Results 21 to 30 of about 380 (97)
Research on sonar image few-shot classification based on deep learning
Xibei Gongye Daxue Xuebao, 2022 The underwater environment is complex and diverse, which makes it difficult to evolve traditional methods such as manually extracting features from blurred images.
CHEN Yule +3 more
doaj +1 more source
Fault diagnosis method for underground coal mining equipment audio signals based on improved transfer learning [PDF]
The underground production environment in coal mines is harsh, and key equipment such as gas pumps, ventilators, and coal shearers often operate continuously, making them susceptible to faults.
QIU Ji'er, WANG Peng, WANG Qi
core +1 more source
Key technologies of 6G mobile network [PDF]
, 2022 The development and social needs of mobile communication networks were firstly introduced.Then four key technologies of 6G network were respectively introduced from the perspectives of communication spectrum, coverage dimension, communication empowerment,
Anqi CHEN +3 more
core +1 more source
Methods in Ecology and Evolution, Volume 17, Issue 4, Page 1143-1160, April 2026.Abstract DNA barcode‐based species identification has become pivotal in biodiversity research. Current barcoding‐based deep learning methods have advantages in species identification but exhibit significant limitations. By using COI barcoding alone, previous studies were unable to fully capture species identification features. Prior methods showed that
Bin Ye +4 more
wiley +1 more source
Research on Scene-specific Pedestrian Detection Method Based on Deep Learning [PDF]
, 2015 行人检测一直是计算机视觉中，尤其是目标检测领域的研究重点。而由于环境的时变性和多样性，不同场景之间样本不满足同分布，普通场景下训练得到的检测器直接应用到某一特定场景时性能会急剧下降。基于这样的背景，本文依据场景的复杂程度不同提出了两种对应的解决方法，主要工作和创新点如下： 1）当背景比较简单时，容易获取样本的标定信息，本文提出了一种快速的行人检测算法，首先基于结构化局部边缘模式计算样本特征，然后通过积分图技术快速计算分类器分数，从而使得检测过程更加高效 ...
袁德东
core
Synthesis of embroidery based on convolutional neural network(基于卷积神经网络的刺绣风格数字合成)
Zhejiang Daxue xuebao. Lixue ban, 2019 针对刺绣风格数字化模拟方法立体感不强、缺少线条方向等问题，提出了一种基于深度学习和卷积神经网络的算法，将刺绣艺术风格传输到目标图像。利用图像语义分割网络及风格迁移网络，分别对目标内容图像与刺绣艺术风格图像进行目标提取和风格迁移。首先，输入目标内容图像与刺绣艺术风格图像，采用基于条件随机场的图像语义分割，将目标内容图与刺绣艺术风格图的前景与背景分离，并进行二值化处理，形成掩模图像；其次，将目标内容图与刺绣艺术风格图的RGB 颜色空间转换为YIQ；最后，参照掩模图像使用VGG19 ...
ZHENGRui(郑锐) +3 more
doaj +1 more source
Study on learning algorithm of transfer reinforcement for multi-agent formation control
Xibei Gongye Daxue Xuebao, 2023 Considering the obstacle avoidance and collision avoidance for multi-agent cooperative formation in multi-obstacle environment, a formation control algorithm based on transfer learning and reinforcement learning is proposed.
HU Penglin +3 more
doaj +1 more source
Competence Development and Evaluation Dynamics in the Context of Learning
Risk, Hazards &Crisis in Public Policy, Volume 17, Issue 1, March 2026.ABSTRACT Organizations operating in high‐risk environments rely on learning from real incidents, yet how evaluation practices contribute to competence development and organizational learning remains insufficiently understood. This challenge is evident in police operations, where decisions made under uncertainty have immediate implications for safety ...
Ensieh Roud, Riana Steen, Marita Aune
wiley +1 more source
Bi-directional Pre-trained Network for Single-station Seismic Waveform Analysis [PDF]
The application of machine learning, particularly deep learning methods, is becoming increasingly widespread in seismology, achieving near-human accuracy in tasks such as phase detection and event classification.
Lu LI +4 more
core +1 more source
野生动物学报, 2022 蛇在野外广泛分布,不同种类的蛇具有不同的特性,实现蛇的准确识别对保护生物多样性和促进全球健康具有重要意义。为提高传统神经网络模型在蛇类图像上的识别效果,以中国地区常见蛇种作为研究对象,包括金环蛇(Bungarus fasciatus)、银环蛇(B.multicinctus)、圆斑蝰(Daboia russelli siamensis)、尖吻蝮(Deinagkistrodon acutus)、竹叶青(Trimeresurus stejnegeri)和王锦蛇(Elaphe carinata ...
周志斌 罗志聪 张展榜 孙奇燕
doaj