sensor-based framework was implemented, which utilizes the Short Physical Performance Battery (SPPB), combined with PoseNet (a vision-based sensor) for dynamic gait analysis, and the InBody bioelectrical impedance device for static body composition assessment. Key variables comprised the dynamic metric mean directional shift and static metrics, including skeletal muscle index (SMI), skeletal muscle mass (SMM), body fat percentage (PBF), visceral fat area (VFA), and intracellular water. Nineteen elderly participants aged 60–89 years underwent assessments; among them, 16 were males (84.21%), and 3 were females (15.79%), 50% were in the 80–89 age group, 95% did not live alone, and 90% were married. Dynamic gait data were analyzed for center displacement and horizontal directional shifts. A Pearson correlation analysis revealed that the mean directional shift positively correlated with SMI ($\rho =0.561$, $p<0.01$), SMM ($\rho =0.496$, $p<0.01$), and intracellular water ($\rho =0.497$, $p<0.01$), highlighting the role of muscle strength in movement adaptability. Conversely, negative correlations were found with PBF ($\rho =-0.256$) and VFA ($\rho =-0.342$, $p<0.05$), suggesting that greater fat mass impedes dynamic mobility. This multimodal integration of dynamic movement patterns and static physiological metrics may enhance health monitoring comprehensiveness, particularly for early sarcopenia risk detection. The findings demonstrate the framework’s potential, indicating mean directional shift as a valuable dynamic health indicator. Full article

Assessing the fall risk of a patient in a busy clinical setting is challenging. Tests such as the timed-up-and-go test and narrow beam walking are difficult to perform due to space restrictions. Moreover, it is not easy to directly connect the results of these tests to fundamental biomechanical principles of gait stability, which emphasize the interplay between the movements of the body’s center of mass (CoM) and its base of support (BoS). Herein, we show how a 1.2 m-long treadmill and a single “time-of-flight” Azure Kinect camera can capture the CoM-BoS interplay within 5 min. The CoM was calculated by dividing the body into 14 segments determined from 20 joint positions measured by the Kinect camera’s body tracking SDK. By tracking the CoM and joint positions from stride to stride, we can evaluate different gait stability metrics using a markerless, contactless, space-efficient approach. A large digital database of CoM movements relative to foot placement will be useful for the future development of statistical and machine learning techniques for identifying subjects at higher risk of falling. Full article

Background: A single lumbar-mounted inertial sensor offers a practical alternative to optoelectronic systems for gait analysis, simplifying measurements and improving usability in the clinical field. However, its validity can be influenced by sensor placement and signal choice. This study aimed to develop and validate a novel algorithm for estimating spatiotemporal parameters using anteroposterior linear acceleration and angular velocity around the sagittal axis using a single inertial measurement unit (IMU) placed on the lumbar region. The proposed algorithm was validated comparing the parameters computed by the algorithm with the ones computed using a commercial wearable system based on a two-foot-mounted IMU configuration. Thirty healthy subjects underwent a 2 min walk test, and five spatiotemporal parameters were computed using the two methodologies. Study results showed that cadence and gait cycle time exhibited very high agreement, with only a small, statistically significant bias in cadence negligible for practical purposes. In contrast, swing, stance, and double-support parameters showed disagreement due to the presence of systematic proportional errors. This work introduces a novel algorithm for gait event detection and spatiotemporal parameter estimation, addressing uncertainties related to sensor placement, metric models, processing techniques, and signal selection, while avoiding synchronization issues associated with using multiple sensors. Full article

Autonomic dysfunction is a key non-motor feature of Parkinson’s disease (PD) and may influence motor performance, particularly gait. While heart rate variability (HRV) has been associated with freezing of gait, its relationship with broader gait parameters remains unclear. The objective was to investigate correlations between resting-state HRV time-domain measures and spatiotemporal gait parameters during comfortable and fast walking in patients with idiopathic PD. Twenty-eight PD patients (mean age 68 ± 9 years) were evaluated at Campus Bio-Medico University Hospital. HRV was recorded at rest using the e-Sense pule™ portable sensor, including the Baevsky’s Stress Index a measure increasing with sympathetic burden. Gait parameters were assessed via the 10 m Timed Up and Go (TUG) test using the Mon4t™ smartphone app at comfortable and fast pace. Clinical data included UPDRS III, MoCA, and disease characteristics. Gait metrics significantly changed between walking conditions. HRV parameters clustered separately from gait metrics but intersected with significant correlations. Higher Stress Index values, reflecting sympathetic dominance, were associated with poorer gait performance, including prolonged transition times, shorter steps, and increased variability (p < 0.001, r = 0.57–0.61). MoCA scores inversely correlated with the Stress Index (r = −0.52, p = 0.004), linking cognitive and autonomic status. UPDRS III and MoCA were related to TUG metrics but not HRV. Time-domain HRV measures, particularly the Stress Index, are significantly associated with spatiotemporal gait features in PD, independent of gait speed. These findings suggest that impaired autonomic regulation contributes to functional mobility deficits in PD and supports the role of HRV as a biomarker in motor assessment. Full article

Exoskeletons are a fast-growing technology that enables multiple use-cases in clinical scenarios. They can be useful tools for the rehabilitation of patients with motor dysfunctions caused by neurological conditions, aging or trauma. Assistive exoskeletons modulate the torque exerted by the electrical motors moving their joints to allow the patients wearing them to achieve an intended movement, such as gait, correctly. Their effectiveness, therefore, requires accurate online control of such torques to complement those generated by the patient. Hereby we explored Deep Learning (DL) models to generate an online prediction of the gait phase, i.e., stance or swing, during assisted walking with a lower-limb exoskeleton based on surface electromyography (sEMG) data. We leveraged the lead of muscular activation with respect to the movement of the limbs to adjust the labeling based on joints kinematics. The cross-subject design allowed to generalize over subjects not considered for training A hyperparameter optimization algorithm was also implemented to further explore the capabilities of DL models of a reduced size. We simulated a use case scenario to assess whether online implementation of the proposed technique is feasible. We also proposed a new metric called trade-of score (TOS) for evaluating the cost-performance compromise of the optimized models which lead to identifying a DL model capable of classifying gait phases with an accuracy of about 95% while significantly reducing the number of parameters compared to the full architecture. Its mean computational time of less than 10 ms offers the opportunity for accurate, online exoskeleton control based on sEMG data. Full article

Spatiotemporal running metrics such as cadence, stride length (SL), and ground contact time (GCT) are important for assessing performance and injury risk. However, such metrics are traditionally assessed using laboratory-based tools that are often inaccessible in applied settings. Wearable devices including smartwatches and lace-mounted inertial measurement units (IMUs) offer promising alternatives, yet cross-device agreement in reporting spatiotemporal variables remains unclear. This study evaluated agreement between a commercial smartwatch and lace-mounted IMUs across varied distances and environments in 65 physically active adults (33 female/32 male, height: 171.0 ± 8.9 cm; weight: 70.9 ± 15.2 kg). Participants completed indoor and outdoor runs (2.5 km, 5 km, 10 km, 20 km) wearing both devices simultaneously. Average cadence demonstrated acceptable agreement (MAPE = 4.1%, CCC = 0.66) and supported equivalence, particularly among males, during outdoor conditions, and longer run distances. In contrast, peak cadence showed weak correlation (MAPE = 5.3%, CCC = 0.29), and SL and GCT demonstrated poor agreement (MAPE = 14.9–19.0%, CCC = 0.30–0.39) across all conditions. While average cadence may serve as a metric for cross-device comparisons, especially for males, and longer-distance outdoor runs, other spatiotemporal metrics demonstrated poor agreement, limiting interchangeability. Understanding device-specific capabilities is essential when interpreting wearable-derived gait data. Further validation using gold-standard tools is needed to support accurate and applied use of wearable technologies. Full article

Background/Objectives: Multiple sclerosis (MS) often leads to gait impairments, even in early stages, and can affect autonomy and quality of life. Traditional assessment methods, while widely used, have been criticized because they lack sensitivity to subtle gait changes. This scoping review aims to map the landscape of advanced gait analysis technologies—both wearable and non-wearable—and evaluate their application in detecting, characterizing, and monitoring possible gait dysfunction in individuals with MS. Methods: A systematic search was conducted across PubMed and Scopus databases for peer-reviewed studies published in the last decade. Inclusion criteria focused on original human research using technological tools for gait assessment in individuals with MS. Data from 113 eligible studies were extracted and categorized based on gait parameters, technologies used, study design, and clinical relevance. Results: Findings highlight a growing integration of advanced technologies such as inertial measurement units, 3D motion capture, pressure insoles, and smartphone-based tools. Studies primarily focused on spatiotemporal parameters, joint kinematics, gait variability, and coordination, with many reporting strong correlations to MS subtype, disability level, fatigue, fall risk, and cognitive load. Real-world and dual-task assessments emerged as key methodologies for detecting subtle motor and cognitive-motor impairments. Digital gait biomarkers, such as stride regularity, asymmetry, and dynamic stability demonstrated high potential for early detection and monitoring. Conclusions: Advanced gait analysis technologies can provide a multidimensional, sensitive, and ecologically valid approach to evaluating and detecting motor function in MS. Their clinical integration supports personalized rehabilitation, early diagnosis, and long-term disease monitoring. Future research should focus on standardizing metrics, validating digital biomarkers, and leveraging AI-driven analytics for real-time, patient-centered care. Full article

Accurately distinguishing hemiplegic gait from healthy gait is significant for alleviating clinicians’ diagnostic workloads and enhancing rehabilitation efficiency. The center of pressure (CoP) trajectory extracted from pressure sensor arrays can be utilized for hemiplegic gait recognition. Existing research studies on hemiplegic gait recognition based on plantar pressure have paid limited attention to the differences in recognition performance offered by CoP trajectories along different directions. To address this, this paper proposes a neural network model based on time–frequency domain feature interaction—the temporal–frequency domain interaction network (TFDI-Net)—to achieve efficient hemiplegic gait recognition. The work encompasses: (1) collecting CoP trajectory data using a pressure sensor array from 19 hemiplegic patients and 29 healthy subjects; (2) designing and implementing the TFDI-Net architecture, which extracts frequency domain features of the CoP trajectory via fast Fourier transform (FFT) and interacts or fuses them with time domain features to construct a discriminative joint representation; (3) conducting five-fold cross-validation comparisons with traditional machine learning methods and deep learning methods. Intra-fold data augmentation was performed by adding Gaussian noise to each training fold during partitioning. Box plots were employed to visualize and analyze the performance metrics of different models across test folds, revealing their stability and advantages. The results demonstrate that the proposed TFDI-Net outperforms traditional machine learning models, achieving improvements of 2.89% in recognition rate, 4.6% in F1-score, and 8.25% in recall. Full article

Background: Freezing of gait (FoG) is one of the most debilitating motor symptoms in Parkinson’s disease (PD). It often leads to falls and reduces quality of life due to the risk of injury and loss of independence. Several types of wearable sensors have emerged as promising tools for the detection of FoG in clinical and real-life settings. Objective: The main objective of this systematic review was to critically evaluate the current usability of wearable sensor technologies for FoG detection in PD patients. The focus of the study is on sensor types, sensor combinations, placement on the body and the applications of such detection systems in a naturalistic environment. Methods: PubMed, IEEE Explore and ACM digital library were searched using a search string of Boolean operators that yielded 328 results, which were screened by title and abstract. After the screening process, 43 articles were included in the review. In addition to the year of publication, authorship and demographic data, sensor types and combinations, sensor locations, ON/OFF medication states of patients, gait tasks, performance metrics and algorithms used to process the data were extracted and analyzed. Results: The number of patients in the reviewed studies ranged from a single PD patient to 205 PD patients, and just over 65% of studies have solely focused on FoG + PD patients. The accelerometer was identified as the most frequently utilized wearable sensor, appearing in more than 90% of studies, often in combination with gyroscopes (25.5%) or gyroscopes and magnetometers (20.9%). The best overall sensor configuration reported was the accelerometer and gyroscope setup, achieving nearly 100% sensitivity and specificity for FoG detection. The most common sensor placement sites on the body were the waist, ankles, shanks and feet, but the current literature lacks the overall standardization of optimum sensor locations. Real-life context for FoG detection was the focus of only nine studies that reported promising results but much less consistent performance due to increased signal noise and unexpected patient activity. Conclusions: Current accelerometer-based FoG detection systems along with adaptive machine learning algorithms can reliably and consistently detect FoG in PD patients in controlled laboratory environments. The transition of detection systems towards a natural environment, however, remains a challenge to be explored. The development of standardized sensor placement guidelines along with robust and adaptive FoG detection systems that can maintain accuracy in a real-life environment would significantly improve the usefulness of these systems. Full article

Background/Objectives: Beyond the core characteristics of the condition, autistic individuals often significantly struggle with postural balance. This pilot study aimed to investigate the effects of an immersive virtual reality-based training administered with Gait Real-time Analysis Interactive Lab (GRAIL) on postural balance of autistic children. Methods: A total of 20 autistic participants aged 6 to 13 were enrolled in a 5-week randomized, parallel-group, open-label, controlled trial, and received either balance training with the GRAIL system or no training. The trial was registered at ClinicalTrials.gov (identifier: NCT04276571). The primary outcome measures were the change in center of pressure (CoP) metrics during GRAIL balance assessments and the change in motor skills as assessed with Movement Assessment Battery for Children-2. Secondary outcome measures included parent-report Developmental Coordination Disorder Questionnaire, center of mass metrics, and gait parameters evaluated with GRAIL. ANCOVA tests were performed for all outcomes, with time (T0 and T1) as within-subjects factor, the group (training and control groups) as between-subjects factor, and considering age as covariate. Results: Slight but significant time by group interactions were found in some CoP metrics (i.e., sway path length, velocity in the antero-posterior direction, and the jerk). Conclusions: These findings preliminarily suggest that a virtual reality-based training may induce slight modifications in postural balance strategies, which can be enhanced with longer or more intensive training. Full article

Background: High-intensity gait training (HIT) is an evidence-based intervention recommended for stroke rehabilitation; however, its implementation in routine practice is inconsistent. This study examined the real-world implementation of HIT in an inpatient rehabilitation setting in Norway, focusing on fidelity, barriers, and knowledge translation (KT) strategies. Methods: Using the Knowledge-to-Action (KTA) framework, HIT was implemented in three phases: pre-implementation, implementation, and competency. Fidelity metrics and coverage were assessed in 99 participants post-stroke. Barriers and facilitators were documented and categorized using the Consolidated Framework for Implementation Research. Results: HIT was delivered with improved fidelity during the implementation and competency phases, reflected by increased stepping and heart rate metrics. A coverage rate of 52% was achieved. Barriers evolved over time, beginning with logistical and knowledge challenges and shifting toward decision-making complexity. The KT interventions, developed collaboratively by clinicians and external facilitators, supported implementation. Conclusions: Structured pre-implementation planning, clinician engagement, and external facilitation enabled high-fidelity HIT implementation in a real-world setting. Pragmatic, context-sensitive strategies were critical to overcoming evolving barriers. Future research should examine scalable, adaptive KT strategies that balance theoretical guidance with clinical feasibility to sustain evidence-based practice in rehabilitation. Full article

This research presents a reinforcement learning framework for stable quadruped locomotion using Proximal Policy Optimization (PPO). We address critical challenges in articulated robot control—including mechanical complexity and trajectory instability by implementing a 12-degree-of-freedom model in PyBullet simulation. Our approach features three key innovations: (1) a hybrid reward function ($R_t=0.72 · e^{-\Delta {\mathrm{CoG}}_t} + 0.25 · v_t - 0.11 · ‖{\tau }_t‖$) explicitly prioritizing center-of-gravity (CoG) stabilization; (2) rigorous benchmarking demonstrating Adam’s superiority over SGD for policy convergence (68% lower reward variance); and (3) a four-metric evaluation protocol quantifying locomotion quality through reward progression, CoG deviation, policy loss, and KL-divergence penalties. Experimental results confirm an 87.5% reduction in vertical CoG oscillation (from 2.0″ to 0.25″) across 1 million training steps. Policy optimization achieved −6.2 × 10⁻⁴ loss with KL penalties converging to 0.13, indicating stable gait generation. The framework’s efficacy is further validated by consistent CoG stabilization during deployment, demonstrating potential for real-world applications requiring robust terrain adaptation. Full article