Results 91 to 100 of about 13,106 (168)
Gaoya dianqi, 2022 为提高换流站智能化水平，充分利用巡检机器人硬件能力，文中基于变压器声音信息提出一种直流偏磁声纹识别方法，该方法可以无需特定降噪算法应对瞬态和稳态噪声。首先，对变压器声音信号进行分析；其次，为提高有效声音信息权重，结合变压器声音信号特点，使用W-50FMCC特征来表征声音信息；再次，基于多头注意力机制和残差结构设计了非自回归端到端偏磁声纹识别模型，使用信道补偿算法提升特征正交性并获取相似度得分，完成识别；最后通过实验进行了验证。实验表明，该方法可以直接对变压器声学信号的偏磁情况进行准确的识别，无需降噪算法。
刘建华 +5 more
doaj
[A lightweight multiscale target object detection network for melanoma based on attention mechanism manipulation]. [PDF]
Nan Fang Yi Ke Da Xue Xue Bao, 2022 Zhong Y, Che W, Gao S.
europepmc +1 more source
Named Entity Recognition of Vascular Surgery Based on Glyph Features [PDF]
As core components of healthcare information systems, Electronic Medical Record (EMR) entails numerous important medical entities. Named Entity Recognition (NER) of EMRs can significantly advance medical research.
Huaqing ZHANG, Zhangtao XIA, Xiaoqing LU, Jijun TONG
core +1 more source
[Automated detection of sleep-arousal using multi-scale convolution and self-attention mechanism]. [PDF]
Sheng Wu Yi Xue Gong Cheng Xue Za Zhi, 2023 Li F, Xu Y, Zhang B, Cong F.
europepmc +1 more source
Zhendong Ceshi yu Zhenduan针对在线故障诊断中多源信息利用不足与模型识别精度不高的问题，提出了一种主成分分析（principal component analysis， 简称PCA）与残差注意力网络相结合的多传感器融合故障诊断方法（multi‑sensor feature fusion residual attention network， 简称MSF‑ResAttNet），以实现三相异步交流电动机的高精度诊断。首先，采集电动机在不同运行状态下的振动、电压及电流等多源信号；其次，利用PCA对同源传感器数据进行数据层融合 ...
doaj +1 more source
Huli yanjiu, 2008 摘要： （免费在线浏览）随着人们健康需求的日益增长和医疗体制改革的不断深化，医疗服务行业正面临着新的机遇与挑战，只有不断强化公共卫生意识，不断壮大公共卫生应急体系，不断加固疾病防控防线，才能从容不迫地应对各种公共卫生危机。而在“非典”巨大震撼之后应用而生的公共卫生体系的主力军新建传染病医院的建设与发展已成为人们关注的重点。
阅读全文：0
doaj
[Image segmentation of skin lesions based on dense atrous spatial pyramid pooling and attention mechanism]. [PDF]
Sheng Wu Yi Xue Gong Cheng Xue Za Zhi, 2022 Yin W, Zhou D, Fan T, Yu Z, Li Z.
europepmc +1 more source
A neural convolutional network intrusion detection model based on autoencoder dimension reduction [PDF]
In order to improve the accuracy of intrusion detection, considering the advantages of autoencoders in learning features and the mature application of residual networks in constructing deep models, an improved residual network intrusion detection model ...
DING Jiawei, FENG Guanghui, SUN Jing
core +1 more source
[Study on the method of polysomnography sleep stage staging based on attention mechanism and bidirectional gate recurrent unit]. [PDF]
Sheng Wu Yi Xue Gong Cheng Xue Za Zhi, 2023 Liu Y, He C, Yuan C, Zhang H, Ji C.
europepmc +1 more source
Automatic Escalator Pedestrian Safety Detection Algorithm Based on SwinT-YOLOX Model [PDF]
Escalators are widely used in public places. If passenger fall accidents cannot be detected and handled in a timely manner, they will cause serious personal injury.
Ying HOU, Lin YANG, Xin HU, Shun HE, Wanying SONG, Qian ZHAO
core +1 more source