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

14,883 篇 会议
54 篇 期刊文献
11 册 图书

馆藏范围

14,948 篇 电子文献
0 种 纸本馆藏

日期分布

学科分类号

9,199 篇 工学
- 7,511 篇 计算机科学与技术...
- 6,337 篇 软件工程
- 3,600 篇 信息与通信工程
- 2,136 篇 生物工程
- 1,723 篇 控制科学与工程
- 1,541 篇 电气工程
- 1,113 篇 生物医学工程（可授...
- 899 篇 电子科学与技术（可...
- 849 篇 动力工程及工程热...
- 720 篇 光学工程
- 707 篇 机械工程
- 698 篇 网络空间安全
- 681 篇 交通运输工程
- 629 篇 安全科学与工程
- 526 篇 化学工程与技术
- 409 篇 仪器科学与技术
4,986 篇 理学
- 2,391 篇 数学
- 2,207 篇 生物学
- 996 篇 物理学
- 924 篇 统计学（可授理学、...
- 621 篇 化学
- 394 篇 系统科学
2,638 篇 管理学
- 1,442 篇 图书情报与档案管...
- 1,382 篇 管理科学与工程(可...
- 680 篇 工商管理
916 篇 医学
- 774 篇 临床医学
- 762 篇 基础医学(可授医学...
- 536 篇 药学(可授医学、理...
- 391 篇 公共卫生与预防医...
652 篇 法学
- 468 篇 社会学
287 篇 经济学
255 篇 农学
113 篇 教育学
67 篇 文学
46 篇 军事学
1 篇 哲学
1 篇 历史学
1 篇 艺术学

主题

521 篇 deep learning
303 篇 convolutional ne...
286 篇 internet of thin...
261 篇 machine learning
220 篇 neural networks
218 篇 feature extracti...
194 篇 forecasting
190 篇 convolution
184 篇 blockchain
180 篇 long short-term ...
170 篇 training
161 篇 network security
145 篇 support vector m...
140 篇 wireless sensor ...
136 篇 computational mo...
130 篇 predictive model...
120 篇 deep neural netw...
120 篇 generative adver...
116 篇 data models
110 篇 object detection

机构

111 篇 chitkara univers...
106 篇 the islamic univ...
65 篇 national univers...
52 篇 school of comput...
40 篇 medical technica...
37 篇 university of el...
34 篇 school of cyber ...
32 篇 maharishi school...
32 篇 lovely professio...
32 篇 peng cheng labor...
31 篇 college of mlt a...
29 篇 school of automa...
29 篇 uttaranchal inst...
27 篇 school of comput...
27 篇 department of co...
26 篇 university of sc...
26 篇 computer science...
26 篇 shandong provinc...
26 篇 college of infor...
26 篇 school of comput...

作者

26 篇 yang yang
25 篇 chen chen
24 篇 liu yang
19 篇 kukreja vinay
17 篇 pareek piyush ku...
15 篇 mohit tiwari
15 篇 wang wei
14 篇 shiva mehta
14 篇 wei li
14 篇 sakorn mekruksav...
13 篇 wang lei
13 篇 wang jing
13 篇 liu xin
13 篇 chauhan rahul
12 篇 zhang lei
12 篇 qiao junfeng
12 篇 anuchit jitpatta...
11 篇 anjali t.
11 篇 yu wang
11 篇 al-attabi kassem

语言

14,557 篇 英文
389 篇 其他
76 篇 中文
1 篇 土耳其文

检索条件"任意字段=International Conference on Data Science and Network Engineering, ICDSNE 2023"

共 14948 条记录，以下是41-50 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：

Dilated convolution model for lightweight neural network 2nd

Dilated convolution model for lightweight neural network

引用

2nd international conference on Next-Generation Computing and Information Systems, ICNGCIS 2023

作者： Gupta, Sachin Goyal, Priya Vyas, Bhuman Shabaz, Mohammad Bala, Suchitra Sameen, Aws Zuhair Department of CSE Maharaja Agrasen Institute of Technology India Department Computer Science and Engineering Manipal University Jaipur India Credit Acceptance Canton United States Model Institute of Engineering and Technology J&K Jammu India ICT & Cognitive Systems Sri Krishna Arts And Science College India College of Medical Techniques Al-Farahidi University Baghdad Iraq

ISBN: (纸本)9781032738659

Lightweight convolutional neural networks are being studied further in order to better deploy deep convolutional neural networks to edge devices, minimize the number of model parameters in deep neural networks, and reduce network complexity. On accomplish the lightweight goal, the full convolution is performed to the remaining network structure. To increase the light effect, it is merged with point-by-point convolution to build an improved dilated convolution lightweight approach. The enhanced dilated convolution is coupled with conventional convolution to lessen the attenuation of accuracy, and a lightweight fusion dilated convolution is presented. The improved dilated convolution light approach offers the most substantial lightweight benefit, according to the data. Furthermore, the lightweight fusion dilated convolution approach decreases the amount of model parameters and offers the best speed-accuracy trade-off. © 2025 The Author(s).

关键词： Convolution

来源：评论

学校读者我要写书评

暂无评论

Identification of Financial Fraud in Listed Companies Based on Bayesian-LightGBM Model 24

Identification of Financial Fraud in Listed Companies Based ...

引用

2nd international conference on Artificial Intelligence, Systems and network Security, AISNS 2024

作者： Zhao, Runtong Zhang, Li Li, Zhuosong School of Computer Science Beijing Information Science and Technology University Beijing Beijing China

ISBN: (纸本)9798400711237

In line with the priorities outlined in the 20th Party Congress report, which emphasizes enhancing financial supervision and mitigating systemic risks, this paper introduces a Bayesian-optimized LightGBM model for improving the accuracy of financial fraud detection in listed companies. The proposed model integrates a hybrid set of indicators, including executive attributes, ESG performance, and innovation capabilities. Using publicly available firm data from 2014 to 2023, the model performs risk identification with a balanced dataset achieved through the KMeans-SMOTE technique to address data skewness. Bayesian optimization is employed to fine-tune the model’s hyperparameters, significantly enhancing its predictive accuracy. Experimental results demonstrate a prediction accuracy exceeding 95%, underscoring the model’s potential in detecting financial fraud, mitigating risks, and contributing to the stability and sustainable growth of financial markets. © 2024 Copyright held by the owner/author(s).

关键词： Financial markets

来源：评论

学校读者我要写书评

暂无评论

Efficient data visualization through novel recurrent neural network-based dimension reduction 2nd

Efficient data visualization through novel recurrent neural ...

引用

2nd international conference on Next-Generation Computing and Information Systems, ICNGCIS 2023

作者： Sharma, Saurabh Vijyal, Shafalika Upadhyay, Navin Mani Department of Computer Science & Engineering Model Institute of Engineering and Technology J&K Jammu India

ISBN: (纸本)9781032738659

data visualization can be a challenging task in our everyday lives, especially when dealing with large and complex datasets. Multiple researchers have dedicated their efforts to this topic and have put forth various solutions, such as t-SNE, UMAP, and the Tramp technique. These techniques maintain the overall structure, but they do not accurately depict the local structure in the visualization. Therefore, many of them are not suitable for all types of data sets. Because of these issues, the demand for other novel approaches for data visualization will be high. In this paper, the proposed work is based on a novel Recurrent Neural network (RNN) based dimension reduction technique to correctly visualize the selected real-world data set. The RNN models can reliably visualize and forecast the numeric values for a general-purpose machine architecture, but for special-purpose machines, the construction of RNN architecture construction has yet to be devised. The proposed model is based on a trial and error-based iteration technique for multiple input parameters. The major challenge for the selection of such input parameters is: that when there are many input factors, it is hard to determine which ones affect model prediction. This problem is reflected as the "curse of dimensionality." The proposed method shows a significant improvement of up to 3% compared to all three compared models (t-SNE, UMAP, & Tramp). © 2025 The Author(s).

关键词： data visualization

来源：评论

学校读者我要写书评

暂无评论

A Federated Learning network Intrusion Detection System for Multiple Imbalances

A Federated Learning Network Intrusion Detection System for ...

引用

2025 IEEE international conference on Acoustics, Speech, and Signal Processing, ICASSP 2025

作者： Zeng, Yifan Zheng Li, Jian School of Computer Science and Engineering Sun Yat-sen University Guangzhou China Yunnan Key Laboratory of Service Computing Yunnan University of Finance and Economics Kunming China Jinan China

ISBN: (纸本)9798350368741

Centralized training of deep learning-based network intrusion detection systems (DLNIDS) raises privacy concerns and incurs huge overhead. Federated learning (FL), while preserving privacy, confronts challenges including size imbalance, heterogeneous and global imbalance. To address these issues, this paper proposes a Self-Balancing Federated learning network Intrusion Detection System (SBFedNIDS) for accurate and efficient network intrusion detection while preserving privacy and tackling negative impact caused by multiple imbalances resulting from FL. SBFedNIDS can efficiently mitigate model bias cause by multiple imbalances and addresses imbalances at data-level via federated cost sensitive learning (FCSL) and client synthetic minority over-sampling technique (CSMOTE), without requiring additional training resources, unlike generative models. Extensive experiments on a benchmark dataset show that SBFedNIDS outperforms baselines in multiple unbalanced scenarios and even surpasses centralized training in several settings. © 2025 IEEE.

关键词： data Imbalance Deep Learning Federated Learning network Intrusion Detection

来源：评论

学校读者我要写书评

暂无评论

Adaptive PD Neural network Tracking Control for the Uncertain Robot Manipulator with Unmatched Disturbance 26

Adaptive PD Neural Network Tracking Control for the Uncertai...

引用

26th international conference on Industrial Technology, ICIT 2025

作者： Wen, Jingdong Ren, Ling Peng, Chenchen Qi, Runhua School of Information and Control Engineering Qingdao University of Technology Qingdao China

ISBN: (纸本)9798331521950

This paper addressed the tracking control problem of the robot manipulator with uncertainties and unmatched disturbance by PD control based on adaptive neural network. Adaptive control methods can deal with the control problem of systems with nonlinear and uncertain dynamics, which use measured data of system trajectory in order to learn and compensate the uncertainties and external disturbances. In this work, a nominal PD control law is used to achieve a sub-optimal performance, and a scheme based on a neural network is implemented to act as a nonlinear compensation whose task is to improve the performance of the nominal controller. A two-degree-of-freedom robot manipulator is proposed to validate the proposed scheme. © 2025 IEEE.

关键词： Self tuning control systems

来源：评论

学校读者我要写书评

暂无评论

Impact of Receiver Orientation on the QoS of the VLC- Enabled Flying Base Station network 17

Impact of Receiver Orientation on the QoS of the VLC- Enable...

引用

17th international conference on COMmunication Systems and networkS, COMSNETS 2025

作者： Das, Ankana Panda, Kirtan Gopal Naresh Kumar, Murala Laxmi Sen, Debarati Chakraborty, Sandip IIT G. S. Sanyal School of Telecommunications Kharagpur India IIT Department of Computer Science and Engineering Kharagpur India

ISBN: (纸本)9798331531195

The 5G and beyond networks aim to outperform their predecessors in terms of data rate, quality of service (QoS), and latency reduction. Visible light communication (VLC) frequencies are widely explored to enable future-generation communications because of their large, license-free bandwidth. VLC-enabled unmanned aerial vehicles can serve as VLC-enabled flying base stations (V-FBSs) and can significantly contribute towards the increase in coverage and improve the network throughput. However, most studies on VLC-enabled unmanned aerial vehicles have neglected the effect of random receiver orientation in their performance analysis of the networks in terms of outage and data rates. In this paper, we analyze the impact of receiver device orientation on the QoS within the V-FBS network. We thoroughly analyze the permissible degrees of freedom for receiver movement, exploring how it influences the angle of incidence and, consequently, the line of sight (LoS) link between the V-FBS and user equipment (UE). © 2025 IEEE.

关键词： Unmanned aerial vehicles (UAV)

来源：评论

学校读者我要写书评

暂无评论

Development of Prediction Model for Chemicals in Fresh Fruits Using Artificial Neural network 5th

Development of Prediction Model for Chemicals in Fresh Fruit...

引用

5th international conference on data science, Machine Learning and Applications

作者： Raj, G. Bhupal Raghuram, Kadambari Varun, V. L. Sharma, Dilip Kumar Kapila, Dhiraj Kapila, Dhiraj SR Univ Sch Agr Warangal Andhra Pradesh India JNTUK Univ Coll Engn Kakinada Autonomous Comp Sci & Engn Kakinada Andhra Pradesh India SJB Inst Technol Dept Math Bengaluru India Jaypee Univ Engn & Technol Dept Math Guna Madhya Pradesh India Graph Era Hill Univ Sch Comp Bhimtal Uttarakhand India Lovely Profess Univ Dept Comp Sci & Engn Phagwara Punjab India

ISBN: (纸本)9789819780334;9789819780310;9789819780303

The objective of this investigation was to construct an artificial neural network (ANN) prediction model for chemicals like anthocyanin, titratable acidity, total solids soluble (TSS),vitamin C, titratable/TSS, and overall carotenoids levels of peach fruit employing surface color quantities, single fruit mass, liquid quantity, and sphericity percentage. In the initial hidden layer, an ANN framework with 6 inputs and fifteen neurons was built to predict 6 chemical compositional variables. Sensitivity testing found that liquid quantity was the most essential factor for determining titratable acidity,vitamin C, and titratable/TSS acidity. Furthermore, sphericity contributes 23.7% to anthocyanin and 24.0% to the overall carotenoids. Also, the color on TSS prediction had the largest contributing proportion of 20.8% when contrasted to the other characteristics. Chroma accounted for all parameters at varying levels ranging from 5.2 to 19.3%. Also, fruit mass attributed to every parameter at varying rates ranging from 16.6 to 23.4%. The ANN prediction approach represents a viable instrument for predicting the chemical compositional values of peach fruits at certain intended limits.

关键词： Artificial neural network Prediction model Chemicals Peach fruit and Anthocyanin

来源：评论

学校读者我要写书评

暂无评论

High-quality Holography with Progressive Learning and Wrapped Phase Activation 4

High-quality Holography with Progressive Learning and Wrappe...

引用

4th international Computational Imaging conference, CITA 2024

作者： Yuan, Ganzhangqin Tsinghua Shenzhen International Graduate School Tsinghua University China

ISBN: (纸本)9781510688834

This work presents a novel approach for generating high-quality, phase-only holograms by integrating deep learning with optical principles, addressing challenges in hologram generation accuracy and efficiency. We propose a Progressive Learning network (PLN) that optimally translates amplitude data into the phase domain, using a multi-stage architecture for gradual refinement. Additionally, our Wrapped Phase Activation (WPA) function overcomes traditional activation limitations by encapsulating phase periodicity, ensuring phase values remain consistent with physical holographic constraints. Experimental results demonstrate the PLN's ability to reconstruct high-resolution images with superior PSNR and SSIM metrics, underscoring the method's potential for advancing holographic display quality. © 2025 SPIE.

关键词： Holograms

来源：评论

学校读者我要写书评

暂无评论

Brillouin Frequency Shift Extraction for BOTDA Based on Gramian Angular Fields 4

Brillouin Frequency Shift Extraction for BOTDA Based on Gram...

引用

4th international Computational Imaging conference, CITA 2024

作者： Zhu, Borong Zhang, Zhihao Qian, Yuhao Ma, Xiaole Wang, Liang Yu, Kuanglu Beijing Key Laboratory of Advanced Information Science and Network Technology Beijing100044 China Institute of Information Science School of Computer and Information Technology Beijing Jiaotong University Beijing100044 China National Engineering Laboratory for Next Generation Internet Access System School of Optics and Electronic Information Huazhong University of Science and Technology Wuhan430074 China

ISBN: (纸本)9781510688834

To accurately extract Brillouin frequency shift of BOTDA with large sweeping step sizes, a novel structure of GAFCNN is proposed, combining time series coding with convolutional neural networks. The experimental data validation results demonstrate that the GAFCNN is capable of obtaining more accurate results under large sweep steps and low signal-to-noise ratios (SNRs) than other current methods. © 2025 SPIE.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

An Improved Deep Learning Framework Based on Multi-Scale Convolutional Architecture for Road Crack Detection 2nd

An Improved Deep Learning Framework Based on Multi-Scale Con...

引用

2nd international conference on data science and network engineering, icdsne 2024

作者： Idris, Idris Ya’u Ya’u, Badamasi Imam Ali, Usman Gulzar, Yonis Department of Computer Science School of Science and Technology Federal Polytechnic Bauchi Bauchi743001 Nigeria Department of Mathematical Sciences Faculty of Science Abubakar Tafawa Balewa University Bauchi740272 Nigeria Gombe760253 Nigeria Department of Management Information Systems College of Business Administration King Faisal University Al Ahsa31982 Saudi Arabia

ISBN: (纸本)9789819783359

In addition to serving as a means of transportation, a highway connects the local economy. But as the pavement ages, several flaws including cracks, potholes, and deformation gradually show up on the surfaces of the road. Crack evaluation is typically done by hand using field surveys performed by humans. Nevertheless, these labor-intensive, time-consuming, manual survey methods are not reproducible or repeatable and place surveyors in dangerous situations. This proposes a novel deep-learning framework for road crack detection based on multi-scale convolutional architecture. To address the challenges of object occlusion, soft non-maximal suppression (NMS) is applied across crack proposals at various feature scales. The experimental results show that the introduced model attains an accuracy of 0.9989 and better detection performance across four distinct object proposal building block (OPBB) architectures. Thus, our model outperforms the benchmark models in every instance of OPBBs. In this way, the problem of large object scale variation in road crack images with different object occlusion challenges has been tackled, and the positive images are divided into a set of semantically significant regions, such as the road surface and cracks. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.

关键词： Deep learning

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500页 << < 1 2 3 4 5 6 7 8 9 10 > >>

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：