Results 101 to 110 of about 2,703 (160)
Dynamic Obstacle Avoidance for Service Robots Based on Spatio-Temporal Graph Attention Network [PDF]
To solve the problems of collision, freezing, and the unnatural paths of service robots in dense crowds with autonomous decision-making ability, this study proposes a dynamic obstacle avoidance algorithm for service robots based on spatio-temporal graph ...
Haijun DU, Su YU
core +1 more source
Zhongguo shiyan zhenduanxue目的探究基于YOLO11深度学习模型的自动化病理图像分析与HER-2分级方法，提升病理诊断的效率与客观性。方法对原始免疫组化图像进行灰度化、边缘检测、降噪及参数优化等预处理操作，然后利用YOLO11目标检测网络实现肿瘤细胞区域的快速识别与精确定位，结合YOLO检测框结果，构建自适应HER-2评级算法，对不同表达强度进行智能分级并标注病变区域，通过数据增强策略进一步优化模型的泛化性能。结果本文方法分类精确率达到0.91，召回率为0.87，F1值为0.89，表明其在病灶区域定位的准确性与完整性方面均较为突出。
丘佳明 +5 more
doaj
Intelligent matching task offloading scheme in green computing power networks [PDF]
By integrating cloud, edge, and device resources, the computing power networks provide integrated services such as data sensing, transmission, and computation for the digital economy. However, their rapid development is accompanied by pressing challenges
LAN Shizhan, MA Lifang
core +1 more source
Gaoya dianqi随着中国能源结构持续深化转型，高比例波动性新能源接入使得现有的机组组合（unit commitment，UC）理论已经无法适应新型电力系统日前市场决策的发展需要。为此文中结合深度强化学习（deep reinforcement learning，DRL）技术提出了一种UC智能求解算法。首先引入DRL算法，对UC问题进行马尔科夫决策过程（Markov decision process，MDP）建模并给出对应的状态空间、转移函数、动作空间及奖励函数；然后采用策略梯度（policy gradient，PG ...
母欢欢, 余凌, 夏凡, 袁业
doaj
A prediction and correction reentry guidance method based on BP network and deep Q-learning network
Xibei Gongye Daxue XuebaoA prediction and correction reentry guidance method based on the BP network and the deep Q-learning network (DQN) is proposed to address the issues of low computational efficiency and difficulty in the online application of a traditional numerical ...
WANG Kuan +4 more
doaj +1 more source
Resource optimization of space-air-ground integrated network: typical issues and research prospects [PDF]
In the development and application of the space-air-ground integrated network (SAGIN), the intricate network structure and varied resources significantly affect the service capabilities of SAGIN.
DONG Bowen +4 more
core +1 more source
Shuitu Baochi Xuebao[目的] 针对黄土高原坡耕地土壤侵蚀过程复杂、人为干扰强烈且难以量化的特点,利用机器学习定量解析主要影响因素对坡耕地土壤水蚀的作用与贡献,模拟分析坡耕地土壤水蚀特征并探究其机理,为坡耕地土壤侵蚀的预报提供基础支撑。[方法] 基于黄土高原子洲试验站坡耕地小区1959—1969年产流产沙观测数据,精细化表征其影响因子,运用梯度提升树模型对侵蚀量和径流深的变化及其影响因素的贡献进行分析。[结果] 数据集中次降雨侵蚀量(0~122.72 t/km2)、径流深(0.02~17.20 mm)、降雨历时(2~1 ...
李潼亮 +7 more
doaj
野生动物学报东北虎（Panthera tigris altaica）作为世界上最大的猫科（Felidae）动物，同时也是濒危物种，其个体识别是回答进化生物学中许多重大问题的关键步骤。尽管目前已提出虹膜和DNA分析等传统方法用于东北虎个体识别，但这些方法在远程获取和样本收集方面面临挑战，且在很大程度上依赖人工识别。随着计算机视觉技术的发展，深度学习成为动物个体识别的强大工具。因此，提出使用基于深度学习的方法进行东北虎个体识别。首先收集黑龙江东北虎林园20只东北虎个体的监控视频图像，然后采用Mask R ...
马光凯 +5 more
doaj
Gaoya dianqi文中以高压隔离开关视频监测获取的图像数据为研究对象，以隔离开关分合闸状态识别为研究目标，提出了应用于变电站高压开关设备智能监测系统的图像识别算法。为了使样本数据具备多样化的特征，该方法在预处理模块中，采用了多种数据增强技术对样本集进行了处理，在增强特征量的同时，扩充了样本表达维度；在训练模块中，文中基于ResNet深度学习神经网络，构建了不同深度的网络结构，经过训练后得到了层数分别为18、34、50、101的网络模型，并在验证集上对各数据模型进行了性能评估和对比。此外，还构建了其他几种常见的神经网络模型，
张伟 +4 more
doaj
[Research progress on quantitative magnetic susceptibility imaging reconstruction method based on improved U-network model]. [PDF]
Sheng Wu Yi Xue Gong Cheng Xue Za ZhiYang W, Zhang R, Keung S.
europepmc +1 more source