Search Results (141)

In field exploration, disaster rescue, and complex terrain operations, the accuracy of ground type recognition directly affects the walking stability and task execution efficiency of legged robots. To address the problem of terrain recognition in complex ground environments, this paper proposes a high-precision classification method based on single-leg triaxial force signals. The method first employs a one-dimensional convolutional neural network (1D-CNN) module to extract local temporal features, then introduces a long short-term memory (LSTM) network to model long-term and short-term dependencies during ground contact, and incorporates a convolutional block attention module (CBAM) to adaptively enhance the feature responses of critical channels and time steps, thereby improving discriminative capability. In addition, an improved whale optimization algorithm (iBWOA) is adopted to automatically perform global search and optimization of key hyperparameters, including the number of convolution kernels, the number of LSTM units, and the dropout rate, to achieve the optimal training configuration. Experimental results demonstrate that the proposed method achieves excellent classification performance on five typical ground types—grass, cement, gravel, soil, and sand—under varying slope and force conditions, with an overall classification accuracy of 96.94%. Notably, it maintains high recognition accuracy even between ground types with similar contact mechanical properties, such as soil vs. grass and gravel vs. sand. This study provides a reliable perception foundation and technical support for terrain-adaptive control and motion strategy optimization of legged robots in real-world environments. Full article

Abnormal shutdown detection in oilfield pumping units presents significant challenges, including degraded image quality under low-light conditions, difficulty in detecting small or obscured targets, and limited capabilities for dynamic state perception. Previous approaches, such as traditional visual inspection and conventional image processing, often struggle with these limitations. To address these challenges, this study proposes an intelligent method integrating multi-scale feature enhancement and low-light image optimization. Specifically, a lightweight low-light enhancement framework is developed based on the Zero-DCE algorithm, improving the deep curve estimation network (DCE-Net) and non-reference loss functions through training on oilfield multi-exposure datasets. This significantly enhances brightness and detail retention in complex lighting conditions. The DAFE-Net detection model incorporates a four-level feature pyramid (P3–P6), channel-spatial attention mechanisms (CBAM), and Focal-EIoU loss to improve localization of small/occluded targets. Inter-frame difference algorithms further analyze motion states for robust “pump-off” determination. Experimental results on 5000 annotated images show the DAFE-Net achieves 93.9% mAP@50%, 96.5% recall, and 35 ms inference time, outperforming YOLOv11 and Faster R-CNN. Field tests confirm 93.9% accuracy under extreme conditions (e.g., strong illumination fluctuations and dust occlusion), demonstrating the method’s effectiveness in enabling intelligent monitoring across seven operational areas in the Changqing Oilfield while offering a scalable solution for real-time dynamic anomaly detection in industrial equipment monitoring. Full article

This study examines the perceived air quality and contributors to air pollution among residents of Merced and Stanislaus Counties in California’s San Joaquin Valley (SJV), one of the most polluted regions in the United States. A survey was conducted during the summer of 2017, gathering responses from 176 participants to assess their perceptions of air quality, sources of pollution, and behaviors related to air pollution awareness. Findings indicate that only 3.5% of participants perceived the air quality in their city as good, while 57.9% categorized it as unhealthy or unhealthy for sensitive groups. Participants identified cars and trucks as the primary sources of air pollution, followed by forest fires and factories. Seasonal differences in perception were also observed, with summer months being viewed as the most polluted. Additionally, participants living near major roadways reported higher concerns regarding air pollution’s impact on health. Multivariate regression analysis revealed that education was significantly associated with perceived air quality, while proximity to highways influenced perceptions of health risks. This study underscores the need for targeted interventions to raise awareness and promote self-protective behaviors, especially for vulnerable populations living near highways. These findings highlight the importance of localized public health strategies to address air quality concerns in SJV communities. Full article

As a new generation 3D video coding standard, 3D-HEVC offers highly efficient compression. However, its recursive quadtree partitioning mechanism and frequent rate-distortion optimization (RDO) computations lead to a significant increase in coding complexity. Particularly, intra-frame coding in depth maps, which incorporates tools like depth modeling modes (DMMs), substantially prolongs the decision-making process for coding unit (CU) partitioning, becoming a critical bottleneck in compression encoding time. To address this issue, this paper proposes a fast CU partitioning framework based on hierarchical feature fusion convolutional neural networks (HFF-CNNs). It aims to significantly accelerate the overall encoding process while ensuring excellent encoding quality by optimizing depth map CU partitioning decisions. This framework synergistically captures CU’s global structure and local details through multi-scale feature extraction and channel attention mechanisms (SE module). It introduces the wavelet energy ratio designed for quantifying the texture complexity of depth map CU and the quantization parameter (QP) that reflects the encoding quality as external features, enhancing the dynamic perception ability of the model from different dimensions. Ultimately, it outputs depth-corresponding partitioning predictions through three fully connected layers, strictly adhering to HEVC’s quad-tree recursive segmentation mechanism. Experimental results demonstrate that, across eight standard test sequences, the proposed method achieves an average encoding time reduction of 48.43%, significantly lowering intra-frame encoding complexity with a BDBR increment of only 0.35%. The model exhibits outstanding lightweight characteristics with minimal inference time overhead. Compared with the representative methods under comparison, this method achieves a better balance between cross-resolution adaptability and computational efficiency, providing a feasible optimization path for real-time 3D-HEVC applications. Full article

Friction contact regulation has been widely acknowledged, yet research on micro-textured meshing interfaces appears to have reached an impasse. Conventional wisdom holds that the similarity of micro-element configurations is the key factor contributing to textured interface issues. The traditional perception is transcended, and a novel method for presetting the optimal parameters of gradientized micro-textured interface elements is proposed. The study has analyzed the Interface Enriched Lubrication (IEL) performance and meshing Anti-Scuffing Load-Bearing Capacity (ASLBC) of periodic symmetrical and continuously gradient micro-elements. By actively regulating IEL behavior through geometric constraint effects, dynamic micro-cavity lubrication storage units are formed, thereby extending the retention time of medium film layers. The textured edges induce micro-vortices, delaying scuffing failures induced by load-bearing. Validation analyses demonstrate that optimal micro-element configurations can distribute contact stress to achieve stress homogenization, with the maximum contact stress reduced by 21%. The localized hydrodynamic effect of micro-textured elements increases interfacial meshing stiffness by 5.32% while decreasing friction torque by 27.3%. This investigation reveals a synergistic mechanism between IEL performance and meshing ASLBC under heavy loads conditions. The findings confirm that gradient-based micro-textured element configuration presetting offers an effective solution to reconcile the inherent trade-off between lubrication and load-bearing performance in heavy loads applications. Full article

This study investigates the economic viability of a new composting station dedicated to the recycling of date palm by-products. A field experiential analysis was performed in the Figuig Oasis (Morocco), providing the first evidence on the agronomic quality of the compost. The compost produced from date palm by-product was compared to cattle manure and unamended soil and can be considered as a good-quality amendment, demonstrating its ability to enhance soil fertility. Second, a socio-economic survey was conducted to explore farmers’ perceptions and adoption of sustainable agricultural practices. A total of 201 farmers out of 450 farmers registered in Figuig’s municipal administration were surveyed. In terms of fertilisation, farmers preferred locally produced organic fertiliser when available in order to improve soil organic matter content and reduce dependence on chemical inputs. The selling price for the compost was set at 0.14 EUR/kg to reflect the current market price for compost and the willingness of about 38% of the farmers surveyed to buy it. Third, a detailed cost/benefit analysis was performed, with a breakdown of the station’s operational and investment expenses. This illustrates the minimum scale needed to generate a viable business model. Financial projections show that increasing production capacity from 350 tonnes/year to 3500 tonnes/year reduces unit production costs while increasing profits. As illustrated by the application of the Ecocanvas framework, the socio-economic analysis reveals the potential to generate positive environmental, economic, and social impacts, as the circular approach could be replicable and scalable in similar oases agro ecosystems. Full article

The Akkuyu Nuclear Power Plant (NPP) is framed as a flagship of Türkiye’s national low-carbon transition. This study examines how domestic economic actors perceive the project’s socio-economic and environmental impacts, and how those perceptions align with—or diverge from—official assessments and the United Nations Sustainable Development Goals. Using a qualitative phenomenological approach, the research draws on 28 semi-structured interviews with members of the Silifke Chamber of Commerce and Industry Council. This lens captures how locally embedded businesses read the project’s risks and rewards in real time. Four themes stand out. First, respondents see a clear economic uptick—but one that feels time-bound and vulnerable to the project cycle. Second, many feel excluded from decision-making; as a result, their support remains conditional rather than open-ended. Third, participants describe environmental signals as ambiguous, paired with genuine ecological concern. Fourth, skepticism about governance intertwines with sovereignty anxieties, particularly around foreign ownership and control. Overall, while short-term economic benefits are widely acknowledged, support is tempered by procedural exclusion, environmental worry, and distrust of foreign control. Conceptually, the study contributes to energy-justice scholarship by elevating sovereignty as an additional dimension of justice and by highlighting the link between being shut out of processes and perceiving higher environmental risk. Policy implications follow directly: create robust, domestic communication channels; strengthen participatory governance so local actors have a real voice; and embed nuclear projects within regional development strategies so economic gains are durable and broadly shared. Full article

Long-term and accurate prediction of air pollutant concentrations can serve as a foundation for air pollution warning and prevention, which is crucial for social development and human health. In this study, we provide a model for predicting the concentration of air pollutants based on big data spatiotemporal correlation analysis and deep learning methods. Based on an improved temporal convolutional network (TCN) and a bi-directional gated recurrent unit (BiGRU) as the fundamental architecture, the model adds two attention mechanisms to improve performance: Squeeze and Excitation Networks (SENet) and Convolutional Block Attention Module (CBAM). The improved TCN moves the residual connection layer to the network’s front end as a preprocessing procedure, improving the model’s performance and operating efficiency, particularly for big data jobs like air pollution concentration prediction. The use of SENet improves the model’s comprehension and extraction of long-term dependent features from pollutants and meteorological data. The incorporation of CBAM enhances the model’s perception ability towards key local regions through an attention mechanism in the spatial dimension of the feature map. The TCN-SENet-BiGRU-CBAM model successfully realizes the prediction of air pollutant concentrations by extracting the spatiotemporal features of the data. Compared with previous advanced deep learning models, the model has higher prediction accuracy and generalization ability. The model is suitable for prediction tasks from 1 to 12 h in the future, with root mean square error (RMSE) and mean absolute error (MAE) ranging from 5.309~14.043 and 3.507~9.200, respectively. Full article

Due to the challenges of low resolution and incomplete data in the process of power data collection and transmission and the lack of detail in the power data super-resolution algorithm, this paper proposes a generative adversarial network super-resolution perception model based on a linear attention mechanism. It uses the adversarial training mechanism of generator and discriminator to restore high-resolution power data from low-resolution power data. In the generator, the deep residual network structure is innovatively combined with the multi-scale linear attention mechanism, and the linear rectifier unit that can be dynamically learned is combined to improve the model’s ability to extract power data features. The discriminator employs a multi-scale architecture embedded with a dual-attention module, integrating both global and local features to enhance the model’s ability to capture fine details. Experiments were conducted on a dataset of multiple monitoring points in a city in East China. Experimental results indicate that the proposed Lmla-GAN delivers an overall average SSIM improvement of approximately 6.7% over the four baseline models-Bicubic, SRCNN, SubPixelCNN, and VDSR. Full article

Background/Objectives: Vaccine hesitancy is becoming an increasing concern, leading to preventable outbreaks of infectious diseases. During the COVID-19 pandemic, the United States served as an intriguing case study for exploring how risk perception and trust in health authorities, including scientists, are influenced by government policies and how these factors affect vaccine hesitancy. Methods: We conducted a secondary analysis using the MIT COVID-19 Survey dataset to investigate whether risk perception and trust differ between states governed by Democratic or Republican governors. Results: Our analysis (n = 6119) found that participants did not vary significantly by state political affiliation in terms of their sociodemographic factors (such as age, gender, self-rated health, education, and whether they live in a city, town, or rural area), their perceived risk for the community, or their ability to control whether they become infected. However, there was a difference in the perceived risk of infection, which was higher in states governed by Republicans. Trust also varied by gubernatorial affiliation, with higher levels of trust reported among residents of Democratic-leaning states. We also found a strong mediation effect of trust on vaccine hesitancy, but this was not the case for risk perception. Conclusion: Therefore, it appears that vaccine acceptance relies on trust in health authorities, which is influenced by governmental policies. State officials should work with local health officials to build trust and increase timely responses to public health crises. Full article

To address the challenges of low recognition accuracy and substantial model complexity in crop disease identification models operating in complex field environments, this study proposed a novel hybrid model named ConvTransNet-S, which integrates Convolutional Neural Networks (CNNs) and transformers for crop disease identification tasks. Unlike existing hybrid approaches, ConvTransNet-S uniquely introduces three key innovations: First, a Local Perception Unit (LPU) and Lightweight Multi-Head Self-Attention (LMHSA) modules were introduced to synergistically enhance the extraction of fine-grained plant disease details and model global dependency relationships, respectively. Second, an Inverted Residual Feed-Forward Network (IRFFN) was employed to optimize the feature propagation path, thereby enhancing the model’s robustness against interferences such as lighting variations and leaf occlusions. This novel combination of a LPU, LMHSA, and an IRFFN achieves a dynamic equilibrium between local texture perception and global context modeling—effectively resolving the trade-offs inherent in standalone CNNs or transformers. Finally, through a phased architecture design, efficient fusion of multi-scale disease features is achieved, which enhances feature discriminability while reducing model complexity. The experimental results indicated that ConvTransNet-S achieved a recognition accuracy of 98.85% on the PlantVillage public dataset. This model operates with only 25.14 million parameters, a computational load of 3.762 GFLOPs, and an inference time of 7.56 ms. Testing on a self-built in-field complex scene dataset comprising 10,441 images revealed that ConvTransNet-S achieved an accuracy of 88.53%, which represents improvements of 14.22%, 2.75%, and 0.34% over EfficientNetV2, Vision Transformer, and Swin Transformer, respectively. Furthermore, the ConvTransNet-S model achieved up to 14.22% higher disease recognition accuracy under complex background conditions while reducing the parameter count by 46.8%. This confirms that its unique multi-scale feature mechanism can effectively distinguish disease from background features, providing a novel technical approach for disease diagnosis in complex agricultural scenarios and demonstrating significant application value for intelligent agricultural management. Full article

LiDAR point clouds, as direct carriers of 3D spatial information, comprehensively record the geometric features and spatial topological relationships of object surfaces, providing intelligent systems with rich 3D scene representation capability. However, current point cloud semantic segmentation methods primarily extract features through operations such as convolution and pooling, yet fail to adequately consider sparse features that significantly influence the final results of point cloud-based scene perception, resulting in insufficient feature representation capability. To address these problems, a sparse feature dynamic graph convolutional neural network, abbreviated as SFDGNet, is constructed in this paper for LiDAR point clouds of complex scenes. In the context of this paper, sparse features refer to feature representations in which only a small number of activation units or channels exhibit significant responses during the forward pass of the model. First, a sparse feature regularization method was used to motivate the network model to learn the sparsified feature weight matrix. Next, a split edge convolution module, abbreviated as SEConv, was designed to extract the local features of the point cloud from multiple neighborhoods by dividing the input feature channels, and to effectively learn sparse features to avoid feature redundancy. Finally, a multi-neighborhood feature fusion strategy was developed that combines the attention mechanism to fuse the local features of different neighborhoods and obtain global features with fine-grained information. Taking S3DIS and ScanNet v2 datasets, we evaluated the feasibility and effectiveness of SFDGNet by comparing it with six typical semantic segmentation models. Compared with the benchmark model DGCNN, SFDGNet improved overall accuracy $\left(OA\right)$, mean accuracy $\left(mAcc\right)$, mean intersection over union $\left(mIoU\right)$, and $sparsity$ by $1.8\%$, $3.7\%, 3.5\%$, and $85.5\%$ on the S3DIS dataset, respectively. The $mIoU$ on the ScanNet v2 validation set, $mIoU$ on the test set, and $sparsity$ were improved by $3.2\%, 7.0\%$, and $54.5\%$, respectively. Full article

Agricultural green production (AGP) is a key strategy for ensuring stable and sustainable grain production in developing countries. However, from the perspective of technology acquisition, research on farmers’ willingness to adopt AGP remains limited. Based on this, a survey was conducted on 862 households in major grain-producing counties in the Huang Huai Hai Plain of China with a reliable and effective response rate of 97.44%. The aim was to employ Probit and mediation models to empirically analyze the direct impacts of green perception benefits and environmental regulation intensity on farmers’ AGP willingness, and further examine the intrinsic mechanisms of technology acquisition. The results demonstrated that both green perception benefits and environmental regulation intensity significantly enhanced farmers’ willingness to engage in AGP, with green perception benefits having a greater influence. Among the two-dimensional variables, economic benefits had a stronger promoting effect than identity benefits, with a difference of 0.044 units, while subjective regulation intensity outperformed objective regulation intensity by 0.173 units. This suggested the need to strengthen the subjective impact of AGP policies in practice. Further analysis revealed that technology acquisition mediated 5.87% of the effect of green perception benefits on farmers’ AGP willingness, with acquisition evaluation having the greatest mediating effect, followed by acquisition quality and acquisition channels. However, although the overall environmental regulation intensity did not significantly impact farmers’ willingness to engage in AGP, its two-dimensional indicators played a mediating role to varying degrees. The findings in this study provide valuable empirical evidence for promoting AGP among grain producers, contributing to grain production security and the sustainable development of developing countries. Thus, implementing environmental regulatory policies tailored to local conditions, enhancing farmers’ economic awareness and sense of responsibility, and expanding farmers’ channels for technology acquisition are reasonable policy choices. Full article

Learning discriminative features between abnormal and normal instances is crucial for video anomaly detection within the multiple instance learning framework. Existing methods primarily focus on instances with the highest anomaly scores, neglecting the identification and differentiation of hard samples, leading to misjudgments and high false alarm rates. To address these challenges, we propose a dual triplet contrastive loss strategy. This approach employs dual memory units to extract four key feature categories: hard samples, negative samples, positive samples, and anchor samples. Contrastive loss is utilized to constrain the distance between hard samples and other samples, enabling accurate identification of hard samples and enhancing the discriminative ability of hard samples and abnormal features. Additionally, a multi-scale feature perception module is designed to capture feature information at different levels, while an adaptive global–local feature fusion module constructs complementary feature enhancement through feature fusion. Experimental results demonstrate the effectiveness of our method, achieving AUC scores of 87.16% on the UCF-Crime dataset and AP scores of 83.47% on the XD-Violence dataset. Full article

In this study, we introduce an Unmanned Aerial Vehicle (UAV) centric visual semantic simultaneous localization and mapping (SLAM) framework that integrates RGB–D cameras, inertial measurement units (IMUs), and a 5G–enabled remote interaction module. Our system addresses three critical limitations in existing approaches: (1) Distance constraints in remote operations; (2) Static map assumptions in dynamic environments; and (3) High–dimensional perception requirements for UAV–based applications. By combining YOLO–based object detection with epipolar–constraint-based dynamic feature removal, our method achieves real-time semantic mapping while rejecting motion artifacts. The framework further incorporates a dual–channel communication architecture to enable seamless human–in–the–loop control over UAV–Unmanned Ground Vehicle (UGV) teams in large–scale scenarios. Experimental validation across indoor and outdoor environments indicates that the system can achieve a detection rate of up to 75 frames per second (FPS) on an NVIDIA Jetson AGX Xavier using YOLO–FASTEST, ensuring the rapid identification of dynamic objects. In dynamic scenarios, the localization accuracy attains an average absolute pose error (APE) of 0.1275 m. This outperforms state–of–the–art methods like Dynamic–VINS (0.211 m) and ORB–SLAM3 (0.148 m) on the EuRoC MAV Dataset. The dual-channel communication architecture (Web Real–Time Communication (WebRTC) for video and Message Queuing Telemetry Transport (MQTT) for telemetry) reduces bandwidth consumption by 65% compared to traditional TCP–based protocols. Moreover, our hybrid dynamic feature filtering can reject 89% of dynamic features in occluded scenarios, guaranteeing accurate mapping in complex environments. Our framework represents a significant advancement in enabling intelligent UAVs/UGVs to navigate and interact in complex, dynamic environments, offering real-time semantic understanding and accurate localization. Full article