Search Results (178)

Object detection in complex industrial environments is prone to being affected by insufficient dynamic weighting of local and global features, as well as illumination variations and impurities. Moreover, existing models suffer from excessive model complexity, which directly impairs computational efficiency. To more accurately distinguish Chinese herbal materials with diverse morphologies, this paper proposes the MobileAttn module. Drawing on the idea of token representation in the Transformer architecture, this module extracts contextual information through global feature compression, fuses it with tokens to generate a spatial attention map, and realizes dynamic recalibration of convolutional features. This process enhances the feature weights of key semantic regions, suppresses redundant background information, and improves feature discriminability. To address illumination interference, brightness-aware weights are combined with dual-path (channel and spatial) attention for global control, dynamically reducing the impact of illumination; this component is named LightAttn. When Chinese herbal materials contain common industrial unknown impurities (e.g., small stones and weeds), an impurity detection auxiliary module, a post-processing step independent of the main detection network, is proposed. This module refines Non-Maximum Suppression (NMS) logic to distinguish target Chinese herbal materials from interfering impurities. Subsequently, it accurately locates and marks impurities on the conveyor belt, thereby achieving effective unknown impurity detection. Experimental results demonstrate that, compared with the original YOLOv11 on the Chinese herbal materials detection task, the optimized model achieves a 1.7% improvement in the overall mean Average Precision (mAP@0.5:0.95). On a per-class basis, gains are particularly pronounced for certain challenging high-aspect-ratio Chinese herbal materials. Prunella vulgaris and orange peel achieve respective AP improvements of 5.8% and 4.1%. Meanwhile, the model parameter count is reduced by 23.1% and the computational complexity by 20.3%. The F1-Score of the impurity detection results is 86.38%, verifying the effectiveness of the impurity detection auxiliary module. Full article

Background: Basal ganglia calcifications (BGCs) are frequently detected on brain CT scans in older adults, but their clinical relevance for mobility and fall risk is unclear. This study investigated the association of BGCs with impaired mobility and recurrent falls. Methods: In this cross-sectional study, all consecutive patients referred to the mobility clinic of a regional teaching hospital between 2019 and 2021 were included. Mobility was assessed using the Performance-Oriented Mobility Assessment (POMA) for balance, gait and overall mobility, and the Timed Up and Go (TUG) test for functional mobility. All assessments were performed by a trained physiotherapist. Recurrent falls were defined as self-reported occurrence of more than one fall in the past 12 months. Brain CT scans were evaluated for BGCs by a trained senior radiologist and were scored by severity. Univariable and multivariable logistic regression analyses were performed, adjusting for age, sex, and history of cardiovascular events. Results: A total of 253 participants were included (median age 82 years; 58% female), of whom 31% had BGCs. Falls data were available for 246 participants, and 70% reported recurrent falls. In both univariable and multivariable analyses, there was no evidence of a statistically significant association between the presence of BGCs and impaired balance, gait, overall mobility, functional mobility, or recurrent falls. Conclusions: No evidence of a statistically significant association was found between incidentally detected BGCs and impaired mobility or recurrent falls in older adults. Further longitudinal research is needed to confirm these findings and clarify whether BGCs are clinically relevant for mobility and fall risk assessment. Full article

To address the issues of low perception accuracy and poor robustness in traditional motion recognition methods within complex walking environments for visually impaired individuals, this study utilizes multi-modal data, including ECG, PPG, and IMU, for classification. Regarding the low filtering efficiency of multi-modal data, an improved wavelet filtering algorithm based on LSTM is proposed. To further enhance classification accuracy, this paper introduces a motion recognition method for the blindfolded mobility simulation based on an Attention-based Two-Stream Deep Fusion Convolutional Neural Network (ATS-DFCNN). The proposed method constructs a two-stream heterogeneous feature extraction architecture by synchronously collecting tri-axial motion signals and physiological signals from subjects. A 1D-CNN is employed to capture the spatial geometric features of limb movements, while a hybrid CNN-GRU network is utilized to mine the temporal evolution patterns of physiological stress. Furthermore, an attention mechanism is introduced to achieve dynamic weighted fusion at the feature level, which strengthens critical motion features and suppresses environmental noise. Experiments were conducted with 10 subjects simulating the movements of visually impaired individuals, covering typical actions such as walking, standing, climbing stairs, descending stairs, and falling. The results demonstrate that the proposed adaptive filtering algorithm achieves an AUC of 0.942, significantly improving feature distinctiveness compared to traditional algorithms. The ATS-DFCNN model achieved an average recognition accuracy of 92.2% across five activity categories, representing a 4.8% performance increase over single IMU modal classification. Particularly in fall detection, the model effectively reduces false alarms through physiological feedback and accurately infers motion intentions, providing reliable technical support for the safety monitoring of intelligent walking-aid systems. Full article

Urban navigation in dynamic environments remains a challenging problem for blind and visually impaired users due to the presence of unpredictable obstacles and the limitations of conventional navigation systems, which rely primarily on static map-based information and lack real-time environmental awareness. This paper presents a real-time sensor-driven navigation system based on a multi-agent architecture incorporating a reinforcement-learning navigation policy for assistive mobility in urban environments. The proposed system integrates GPS-based global localization with vision-based perception to enable continuous fusion of global route planning and local obstacle detection. This integration allows the system to dynamically adjust navigation strategies in response to changing environmental conditions. The architecture is designed as a modular multi-agent system comprising agents for perception, navigation, sensor fusion, personalization, safety arbitration, interface management, and system monitoring. The reinforcement learning component formulates local navigation as a sequential decision-making problem, where the navigation policy is trained to balance path efficiency, obstacle avoidance, and safety constraints through interaction with simulated environments. Prototype implementation is developed and evaluated in both simulation and controlled real-world scenarios. Experimental results demonstrate that the proposed system shows improved obstacle avoidance performance and navigation stability under the evaluated conditions while maintaining low-latency responsiveness compared to baseline navigation approaches. The system also exhibits robust behaviour under varying environmental conditions, supporting its potential applicability to assistive navigation tasks in controlled urban environments. The proposed approach contributes to a scalable architecture that integrates a reinforcement-learning navigation policy within a multi-agent coordination framework and real-time sensor perception, providing a foundation for the development of intelligent and deployable assistive navigation systems. Full article

Falls in older adults and individuals with balance impairments remain a major concern because they are closely associated with injury, reduced mobility, and loss of independence. This study presents a preclinical proof-of-concept for a cognitive smart walker architecture that combines user-compatible walking assistance with active safety intervention. The system integrates a 2D LiDAR sensor for contactless lower-limb monitoring, a six-degree-of-freedom (6-DOF) force/torque sensor to measure user–walker interaction, and an inertial measurement unit (IMU) for dynamic monitoring, with all data processed in real time on a Raspberry Pi/ROS-based platform. Normal walking assistance is provided through a command-level variable admittance-based controller that converts interaction forces into a smoothed signed duty-cycle command rather than a rigid speed-control signal. Safety decisions are managed by a Hierarchical State Machine (HSM). Early-risk conditions are handled through motor-based dynamic braking, whereas severe physical crises additionally deploy lateral support legs to enlarge the base of support. Within this framework, the system can detect and manage foot entanglement, grip loss, forward fall, vertical collapse, lateral fall, successive crises, and recovery-abort events. In experiments across multiple scenarios, the system correctly detected all 50 crisis cases and did not issue unnecessary interventions in 30 non-crisis cases. These findings show that the proposed architecture can preserve transparent walking assistance during normal gait while providing graded, context-sensitive active safety when risk emerges. Full article

Age-related macular degeneration (AMD) is one of the leading causes of vision impairment worldwide, making early and accurate detection essential for effective clinical intervention. Recent advances in deep learning have demonstrated promising results in automated retinal image analysis; however, most existing approaches rely on datasets acquired under controlled conditions, limiting their generalizability to real-world clinical environments. In this paper, we propose a novel AMD dataset designed to simulate unconstrained imaging conditions, by incorporating noise, luminance variations, and device-related artifacts commonly encountered during retinal scan acquisition. Using this dataset, we conduct a comprehensive comparative evaluation of six widely adopted deep learning architectures: VGG16, VGG19, InceptionV3, MobileNetV2, ResNet50, and DenseNet. Experimental results indicate notable performance variations across models, highlighting the impact of architectural design on robustness to image degradation. Among the evaluated approaches, VGG16 achieved the best overall performance. By further optimizing this architecture through targeted training and fine-tuning strategies, the proposed system reached an accuracy of 88% in AMD detection. These findings demonstrate the effectiveness of the optimized VGG16 model and underline the importance of realistic datasets for developing reliable deep learning-based diagnostic tools for practical clinical settings. Full article

Background: Parkinson’s disease (PD) is a progressive neurodegenerative disorder that affects millions globally, particularly those in the elderly population. Several occupational exposures typical of maritime environments are recognized or suspected risk factors for PD, warranting attention within occupational health frameworks. The disease is characterized by motor symptoms such as tremor, rigidity, and bradykinesia, as well as non-motor impairments including speech abnormalities. Objective: Early diagnosis is crucial for effective disease management but remains challenging due to symptoms overlapping with normal aging and other neurological conditions. This study presents a machine learning (ML)-based approach for the early diagnosis of PD using speech signal analysis. Methods: We employed six supervised ML classifiers to differentiate between PD patients and healthy controls based on vocal features. The experimental dataset, MDVR-KCL, consists of speech recordings from both reading tasks and spontaneous dialogs, collected via mobile devices. From these recordings, we extracted Mel-Frequency Cepstral Coefficients (MFCCs), Gammatone Frequency Cepstral Coefficients (GTCCs), and acoustic features such as jitter, shimmer, and harmonic-to-noise ratio. These features capture a broad range of prosodic, spectral, and articulatory characteristics associated with PD-related speech impairments. Speaker diarization was applied in spontaneous dialog recordings to separate participant speech. Hyperparameter tuning was performed using GridSearchCV with 10-fold cross-validation, while final model evaluation was conducted using Leave-One-Subject-Out Cross-Validation (LOSOCV) to ensure subject-independent performance assessment. Results: In the read-text task, the SVM model performed exceptionally, yielding 95.45% accuracy, 94.62% sensitivity, 95.97% specificity, an F1-score of 94.12%, and an AUC of 0.98 with an MCC value of 0.90, for GTCCs with the acoustic features. In the spontaneous dialog task, the XGB model demonstrated the highest overall performance across all metrics, with a test accuracy of 83.7%, a sensitivity of 76.3.9%, a specificity of 88.9%, an F1-score of 79.5%, an AUC value of 0.88, and an MCC value of 0.66. Conclusions: Comparable results were obtained on both spontaneous dialog and reading speech subsets, demonstrating the robustness of the approach across different speaking contexts. These results demonstrate the effectiveness of integrating cepstral and acoustic features with machine learning models for non-invasive PD classification. The findings support the use of speech-based digital biomarkers in early PD detection and highlight the potential for developing scalable tools. This work highlights the potential of speech-based digital diagnostics to support clinical decision-making and improve patient outcomes. Full article

Background: Wearable powered gait orthoses offer a clinically flexible alternative to treadmill-based robotic systems, yet evidence on different device configurations matched to the site of neuromuscular impairment remains limited. Methods: In this multicenter prospective pilot study, 75 participants with neurological gait impairment were allocated to a hip orthosis (HO; n = 39) or a knee–ankle–foot orthosis (KAFO; n = 36) group based on clinical assessment of predominant gait pattern. Both groups completed six overground gait-training sessions over three weeks. Primary outcomes were the Six-Minute Walk Test (6MWT) and Ten-Meter Walk Test (10MWT), assessed without (WO) and with (WITH) the device. Secondary outcomes were the Berg Balance Scale (BBS), Timed Up and Go Test (TUG), and Dynamic Gait Index (DGI), all assessed without the device. Wilcoxon signed-rank tests were used for pre-to-post comparisons. Results: Both groups demonstrated significant improvements in primary walking outcomes, with consistent gains in unassisted (WO) 6MWT and 10MWT performance across groups and in device-assisted (WITH) 10MWT speed; the one exception was a small statistically significant but clinically negligible decrease in device-assisted 6MWT in the KAFO group (−4.1 m, below established MCID). In the KAFO group, BBS improved by a median of 5.5 points (43.5 to 49.0, p = 0.0005), TUG decreased by 5.1 s (p < 0.001), and DGI improved by 6.0 points (p = 0.002); all three changes exceeded published minimum detectable change thresholds. In the HO group, pre-to-post differences in BBS (+1.0), TUG (+0.8 s; an unfavorable direction), and DGI (−2.0; an unfavorable direction) were statistically detectable but small in absolute magnitude, fell at or below published thresholds for minimum detectable change, and should not be interpreted as clinically meaningful improvement. The WO-WITH performance gap in the KAFO group narrowed substantially after training, with 10MWT time no longer differing significantly between conditions at post-training (p = 0.116). Conclusions: Six sessions of gait pattern-matched powered gait orthosis training produced clinically meaningful within-group improvements in walking outcomes in both groups. In the KAFO group, balance and functional mobility outcomes also showed clinically meaningful improvements; in the HO group, balance and functional mobility outcomes showed only statistically detectable but clinically non-meaningful fluctuations around near-ceiling baseline scores. Walking benefits generalized to unassisted ambulation in both groups. These findings support the feasibility of an individualized orthosis prescription framework and provide a basis for future randomized controlled trials. Full article

The Western Amazon is a global biodiversity hotspot, yet the Upper Napo River Basin (UNRB) remains understudied regarding aquatic ecosystem health along anthropogenic gradients. We integrated benthic macroinvertebrate assemblages with physicochemical and microbiological indicators across 45 sites to assess ecological quality under four impact scenarios: Few Threats (FT, reference sites; n = 6), Crop/Aquaculture (CA; n = 22), Gold Mining (GM; n = 10), and Wastewater Discharge (WD; n = 7). Analysis of 2285 individuals (62 families) revealed clear degradation across the anthropogenic gradient. Reference sites (FT) exhibited high integrity (q₀ = 24.3 families), establishing the regional baseline for Andean–Amazonian freshwater ecosystems. In stark contrast, GM sites showed catastrophic defaunation (q₀ = 9.9 families) coupled with extreme turbidity (1320 ± 1589 NTU) and heavy metal mobilization (Fe: 430 ± 229 µg/L; Cu: 338 ± 128 µg/L), placing these reaches in “Bad” ecological status (Ecological Quality Ratio, EQR ≤ 0.16). Wastewater sites reached critical fecal coliform levels (33,708 ± 58,047 CFU/100 mL)—165-fold higher than FT sites—indicating severe sanitary impairment and community collapse (EQR = 0.28, dominated by Chironomidae at 80%). The application of ASPT (Average Score Per Taxon) and EQR proved essential for detecting functional shifts toward tolerant assemblages even when raw biotic scores appeared moderate. Crop/Aquaculture sites showed intermediate degradation (EQR = 0.37–0.38), reflecting chronic pesticide exposure and habitat loss. We conclude that gold mining and wastewater discharge are the primary drivers pushing the UNRB toward ecological collapse, with GM exerting the most severe impact on aquatic biodiversity. Safeguarding this global freshwater stronghold requires immediate implementation of multimetric biomonitoring, enhanced mining regulation, wastewater treatment infrastructure, and establishment of Indigenous-led fluvial reserves to maintain long-term connectivity. Full article

This paper presents a prototype for an assistive navigation system that integrates three-dimensional audio spatialization with computer vision to improve the mobility of visually impaired individuals. The system uses stereoscopic depth perception and real-time point cloud reconstruction alongside a modified YOLO convolutional neural network for object detection and auralization techniques with head-related impulse response functions. Twenty participants (ten who were visually impaired and ten who were blindfolded) navigated controlled obstacle scenarios while wearing a chest-mounted camera and specialized headphones. The prototype achieved 95.00% precision in object classification across eleven obstacle categories and a 33.19% recall, indicating conservative detection behavior. The processing efficiency was 0.042489 s per image, which exceeds real-time requirements. User evaluation revealed an average collision rate of 0.5 per scenario and a mean completion time of 48 s. Statistical analysis showed no significant difference in collision rates between participant groups ($p=0.172$), though visually impaired participants demonstrated faster completion times ($p=0.003$). Integrating segmented, convolution-based audio processing with stereoscopic depth estimation enabled users to perceive obstacle locations through spatial sound cues, establishing a foundation for advancing assistive navigation technologies without extensive training. Full article

Sit-to-stand (STS) transitions are clinically informative indicators of functional independence and are sensitive to compensatory strategies associated with physical decline and pain. This study presents a non-contact, non-visual framework for quantitative STS assessment using a 60 GHz frequency-modulated continuous-wave (FMCW) radar in a residential setting. We developed a signal-processing pipeline that converts intermediate-frequency radar data into range–time intensity (RTI) maps, tracks dominant torso motion, and extracts temporal, kinematic, and spectral features. Experiments were conducted across two sensing orientations (subject-facing and side-facing), five mounting heights (45–153 cm), and three execution speeds, with approximately 30 repeated cycles per condition. For normal non-compensated STS transitions, radar-derived metrics reflected expected biomechanical scaling: mean full-cycle duration decreased from $23.90$ s (slow) to $13.95$ s (medium) and $7.98$ s (fast), while peak ascent velocity increased from $0.311$ m/s to $0.358$ m/s and dominant cadence increased from 0.0416 Hz to 0.125 Hz. Simulated abnormal transitions produced distinct and quantifiable deviations. Preparatory rocking introduced an additional oscillatory phase (mean rocking duration 2.36 s), prolonging the standing transition to 4.80 s and altering trajectory regularity. Across configurations, subject-facing mid-torso mounting provided the most continuous and separable STS signatures, whereas side-facing placement and extreme heights reduced effective radial motion or introduced clutter artifacts. These findings establish practical deployment guidelines and demonstrate that radar-derived STS metrics can serve as candidate digital biomarkers for unobtrusive, privacy-preserving detection of mobility decline, compensatory pain behaviors, and functional impairment in real-world home environments. Full article

Background: Post-COVID-19 syndrome (PCS) is associated with impairments in mobility, balance, and physical function, which may reduce quality of life. The 30 s Sit-to-Stand (30STS) and Timed Up and Go (TUG) tests are widely used clinical measures; however, their intra-rater reliability in older adults with PCS has not been established. Reliable outcome measures are essential for clinical assessment and rehabilitation planning. Methods: In this single-center pilot study, nineteen older adults with PCS were recruited as a convenience sample. Participants completed three trials of the 30STS and TUG tests on day one, with the protocol repeated after three days. The 30STS evaluates lower-limb strength and functional performance, while the TUG assesses balance, gait, and fall risk. Intra-class correlation coefficient (ICC), standard error of measurement (SEM), and minimum detectable change (MDC) were calculated. Results: The TUG showed an ICC of 0.995 (95% CI: 0.991–0.998), SEM of 0.48 s, and MDC of 1.33 s. The 30STS showed an ICC of 0.986 (95% CI: 0.973–0.994), SEM of 0.26 repetitions, and MDC of 0.72 repetitions. Conclusions: The TUG and 30STS demonstrate excellent intra-rater reliability and appear to be feasible clinical tools for assessing functional performance in older adults with PCS. However, findings should be interpreted cautiously due to the small, single-center pilot design and single evaluator. Further research is needed to confirm generalizability across broader PCS populations and clinical settings. Full article

Background: The Mobility and Quality of Life-7 Dimension (MobQoL-7D) is a new patient-reported outcome measure for mobility-related quality of life. Our aim was to translate and test a Dutch-language version. Methods: A cross-sectional psychometric evaluation study was undertaken. The sampling frame was community-dwelling adults living in the Netherlands who had a long-term (>6 months) mobility impairment. Participants were recruited through a Dutch research agency, and data were collected via online survey. Statistical and psychometric analyses were undertaken to assess the interpretability, validity and reliability of the MobQoL-7D Dutch, including assessment of missing data, floor/ceiling effects, test–retest reliability, structural validity, known-group validity and convergent validity. Results: n = 308 respondents completed the survey; sub-group sample sizes ranged from n = 29 to n = 87. No issues with missing data were found. Despite ceiling effects per item (ranging from 23.1% to 56.5%), there were no floor/ceiling effects for overall index values (12.3% and 0%, respectively). The findings show excellent test–retest reliability of the index value over a two-week period (n = 37; ICC = 0.95), and potential discriminative ability to detect differences between known groups. Factor analyses confirmed unidimensionality. Conclusions: The results provide promising evidence of the validity and reliability of the MobQoL-7D Dutch; further research is needed to confirm these findings. Full article

Water supplies contaminated by heavy metals pose a serious threat to human health, especially in areas without access to centralized testing facilities. While copper is a necessary heavy metal in trace levels, high concentrations can have detrimental effects on health, such as oxidative stress, cognitive impairment, and liver damage. Due to their expense, complexity, and reliance on laboratories, conventional detection techniques are accurate but unsuitable for real-time, dispersed deployment. Machine learning offers a potent solution to these constraints by facilitating the automatic, precise, and quick interpretation of complicated sensor data. It makes it possible to make decisions in real time without requiring a large laboratory infrastructure. In this work, a dual-mode optical sensor was developed using the colorimetry and fluorometry images of carbon dots embedded in hydrogels with the Cu²⁺ concentration of 0, 20, 50, 100, 200, and 500 μM. Data augmentation was used to expand the RGB picture dataset for each modality, and these data were interpolated to provide responses at 1 µM intervals (0–500 µM). We trained a comprehensive set of supervised machine learning models, including Logistic Regression, Support Vector Machines, Random Forest, and XGBoost, to categorize water samples into five risk-informed quality levels. The system achieved classification accuracies exceeding 96%. Furthermore, we built a simple user interface to make the system practically deployable in mobile phone. Together, these results demonstrate a scalable, interpretable, cost-effective, and quick solution for real-time water quality monitoring in resource-constrained environments. Since the proposed method focuses on classifying concentration ranges rather than precise quantification, a formal limit of detection (LOD) was not calculated; instead, the lowest concentration in the experimental dataset serves as the minimum detectable level. Full article

Background/Objectives: Cognitive impairment affects multiple brain functions, and its early detection is essential to prevent progression to dementia; artificial intelligence has shown considerable potential in this field. This scoping review aims to map the impact of artificial intelligence–based tools for the early detection of cognitive impairment by identifying the main technologies used, examining their effectiveness, and exploring their ethical implications. Methods: A scoping review was conducted between April and May 2025 following the PRISMA-ScR methodological framework; the review protocol was previously registered on the Open Science Framework. PubMed, Scopus, and Cochrane databases were searched using natural language and controlled vocabulary terms via Medical Subject Headings. The search was limited to articles published between 2020 and 2025, in English or Spanish, with free full-text access. Methodological quality was assessed using CASPe, JBI, and MMAT. Results: A total of 14 studies were included after the selection and critical appraisal process. The findings show that artificial intelligence–based tools such as deep-learning models applied to neuroimaging, speech and gait analysis, electronic health record analysis, and mobile health applications demonstrate promising accuracy in detecting early cognitive changes. These technologies enable the identification of subtle patterns that may be difficult to detect using conventional clinical assessments. Conclusions: AI-based tools can provide substantial support for clinical decision-making by effectively identifying subtle changes that are imperceptible to human intelligence. However, their use also raises ethical issues related to patient privacy and data security. Full article