检索结果-内蒙古大学图书馆

您好，读者！请登录

内蒙古大学图书馆

首页
概况
党建
资源
服务
科研支持
- 论文收录引用证明
- 科技查新
知识产权
档案馆
帮助

咨询与建议

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

您的常用邮箱：*

您的手机号码：*

问题描述：

当前已输入0个字，您还可以输入200个字

全部搜索
期刊论文
图书
学位论文
标准
纸本馆藏
外文资源发现
数据库导航
超星发现

高级检索

时间限定

出版年份：

文献类型

图书期刊文献学位论文多媒体

馆藏选择

电子馆藏纸本馆藏

核心期刊

全部期刊 SCI 收录期刊 SSCI 收录期刊 EI 收录期刊 CSCD 收录期刊 CSSCI 收录期刊

语言

中文英文

文献类型

期刊文献图书学位论文标准纸本馆藏

帮助

文字说明：

T=题名（书名、题名），A=作者（责任者），K=主题词，P=出版物名称，PU=出版社名称，O=机构（作者单位、学位授予单位、专利申请人），L=中图分类号，C=学科分类号，U=全部字段，Y=年（出版发行年、学位年度、标准发布年）

检索规则说明：

AND代表“并且”；OR代表“或者”；NOT代表“不包含”；(注意必须大写,运算符两边需空一格)

检索范例：

范例一：(K=图书馆学 OR K=情报学) AND A=范并思 AND Y=1982-2016
范例二：P=计算机应用与软件 AND (U=C++ OR U=Basic) NOT K=Visual AND Y=2011-2016

分类表

所选分类

>> <<

限定检索结果

文献类型

2,471 篇 会议
1,510 篇 期刊文献
12 册 图书

馆藏范围

3,993 篇 电子文献
0 种 纸本馆藏

日期分布

学科分类号

2,415 篇 工学
- 1,457 篇 计算机科学与技术...
- 1,286 篇 软件工程
- 766 篇 控制科学与工程
- 446 篇 信息与通信工程
- 344 篇 生物工程
- 340 篇 机械工程
- 264 篇 光学工程
- 218 篇 电气工程
- 205 篇 生物医学工程（可授...
- 181 篇 交通运输工程
- 144 篇 仪器科学与技术
- 144 篇 电子科学与技术（可...
- 124 篇 化学工程与技术
- 94 篇 土木工程
- 87 篇 建筑学
- 80 篇 力学（可授工学、理...
- 79 篇 动力工程及工程热...
- 69 篇 安全科学与工程
1,203 篇 理学
- 570 篇 数学
- 357 篇 生物学
- 352 篇 物理学
- 205 篇 统计学（可授理学、...
- 139 篇 系统科学
- 120 篇 化学
496 篇 管理学
- 323 篇 管理科学与工程(可...
- 197 篇 图书情报与档案管...
- 136 篇 工商管理
145 篇 医学
- 136 篇 临床医学
- 103 篇 基础医学(可授医学...
87 篇 法学
- 84 篇 社会学
52 篇 经济学
27 篇 教育学
25 篇 农学
8 篇 文学
7 篇 艺术学
4 篇 军事学
2 篇 历史学
1 篇 哲学

主题

135 篇 training
134 篇 feature extracti...
104 篇 robots
97 篇 intelligent robo...
94 篇 artificial intel...
89 篇 object detection
89 篇 accuracy
84 篇 semantics
82 篇 three-dimensiona...
79 篇 reinforcement le...
72 篇 cameras
72 篇 robustness
71 篇 computer vision
70 篇 computational mo...
70 篇 robot sensing sy...
66 篇 real-time system...
64 篇 convolution
62 篇 visualization
61 篇 trajectory
58 篇 deep learning

机构

406 篇 institute of art...
338 篇 shenzhen institu...
157 篇 institute of art...
136 篇 school of artifi...
118 篇 school of scienc...
82 篇 university of ch...
79 篇 institute of art...
69 篇 institute of aut...
67 篇 the chinese univ...
63 篇 siat branch shen...
62 篇 state key labora...
60 篇 centre for artif...
48 篇 shenzhen institu...
47 篇 the shenzhen ins...
44 篇 tianjin key labo...
43 篇 school of softwa...
42 篇 national key lab...
41 篇 institute of rob...
39 篇 institute of art...
37 篇 lamarr institute...

作者

254 篇 nanning zheng
214 篇 zheng nanning
77 篇 chen badong
70 篇 jingmin xin
54 篇 badong chen
53 篇 al-turjman fadi
51 篇 jianru xue
51 篇 zhang zhaoxiang
50 篇 huang jianwei
49 篇 shaoyi du
48 篇 liu yuehu
48 篇 zhou sanping
48 篇 lei zhen
45 篇 yuehu liu
45 篇 shen linlin
41 篇 xin jingmin
40 篇 wang le
37 篇 lan xuguang
37 篇 shitao chen
36 篇 fang yongchun

语言

3,636 篇 英文
309 篇 其他
51 篇 中文
1 篇 朝鲜文

检索条件"机构=Institute of artificial intelligence and robotics"

共 3993 条记录，以下是471-480 订阅

全选清除本页清除全部题录导出标记到"检索档案"

详细简洁

排序：

Recovering Visual Human's Attention in Human-Robot Interaction for a Promoter Service Robot

Recovering Visual Human's Attention in Human-Robot Interacti...

引用

Intelligent Reality (ICIR), IEEE International Conference on

作者： Jesus Eduardo Hermosilla-Diaz Andrey Solovov Mohammad Zarei Jeeangh Jennessi Reyes-Montiel Vishal Gautam Bruno Perreira Gustavo Assuncao Paulo Menezes Antonio Marin-Hernandez Research Institute of Artificial intelligence Universidad Veracruzana Xalapa Mexico Institute of Systems and Robotics University of Coimbra Coimbra Portugal

ISBN: (数字)9798331534424

ISBN: (纸本)9798331534431

The use of service robots is an alternative for prod-ucts and services promotion. In commercial areas an effective human-robot interaction is essential. However, communicating information effectively and thus maximizing the likelihood of a product or service's acceptance by the potential consumer remains challenging. In this work, we propose an architecture that integrates multiple modules, including visual gaze esti-mation, head tracking, human detection, position estimation, and attention recovery behaviors, to recover human attention during potential scenarios such as promotional tasks. Attention is presented as a decay function on different parameters, such as visual gaze and head position. When the robot detects a shutdown at the attention level, it executes a behavior to recover it. The proposal details our architecture's design and the modules' theoretical implications, highlighting the potential for improved service-robot interaction.

关键词： Measurement Visualization Service robots Natural languages Estimation Human-robot interaction Gesture recognition Behavioral sciences Proposals

来源：评论

学校读者我要写书评

暂无评论

Categorization of IRIS Flower Using Different Machine Learning Strategies

Categorization of IRIS Flower Using Different Machine Learni...

引用

Electrical, Electronics, Communication and Computers (ELEXCOM), International Conference on

作者： Amit Singh Rajawat Ashutosh Kewat Manjhi Anshika Srivastava Department of Information Technology (Artificial Intelligence and Robotics) Madhav Institute of Technology & Science Gwalior India Centre for Artificial Intelligence (Artificial Intelligence and Data Science) Madhav Institute of Technology & Science Gwalior India

Today, machine learning is important in many areas, including agriculture, computer science, healthcare, and medicine, to name a few. It is known that our planet is abundant in species and millions of biomes thrive in the Earth's ecosystem. Some of them share physical characteristics such as size, shape, and color. It is quite difficult for a general human being to determine which items are of which sort. Similarly, it is difficult to determine which flower is of which subspecies in flower species. Classification is the most essential machine learning approach for distinguishing one item from another. Setosa, Versicolor, and Virginica are the three subspecies of the Iris flower. Five approaches are presented in depth, including Decision tree, Naive Bayes, Linear Support Vector Machine (SVM), K-nearest neighbor, and Logistic regression, and the implementation is done using the sci-kit learn the tool. Furthermore, different sizes of training and testing sets are applied to and compared with each method. The IRIS dataset was analyzed using classification and regression algorithms with a 10-fold cross-validation score. The emphasis was on examining patterns utilizing the flower's sepal and petal sizes. In terms of accuracy, the findings showed that the Linear SVM classifier outperformed with 99.17% Model accuracy and 100% of Test accuracy as compared to the Decision tree, Naive Bayes, K-nearest neighbor, and Logistic regression models.

关键词：

来源：评论

学校读者我要写书评

暂无评论

GelPixel: A Single-Pixel-Based Tactile Sensor

GelPixel: A Single-Pixel-Based Tactile Sensor

引用

2023 IEEE International Conference on Real-Time Computing and robotics, RCAR 2023

作者： Huang, Binhua Li, Xiaoyu Sumari, Putra Ye, Chaoxiang Zhou, Zhenning Yin, Meng Yi, Zhengkun Wu, Xinyu Shenzhen Institute of Artificial Intelligence and Robotics for Society Siat Branch Shenzhen518055 China Universiti Sains Malaysia School of Computer Science 11800 Malaysia Chinese Academy of Sciences Guangdong Provincial Key Laboratory of Robotics and Intelligent System Shenzhen Institute of Advanced Technology Shenzhen518055 China

ISBN: (纸本)9798350327182

In this paper, we present the design and development of a novel optical tactile sensor that uses a single-pixel color light-to-frequency converter (TCS3200) and spectral decoding to recognize presses at different positions. This innovative approach overcomes the limitations associated with camera-based sensors, such as increased manufacturing costs and shape restrictions, enabling potential integration as a skin-like layer over a robot's body. Our proposed direct light propagation structure demonstrates enhanced sensitivity and a broader measuring range compared to traditional reflection structures. Using Ecoflex as the elastomer, the sensor's design incorporates a three-layer structure, including an LED layer, an elastomer layer, and a color sensor layer. Experimental results demonstrate that the proposed sensor performs well in localization tasks, achieving over 95% accuracy using multi-target regression for rendering poked positions. This study demonstrates the potential of single-pixel-based tactile sensors in various applications and provides a foundation for further exploration in this area. © 2023 IEEE.

关键词： Tactile sensors

来源：评论

学校读者我要写书评

暂无评论

Visual Detection for Non-Ferrous Metal Ingots With Wavelet Denoising and Contour Corner Extraction 7

Visual Detection for Non-Ferrous Metal Ingots With Wavelet D...

引用

7th Asia-Pacific Conference on Intelligent Robot Systems, ACIRS 2022

作者： Qiu, Zehao Sun, Ning Zhang, Chenglin Sang, Wenchuang Fang, Yongchun Institute of Robotics and Automatic Information Systems College of Artificial Intelligence Nankai University Tianjin300350 China Institute of Intelligence Technology and Robotic Systems Shenzhen Research Institute of Nankai University Shenzhen518083 China

ISBN: (数字)9781665485197

ISBN: (纸本)9781665485197

To realize the intelligent grinding of non-ferrous metal ingots, visual detection algorithms are required to provide the information of metal ingots for robotic manipulators. However, metal ingots in moving molds on ingot casting lines are accompanied by complicated backgrounds and continuous changes, which demands higher accuracy and stronger robustness of visual detection. Based on two kinds of metal ingots and the analysis of metal ingot images, a wavelet-based method with an improved threshold and threshold function is utilized to reduce noises. Afterward, the edge information of metal ingots is obtained by edge line segment detection, and the detected edges are selected according to their positions and lengths. Moreover, in order to extract the contour corners of metal ingots, basic contours are detected and further fitted into metal ingot contours. Finally, experimental results verify that the proposed metal ingot detection algorithm achieves satisfactory accuracy, robustness, and real-time performance for different images and metal ingots. © 2022 IEEE.

关键词： Metals

来源：评论

学校读者我要写书评

暂无评论

Fin-MLGAT: Line Graph Attention Network for Dialogue Emotion Recognition in Stock Market and its Evaluations 11

Fin-MLGAT: Line Graph Attention Network for Dialogue Emotion...

引用

11th International Conference on Dependable Systems and Their Applications, DSA 2024

作者： Feng, Xiaobing Feng, Ling Xu, Xiujuan Qiao, Jiaqi Zhang, Wenjian Shanghai University of International Business and Economics School of Finance Institute of Change Management and Artificial Intelligence Shanghai China Shanghai Ocean University School of Robotics Engineering Shanghai China Dalian University of Technology School of Software Technology Dalian China

ISBN: (纸本)9798331532390

With the rapid development of social media and digitalization, the task of emotion pattern recognition and extreme emotion detection in conversation is playing an increasingly important role in understanding emotion interaction among and between parties. Traditional methods employ probabilistic statistical models that leverage prior knowledge to construct models However when dealing with complex patterns, large scale data, and high-dimensional features, their performance becomes limited. Alternatively, deep learning methods are capable of automatically learning highly abstract feature representations from raw datasets. Our Fin-MLGAT mines the emotional information dependent on the target utterance by focusing on local con text and global context at different scales. Experiments show that our model achieves the second-highest performance among all current methods by Wa-F1. Moreover, the model can show high accuracy in a few classes without additional measures. © 2024 IEEE.

关键词： Marketplaces

来源：评论

学校读者我要写书评

暂无评论

A Spatial Feature Extraction Method for Enhancing Upper Limb Motion Intent Prediction in EMG-PR System 46

A Spatial Feature Extraction Method for Enhancing Upper Limb...

引用

46th Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBC 2024

作者： Peng, Boxing Zhang, Haoshi Li, Xiangxin Zheng, Yue Li, Guanglin Cas Key Laboratory of Human-Machine Intelligence-Synergy Systems Shenzhen518055 China University of Chinese Academy of Sciences Shenzhen College of Advanced Technology Shenzhen518055 China Southern University of Science and Technology Guangdong Provincial Key Laboratory of Human-Augmentation and Rehabilitation Robotics in Universities Shenzhen518055 China Siat Branch Shenzhen Institute of Artificial Intelligence and Robotics for Society Shenzhen518055 China

ISBN: (纸本)9798350371499

High-Density Surface Electromyography (HD-sEMG) enriches motion intention pattern recognition systems by providing more spatial information. Multichannel linear descriptors (MLD) could provide a comprehensive description of the overall state characteristics within the muscle regions. In this study, an MLD-based spatial feature extraction method was proposed to capture differences and correlations in various muscle regions during movement, ultimately enhancing the system's classification accuracy. The performance of the feature extraction method was compared with traditional time domain feature extraction method under various classifiers and different movement types. The results show that employing the proposed method with the spatial features improves the classification error rates of combined movements from 11.14% to 7.28%, and better adaptability for all classifiers utilized in this study, which shows the effect of utilization of spatial information in different muscle regions. © 2024 IEEE.

关键词： Electromyography

来源：评论

学校读者我要写书评

暂无评论

Pest Detection and Identification Guided by Feature Maps 12

Pest Detection and Identification Guided by Feature Maps

引用

12th International Conference on Image Processing Theory, Tools and Applications, IPTA 2023

作者： Chen, Miao Chen, Yanan Guo, Minghui Wang, Jianji Xi'an Jiaotong University National Key Laboratory of Human-Machine Hybrid Augmented Intelligence National Engineering Research Center for Visual Information and Applications Institute of Artificial Intelligence and Robotics China Xi'an Jiaotong University School of Software Engineering Xi'an China

ISBN: (纸本)9798350325416

Effective pest detection and identification are of great significance for agricultural activities, and morden machine learning methods, especially the deep neural network, undoubtedly provide convenient and effective ways for this issue. Most of the mainstream methods for pest detection require annotation of manual bounding box. However, the public pest datasets usually lack the labeling information. In this work, we propose a method for detecting pests with weak supervision. We obtain the key regions of the pest targets by deeply mining the information in the feature maps of the convolutional neural networks (CNNs). First, using the class activation mapping technique to generate activation maps of the target class during forward propagation of the model, and then obtaining the key regions of the target based on the hotspots extracted from the activation maps. In addition, our proposed method can be deployed as a general strategy to other CNNs, and experimental results demonstrate that our method can steadily improve the classification accuracy of the model. By applying our method to the single Resnet50, we can achieve 74.27% classification accuracy on the publicly accessible IP102 dataset. Another attribution of this paper is that we propose a lightweight approach to find solutions for pest detection in agricultural automation applications. © 2023 IEEE.

关键词： Deep neural networks

来源：评论

学校读者我要写书评

暂无评论

Large-scale Deployment of Vision-based Tactile Sensors on Multi-fingered Grippers

Large-scale Deployment of Vision-based Tactile Sensors on Mu...

引用

IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)

作者： Meng Wang Wanlin Li Hao Liang Boren Li Kaspar Althoefer Yao Su Hangxin Liu State Key Laboratory of General Artificial Intelligence Beijing Institute for General Artificial Intelligence (BIGAI) Centre for Advanced Robotics @ Queen Mary (ARQ) Queen Mary University of London

ISBN: (数字)9798350377705

ISBN: (纸本)9798350377712

Vision-based Tactile Sensors (VBTSs) show significant promise in that they can leverage image measurements to provide high-spatial-resolution human-like performance. However, current VBTS designs, typically confined to the fingertips of robotic grippers, prove somewhat inadequate, as many grasping and manipulation tasks require multiple contact points with the object. With an end goal of enabling large-scale, multi-surface tactile sensing via VBTSs, our research (i) develops a synchronized image acquisition system with minimal latency, (ii) proposes a modularized VBTS design for easy integration into finger phalanges, and (iii) devises a zero-shot calibration approach to improve data efficiency in the simultaneous calibration of multiple VBTSs. In validating the system within a miniature 3-fingered robotic gripper equipped with 7 VBTSs we demonstrate improved tactile perception performance by covering the contact surfaces of both gripper fingers and palm. Additionally, we show that our VBTS design can be seamlessly integrated into various end-effector morphologies significantly reducing the data requirements for calibration.

关键词： Fingers Tactile sensors Surface morphology Morphology Grasping Calibration Sensors Synchronization Grippers Intelligent robots

来源：评论

学校读者我要写书评

暂无评论

Hip Hiking Gait Improvement with Electrohydraulic Robotic Knee: Preliminary Results 46

Hip Hiking Gait Improvement with Electrohydraulic Robotic Kn...

引用

46th Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBC 2024

作者： Zhong, Heran Gao, Siyuan Wang, Qining Peking University College of Engineering Department of Advanced Manufacturing and Robotics Beijing100871 China Peking University College of Engineering The Institute for Artificial Intelligence Department of Advanced Manufacturing and Robotics Beijing100871 China Peking University Third Hospital Beijing100191 China University of Health and Rehabilitation Sciences Qingdao266071 China

ISBN: (纸本)9798350371499

Individuals with Transfemoral Amputation (TFA) usually exhibit hip hiking walking with passive prostheses due to insufficient knee flexion. Powered knee prostheses can provide net-positive energy in the knee joint with improved gait symmetry. However, their effects on improving hip hiking are not well understood. This study investigates residual hip hiking through walking experiments using a robotic transfemoral prosthesis that can provide swing assistance. Different levels of assistive flexion torque were provided during the pre-swing and the mid-swing (no assistance, low assistance, medium assistance, high assistance). The kinematic and electromyographic (EMG) results indicate that with the increasing assistive torque level applied, the residual hip hiking was improved. The results preliminarily demonstrate the positive effect of knee flexion assistance on hip hiking improvement. © 2024 IEEE.

关键词： Knee prostheses

来源：评论

学校读者我要写书评

暂无评论

Real-Time Polygonal Semantic Mapping for Humanoid Robot Stair Climbing 23

Real-Time Polygonal Semantic Mapping for Humanoid Robot Stai...

引用

23rd IEEE-RAS International Conference on Humanoid Robots, Humanoids 2024

作者： Bin, Teng Yao, Jianming Lam, Tin Lun Zhang, Tianwei The Shenzhen Institute of Artificial Intelligence and Robotics for Society Shenzhen China Harbin Engineering University College of Intelligent Systems Science and Engineering Harbin China Guangdong University of Technology Guangzhou China The Chinese University of Hong Kong - Shenzhen Shenzhen China

ISBN: (纸本)9798350373578

We present a novel algorithm for real-time planar semantic mapping tailored for humanoid robots navigating complex terrains such as staircases. Our method is adaptable to any odometry input and leverages GPU-accelerated processes for planar extraction, enabling the rapid generation of globally consistent semantic maps. We utilize an anisotropic diffusion filter on depth images to effectively minimize noise from gradient jumps while preserving essential edge details, enhancing normal vector images' accuracy and smoothness. Both the anisotropic diffusion and the RANSAC-based plane extraction processes are optimized for parallel processing on GPUs, significantly enhancing computational efficiency. Our approach achieves real-time performance, processing single frames at rates exceeding 30 Hz, which facilitates detailed plane extraction and map management swiftly and efficiently. Extensive testing underscores the algorithm's capabilities in real-time scenarios and demonstrates its practical application in humanoid robot gait planning, significantly improving its ability to navigate dynamic environments. © 2024 IEEE.

关键词： Anisotropy

来源：评论

学校读者我要写书评

暂无评论

没有更多数据了...

全选清除本页清除全部题录导出标记到“检索档案”

共400页 << < 44 45 46 47 48 49 50 51 52 53 > >>

检索报告对象比较合并检索0

隐藏清空

合并搜索

回到顶部

执行限定条件

内容：

评分：

请选择保存的检索档案：

请选择收藏分类：

订阅名称：

通借通还

温馨提示：

图书名称：

借书校区：

取书校区：

手机号码：

邮箱地址：

一卡通帐号：

电话和邮箱必须正确填写，我们会与您联系确认。

联系人：

所在院系：

联系邮箱：

联系电话：

内蒙古自治区呼和浩特市赛罕区大学西街235号邮编: 010021

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：