Electrospun nanofibers, owing to their high porosity, flexibility, straightforward fabrication, and tunable physicochemical properties, have been widely employed in wearable sensors for gas detection, temperature monitoring, pulse measurement, gesture recognition, and other applications. In recent years, research on employing electrospun nanofibers in wearable sweat sensors has grown substantially. This paper provides the first comprehensive review of the research progress in electrospun nanofiber-based wearable sweat sensors, focusing on structural design, device fabrication, and potential applications. The review begins with a concise introduction to the fundamental aspects of electrospun nanofibers, including their formation principles, processing routes, material selection, and morphological characteristics. It then delves into the key components involved in constructing wearable sweat sensors based on electrospun nanofibers, such as reagent immobilization matrices, signal-enhancing materials, flexible substrates, and sweat collection components. A detailed analysis of the functional mechanisms of nanofibers in these contexts is provided, accompanied by an assessment of their advantages and limitations. Furthermore, recent applications of electrospun nanofiber-based wearable sweat sensors are systematically reviewed. Finally, the review discusses the challenges and potential future applications of electrospun nanofibers in wearable sweat sensors. This comprehensive overview aims to keep researchers informed of the latest advancements in the field and to stimulate further innovative developments.
Soft pneumatic actuators promise gentle, body-safe assistance, yet many fail at the moment of integration: inflation alters geometry, increases profile, and stresses seams and ports. This topical review reframes actuator selection through a structure-first lens that links how an actuator is built to how it deforms and how it embeds in garments. Actuators are classified by structural architecture, deformation behaviour, and fabrication method, and evaluated against four integration criteria central to wearable systems: geometric compatibility, fabrication scalability, system integration readiness, and actuation simplicity. A staged selection pathway is proposed and presented as a literature-informed mapping table that links reported wearable application contexts to dominant integration priorities and a practical structural-class starting point. Planar sheet designs can preserve a thin, predictable pressurized envelope at modest pressures when seam paths, constraint layers, and attachment features are co-designed. Pouch and bladder actuators are thin at rest, simple to fabricate, and readily integrated with textiles, but commonly bulge under load without external constraint; envelope control and port or manifold routing frequently limit garment integration. Fiber-constrained actuators deliver high specific force but often require rigid end terminations and elevated pressures. Segmented elastomers provide rich kinematics through chamber layout while tending toward bulging and routing burden in multi-segment formats. Mechanical metamaterials realize geometry-programmed motion when hinge fidelity and pattern alignment are maintained; durability of compliant joints and consistent crease formation set current limits. The resulting synthesis identifies practical priorities for wearable use: preserve thin profiles under load, embed stitchable or bondable attachment features, document reproducible process windows, minimize dead volume, routing, and valve count with compact pneumatic architectures, and target low-pressure operation compatible with lightweight hardware. Framing integration in structural terms standardizes comparison across actuator classes, clarifies the narrow feasible design space for compact, body-conforming devices, and supports deliberate actuator choice for biomedical wearables.
Accurate color classification plays a critical role across diverse fields, from textile manufacturing and environmental monitoring to biomedical diagnostics. This study introduces a machine-learning-driven approach to spectral color sensing using SENSIPATCH, a compact, wearable sensor system; while SENSIPATCH integrates multiple sensing modalities, including bioimpedance, electrochemical, thermal, humidity, and vibrational sensors, this work specifically utilizes its spectrometer module, which comprises multi-wavelength LEDs and photodiodes. Targeting the classification of 100 standardized PANTONE colors, the proposed framework is evaluated under controlled lighting conditions to ensure repeatable spectral acquisition. The experimental design includes both firm and loose contact scenarios to emulate variability in wearable placement. A structured data-preprocessing pipeline involving baseline correction, bootstrapping, and Z-score normalization was employed to enhance signal quality and improve model generalization. Five machine learning models were evaluated: Random Forest, SVM, MLP, CNN, and LSTM. The MLP demonstrated the strongest classification performance. Notably, the MLP achieved consistent accuracy across both contact conditions, indicating robustness against sensor placement variations. These results highlight the feasibility of compact LED-based wearable spectroscopy for reliable color classification under controlled measurement conditions, providing a baseline for future extensions to more diverse lighting conditions.
Wearable sweat-sensing technologies are limited by their inability to detect multiple molecular biomarkers, lack of multimodal capabilities, insufficient environmental robustness and the absence of in situ regenerability needed for long-term use outside laboratory conditions. Here we show a wireless, battery-free, multimodal wearable molecular sweat sensor that incorporates automated in-sensory regeneration and stable performance in real-world environments. Synthetic molecularly imprinted polymers, selected using density functional theory, allow selective biomarker recognition in sweat. In situ full regeneration of sensing components is achieved via voltage-based processes, whereby an electrical potential is applied to the molecularly imprinted polymer layers, causing the captured target molecules to be eluted from the sensor surface thus restoring the sensor for continuous use without manual intervention. We show simultaneously monitoring of cortisol, urea, lactate and glucose, with reliable operation validated for up to 21 days in both ex situ and in situ conditions. The presented advance enables long-term, comprehensive molecular health monitoring, suggesting future applications in healthcare, sports and personal well-being outside standard clinical settings.
Punch velocity is a key performance indicator in boxing and reflects effective coordination along the kinetic chain. This study aimed to investigate the relationship between punch acceleration and plantar pressure distribution using wearable sensing technologies. Twenty-four collegiate boxers (12 professional-level and 12 amateur-level athletes) performed jab and cross punches under controlled conditions. Punch acceleration was measured using a glove-mounted inertial measurement unit (IMU), while plantar pressure distribution was recorded using pressure-sensing insoles. Professional boxers demonstrated significantly higher punch acceleration (22-31%, p < 0.05) and greater forefoot plantar pressure (18-27%, p < 0.05) compared to amateur athletes. Correlation analysis revealed significant positive associations between forefoot pressure and punch acceleration (r = 0.62-0.71, p < 0.01), indicating that increased lower-limb force contributes to higher upper-limb striking performance. These findings demonstrate that combined wearable sensing provides a practical approach for quantifying punching biomechanics and identifying level-dependent kinetic-chain characteristics in boxing.
Spinal Bulbar Muscular Atrophy (SBMA) is a rare and slowly progressive disease that affects males. The Timed Up and Go (TUG) and 6-minute walk test (6MWT) are used in the clinic to track progression. Recent studies have used wearable sensors to track subtle changes in gait and balance in people with rare disease. The objective of this study was to determine whether inertial sensors could be used in men with SBMA to track changes in gait and balance. Our methods included ten participants with SBMA who completed the TUG and 6MWT while wearing six wearable sensors at the baseline, 6-month, and 12-month follow up visits. Our findings showed that this group of men did not progress in their disease over 12 months as evidenced by the stability of TUG durations, 6MWT distance, and sensor parameters. We observed strong associations between the sensor-derived parameters and both TUG duration and 6MWT distance. The sensors can be used during clinic assessments to measure gait and balance parameters. Further studies examining a larger sample size and at-home monitoring should be considered.
Accurate, continuous monitoring of psychophysiological states is central to understanding stress and autonomic dysfunction across diverse medical contexts. Current approaches such as polygraphy and polysomnography rely on cumbersome, wired sensors that limit real-world utility and burden patients, particularly vulnerable populations such as infants. Here, we introduce a wireless, skin-interfaced multimodal sensing system capable of simultaneously recording cardiac, respiratory, electrodermal, and thermal signals in a time-synchronized manner. Leveraging compact and soft designs, the technology enables unobtrusive monitoring across controlled, clinical, and naturalistic settings. Validation studies performed in parallel with gold standard systems demonstrate high fidelity in quantifying stress responses during polygraph interviews, cognitive load tasks, and cold pressor tests. In pediatric sleep studies, the data reliably identify arousals, hypopnea, and apnea while revealing disease-specific autonomic signatures in infants with Down syndrome. Real-world deployment during emergency simulation training shows that multimodal stress signatures correlate inversely with performance, underscoring translational value in medical education. Machine learning analyses across all studies confirm that multimodal features outperform single-signal approaches in detecting stress and clinical events with high sensitivity and specificity. Collectively, these findings establish the technology as a next-generation wearable platform that bridges engineering innovation and clinical practice, offering mechanistic insight and diagnostic potential in stress medicine, sleep medicine, and beyond.
Neurological disorders, such as Parkinson's disease and stroke, often lead to neurogenic dysphagia, a swallowing disorder that compromises nutrition and increases the risk of malnutrition, aspiration of food, and even death. Although instrumental assessments remain the gold standard for evaluating swallowing function, their invasiveness, costs, and reliance on specialized clinical facilities limit their routine use. In this scoping review, we provide an overview of emerging noninvasive wearable devices for assessing and monitoring dysphagia in neurological disorders. We highlight the most widely used sensing technologies, such as accelerometers, microphones, and surface electromyography, alone and in multimodal configurations, discuss their respective strengths and limitations, and outline the main challenges and opportunities for advancing this field. Particular attention is given to the need for standardized protocols, robust clinical validation, and the integration of artificial intelligence to enable scalable and precise assessment. We conclude by discussing how these technologies can be applied in clinical practice to support earlier diagnosis, continuous monitoring, and improved management of swallowing function in individuals with neurological disorders.
Smart textiles require advanced sensing capabilities, yet existing sensor-integrated fabrics suffer from poor breathability, brittleness, and thermal vulnerability, restricting large-scale deployment. Herein, inspired by the epidermal bubble-like cell structure of ice plants, we developed an ultra-lightweight Janus fabric, with a polyelectrolyte membrane as the key component-its inherent high stability, excellent ion conductivity, and good compatibility endow the fabric with superior structural flexibility and functional synergy. This design integrates passive daytime radiative cooling (PDRC) and sensing functions, retaining breathability and directional moisture transport. Notably, the polyelectrolyte membrane-enhanced fabric achieves 9.86°C sub-ambient cooling (101 W m- 2 net cooling power) under 1 sun intensity, 100% accurate motion monitoring, and stable triboelectric output (10 V stable output under 10 N constant force), along with exceptional durability (1000 folding cycles), recyclability, and antibacterial activity. Owing to the prominent advantages of structural innovation, excellent performance, and strong practicality, this study can not only be effectively extended to other inorganic particle systems (e.g., SiO2, boron nitride) but also holds broad application prospects in wearable electronic devices, flexible robots, and intelligent sensing systems.
Objective: Myocardial infarction (MI) triggers inflammation and fibrosis that drive the progressive impairment of cardiac function. Yet most pharmacological studies still depend on single-time-point histological or imaging endpoints and lack longitudinal, non-invasive assessments of treatment response. Electrocardiography (ECG) detects conduction and repolarization abnormalities tightly associated with myocardial injury and structural remodeling. However, ECG monitoring in mice is limited by rigid or invasive hardware, which restricts its use for longitudinal assessment of cardiac structure and function. Approach: Here, we propose an ECG-based non-invasive post-MI cardiac remodeling assessment approach and develop a flexible electrocardiographic monitoring microsystem (FECMS). Using the anti-remodeling drug (colchicine) therapy in an MI mouse model (Sham n = 4, MI n = 7 survivors, Col n = 7 survivors) for validation, we longitudinally track drug-induced changes in ECG parameters and systematically evaluate their concordance with functional, structural, and molecular indicators of cardiac injury and remodeling. Results: Colchicine treatment induced progressive shortening of the QRS and QT intervals and gradual stabilization of the PR interval. These interval changes were accompanied by increased EF and FS, decreased LVESV, reduced myocardial fibrosis and inflammatory infiltration, and lower plasma troponin I levels at the endpoint. Correlation analyses revealed strong relationships between drug-induced changes in ECG parameters and functional recovery and inhibited structural remodeling. Significance: The FECMS provides a new, non-invasive tool for longitudinal cardiovascular drug evaluation. This approach has the potential to complement or reduce reliance on terminal histological endpoints and to facilitate the optimization of dosing strategies in preclinical cardiovascular pharmacology.
Introduction: Motor reserve (MR) has been hypothesized as a protective factor against age-related and pathological motor decline, potentially enhancing quality of life. This study aimed to investigate the influence of MR on motor performance, assessed via mobile health technology (MHT), in drug-naïve Parkinson's disease (PD) patients. Methods: Consecutive drug-naïve PD patients and age-matched healthy controls (HC) underwent cognitive and motor assessments. Turning MHT parameters were extracted from the Timed Up and Go test (TUG) performed at self-selected and fast speeds. Participants were categorized into high- or low-MR groups based on the Motor Reserve Index questionnaire (MRIq). Results: Forty-five PD patients and forty healthy controls (HC) were enrolled. PD patients showed longer TUG durations and altered performance compared to HC. No differences were found between high and low motor reserve (MR) groups in demographics or clinical severity. However, high-MR patients exhibited shorter turn duration and higher angular velocities at both self-selected (p < 0.005) and fast speeds (p < 0.05). MR subdomains related to physical and care activities correlated with MHT turning metrics, unlike housework and leisure domains. Conclusions: the findings highlighted the relevance of MR on motor performances assessed by MHT in drug naïve PD, independently from motor severity.
Sleep duration is a key component of overall sleep health, but prior population-level studies characterizing this have relied on brief self-report questions (often one item) or used different objective devices within the same study. We examined the normal variation of sleep duration in an adult population using a single consumer-grade wearable device with a unified algorithm. Retrospective cohort study conducted in the United States. Data were analyzed from 274,128 U.S.-based adults aged 20 to 69 who used a Samsung Galaxy Watch between February 2023 and April 2023; participants were included if they had ≥20 valid weekdays and ≥8 valid weekend days of data. Sleep duration was the primary outcome, defined as the longest continuous nighttime sleep period between 6:00 p.m. and 6:00 a.m. averaged over a three-month period. Sleep duration and weekday-weekend variability were examined across age groups and by sex using descriptive statistics and independent t-tests. Overall, average sleep duration was 7.57 hours, with a 10th-90th percentile range of 6.5 to 8.9 hours. Sleep duration was shortest in the 40-49 year old group (7.54 hours) and longest in the 60-69 year old group (7.75 hours; p < .001). Overall, 23.0% of adults slept less than 7 hours, more commonly among those aged 40-49 (25.1%) and 50-59 (24.7%). Across all age groups, weekend sleep was longer than weekday sleep by an average of 28 minutes, with the largest gap in the 40-49 year old group (34 minutes), and the smallest in the 60-69 year old group (20 minutes). Women consistently slept longer than men (+18 minutes on average), and exhibited greater between-subject variability in total sleep duration (SD = 1.61 hours for women vs. 1.54 hours for men). This study demonstrates considerable variability in objectively measured sleep duration across adulthood, spanning a broad range and differing by age groups and sex. These findings provide reference distributions that may inform clinical expectations and public health messaging regarding sleep duration.
We present a large-scale (N=120) comparative study of gel-based and
dry electroencephalography systems for cognitive load analysis in tasks involving
information visualization stimuli. Although dry systems are increasingly adopted
owing to their portability and fast setup, their sensitivity to cognitive-related
measurements (as compared to gel-based systems) remains debated. This limits
the understanding of whether dry systems provide sufficient sensitivity for cognitive
load assessment under controlled task conditions. We analyzed
a diverse set of signal quality metrics, such as signal-to-noise ratio and channel
retention, combined with spectral features across frequency bands to evaluate
the ability for each device to capture workload-related neural markers during
information visualization tasks. Although the gel-based device showed
consistently better quality results than the dry one, the effect sizes suggest a
small practical significance of the differences between systems. These results
demonstrate that dry systems can provide adequate physiological sensitivity for
cognitive load assessments. Our findings highlight the trade-off
between usability (setup, calibration, etc.) and data fidelity, providing practical
guidance for choosing electroencephalography systems for cognitive workload
monitoring and applied neuroengineering research. Overall, the results suggest
that dry systems can support coarse-grained cognitive load assessment, while
gel-based systems remain advantageous when greater sensitivity is required.
In Chuckwagon racing, teams of four Thoroughbred horses pull wagons at high speeds. Movement symmetry is a key locomotion metric linked to force production, racing direction, and lameness. Racehorse symmetry in trot during on-track warmups and cooldowns was assessed. Over 10 days, 60 horses (average 8 per day) were fitted with Global Navigation Satellite Systems combined with Inertial Measurement Unit (GNSS-IMU) sensors. Weight-bearing asymmetry was quantified using the minimum difference (MnD) in vertical trunk displacement between diagonal limb pairs, and push-off asymmetry was quantified using the upwards difference (UpD). Absolute (mm) and normalized (% ROM) asymmetries were compared between warmups and cooldowns using linear mixed models. Mean MnD was similar between warmup (6.2 mm; 17.6%) and cooldown (6.4 mm, 19.7%). Mean UpD increased from warmup (11.3 mm, 31.7%) to cooldown (12.8 mm, 38.0%), with UpD% significantly higher in cooldown (p = 0.046). No other differences were significant (all p ≥ 0.202). One horse sustained a catastrophic musculoskeletal (MSK) injury. This horse's UpD ranged from 3.3-29.7 mm (11.4-69.3%) during warmups and 24.3-25.5 mm (47.8-76.4%) during cooldowns. Push-off asymmetry may increase after Chuckwagon racing. The injured horse showed high asymmetries, but high values also occurred in uninjured horses. Further work needs to establish normal asymmetry ranges in Chuckwagon racing and identify patterns associated with MSK injuries.
Mine rescue operations are frequently conducted in hazardous underground environments characterized by damaged infrastructure, unstable communications, heat stress, and hypoxia risk, all of which threaten the safety of rescue personnel. To address these challenges, this study proposes a prototype-oriented mine-rescue monitoring framework that combines a Wi-Fi/optical-fiber communication architecture with flexible wearable sensing modules for physiological monitoring. The communication design employs Wi-Fi for local wireless data aggregation and optical fiber for reliable long-distance backhaul to the surface command side. For wearable monitoring, two flexible sensing modules were developed: a temperature sensor based on a polyaniline/graphene-polyvinyl butyral composite film and a PPG-oriented flexible optoelectronic module based on an ITO/Ag/ITO multilayer transparent electrode structure. Experimental results show that the temperature sensor exhibits a clear temperature-dependent resistance response within the tested range, while the optoelectronic module demonstrates low sheet resistance and acceptable electrical continuity under repeated bending. These results provide preliminary support for combining hybrid underground communication architecture with flexible wearable sensing components in mine-rescue scenarios. However, the present work remains at the stage of architecture design and component-level validation, and full end-to-end system verification under simulated or field rescue conditions will be the focus of future studies.
Surface electromyography (sEMG) has shown potential for intuitive control of wearable assistive technologies in individuals with motor impairments. However, accurately classifying sEMG signals in stroke patients, particularly those with severe impairments and no visible voluntary hand movement, is difficult due to altered neuromuscular patterns. While robust machine learning models require large and diverse datasets, high variability among stroke patients means that even extensive data may fail to capture individual differences. To address this challenge, this study applies a transfer learning approach that leverages richer sEMG signals from healthy individuals to pretrain a model, which is then adapted to the altered patterns of stroke patients. This process enables effective classification even with limited patient-specific data. Ten stroke patients wore a Myo armband, a wearable sEMG acquisition device, and performed hand-closing, rest, and hand-opening gestures across up to 26 arm postures. Healthy sEMG data were obtained from the Ninapro DB5 dataset. Multiple transfer learning configurations were evaluated by varying the number of frozen layers. The best-performing configuration achieved an overall accuracy of 93.6% across all participants, with 84.32% for severe, 97.42% for moderate, and 99.07% for low impairments. In comparison, training the model solely on stroke data without transfer learning resulted in a considerably lower accuracy of 46%. These findings highlight the value of incorporating healthy sEMG data for pattern recognition in stroke patients and demonstrate the potential of transfer learning to support inclusive and adaptive wearable sEMG-based control systems for individuals with varying levels of post-stroke motor impairment.
(1) Background: Breast cancer screening remains limited by mammography, particularly in younger women, in dense breast tissue, and in the detection of interval cancers. The PHI-BRA Smart Bra was developed as a wearable, non-invasive device combining thermography and bioimpedance for frequent breast monitoring. This first-in-human study aimed to assess the feasibility and in vivo diagnostic performance of the PHI-BRA system in discriminating between women with and without breast lesions. (2) Methods: A prospective feasibility study was conducted between March 2023 and February 2024. A calibration cohort (n = 15) was used to define the discrimination model, followed by an analysis cohort (n = 26; 13 with breast lesions and 13 without). Thermal and bioimpedance signals were acquired using the PHI-BRA device. Diagnostic performance was evaluated using receiver operating characteristic (ROC) analysis, with mammography as the reference standard. (3) Results: In the analysis cohort, the temperature-based model achieved an area under the ROC curve (AUC) of 80.8% (95% CI [63.2-98.3]). At the optimal threshold, sensitivity was 84.6% (95% CI [61.5-100]) and specificity was 76.9% (95% CI [53.8-100]). Exploratory bioimpedance analyses showed lower sensitivity but high specificity, mainly limited by sensor contact stability. No adverse events were reported. (4) Conclusions: This first-in-human study demonstrates an initial exploration of the feasibility and safety of a wearable thermography-based approach for breast lesion discrimination. The results support further clinical validation of a multimodal wearable system as a complementary tool to existing breast cancer screening strategies.
Intellectual disability often impairs an individual's ability to communicate and engage in social interactions. Augmentative and Alternative Communication (AAC) systems, as a subset of Assistive Technology (AT), provide essential support for individuals facing such challenges. Despite their potential, issues related to accessibility, usability, and social acceptability continue to hinder the widespread adoption of AAC solutions. This study presents AAC Vest, a novel wearable AAC solution, grounded in user need-driven scenarios and developed through iterative prototyping and interdisciplinary expert workshops. The developed AAC vest integrates touch and pressure sensors into a vest, enabling users to trigger pre-recorded voice messages and send text alerts via a Bluetooth-connected smartphone application. It offers a discreet and easy-to-use communication aid that supports both users and caregivers in everyday interactions. Findings highlight the potential of wearable AAC technologies to bridge gaps between user needs and technical solutions. Furthermore, the study underscores both the importance and the complexity of interdisciplinary collaboration in the development of effective assistive technologies. The AAC Vest demonstrates the potential of wearable assistive technology to support communication for individuals with intellectual disabilities. Using discreet textile-based sensors and a smartphone application, it enables users to express needs through touch, triggering audio and text alerts to caregivers. This supports independence and safety across contexts. Its comfortable, customizable design and interdisciplinary, user-informed development highlight the importance of collaborative approaches in creating effective AAC solutions.
Hypertension is a major risk factor for cardiovascular disease and requires effective long-term monitoring. Photoplethysmography (PPG), acquired from wearable optical sensors, offers a convenient and non-invasive signal source for cuffless blood pressure (BP) estimation, but existing studies have mainly emphasized model architecture optimization, with limited systematic investigation of signal representation. This study systematically compares seven one-dimensional-to-two-dimensional signal transformation methods and evaluates multiple architectural variants for PPG-based cuffless BP estimation under a unified framework. Experiments were conducted using PPG and arterial BP signals from the UCI Open Blood Pressure Database. The best-performing configuration, based on continuous wavelet transform (CWT), achieved estimation errors of 3.80 ± 5.02 mmHg for systolic BP and 1.65 ± 2.70 mmHg for diastolic BP. Further real-world validation on 26 participants using an Omron cuff-based monitor as the reference showed good consistency, with correlation coefficients of R = 0.96 for SBP and R = 0.74 for DBP. The results demonstrate that appropriate signal representation, particularly CWT, plays a critical role in improving estimation accuracy and robustness, and may facilitate the development of wearable cuffless BP monitoring systems.
Osteoarthritis is a leading cause of lower-limb arthroplasty, and although total hip arthroplasty (THA) and total knee arthroplasty (TKA) reduce pain and improve quality of life, gait impairments often persist after surgery. This study aimed to analyze gait patterns in individuals following THA and TKA using the wearable RunScribe™ sensor system and to examine its sensitivity to short-term changes during rehabilitation. Thirty-seven patients (19 THA, 18 TKA) attending a two-week inpatient rehabilitation program were assessed twice, on the first and final day of rehabilitation. Gait was measured during a 2 min circular walk test, and both global spatiotemporal variables and limb-specific loading-related variables were analyzed. A significant main effect of time was observed for walking speed (p = 0.001, ηp2 = 0.284), with improvements of approximately 10% in both groups, as well as for step cadence (p < 0.001, ηp2 = 0.429) and contact time (p < 0.001, ηp2 = 0.380). Loading-related variables also changed significantly over time, including impact acceleration (p = 0.004, ηp2 = 0.226), braking acceleration (p < 0.001, ηp2 = 0.419), and rate of force development (p < 0.001, ηp2 = 0.412). No statistically significant between-group differences were observed for global gait variables, although participants following THA showed a tendency toward better walking performance (e.g., higher cadence, p = 0.065). These findings suggest that early rehabilitation is associated with measurable improvements in gait after arthroplasty and support the potential of affordable wearable sensors as practical tools for objective gait assessment in clinical settings.