Results 11 to 20 of about 12,984 (168)
智能科学与技术学报, 2022 现有群体智能系统执行探索任务时往往获取、计算和传输大量冗余信息，造成群智系统资源利用效率低下。设计任务驱动的计算和通信资源高效融合利用机理成为亟待解决的关键科学问题。基于此，提出了一种脑注意力机制启发的群体智能协同避障方法。受脑注意力机制启发，群智系统引入基于深度Q网络的传感器智能选择模块，实现在探索未知环境时高效选择传感器的工作状态，利用尽量少的传感器开销获取和计算关键信息；以最佳交互碰撞避免算法为基础，单一智能体融合邻居智能体的少量关键信息，驱动传感器智能选择模块，在完成集群协同避障的同时 ...
项羽铭 +4 more
doaj +1 more source
Automatic Summarization Model Combining BERT Word Embedding Representation and Topic Information Enhancement [PDF]
, 2022 Automatic text summarization can help people to filter and identify information quickly,grasp the key content of news,and alleviate the problem of information overload.The mainstream abstractive summarization model is mainly based on the encoder-decoder ...
GUO Yu-xin, CHEN Xiu-hong
core +1 more source
YOLOv3-A: a traffic sign detection network based on attention mechanism [PDF]
, 2021 To solve the problem that the existing YOLOv3 algorithm had more false detections and missed detections for traffic sign detection task with small target problems and complex background, based on the YOLOv3, a channel attention method for target ...
Fan GUO +3 more
core +1 more source
智能科学与技术学报, 2021 与中英文相比，藏文实体关系训练语料规模较小，传统有监督的学习方法难以获得较高的准确率。针对基于远程监督的实体关系抽取存在错误标记的问题，利用远程监督方法将知识库与文本对齐，构建藏文实体关系抽取的数据集，提出一个基于多级注意力融合机制的藏文实体关系抽取模型。在词级别引入自注意力机制来提取单词的内部特征，在句子级别引入注意力机制为每个实例分配权重，从而充分利用包含信息的句子，减少噪声实例的权重。同时引入联合评分函数，修正远程监督的错误标签，并将神经网络与支持向量机结合，实现藏文实体关系分类。实验结果表明 ...
王丽客, 孙媛, 刘思思
doaj
智能科学与技术学报, 2022 当前利用社交媒体数据预测抑郁症的研究忽视语言风格和情感随时间推移变化的特征，缺乏对情感状态和帖子元数据特征的研究，基于此，提出一种基于情感信息融合注意力机制的抑郁症识别模型。首先，在现有抑郁症识别研究的基础上，使用文本分类卷积神经网络按时间顺序提取用户每个时间段的帖子信息和情感信息，引入注意力机制为得到的特征矩阵分配不同的注意力权重，进而得到用户帖子信息特征和用户情感信息特征。其次，使用正则匹配提取文本的情感倾向信息，拼接注意力机制输出分配权重后的情感特征矩阵，以增强情感学习表示。然后 ...
陈妍, 罗雪琴, 梁伟, 谢永芳
doaj
Zhejiang Daxue xuebao. Lixue ban, 2023 提出了一种新颖的广义无监督函数映射学习的三维形状密集对应方法。首先，基于多层感知器（multilayer perceptron，MLP）和残差网络，直接学习深度点特征。其次，计算点云的近似测地线距离，并对其进行特征分解，建立特征嵌入空间，引入注意力机制，有效学习广义基函数表示。再次，结合点特征与广义基函数生成三维形状的深度特征表示。最后，建立无监督的函数映射网络框架，获取形状之间的密集对应表示。提出的三元正则优化机制，联合重构损失、特征损失和形状匹配的距离损失 ...
窦丰(DOU Feng) +6 more
doaj +1 more source
Research on Entity Relationship Extraction Model of Food Public Opinion Based on CNN-BLSTM(基于CNN-BLSTM的食品舆情实体关系抽取模型研究) [PDF]
Shipin kexue jishu xuebao, 2021 The extraction of food public opinion entity relationship is the key technology for constructing the map of food sensation knowledge, and it is also an important research topic in the field of information extraction.
WANG Qingbang(王庆棒) +5 more
doaj +1 more source
Grid self-attention mechanism 3D object detection method based on raw point cloud [PDF]
, 2023 To enhance the feature representation of region of interest (RoI), which incorporated a spatial context encoding module and soft regression loss, a grid self-attention mechanism 3D object detection method based on raw point cloud, named GT3D, was ...
Bin LU, Yang SUN, Zhenyu YANG
core +1 more source
Hybrid Recommender System Based on Attention Mechanisms and Gating Network [PDF]
, 2022 Combining user reviews with user ratings to improve the performance of recommender system is the current mainstream research direction of recommender system.However,when user review data is sparse,the performance of most existing recommender systems will
GUO Liang, YANG Xing-yao, YU Jiong, HAN Chen, HUANG Zhong-hao
core +1 more source
Class Attention to Regions of Lesion for Imbalanced Medical Image Recognition
, 2023 Automated medical image classification is the key component in intelligent diagnosis systems. However, most medical image datasets contain plenty of samples of common diseases and just a handful of rare ones, leading to major class imbalances. Currently,
Cai, Jiabin +4 more
core