Search Results (65,237)

The growing concern over pollution from vehicle exhausts has underscored the need for effective detection of black smoke emissions from motor vehicles. We believe that the optimal approach for the detection of black smoke is to leverage existing roadway CCTV cameras. To facilitate this, we have collected and publicly released a black smoke detection dataset sourced from roadway CCTV cameras in China. After analyzing the existing detection methods on this dataset, we found that they have subpar performance. As a result, we decided to develop a novel detection model that focuses on temporal information. This model utilizes the continuous nature of CCTV video feeds rather than treating footage as isolated images. Specifically, our model incorporates a 3D convolution module to capture short-term dynamic and semantic features in consecutive black smoke video frames. Additionally, a cross-scale feature fusion module is employed to integrate features across different scales, and a self-attention mechanism is used to enhance the detection of black smoke while minimizing the impact of noise, such as occlusions and shadows. The validation of our dataset demonstrated that our model achieves a detection accuracy of 89.42%,showing around 3% improvement over existing methods. This offers a novel and effective solution for black smoke detection in real-world applications. Full article

The Pendjari Biosphere Reserve is one of the protected areas of Benin where biodiversity conservation policies intertwine with the economic development of local populations. It is located in the Atacora region in northern Benin, which has a high prevalence of poverty and food insecurity among households. Agriculture and livestock farming are the primary activities of the local communities in the villages surrounding the reserve. However, wild animals sometimes cause damage to people’s fields or livestock. To deal with the damage caused by wild animals, local populations have developed several mitigation measures that may not be effective, leading them into a vulnerable situation. Vulnerability is often associated with the impacts of natural disasters and their management, anticipation, and recovery. In the context of human–wildlife conflict, vulnerability refers to the level of risk farmers face from issues such as crop raiding, livestock depredation, and human injury caused by wildlife, as well as farmers’ ability to cope with such damage. To assess the vulnerability of households, we used the Livelihood Vulnerability Index (LVI). Data were collected from July to December 2019 through questionnaires and interviews. We surveyed 320 households to collect data on their socio-demographics, livelihoods, social networks, natural capital, food and water security, and the incidence and severity of human–wildlife conflicts. The results showed that farmers around the Pendjari Biosphere Reserve are highly sensitive to human–wildlife conflicts, with a low adaptive capacity, revealing their vulnerability. More precisely, farmers are vulnerable in terms of major components of the LVI such as water, food, social networks, and livelihoods. Conservation policies are expected to pay more attention to local populations’ vulnerability to human–wildlife conflicts in order to improve their tolerance towards wildlife and guarantee the success of conservation efforts. Full article

Parkinson’s disease (PD) patients are impaired in word production when the word has to be selected among competing alternatives requiring higher attentional resources. In PD, word selection processes are correlated with the structural integrity of the inferior frontal gyrus, which is critical for response selection, and the uncinate fasciculus, which is necessary for processing lexical information. In early PD, we investigated the role of the main cognitive large-scale networks, namely the salience network (SN), the central executive networks (CENs), and the default mode network (DMN), in word selection. Eighteen PD patients and sixteen healthy controls were required to derive nouns from verbs or generate verbs from nouns. Participants also underwent a resting-state functional MRI. Functional connectivity (FC) was examined using independent component analysis. Functional seeds for the SN, CENs, and DMN were defined as spheres, centered at the local activation maximum. Correlations were calculated between the FC of each functional seed and word production. A significant association between SN connectivity and task performance and, with less evidence, between CEN connectivity and the task requiring selection among a larger number of competitors, emerged in the PD group. These findings suggest the involvement of the SN and CEN in word selection in early PD, supporting the hypothesis of impaired executive control. Full article

Stock index fluctuations are characterized by high noise and their accurate prediction is extremely challenging. To address this challenge, this study proposes a spatial–temporal–bidirectional long short-term memory (STBL) model, incorporating spatiotemporal attention mechanisms. The model enhances the analysis of temporal dependencies between data by introducing graph attention networks with multi-hop neighbor nodes while incorporating the temporal attention mechanism of long short-term memory (LSTM) to effectively address the potential interdependencies in the data structure. In addition, by assigning different learning weights to different neighbor nodes, the model can better integrate the correlation between node features. To verify the accuracy of the proposed model, this study utilized the closing prices of the Hong Kong Hang Seng Index (HSI) from 31 December 1986 to 31 December 2023 for analysis. By comparing it with nine other forecasting models, the experimental results show that the STBL model achieves more accurate predictions of the closing prices for short-term, medium-term, and long-term forecasts of the stock index. Full article

The application of the resilience concept within socioecological systems has recently received much attention. Assessing the characteristics of cocoa agroecosystems in the dry and moist semi-deciduous ecological zones has become critical for resilience analysis in this era of climate change and the constant shrinking of cocoa suitability areas. Previous studies have used one of the dimensions of resilience to analyse complex adaptive systems, excluding critical factors and variables. This study applied a multi-criteria decision-making process, the Analytic Hierarchy Process (AHP) that accommodates the three dimensions of resilience, i.e., buffer capacity, adaptive capacity and self-organisation. The AHP is a multi-criteria decision-making tool that proceeds with the design of a hierarchy system for the goal, criteria, attributes and variables. Selected cocoa farmers were assigned weights related to criteria, attributes and variables in a comparison matrix. The resilience of the cocoa agroecosystems in Offinso Municipal and Adansi North Districts was 2.75 ± 0.06 (mean ± SD) and 3.23 ± 0.10 (mean ± SD), respectively. Buffer capacity contributed the highest proportion (44.3%) in the Offinso Municipal District, followed by adaptive capacity (38.7%) and self-organisation (17%). A similar trend was recorded for the Adansi North District: buffer capacity (42.9%), adaptive capacity (42.9%) and self-organisation (14.3%). Across the two study areas, shade trees, crop diversification, soil quality, cocoa variety, farm size, farm age, alternative livelihood, annual income and co-operative membership contributed prominently to the construction of cocoa agroecosystem resilience. The assessment of agroecosystem resilience is location-specific, and the study provides a simplified methodology for evaluating resilience. The paper aims to understand the importance of the components of the cocoa agroecosystem, and a simplified methodology for evaluating its resilience to perturbations. It presents a conceptual and methodological framework for the analysis and measurement of agroecosystem resilience in a participatory manner. Full article

Hexapod robots have gained significant attention due to their potential applications in complex terrains and dynamic environments. However, traditional inverse kinematics approaches often face challenges in meeting the precision required for adaptive omnidirectional movement. This work introduces a novel approach to addressing these challenges through the Directed Angular Restitution (DAR) method. The DAR method offers significant innovation by simplifying the calculation of rotational transformations necessary for aligning vectors across different planes, thus enhancing control, stability, and accuracy in robotic applications. Unlike conventional methods, the DAR method extends the range of trigonometric functions and incorporates spin functions to ensure continuous and smooth trajectory tracking. This innovative approach has been rigorously tested on a hexapod robot model, demonstrating superior performance in movement precision and stability. The results confirm that the DAR method provides a robust and scalable solution for the inverse kinematics of hexapod robots, making it a critical advancement for applications in robotics and automation where precise control and adaptability are paramount. Full article

Water electrolysis has been recognized as a promising technology that can convert renewable energy into hydrogen for storage and utilization. The superior activity and low cost of catalysis are key factors in promoting the industrialization of water electrolysis. Single-atom catalysts (SACs) have attracted attention due to their ultra-high atomic utilization, clear structure, and highest hydrogen evolution reaction (HER) performance. In addition, the performance and stability of single-atom (SA) substrates are crucial, and various two-dimensional (2D) nanomaterial supports have become promising foundations for SA due to their unique exposed surfaces, diverse elemental compositions, and flexible electronic structures, to drive single atoms to reach performance limits. The SA supported by 2D nanomaterials exhibits various electronic interactions and synergistic effects, all of which need to be comprehensively summarized. This article aims to organize and discuss the progress of 2D nanomaterial single-atom supports in enhancing HER, including common and widely used synthesis methods, advanced characterization techniques, different types of 2D supports, and the correlation between structural hydrogen evolution performance. Finally, the latest understanding of 2D nanomaterial supports was proposed. Full article

The most prevalent form of bladder cancer is urothelial carcinoma, characterized by a high recurrence rate and substantial lifetime treatment costs for patients. Grading is a prime factor for patient risk stratification, although it suffers from inconsistencies and variations among pathologists. Moreover, absence of annotations in medical imaging renders it difficult to train deep learning models. To address these challenges, we introduce a pipeline designed for bladder cancer grading using histological slides. First, it extracts urothelium tissue tiles at different magnification levels, employing a convolutional neural network for processing for feature extraction. Then, it engages in the slide-level prediction process. It employs a nested multiple-instance learning approach with attention to predict the grade. To distinguish different levels of malignancy within specific regions of the slide, we include the origins of the tiles in our analysis. The attention scores at region level are shown to correlate with verified high-grade regions, giving some explainability to the model. Clinical evaluations demonstrate that our model consistently outperforms previous state-of-the-art methods, achieving an F1 score of 0.85. Full article

Brain tumor detection and categorization of its subtypes are essential for early diagnosis and improving patient outcomes. This research presents a cutting-edge approach that employs advanced data augmentation and deep learning methodologies for brain tumor classification. For this work, a dataset of 6982 MRI images from the IEEE Data Port was considered, in which a total of 5712 images of four classes (1321 glioma, 1339 meningioma, 1595 no tumor, and 1457 pituitary) were used in the training set and a total of 1270 images of the same four classes were used in the testing set. A Wasserstein Generative Adversarial Network was implemented to generate synthetic images to address class imbalance, resulting in a balanced and consistent dataset. A comparison was conducted between various data augmentation metholodogies demonstrating that Wasserstein Generative Adversarial Network-augmented results perform excellently over traditional augmentation (such as rotation, shift, zoom, etc.) and no augmentation. Additionally, a Gaussian filter and normalization were applied during preprocessing to reduce noise, highlighting its superior accuracy and edge preservation by comparing its performance to Median and Bilateral filters. The classifier model combines parallel feature extraction from modified InceptionV3 and VGG19 followed by custom attention mechanisms for effectively capturing the characteristics of each tumor type. The model was trained for 64 epochs using model checkpoints to save the best-performing model based on validation accuracy and learning rate adjustments. The model achieved a 99.61% accuracy rate on the testing set, with precision, recall, AUC, and loss of 0.9960, 0.9960, 0.0153, and 0.9999, respectively. The proposed architecture’s explainability has been enhanced by t-SNE plots, which show unique tumor clusters, and Grad-CAM representations, which highlight crucial areas in MRI scans. This research showcases an explainable and robust approach for correctly classifying four brain tumor types, combining WGAN-augmented data with advanced deep learning models in feature extraction. The framework effectively manages class imbalance and integrates a custom attention mechanism, outperforming other models, thereby improving diagnostic accuracy and reliability in clinical settings. Full article

High-strength engineered cementitious composites (HS-ECCs) have garnered significant attention for their superior mechanical properties and ductility. However, their high autogenous shrinkage, caused by a low water-to-binder ratio, high cementitious content, and lack of coarse aggregate, often results in early-age cracking, limiting their broader use in civil engineering. Incorporating iron sand in HS-ECCs has enhanced their mechanical properties, reduced the carbon footprint, and moderately decreased shrinkage strain compared to traditional silica sand; however, the shrinkage strain remains substantial. This study aims to reduce the autogenous shrinkage of HS-ECCs further by incorporating united expanding admixtures (UEAs)—calcium oxide-based (CEA) and magnesium oxide-based (MEA) expansive agents—in varying amounts (3% to 10% by mass of cement). This study also examines the impact of these admixtures on the workability and mechanical properties of HS-ECCs. The results show that increasing the UEA content significantly reduces autogenous shrinkage strain, achieving a 40.66% reduction at 10% UEA, from 1007.31 με to 647.18 με. While higher UEA content decreases workability, as indicated by lower fluidity and penetration depth, the compressive strength remains largely unaffected. The tensile strength peaks at 12.38 MPa with 3% UEA but declines at higher contents, with higher UEA content effectively minimizing crack formation. The novelty of this research lies in the combined use of waste iron sand and UEA, optimizing the balance between workability, mechanical properties, and autogenous shrinkage reduction in HS-ECCs. These findings support the broader application of HS-ECCs in civil engineering projects requiring high mechanical properties and low shrinkage. Full article

As an essential component of the global economic crop, cotton is highly susceptible to the impact of diseases on its yield and quality. In recent years, artificial intelligence technology has been widely used in cotton crop disease recognition, but in complex backgrounds, existing technologies have certain limitations in accuracy and efficiency. To overcome these challenges, this study proposes an innovative cotton disease recognition method called CANnet, and we independently collected and constructed an image dataset containing multiple cotton diseases. Firstly, we introduced the innovatively designed Reception Field Space Channel (RFSC) module to replace traditional convolution kernels. This module combines dynamic receptive field features with traditional convolutional features to effectively utilize spatial channel attention, helping CANnet capture local and global features of images more comprehensively, thereby enhancing the expressive power of features. At the same time, the module also solves the problem of parameter sharing. To further optimize feature extraction and reduce the impact of spatial channel attention redundancy in the RFSC module, we connected a self-designed Precise Coordinate Attention (PCA) module after the RFSC module to achieve redundancy reduction. In the design of the classifier, CANnet abandoned the commonly used MLP in traditional models and instead adopted improved Kolmogorov Arnold Networks-s (KANs) for classification operations. KANs technology helps CANnet to more finely utilize extracted features for classification tasks through learnable activation functions. This is the first application of the KAN concept in crop disease recognition and has achieved excellent results. To comprehensively evaluate the performance of CANnet, we conducted extensive experiments on our cotton disease dataset and a publicly available cotton disease dataset. Numerous experimental results have shown that CANnet outperforms other advanced methods in the accuracy of cotton disease identification. Specifically, on the self-built dataset, the accuracy reached 96.3%; On the public dataset, the accuracy reached 98.6%. These results fully demonstrate the excellent performance of CANnet in cotton disease identification tasks. Full article

Sustainable development has become a corporate goal all over the world, and innovation as a crucial prerequisite for sustainable development has attracted much attention. This study investigates the relationship between the business environment and corporate innovation in Chinese A-share listed enterprises from 2017 to 2020. We use a complex indicator to measure the business environment and use multiple regression models to conduct the analysis. The findings suggest that a favorable business environment promotes corporate innovation by reducing financing constraints and environmental uncertainty. Compared to non-state-owned enterprises, the positive impact of the business environment on corporate innovation is enhanced in state-owned enterprises. Concentrated ownership enhances the positive impact of a favorable business environment on corporate innovation. Our study provides a new analytical perspective on the relationship between the business environment and corporate innovation in the context of China. Full article

To detect fundus diseases, for instance, diabetic retinopathy (DR) at an early stage, thereby providing timely intervention and treatment, a new diabetic retinopathy grading method based on a convolutional neural network is proposed. First, data cleaning and enhancement are conducted to improve the image quality and reduce unnecessary interference. Second, a new conditional generative adversarial network with a self-attention mechanism named SACGAN is proposed to augment the number of diabetic retinopathy fundus images, thereby addressing the problems of insufficient and imbalanced data samples. Next, an improved convolutional neural network named DRMC Net, which combines ResNeXt-50 with the channel attention mechanism and multi-branch convolutional residual module, is proposed to classify diabetic retinopathy. Finally, gradient-weighted class activation mapping (Grad-CAM) is utilized to prove the proposed model’s interpretability. The outcomes of the experiment illustrates that the proposed method has high accuracy, specificity, and sensitivity, with specific results of 92.3%, 92.5%, and 92.5%, respectively. Full article

Remote-sensing image captioning (RSIC) aims to generate descriptive sentences for ages by capturing both local and global semantic information. This task is challenging due to the diverse object types and varying scenes in ages. To address these challenges, we propose a positional-channel semantic fusion transformer (PCSFTr). The PCSFTr model employs scene classification to initially extract visual features and learn semantic information. A novel positional-channel multi-headed self-attention (PCMSA) block captures spatial and channel dependencies simultaneously, enriching the semantic information. The feature fusion (FF) module further enhances the understanding of semantic relationships. Experimental results show that PCSFTr significantly outperforms existing methods. Specifically, the BLEU-4 index reached 78.42% in UCM-caption, 54.42% in RSICD, and 69.01% in NWPU-captions. This research provides new insights into RSIC by offering a more comprehensive understanding of semantic information and relationships within images and improving the performance of image captioning models. Full article

Background/Objectives: Rett syndrome is a rare neurodevelopmental disorder that can severely affect motor functioning, particularly walking. Previous training programs proposed treadmills as tools to increase walking endurance of patients with Rett syndrome, but these trainings did not include virtual reality (VR). The aim of this study was to assess the feasibility of a short treadmill training coupled to VR in girls with Rett syndrome. Methods: Nine patients with Rett syndrome underwent a 3-day treadmill walking program performed in semi-immersive VR. During the training, the happiness index and performance metrics were collected. At the end of the training parents filled out the Suitability Evaluation Questionnaire (SEQ) and, when feasible, patients underwent a gait assessment. Results: All the subjects recruited performed the three GRAIL sessions and parents showed a good satisfaction and considered the integration of treadmill and VR a good possibility for future rehabilitative programs. Participants showed greater satisfaction in environments requiring walking and their attention increased during training sessions, hypothesizing the feasibility of longer trainings with treadmill and VR. Data collected from gait analysis provided insights, although preliminary, concerning differences in gait pattern amongst the recruited subjects. Conclusions: Despite the small sample size and limited training duration, the paper suggests that a walking training with a treadmill combined with VR can represent a new strategy for Rett rehabilitation. Full article