Search Results (5,837)

High-resolution remote sensing imagery (HRRSI) presents significant challenges for building extraction tasks due to its complex terrain structures, multi-scale features, and rich spectral and geometric information. Traditional methods often face limitations in effectively integrating multi-scale features while maintaining a balance between detailed and global semantic information. To address these challenges, this paper proposes an innovative deep learning network, Multi-Source Multi-Scale Residual Attention Network (MMRAD-Net). This model is built upon the classical encoder–decoder framework and introduces two key components: the GCN OA-SWinT Dense Module (GSTDM) and the Res DualAttention Dense Fusion Block (R-DDFB). Additionally, it incorporates Digital Surface Model (DSM) data, presenting a novel feature extraction and fusion strategy. Specifically, the model enhances building extraction accuracy and robustness through hierarchical feature modeling and a refined cross-scale fusion mechanism, while effectively preserving both detail information and global semantic relationships. Furthermore, we propose a Hybrid Loss, which combines Binary Cross-Entropy Loss (BCE Loss), Dice Loss, and an edge-sensitive term to further improve the precision of building edges and foreground reconstruction capabilities. Experiments conducted on the GF-7 and WHU datasets validate the performance of MMRAD-Net, demonstrating its superiority over traditional methods in boundary handling, detail recovery, and adaptability to complex scenes. On the GF-7 Dataset, MMRAD-Net achieved an F1-score of 91.12% and an IoU of 83.01%. On the WHU Building Dataset, the F1-score and IoU were 94.04% and 88.99%, respectively. Ablation studies and transfer learning experiments further confirm the rationality of the model design and its strong generalization ability. These results highlight that innovations in multi-source data fusion, multi-scale feature modeling, and detailed feature fusion mechanisms have enhanced the accuracy and robustness of building extraction. Full article

The Agricultural Guide application is a crucial component of the digital extension system in Saudi Arabia, providing modern and evidence-based information on sustainable agricultural practices to the farming community. The adoption of digital extension tools has been widely recognized as a key driver in enhancing crop productivity. This study aimed to assess the impact of the Agricultural Guide application on the adoption of sustainable olive farming practices in the Kingdom of Saudi Arabia. The impact was evaluated by analyzing the farming practices of the users and non-users of the application, identifying key determinants of application usage through machine learning techniques. The study also analyzed barriers to its adoption. A structured questionnaire was employed to collect data from 229 olive farmers in the Al-Jouf region. The findings reveal that the majority of respondents were non-users of the application. Significant differences were observed between users and non-users regarding the adoption of sustainable agricultural practices, including irrigation management, soil improvement, pest control, and harvesting techniques. Furthermore, farmers’ productivity, income levels, and digital information sources were significantly influenced by their usage of the application. A random forest analysis, with a predictive accuracy of 94.12%, identified key determinants of the application usage, including digital information sources, soil improvement practices, irrigation management, and education level. The study highlights the need for targeted educational programs under the supervision of the Agricultural Extension Department to enhance farmers’ awareness and knowledge of the Agricultural Guide application. Expanding its adoption within the farming community has the potential to significantly promote sustainable agricultural practices and improve overall agricultural productivity in Saudi Arabia. Full article

As generative AI (GenAI) technologies proliferate, ensuring trust and transparency in digital ecosystems becomes increasingly critical, particularly within democratic frameworks. This article examines decentralized Web3 mechanisms—blockchain, decentralized autonomous organizations (DAOs), and data cooperatives—as foundational tools for enhancing trust in GenAI. These mechanisms are analyzed within the framework of the EU’s AI Act and the Draghi Report, focusing on their potential to support content authenticity, community-driven verification, and data sovereignty. Based on a systematic policy analysis, this article proposes a multi-layered framework to mitigate the risks of AI-generated misinformation. Specifically, as a result of this analysis, it identifies and evaluates seven detection techniques of trust stemming from the action research conducted in the Horizon Europe Lighthouse project called ENFIELD: (i) federated learning for decentralized AI detection, (ii) blockchain-based provenance tracking, (iii) zero-knowledge proofs for content authentication, (iv) DAOs for crowdsourced verification, (v) AI-powered digital watermarking, (vi) explainable AI (XAI) for content detection, and (vii) privacy-preserving machine learning (PPML). By leveraging these approaches, the framework strengthens AI governance through peer-to-peer (P2P) structures while addressing the socio-political challenges of AI-driven misinformation. Ultimately, this research contributes to the development of resilient democratic systems in an era of increasing technopolitical polarization. Full article

In order to avoid the dependence of traditional sub-pixel displacement methods on interpolation method calculation, image gradient calculation, initial value estimation and iterative calculation, a Swin Transformer-based sub-pixel displacement measurement method (ST-SDM) is proposed, and a square dataset expansion method is also proposed to rapidly expand the training dataset. The ST-SDM computes sub-pixel displacement values of different scales through three-level classification tasks, and solves the problem of positive and negative displacement with the rotation relative tag value method. The accuracy of the ST-SDM is verified by simulation experiments, and its robustness is verified by real rigid body experiments. The experimental results show that the ST-SDM model has higher accuracy and higher efficiency than the comparison algorithm. Full article

This study proposes an object detector for apple trees as a first step in developing agricultural digital twins. An original dataset of orchard images was created and used to train Single Shot MultiBox Detector (SSD) and You Only Look Once (YOLO) models. Performance was evaluated using mean Average Precision (mAP). YOLO significantly outperformed SSD, achieving 91.3% mAP compared to the SSD’s 46.7%. Results indicate YOLO’s Darknet-53 backbone extracts more complex features suited to tree detection. This work demonstrates the potential of deep learning for automated data collection in smart farming applications. Full article

In the wave of digital transformation and Industry 4.0, accurate time series forecasting has become critical across industries such as manufacturing, energy, and finance. However, while deep learning models offer high predictive accuracy, their lack of interpretability often undermines decision-makers’ trust. This study proposes a linear time series model architecture based on seasonal decomposition. The model effectively captures trends and seasonality using an additive decomposition, chosen based on initial data visualization, indicating stable seasonal variations. An augmented feature generator is introduced to enhance predictive performance by generating features such as differences, rolling statistics, and moving averages. Furthermore, we propose a gradient-based feature importance method to improve interpretability and implement a gradient feature elimination algorithm to reduce noise and enhance model accuracy. The approach is validated on multiple datasets, including order demand, energy load, and solar radiation, demonstrating its applicability to diverse time series forecasting tasks. Full article

Remote sensing is essential in precision agriculture as this approach provides high-resolution information on the soil’s physical and chemical parameters for detailed decision making. Globally, technologies such as remote sensing and machine learning are increasingly being used to infer these parameters. This study evaluates soil fertility changes and compares them with previous fertilization inputs using high-resolution multispectral imagery and in situ measurements. A UAV-captured image was used to predict the spatial distribution of soil parameters, generating fourteen spectral indices and a digital surface model (DSM) from 103 soil plots across 49.83 hectares. Machine learning algorithms, including classification and regression trees (CART) and random forest (RF), modeled the soil parameters (N-ppm, P-ppm, K-ppm, OM%, and EC-mS/m). The RF model outperformed others, with R² values of 72% for N, 83% for P, 87% for K, 85% for OM, and 70% for EC in 2023. Significant spatiotemporal variations were observed between 2022 and 2023, including an increase in P (14.87 ppm) and a reduction in EC (−0.954 mS/m). High-resolution UAV imagery combined with machine learning proved highly effective for monitoring soil fertility. This approach, tailored to the Peruvian Andes, integrates spectral indices and field-collected data, offering innovative tools to optimize fertilization practices, address soil management challenges, and merge modern technology with traditional methods for sustainable agricultural practices. Full article

The study examines the impact of the COVID-19 pandemic on the digital competencies of teachers and the educational achievements of students, focusing on Serbia and comparisons with other countries. For this study, a survey was conducted in three phases, completed by teachers. The time periods during which the surveys were filled out are characteristic because they correspond to specific points in time (June 2019, June 2022, and May 2023). The aim of the first study, conducted in June 2019, was for every school in the Republic of Serbia to explore teachers’ digital competencies as a recommendation of the Ministry of Education. Later, this survey took on a different purpose with the onset of the pandemic. The pandemic exposed challenges such as insufficient teacher preparation for online teaching, educational inequalities affecting students from lower socio-economic backgrounds, and varying levels of adaptability among students. The hypothesis of this research is as follows: Teachers demonstrate a significantly higher level of digital literacy after the crisis caused by the COVID-19 virus than before the crisis. The findings reveal improvements in teachers’ digital skills after the crisis situation, particularly in hardware, software, and internet use, alongside a shift in the primary purpose of digital tools from entertainment to education. The study emphasizes the importance of continuous professional development, standardized e-learning devices, and improved digital infrastructure to enhance the quality of education. The research found that teachers in Serbia showed a significantly higher level of digital competencies after the crisis situation. Key recommendations include integrating digital skills into teacher training, fostering innovative pedagogical practices, and addressing the digital divide to ensure equitable access to education in the future. Full article

The global energy sector has been profoundly reshaped by the COVID-19 pandemic, triggering diverse reactions in energy demand patterns, accelerating the transition toward renewable energy sources, and amplifying concerns over global energy security and the digital safety of energy infrastructure. Five years after the pandemic’s onset, this study provides a taxonomy-based lesson-learned analysis, offering a comprehensive examination of the pandemic’s enduring effects on energy systems. It employs a detailed analytical framework to map short-, medium-, and long-term transformations across various energy-related sectors. Specifically, the study investigates significant shifts in the global energy landscape, including the electric and conventional vehicle markets, the upstream energy industry (oil, coal, and natural gas), conventional and renewable energy generation, aerial transportation, and the broader implications for global and continental energy security. Additionally, it highlights the growing importance of cybersecurity in the context of digital evolution and remote operations, which became critical during the pandemic. The study is structured to dissect the initial shock to energy supply and demand, the environmental consequences of reduced fossil fuel consumption, and the subsequent pivot toward sustainable recovery pathways. It also evaluates the strategic actions and policy measures implemented globally, providing a comparative analysis of recovery efforts and the evolving patterns of energy consumption. In the face of a global reduction in energy demand, the analysis reveals both spatial and temporal disparities, underscoring the complexity of the pandemic’s impact on the energy sector. Drawing on the lessons of COVID-19, this work emphasizes the need for flexible, forward-thinking strategies and deeper international collaboration to build energy systems that are both resilient and sustainable in the face of uncertainties. Full article

Background: Although digital cognitive behavioral therapy (dCBT) is considered effective for anxiety disorders, there is considerable heterogeneity in its efficacy across studies, and its varied treatment content and clinical components may explain such heterogeneity. Objective: This review aimed to identify the efficacy of digital cognitive behavioral therapy for panic disorder and agoraphobia, and examine whether applying relevant clinical components of interoceptive exposure, inhibitory-learning-based exposure, and personalization of treatment enhances its efficacy. Methods: Randomized controlled trials of dCBT for panic disorder and agoraphobia with passive or active controls were identified from OVID Medline, Embase, Cochrane Library, and PsycINFO. The overall effect sizes for dCBT groups (interventions through digital platforms based on the internet, mobile, computers, VR, etc.) were aggregated against passive control (placebo/sham) and active control (traditional CBT) groups. For subgroup analysis, key intervention components such as interoceptive exposure, inhibitory learning, and personalization were assessed dichotomously (0 or 1) along with other study characteristics. The stepwise meta-regression models were applied with traditional and Bayesian statistical testing. The risk of bias and publication bias of included studies were assessed. Results: Among the 31 selected studies, dCBT had an overall effect size of g = 0.70 against passive control and g = −0.05 against active control. In subgroup analysis, interoceptive exposure improved the clinical effects for both controls, and inhibitory learning and personalization increased the clinical effects for passive control along with therapist guide/support and the length of sessions. Many studies were vulnerable to therapist bias and attrition bias. No publication bias was detected. Conclusions: The heterogeneity in clinical effects of dCBT for panic and agoraphobia can be explained by the different intervention factors they include. For effective dCBT, therapists should consider the clinical components relevant to the treatment. Full article

Technological advancement and growing interest in digitalizing education increased Augmented Reality (AR) use in education. However, previous research findings on AR’s potential for knowledge acquisition are inconclusive. Furthermore, computer self-efficacy has seldom been evaluated. AR is frequently combined with game-based approaches (GAME), yet the specific impact of each feature, “AR” and “GAME”, is often not differentiated in the research design. This work analyzed an AR game-based learning environment for science teaching. It was conducted with German pre-service teachers, assessing “Knowledge” and “Computer Self-Efficacy”. These measures were used to analyze the effect of AR and GAME in four intervention groups. The results showed a significant time effect for all groups in both variables, indicating all intervention designs led to knowledge and self-efficacy gains. However, no interaction effect was found, indicating the groups did not significantly differ in their knowledge and self-efficacy gains over time. The results further indicate no clear advantage of either AR or GAME for the design of science teaching. However, AR and GAME also did not hinder learning and both led to successful knowledge and self-efficacy gains. This indicates that AR and game-based learning support the learning process and strengthen learners’ computer self-efficacy. Combining both features aids in easing the transition toward technology-enhanced learning by providing a playful learning experience, using digital as well as analog components. Full article

Geological hazards in densely vegetated mountainous regions are challenging to detect due to terrain concealment and the limitations of traditional visualization methods. This study introduces the LiDAR image highlighting algorithm (LIHA), a novel approach for enhancing micro-topographical features in digital elevation models (DEMs) derived from airborne LiDAR data. By analogizing terrain profiles to non-stationary spectral signals, LIHA applies locally estimated scatterplot smoothing (Loess smoothing), wavelet decomposition, and high-frequency component amplification to emphasize subtle features such as landslide boundaries, cracks, and gullies. The algorithm was validated using the Mengu landslide case study, where edge detection analysis revealed a 20-fold increase in identified micro-topographical features (from 1907 to 37,452) after enhancement. Quantitative evaluation demonstrated LIHA’s effectiveness in improving both human interpretation and automated detection accuracy. The results highlight LIHA’s potential to advance early geological hazard identification and mitigation, particularly when integrated with machine learning for future applications. This work bridges signal processing and geospatial analysis, offering a reproducible framework for high-precision terrain feature extraction in complex environments. Full article

The rapid advancement of digital technologies in education is revolutionizing learning environments and influencing the future of educational methodologies. This study seeks to determine the parameters affecting students’ satisfaction with e-learning platforms utilized during the COVID-19 pandemic, within a multimodal educational framework. A Structural Equation Modeling (SEM) approach was used to examine the contributions of different components to students’ views of e-learning tools and the inter-relationships between them. Data were gathered from 314 students via a questionnaire, with the dependent variable being student satisfaction with e-learning platforms and the independent variables comprising the perceived benefits and disadvantages, ease of use, prior experience, perceptions of the platforms, perceived risks, and communication efficiency between students and professors. The results indicated that 78% of the variance in student satisfaction was explained by these parameters (R-squared = 0.78), underscoring the substantial impact of these features on the digital learning experience. This study enhances the comprehension of the influence of e-learning platforms within a multimodal educational framework on students’ learning experiences, especially with the challenges presented by the pandemic. The collected insights can guide the development of more effective, accessible, and user-focused educational tools. Full article

The transition from conventional soil mapping (CSM) to digital soil mapping (DSM) not only affects the final map products, but it also affects the concepts of scale, resolution, and sampling intensity. This is critical because in the CSM approach, sampling intensity is intricately linked to the desired scale of soil map publication, which provided standardization of sampling. This is not the case for DSM where sample size varies widely by project, and sampling design studies have largely focused on where to sample without due consideration for sample size. Using a regional soil survey dataset with 1791 sampled and described soil profiles, we first extracted an external validation dataset using the conditioned Latin hypercube sampling (cLHS) algorithm and then created repeated (n = 10) sample plans of increasing size from the remaining calibration sites using the cLHS, feature space coverage sampling (FSCS), and simple random sampling (SRS). We then trained random forest (RF) models for four soil properties: pH, CEC, clay content, and SOC at five different depths. We identified the effective sample size based on the model learning curves and compared it to the optimal sample size determined from the Jensen–Shannon divergence (D_JS) applied to the environmental covariates. Maps were then generated from models that used all the calibration points (reference maps) and from models that used the optimal sample size (optimal maps) for comparison. Our findings revealed that the optimal sample sizes based on the D_JS analysis were closely aligned with the effective sample sizes from the model learning curves (815 for cLHS, 832 for FSCS, and 847 for SRS). Furthermore, the comparison of the optimal maps to the reference maps showed little difference in the global statistics (concordance correlation coefficient and root mean square error) and spatial trends of the data, confirming that the optimal sample size was sufficient for creating predictions of similar accuracy to the full calibration dataset. Finally, we conclude that the Ottawa soil survey project could have saved between CAD 330,500 and CAD 374,000 (CAD = Canadian dollars) if the determination of optimal sample size tools presented herein existed during the project planning phase. This clearly illustrates the need for additional research in determining an optimal sample size for DSM and demonstrates that operationalization of DSM in public institutions requires a sound scientific basis for determining sample size. Full article

Background: People with multiple sclerosis (MS) often demonstrate both cognitive and physical dysfunctions, particularly with greater age and lower physical activity levels, and there is evidence of a relationship between these outcomes (i.e., cognitive–motor coupling) in MS. To date, little is known about cognitive–motor coupling when controlling for chronological age and levels of physical activity. Objectives: We examined cognitive–motor coupling in people with MS while accounting for chronological age and physical activity. Methods: The sample included 290 people with MS between the ages of 22 and 77 years. Participants underwent the Symbol Digit Modalities Test (SDMT) for cognitive processing speed and the California Verbal Learning and Memory Test–Second Edition (CVLT-II) for verbal learning and memory. Participants completed the 6-Minute Walk and the Timed 25-Foot Walk tests for walking endurance and speed, respectively. Participants wore an accelerometer for a 7-day period to measure moderate-to-vigorous physical activity (MVPA). Results: The bivariate correlation analyses indicated that cognitive function had moderate-to-strong associations with motor function (range of r_s between 0.433 and 0.459). The linear regression analyses indicated cognitive–motor coupling between SDMT and motor function (with a range of β between 0.139 and 0.145) when controlling for demographic and clinical characteristics. The regression analyses further indicated that the CVLT-II was associated with motor function (with a range of β between 0.125 and 0.135) when controlling for demographic and clinical characteristics. When age and MVPA were entered into the regression analyses, SDMT was still associated with the motor function of individuals (β = 0.119), and CVLT-II was still associated with the motor function of individuals (with a range of β between 0.115 and 0.124). Conclusions: Cognitive–motor coupling is present in people with MS independent of chronological age and levels of physical activity. This warrants further investigation of the underlying mechanism and potential approaches for the management of co-occurring MS-related dysfunction. Full article