Search Results (871)

The implementation of the trans-European tourist cycle route network “EuroVelo” is fostering new strategic importance for non-motorized mobility and the associated practice of cycling tourism. Indeed, slow tourism offers a pathway for the development of inland areas. The infrastructure supporting it, such as long-distance cycling and walking paths, can act as a vital connection, stimulating regeneration in peripheral territories by enhancing environmental and landscape assets, as well as preserving heritage, local identity, and culture. The regeneration of peri-urban landscapes through soft mobility is recognized as the cornerstone for accessibility to material and immaterial resources (including ecosystem services) for multiple categories of users, including the most vulnerable, especially following the restoration of green-area systems and non-urbanized areas with degraded ecosystems. Considering the forthcoming implementation of the Magna Grecia cycling route, the southernmost segment of the “EuroVelo” network traversing three regions in southern Italy, this contribution briefly examines the necessity of defining new development policies to effectively integrate sustainable slow tourism with the enhancement of environmental and landscape values in the coastal areas along the route. Specifically, this case study focuses on a coastal stretch characterized by significant morphological and environmental features and notable landscapes interwoven with densely built environments. In this area, environmental and landscape values face considerable threats from scattered, irregular, low-density settlements, abandoned sites, and other inappropriate constructions along the coastline. Full article

Understanding the carbon emissions of multimodal travel—comprising walking, metro, bus, cycling, and ride-hailing—is essential for promoting sustainable urban mobility. However, most existing studies focus on single-mode travel, while underlying spatiotemporal and behavioral determinants remain insufficiently explored due to the lack of fine-grained data and interpretable analytical frameworks. This study proposes a novel integration of high-frequency, real-world mobility trajectory data with interpretable machine learning to systematically identify the key drivers of carbon emissions at the individual trip level. Firstly, multimodal travel chains are reconstructed using continuous GPS trajectory data collected in Beijing. Secondly, a model based on Calculate Emissions from Road Transport (COPERT) is developed to quantify trip-level CO₂ emissions. Thirdly, four interpretable machine learning models based on gradient boosting—XGBoost, GBDT, LightGBM, and CatBoost—are trained using transportation and built environment features to model the relationship between CO₂ emissions and a set of explanatory variables; finally, Shapley Additive exPlanations (SHAP) and partial dependence plots (PDPs) are used to interpret the model outputs, revealing key determinants and their non-linear interaction effects. The results show that transportation-related features account for 75.1% of the explained variance in emissions, with bus usage being the most influential single factor (contributing 22.6%). Built environment features explain the remaining 24.9%. The PDP analysis reveals that substantial emission reductions occur only when the shares of bus, metro, and cycling surpass threshold levels of approximately 40%, 40%, and 30%, respectively. Additionally, travel carbon emissions are minimized when trip origins and destinations are located within a 10 to 11 km radius of the central business district (CBD). This study advances the field by establishing a scalable, interpretable, and behaviorally grounded framework to assess carbon emissions from multimodal travel, providing actionable insights for low-carbon transport planning and policy design. Full article

In this study, four types of fall detection systems for seniors living alone using x-y scatter and Doppler range images measured from frequency-modulated continuous wave (FMCW) millimeter-wave (mmWave) sensors were introduced. Despite advancements in fall detection, existing long short-term memory (LSTM)-based approaches often struggle with effectively distinguishing falls from similar activities of daily living (ADLs) due to their uniform treatment of all time steps, potentially overlooking critical motion cues. To address this limitation, an attention mechanism has been integrated. Data was collected from seven participants, resulting in a dataset of 669 samples, including 285 falls and 384 ADLs with walking, lying, inactivity, and sitting. Four LSTM-based architectures for fall detection were proposed and evaluated: Raw-LSTM, Raw-LSTM-Attention, HOG-LSTM, and HOG-LSTM-Attention. The histogram of oriented gradient (HOG) method was used for feature extraction, while LSTM networks captured temporal dependencies. The attention mechanism further enhanced model performance by focusing on relevant input features. The Raw-LSTM model processed raw mmWave radar images through LSTM layers and dense layers for classification. The Raw-LSTM-Attention model extended Raw-LSTM with an added self-attention mechanism within the traditional attention framework. The HOG-LSTM model included an additional preprocessing step upon the RAW-LSTM model where HOG features were extracted and classified using an SVM. The HOG-LSTM-Attention model built upon the HOG-LSTM model by incorporating a self-attention mechanism to enhance the model’s ability to accurately classify activities. Evaluation metrics such as Sensitivity, Precision, Accuracy, and F1-Score were used to compare four architectural models. The results showed that the HOG-LSTM-Attention model achieved the highest performance, with an Accuracy of 95.3% and an F1-Score of 95.5%. Optimal self-attention configuration was found at a 2:64 ratio of number of attention heads to channels for keys and queries. Full article

Background: Gait impairments are common in individuals with knee osteoarthritis awaiting total knee arthroplasty, affecting their mobility and quality of life. This study aimed to assess and compare biomechanical gait features between individuals awaiting total knee arthroplasty and healthy, non-arthritic controls, focusing on less-explored variables using sensor-based measurements. Methods: A cross-sectional observational study was conducted with 60 participants: 21 individuals awaiting total knee arthroplasty and 39 nonarthritic controls aged 64–85 years. Participants completed a standardized 14 m walk, and 17 biomechanical gait parameters were measured using the BTS G-Walk inertial sensor. Key variables, such as stride duration, cadence, symmetry indices, and pelvic angles, were analyzed for group differences. Results: The pre-total knee arthroplasty group exhibited significantly longer gait cycles and stride durations (p < 0.001), reduced cadence (p < 0.001), and lower gait cycle symmetry index (p < 0.001) than the control group. The pelvic angle symmetry indices for tilt (p = 0.014), rotation (p = 0.002), and obliquity (p < 0.001) were also lower. Additionally, the pre-total knee arthroplasty group had lower propulsion indices for both legs (p < 0.001) and a lower walking quality index on the right leg (p = 0.005). The number of elaborated steps was significantly greater in the pre-total knee arthroplasty group (left, p < 0.001, right: p < 0.001). No significant differences were observed in any other gait parameters. Conclusions: This study revealed significant gait impairment in individuals awaiting total knee arthroplasty. Although direct evidence for prehabilitation is lacking, future research should explore whether targeted approaches, such as strengthening exercises or gait retraining, can improve gait and functional outcomes before surgery. Full article

Falls are a major safety concern in physically demanding occupations such as roofing, where workers operate on inclined surfaces under unstable postures. While inertial measurement units (IMUs) are widely used in wearable fall detection systems, they often fail to capture early indicators of instability related to foot–ground interactions. This study evaluates the effectiveness of plantar pressure sensors, alone and combined with IMUs, for fall detection on sloped surfaces. We collected data in a controlled laboratory environment using a custom-built roof mockup with incline angles of 0°, 15°, and 30°. Participants performed roofing-relevant activities, including standing, walking, stooping, kneeling, and simulated fall events. Statistical features were extracted from synchronized IMU and plantar pressure data, and multiple machine learning models were trained and evaluated, including traditional classifiers and deep learning architectures, such as MLP and CNN. Our results show that integrating plantar pressure sensors significantly improves fall detection. A CNN using just three IMUs and two plantar pressure sensors achieved the highest F1 score of 0.88, outperforming the full 17-sensor IMU setup. These findings support the use of multimodal sensor fusion for developing efficient and accurate wearable systems for fall detection and physical health monitoring. Full article

Background/Objectives: Prehabilitation is a multimodal intervention introduced in preparation for various surgical procedures. The most effective treatment for obesity is bariatric surgery. Physiotherapy during prehabilitation for bariatric surgery may be an effective method of functional capacity improvement. We aimed to evaluate the impact of an individual outpatient 12-week, exercise-based physiotherapy program featuring prehabilitation on functional status, exercise tolerance, everyday mobility, and fatigue among patients qualified for bariatric surgery. Methods: The completion of an individual outpatient 12-week, exercise-based physiotherapy program during prehabilitation was an inclusion criterion for the study group. Participants included in the study and control groups were assessed twice, after enrollment into the prehabilitation program (the first assessment) and after prehabilitation but before surgery (the second assessment). Both assessments involved functional tests (a six-minute walking test [6MWT], a timed up and go test [TUG], a chest mobility test, anthropometric measures, a mobility index [Barthel], and a modified Borg scale). The collected anthropometric data and values from the 6MWT were used to create original linear models. This study followed STROBE recommendations. Results: The study group and control group did not differ statistically in terms of their anthropometric data. Statistically significant results were obtained between the first and second assessments in both groups in terms of body weight and waist circumference. However, only the study group showed improved results in the TUG test (p = 0.0001) and distance in the 6MWT (p = 0.0005). The study group presented with the normalization of blood pressure (BP) after exertion in the second assessment (systolic BP p = 0.0204; diastolic BP p = 0.0377), and the 6MWT results were close to the norms. According to the original linear model used to predict performance in the 6MWT, the primary modifiable determinant of exercise tolerance was the participant’s weight, while gender served as a non-modifiable determinant. Conclusions: Exercise-based physiotherapy in prehabilitation was associated with improved functional capacity in patients preparing for bariatric surgery, contributing to the improvement in 6MWT results in relation to the norms as well as exercise tolerance. Body weight may be an independent factor determining distance in the 6MWT for patients undergoing prehabilitation for bariatric surgery. Full article

Phishing attacks pose significant risks to security, drawing considerable attention from both security professionals and customers. Despite extensive research, the current phishing website detection mechanisms often fail to efficiently diagnose unknown attacks due to their poor performances in the feature selection stage. Many techniques suffer from overfitting when working with huge datasets. To address this issue, we propose a feature selection strategy based on a convolutional graph network, which utilizes a dataset containing both labels and features, along with hyperparameters for a Support Vector Machine (SVM) and a graph neural network (GNN). Our technique consists of three main stages: (1) preprocessing the data by dividing them into testing and training sets, (2) constructing a graph from pairwise feature distances using the Manhattan distance and adding self-loops to nodes, and (3) implementing a GraphSAGE model with node embeddings and training the GNN by updating the node embeddings through message passing from neighbors, calculating the hinge loss, applying the softmax function, and updating weights via backpropagation. Additionally, we compute the neighborhood random walk (NRW) distance using a random walk with restart to create an adjacency matrix that captures the node relationships. The node features are ranked based on gradient significance to select the top k features, and the SVM is trained using the selected features, with the hyperparameters tuned through cross-validation. We evaluated our model on a test set, calculating the performance metrics and validating the effectiveness of the PhishGNN dataset. Our model achieved a precision of 90.78%, an F1-score of 93.79%, a recall of 97%, and an accuracy of 93.53%, outperforming the existing techniques. Full article

Blind and visually impaired (BVI) people face significant challenges in perception, navigation, and safety during travel. Existing infrastructure (e.g., blind lanes) and traditional aids (e.g., walking sticks, basic audio feedback) provide limited flexibility and interactivity for complex environments. To solve this problem, we propose a real-time travel assistance system based on deep learning. The hardware comprises an NVIDIA Jetson Nano controller, an Intel D435i depth camera for environmental sensing, and SG90 servo motors for feedback. To address embedded device computational constraints, we developed a lightweight object detection and segmentation algorithm. Key innovations include a multi-scale attention feature extraction backbone, a dual-stream fusion module incorporating the Mamba architecture, and adaptive context-aware detection/segmentation heads. This design ensures high computational efficiency and real-time performance. The system workflow is as follows: (1) the D435i captures real-time environmental data; (2) the processor analyzes this data, converting obstacle distances and path deviations into electrical signals; (3) servo motors deliver vibratory feedback for guidance and alerts. Preliminary tests confirm that the system can effectively detect obstacles and correct path deviations in real time, suggesting its potential to assist BVI users. However, as this is a work in progress, comprehensive field trials with BVI participants are required to fully validate its efficacy. Full article

Gait recognition is a reliable biometric approach that uniquely identifies individuals based on their natural walking patterns. It is widely used to recognize individuals who are challenging to camouflage and do not require a person’s cooperation. The general face-based person recognition system often fails to determine the offender’s identity when they conceal their face by wearing helmets and masks to evade identification. In such cases, gait-based recognition is ideal for identifying offenders, and most existing work leverages a deep learning (DL) model. However, a single model often fails to capture a comprehensive selection of refined patterns in input data when external factors are present, such as variation in viewing angle, clothing, and carrying conditions. In response to this, this paper introduces a fusion-based multi-model gait recognition framework that leverages the potential of convolutional neural networks (CNNs) and a vision transformer (ViT) in an ensemble manner to enhance gait recognition performance. Here, CNNs capture spatiotemporal features, and ViT features multiple attention layers that focus on a particular region of the gait image. The first step in this framework is to obtain the Gait Energy Image (GEI) by averaging a height-normalized gait silhouette sequence over a gait cycle, which can handle the left–right gait symmetry of the gait. After that, the GEI image is fed through multiple pre-trained models and fine-tuned precisely to extract the depth spatiotemporal feature. Later, three separate fusion strategies are conducted, and the first one is decision-level fusion (DLF), which takes each model’s decision and employs majority voting for the final decision. The second is feature-level fusion (FLF), which combines the features from individual models through pointwise addition before performing gait recognition. Finally, a hybrid fusion combines DLF and FLF for gait recognition. The performance of the multi-model fusion-based framework was evaluated on three publicly available gait databases: CASIA-B, OU-ISIR D, and the OU-ISIR Large Population dataset. The experimental results demonstrate that the fusion-enhanced framework achieves superior performance. Full article

The behavior of floor-raised chickens is closely linked to their health status and environmental comfort. As a type of broiler chicken with special behaviors, understanding the daily actions of yellow-feathered chickens is crucial for accurately checking their health and improving breeding practices. Addressing the challenges of high computational complexity and insufficient detection accuracy in existing floor-raised chicken behavior recognition models, a lightweight behavior recognition model was proposed for floor-raised yellow-feathered chickens, based on a Dual-Backbone Heterogeneous YOLO Network. Firstly, DualHet-YOLO enhances the feature extraction capability of floor-raised chicken images through a dual-path feature map extraction architecture and optimizes the localization and classification of multi-scale targets using a TriAxis Unified Detection Head. Secondly, a Proportional Scale IoU loss function is introduced that improves regression accuracy. Finally, a lightweight structure Eff-HetKConv was designed, significantly reducing model parameters and computational complexity. Experiments on a private floor-raised chicken behavior dataset show that, compared with the baseline YOLOv11 model, the DualHet-YOLO model increases the mAP for recognizing five behaviors—pecking, resting, walking, dead, and inactive—from 77.5% to 84.1%. Meanwhile, it reduces model parameters by 14.6% and computational complexity by 29.2%, achieving a synergistic optimization of accuracy and efficiency. This approach provides an effective solution for lightweight object detection in poultry behavior recognition. Full article

Pedestrian flow simulations play a pivotal role in urban planning, transportation engineering, and disaster response by enabling the detailed analysis of crowd dynamics and walking behavior. While physical models such as the Social Force model and Boids have been widely used, they often struggle to replicate complex inter-agent interactions. On the other hand, reinforcement learning (RL) methods, although adaptive, suffer from limited interpretability due to their opaque policy structures. To address these limitations, this study proposes a pedestrian simulation framework based on the Anticipatory Classifier System 2 (ACS2), a rule-based evolutionary learning model capable of extracting explicit behavior rules through trial-and-error learning. The proposed model captures the interactions between agents and environmental features while preserving the interpretability of the acquired strategies. Simulation experiments demonstrate that the ACS2-based agents reproduce realistic pedestrian dynamics and achieve comparable adaptability to conventional reinforcement learning approaches such as tabular Q-learning. Moreover, the extracted behavior rules enable systematic analysis of movement patterns, including the effects of obstacles and crowd composition on flow efficiency and group alignment. The results suggest that the ACS2 provides a promising approach to constructing interpretable multi-agent simulations for real-world pedestrian environments. Full article

Accurate wind-speed prediction plays an important role in improving the operation stability of wind-power generation systems. However, the inherent complexity of meteorological dynamics poses a major challenge to forecasting accuracy. In order to overcome these limitations, we propose a new hybrid framework, which combines variational mode decomposition (VMD) for signal processing, enhanced quantum particle swarm optimization (e-QPSO), an improved walking optimization algorithm (IHOA) for feature selection and the long short-term memory (LSTM) network, and which finally establishes a reliable prediction architecture. The purpose of this paper is to optimize VMD by using the e-QPSO algorithm to improve the problems of excessive filtering or error filtering caused by parameter problems in VMD, as the noise signal cannot be filtered completely, and the number of sources cannot be accurately estimated. The IHOA algorithm is used to find the optimal hyperparameters of LSTM to improve the learning efficiency of neurons and improve the fitting ability of the model. The proposed e-QPSO-VMD-IHOA-LSTM model is compared with six established benchmark models to verify its predictive ability. The effectiveness of the model is verified by experiments using the hourly wind-speed data measured in four seasons in Changchun in 2023. The MAPE values of the four datasets were 0.0460, 0.0212, 0.0263, and 0.0371, respectively. The results show that e-QPSO-VMD effectively processes the data and avoids the problem of error filtering, while IHOA effectively optimizes the LSTM parameters and improves prediction performance. Full article

The use of gait analysis to differentiate among paediatric populations with neurological and developmental conditions such as idiopathic toe walking (ITW), cerebral palsy (CP), and hereditary spastic paraplegia (HSP) remains challenging due to the insufficient precision of current diagnostic approaches, leading in some cases to misdiagnosis. Existing methods often isolate the analysis of gait variables, overlooking the whole complexity of biomechanical patterns and variations in motor control strategies. While previous studies have explored the use of statistical physics principles for the analysis of impaired gait patterns, gaps remain in integrating both kinematic and kinetic information or benchmarking these approaches against Deep Learning models. This study evaluates the robustness of statistical physics metrics in differentiating between normal and abnormal gait patterns and quantifies how the data source affects model performance. The analysis was conducted using gait data sets from two research institutions in Madrid and Dublin, with a total of 81 children with ITW, 300 with CP, 20 with HSP, and 127 typically developing children as controls. From each kinematic and kinetic time series, Shannon’s entropy, permutation entropy, weighted permutation entropy, and time irreversibility metrics were derived and used with Random Forest models. The classification accuracy of these features was compared to a ResNet Deep Learning model. Further analyses explored the effects of inter-laboratory comparisons and the spatiotemporal resolution of time series on classification performance and evaluated the impact of age and walking speed with linear mixed models. The results revealed that statistical physics metrics were able to differentiate among impaired gait patterns, achieving classification scores comparable to ResNet. The effects of walking speed and age on gait predictability and temporal organisation were observed as disease-specific patterns. However, performance differences across laboratories limit the generalisation of the trained models. These findings highlight the value of statistical physics metrics in the classification of children with different toe walking conditions and point towards the need of multimetric integration to improve diagnostic accuracy and gain a more comprehensive understanding of gait disorders. Full article

The electrocardiogram (ECG) signal plays a crucial role in medical diagnosis, home care, and exercise intensity assessment. However, traditional ECG monitoring devices are difficult to blend with users’ daily routines due to their lack of portability, poor wearability, and inconvenient electrode usage methods. Therefore, utilizing reusable and cost-effective flexible bioelectrodes (with a signal-to-noise ratio of 33 dB), a miniaturized wearable system (MWS) is proposed for unconstrained ECG monitoring, which holds a size of 65 × 52 × 12 mm³ and a weight of 69 g. Given these compelling features, this system enables reliable and high-quality ECG signal monitoring in individuals’ daily activities, including sitting, walking, and cycling, with the acquired signals exhibiting distinguishable QRS characteristics. Furthermore, an exercise intensity classification model was developed based on ECG characteristics and a fully connected neural network (FCNN) algorithm, with an evaluation accuracy of 98%. These results exhibit the promising potential of the MWS in tracking individuals’ physiological signals and assessing exercise intensity. Full article

As modern generative models advance rapidly, AI-generated images exhibit higher resolution and lifelike details. However, the generated images may not adhere to world knowledge and common sense, as there is no such awareness and supervision in the generative models. For instance, the generated images could feature a penguin walking in the desert or a man with three arms, scenarios that are highly unlikely to occur in real life. Current AI-generated image detection methods mainly focus on low-level features, such as detailed texture patterns and frequency domain inconsistency, which are specific to certain generative models, making it challenging to identify the above-mentioned general semantic fakes. In this work, (1) we propose a new task, reasoning AI-generated image detection, which focuses on identifying semantic fakes in generative images that violate world knowledge and common sense. (2) To benchmark the new task, we collect a new dataset Spot the Semantic Fake (STSF). STSF contains 358 images with clear semantic fakes generated by three different modern diffusion models and provides bounding boxes as well as text annotations to locate the fakes. (3) We propose RADAR, a reasoning AI-generated image detection assistor, to locate semantic fakes in the generative images and output corresponding text explanations. Specifically, RADAR contains a specialized multimodal LLM to process given images and detect semantic fakes. To improve the generalization ability, we further incorporate ChatGPT as an assistor to detect unrealistic components in grounded text descriptions. The experiments on the STSF dataset show that RADAR effectively detects semantic fakes in modern generative images. Full article