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

756 篇 会议
3 册 图书
2 篇 期刊文献

馆藏范围

761 篇 电子文献
0 种 纸本馆藏

日期分布

学科分类号

655 篇 工学
- 535 篇 计算机科学与技术...
- 465 篇 软件工程
- 247 篇 信息与通信工程
- 147 篇 生物工程
- 114 篇 光学工程
- 93 篇 电气工程
- 92 篇 控制科学与工程
- 91 篇 电子科学与技术（可...
- 76 篇 生物医学工程（可授...
- 54 篇 化学工程与技术
- 39 篇 机械工程
- 34 篇 仪器科学与技术
- 34 篇 材料科学与工程（可...
- 30 篇 安全科学与工程
- 27 篇 动力工程及工程热...
- 25 篇 交通运输工程
- 24 篇 土木工程
439 篇 理学
- 204 篇 数学
- 159 篇 物理学
- 152 篇 生物学
- 71 篇 统计学（可授理学、...
- 66 篇 化学
- 34 篇 系统科学
199 篇 管理学
- 123 篇 图书情报与档案管...
- 98 篇 管理科学与工程(可...
- 39 篇 工商管理
52 篇 医学
- 49 篇 基础医学(可授医学...
- 49 篇 临床医学
- 36 篇 药学(可授医学、理...
28 篇 法学
- 25 篇 社会学
15 篇 经济学
15 篇 农学
14 篇 教育学
2 篇 军事学

主题

23 篇 deep learning
19 篇 machine learning
16 篇 support vector m...
15 篇 feature extracti...
14 篇 computer vision
11 篇 convolution
11 篇 natural language...
11 篇 sentiment analys...
10 篇 internet of thin...
10 篇 object detection
10 篇 big data
10 篇 semantics
10 篇 convolutional ne...
9 篇 natural language...
7 篇 signal processin...
7 篇 visualization
6 篇 signal detection
6 篇 deep neural netw...
6 篇 graphics process...
6 篇 neural networks

机构

7 篇 key laboratory o...
7 篇 school of inform...
6 篇 school of comput...
6 篇 xinjiang key lab...
6 篇 school of inform...
6 篇 xinjiang key lab...
6 篇 key laboratory o...
4 篇 nss college of e...
4 篇 school of comput...
4 篇 college of infor...
4 篇 school of contro...
3 篇 school of comput...
3 篇 department of co...
3 篇 college of compu...
3 篇 college of intel...
3 篇 guangdong polyte...
3 篇 school of comput...
3 篇 school of comput...
3 篇 academy for engi...
2 篇 hefei university...

作者

10 篇 hamdulla askar
6 篇 ablimit mijit
5 篇 gao yanxia
5 篇 liu yiwen
4 篇 shi yuanquan
4 篇 xiao jianhua
3 篇 faisal rehman
3 篇 wang chao
3 篇 xiao hongbo
3 篇 sharif hanan
3 篇 peng xiaoning
3 篇 rehman faisal
3 篇 chen xi
3 篇 mala c.
3 篇 shi zhen-gang
3 篇 li chao
3 篇 jiang huiming
3 篇 yuan jing
3 篇 li jing
3 篇 zhao qian

语言

753 篇 英文
8 篇 其他

检索条件"任意字段=2022 3rd International Conference on Signal Processing and Computer Science, SPCS 2022"

共 761 条记录，以下是701-710 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：

Deep-OCTA: Ensemble Deep Learning Approaches for Diabetic Retinopathy Analysis on OCTA Images 25th

Deep-OCTA: Ensemble Deep Learning Approaches for Diabetic R...

引用

25th international conference on Medical Image Computing and computer-Assisted Intervention , MICCAI 2022

作者： Hou, Junlin Xiao, Fan Xu, Jilan Zhang, Yuejie Zou, Haidong Feng, Rui School of Computer Science Shanghai Key Laboratory of Intelligent Information Processing Fudan University Shanghai China Academy for Engineering and Technology Fudan University Shanghai China Department of Ophthalmology Shanghai General Hospital School of Medicine Shanghai Jiao Tong University Shanghai China

ISBN: (纸本)9783031336577

The ultra-wide optical coherence tomography angiography (OCTA) has become an important imaging modality in diabetic retinopathy (DR) diagnosis. However, there are few researches focusing on automatic DR analysis using ultra-wide OCTA. In this paper, we present novel and practical deep-learning solutions based on ultra-wide OCTA for the Diabetic Retinopathy Analysis Challenge (DRAC). In the first task of segmentation of DR lesions, we utilize UNet and UNet++ to segment three lesions with strong data augmentation and model ensemble. In the second task of image quality assessment, we create an ensemble of Inception-V3, SE-ResNeXt, and Vision Transformer models. Pre-training on the large dataset as well as the hybrid MixUp and CutMix strategy are both adopted to boost the generalization ability of our models. In the third task of DR grading, we build a Vision Transformer and find that the model pre-trained on color fundus images serves as a useful substrate for OCTA images. Extensive ablation studies demonstrate the effectiveness of each designed component in our solutions. The proposed methods rank 4th, 3rd, and 5th on the three leaderboards of DRAC, respectively. Our code is publicly available at https://***/FDU-VTS/DRAC. © 2023, The Author(s), under exclusive license to Springer Nature Switzerland AG.

关键词： Optical tomography

来源：评论

学校读者我要写书评

暂无评论

computer simulation and prediction of coordination capture of Pb2+and Hg2+by the Salophen 3

Computer simulation and prediction of coordination capture o...

引用

3rd international conference on Advanced Algorithms and signal Image processing, AASIP 2023

作者： Duan, Shuangni Ling, Ming Lan, Wenbo Zhou, Feng Deng, Chao Xiong, Junhui Liu, Zhijuan Zeng, Can School of Public Health Xiangnan University Hunan Chenzhou423000 China Chenzhou City Heavy Metal Poll. Health Risk Assessment Technology Research and Development Center Hunan Chenzhou423000 China The Second People's Hospital of Chenzhou Hunan Chenzhou423000 China Affiliated Hospital of Xiangnan University Chenzhou Hunan423000 China University of South China Hengyang Hunan421000 China

ISBN: (纸本)9781510668522

This study used Gauss 16 computing software based on the computational methods of density functional theory (DFT) to simulate and compare the Salophen-Cd and Salophen-Hg complexes. The structural parameters, infrared vibrational, ultraviolet absorption spectra and coordination binding energies of the Salophen ligand with Cd2+ and Hg were analyzed and compared. The results showed that Salophen can form stable complexes with Cd2+ and Hg2+, which can be qualitatively distinguished by their characteristic infrared vibrational spectra and ultraviolet absorption peak values. Importantly, Salophen showed a significantly higher capture ability for Cd than for Hg, suggesting its potential application in the selective capture of Cd2+. © COPYRIGHT SPIE. Downloading of the abstract is permitted for personal use only.

关键词： Mercury compounds

来源：评论

学校读者我要写书评

暂无评论

Efficient Binarization of Ancient Handwritten Vattezhuthu Documents

Efficient Binarization of Ancient Handwritten Vattezhuthu Do...

引用

international conference on Issues and Challenges in Intelligent Computing Techniques (ICICT)

作者： MP Ayyoob P. Muhamed Ilyas Department of Computer Science Sullamussalam Science College Kerala India

Vattezhuthu, mostly written on palm leaves, was one of the ancient scripts of India which existed from 8th century AD to 15th century AD. This was one of the degraded handwritten scripts due to many reasons. The main obstacles of binarizing these ancient handwritten texts are its variable background intensity, ink bleed, uneven illumination, blurred character and contrast issues, smear or smudge and shadows etc. Therefor an effective pre-processing method is required to binarize these degraded documents. In this paper, we propose a hybrid approach for binarization and enhancement of Vattezhuthu script. In the proposed technique pixel expansion is conducted on thin handwritten vattezhuthu script using super resolution. After that image enhancement is done using median filter. Noise is filtered out by finding out the contour of enhanced image by using contour approximation and area filter. Then the morphological operation, boundaries, is used on this result.

关键词： Filtering Superresolution Lighting Ink Image enhancement

来源：评论

学校读者我要写书评

暂无评论

Quantum Computing and Machine Learning Algorithms - A Review

Quantum Computing and Machine Learning Algorithms - A Review

引用

Innovations in computer science & Software Engineering (ICONICS), international conference on

作者： Iram Manan Faisal Rehman Hanan Sharif Naveed Riaz Muhammad Atif Muhammad Aqeel Department of Information Technology Khawaja Fareed University of Engineering and Information Technology Rahim Yar Khan Pakistan Department of Computer Science & Information Technology Lahore Leads University Lahore Pakistan Department of Computer Science & Information Technology NUST Islamabad Pakistan

The goal of machine learning (ML) is to develop models that automatically learn from the past without being explicitly programmed. ML has numerous applications, such as pattern recognition, forecasting upcoming trends, and judgement. It can handle massive amounts of huge vectors and tensors representing multidimensional data. To handle these processes on traditional computers, enormous time and computational resources are required. Unlike traditional computers, which use binary bits to compute, quantum computers (Q.C.) use qubits, which can simultaneously hold 0 and 1 combinations through superposition and entanglement. This makes *** an excellent choice for implementing ML algorithms because they are skilled at handling and post-processing large tensors. Although many of the models used for ML on quantum computers are based on concepts from their classical computing counterparts, the use of quantum computers has made them the better of the two. This paper assess the speed and complexity benefits of using quantum computers and gives a general overview of the state of knowledge regarding the use of ML on Q.C.

关键词： computers Quantum computing Tensors Quantum entanglement Computational modeling Qubit Machine learning

来源：评论

学校读者我要写书评

暂无评论

Highly Accurate Dynamic Gesture Recognition Method Based on Edge Intelligence 1

引用

3rd EAI international conference on Edge Computing and IoT, EAI ICECI 2022

作者： Changkai, Lu Yiwen, Liu Yanxia, Gao Yuanquan, Shi Xiaoning, Peng School of Computer and Artificial Intelligence Huaihua University Huaihua418000 China Key Laboratory of Wuling-Mountain Health Big Data Intelligent Processing and Application in Hunan Province Universities Huaihua418000 China Key Laboratory of Intelligent Control Technology for Wuling-Mountain Ecological Agriculture in Hunan Province Huaihua418000 China

ISBN: (数字)9783031289903

ISBN: (纸本)9783031289897

In recent years, gestures have been widely used in many fields. For example, human-computer interaction, virtual reality, gesture translation, etc. The reason for its rapid development is due to the emergence of deep learning and artificial intelligence under today’s society. Due to dynamic gestural interactions, such large intelligent models are often characterized by many parameters, large sample size, frequent parameter updates, and high communication volume. Based on this feature, we propose a cloud-based edge design architecture approach for gesture recognition based on an improved YOLOv5 network model optimization by changing different gestures, background interference, which uses a 21-layer model for the neural network. With the use of edge intelligence, the computational accuracy can be improved by 10.6% over the traditional YOLOv5 with a MAP value of 93.3%. The final recall rate is also improved by 3.6%. The parameter model is only 43.6% of the original one. This shows the practicality and operability of using edge computing as a technique in gesture recognition, as well as the small improvement cost and obvious effect. © 2023, ICST Institute for computer sciences, Social Informatics and Telecommunications Engineering.

关键词： Gesture recognition

来源：评论

学校读者我要写书评

暂无评论

Design and optimization of MobileNet neural network acceleration system based on FPGA

Design and optimization of MobileNet neural network accelera...

引用

international conference on Electronics, Communications and Information Technology (CECIT)

作者： Wenqiang Qin Zhongcheng Wu Jun Zhang Fang Li Institute of Physical Science and Information Technology Anhui University Hefei China Center for High Magnetic Field Science Hefei Institutes of Physical Science Chinese Academy of Sciences Hefei China

Aiming at the problem of low computational efficiency when convolutional neural network is deployed in embedded devices, this work proposes a convolution neural network acceleration architecture based on FPGA, and designs and implements a MobileNet neural network acceleration system based on FPGA. Firstly, the method of dynamic fixed-point quantization and operator fusion is designed to optimize the model. Secondly, the method of convolution block, parallel convolution calculation and data stream optimization is designed based on FPGA to improve the efficiency of convolution operation and system throughput. The system is tested on Xilinx PYNQ-Z2 platform. The average frame rate of the system is 6 fps and the power consumption is 2.45w. The system has the characteristics of low power consumption and low delay, which can effectively improve the operation efficiency of convolutional neural network algorithm in embedded devices.

关键词： Power demand Quantization (signal) Convolution Neural networks Parallel processing Throughput Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Lung Cancer Detection Using Convolutional Neural Network

Lung Cancer Detection Using Convolutional Neural Network

引用

international conference on Issues and Challenges in Intelligent Computing Techniques (ICICT)

作者： Dhyanendra Jain Prashant Singh Amit Kumar Pandey Mayank Singh Harikesh Singh Amarjeet Singh Department of CSE-AIML ABES Engineering College Ghaziabad India Department of computer science & engineering Sunder Deep Engineering College Ghaziabad India Department of CSE-DS ABES Engineering College Ghaziabad India Department of computer science & engineering JSS Academy of Technical Education Noida India

Automatic detection of defects and abnormalities in CT scan images has gain lot of importance in the recent times as because of the deteriorating quality of air almost everyone is facing one or the other type of lung related issues thus it is of esteem importance to study the computed tomography (CT) images of the pulmonary nodules to efficiently treat the diseases like lung cancer. The use of machine learning is an efficient way to distribute the work of doctors and process the large amount of data to produce accurate results on the go. Three phases of CT image pre-processing, Deep Learning, and Convolutional Neural Network use make up the diagnosis approach. The pre-processing converts raw data into usable form and deep learning algorithm assigns weight to the data, in the last stage CNN is use to conclude the health status of the lung, i.e. normal or abnormal.

关键词： Deep learning Computed tomography Lung Lung cancer Medical services Convolutional neural networks Tumors

来源：评论

学校读者我要写书评

暂无评论

Evaluation of Subjective Answers Using Machine Learning

Evaluation of Subjective Answers Using Machine Learning

引用

international conference on Issues and Challenges in Intelligent Computing Techniques (ICICT)

作者： Sneha G Shreya Shree G Tina Babu Rekha R Nair Department of Computer Science and Engineering School of Engineering Dayananda Sagar University Bengaluru India Department of Computer Applications School of Engineering Dayananda Sagar University Bengaluru India

Negative methods are currently used to evaluate subjective writing. The evaluation of the subjective responses is an essential responsibility. When a human analyses anything, the evaluation's quality can change depending on the person's emotions. All outcomes in machine learning are solely dependent upon the user's input data. To address this issue, our suggested method combines machine learning (ML) and natural language processing (NLP). To analyse the subjective response, our algorithm performs tasks including tokenizing words and phrases, classifying parts of speech, chunking and chinking, lemmatizing words, and word netting. Our suggested approach also offers the context's semantic meaning. There are two modules in our system. Extracting data from scanned photos is the initial step. Then arranging it properly, and the second is using ML and NLP to analyse the text obtained in the previous phase and assigning grades to it.

关键词： Machine learning algorithms Semantics Machine learning Writing Natural language processing Classification algorithms Data mining

来源：评论

学校读者我要写书评

暂无评论

Path planning based on fuzzy-control Dynamic Window Approach 3

Path planning based on fuzzy-control Dynamic Window Approach

引用

3rd international conference on Control and Intelligent Robotics, ICCIR 2023

作者： Chen, Wantong Yang, Qianqian Chen, Min Li, Xiaoqiang Liu, Zhuo Tianjin Key Lab for Advanced Signal Processing Civil Aviation University of China Tianjin China School of Electronic Information and Automation Civil Aviation University of China Tianjin China Beijing Sky Aviation Co. Ltd China Sichuan Jiuzhou Aerocont Technologies Co. Ltd China

ISBN: (纸本)9781510671867

A method integrating rapidly-exploring random tree (RRT) and improved dynamic window approach (DWA) is proposed to realize obstacle avoidance of mobile robots in complex dynamic obstacle environments. Based on the known environment information, the global optimal safe path is generated using the improved RRT algorithm. To address the problem of too many invalid nodes in the expansion of the RRT algorithm, the efficiency of the algorithm is improved by introducing a bidirectional alternating search (BAS) strategy;the forward search tree and the backward search tree alternate searching paths with new nodes as the target nodes until the paths meet;and the redundant nodes in the paths are removed using path node filtering to shorten the path. Secondly, the DWA algorithm is used to track the improved RRT algorithm to plan the path. When unknown obstacles appear in the environment, the weights of the DWA algorithm evaluation function are dynamically adjusted by fuzzy control to avoid the obstacles and return to the original route in time. Finally, the simulation experiments verify that the proposed improved fusion algorithm in complex dynamic environment has short running time, small path cost, and always keeps a safe distance from the obstacles to ensure the optimal path is tracked while safely avoiding the dynamic obstacles. © 2023 SPIE.

关键词： Fuzzy control

来源：评论

学校读者我要写书评

暂无评论

Research on patent classification based on hierarchical label semantics

Research on patent classification based on hierarchical labe...

引用

Education, Knowledge and Information Management (ICEKIM), international conference on

作者： Jie Chen Shu Zhao Fan Lu Feng Liu Yangping Zhang Key Laboratory of Intelligent Computing and Signal Processing Ministry of Education Anhui University Hefei China School of Computer Science and Technology Anhui University Hefei China

ISBN: (纸本)9781665416672

Patent classification is an essential task in patent information management and knowledge mining. Most existing studies are based on the textual content of individual patent texts (e.g., titles and abstracts) for classification, but the patent also has label information with hierarchical structure and semantic description. However, the semantics correlation of patent texts and their labels have been largely ignored. In this paper, we propose a novel framework called HLSPC for patent classification by leveraging the hierarchical semantics correlation of patent texts and their labels. Specifically, we first apply a patent representation learning module for capturing the semantics representation of patent texts and hierarchical labels. Then, we design a label attention learning module to build the semantics correlation between patent texts and hierarchical labels, which enhances patent representation. Finally, we deploy a multi-level fusion module to get the refined category prediction for each patent which can preserve both local and global hierarchical prediction information. Extensive experimental results on two English patent datasets demonstrate the effective power of the HLSPC model.

关键词： Representation learning Patents Correlation Semantics Text categorization Education Information management

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77页 << < 67 68 69 70 71 72 73 74 75 76 > >>

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：