Search Results (1,195)

We present a (Light)weight (S)atellite–(A)erial feature (M)atching framework (LiteSAM) for robust UAV absolute visual localization (AVL) in GPS-denied environments. Existing satellite–aerial matching methods struggle with large appearance variations, texture-scarce regions, and limited efficiency for real-time UAV applications. LiteSAM integrates three key components to address these issues. First, efficient multi-scale feature extraction optimizes representation, reducing inference latency for edge devices. Second, a Token Aggregation–Interaction Transformer (TAIFormer) with a convolutional token mixer (CTM) models inter- and intra-image correlations, enabling robust global–local feature fusion. Third, a MinGRU-based dynamic subpixel refinement module adaptively learns spatial offsets, enhancing subpixel-level matching accuracy and cross-scenario generalization. The experiments show that LiteSAM achieves competitive performance across multiple datasets. On UAV-VisLoc, LiteSAM attains an RMSE@30 of 17.86 m, outperforming state-of-the-art semi-dense methods such as EfficientLoFTR. Its optimized variant, LiteSAM (opt., without dual softmax), delivers inference times of 61.98 ms on standard GPUs and 497.49 ms on NVIDIA Jetson AGX Orin, which are 22.9% and 19.8% faster than EfficientLoFTR (opt.), respectively. With 6.31M parameters, which is 2.4× fewer than EfficientLoFTR’s 15.05M, LiteSAM proves to be suitable for edge deployment. Extensive evaluations on natural image matching and downstream vision tasks confirm its superior accuracy and efficiency for general feature matching. Full article

The accurate segmentation of multiple sclerosis (MS) lesions in magnetic resonance imaging (MRI) is essential for diagnosis, disease monitoring, and therapeutic assessment. Despite the significant advances in deep learning-based segmentation, the current boundary-aware approaches are limited by their reliance on spatial distance transforms, which fail to fully exploit the rich texture and intensity information inherent in MRI data. This limitation is particularly problematic in regions where MS lesions and normal-appearing white matter exhibit overlapping intensity distributions, resulting in ambiguous boundaries and reduced segmentation accuracy. To address these challenges, we propose a novel Mahalanobis distance map (MDM) and a corresponding Mahalanobis distance loss, which generalize traditional distance transforms by incorporating spatial coordinates, the FLAIR intensity, and radiomic texture features into a unified feature space. Our method leverages the covariance structure of these features to better distinguish ambiguous regions near lesion boundaries, mimicking the texture-aware reasoning of expert radiologists. Experimental evaluation on the ISBI-MS and MSSEG datasets demonstrates that our approach achieves superior performance in both boundary quality metrics (HD95, ASSD) and overall segmentation accuracy (Dice score, precision) compared to state-of-the-art methods. These results highlight the potential of texture-integrated distance metrics to overcome MS lesion segmentation difficulties, providing more reliable and reproducible assessments for MS management and research. Full article

This paper applies a Convolutional Neural Network (CNN)-based vehicle security enhancement model, with a specific focus on the South African context. While conventional security systems, including immobilizers, alarms, steering locks, and GPS trackers, provide a baseline level of protection, they are increasingly being circumvented by technologically adept adversaries. These limitations have spurred the development of advanced security solutions leveraging artificial intelligence (AI), with a particular emphasis on computer vision and deep learning techniques. This paper presents a CNN-based Vehicle Security Enhancement Model (CNN-based VSEM) that integrates facial recognition with GSM and GPS technologies to provide a robust, real-time security solution in South Africa. This study contributes a novel integration of CNN-based authentication with GSM and GPS tracking in the South African context, validated on a functional prototype.The prototype, developed on a Raspberry Pi 4 platform, was validated through practical demonstrations and user evaluations. The system achieved an average recognition accuracy of 85.9%, with some identities reaching 100% classification accuracy. While misclassifications led to an estimated False Acceptance Rate (FAR) of ~5% and False Rejection Rate (FRR) of ~12%, the model consistently enabled secure authentication. Preliminary latency tests indicated a decision time of approximately 1.8 s from image capture to ignition authorization. These results, together with positive user feedback, confirm the model’s feasibility and reliability. This integrated approach presents a promising advancement in intelligent vehicle security for regions with high rates of vehicle theft. Future enhancements will explore the incorporation of 3D sensing, infrared imaging, and facial recognition capable of handling variations in facial appearance. Additionally, the model is designed to detect authorized users, identify suspicious behaviour in the vicinity of the vehicle, and provide an added layer of protection against unauthorized access. Full article

Autism diagnosis through magnetic resonance imaging (MRI) has advanced significantly with the application of artificial intelligence (AI). This systematic review examines three computational paradigms: radiomics-based machine learning (ML), deep learning (DL), and hybrid models combining both. Across 49 studies (2011–2025), radiomics methods relying on classical classifiers (i.e., SVM, Random Forest) achieved moderate accuracies (61–89%) and offered strong interpretability. DL models, particularly convolutional and recurrent neural networks applied to resting-state functional MRI, reached higher accuracies (up to 98.2%) but were hampered by limited transparency and generalizability. Hybrid models combining handcrafted radiomic features with learned DL representations via dual or fused architectures demonstrated promising balances of performance and interpretability but remain underexplored. A persistent limitation across all approaches is the lack of external validation and harmonization in multi-site studies, which affects robustness. Future pipelines should include standardized preprocessing, multimodal integration, and explainable AI frameworks to enhance clinical viability. This review underscores the complementary strengths of each methodological approach, with hybrid approaches appearing to be a promising middle ground of improved classification performance and enhanced interpretability. Full article

Conventional projection systems typically require a fixed spatial configuration relative to the projection surface, with strict control over distance and angle. In contrast, UAV-mounted projectors overcome these constraints, enabling dynamic, large-scale projections onto non-planar and complex environments. However, such flexible scenarios introduce a key challenge: severe geometric distortions caused by intricate surface geometry and continuous camera–projector motion. To address this, we propose a novel image registration method based on global dense matching, which estimates the real-time optical flow field between the input projection image and the target surface. The estimated flow is used to pre-warp the image, ensuring that the projected content appears geometrically consistent across arbitrary, deformable surfaces. The core idea of our method lies in reformulating the geometric distortion correction task as a global feature matching problem, effectively reducing 3D spatial deformation into a 2D dense correspondence learning process. To support learning and evaluation, we construct a hybrid dataset that covers a wide range of projection scenarios, including diverse lighting conditions, object geometries, and projection contents. Extensive simulation and real-world experiments show that our method achieves superior accuracy and robustness in correcting geometric distortions in dynamic UAV projection, significantly enhancing visual fidelity in complex environments. This approach provides a practical solution for real-time, high-quality projection in UAV-based augmented reality, outdoor display, and aerial information delivery systems. Full article

Sustainability is a foundational principle in Chilean education, reflected in curricular objectives related to environmental care, economic development, and social well-being. This study analyzes the integration of sustainability concepts and dimensions into the curricular bases of the third year (11th grade) and fourth year (12th grade) in Chilean secondary education. Using a sequential explanatory mixed-methods design and content analysis, the quantitative phase identified six key sustainability-related terms and their presence across curricular components and subject areas. The qualitative phase examined the inclusion of the environmental, social, and economic dimensions within those areas. The results show that sustainability concepts appear in seven subject areas, with greater emphasis on learning objectives and educational purposes. However, the environmental dimension dominates, while the social and economic aspects are underrepresented. These findings reveal conceptual ambiguities and uneven integration, highlighting challenges for implementing a multidimensional sustainability approach in Chilean classrooms. Full article

Identifying the material composition of objects is crucial for many recycling sector applications. Traditionally, object classification relies either on hyperspectral imaging (HSI), which analyses the chemometric properties of objects to infer material types, or on RGB imaging, which captures an object’s visual appearance and compares it to a reference sample. While both approaches have their strengths, each also suffers from limitations, particularly in challenging scenarios such as robotic municipal waste sorting, where objects are often heavily deformed or contaminated with various forms of dirt, complicating material recognition. This work presents a novel method for material-based object classification that jointly exploits HSI and RGB imaging. The proposed approach aims to mitigate the weaknesses of each technique while amplifying their respective advantages. It involves the real-time alignment of HSI and RGB data streams to ensure reliable result correlation, alongside a machine learning framework that learns to exploit the strengths and compensate for the weaknesses of each modality across different material types. Experimental validation on a municipal waste sorting facility demonstrates that the combined HSI–RGB approach significantly outperforms the individual methods, achieving robust and accurate classification even in highly challenging conditions. Full article

(1) Background: Soccer action recognition (SAR) is essential in modern sports analytics, supporting automated performance evaluation, tactical strategy analysis, and detailed player behavior modeling. Although recent advances in deep learning and computer vision have enhanced SAR capabilities, many existing methods remain limited to coarse-grained classifications, grouping actions into broad categories such as attacking, defending, or goalkeeping. These models often fall short in capturing fine-grained distinctions, contextual nuances, and long-range temporal dependencies. Transformer-based approaches offer potential improvements but are typically constrained by the need for large-scale datasets and high computational demands, limiting their practical applicability. Moreover, current SAR systems frequently encounter difficulties in handling occlusions, background clutter, and variable camera angles, which contribute to misclassifications and reduced accuracy. (2) Methods: To overcome these challenges, we propose TAT-SARNet, a structured framework designed for accurate and fine-grained SAR. The model begins by applying Sparse Dilated Attention (SDA) to emphasize relevant spatial dependencies while mitigating background noise. Refined spatial features are then processed through the Split-Stream Feature Processing Module (SSFPM), which separately extracts appearance-based (RGB) and motion-based (optical flow) features using ResNet and 3D CNNs. These features are temporally refined by the Multi-Granular Temporal Processing (MGTP) module, which integrates ResIncept Patch Consolidation (RIPC) and Progressive Scale Construction Module (PSCM) to capture both short- and long-range temporal patterns. The output is then fused via the Context-Guided Dual Transformer (CGDT), which models spatiotemporal interactions through a Bi-Transformer Connector (BTC) and Channel–Spatial Attention Block (CSAB); (3) Results: Finally, the Cascaded Temporal Classification (CTC) module maps these features to fine-grained action categories, enabling robust recognition even under challenging conditions such as occlusions and rapid movements. (4) Conclusions: This end-to-end architecture ensures high precision in complex real-world soccer scenarios. Full article

The Internet of Things allows us to implement concepts such as Education 4.0 by connecting sensors, actuators, and applications. In the case of direct and explicit connections, we refer to ensembles that can consist of devices and applications. When realizing spatially distributed applications, there are scenarios in which these ensembles must coordinate with each other. In software development, this process is referred to as orchestration or choreography. This paper describes a software framework that provides orchestration or choreography for self-explaining ensembles using predefined rules based on a self-description of all involved components. The framework is capable of generating user instructions or explanations for smart environments that cover interaction details. The approach also forms a basis to provide information about event-based coordination. In a case study, we investigated the technical perception of a coordinated spatial learning game application (an ambient serious game). Most participants perceived the application as cohesive and found it responsive. These results suggest that our framework provides a solid foundation for implementing coordinated applications within smart environments that appear as unified applications. Full article

Siamese network trackers are a prominent paradigm in visual object tracking due to efficient similarity learning. However, most Siamese trackers are restricted to the bounding box tracking format, which often fails to accurately describe the appearance of non-rigid targets with complex deformations. Additionally, since the bounding box frequently includes excessive background pixels, trackers are sensitive to similar distractors. To address these issues, we propose a novel segmentation-assisted model that learns binary mask representations of targets. This model is generic and can be seamlessly integrated into various Siamese frameworks, enabling pixel-wise segmentation tracking instead of the suboptimal bounding box tracking. Specifically, our model features two core components: (i) a multi-stage precise mask representation module composed of cascaded U-Net decoders, designed to predict segmentation masks of targets, and (ii) a saliency localization head based on the Euclidean model, which extracts spatial position constraints to boost the decoder’s discriminative capability. Extensive experiments on five tracking benchmarks demonstrate that our method effectively improves the performance of both anchor-based and anchor-free Siamese trackers. Notably, on GOT-10k, our method increases the AO scores of the baseline trackers SiamRPN++ (anchor-based) and SiamBAN (anchor-free) by 5.2% and 7.5%, respectively while maintaining speeds exceeding 60 FPS. Full article

Evapotranspiration (ET) estimation is crucial for sustainable water resource management in arid and semi-arid regions, particularly in the Arab world, where water scarcity remains a significant challenge. The objectives of this study were to map dominant ET estimation techniques and their geographic distribution, demonstrate fusion-based ET estimation under data-scarce conditions, and examine their alignment with climate change and food security priorities. The study reviewed 1279 ET-related articles indexed in the Web of Science, highlighting methodological trends, regional disparities, and the emergence of data-driven techniques. The results showed that traditional methods—primarily the Penman-Monteith model—dominate nearly 70% of the literature. In contrast, machine learning (ML), remote sensing (RS), and artificial intelligence (AI) collectively account for approximately 30%, with hybrid fusion frameworks appearing in only 2% of studies. ML applications are concentrated in Morocco, Egypt, and Iraq, while 50% of Arab countries lack any ML or AI-based research on energy transition (ET). Complementing the bibliometric analysis, this study demonstrates the practical potential of ML-based ET fusion using Landsat and the FAO Water Productivity (WaPOR) data within Saudi Arabia. A random forest model outperformed traditional averaging, reducing the mean absolute error (MAE) to 215.08 mm/year and the root mean square error (RMSE) to 531.34 mm/year, with a Pearson correlation coefficient of 0.86. The findings advocate for greater support and regional collaboration to advance ET monitoring and integrate ML-based modelling into climate resilience frameworks. Full article

Developmental dyscalculia is a neurobiologically based learning disorder that impairs numerical processing and calculation abilities. Numerous studies underscore the critical importance of early detection to enable effective intervention, highlighting the need for individualized, structured, and adaptive approaches. Digital tools, particularly those based on serious games, appear to offer a promising level of personalization. This systematic review aims to evaluate the relevance of serious game-based digital solutions as tools for the detection and remediation of developmental dyscalculia in children aged 5 to 12 years. To provide readers with a comprehensive understanding of this field, the selected solutions were analyzed and classified according to the technologies employed (including emerging ones), their thematic focus, the mathematical abilities targeted, the configuration of experimental trials, and the outcomes reported. A systematic search was conducted across Scopus, Web of Knowledge, PubMed, Eric, PsycInfo, and IEEEXplore for studies published between 2000 and March 2025, yielding 7799 records. Additional studies were identified through reference screening. A total of 21 studies met the eligibility criteria. All procedures were registered in PROSPERO and conducted in accordance with PRISMA guidelines for systematic reviews. The methodological analysis of the included studies emphasized the importance of employing both control and experimental groups with adequate sample sizes to ensure robust evaluation. In terms of remediation, the findings highlight the value of pre- and post-intervention assessments and the implementation of individualized training sessions, ideally not exceeding 20 min in duration. The review revealed a greater prevalence of remediation-focused serious games compared to screening tools, with a growing trend toward the use of mobile technologies. However, the substantial methodological limitations observed across studies must be addressed to enable the rigorous evaluation of the potential of SGs to detect and support the improvement of difficulties associated with developmental dyscalculia. Moreover, despite the recognized importance of personalization and adaptability in effective interventions, relatively few studies incorporated machine learning algorithms to enable the development of fully adaptive systems. Full article

Prototype-Based Networks (PBNs) are inherently interpretable architectures that facilitate understanding of model outputs by analyzing the activation of specific neurons—referred to as prototypes—during the forward pass. The learned prototypes serve as transformations of the input space into a latent representation that more effectively encapsulates the main characteristics shared across data samples, thereby enhancing classification performance. Crucially, these prototypes can be decoded and projected back into the original input space, providing direct interpretability of the features learned by the network. While this characteristic marks a meaningful advancement toward the realization of fully interpretable artificial intelligence systems, our findings reveal that prototype representations can be deliberately or inadvertently manipulated without compromising the superficial appearance of explainability. In this study, we conduct a series of empirical investigations that demonstrate this phenomenon, framing it as a structural paradox potentially intrinsic to the architecture or its design, which may represent a significant robustness challenge for explainable AI methodologies. Full article

This study investigated the professional attitudes of Croatian preservice primary school teachers towards science teaching and their epistemological views on science in the context of the ongoing educational reform. In a quantitative survey conducted at a Croatian university, teachers’ overall attitudes were assessed; it investigated whether participation in a science course influenced these attitudes, and the relationship between their attitudes towards teaching and their epistemological views on science was analyzed. The results showed predominantly positive but nuanced attitudes that combined both traditional and contemporary conceptions of science education. Furthermore, the results showed that participation in the science course had no significant influence on these attitudes, and that professional attitudes appeared to develop independently of epistemological views. The study emphasizes the need to effectively integrate theoretical knowledge and practical experience in teacher education. Furthermore, it emphasizes the importance of inquiry-based learning, reflective teaching practice, promoting gender equality, effective mentoring and maintaining professional networks. Future research should investigate specific curricular interventions aimed at improving trainee teachers’ coherence and confidence in science teaching. Full article

Introduction: Asthma is a chronic airway inflammatory disease characterized by variable airflow limitation and intermittent symptoms. In well-controlled asthma, auscultation and spirometry often appear normal, making diagnosis challenging. Moreover, bronchial provocation tests carry a risk of inducing acute bronchoconstriction. This study aimed to develop a non-invasive, objective, and reproducible diagnostic method using machine learning-based lung sound analysis for the early detection of asthma, even during stable periods. Methods: We designed a machine learning algorithm to classify controlled asthma patients and healthy individuals using respiratory sounds recorded with a digital stethoscope. We enrolled 120 participants (60 asthmatic, 60 healthy). Controlled asthma was defined according to Global Initiative for Asthma (GINA) criteria and was supported by normal spirometry, no pathological auscultation findings, and no exacerbations in the past three months. A total of 3600 respiratory sound segments (each 3 s long) were obtained by dividing 90 s recordings from 120 participants (60 asthmatic, 60 healthy) into non-overlapping clips. The samples were analyzed using Mel-Frequency Cepstral Coefficients (MFCCs) and Tunable Q-Factor Wavelet Transform (TQWT). Significant features selected with ReliefF were used to train Quadratic Support Vector Machine (SVM) and Narrow Neural Network (NNN) models. Results: In 120 participants, pulmonary function test (PFT) results in the asthma group showed lower FEV1 (86.9 ± 5.7%) and FEV1/FVC ratios (86.1 ± 8.8%) compared to controls, but remained within normal ranges. Quadratic SVM achieved 99.86% accuracy, correctly classifying 99.44% of controls and 99.89% of asthma cases. Narrow Neural Network achieved 99.63% accuracy. Sensitivity, specificity, and F1-scores exceeded 99%. Conclusion: This machine learning-based algorithm provides accurate asthma diagnosis, even in patients with normal spirometry and clinical findings, offering a non-invasive and efficient diagnostic tool. Full article