Search Results (4,395)

Object detection is an essential component of autonomous driving, unmanned aerial vehicle (UAV) reconnaissance, and other domains. It equips drones and vehicles with the capability to perceive and comprehend their surrounding environment, making it a crucial technology for achieving safe and reliable autonomous driving as well as UAV spot reconnaissance. This paper proposes an end-to-end, high-precision, multi-scale real-time detection algorithm called MRT-YOLO based on YOLOv8. Firstly, in the feature downsampling process of the backbone network, we extend the channel depth to enhance the model’s learning capability for fine-grained features and thereby improve its performance in retaining feature information. Secondly, we enhance the cross-stage partial layer version 2 (C2f) module in YOLOv8 by incorporating a channel self-attention mechanism within it, which optimizes performance through effective feature interaction and integration. Simultaneously, we also employ an improved bidirectional feature pyramid network (BiFPN) and introduce the proposed multi-scale feature learning (MFL) module to further enhance the model’s feature extraction ability. In this study, we fuse the feature maps (C2, C3, C4, and C5) from the backbone network to generate a new feature map C6, thus increasing cross-connections between low-level and high-level features. Lastly, a multi-scale small object detection structure is designed to enhance recognition sensitivity toward densely distributed small objects. The proposed algorithm’s effectiveness and superiority are demonstrated through experiments conducted on two datasets: VisDrone (UAV vision dataset) and BDD100K (automatic driving dataset). Full article

Deep coalbed methane (CBM) resources are abundant in China, and in the last few years, the country’s search for and extraction of CBM have intensified, progressively moving from shallow to deep strata and from high-rank coal to medium- and low-rank coal. On the other hand, little is known about the gas content features of deep coal reservoirs in the eastern Junggar Basin, especially with regard to the gas content and the factors that affect it. Based on data from CBM drilling, logging, and seismic surveys, this study focuses on the gas content of Baijiahai Uplift’s primary Jurassic coal seams through experiments on the microscopic components of coal, industrial analysis, isothermal adsorption, low-temperature CO₂, low-temperature N₂, and high-pressure mercury injection. A systematic investigation of the controlling factors, including the depth, thickness, and quality of the coal seam and pore structure; tectonics; and lithology and thickness of the roof, was conducted. The results indicate that the Xishanyao Formation in the Baijiahai Uplift usually has a larger gas content than that in the Badaowan Formation, with the Xishanyao Formation showing that free gas and adsorbed gas coexist, while the Badaowan Formation primarily consists of adsorbed gas. The coal seams in the Baijiahai Uplift are generally deep and thick, and the coal samples from the Xishanyao and Badawan formations have a high vitrinite content, which contributes to their strong gas generation capacity. Additionally, low moisture and ash contents enhance the adsorption capacity of the coal seams, facilitating the storage of CBM. The pore-specific surface area of the coal samples is primarily provided by micropores, which is beneficial for CBM adsorption. Furthermore, a fault connecting the Carboniferous and Permian systems (C-P) developed in the northeastern part of the Baijiahai Uplift allows gas to migrate into the Xishanyao and Badaowan formations, resulting in a higher gas content in the coal seams. The roof lithology is predominantly mudstone with significant thickness, effectively reducing the dissipation of coalbed methane and promoting its accumulation. Full article

On 18 December 2023, a 6.2-magnitude earthquake struck Jishishan, affecting multiple counties and cities in Gansu and Qinghai Provinces. The seismic intensity of the meizoseismal area was VIII, resulting in extensive structural damage and building collapses. A damage assessment was conducted of the epicenter and surrounding high-intensity zones. To understand the typical structures and characteristics of the buildings that were damaged in these high-intensity zones, this study summarizes the characteristics of the damage to typical rural houses, compares the damage of the rural houses across different sites, and analyzes the causes behind these variations. The findings of the study indicate the following: (1) Timber and some brick–timber structures, due to their age, insufficient material strength, and lack of adequate connections between parts of the building, primarily experienced severe damage or total collapse, characterized by through-wall cracks, partial collapses, or complete collapses. (2) Brick–concrete structures predominantly suffered moderate to severe damage due to factors such as improper layout, uneven façades, and inadequate or incomplete seismic measures. The observed damage included significant wall cracks and extensive damage to two-story buildings. (3) Frame structures, mainly used for public facilities like schools, hospitals, and health centers, exhibited strong integrity and excellent seismic performance, resulting in minimal to no damage, with damage largely confined to non-load-bearing components. (4) The amplification effects of seismic waves in thick loess basin areas, slope sites, and the hanging wall effect of faults exacerbated structural damage to rural houses located in certain villages within the high-intensity areas. The results of this study can serve as a reference for post-disaster reconstruction and seismic retrofitting of buildings and contribute positively to enhancing the disaster resilience of rural housing. Full article

Data in-transit from an at-rest state can be securely transmitted and managed within a network. Background: This work covers the design and simulation of an Enhanced Network Topology (ENT) with multiple components that connects multiple locations of an imaginary organisation structure. The components of the network locations are mix-vendor components. The focus is on how classless IP address allocation, routing protocols, hierarchical network topology, and the updated Transmission Control Protocol/Internet Protocol (TCP/IP) model are put together to enhance performance and security. The simulation is performed using Cisco Packet Tracer where the packet transfer and connections within the network are examined. Methods: The Variable Length Subnet Mask (VLSM) approach is applied to a network design to secure data and information. We provided and detailed the implementation of subnetting, routing protocols, the updated TCP/IP model, and simulation within Cisco Packet Tracer. Our paper demonstrates the applicability of a single IP address range (0-255) where only the fourth octet changes to serve to secure information across networks through creating subnets. Results: The results of the simulation are further analysed; the security protocols are summarised. Conclusions: Our work has potential to be applied to Supervisory Control and Data Acquisition (SCADA) networks, Internet of Things (IoT) and Cloud networks; a useful resource for academia and industry professionals. Full article

Emotional intelligence significantly influences various aspects of teachers’ professional and personal lives, notably affecting preschoolers’ social skills and emotional development during formative years. This study utilizes a network analysis approach to explore the complex relationships among four components of emotional intelligence: emotional labor, emotional regulation, professional well-being, and professional identity. Participants included 2069 frontline Chinese teachers (34 males, 2035 females; M = 28.64, SD = 5.98; M years of teaching = 6.88, SD = 5.29) with no leadership roles, categorized into three stages of their careers based on years of teaching experience: novice (0–3 years; n = 612), advanced beginners (4–6 years; n = 537), and competent (7–40 years; n = 920). Findings revealed that joy of teaching, role value, and professional value were identified as the most critical elements within the emotional state network of early childhood education teachers. The strongest connections in teachers’ emotional networks were found between school connectedness and joy of teaching (r = 0.474), surface acting behavior and natural acting behavior (r = 0.419), and professional value and professional behavior (r = 0.372). Furthermore, teachers across different career stages exhibited similar characteristics and intrinsic connections among emotional state components. These findings deepen our understanding of the emotional state networks of ECE teachers, highlighting shared features and interconnected mechanisms, and suggest that enhancing teachers’ emotional intelligence through targeted professional development can improve both teacher well-being and preschoolers’ social–emotional outcomes. Policies that foster strong school connectedness and reduce emotional labor are key to promoting sustained joy in teaching, particularly for novice and advanced beginner teachers. Full article

We propose a novel architecture, Transformer Dil-DenseUNet, designed to address the challenges of accurately segmenting stroke lesions in MRI images. Precise segmentation is essential for diagnosing and treating stroke patients, as it provides critical spatial insights into the affected brain regions and the extent of damage. Traditional manual segmentation is labor-intensive and error-prone, highlighting the need for automated solutions. Our Transformer Dil-DenseUNet combines DenseNet, dilated convolutions, and Transformer blocks, each contributing unique strengths to enhance segmentation accuracy. The DenseNet component captures fine-grained details and global features by leveraging dense connections, improving both precision and feature reuse. The dilated convolutional blocks, placed before each DenseNet module, expand the receptive field, capturing broader contextual information essential for accurate segmentation. Additionally, the Transformer blocks within our architecture address CNN limitations in capturing long-range dependencies by modeling complex spatial relationships through multi-head self-attention mechanisms. We assess our model’s performance on the Ischemic Stroke Lesion Segmentation Challenge 2015 (SISS 2015) and ISLES 2022 datasets. In the testing phase, the model achieves a Dice coefficient of 0.80 ± 0.30 on SISS 2015 and 0.81 ± 0.33 on ISLES 2022, surpassing the current state-of-the-art results on these datasets. Full article

Background: The enhancer–promoter interaction (EPI) is a critical component of gene regulatory networks, playing a significant role in understanding the complexity of gene expression. Traditional EPI prediction methods focus on one-to-one interactions, neglecting more complex one-to-many and many-to-many patterns. To address this gap, we utilize graph neural networks to comprehensively explore all interaction patterns between enhancers and promoters, capturing complex regulatory relationships for more accurate predictions. Methods: In this study, we introduce a novel EPI prediction framework, GATv2EPI, based on dynamic graph attention neural networks. GATv2EPI leverages epigenetic information from enhancers, promoters, and their surrounding regions and organizes interactions into a network to comprehensively explore complex EPI regulatory patterns, including one-to-one, one-to-many, and many-to-many relationships. To avoid overfitting and ensure diverse data representation, we implemented a connectivity-based sampling method for dataset partitioning, which constructs graphs for each chromosome and assigns entire connected subgraphs to training or test sets, thereby preventing information leakage and ensuring comprehensive chromosomal representation. Results: In experiments conducted on four cell lines—NHEK, IMR90, HMEC, and K562—GATv2EPI demonstrated superior EPI recognition accuracy compared to existing similar methods, with a training time improvement of 95.29% over TransEPI. Conclusions: GATv2EPI enhances EPI prediction accuracy by capturing complex topological structure information from gene regulatory networks through graph neural networks. Additionally, our results emphasize the importance of epigenetic features surrounding enhancers and promoters in EPI prediction. Full article

Retinal vessel segmentation is crucial for diagnosing and monitoring ophthalmic and systemic diseases. Optical Coherence Tomography Angiography (OCTA) enables detailed imaging of the retinal microvasculature, but existing methods for OCTA segmentation face significant limitations, such as susceptibility to noise, difficulty in handling class imbalance, and challenges in accurately segmenting complex vascular morphologies. In this study, we propose VDMNet, a novel segmentation network designed to overcome these challenges by integrating several advanced components. Firstly, we introduce the Fast Multi-Head Self-Attention (FastMHSA) module to effectively capture both global and local features, enhancing the network’s robustness against complex backgrounds and pathological interference. Secondly, the Vessel Dynamic Convolution (VDConv) module is designed to dynamically adapt to curved and crossing vessels, thereby improving the segmentation of complex morphologies. Furthermore, we employ the Multi-Scale Fusion (MSF) mechanism to aggregate features across multiple scales, enhancing the detection of fine vessels while maintaining vascular continuity. Finally, we propose Weighted Asymmetric Focal Tversky Loss (WAFT Loss) to address class imbalance issues, focusing on the accurate segmentation of small and difficult-to-detect vessels. The proposed framework was evaluated on the publicly available ROSE-1 and OCTA-3M datasets. Experimental results demonstrated that our model effectively preserved the edge information of tiny vessels and achieved state-of-the-art performance in retinal vessel segmentation across several evaluation metrics. These improvements highlight VDMNet’s superior ability to capture both fine vascular details and overall vessel connectivity, making it a robust solution for retinal vessel segmentation. Full article

A microgrid (MG) is a unique area of a power distribution network that combines distributed generators (conventional as well as renewable power sources) and energy storage systems. Due to the integration of renewable generation sources, microgrids have become more unpredictable. MGs can operate in two different modes, namely, grid-connected and islanded modes. MGs face various challenges of voltage variations, frequency deviations, harmonics, unbalances, etc., due to the uncertain behavior of renewable sources. To study the impact of these issues, it is necessary to analyze the behavior of the MG system under normal and abnormal operating conditions. Two different tools are used for the analysis of microgrids under normal and abnormal conditions, namely, power flow and short-circuit analysis, respectively. Power flow analysis is used to determine the voltages, currents, and real and reactive power flow in the MG system under normal operating conditions. Short-circuit analysis is carried out to analyze the behavior of MGs under faulty conditions. In this paper, a review of power flow and short-circuit analysis algorithms for MG systems under two different modes of operation, grid-connected and islanded, is presented. This paper also presents a comparison of various power flow as well as short-circuit analysis techniques for MGs in tabular form. The modeling of different components of MGs is also discussed in this paper. Full article

The failure mechanism of square lithium iron phosphate battery cells under vibration conditions was investigated in this study, elucidating the impact of vibration on their internal structure and safety performance using high-resolution industrial CT scanning technology. Various vibration states, including sinusoidal, random, and classical impact modes, were tested to simulate real-world usage scenarios. The findings demonstrate that different vibration conditions exert varying degrees of influence on the battery cells. Despite experiencing slight deformation and displacement after exposure to vibrations, their overall performance remains stable, with no significant safety hazards detected. Moreover, it was observed that while the side gap increases due to the partial absorption of impact load by both the battery cells and connection components, the bottom gap remains unchanged. This study holds immense significance in enhancing electric vehicle safety and reliability, while providing a scientific foundation for future optimization designs of lithium iron phosphate batteries. Full article

Integrating remote monitoring systems is crucial in the ever-changing field of data center management to enhance performance and guarantee reliability. This paper outlines a comprehensive strategy for monitoring remote servers by utilizing agents that establish connections to the RedFish API (Application Programming Interface) and vSphere hypervisor API. Our solution uses the RedFish standard to provide secure and standardized management of hardware components in diverse server environments. This improves interoperability and scalability. Simultaneously, the vSphere agent enables monitoring and hardware administration in vSphere-based virtualized environments, offering crucial insights into the state of the underlying hardware. This system, which employs two agents, simplifies the management of servers and seamlessly integrates with current data center infrastructures, enhancing efficiency. The policy-based alerting system built on top of these agents offers many capabilities based on both agents leveraging their alerting systems. This, in turn, can improve the capabilities of next-generation data centers. Full article

Vaginal intraepithelial neoplasia (VAIN), linked to HPV infection, is a condition that is often overlooked during colposcopy, especially in the vaginal vault area, as clinicians tend to focus more on cervical lesions. This oversight can lead to missed or delayed diagnosis and treatment for patients with VAIN. Timely and accurate classification of VAIN plays a crucial role in the evaluation of vaginal lesions and the formulation of effective diagnostic approaches. The challenge is the high similarity between different classes and the low variability in the same class in colposcopic images, which can affect the accuracy, precision, and recall rates, depending on the image quality and the clinician’s experience. In this study, a dual-branch lesion-aware residual network (DLRNet), designed for small medical sample sizes, is introduced, which classifies vaginal lesions by examining the relationship between cervical and vaginal lesions. The DLRNet model includes four main components: a lesion localization module, a dual-branch classification module, an attention-guidance module, and a pretrained network module. The dual-branch classification module combines the original images with segmentation maps obtained from the lesion localization module using a pretrained ResNet network to fine-tune parameters at different levels, explore lesion-specific features from both global and local perspectives, and facilitate layered interactions. The feature guidance module focuses the local branch network on vaginal-specific features by using spatial and channel attention mechanisms. The final integration involves a shared feature extraction module and independent fully connected layers, which represent and merge the dual-branch inputs. The weighted fusion method effectively integrates multiple inputs, enhancing the discriminative and generalization capabilities of the model. Classification experiments on 1142 collected colposcopic images demonstrate that this method raises the existing classification levels, achieving the classification of VAIN into three lesion grades, thus providing a valuable tool for the early screening of vaginal diseases. Full article

With the growth in road transport volume and increasingly stringent environmental regulations, the use of lightweight dump trucks not only reduces fuel consumption but also enhances transport efficiency, aligning with the principles of green development. It has now become a key focus in the field of heavy-duty vehicle research. The carriage is located at the rear of the dump truck, connected to the chassis, and serves as the box for carrying cargo, making its strength and durability crucial. As one of the important components of heavy-duty vehicles, the carriage accounts for 15% to 25% of the total vehicle weight, and its weight reduction efficiency is significantly higher than that of other vehicle systems. This paper presents a prefabricated carriage structure based on basalt fiber composite panels combined with a metal frame, achieving the lightweight design of the carriage while meeting the stringent requirements for high load-bearing capacity and strength in heavy-duty vehicles, and significantly improving assembly and production efficiency. Given the complex working environment and diverse loading demands of heavy vehicles, this study incorporates real operating conditions of dump trucks, utilizing theoretical calculations and design analyses to construct finite element models for various scenarios, followed by detailed numerical simulations in ABAQUS (2023). Additionally, a bending–shear test of the side panel was designed and conducted to validate the accuracy of the finite element model, with comparative analysis performed between simulation results and experimental data, effectively assessing the safety and reliability of this lightweight composite carriage structure. The results indicate that the designed carriage not only meets the strength, stiffness, and impact resistance requirements of current heavy-duty carriages but also significantly reduces the carriage weight. This research provides scientific reference and engineering value for the application of composite materials in the lightweight design and structural optimization of dump trucks. Full article

As a new development direction in exoskeleton research, wearable flexible exoskeleton systems are highly favored for their freedom of movement, flexibility, lightweight design, and comfortable wearability. These systems are gradually becoming the preferred choice for rehabilitation therapy, and enhancing physical performance. In this thesis, based on existing research in wearable flexible exoskeletons, we aim to design a lightweight wearable upper limb rehabilitation exoskeleton that meets the needs of stroke patients with a high likelihood of upper limb impairment. The system should provide sufficient flexibility for comfortable and convenient use while minimizing the weight to reduce the user’s burden during wear. Our proposed lightweight wearable flexible exoskeleton assists users in achieving rehabilitation exercises for both the shoulder (external/internal rotation) and forearm (flexion/extension) movements. The system consists of a flexible fabric section connecting the torso–shoulder–upper arm, a flexible fabric section for the forearm, and a back-mounted actuation device. The fabric sections primarily consist of elastic textile materials with a few rigid components. Emphasizing lightweight design, we strive to minimize the exoskeleton’s weight, ensuring optimal user comfort. The actuation device connects to the fabric sections via tensioned wires, driven by a motor to induce arm movement during rehabilitation exercises. To enhance safety and prevent secondary upper limb injuries due to exoskeleton malfunction, we incorporate a physical limiter retricting the exoskeleton’s range of motion. Additionally, we include tension-adjustment mechanisms and cushioning springs to improve the feasibility of this wearable flexible exoskeleton. After completing the structural design, this paper conducted a basic static and kinematic analysis of the exoskeleton system to provide theoretical support. Additionally, the feasibility and effectiveness of the exoskeleton system design were verified through dynamic simulations. Full article

To realize abnormal-sound diagnosis in hydroelectric generating units, this study proposes a method based on continuous wavelet transform (CWT) and Transfer Learning (TL). A denoising algorithm utilizing spectral noise-gate technology is proposed to enhance fault characteristics in hydroelectric units. Subsequently, Continuous Wavelet Transform is applied to obtain frequency components, and the results are converted into a series of pseudo-color images to highlight information differences. A transfer model is subsequently developed for feature extraction, utilizing simplified fully connected layers to reduce modeling costs. The study optimizes key parameters during the signal-processing stage and achieves an improved parameter-setting scheme. Acoustic signals corresponding to four different fault states and a normal state are collected from a Kaplan hydroelectric generating unit in a hydropower station. The signal diagnosis accuracy rates before filtering are 84.83% and 95.14%. These rates significantly improved to 98.88% and 98.06%, respectively, demonstrating the effectiveness of the noise-reduction process. To demonstrate the superiority of the improved model in this work, a series of classic deep-learning models, including AlexNet, Resnet18, and MobileNetV3, are used for comparative analysis. The proposed method can effectively diagnose faults in Kaplan hydroelectric generating units with a high accuracy, which is crucial for the daily monitoring and maintenance of these units. Full article