Marine debris poses a significant threat to marine ecosystems, necessitating efficient and accurate detection methods. Autonomous underwater vehicles (AUVs) offer a promising solution, but they require lightweight, real-time algorithms for debris detection. This paper introduces DRPI-DEIM, a novel lightweight debris detection model based on the DEIM framework, incorporating four architectural modules plus a distillation-based compact variant: an Information Integration Attention (IIA) mechanism for precise spatial positioning, a Progressive-Wavelet Transform Enhancement (PWTE) Module for addressing image degradation, a Dimension-Aware Diffusion Network (DADN) for enhanced multi-scale feature representation, and a RepGhost Efficient Layer Aggregation Network (RGELAN) for reduced computational cost. Evaluated on the Trash-ICRA19 dataset, DRPI-DEIM achieved an AP of 82.2 ± 0.2

Underwater object detection (UOD) plays a pivotal role in marine robotics, ecological monitoring, and environmental protection. However, existing deep learning-based detection methods face significant challenges in underwater scenarios, including coupled frequency-spatial distortions and insufficient integration of multi-scale object features caused by optical degradation. To address these limitations, we propose UHF-UOD, a novel underwater detection algorithm. The proposed framework incorporates three fundamental innovation modules: (1) Underwater Multi-Scale Feature Extraction (UMFE) module, which synergistically combines parallel deep convolutions with multi-scale kernels alongside spatial adaptive attention mechanisms, effectively expanding the receptive field while enhancing scale-adaptive feature extraction capabilities under varying degradation characteristics; (2) Frequency-Spatial Transformer Block (FSTB) integrates Fourier Transform-based Frequency Self-Attention (FSA), Multi-Scale Spatial Self-Attention (MSSA) and Convolutional Gated Linear Unit (CGLU) to address coupled frequency-spatial degradation comprehensively; (3) Hierarchical Scale-Aware Fusion Network (HSAFN), which captures long-distance dependencies through Scale-Aware Mamba (SAMamba) and is combined with the Adaptive Progressive Fusion Module (APFM) to enable cross-scale feature interaction. Experimental validation on four public datasets (UDD, UODD, DUO, RUOD) demonstrates that UHF-UOD achieves state-of-the-art performance in underwater object detection. This research offers a high-precision and high-efficiency solution for underwater object detection. The source code is available at https://github.com/EUOD/UHF-UOD.

With the swift progress of deep learning and its wide application in semantic segmentation, the effect of semantic segmentation has been significantly improved. However, how to achieve a reasonable compromise between accuracy, model size, and inference speed is crucial. In this paper, we propose a lightweight multi-scale asymmetric encoder–decoder network (LMANet) that is designed on the basis of an encoder–decoder structure. First, an optimized bottleneck module is used to extract features from different levels, and different receptive fields are applied to obtain effective information on different scales. Then, a channel-attention module and a feature-extraction module are introduced to constitute the residual structure, and different feature maps are connected by a feature-fusion module to effectively improve segmentation accuracy. Finally, a lightweight multi-scale decoder is designed to recover the image, and a spatial attention module is added to recover the spatial details effectively. This paper has verified the proposed method on the Cityscapes dataset and CamVid dataset and achieved mean intersection over union (mIoU) of 73.9% and 71.3% with the inference speeds of 111 FPS and 118 FPS, respectively, and the number of parameters is only 0.85 M.

针对水下退化图像细节模糊、对比度低和蓝绿色偏问题,提出了一种基于多尺度特征融合生成对抗网络的水下图像增强算法.算法以生成对抗网络为基本框架,结合传统白平衡算法和多尺度增强网络实现对水下退化图像的增强.通过改进的通道补偿白平衡算法矫正蓝绿色偏,并以卷积神经网络提取偏色校正后图像的特征;提取图像多尺度特征,结合提出的残差密集块将每一层的局部特征增强为捕获语义信息的全局特征,并与偏色校正图像的特征相融合;通过重建模块将融合特征重建为清晰图像,恢复图像的细节信息.实验结果表明,该算法增强的水下图像去雾效果较好且颜色更真实,有效改善了水下图像色偏和模糊的问题,在主观指标和客观指标上的实验结果均优于对比算法.

针对常规DV-Hop算法存在定位精确度偏低,难以满足高精度定位应用的需求等问题,提出一种基于自适应差分粒子群优化的DV-Hop定位算法.该算法首先利用节点间RSSI值实现跳数计算的精确化,然后引入跳距可信度提高平均跳距的计算精度,最后利用自适应差分粒子群优化算法来估计未知节点的位置.实验结果表明,在不同节点数量、通信半径以及锚节点数三种情况下,改进后算法的节点定位精确度相比于传统DV-hop定位算法分别提高了 45.3％、42.9％和 39.7％.

To address the problems of low monitoring area coverage rate and the long moving distance of nodes in the process of coverage optimization in wireless sensor networks (WSNs), a multi-strategy improved sparrow search algorithm for coverage optimization in a WSN (IM-DTSSA) is proposed. Firstly, Delaunay triangulation is used to locate the uncovered areas in the network and optimize the initial population of the IM-DTSSA algorithm, which can improve the convergence speed and search accuracy of the algorithm. Secondly, the quality and quantity of the explorer population in the sparrow search algorithm are optimized by the non-dominated sorting algorithm, which can improve the global search capability of the algorithm. Finally, a two-sample learning strategy is used to improve the follower position update formula and to improve the ability of the algorithm to jump out of the local optimum. Simulation results show that the coverage rate of the IM-DTSSA algorithm is increased by 6.74%, 5.04% and 3.42% compared to the three other algorithms. The average moving distance of nodes is reduced by 7.93 m, 3.97 m, and 3.09 m, respectively. The results mean that the IM-DTSSA algorithm can effectively balance the coverage rate of the target area and the moving distance of nodes.

In recent years, chest X-ray (CXR) imaging has become one of the significant tools to assist in the diagnosis and treatment of novel coronavirus pneumonia. However, CXR images have complex-shaped and changing lesion areas, which makes it difficult to identify novel coronavirus pneumonia from the images. To address this problem, a new deep learning network model (BoT-ViTNet) for automatic classification is designed in this study, which is constructed on the basis of ResNet50. First, we introduce multi-headed self-attention (MSA) to the last Bottleneck block of the first three stages in the ResNet50 to enhance the ability to model global information. Then, to further enhance the feature expression performance and the correlation between features, the TRT-ViT blocks, consisting of Transformer and Bottleneck, are used in the final stage of ResNet50, which improves the recognition of complex lesion regions in CXR images. Finally, the extracted features are delivered to the global average pooling layer for global spatial information integration in a concatenated way and used for classification. Experiments conducted on the COVID-19 Radiography database show that the classification accuracy, precision, sensitivity, specificity, and F1-score of the BoT-ViTNet model is 98.91%, 97.80%, 98.76%, 99.13%, and 98.27%, respectively, which outperforms other classification models. The experimental results show that our model can classify CXR images better.

Abstract To improve the accuracy of remote-sensing image semantic segmentation in complex scenario, an improved DeepLabv3+ lightweight neural network is proposed. Specifically, the lightweight network MobileNetv2 is used as the backbone network. In atrous spatial pyramid pooling (ASPP), to alleviate the gridding effect, the Dilated Convolution in original DeepLabv3+ network is replaced with the Hybrid Dilated Convolution (HDC) module. In addition, the traditional spatial mean pooling is replaced by the strip pooling module (SPN) to improve the local segmentation effect. In the decoder, to obtain the rich low-level target edge information, the ResNet50 residual network is added after the low-level feature fusion. To enhance the shallow semantic information, the efficient and lightweight Normalization-based Attention Module (NAM) is added to capture the feature information of small target objects. The results show that, under the INRIA Aerial Image Dataset and same parameter setting, the Mean Pixel Accuracy (MPA) and Mean Intersection over Union (MIoU) are generally best than DeepLabv3+ , U-Net, and PSP-Net, which are respectively improved by 1.22%, − 0.22%, and 2.22% and 2.17%, 1.35%, and 3.42%. Our proposed method has also a good performance on the small object segmentation and multi-object segmentation. What’s more, it significantly converges faster with fewer model parameters and stronger computing power while ensuring the segmentation effect. It is proved to be robust and can provide a methodological reference for high-precision remote-sensing image semantic segmentation.

多系统组合精密单点定位(Precise Point Positioning,PPP)中系统间偏差(Inter-System Bias,ISB)是必须要考虑的问题.对ISB可以通过参数估计进行消除,由于参数估计有多种策略,所以本研究利用MGEX观测站的精密产品,采用不同的估计策略对"GPS+BDS""GPS+Galileo"组合进行动态、静态解算分析PPP性能,并分析ISB的单天特性.试验表明,采用随机游走和时间常数策略估计获得的ISB稳定性最优,而采用白噪声估计得到的ISB具有较大的波动.对于多系统PPP解算而言,无论是动态还是静态,ISB采用随机游走和白噪声策略可以获得较高的稳定性并减少收敛时间,而采用时间常数进行ISB估计效果较差.

为了避免池化层重要特征信息的丢失以及改善CNN和RNN无法全面提取特征的局限性,文章提出一种基于BiGRU和胶囊网络的神经网络模型—BGCapNet模型,该模型使用两个不同尺寸的BiGRU进行特征提取,实现文本长距离相互依赖的特性,胶囊网络获取更丰富的特征信息并通过胶囊预测进行情感分类.为了评估模型的有效性,在电影评论IMDB和SST-2这两个数据集上进行了实验.实验结果表明,BGCapNet模型在影评数据集上的准确率和F1值优于其他传统方法,有效提高了文本情感分类的效果.

针对物联网工程专业实践教学中存在的课程间关系不明晰、课程支撑专业方向不明显、实验内容与工程应用联系不紧密以及实践创新性体现不足等问题,结合新工科建设需求、专业培养目标以及专业办学基础,系统梳理物联网工程专业的课程结构,提出多层次的物联网工程专业实践教学新体系,包括课程实验、课程设计、实习和实训、科技创新实践等方面.实施效果表明,多层次实践教学体系能有效提高物联网工程专业学生的实践能力和创新能力.

针对用户评分信息密度稀疏以及推荐结果排序不够理想的问题,提出一种基于改进相似度的深度神经网络矩阵分解推荐算法.该算法将用户信息作为类序列,采用最长公共子序列算法寻找相似用户,让近期更符合用户兴趣的推荐结果出现在更靠前的位置,使得相似用户间的隐藏特征向量更加接近,并在运用深度神经网络学习用户和项目之间的隐藏特征时维持这种关系,从而提高模型的预测精度.在Epinions数据集上根据不同的性能指标进行对比实验,验证了该算法的推荐效果.

为解决高级语言程序设计传统课堂存在的一些问题,从辅助教学平台、教学内容、教学方法、课程评价体系4个方面对课程进行改革,通过科学、合理地融入思政元素,采用线上线下混合教学、案例教学、分级分层教学、翻转教学等多种模式相结合的新颖教学方式,实现了知识传授与价值引导结合、理论传授与能力训练结合以及重结果更重过程的教学理念.通过实施结果看,教学改革有效提高了高级语言程序设计课程教学效果,满足了工程教育专业认证人才的培养要求.

针对当前汇编语言课程教学中存在的问题并结合教学实践,以工程教育专业认证理念为导向,以改善教学效果、加强学生的实践能力和专业素养为出发点,从教学形式和课堂教学模式2个方面提出改革方案并具体实施,为汇编语言教学提供借鉴和参考.

目前,石油资源仍然是人类生存和发展的重要资源,石油开采能力依然决定着石油的产量.以修井作业机械臂抓手作为研究对象,根据已有模型参数利用SolidWorks建立修井作业机械臂的三维实体模型,基于ANSYS Workbench对修井作业机械臂抓手进行静力学分析及模态分析,得到修井作业机械臂抓手在载荷作用下的变形情况以及模态分析中各阶段的固有频率和振型.结果表明,机械臂抓手在362.05Hz时受到最大变形,并根据分析结果对机械臂抓手进行结构优化,优化后机械臂抓手的性能得到进一步提升.

无线传感器网络具有感知和处理信息的能力,只有当被测网络内节点的位置已知时,节点传递给用户的信息才有意义.针对DV-Hop定位中传统最小二乘法不可避免的精度低的缺点,引入粒子群算法(PSO)和灰狼优化器(GWO)来估计未知节点位置.粒子群算法具有个体记忆的特点,采用粒子位置更新代替灰狼个体位置更新,使灰狼算法在优化上具有可记忆性.仿真数据表明,改进后的算法可以有效降低节点定位误差,实现更高的定位精度.

为了充分发挥GPS的优越性,提高作业效率,本课题通过设计GPS网形观测方案,采用GPS静态相对定位测量的方法,实地进行测量,再运用软件对测量数据进行处理精度评定,从网形特征条件、点位精度、效益指标等方面进行对比分析,最终得出最优布网方案.通过本课题的研究,在考虑点位精度的同时要充分发挥各个网形结构的优势,使某些重要控制点能有更多连接基线,提高精度,而次要点可采用其它效率高的网形结构,提高效益,此研究为优化GPS网形结构,提高GPS控制网测量的工作效率和精度提供了参考,具有较好的现实意义.

针对无线传感器网络由于节点异常或受干扰等原因导致网络监测数据可靠性降低的问题,提出一种基于信任模型的可靠数据采集方法.该方法首先利用箱型模型筛选当前时刻采集的数据值变化较大的节点,并判断其是否为异常数据节点;然后,根据异常数据节点的占比和节点可信度确定数据是否被采集.当数据异常节点数量低于设定阈值时,基于信任模型过滤掉可信度低的非正常节点后再对数据进行采集;当高于设定阈值时,启动监测事件发生时的紧急数据传输机制,以保障紧急数据的快速收集.仿真实验结果表明:该算法在不同异常节点占比下较经典信任模型RFSN平均检测率高9.14％左右;较原生HEED协议平均数据采集准确率高20％左右.