Search Results (5,480)

The rapid increase in companion animal ownership has intensified the demand for innovative tools that support animal health and overall welfare. In recent years, artificial intelligence (AI), particularly machine learning (ML) and deep learning (DL), has emerged as a promising approach in veterinary medicine. However, its application beyond clinical diagnostics, especially in behaviour and personality assessment, remains fragmented and insufficiently integrated into routine practice. This systematic review aims to synthesise current knowledge on AI-based applications in companion animal care, with a focus on behavioural monitoring, personality prediction, and welfare-related challenges. Following PRISMA guidelines, a structured literature search was conducted in the Scopus and PubMed databases from 2020 to 2025. In addition, grey literature sources were searched to capture relevant non-peer-reviewed data. A total of 115 studies met the inclusion criteria and were included in the analysis. Eligibility criteria included studies applying AI methods (machine learning or deep learning) to companion animals (dogs, cats, and exotic pets), while studies on humans, farm animals, or without AI methods were excluded. Due to the heterogeneity of included studies, no formal risk of bias assessment was performed, and results were synthesised narratively. The findings indicate that AI applications are most advanced in diagnostic imaging and clinical decision support, where data availability and methodological maturity are highest. In contrast, AI-based approaches for behaviour and personality prediction remain limited, particularly in cats and exotic companion animals, largely due to small, heterogeneous datasets, potential bias, and a lack of external validation. Emerging technologies such as wearable sensors, computer vision, and multimodal data integration demonstrate substantial potential for continuous behavioural monitoring and early detection of welfare-related issues in real household environments. Nevertheless, significant challenges persist, including data heterogeneity, limited model explainability, ethical considerations, and the absence of regulatory frameworks specifically addressing AI-based veterinary applications. Overall, this review highlights a substantial gap between the technical potential of AI and its current readiness for widespread application in companion animal behaviour and welfare assessment. Future research should prioritise large-scale and standardised data collection, cross-species validation, and interdisciplinary collaboration to ensure that AI-driven tools effectively support veterinary decision-making, animal welfare, and the well-being of owners. Full article

A dual-mode electrical–optical nanocomposite hydrogel is developed by integrating carboxyl-modified upconversion nanoparticles (UCNPs-COOH) and quaternized chitosan (CQAS) into a polyacrylamide (PAAm) covalent network. The hydrogel exhibits high optical transparency (>90% in the visible region), excellent mechanical properties (fracture strain of 1742%, tensile strength of 0.85 MPa, toughness of 6.57 MJ/m³), and robust adhesion to various substrates. The synergistic covalent–noncovalent hybrid network enables efficient energy dissipation, while CQAS-enhanced dispersion of UCNPs significantly improves upconversion luminescence intensity and stability, as evidenced by prolonged fluorescence lifetime from 0.564 ms to 0.691 ms at 539 nm. Leveraging distinct electrical and optical signal transduction pathways, the hydrogel functions as a highly sensitive resistive strain sensor with multistage gauge factors up to 13.85 and excellent cyclic stability over 1200 loading–unloading cycles at 100% strain for human motion monitoring. It also serves as a ratiometric optical pH sensor over a broad range (pH 1–13) based on phenolphthalein-sensitized upconversion luminescence, with excellent repeatability. By integrating real-time resistance responses with optical readouts within a single soft material, this work demonstrates a reliable dual-mode sensing strategy for simultaneous mechanical and chemical monitoring, holding promise for wearable electronics, smart healthcare, and environment-responsive sensing systems. Full article

This review examines the current state of development and application of artificial intelligence (AI) tools for monitoring nutrition and physical activity in individuals with obesity, with a focus on the physiological complexity of energy balance and the role of chrono-nutrition. Energy intake and expenditure are dynamically coupled and circadian-regulated: meal timing and movement patterns influence insulin sensitivity, thermogenesis, and Non-Exercise Activity Thermogenesis within the same day. Traditional monitoring methods suffer from recall bias and low granularity, while isolated sensors operate in data silos, limiting accuracy. Effective solutions require multimodal, continuous, and temporally aligned data streams. Current AI models exhibit critical limitations in obesity-specific contexts: inaccurate gait and energy expenditure estimates due to biomechanical differences, dietary models underestimating glycemic variability, poor performance on mixed dishes, sauces, and culturally diverse foods, and a lack of validation against gold standards such as doubly labelled water (DLW) and weighed food records. This review proposes a paradigm shift toward obesity-specific AI design, including enriched datasets and multimodal integration. Physical activity monitoring faces similar challenges: systematic measurement bias in wearables, sensor placement issues, and algorithms trained on normal-weight cohorts. In the GLP-1/GIP era, if transparency, ethical safeguards, and equitable access are ensured, AI will act as a catalyst for personalized care, remote monitoring, trial optimization, and next-generation drug discovery. In conclusion, the integration of AI with rigorous validation procedures and inclusive sampling strategies is essential to achieve reliable, fair, and clinically relevant monitoring approaches for obesity management. Full article

Postural control relies on the integration of visual, vestibular, and somatosensory inputs under biomechanical constraints. Conventional Romberg testing provides limited quantitative insight, particularly regarding directional control and sensory dependence. Wearable inertial measurement units (IMUs) enable portable, multidimensional assessment of postural sway. Thirty healthy adults (15 females, 15 males) completed a modified Romberg protocol with systematic manipulation of stance (normal, tandem), visual condition (eyes open, eyes closed), and arm position (arms at sides, arms forward), including both left and right leading foot during tandem stance. Whole-body kinematics were recorded using a full-body IMU system comprising 17 wireless sensors. Center-of-mass (CoM) trajectories were derived from a 23-segment biomechanical model, and linear, spatial, and nonlinear sway metrics were computed. Statistical analyses were conducted using repeated-measures ANOVA, with significance set at p < 0.05. Visual deprivation significantly increased sway path length, mean sway velocity, and sway area across all stance conditions (p < 0.001). Tandem stance elicited greater mediolateral sway than normal stance (p < 0.001). Romberg ratios exceeded unity for all metrics and were significantly higher in tandem stance (p < 0.01). Arm position effects were negligible in normal stance but showed significant Vision × Arm interactions during tandem stance (p < 0.05). Leading foot position had no significant main effects. Combining a modified Romberg protocol with full-body IMU-based CoM analysis enables sensitive characterization of sensory dependence and directional postural control. Tandem stance with visual deprivation increases mediolateral postural demands under reduced base-of-support conditions, providing a more challenging context for evaluating directional postural control. Full article

The closed kinetic chain is an essential movement method for humans in daily life, and is also important as a training method. However, there have been few studies focusing on the hip adductor muscles. We used electromyography to measure the muscle activity of the hip adductor muscles during walking and standing movements as part of daily living activities, as well as bicycle ergometer exercise and squats. Concerning the role of the adductor muscles, they are thought to stabilize the pelvis during the unilateral support phase when walking, and to act as hip extension and hip alignment adjustment during cycle ergometer exercise. By using electromyography and inertial sensors, the results of this study showed that wearable technologies can be used to quantify neuromuscular function during closed kinetic chain movements. The results serve as a reference for the development of rehabilitation devices, assistive technologies, and computational models that need the simulation of hip joint mechanics. Linking muscle activity data to engineering-based strategies enables precise musculoskeletal assessment and intervention beyond biological observation. Full article

Flexible conductive hydrogels hold great promise in wearable electronics and biomonitoring applications, yet their practical use is constrained by issues such as poor low-temperature tolerance, susceptibility to dehydration, and limited multifunctional sensing capabilities. This study successfully synthesized a dual-conductive lithium-ion and calcium-ion hydrogel based on acrylamide/gelatin via a simplified low-temperature one-pot polymerization method. At 60 °C, mixing acrylamide, gelatin, lithium chloride, and calcium chloride within 40 min constructed a network structure featuring covalent bonds, ionic bonds, and hydrogen bonds. The resulting material exhibited exceptional extensibility with a break elongation of 1408.5% and tensile strength of 134.2 kPa while maintaining strong adhesion to nine different substrates. It retained flexibility at −20 °C and demonstrated minimal mass loss (3% of initial value) after 10 days of aging. As a sensor, this hydrogel reliably responds to pressure, temperature, large-amplitude body movements, and subtle physiological signals like pulse and vocal cord vibrations. In animal simulation monitoring, its electrical resistance signals increased linearly with model body weight and remained stable between −20 °C and 20 °C. These results demonstrate the hydrogel’s broad application potential in wearable sensing, ecological monitoring, and smart agriculture. Full article

We investigated the effects of manipulating visual information on motor control indicators during the Waiter’s Bow Test. The results suggested that visual information occlusion reduced the maximum flexion angles of the lumbar spine and upper lumbar region. Furthermore, subjects who tested negative under the open-eye condition tested positive under the closed-eye condition. Regarding muscle activity in the rectus abdominis and erector spinae muscles, it was suggested that this activity was not affected by visual information. These findings indicate that visual sensory feedback is one factor influencing lumbar motor control. The integration of electromyography and accelerometer systems in this study highlights the role of wearable sensor technologies in quantifying neuromuscular function in Bioengineering. By restricting visual information, a model for sensory reweighting can be established for the design of biofeedback systems, rehabilitation robotics, and assistive devices. The results of this study demonstrate how sensor-based evaluation and sensory manipulation can inform the engineering of diagnostic and therapeutic technologies for motor control assessment. Full article

Inherited cardiomyopathies associated with high-risk genotypes, are characterized by a disproportionate risk of malignant ventricular arrhythmias and sudden cardiac death, often independent of left ventricular systolic dysfunction or advanced structural remodeling. Traditional surveillance strategies based on intermittent electrocardiography and phenotype-driven risk assessment are insufficient to capture the dynamic and often silent progression of electrical instability in these populations. This narrative review evaluates the emerging role of artificial intelligence (AI)-enabled sensor technologies in remote arrhythmic monitoring of genetically defined cardiomyopathy cohorts. Wearable ECG devices, implantable cardiac monitors, multisensor cardiac implantable electronic device algorithms, pulmonary artery pressure sensors, and contact-free systems enable continuous acquisition of electrophysiological and hemodynamic data, generating digital biomarkers that may reflect early arrhythmic vulnerability and subclinical decompensation. AI-driven analytics enhance signal processing, automated event detection, and remote data triage, with the potential to reduce clinical workload while preserving diagnostic sensitivity. However, current evidence predominantly derives from heterogeneous heart failure or general arrhythmia populations, and prospective validation in genotype-specific cohorts remains limited. Key challenges include algorithm generalizability, signal quality in ambulatory environments, data governance, interpretability of AI models, and integration into structured remote-care pathways. The convergence of genotype-informed risk stratification and multimodal AI-enabled sensing represents a promising strategy to transition from reactive device-based protection to proactive, precision-guided arrhythmic prevention. Dedicated genotype-focused studies and standardized digital endpoints are required to support safe and effective implementation in inherited cardiomyopathies. Full article

This work presents the development of a wrist-worn wireless sensor system for high-accuracy indoor human zone tracking. The proposed system employs machine learning techniques to combine data from multiple sources, including a Received Signal Strength Indicator (RSSI) from wireless signals, three-axis acceleration, and three-axis angular velocity. A prototype wearable wireless sensor device was implemented using a SparkFun Thing Plus-XBee3 microcontroller supporting the Zigbee/IEEE 802.15.4 standard at 2.4 GHz, integrated with a six-degree-of-freedom IMU sensor (MPU-6050). Experiments using one wrist-worn sensor as a transmitter and one base station as a receiver were conducted in a two-story residential building environment covering three zones (i.e., staircase area, living room, and dining room) under static and dynamic test scenarios. Classification performances of 33 machine learning classifiers with different data feature groups and window sizes were evaluated. The results demonstrate the achievement of wrist-worn wireless sensor system development. The system exhibits high communication reliability with a packet delivery ratio (PDR) of 99.99% and can efficiently track data signals in real time. Results indicate that using only raw RSSI data achieves 75.0% accuracy in classifying human zones. However, when statistical RSSI features and accelerometer data fusion are applied, accuracies significantly increase to 98.7% (static scenario, wide neural network with a window size of 25) and 99.6% (dynamic scenario, Fine k-NN). These results demonstrate the system’s potential for indoor human tracking applications. Full article

Sleep abnormalities and circadian rhythm disruptions are frequently observed in psychiatric disorders such as depression and schizophrenia. However, most previous studies have examined circadian rhythms and sleep separately, limiting understanding of how these processes interact within individuals. This study examined circadian and sleep characteristics in depression and schizophrenia compared with healthy controls using multi-day wrist actigraphy. Circadian rhythms were assessed using parametric and non-parametric measures of rest–activity patterns, and sleep metrics were derived using a validated actigraphy-based algorithm. Distinct patterns were observed across diagnostic groups. Schizophrenia showed widespread disruption in daily activity patterns, with altered timing and reduced rhythm strength. Sleep was longer but highly fragmented, with frequent awakenings despite increased time in bed. In contrast, depression showed more limited changes, mainly in activity timing and overall activity levels, while sleep and daily patterns remained closer to controls. A key finding was the identification of distinct circadian–sleep profiles for each condition, with global disruption in schizophrenia and more selective alterations in depression. These findings show that combining circadian and sleep measures provides a clearer understanding of psychiatric disorders and may support monitoring and targeted interventions based on daily behavioral rhythms. Full article

(1) Background: The local divergence exponent (LDE) is a sensitive measure of walking stability deterioration and risk of falling in older adults. We aim to determine the validity the LDE measured using a mobile phone and to assess its ability to discriminate between healthy young and older adults; (2) Methods: 20 older adults (76.4 ± 4.6 years) and 20 young adults (29.1 ± 6.5 yrs) walked for 6 min on a 20-m walkway while wearing a research-grade inertial measurement unit (IMU) and a mobile phone placed on the sternum to record 3D acceleration data. The LDE was calculated using data from both devices for 3D, vertical (VT), mediolateral (ML), anteroposterior (AP), and norm (N) accelerations. ICC (3,1) was used to determine the validity of the mobile phone’s LDE. Mann–Whitney U tests were used to determine age-group discriminability of LDE measures; (3) Results: LDEs demonstrated excellent absolute agreement between the wearable IMU and mobile phone (ICC = 0.844). Mobile phone-derived LDEs demonstrated excellent validity relative to the wearable IMU (ICC > 0.75). No significant age-related differences in LDE were observed; wearable or mobile sensors (both p > 0.05); (4) Conclusions: LDEs measures obtained with a mobile phone are valid. No age group differences were identified. Full article

Background: Freezing of gait (FoG) is a common symptom of Parkinson’s disease, especially in its later stages of progression. Characterized by involuntary stopping during normal gait patterns, FoG greatly increases fall risk, reducing quality of life. Given the complex presentation and etiology of FoG, current treatments have proven ineffective in managing episodes. In recent years, machine learning algorithms have been leveraged to derive actionable clinical insights from biomedical datasets. As a manifestation of neuromechanical dysfunction, impending FoG episodes may be characterized through data collected by wearable devices and sensors. Objective: This scoping review evaluates the current landscape of machine and deep learning-derived biomarkers to enhance the personalized management of FoG. Methods: This scoping review was conducted using established methodological frameworks for scoping reviews and is reported in accordance using the PRISMA-ScR checklist. Three databases were queried, with screening yielding 60 studies. Results: Thirty-nine papers reported on deep learning techniques, with the most common architectures being convolutional neural networks and long short-term memory models. Conclusions: Inertial measurement units, which can be worn on various locations, may be a promising modality for practical implementation. To generate closed-loop FoG therapies, algorithms can be integrated into real-time systems like robotic exoskeletons or adaptive deep brain stimulation. Future work in generating datasets from ambulatory devices, as well as distributed computing strategies, may lead to real-time FoG management. Full article

Wearable biosensors increasingly stream multi-channel physiological and behavioral data outside the laboratory, yet most deployments still end in dashboards or threshold alarms that leave interpretation open to the user. In high-stakes domains, such as military, emergency response, aviation, industry, and elite sport, the constraint is rarely data availability but the cognitive effort required to convert noisy signals into timely, actionable decisions. We argue for on-person cognitive co-pilots: systems that integrate multimodal sensing, compute probabilistic state estimates on devices, synthesize those states with task and environmental context using locally hosted large language models (LLMs), and deliver recommendations through attention-appropriate cues that preserve autonomy. Enabling conditions include mature wearable sensing, edge artificial intelligence (AI) accelerators, tiny machine learning (TinyML) pipelines, privacy-preserving learning, and open-weight LLMs capable of local deployment with retrieval and guardrails. However, critical research gaps remain across layers: sensor validity under real-world conditions, uncertainty calibration and fusion under distribution shift, verification of LLM-mediated reasoning, interaction design that avoids alarm fatigue and automation bias, and governance models that protect privacy and consent in constrained settings. We propose a layered technical framework and research agenda grounded in cognitive engineering and human–automation interaction. Our core claim is that local, uncertainty-aware reasoning is an architectural prerequisite for trustworthy, low-latency augmentation in isolated, confined, and extreme environments. Full article

Accurately monitoring physical activity, including stationary cycling on an exercise bike, is important in managing chronic diseases and rehabilitation after lower limb surgery. This study aimed to validate a new smartphone-based sensor application (the BeSAFE+) for activity recognition and step counting across five phone placements, using the SENS Motion^® system as a reference standard, and observed activity time as ground truth. In a laboratory-based study, 20 participants performed walking, brisk walking, running, high- and low-intensity cycling, sitting, standing, and lying activities while carrying five smartphones placed in the front and back trouser pockets, a backpack, a running armband, and a fanny pack, and wearing the activity tracker. The front pocket placement had the most accurate classification during cycling activities (89–93%) versus SENS Motion^® (96–98%). For other activities, the highest overall classification accuracy was achieved with the phone in the back pocket. Overall, the SENS Motion^® activity tracker demonstrated higher classification accuracy than most smartphone placements across all activities, except for running. Nevertheless, several smartphone placements and Application Programming Interface (API) approaches achieved activity recognition and step count estimates that were not significantly different from the SENS Motion^® activity tracker, indicating that smartphone-based activity recognition can be valid under specific conditions. Full article

Continuous monitoring of pathological motor features is vital for post-stroke rehabilitation but remains challenged by power reliance and low sensitivity of wearable sensors. Here, we develop a high-sensitivity, self-powered breathable nanogenerator (BN-TENG) utilizing fish-scale-derived biological hydroxyapatite/carbon (Bio-HAp/C) fillers within electrospun polyvinylidene fluoride (PVDF) nanofibers. The Bio-HAp/C enhances electron-trapping capability, while a high-resilience ethylene-vinyl acetate (EVA) spacer optimizes contact-separation dynamics. The BN-TENG achieves a superior sensitivity of 16.28 V·N⁻¹ and remarkable stability over 10,000 cycles. By implementing a multi-node sensing strategy, the sensor successfully captures complex hemiplegic patterns, including compensatory shoulder hiking, distal muscle spasticity, and postural asymmetry. By resolving subtle micro-vibrations missed by traditional electronics, this work provides a sustainable, autonomous interface for characterizing pathological motor features and assessing rehabilitation progress in hemiplegic patients. Full article