Search Results (283)

The accurate forecasting of surface air temperature (T2M) is crucial for climate analysis, agricultural planning, and energy management. This study proposes a novel forecasting framework grounded in structured temporal decomposition. Using the Kolmogorov–Zurbenko (KZ) filter, all predictor variables are decomposed into three physically interpretable components: long-term, seasonal, and short-term variations, forming an expanded multi-scale feature space. A central innovation of this framework lies in training a single unified model on the decomposed feature set to predict the original target variable, thereby enabling the direct learning of scale-specific driver–response relationships. We present the first comprehensive benchmarking of this architecture, demonstrating that it consistently enhances the performance of both regularized linear models (Ridge and Lasso) and tree-based ensemble methods (Random Forest and XGBoost). Under rigorous walk-forward validation, the framework substantially outperforms conventional, non-decomposed approaches—for example, XGBoost improves the coefficient of determination ($R^2$) from 0.80 to 0.91. Furthermore, temporal decomposition enhances interpretability by enabling Ridge and Lasso models to achieve performance levels comparable to complex ensembles. Despite these promising results, we acknowledge several limitations: the analysis is restricted to a single geographic location and time span, and short-term components remain challenging to predict due to their stochastic nature and the weaker relevance of predictors. Additionally, the framework’s effectiveness may depend on the optimal selection of KZ parameters and the availability of sufficiently long historical datasets for stable walk-forward validation. Future research could extend this approach to multiple geographic regions, longer time series, adaptive KZ tuning, and specialized short-term modeling strategies. Overall, the proposed framework demonstrates that temporal decomposition of predictors offers a powerful inductive bias, establishing a robust and interpretable paradigm for surface air temperature forecasting. Full article

Background and Objectives: Sarcopenia, characterized by progressive loss of skeletal muscle mass and function, has increasingly been recognized not only as a physical health concern but also as a potential risk factor for cognitive decline. This study investigates the application of machine learning algorithms to classify cognitive status based on Mini-Mental State Examination (MMSE) scores in community-dwelling sarcopenic women. Materials and Methods: A dataset of 67 participants was analyzed, with MMSE scores categorized into severe (≤17) and mild (>17) cognitive impairment. Eight classification models—MLP, CatBoost, LightGBM, XGBoost, Random Forest (RF), Gradient Boosting (GB), Logistic Regression (LR), and AdaBoost—were evaluated using a repeated holdout strategy over 100 iterations. Hyperparameter optimization was performed via Bayesian optimization, and model performance was assessed using metrics including weighted F1-score (w_f1), accuracy, precision, recall, PR-AUC, and ROC-AUC. Results: Among the models, CatBoost achieved the highest w_f1 (87.05 ± 2.85%) and ROC-AUC (90 ± 5.65%), while AdaBoost and GB showed superior PR-AUC scores (92.49% and 91.88%, respectively), indicating strong performance in handling class imbalance and threshold sensitivity. SHAP (SHapley Additive exPlanations) analysis revealed that moderate physical activity (moderatePA minutes), walking days, and sitting time were among the most influential features, with higher physical activity associated with reduced risk of cognitive impairment. Anthropometric factors such as age, BMI, and weight also contributed significantly. Conclusions: The results highlight the effectiveness of boosting-based models in capturing complex patterns in clinical data and provide interpretable evidence supporting the role of modifiable lifestyle factors in cognitive health. These findings suggest that machine learning, combined with explainable AI, can enhance risk assessment and inform targeted interventions for cognitive decline in older women. Full article

This study investigated differences in energy-expenditure (EE) modeling between badminton players of varying competitive levels during aerobic training. It evaluated the impact of sensor quantity and sample size on prediction model accuracy and generalizability, providing evidence for personalized training-load monitoring. Fifty badminton players (25 elite, 25 enthusiasts) performed treadmill running, cycling, rope skipping, and stair walking. Data were collected using accelerometers (waist, wrists, ankles), a heart rate monitor, and indirect calorimetry (criterion EE). Multiple machine learning models (Linear Regression, Bayesian Ridge Regression, Random Forest, Gradient Boosting) were employed to develop EE prediction models. Performance was assessed using R², mean absolute percentage error (MAPE), and root mean square error (RMSE), with further evaluation via the Triple-E framework (Effectiveness, Efficiency, Extension). Elite athletes demonstrated stable, coordinated movement patterns, achieving the best values for R² and the smallest errors using minimal core sensors (typically dominant side). Enthusiasts required multi-site sensors to compensate for greater execution variability. Increasing sensors beyond three yielded no performance gains; optimal configurations involved 2–3 core accelerometers combined with heart rate data. Expanding sample size significantly enhanced model stability and generalizability (e.g., running task R² increased from 0.49 (N = 20) to 0.95 (N = 40)). Triple-E evaluation indicated that strategic sensor minimization coupled with sufficient sample size maximized predictive performance while reducing computational cost and deployment burden. Competitive level significantly influences EE modeling requirements. Elite athletes are suited to a “low-sensor, small-sample” scenario, whereas enthusiasts necessitate a “multi-sensor, large-sample” strategy. Full article

Background and Objectives: Sarcopenia is a progressive loss of skeletal muscle mass and function in elderly adults, posing a significant risk of frailty, falls, and morbidity. The current study designs and evaluates SarcoNet, a novel artificial neural network (ANN)-based classification framework developed in order to classify Sarcopenic from non-Sarcopenic subjects using a comprehensive real-time dataset. Methods: This pilot study involved 30 subjects, who were divided into Sarcopenic and non-Sarcopenic groups based on physician assessment. The collected dataset consists of thirty-one clinical parameters like skeletal muscle mass, which is collected using various equipment such as Body Composition Analyser, along with ten kinetic features which are derived from video-based gait analysis of joint angles obtained during walking on three terrain types such as slope, steps, and parallel path. The performance of the designed ANN-based SarcoNet was benchmarked against the traditional machine learning classifiers utilised including Support Vector Machine (SVM), k-Nearest Neighbours (k-NN), and Random Forest (RF), as well as hard and soft voting ensemble classifiers. Results: SarcoNet achieved the highest overall classification accuracy of about 94%, with a specificity and precision of about 100%, an F1-score of about 92.4%, and an AUC of 0.94, outperforming all other models. The incorporation of lower-limb joint kinetics such as knee flexion, extension, ankle plantarflexion and dorsiflexion significantly enhanced predictive capability of the model and thus reflecting the functional deterioration characteristic of muscles in Sarcopenia. Conclusions: SarcoNet provides a promising AI-driven solution in Sarcopenia diagnosis, especially in low-resource healthcare settings. Future work will focus on improving the dataset, validating the model across diverse populations, and incorporating explainable AI to improve clinical adoption. Full article

Parkinson’s disease (PD) impairs balance and gait through neuromotor dysfunction, yet conventional assessments often overlook subtle postural deficits during dynamic tasks. This study evaluated the diagnostic utility of center-of-pressure (CoP) features captured by pressure-sensing insoles during the Timed Up and Go (TUG) test. Using 39 PD and 38 control participants from the recently released open-access WearGait-PD dataset, the authors extracted 144 CoP features spanning positional, dynamic, frequency, and stochastic domains, including per-foot averages and asymmetry indices. Two scenarios were analyzed: the complete TUG and its 3 m walking segment. Model development followed a fixed protocol with a single participant-level 80/20 split; sequential forward selection with five-fold cross-validation optimized the number of features within the training set. Five classifiers were evaluated: SVM-RBF, logistic regression (LR), random forest (RF), k-nearest neighbors (k-NN), and Gaussian naïve Bayes (NB). LR performed best on the held-out test set (accuracy = 0.875, precision = 1.000, recall = 0.750, F1 = 0.857, ROC-AUC = 0.921) using a 23-feature subset. RF and SVM-RBF each achieved 0.812 accuracy. In contrast, applying the identical pipeline to the 3 m walking segment yielded lower performance (best model: k-NN, accuracy = 0.688, F1 = 0.615, ROC–AUC = 0.734), indicating that the multi-phase TUG task captures PD-related balance deficits more effectively than straight walking. All four feature families contributed to classification performance. Dynamic and frequency-domain descriptors, often appearing in both average and asymmetry form, were most consistently selected. These features provided robust magnitude indicators and offered complementary insights into reduced control complexity in PD. Full article

Truffle hunting in the Piedmontese landscapes of Northern Italy is not merely a foraging practice but a deeply embodied and multispecies relationship grounded in intergenerational knowledge, sensory attunement, and emotional connection to forest ecologies. This study draws on qualitative interviews with local truffle hunters (Trifulau) to examine how socio-ecological transformations driven by land privatization, vineyard expansion, monocultural hazelnut plantations, and tourism disrupt these traditional practices. Thematic analysis reveals five dimensions of transformation: ecological estrangement, dispossession and exclusion, erosion of knowledge transmission, commodification and spectacularizing, emotional and ontological loss. Hunters describe a loss of sensory orientation, access to ancestral commons, and a breakdown of the human–dog forest relational web, accompanied by feelings of grief, alienation, and identity erosion. We argue that these changes undermine ecological sustainability and threaten emotional, cultural, and epistemological sustainability. The findings call for a broadened understanding of sustainability, one that recognizes affective, multispecies, and place-based knowledge systems as vital to sustaining cultural landscapes. This study contributes to debates on rural transformation, non-material heritage, and the invisible costs of commodifying traditional ecological practices in globalizing economies. Full article

In this article, the classification of signals arising from the movements of the lower limb of the leg (LLL) based on electromyography (EMG) (walking, sitting, up and down the stairs) was carried out. In the data collection process, 25 athletes aged 15–22 were involved, and two types of data sets (DS-dataset) were formed using FreeEMG and Biosignalsplux devices. Six important time and frequency domain features were extracted from the EMG signals—RMS (Root Mean Square), MAV (Mean Absolute Value), WL (Waveform Length), ZC (Zero Crossing), MDF (Median Frequency), and SSCs (Slope Sign Changes). Several classification algorithms were used to detect and classify movements, including RF (Random Forest), NN (Neural Network), SVM (Support Vector Machine), k-NN (k-Nearest Neighbors), and LR (Logistic Regression) models. Analysis of the experimental results showed that the RF algorithm achieved the highest accuracy of 98.7% when classified with DS collected via the Biosignalsplux device, demonstrating an advantage in terms of performance in motion recognition. The results obtained from the open systems used in signal processing enable real-time monitoring of athletes’ physical condition, which plays a crucial role in accurately and rapidly determining the degree of muscle fatigue and the level of physical stress experienced during training sessions, thereby allowing for more effective control of performance and timely prevention of injuries. Full article

In the native açaí groves of Lago do Maicá, in western Pará, harvesting is still performed using traditional techniques such as the peconha, which is a rope device tied to the feet that helps with climbing açaí palms. The absence of affordable and locally adaptable technologies compromises the safety of extractivists and limits the strengthening of the açaí value chain, affecting the development of a forest-based bioeconomy. This study focused on the Quilombo of Murumuru to understand the profile of local extractivists and identify which technologies could be more easily adopted in floodplain environments. After ethics approval, fieldwork involved participatory activities including knowledge-sharing meetings, transect walks, community discussions, and structured interviews. The results indicated that most collectors identify themselves primarily as açaí extractivists. Some rely exclusively on this activity for income, while others complement it with fishing or agro-extractivism. Reports of occupational risks were frequent, especially due to falls and contact with venomous animals. There was also a clear lack of technical assistance and limited access to context-sensitive technologies. The study highlights the need for institutional partnerships that support income diversification, value traditional knowledge, and improve working conditions. Strengthening the native açaí value chain in floodplain regions is essential for reducing socioeconomic vulnerability and advancing a regenerative, community-centered bioeconomy in the Amazon. Full article

Classifying human locomotor activities from wearable sensor data is an important high-level component of control schemes for many wearable robotic exoskeletons. In this study, we evaluated three machine learning models for classifying activity type (walking, running, jumping), speed, and surface incline using input data from body-worn inertial measurement units (IMUs) and e-textile insole pressure sensors. The IMUs were positioned on segments of the lower limb and pelvis during lab-based data collection from 16 healthy participants (11 men, 5 women), who walked and ran on a treadmill at a range of preset speeds and inclines. Logistic Regression (LR), Random Forest (RF), and Light Gradient-Boosting Machine (LGBM) models were trained, tuned, and scored on a validation data set (n = 14), and then evaluated on a test set (n = 2). The LGBM model consistently outperformed the other two, predicting activity and speed well, but not incline. Further analysis showed that LGBM performed equally well with data from a limited number of IMUs, and that speed prediction was challenged by inclusion of abnormally fast walking and slow running trials. Gyroscope data was most important to model performance. Overall, LGBM models show promise for implementing locomotor activity prediction from lower-limb-mounted IMU data recorded at different anatomical locations. Full article

This study introduces GaitX, a real-time pedestrian behavior recognition system that leverages only the built-in sensors of a smartphone eliminating the need for external hardware. The system is capable of detecting abnormal walking behavior, such as using a smartphone while walking, regardless of whether the device is handheld or pocketed. GaitX applies multivariate time-series features derived from accelerometer data, using ensemble machine learning models like XGBoost and Random Forest for classification. Experimental validation across 21 subjects demonstrated an average classification accuracy of 92.3%, with notably high precision (97.1%) in identifying distracted walking. In addition to real-time detection, the system explores the link between gait variability and psychological traits by integrating MBTI personality profiling, revealing the potential for emotion-aware mobility analytics. Our findings offer a scalable, cost-effective solution for mobile safety applications and personalized health monitoring. Full article

In the context of promoting sustainable mobility, walking and cycling have been widely recognized for their environmental and health benefits. However, a notable gap often exists between residents’ motivation to engage in these modes and their actual behavior. This study focuses on this motivation–behavior discrepancy and explores how heterogeneous information interventions—within the constraints of the existing built environment—can effectively influence residents’ travel psychology and behavior. Drawing on Protection Motivation Theory, this study aims to uncover the psychological mechanisms behind travel-mode choices and quantify the relative impacts of different types of information interventions. A travel survey was conducted in Yangzhou, China, collecting data from 1052 residents. Cluster analysis was performed using travel psychology data to categorize travel motivations and examine their alignment with actual travel behavior. A random forest model was then employed to assess the effects of individual attributes, travel characteristics, and information intervention attributes on the choice of walking and cycling. The results reveal a significant motivation–behavior gap: while 76% of surveyed residents expressed motivation to walk or cycle, only 30% actually adopted these modes. Based on this, further research shows that informational attributes exhibit a stronger effect in terms of promoting walking and cycling behavior compared to individual attributes and travel characteristics. Among these, health-related information demonstrates the maximum efficacy in areas with well-developed infrastructure. Specifically, health-related information has a greater impact on cycling (21.4%), while environmental information exerts a stronger influence on walking (7.31%). These findings suggest that leveraging information to promote walking and cycling should be more targeted. Full article

This study employs Hannah Arendt’s (1958) the human condition as a philosophical framework to examine walking not merely as a physical activity but as a meaningful form of environmental consciousness. Homo faber, which denotes tool making, corresponds to the nature-based railway regeneration exemplified by the Gyeongui Line Forest Park in Seoul City, South Korea. By applying walking as a method, bifurcated themes are explored: a pedestrian-provision focus on walkability and an environmentally oriented focus consisting of nature and culture, supporting the notion that environmental elements are co-experienced through the embodied activity of walking. Thematic findings are supported by generalized additive models, grounded in a between-method triangulation attempt. The results confirm the interdependencies among the park’s environment, pedestrian satisfaction, and environmental consciousness. Specifically, the environment surrounding the park, which traverses natural and cultural elements, is strongly associated with both pedestrian satisfaction and environmental sensitivity. The research reifies walking as a fundamental human condition, encompassing labor, work, and action, while arguing for heuristic reciprocity between homo faber and nature, as well as framing walking as a sustainably meaningful urban intervention. This study contributes to maturing the theoretical understanding of walking as a vital human condition and suggests practical insights for pedestrian-centered spatial transformation. Full article

Background/Objectives: The main objective of the present study is to assess the short-term effects of Forest Bathing (FB) conducted in a Mediterranean forest on individuals with fibromyalgia (FM) and/or chronic fatigue syndrome/myalgia encephalomyelitis (CFS/ME) on perceived pain, fatigue, state anxiety, positive and negative affect, mood states, and state mindfulness. Methods: A total of 44 participants with FM and/or CSF/ME agreed to participate in this study. The FB session consisted of a 3 km silent walk, lasting three hours and guided by a specialized psychologist and a mountain guide to guarantee the safety of the activity. Paired-sample t-tests were used to analyze the pre–post changes in perceived pain, fatigue, state anxiety, positive and negative affect, mood states, and mindfulness. Results: All reported variables but self-reported pain showed statistically significant pre–post variations after the FB session. Particularly, large-to-very-large improvements in positive and negative affect, state anxiety, tension, depression, anger, and vigor were found. Small-to-moderate effect sizes for fatigue, friendliness, and state mindfulness were also reported. Conclusions: This study provides preliminary evidence of the short-term benefits of FB in individuals with FM and/or CFS/ME, especially on state anxiety and negative affect. Full article

Since its introduction into the USA, the spotted lanternfly (SLF), Lycorma delicatula, (White) (Hemiptera: Fulgoridae) has spread across the landscape relatively unchecked. With a wide host range, it is considered a serious pest of native forest species, as well as agricultural crops. Circle traps placed on Ailanthus altissima (Miller) Swingle (Sapindales: Simaroubaceae) are passive traps collecting SLF as they walk up and down the tree trunk. These traps are successful at detecting new populations of SLF, but this can be challenging to implement at a large scale due to costs and host availability. To improve and facilitate SLF trapping practices, we investigated three key trapping components: improved collection containers, placement on alternative hosts, and lure (methyl salicylate) impact. In initial trials comparing collection jars to removable plastic bags, the adult SLF catch was four times higher using the bag design. In a multi-state survey at varying population densities, the bag traps were comparable to the jar traps but were significantly more effective than BugBarrier^® tree bands, especially during the adult stage. Catch and detection in circle traps placed on alternative hosts, Acer spp. L. (Sapindales: Sapindalaceae) and Juglans nigra L. (Fagales: Juglandaceae), were comparable to those placed on the preferred host A. altissima, especially in the earlier life stages. Additionally, detection rates of methyl salicylate-baited traps on all three hosts were comparable to those on non-baited traps. These results suggest that circle traps fitted with bags provide higher trap catch and an improvement in sample quality. In addition, circle traps were equally effective when placed on maple and black walnut, while methyl salicylate lures do not enhance trap catch or detection. Full article

Motor deficits, including atypical gait, are common in individuals with autism spectrum disorder (ASD), although the precise nature and cause of this co-occurrence is unclear. Because walking is a natural activity and gait timing is a metric that is relatively accessible to measurement, we explored whether autistic gait could be described solely in terms of the timing of gait parameters. The aim was to establish whether temporal analysis, including machine learning models, could be used as a group classifier between ASD and typically developing (TD) individuals. Thus, we performed a high-resolution temporal analysis of gait on two age-matched groups of male participants: one group with high-functioning ASD and a comparison TD group (each N = 16, age range 7 to 35 years). The primary data were collected using a VICON^® 3D motion analysis system. Significant increased temporal variability of all gait parameters tested was observed for the ASD group compared to the TD group (p < 0.001). Further machine learning analysis showed that the temporal variability of gait could be used as a group classifier for ASD. Of the twelve models tested, the best-fitting model type was random forest. The temporal analysis of gait with machine learning algorithms may be useful as a future ASD diagnostic aid. Full article