Search Results (286)

This study investigates the encroachment risk in the Makause informal settlement by analysing resident survey data to identify key contributing factors and build predictive models. Encroachment threatens the water infrastructure through damage, contamination, and service disruptions, highlighting the need for informed, community-based planning. The data was collected from 105 residents, with responses (“Yes,” “No,” “Unsure”) analysed using descriptive statistics and a one-way ANOVA to identify significant differences across categories. The ReliefF algorithm was used to rank the importance of features predicting the encroachment risk. These inputs were then used to train, validate, and test an Artificial Neural Network (ANN) model. The Artificial Neural Network demonstrated a high predictive accuracy, achieving correlation coefficients above 95% and low mean squared errors. The ANOVA identified statistically significant mean differences for selected variables, while ReliefF helped determine the most influential predictors. A high agreement level (p > 0.900) between predicted and actual responses confirmed the model’s validity. This research introduces an innovative, data-driven framework that integrates machine learning and a statistical analysis to support municipalities and utility providers in engaging informal communities to protect infrastructure. While this study is limited to Makause and may be affected by a self-reported bias, it demonstrates the potential of Artificial Neural Networks and ReliefF in enhancing the risk analysis and infrastructure management in informal settlements. Full article

Groundwater level monitoring is crucial for assessing hydrological responses to climate change and human activities, which pose significant threats to the sustainability of semi-arid aquifers and the cultural heritage they sustain. This study presents an integrated remote sensing and transformer-based deep learning framework that combines diverse geospatial datasets to predict spatiotemporal variations across the plain near the Persepolis and Naqsh-e Rustam archaeological complexes—UNESCO World Heritage Sites situated at the plain’s edge. We assemble 432 synthetic aperture radar (SAR) scenes (2015–2022) and derive vertical ground motion rates greater than −180 mm yr⁻¹, which are co-localized with multisource geoinformation, including hydrometeorological indices, biophysical parameters, and terrain attributes, to train transformer models with traditional deep learning methods. A sparse probabilistic transformer (ConvTransformer) trained on 95 gridded variables achieves an out-of-sample R² = 0.83 and RMSE = 6.15 m, outperforming bidirectional deep learning models by >40%. Scenario analysis indicates that, in the absence of intervention, subsidence may exceed 200 mm per year within a decade, threatening irreplaceable Achaemenid stone reliefs. Our results indicate that attention-based networks, when coupled to synergistic geodetic constraints, enable early-warning quantification of groundwater stress over heritage sites and provide a scalable template for sustainable aquifer governance worldwide. Full article

Background: More than merely determining our sleep pattern, our body’s internal clock also improves the quality of our sleep, alleviates the symptoms of depression, and maintains the balance of our gut flora. Methods: We carried out a 12-week randomized controlled trial with 99 adults from Kolkata, New Delhi, and Pune who reported sleep problems and symptoms of depression or anxiety. Participants received either a probiotic formulated to improve sleep quality and reduce depressive symptoms or a placebo. We tracked sleep using overnight studies and wearable devices, assessed depressive symptoms with standardized questionnaires, and analyzed stool samples to profile gut bacteria and their metabolites using gene sequencing and metabolomics. Advanced statistics and machine learning helped us pinpoint the key microbial and metabolic factors tied to sleep and mental health. Results: At the start, participants with disrupted sleep and depressive symptoms had fewer beneficial gut bacteria like Bifidobacterium and Lactobacillus, more inflammation-related microbes, and lower levels of helpful short-chain fatty acids. These imbalances were linked to poorer sleep efficiency, less REM sleep, and higher depression and anxiety scores. After 12 weeks, those taking the circadian-supporting probiotic saw a statistically significant increase in beneficial gut bacteria, improved sleep efficiency (+7.4%, p = 0.02), and greater reductions in depression and anxiety compared to the placebo. Increases in SCFA-producing bacteria most strongly predicted improvements. Conclusions: Our results show that taking a probiotic supplement can help bring your gut back into balance, support better sleep, and lift symptoms of depression and anxiety. This offers a hopeful and practical option for people looking for real relief from these deeply connected challenges. Full article

Emergency communication networks play a crucial role in disaster relief operations. Current automated deployment strategies based on rule-driven or heuristic algorithms struggle to adapt to the dynamic and heterogeneous network environments in disaster scenarios, while manual command deployment is constrained by personnel expertise and response time requirements, leading to suboptimal trade-offs between deployment efficiency and reliability. To address these challenges, this study proposes a novel deep reinforcement learning framework with a fully convolutional value network architecture, which achieves breakthroughs in multi-dimensional spatial decision-making through end-to-end feature extraction. This design effectively mitigates the “curse of dimensionality” inherent in traditional reinforcement learning methods for topology planning. Experimental results demonstrate that the proposed method effectively accomplishes the planning tasks of emergency communication hub elements, significantly improving deployment efficiency while maintaining robustness in complex environments. Full article

The integration of traditional geomorphological approaches with advanced artificial intelligence techniques represents a promising frontier in flood risk assessment for arid regions. This study presents a comprehensive analysis of the Wadi Ranuna basin in Medina, Saudi Arabia, combining detailed morphometric parameters with advanced Geospatial Artificial Intelligence (GeoAI) algorithms to enhance flood susceptibility modeling. Using digital elevation models (DEMs) and geographic information systems (GISs), we extracted 23 morphometric parameters across 67 sub-basins and applied XGBoost, Random Forest, and Gradient Boosting (GB) models to predict both continuous flood susceptibility indices and binary flood occurrences. The machine learning models utilize morphometric parameters as input features to capture complex non-linear interactions, including threshold-dependent relationships where the stream frequency impact intensifies above 3.0 streams/km², and the compound effects between the drainage density and relief ratio. The analysis revealed that the basin covers an area of 188.18 km² with a perimeter of 101.71 km and contains 610 streams across six orders. The basin exhibits an elongated shape with a form factor of 0.17 and circularity ratio of 0.23, indicating natural flood-moderating characteristics. GB emerged as the best-performing model, achieving an RMSE of 6.50 and an R² value of 0.9212. Model validation through multi-source approaches, including field verification at 35 locations, achieved 78% spatial correspondence with documented flood events and 94% accuracy for very high susceptibility areas. SHAP analysis identified the stream frequency, overland flow length, and drainage texture as the most influential predictors of flood susceptibility. K-Means clustering uncovered three morphometrically distinct zones, with Cluster 1 exhibiting the highest flood risk potential. Spatial analysis revealed 67% of existing infrastructure was located within high-risk zones, with 23 km of major roads and eight critical facilities positioned in flood-prone areas. The spatial distribution of GBM-predicted flood susceptibility identified high-risk zones predominantly in the central and southern parts of the basin, covering 12.3% (23.1 km²) of the total area. This integrated approach provides quantitative evidence for informed watershed management decisions and demonstrates the effectiveness of combining traditional morphometric analysis with advanced machine learning techniques for enhanced flood risk assessment in arid regions. Full article

The present research is related to the application of artificial intelligence (AI) approaches for classifying surface textures, specifically regular reliefs patterns formed by ball burnishing operations. A two-stage methodology is employed, starting with the creation of regular reliefs (RRs) on test parts by ball burnishing, followed by 3D topography scanning with Alicona device and data preprocessing with Gwyddion, and Blender software, where the acquired 3D topographies are converted into a set of 2D images, using various virtual camera movements and lighting to simulate the symmetrical fluctuations around the tool-path of the real camera. Four pre-trained convolutional neural networks (DenseNet121, EfficientNetB0, MobileNetV2, and VGG16) are used as a base for transfer learning and tested for their generalization performance on different combinations of synthetic and real image datasets. The models were evaluated by using confusion matrices and four additional metrics. The results show that the pretrained VGG16 model generalizes the best regular reliefs textures (96%), in comparison with the other models, if it is subjected to transfer learning via feature extraction, using mixed dataset, which consist of 34,037 images in following proportions: non-textured synthetic (87%), textured synthetic (8%), and real captured (5%) images of such a regular relief. Full article

Music learning can provide students with significant emotional and educational benefits, including stress relief, increased confidence, self-expression, brain development, enhanced attention, and perseverance. Despite these advantages, many students perceive music lessons as less important and tend to pay less attention in music classrooms. Consequently, motivation plays a crucial role for both teachers and students in facilitating an effective teaching and learning process in music education. Although motivation is generally understood as a student’s desire to engage in the learning process, it remains a complex concept that researchers and educators continue to explore across various educational contexts. This study aimed to review students’ motivation for classroom music by analyzing research from different studies in music education. Following the PRISMA (Preferred Reporting Items for Systematic Reviews and Meta-Analyses) guidelines, 27 studies were reviewed and included. The findings identified four theoretical constructs related to motivation in classroom music: expectancy–value theory, self-determination theory, mastery motivation, and achievement goal theory. Among these, the first two were most commonly discussed across the reviewed studies. All the reviewed studies employed self-reported questionnaires as their primary assessment tools. Most studies indicated that girls demonstrated higher motivation levels than boys in music classrooms. Additionally, the findings emphasized that teachers’ instructional strategies are critical for enhancing students’ motivation. This study contributes to the field of music education by highlighting the pivotal role of teacher strategies in fostering motivation and by providing a comprehensive review of motivational theories, assessment tools, and gender-related motivational differences in music education. Full article

Quadruped robots have shown significant potential in disaster relief applications, where they have to navigate complex terrains for search and rescue or reconnaissance operations. However, their deployment is hindered by limited adaptability in highly uncertain environments, especially when relying solely on vision-based sensors like cameras or LiDAR, which are susceptible to occlusions, poor lighting, and environmental interference. To address these limitations, this paper proposes a novel sensor-enhanced hierarchical switching model predictive control (MPC) framework that integrates proprioceptive sensing with a bi-level hybrid dynamic model. Unlike existing methods that either rely on handcrafted controllers or deep learning-based control pipelines, our approach introduces three core innovations: (1) a situation-aware, bi-level hybrid dynamic modeling strategy that hierarchically combines single-body rigid dynamics with distributed multi-body dynamics for modeling agility and scalability; (2) a three-layer hybrid control framework, including a terrain-aware switching MPC layer, a distributed torque controller, and a fast PD control loop for enhanced robustness during contact transitions; and (3) a multi-IMU-based proprioceptive feedback mechanism for terrain classification and adaptive gait control under sensor-occluded or GPS-denied environments. Together, these components form a unified and computationally efficient control scheme that addresses practical challenges such as limited onboard processing, unstructured terrain, and environmental uncertainty. A series of experimental results demonstrate that the proposed method outperforms existing vision- and learning-based controllers in terms of stability, adaptability, and control efficiency during high-speed locomotion over irregular terrain. Full article

This study reframes closure intention in small- and medium-sized enterprises (SMEs) as an ex ante diagnostic signal rather than a post-mortem symptom of failure. The survey evidence from 385 Ecuadorian SMEs was analyzed in two stages; confirmatory factor analysis validated the scales capturing environmental pessimism and personal pressures, and a structural equation model confirmed that both latent constructs directly heighten exit propensity. A binomial logistic regression model correctly classified 71% of the cases and explained 30% of variance. Five variables proved decisive: low-level liquidity (OR = 0.84), a high debt-to-equity ratio (1.41), weak profitability (0.14), negative environmental perceptions (1.72), and a shorter operating tenure (0.91); the sector and the firm size were non-significant. The combined CFA-SEM-logit sequence yields practical early warning thresholds—debt-to-equity ratio > 1.4, current ratio < 1.0, and ROA < 0.15—that lenders, advisers, and entrepreneurs can embed in dashboards or credit screens. Recognizing closure intention as a rational, strategic step challenges the stigma surrounding exit and links financial distress and the strategic exit theory. Policymakers can use the findings to pair debt relief and liquidity programs with cognitive bias training that helps owners interpret risk signals realistically. For scholars, the results highlight closure intention as a dynamic learning process, especially pertinent in emerging economies characterized by informality and institutional fragility. Full article

In recent years, significant advancements in artificial intelligence, particularly in the field of deep learning, have increasingly been integrated into agricultural applications, including critical processes such as disease detection. Tomato, being one of the most widely consumed agricultural products globally and highly susceptible to a variety of fungal, bacterial, and viral pathogens, remains a prominent focus in disease detection research. In this study, we propose a deep learning-based approach for the detection of tomato diseases, a critical challenge in agriculture due to the crop’s vulnerability to fungal, bacterial, and viral pathogens. We constructed an original dataset comprising 6414 images captured under real production conditions, categorized into three image types: leaves, green tomatoes, and red tomatoes. The dataset includes five classes: healthy samples, late blight, early blight, gray mold, and bacterial cancer. Twenty-one deep learning models were evaluated, and the top five performers (EfficientNet-b0, NasNet-Large, ResNet-50, DenseNet-201, and Places365-GoogLeNet) were selected for feature extraction. From each model, 1000 deep features were extracted, and feature selection was conducted using MRMR, Chi-Square (Chi²), and ReliefF methods. The top 100 features from each selection technique were then used for reclassification with traditional machine learning classifiers under five-fold cross-validation. The highest test accuracy of 92.0% was achieved with EfficientNet-b0 features, Chi² selection, and the Fine KNN classifier. EfficientNet-b0 consistently outperformed other models, while the combination of NasNet-Large and Wide Neural Network yielded the lowest performance. These results demonstrate the effectiveness of combining deep learning-based feature extraction with traditional classifiers and feature selection techniques for robust detection of tomato diseases in real-world agricultural environments. Full article

The increasingly observable financial vulnerability of households in emerging market countries makes it imperative to investigate the factors influencing it. Considering that China stands as a representative of emerging market economies, analyzing the factors influencing household financial vulnerability in China presents great reference significance for the sustainable development of households in emerging market countries. Using data from the China Household Finance Survey (CHFS) household samples, this paper presents the regional distribution of households with financial vulnerability in China. Utilizing machine learning (ML), this research examines the factors that influence household financial vulnerability in China and determines the most significant ones. The results reveal that households with financial vulnerability in China takes up a proportion of more than 63%, and household financial vulnerability is lower in economically developed coastal regions than in medium and small-sized cities in the central and western parts of China. The analysis results of the SHAP method show that the debt leverage ratio of a household is the most significant feature variable in predicting financial vulnerability. The ALE plots demonstrate that, in a household, the debt leverage ratio, the age of household head, health condition, economic development and literacy level are significantly nonlinearly related to financial vulnerability. Heterogeneity analysis reveals that, except for household debt leverage and insurance participation, the key characteristic variables exerting the most pronounced effect on financial fragility differ between urban and rural households: household head age for urban families and physical health status for rural families. Furthermore, digital financial inclusion and social security exert distinct impacts on financial vulnerability, showing significantly stronger effects in high per capita GDP regions and low per capita GDP regions, respectively. These findings offer valuable insights for policymakers in emerging economies to formulate targeted financial risk mitigation strategies—such as developing household debt relief and prevention mechanisms and strengthening rural health security systems—and optimize policies for household financial health. Full article

The rapid advancement of unmanned aerial vehicle (UAV) technology has enabled the coordinated operation of multi-UAV systems, offering significant applications in agriculture, logistics, environmental monitoring, and disaster relief. In agriculture, UAVs are widely utilized for tasks such as ecological restoration, crop monitoring, and fertilization, providing efficient and cost-effective solutions for improved productivity and sustainability. This study addresses the collaborative task allocation problem for multi-UAV systems, using ecological grassland restoration as a case study. A multi-objective, multi-constraint collaborative task allocation problem (MOMCCTAP) model was developed, incorporating constraints such as UAV collaboration, task completion priorities, and maximum range restrictions. The optimization objectives include minimizing the maximum task completion time for any UAV and minimizing the total time for all UAVs. To solve this model, a deep reinforcement learning-based seagull optimization algorithm (DRL-SOA) is proposed, which integrates deep reinforcement learning with the seagull optimization algorithm (SOA) for adaptive optimization. The algorithm improves both global and local search capabilities by optimizing key phases of seagull migration, attack, and post-attack refinement. Evaluation against five advanced swarm intelligence algorithms demonstrates that the DRL-SOA outperforms the alternatives in convergence speed and solution diversity, validating its efficacy for solving the MOMCCTAP. Full article

Background/Objectives: Alzheimer’s disease (AD) is the leading cause of dementia and is characterized by progressive neurodegeneration, resulting in cognitive impairment and structural brain changes. Although no curative treatment exists, pharmacological therapies like cholinesterase inhibitors and NMDA receptor antagonists may deliver symptomatic relief and modestly delay disease progression. Structural magnetic resonance imaging (sMRI) is a commonly utilized modality for the diagnosis of brain neurological diseases and may indicate abnormalities. However, improving the recognition of discriminative characteristics is the primary difficulty in diagnosis utilizing sMRI. Methods: To tackle this problem, the Fuzzy Optimized Attention Network with Multi-Instance Deep Learning (FOA-MIDL) system is presented for the prodromal phase of mild cognitive impairment (MCI) and the initial detection of AD. Results: An attention technique to estimate the weight of every case is presented: the fuzzy salp swarm algorithm (FSSA). The swarming actions of salps in oceans serve as the inspiration for the FSSA. When moving, the nutrient gradients influence the movement of leading salps during global search exploration, while the followers fully explore their local environment to adjust the classifiers’ parameters. To balance the relative contributions of every patch and produce a global distinct weighted image for the entire brain framework, the attention multi-instance learning (MIL) pooling procedure is developed. Attention-aware global classifiers are presented to improve the understanding of the integral characteristics and form judgments for AD-related categorization. The Alzheimer’s Disease Neuroimaging Initiative (ADNI) and the Australian Imaging, Biomarker, and Lifestyle Flagship Study on Ageing (AIBL) provided the two datasets (ADNI and AIBL) utilized in this work. Conclusions: Compared to many cutting-edge techniques, the findings demonstrate that the FOA-MIDL system may determine discriminative pathological areas and offer improved classification efficacy in terms of sensitivity (SEN), specificity (SPE), and accuracy. Full article

While previous studies have explored the use of digital technologies in cultural heritage site reconstruction, limited attention has been given to systems that simultaneously support cultural restoration and psychological healing. This study investigates how multimodal, deep learning–assisted digital technologies can aid displaced populations by enabling both digital reconstruction and trauma relief within virtual environments. A demonstrative virtual reconstruction workflow was developed using the Great Mosque of Aleppo in Damascus as a case study. High-precision three-dimensional models were generated using Neural Radiance Fields, while Stable Diffusion was applied for texture style transfer and localized structural refinement. To enhance immersion, Vector Quantized Variational Autoencoder–based audio reconstruction was used to embed personalized ambient soundscapes into the virtual space. To evaluate the system’s effectiveness, interviews, tests, and surveys were conducted with 20 refugees aged 18–50 years, using the Impact of Event Scale-Revised and the System Usability Scale as assessment tools. The results showed that the proposed approach improved the quality of digital heritage reconstruction and contributed to psychological well-being, offering a novel framework for integrating cultural memory and emotional support in post-disaster contexts. This research provides theoretical and practical insights for future efforts in combining cultural preservation and psychosocial recovery. Full article

Background/Objectives: The aim of this study is to develop a hybrid artificial intelligence (AI) approach to improve the accuracy, efficiency, and reliability of Down Syndrome (DS) risk prediction during first trimester prenatal screening. The proposed method transforms one-dimensional (1D) patient data—including features such as nuchal translucency (NT), human chorionic gonadotropin (hCG), and pregnancy-associated plasma protein A (PAPP-A)—into two-dimensional (2D) Aztec barcode images, enabling advanced feature extraction using transformer-based deep learning models. Methods: The dataset consists of 958 anonymous patient records. Each record includes four first trimester screening markers, hCG, PAPP-A, and NT, expressed as multiples of the median. The DS risk outcome was categorized into three classes: high, medium, and low. Three transformer architectures—DeiT3, MaxViT, and Swin—are employed to extract high-level features from the generated barcodes. The extracted features are combined into a unified set, and dimensionality reduction is performed using two feature selection techniques: minimum Redundancy Maximum Relevance (mRMR) and RelieF. Intersecting features from both selectors are retained to form a compact and informative feature subset. The final features are classified using machine learning algorithms, including Bagged Trees and Naive Bayes. Results: The proposed approach achieved up to 100% classification accuracy using the Naive Bayes classifier with 1250 features selected by RelieF and 527 intersecting features from mRMR. By selecting a smaller but more informative subset of features, the system significantly reduced hardware and processing demands while maintaining strong predictive performance. Conclusions: The results suggest that the proposed hybrid AI method offers a promising and resource-efficient solution for DS risk assessment in first trimester screening. However, further comparative studies are recommended to validate its performance in broader clinical contexts. Full article