Search Results (2,761)

With the continuous maturation of prefabricated buildings, the errors and efficiency issues in the design of prefabricated buildings have gradually drawn the attention of architectural designers. The characteristics of standardized design for prefabricated buildings also provide a foundation for the application of computer-learning methods in the field of architectural design, thereby improving design quality and efficiency. This study combined BIM technology to construct the information data on prefabricated buildings, applied the transfer-learning method to build the training model, and utilized the traditional architectural design collision concept to construct a prediction model applicable to the collision detection of prefabricated building design. The training set and test set were constructed in a 9:1 ratio, and the loss function and accuracy function were calculated. The error rate of the model was verified to be within 10% through trial calculations based on engineering cases. The results show that, in the selected engineering cases, the collision detection accuracy of the model reached 90.3%, with an average absolute error (MAE) of 0.199 and a root mean square error (RMSE) of 0.245. The prediction error rate was controlled within 10%, representing an approximately 65% improvement in efficiency compared to traditional manual inspections. This method significantly improves the efficiency and accuracy of collision detection, providing reliable technical support for the optimization of prefabricated building design. Full article

The precise mapping of rock joint traces is fundamental to the design and safety assessment of foundations, retaining structures, and underground cavities in building and civil engineering. Existing deep learning approaches either impose prohibitive computational demands for on-site deployment or disrupt the topological continuity of subpixel lineaments that govern rock mass behavior. This study presents BATNet-Lite, a lightweight encoder–decoder architecture optimized for joint segmentation on resource-constrained devices. The encoder introduces a Boundary-Aware Token-Mixing (BATM) block that separates feature maps into patch tokens and directionally pooled stripe tokens, and a bidirectional attention mechanism subsequently transfers global context to local descriptors while refining stripe features, thereby capturing long-range connectivity with negligible overhead. A complementary Multi-Scale Line Enhancement (MLE) module combines depth-wise dilated and deformable convolutions to yield scale-invariant responses to joints of varying apertures. In the decoder, a Skeletal-Contrastive Decoder (SCD) employs dual heads to predict segmentation and skeleton maps simultaneously, while an InfoNCE-based contrastive loss enforces their topological consistency without requiring explicit skeleton labels. Training leverages a composite focal Tversky and edge IoU loss under a curriculum-thinning schedule, improving edge adherence and continuity. Ablation experiments confirm that BATM, MLE, and SCD each contribute substantial gains in boundary accuracy and connectivity preservation. By delivering topology-preserving joint maps with small parameters, BATNet-Lite facilitates rapid geological data acquisition for tunnel face mapping, slope inspection, and subsurface digital twin development, thereby supporting safer and more efficient building and underground engineering practice. Full article

The use of single-layer aerated concrete walls in residential construction has a tradition of over 60 years. Its main advantage is thermal insulation. It is the most advantageous among construction materials used for the construction of external walls. The possibility of modifying the dimensions of the blocks leads to meeting subsequent restrictive values of the heat transfer coefficient U. The high dimensional accuracy of the blocks allows the use of dry vertical joints and thin joints with a thickness of 1–3 mm, the thermal influence of which is omitted. However, the thermal uniformity of such a wall is strictly dependent on the quality of workmanship. The main objective of the analysis is to assess the impact of moisture on the U_wall of walls as a function of vertical joint spacing and horizontal joint thickness. It should be said that the effect of humidity and manufacturing accuracy on the thermal properties of aerated concrete walls has not been sufficiently studied. Further study of these patterns is necessary. Particular attention should be paid to the thin-bed mortar, which depends on the manufacturing accuracy. The separation of AAC masonry elements that occurs during bricklaying significantly affects the thermal insulation of walls. This issue has not yet been analysed. The scientific objective of this article is to develop a procedure for determining the thermal properties of a small, irregular air space created as a result of the separation of masonry elements and the impact of this separation on the thermal insulation of the wall. Based on the analysis of the thermal conductivity of voids and masonry elements, it was determined that this impact is visible at low AAC densities. A detailed analysis taking into account both these joints and horizontal joints, as well as different moisture levels, made it possible to determine the permissible separation of AAC blocks, at which the high thermal insulation requirements applicable in most European countries are met. The analysis showed that it is possible to meet the thermal protection requirements for 42 cm wide blocks intended for single-layer walls with a maximum vertical contact width of 3 mm and a joint thickness of up to 2 mm. AAC moisture content plays a major role in thermal insulation. Insulation requirements can be met for AAC in an air-dry state, as specified by ISO 10456. Full article

To address the challenges of real-time monitoring via highway vehicle-mounted cameras—specifically, the difficulty in detecting distant pedestrians and vehicles in real time—this study proposes an enhanced object detection algorithm, YOLOv5s-F. Firstly, the FasterNet network structure is adopted to improve the model’s runtime speed. Secondly, the attention mechanism BRA, which is derived from the Transformer algorithm, and a 160 × 160 small-object detection layer are introduced to enhance small target detection performance. Thirdly, the improved upsampling operator CARAFE is incorporated to boost the localization and classification accuracy of small objects. Finally, Focal EIoU is employed as the localization loss function to accelerate model training convergence. Quantitative experiments on high-speed sequences show that Focal EIoU reduces bounding box jitter by 42.9% and improves tracking stability (consecutive frame overlap) by 11.4% compared to CIoU, while accelerating convergence by 17.6%. Results show that compared with the YOLOv5s baseline network, the proposed algorithm reduces computational complexity and parameter count by 10.1% and 24.6%, respectively, while increasing detection speed and accuracy by 15.4% and 2.1%. Transfer learning experiments on the VisDrone2019 and Highway-100k dataset demonstrate that the algorithm outperforms YOLOv5s in average precision across all target categories. On NVIDIA Jetson Xavier NX, YOLOv5s-F achieves 32 FPS after quantization, meeting the real-time requirements of in-vehicle monitoring. The YOLOv5s-F algorithm not only meets the real-time detection and accuracy requirements for small objects but also exhibits strong generalization capabilities. This study clarifies core challenges in highway small-target detection and achieves accuracy–speed improvements via three key innovations, with all experiments being reproducible. If any researchers need the code and dataset of this study, they can consult the author through email. Full article

For multiple unmanned underwater vehicles (UUVs) systems, obstacle avoidance during cooperative operation in complex marine environments remains a challenging issue. Recent studies demonstrate the effectiveness of deep reinforcement learning (DRL) for obstacle avoidance in unknown marine environments. However, existing methods struggle in marine environments with complex non-convex obstacles, especially during multi-UUV cooperative operation, as they typically simplify environmental obstacles to convex shapes with sparse distributions and ignore the dynamic coupling between cooperative operation and collision avoidance. To address these limitations, we propose a centralized training with decentralized execution framework with a novel multi-agent dynamic encoder based on an efficient self-attention mechanism. The framework, to our knowledge, is the first to dynamically process observations from an arbitrary number of neighbors that effectively addresses multi-UUV collision avoidance in marine environments with complex non-convex obstacles while satisfying additional constraints derived from cooperative operation. Experimental results show that the proposed method effectively avoids obstacles and satisfies cooperative constraints in both simulated and real-world scenarios with complex non-convex obstacles. Our method outperforms typical collision avoidance baselines and enables policy transfer from simulation to real-world scenarios without additional training, demonstrating practical application potential. Full article

Although forest tenure devolution has been widely implemented, limited research has examined the carbon sequestration effects of property rights, particularly the interactions among rights within the tenure bundle. This research quantifies the structure of forest tenure at the village level over a 20-year period (2000–2019) and links it with village-year satellite observations of forest carbon sequestration. Using two-way fixed effects regression, interaction effect models, and mediation analysis, the research examines the carbon responses to devolved forest tenure, with particular attention to the interactions among tenure rights and the heterogeneity across forest types. Empirical results indicate that the logging right constitutes the core component of the tenure bundle that promotes carbon sequestration in mature forests and shrublands. When the logging right was completely absent, the impact of ownership on carbon sequestration became insignificant. Tenure rights bundles interact significantly in shaping carbon sequestration outcomes in mature forests. Specifically, longer tenure duration reinforces the effects of ownership and logging rights, whereas transferability tends to substitute for their returns. In terms of young plantations, only official certification of ownership would promote their carbon sequestration and there are no interaction impacts between rights. Further analyses combining farmer behavior find that the reduction in logging intensity, rather than frequency, is a significant channel for logging rights to promote carbon sequestration of mature stands. Ownership increases the frequency but the intensity of afforestation/reforestation, which in turn increases carbon sequestration of young plantations. Full article

Fault diagnosis under variable operating conditions remains challenging due to the limited adaptability of traditional methods. This paper proposes a transfer learning-based approach for bearing fault diagnosis across different rotational speeds, addressing the critical need for reliable detection in changing industrial environments. The method trains a diagnostic model on labeled source-domain data and transfers them to unlabeled target domains through a two-stage adaptation strategy. First, only the source-domain data are labeled to reflect real-world scenarios where target-domain labels are unavailable. The model architecture combines a convolutional neural network (CNN) for feature extraction with a self-attention mechanism for classification. During source-domain training, the feature extractor parameters are frozen to focus on classifier optimization. When transferring to target domains, the classifier parameters are frozen instead, allowing the feature extractor to adapt to new speed conditions. Experimental validation on the Case Western Reserve University bearing dataset (CWRU), Jiangnan University bearing dataset (JNU), and Southeast University gear and bearing dataset (SEU) demonstrates the method’s effectiveness, achieving accuracies of 99.95%, 99.99%, and 100%, respectively. The proposed method achieves significant model size reduction compared to conventional TL approaches (e.g., DANN and CDAN), with reductions of up to 91.97% and 64%, respectively. Furthermore, we observed a maximum reduction of 61.86% in FLOPs consumption. The results show significant improvement over conventional approaches in maintaining diagnostic performance across varying operational conditions. This study provides a practical solution for industrial applications where equipment operates under non-stationary speeds, offering both computational efficiency and reliable fault detection capabilities. Full article

This study reviews heat transfer fluids (HTFs) and their velocity effects on the thermal behavior of ground heat exchangers (GHEs) within geothermal heat pump (GHP) applications. It examines the classification, thermophysical properties, and operational behavior of standard working fluids, including water–glycol mixtures, as well as emerging nanofluids. Fundamental heat exchange mechanisms are discussed, with emphasis on how conductivity, viscosity, and heat capacity interact with fluid velocity to influence energy transfer performance, hydraulic resistance, and system reliability. Special attention is given to nanofluids, whose enhanced thermal behavior depends on nanoparticle type, concentration, dispersion stability, and flow conditions. The review analyzes stabilization strategies, including surfactants, functionalization, and pH control, for maintaining long-term performance. It also highlights the role of velocity optimization in balancing convective benefits with pumping energy demands, providing velocity ranges suited to different GHE configurations. Drawing from recent experimental and numerical studies, the review offers practical guidelines for integrating nanofluid formulation with engineered operating conditions to maximize energy efficiency and extend system lifespan. Full article

Recent approaches to geo-referencing X posts have focused on the use of language modelling techniques that learn geographic region-specific language and use this to infer geographic coordinates from text. These approaches rely on large amounts of labelled data to build accurate predictive models. However, obtaining significant volumes of geo-referenced data from Twitter, recently renamed X, can be difficult. Further, existing language modelling approaches can require the division of a given area into a grid or set of clusters, which can be dataset-specific and challenging for location prediction at a fine-grained level. Regression-based approaches in combination with deep learning address some of these challenges as they can assign coordinates directly without the need for clustering or grid-based methods. However, such approaches have received only limited attention for the geo-referencing task. In this paper, we adapt state-of-the-art neural network models for the regression task, focusing on geo-referencing wildlife Tweets where there is a limited amount of data. We experiment with different transfer learning techniques for improving the performance of the regression models, and we also compare our approach to recently developed Large Language Models and prompting techniques. We show that using a location names extraction method in combination with regression-based disambiguation, and purely regression when names are absent, leads to significant improvements in locational accuracy over using only regression. Full article

The rapid advancement of Artificial Intelligence of Things (AIoT) has driven an urgent demand for intelligent video anomaly detection (VAD) to ensure industrial safety. However, traditional approaches struggle to detect unknown anomalies in complex and dynamic environments due to the scarcity of abnormal samples and limited generalization capabilities. To address these challenges, this paper presents an adaptive VAD framework powered by edge intelligence tailored for resource-constrained industrial settings. Specifically, a lightweight feature extractor is developed by integrating residual networks with channel attention mechanisms, achieving a 58% reduction in model parameters through dense connectivity and output pruning. A multidimensional evaluation strategy is introduced to dynamically select optimal models for deployment on heterogeneous edge devices. To enhance cross-scene adaptability, we propose a multilayer adversarial domain adaptation mechanism that effectively aligns feature distributions across diverse industrial environments. Extensive experiments on a real-world coal mine surveillance dataset demonstrate that the proposed framework achieves an accuracy of 86.7% with an inference latency of 23 ms per frame on edge hardware, improving both detection efficiency and transferability. Full article

Background/Objectives: Post-stroke cognitive impairment significantly impacts long-term functional outcomes, particularly in instrumental activities of daily living (IADLs). Working memory training (WMT) has emerged as a potential cognitive rehabilitation strategy; however, its transfer to real-world functionality remains unclear. This study evaluated whether adaptive computerized WMT enhances IADLs performance compared to a non-adaptive control condition in chronic stroke survivors. Methods: A single-blind, randomized controlled trial was conducted with 50 adults aged 50–79 years, ≥12 months post-ischemic stroke, and diagnosed with a mild neurocognitive disorder. Participants were randomized to adaptive WMT or non-adaptive cognitive training, each completing 25 home-based sessions over 12 weeks via a standardized online platform. Primary outcomes included the Lawton and Brody IADL Scale and the Working Memory Questionnaire (WMQ); secondary outcomes included the Working Memory Index (WMI) from the WAIS-IV. Analyses included frequentist and Bayesian methods. Results: Both groups showed significant pre–post improvements in IADL independence and WMI (p < 0.05; BF₁₀ > 10), with no significant between-group differences on overall IADL outcomes. The adaptive WMT group demonstrated specific gains in WMQ—Storing (p = 0.033; BF₁₀ = 3.83), while the control group improved in WMQ—Attention and IADL—Assistance Required (p = 0.004–0.035; BF₁₀ > 6). Bayesian ANOVA indicated that these effects were primarily driven by the interventions, with minimal influence from depressive symptoms or global cognition. Conclusions: Adaptive WMT yielded domain-specific cognitive benefits but did not enhance IADL performance beyond non-adaptive training. These findings highlight the limited far transfer of WMT and the importance of designing ecologically valid, multimodal rehabilitation strategies post-stroke. Full article

The escalating scale and psychological harm of cyberbullying across digital platforms present a critical social challenge, demanding the urgent development of highly accurate and reliable automated detection systems. Standard fine-tuned transformer models, while powerful, often fall short in capturing the nuanced, context-dependent nature of online harassment. This paper introduces a novel hybrid deep learning model called Robustly Optimized Bidirectional Encoder Representations from the Transformers with the Bidirectional Long Short-Term Memory-based Attention model (RoBERTa-BiLSTM), specifically designed to address this challenge. To maximize its effectiveness, the model was systematically optimized using the Optuna framework and rigorously benchmarked against eight state-of-the-art transformer baseline models on a large cyberbullying dataset. Our proposed model achieves state-of-the-art performance, outperforming BERT-base, RoBERTa-base, RoBERTa-large, DistilBERT, ALBERT-xxlarge, XLNet-large, ELECTRA-base, DeBERTa-v3-small with an accuracy of 94.8%, precision of 96.4%, recall of 95.3%, F1-score of 95.8%, and an AUC of 98.5%. Significantly, it demonstrates a substantial improvement in F1-score over the strongest baseline and reduces critical false negative errors by 43%, all while maintaining moderate computational efficiency. Furthermore, our efficiency analysis indicates that this superior performance is achieved with a moderate computational complexity. The results validate our hypothesis that a specialized hybrid architecture, which synergizes contextual embedding with sequential processing and attention mechanism, offers a more robust and practical solution for real-world social media applications. Full article

Steady-State Visual Evoked Potentials (SSVEPs) have emerged as an efficient means of interaction in brain–computer interfaces (BCIs), achieving bioinspired efficient language output for individuals with aphasia. Addressing the underutilization of frequency information of SSVEPs and redundant computation by existing transformer-based deep learning methods, this paper analyzes signals from both the time and frequency domains, proposing a stacked encoder–decoder (SED) network architecture based on an xLSTM model and spatial attention mechanism, termed SED-xLSTM, which firstly applies xLSTM to the SSVEP speller field. This model takes the low-channel spectrogram as input and employs the filter bank technique to make full use of harmonic information. By leveraging a gating mechanism, SED-xLSTM effectively extracts and fuses high-dimensional spatial-channel semantic features from SSVEP signals. Experimental results on three public datasets demonstrate the superior performance of SED-xLSTM in terms of classification accuracy and information transfer rate, particularly outperforming existing methods under cross-validation across various temporal scales. Full article

Agricultural image processing technology plays a critical role in enabling precise disease detection, accurate yield prediction, and various smart agriculture applications. However, its practical implementation faces key challenges, including environmental interference, data scarcity and imbalance datasets, and the difficulty of deploying models on resource-constrained edge devices. This paper presents a systematic review of recent advances in addressing these challenges, with a focus on three core aspects: environmental robustness, data efficiency, and model deployment. The study identifies that attention mechanisms, Transformers, multi-scale feature fusion, and domain adaptation can enhance model robustness under complex conditions. Self-supervised learning, transfer learning, GAN-based data augmentation, SMOTE improvements, and Focal loss optimization effectively alleviate data limitations. Furthermore, model compression techniques such as pruning, quantization, and knowledge distillation facilitate efficient deployment. Future research should emphasize multi-modal fusion, causal reasoning, edge–cloud collaboration, and dedicated hardware acceleration. Integrating agricultural expertise with AI is essential for promoting large-scale adoption, as well as achieving intelligent, sustainable agricultural systems. Full article

In resource-constrained edge environments—such as mobile devices, IoT systems, and electric vehicles—energy-efficient Convolution Neural Network (CNN) accelerators on mobile Field Programmable Gate Arrays (FPGAs) are gaining significant attention for real-time object detection tasks. This paper presents a low-power implementation of the Tiny YOLOv4 object detection model on the Xilinx ZCU104 FPGA platform by using Register Transfer Level (RTL) optimization techniques. We proposed three RTL techniques in the paper: (i) Local Explicit Clock Enable (LECE), (ii) operand isolation, and (iii) Enhanced Clock Gating (ECG). A novel low-power design of Multiply-Accumulate (MAC) operations, which is one of the main components in the AI algorithm, was proposed to eliminate redundant signal switching activities. The Tiny YOLOv4 model, trained on the COCO dataset, was quantized and compiled using the Tensil tool-chain for fixed-point inference deployment. Post-implementation evaluation using Vivado 2022.2 demonstrates around 29.4% reduction in total on-chip power. Our design supports real-time detection throughput while maintaining high accuracy, making it ideal for deployment in battery-constrained environments such as drones, surveillance systems, and autonomous vehicles. These results highlight the effectiveness of RTL-level power optimization for scalable and sustainable edge AI deployment. Full article