Search Results (623)

Background: Breast cancer remains a critical public health problem worldwide and is a leading cause of cancer-related mortality. Optimizing clinical outcomes is contingent upon the early and precise detection of malignancies. Advances in medical imaging and artificial intelligence (AI), particularly in the fields of radiomics and deep learning (DL), have contributed to improvements in early detection methodologies. Nonetheless, persistent challenges, including limited data availability, model overfitting, and restricted generalization, continue to hinder performance. Methods: This study aims to overcome existing challenges by improving model accuracy and robustness through enhanced data augmentation and the integration of radiomics and deep learning features from the CBIS-DDSM dataset. To mitigate overfitting and improve model generalization, data augmentation techniques were applied. The PyRadiomics library was used to extract radiomics features, while transfer learning models were employed to derive deep learning features from the augmented training dataset. For radiomics feature selection, we compared multiple supervised feature selection methods, including RFE with random forest and logistic regression, ANOVA F-test, LASSO, and mutual information. Embedded methods with XGBoost, LightGBM, and CatBoost for GPUs were also explored. Finally, we integrated radiomics and deep features to build a unified multimodal feature space for improved classification performance. Based on this integrated set of radiomics and deep learning features, 13 pre-trained transfer learning models were trained and evaluated, including various versions of ResNet (50, 50V2, 101, 101V2, 152, 152V2), DenseNet (121, 169, 201), InceptionV3, MobileNet, and VGG (16, 19). Results: Among the evaluated models, ResNet152 achieved the highest classification accuracy of 97%, demonstrating the potential of this approach to enhance diagnostic precision. Other models, including VGG19, ResNet101V2, and ResNet101, achieved 96% accuracy, emphasizing the importance of the selected feature set in achieving robust detection. Conclusions: Future research could build on this work by incorporating Vision Transformer (ViT) architectures and leveraging multimodal data (e.g., clinical data, genomic information, and patient history). This could improve predictive performance and make the model more robust and adaptable to diverse data types. Ultimately, this approach has the potential to transform breast cancer detection, making it more accurate and interpretable. Full article

Local Climate Zones (LCZs) provide a critical framework for analyzing how urban morphology influences the surface urban heat island (SUHI) effect. However, the spatiotemporal heterogeneity of the driving mechanisms of urban morphology in SUHI within LCZs under urban renewal remains insufficiently understood. In this study, estimated building heights for 2018, 2021, and 2024 in the main urban area of Guangzhou were used to generate LCZ maps using GIS-based methods. Land surface temperatures (LSTs) were retrieved to quantity the SUHI effect. The Geographical-XGBoost (G-XGBoost) model was applied to evaluate the impacts of urban morphology on SUHI. The results indicated the following: (1) Building height estimation errors range from 5.92 to 7.03 m, and incorporating building height data into LCZ classification enabled sensitive detection of urban evolution dynamics. (2) Built LCZ types accounted for the majority of the study area. Between 2018 and 2024, LCZ 3 decreased markedly, by 9.57%, and land cover LCZ types declined annually to 21.35%. (3) Low-level SUHII was predominant, while the proportion of high and extremely high levels of SUHII initially rose before declining to 16.62%. LCZ 2 and LCZ 3 exhibited the highest SUHII. (4) Pervious surface fraction (PSF) is generally regarded as the most important explanatory factor across LCZ types; however, LCZ 4 represents an exception where its importance significantly decreases. This study reveals the nonlinear impacts of urban morphology evolution on SUHI under the effect of the interaction between LCZs and urban renewal, supporting efforts to optimize urban microclimates and promote sustainable development. Full article

This study presents a low-cost wearable system for monitoring and classifying paddle strokes in open-water environments. Building upon our previous work in controlled aquatic and dryland settings, the proposed system consists of ESP32-based embedded nodes equipped with MPU6050 accelerometer–gyroscope sensors. These nodes communicate via the ESP-NOW protocol in a master–slave architecture. With minimal hardware modifications, the system implements gesture classification using Dynamic Time Warping (DTW) to distinguish between left and right paddle strokes. The collected data, including stroke type, count, and motion similarity, are transmitted in real time to a local interface for visualization. Field experiments were conducted on a calm lake using a paddleboard, where users performed a series of alternating strokes. In addition to gesture recognition, the study includes empirical testing of ESP-NOW communication range in the open lake environment. The results demonstrate reliable wireless communication over distances exceeding 100 m with minimal packet loss, confirming the suitability of ESP-NOW for low-latency data transfer in open-water conditions. The system achieved over 80% accuracy in stroke classification and sustained more than 3 h of operational battery life. This approach demonstrates the feasibility of real-time, wearable-based motion tracking for water sports in natural environments, with potential applications in kayaking, rowing, and aquatic training systems. Full article

Precise classification of landslide types is critical for targeted hazard mitigation, although the absence of type-specific classifications in many existing inventories limits their utility for effective risk management. This study develops a transferable machine learning approach to identify cliff-type landslides from unclassified records, with a focus on earthquake-prone regions. Using the Forest-based and Boosted Classification and Regression (FBCR) tools in ArcGIS Pro, a model was trained on 167 landslide points and 167 non-landslide points from Tokushima Prefecture, Japan. The model achieved high predictive performance, with 84% accuracy and sensitivity, an F1 score of 84%, and a Matthews correlation coefficient (MCC) of 0.68. The trained model was applied to the Kegalle District, Sri Lanka, and validated against a recently updated inventory specifying landslide types, resulting in an accuracy of 80.1%. It also enabled retrospective identification of cliff-type landslides in older inventories, providing valuable insights for early hazard assessment. Spatial analysis showed strong correspondence between predicted cliff-type zones and key conditioning factors, including specific elevation ranges, steep slopes, high soil thickness, and proximity to roads and buildings. This study integrates FBCR-based modelling with a cross-regional application framework for cliff-type landslide classification, offering a practical, transferable tool for refining inventories, guiding countermeasures, and improving preparedness in regions with similar geomorphological and seismic settings. Full article

Series arc faults are a major cause of electrical fires, posing significant risks to life and property. Their negative-resistance characteristics make fault features difficult to detect, and the existing methods often suffer from high false-alarm rates, poor adaptability, and reliance on high sampling rates and long sampling windows. To enhance the accuracy and efficiency of series AC arc fault detection, this paper proposes a rapid identification method based on singular spectrum statistical features and a differential evolution-optimized XGBoost classifier. The approach first constructs the singular spectrum of current waveforms via a Hankel matrix singular value decomposition and extracts nine statistical features. It then optimizes seven XGBoost hyperparameters using differential evolution to build an efficient classification model. The experiments on 18,240 current samples covering 16 load conditions (including eight arc fault types) show that the method achieves an average identification accuracy of 98.90% using only three nominal cycles (60 ms) of current waveform. Even with a training set ratio as low as 5%, it maintains 97.11% accuracy, outperforming Back-propagation Neural Network, Support Vector Machine, and Recurrent Neural Network methods by up to three percentage points. The method avoids the need for high sampling rates or complex time–frequency transformations, making it suitable for resource-constrained embedded platforms and offering a generalizable solution for series arc fault detection. Full article

Loess landslide disasters are influenced by a multitude of factors, including slope conditions, triggering mechanisms, and spatial attributes. Extracting these factors from unstructured geological texts is challenging due to nested entities, semantic ambiguity, and rare domain-specific terms. This study proposes a joint extraction framework guided by a domain ontology that categorizes six types of loess landslide influencing factors, including spatial relationships. The ontology facilitates conceptual classification and semi-automatic nested entity annotation, enabling the construction of a high-quality corpus with eight tag types. The model integrates a Soft-Lexicon mechanism that enhances character-level GloVe embeddings with explicit lexical features, including domain terms, part-of-speech tags, and word boundary indicators derived from a domain-specific lexicon. The resulting hybrid character-level representations are then fed into a BiLSTM-CRF architecture to jointly extract entities, attributes, and multi-level spatial and causal relationships. Extracted results are structured using a content-knowledge model to build a spatially enriched knowledge graph, supporting semantic queries and intelligent reasoning. Experimental results demonstrate improved performance over baseline methods, showcasing the framework’s effectiveness in geohazard information extraction and disaster risk analysis. Full article

Evaluating the renewable energy potential, such as that of solar photovoltaics (PV), is important for developing renewable energy policies. This study investigated rooftop solar PV potential in Thailand based on open-source geographic information system (GIS) building footprints, solar PV power output, and the most recent land use data (2022). GIS-based overlay analysis, buffering, fishnet modeling, and spatial join operations were applied to assess rooftop availability across various building types, taking into account PV module installation parameters and optimal panel orientation. Economic feasibility and sensitivity analyses were conducted using standard economic metrics, including net present value (NPV), internal rate of return (IRR), payback period, and benefit–cost ratio (BCR). The findings showed a total rooftop solar PV power generation potential of 50.32 TWh/year, equivalent to 25.5% of Thailand’s total electricity demand in 2022. The Central region contributed the highest potential (19.59 TWh/year, 38.94%), followed by the Northeastern (10.49 TWh/year, 20.84%), Eastern (8.16 TWh/year, 16.22%), Northern (8.09 TWh/year, 16.09%), and Southern regions (3.99 TWh/year, 7.92%). Both commercial and industrial sectors reflect the financial viability of rooftop PV installations and significantly contribute to the overall energy output. These results demonstrate the importance of incorporating rooftop solar PV in renewable energy policy development in regions with similar data infrastructure, particularly the availability of detailed and standardized land use data for building type classification. Full article

This study presents a comprehensive review and comparative analysis of traditional machine learning (ML) and deep learning (DL) models for land cover classification in agricultural remote sensing. We evaluate the reported successes, trade-offs, and performance metrics of ML and DL models across diverse agricultural contexts. Building on this foundation, we apply both model types to the specific case of almond crop field identification in California’s Central Valley using Landsat data. DL models, including U-Net, MANet, and DeepLabv3+, achieve high accuracy rates of 97.3% to 97.5%, yet our findings demonstrate that conventional ML models—such as Decision Tree, K-Nearest Neighbor, and Random Forest—can reach comparable accuracies of 96.6% to 96.8%. Importantly, the ML models were developed using data from a single year, while DL models required extensive training data spanning 2008 to 2022. Our results highlight that traditional ML models offer robust classification performance with substantially lower computational demands, making them especially valuable in resource-constrained settings. This paper underscores the need for a balanced approach in model selection—one that weighs accuracy alongside efficiency. The findings contribute actionable insights for agricultural land cover mapping and inform ongoing model development in the geospatial sciences. Full article

The integration of Life Cycle Assessment (LCA) into Building Information Modeling (BIM) processes is becoming increasingly important for enhancing the environmental performance of construction projects. This scoping review examines how LCA methods and environmental data are currently integrated into BIM workflows, focusing on automation, data standardization, and visualization strategies. We selected 43 peer-reviewed studies (January 2010–May 2025) via structured searches in five major academic databases. The review identifies five main types of BIM–LCA integration workflows; the most common approach involves exporting quantity data from BIM models to external LCA tools. More recent studies explore the use of artificial intelligence for improving automation and accuracy in data mapping between BIM objects and LCA databases. Key challenges include inconsistent levels of data granularity, a lack of harmonized EPD formats, and limited interoperability between BIM and LCA software environments. Visualization methods such as color-coded 3D models are used to support early-stage decision-making, although uncertainty representation remains limited. To address these issues, future research should focus on standardizing EPD data structures, enriching BIM objects with validated environmental information, and developing explainable AI solutions for automated classification and matching. These advancements would improve the reliability and usability of LCA in BIM-based design, contributing to more informed decisions in sustainable construction. Full article

Indoor navigation poses persistent challenges due to the limitations of traditional positioning systems within buildings. In this study, we propose a novel approach to address this issue—not by continuously tracking the user’s location, but by estimating their position based on how closely their observed behavior matches the expected progression along a predefined route. This concept, while not universally applicable, is well-suited for specific indoor navigation scenarios, such as guiding couriers or delivery personnel through complex residential buildings. We explore this idea in detail in our paper. To implement this behavior-based localization, we introduce an LSTM-based method for classifying user behavior patterns, including standing, walking, and using stairs or elevators, by analyzing velocity sequences derived from smartphone sensors’ data. The developed model achieved 75% accuracy for individual activity type classification within one-second time windows, and 98.6% for full-sequence classification through majority voting. These results confirm the viability of real-time activity recognition as the foundation for a navigation system that aligns live user behavior with pre-recorded patterns, offering a cost-effective alternative to infrastructure-heavy indoor positioning systems. Full article

The complex microenvironment of wounds, along with challenges such as microbial infections, tissue damage, and inflammatory responses during the healing process, renders wound repair a complex medical issue. Owing to their ease of administration, effective outcomes, and painless application, biomacromolecule-based wound dressings have become a focal point in current clinical research. In recent years, hydrogels, microneedles, and electrospun nanofibers have emerged as three novel types of wound dressings. By influencing various stages of healing, they have notably enhanced chronic wound healing outcomes and hold considerable potential for wound repair applications. This review describes the preparation methods, classification, and applications of hydrogels, microneedles, and electrospun nanofibers around the various stages of wound healing, clarifying the healing-promoting mechanisms and characteristics of the three methods in different stages of wound healing. Building upon this foundation, we further introduce smart responsiveness, highlighting the application of stimuli-responsive wound dressings in dynamic wound management, aiming to provide insights for future research. Full article

An important aspect of geoscience and energy research is the analysis of microscopic images, where the assessment of rock properties combines imaging methods with numerical analysis. Given the significant advancements in generative artificial intelligence technologies in recent years, which have enabled the creation of realistic images, a need arises to assess the authenticity of synthetic visual data compared to authentic geological data images. This article evaluates the potential for identifying artificially generated microscopic rock images. Synthetic images were generated using a widely accessible diffusion model, based on real training data. Expert evaluation noted high realism, though some structural and rock-type differences remained detectable. In the study, image descriptors were analyzed to assess their usefulness in distinguishing synthetic data from real data. Discriminative feature selection was conducted, and the effectiveness of various classification models based on the selected parameter sets was compared. The study also proposes a heuristic coefficient demonstrating discriminative potential for the analyzed images. The results confirm the feasibility of building classifiers for synthetic images that could aid in detecting generated visual data in geological and petrographic research. They also serve as a foundation for further exploration of the importance of individual features in such applications. Full article

With the acceleration of modernization, villages in Southwest China are experiencing spatial fragmentation and homogenization, leading to the loss of traditional identity. Addressing how to balance scientific planning with cultural and spatial continuity has become a key challenge in rural governance. This study takes Xuyong County in Luzhou City as a case and develops a three-tier analytical framework—“genome–spatial factors–specific indicators”—based on the space gene theory to identify, classify, and map spatial patterns in marginal villages of southern Sichuan. Through cluster analysis, common and distinctive spatial genes are extracted. Common genes—such as medium surface roughness (GeneN-2-b), medium building dispersion (GeneA-3-b), and low intelligibility (GeneT-2-b)—are prevalent across multiple village types, reflecting shared adaptive strategies to complex terrains, ecological constraints, and historical development. In contrast, distinctive genes—such as high building dispersion (GeneA-3-a) and linear boundaries (GeneB-1-c)—highlight unique spatial responses that are shaped by local cultural and environmental conditions. The results contribute to a deeper understanding of spatial morphology and adaptive mechanisms in rural settlements. This research offers a theoretical and methodological basis for village classification, conservation zoning, and spatial optimization, providing practical guidance for rural revitalization efforts focusing on both development and heritage protection. Full article

Oases in arid regions are critical ecosystems, providing essential ecological, agricultural, and socio-economic functions. However, urbanization and climate change increasingly threaten their sustainability. This study examines land cover (LULC) and land surface temperature (LST) dynamics in four representative North African oases: Tolga (Algeria), Nefta (Tunisia), Ghadames (Libya), and Siwa (Egypt) over the period 2000–2023, using Landsat satellite imagery. A three-step analysis was employed: calculation of NDVI (Normalized Difference Vegetation Index), NDBI (Normalized Difference Built-up Index), and LST, followed by supervised land cover classification and statistical tests to examine the relationships between the studied variables. The results reveal substantial reductions in bare soil (e.g., 48.10% in Siwa) and notable urban expansion (e.g., 136.01% in Siwa and 48.46% in Ghadames). Vegetation exhibited varied trends, with a slight decline in Tolga (0.26%) and a significant increase in Siwa (+27.17%). LST trends strongly correlated with land cover changes, demonstrating increased temperatures in urbanized areas and moderated temperatures in vegetated zones. Notably, this study highlights that traditional urban designs integrated with dense palm groves significantly mitigate thermal stress, achieving lower LST compared to modern urban expansions characterized by sparse, heat-absorbing surfaces. In contrast, areas dominated by fragmented vegetation or seasonal crops exhibited reduced cooling capacity, underscoring the critical role of vegetation type, spatial arrangement, and urban morphology in regulating oasis microclimates. Preserving palm groves, which are increasingly vulnerable to heat-driven pests, diseases and the introduction of exotic species grown for profit, together with a revival of the traditional compact urban fabric that provides shade and has been empirically confirmed by other oasis studies to moderate the microclimate more effectively than recent low-density extensions, will maintain the crucial synergy between buildings and vegetation, enhance the cooling capacity of these settlements, and safeguard their tangible and intangible cultural heritage. Full article

This research presents a novel method for detecting building roof types using deep learning models based on height profiles from high-resolution digital surface models. While deep learning has proven effective in digit, handwritten, and time series classification, this study focuses on the emerging and crucial area of height profile detection for building roof type classification. We propose an innovative approach to automatically generate, classify, and detect building roof types using height profiles derived from normalized digital surface models. We present three distinct methods to detect seven roof types from two height profiles of the building cross-section. The first two methods detect the building roof type from two-dimensional (2D) height profiles: two binary images and a two-band spectral image. The third method, vector-based, detects the building roof type from two one-dimensional (1D) height profiles represented as two 1D vectors. We trained various one- and two-dimensional convolutional neural networks on these 1D and 2D height profiles. The DenseNet201 network could directly detect the roof type of a building from two height profiles stored as a two-band spectral image with an average accuracy of 97%, even in the presence of consecutive chimneys, dormers, and noise. The strengths of this approach include the generation of a large, detailed, and storage-efficient labeled height profile dataset, the development of a robust classification method using both 1D and 2D height profiles, and an automated workflow that enhances building roof type detection. Full article