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

1,576 篇 会议
1 篇 期刊文献

馆藏范围

1,577 篇 电子文献
0 种 纸本馆藏

日期分布

学科分类号

899 篇 工学
- 774 篇 计算机科学与技术...
- 533 篇 软件工程
- 253 篇 信息与通信工程
- 194 篇 控制科学与工程
- 130 篇 电气工程
- 84 篇 网络空间安全
- 78 篇 生物医学工程（可授...
- 75 篇 安全科学与工程
- 64 篇 交通运输工程
- 62 篇 生物工程
- 55 篇 电子科学与技术（可...
- 45 篇 动力工程及工程热...
- 43 篇 仪器科学与技术
- 42 篇 光学工程
- 42 篇 石油与天然气工程
306 篇 理学
- 164 篇 数学
- 83 篇 生物学
- 73 篇 统计学（可授理学、...
- 61 篇 物理学
- 37 篇 系统科学
- 33 篇 化学
267 篇 管理学
- 203 篇 管理科学与工程(可...
- 106 篇 图书情报与档案管...
- 84 篇 工商管理
- 34 篇 公共管理
114 篇 医学
- 80 篇 临床医学
- 77 篇 公共卫生与预防医...
- 64 篇 基础医学(可授医学...
51 篇 法学
- 48 篇 社会学
39 篇 经济学
- 39 篇 应用经济学
18 篇 文学
15 篇 教育学
11 篇 农学
2 篇 军事学
1 篇 艺术学

主题

193 篇 data models
157 篇 accuracy
153 篇 computational mo...
92 篇 training
86 篇 feature extracti...
86 篇 machine learning
77 篇 predictive model...
69 篇 data mining
68 篇 deep learning
63 篇 real-time system...
57 篇 big data
49 篇 adaptation model...
45 篇 security
44 篇 robustness
41 篇 decision making
40 篇 convolutional ne...
39 篇 cloud computing
36 篇 analytical model...
35 篇 neural networks
34 篇 optimization

机构

14 篇 lovely professio...
7 篇 shandong provinc...
7 篇 key laboratory o...
6 篇 college of mecha...
6 篇 institute of aer...
5 篇 lloyd institute ...
5 篇 college of intel...
5 篇 university of ch...
5 篇 national univers...
5 篇 department of co...
5 篇 shandong fundame...
5 篇 national univers...
5 篇 institute of aer...
4 篇 karnataka bangal...
4 篇 shanghai jiao to...
4 篇 school of comput...
4 篇 chitkara univers...
4 篇 new horizon coll...
4 篇 srm institute of...
4 篇 school of softwa...

作者

7 篇 nijhawan ginni
5 篇 jeanette miriam ...
5 篇 lu xiaobo
5 篇 singh navdeep
4 篇 nicola franco
4 篇 choudhry mani de...
4 篇 akhil karnam
4 篇 zhang rui
4 篇 yu zhang
4 篇 akshya j.
4 篇 lihui wang
4 篇 qu yuben
4 篇 wang lihui
4 篇 li lei
4 篇 dong chao
4 篇 dutt varun
4 篇 puri chetan
3 篇 yuangan wang
3 篇 junqi luo
3 篇 zhang lei

语言

1,273 篇 英文
303 篇 其他
4 篇 中文

检索条件"任意字段=2024 IEEE International Conference on Cognitive Computing and Complex Data"

共 1577 条记录，以下是771-780 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：

CLE: Context-Aware Local Explanations for High Dimensional Tabular data 23

CLE: Context-Aware Local Explanations for High Dimensional T...

引用

23rd ieee international conference on Machine Learning and Applications, ICMLA 2024

作者： Rahat, Fazle Hossain, M Shifat Ahmed, Md Rubel Ewetz, Rickard University of Central Florida OrlandoFL United States University of Florida GainesvilleFL United States

ISBN: (纸本)9798350374889

Explainable artificial intelligence (XAI) seeks to enhance the transparency, interpretability, and trustworthiness of AI models. One solution strategy for explaining complex AI models for high-dimensional tabular data is to approximate them locally using surrogate models. Surrogate models such as linear regression and decision trees are inherently interpretable and can be used as an explanation. However, it is challenging for linear regression and decision trees to provide meaningful explanations for data points far from the decision boundary. In this paper, we propose a framework that provides Context-aware Local Explanations for high-dimensional tabular data called CLE. We observe that the quality of explanations from different local models varies depending on the data point. The CLE framework uses the context around a data point to select the type of symbolic explanation. Moreover, we propose to utilize feature attributions to explain data points that are far from the decision boundary. The proposed method is evaluated using high-dimensional tabular datasets from the domains of power systems, breast cancer detection, heart disease detection, and website phishing detection. The experimental results show that CLE can provide meaningful local explanations for data points far from the decision boundary. The framework explains data points using three different types of local models and demonstrates a smooth trade-off between explanation accuracy and interpretability. It can be observed that a relatively simple decision tree can explain a data point with 92.31 % accuracy. © 2024 ieee.

关键词： Economic and social effects

来源：评论

学校读者我要写书评

暂无评论

Multimodal Knowledge Graph Vision-Language Models for Precision Retrieval and Inference in Embedded Systems

Multimodal Knowledge Graph Vision-Language Models for Precis...

引用

2024 ieee international conference on Robotics and Biomimetics, ROBIO 2024

作者： Li, Mingyi Li, Jiayin Liu, Hui Han, Lijin Liao, Dengting Zhang, Zekun Gao, Zong Liu, Baoshuai Jin, Zhongfeng School of Mechanical Engineering Beijing Institute of Technology Beijing100081 China School of Computing and Data Science Xiamen University Malaysia Selangor 43900 Malaysia Shanghai Zhangjiang Institute of Mathematicas Zhangjiang Institute of Shanghai Shanghai201203 China China North Vehicle Research Institute General Technology Department 100072 China Coordination Center of China GNational Computer Network Emergency Response Technical Team 100083 China

ISBN: (纸本)9781665481090

In light of the challenges associated with enhancing multimodal knowledge graph retrieval and improving embodied intelligence in dynamic environments, we propose the Multimodal Knowledge Graph Vision-Language System (MKGVL). This system is designed to enhance the reasoning and feedback capabilities of embodied intelligent systems by continuously updating the knowledge graph through real-time feedback from the Vision-Language Model (VLM). By integrating visual encoders, language models, and knowledge graph networks, MKGVL constructs a unified multimodal representation that enables adaptive decision-making and responsiveness to environmental changes. Experimental results show that MKGVL outperforms existing models in fine-grained retrieval tasks, achieving an 11.5% improvement in Rank1 accuracy and a mean Average Precision (mAP) of 97.49%. Further evaluations conducted on datasets such as ARKitScenes, MultiScan, and 3RScan highlight the model's robustness and adaptability. Additionally, MKGVL's deployment on embedded platforms like Jetson Orin demonstrates its efficiency in real-time multimodal tasks, particularly in resource-constrained environments. These findings underscore MKGVL's ability to deliver accurate and efficient multimodal processing, making it a strong solution for adaptive knowledge-based systems in complex settings. © 2024 ieee.

关键词： Knowledge graph

来源：评论

学校读者我要写书评

暂无评论

Dual-Level data Compression and Reduction in IoT Networks: Enhancing Efficiency through Sensor Node and Gateway Optimization

Dual-Level Data Compression and Reduction in IoT Networks: E...

引用

2024 international conference on Artificial Intelligence and Emerging Technology, Global AI Summit 2024

作者： Dutta, Pushan Kumar Bhattacharya, Pronaya Singh, Sushil Kumar El-Kenawy, El-Sayed M. Pandey, Richa School of Engineering and Technology Amity University Kolkata India Marwadi University Computer Engineering Department Gujarat Rajkot India Department of Communications and Electronics Delta Higher Institute of Engineering and Technology Mansoura Egypt Graphic Era Hill University Uttarakhand Haldwani India

ISBN: (纸本)9798350379716

The proliferation of Internet of Things (IoT) devices has led to unprecedented challenges in data management and transmission efficiency. This paper introduces a novel dual-level approach to data compression and reduction in IoT networks, addressing these challenges by optimizing data handling at both sensor node and gateway levels. Unlike conventional single-level techniques, our method provides a more comprehensive solution to data optimization in IoT ecosystems. At the sensor node level, we implement Run Length Encoding (RLE) compression, while at the gateway level, we integrate progressive data clustering and reduction strategies. This dual-level approach demonstrates significant improvements in data reduction compared to single-point optimization methods. Our comparative analysis reveals the synergistic effects of combining node-level compression with gateway-level data reduction, resulting in enhanced overall system performance. We evaluate the scalability and adaptability of our approach across diverse IoT applications, considering energy efficiency implications for resource-constrained devices. Additionally, we discuss alternative data reduction techniques such as attribute reduction, canonical polyadic decomposition, and edge computing-based filtering, contextualizing our method within the broader landscape of IoT data optimization. The paper also examines the impact of our approach on network bandwidth utilization and explores future directions for multi-level data optimization in complex IoT architectures. Our findings suggest that the proposed dual-level method offers a promising solution for managing the growing data challenges in IoT networks, paving the way for more efficient and scalable IoT systems. © 2024 ieee.

关键词： Encoding (symbols)

来源：评论

学校读者我要写书评

暂无评论

The Method of Object Saliency Detection in Remote Sensing Images Based on Gestalt Theory and Visual Attention 5

The Method of Object Saliency Detection in Remote Sensing Im...

引用

5th international conference on Intelligent computing and Human-Computer Interaction, ICHCI 2024

作者： Liu, Huan Xiao, Genfu College of Electronic and Information Engineering Jinggangshan University Key Laboratory of Jiangxi Electronic Data Control and Forensics Jiangxi Ji'An343009 China Jiangxi Engineering Laboratory of IoT Technologies for Crop Growth Jiangxi Ji'An343009 China College of Mechanical and Electronic Jinggangshan University Jiangxi Ji'An343009 China

ISBN: (纸本)9798350368284

There are some shortcomings in existing salient object detection methods of remote sensing images. For example, the extracting features are insufficient and they are always seriously interfered by complex background information. To solve these problems, a visual attention model based on Gestalt theory is proposed. First, a pyramid anisotropic scale space model is built, followed by the extraction of multi-scale, multi-directional low-And high-frequency visual features to construct multi-space saliency maps. Then each spatial saliency map can be adaptively fused based on the similarity principle of Gestalt theory. Comparison and analysis are implemented among our proposed method and some existing methods on the public natural image dateset ECSSD and remote sensing image dateset ORSSD. The experimental results show that the proposed method has higher detection accuracy than existing saliency detection methods, especially in the detection of remote sensing images. It is greatly demonstrated that the effectiveness and feasibility of the proposed method. © 2024 ieee.

关键词： Optical remote sensing

来源：评论

学校读者我要写书评

暂无评论

RFID-based Clothing Life Cycle Operation Management

RFID-based Clothing Life Cycle Operation Management

引用

2023 international conference on cognitive computing and complex data, ICCD 2023

作者： Huang, Songchen Huang, Liyan Lin, Shirong Heilan Home Group Co. Ltd Project Department Jiangyin China Heilan Home Group Co. Ltd Information Department Jiangyin China Changshu Institute of Technology Department of Big Data Suzhou China

ISBN: (纸本)9798350306293

Problems such as product production, scheduling and quality issues from supply chain enterprises, and product allocation by agents and stores, restrict the development of group companies. This usually manifests as the inability to guarantee the quality of the supplier's products and the opaque information on the goods at the supplier and agent end. Deployment cannot be carried out due to commercial interests, information blockage and other reasons, and store product information is not transparent and cannot be dispatched. Although the current intelligent manufacturing process in my country also emphasizes the effectiveness of identification technologies such as QR codes and barcodes, H Company also used QR codes and barcodes in conjunction with three-dimensional warehouses to manage the entire life cycle of goods in the early days. However, the inefficiency of QR codes and barcodes Seriously restricting the cost, accuracy and effectiveness of enterprise goods control. Although some companies have explored the application of RFID technology in warehousing and distribution, supermarket product management and other aspects, there is no way to use this technology to effectively manage the warehousing and warehousing, deployment, store management and other aspects in the case of multiple operators and massive quantities of goods. Reference cases and experiences. As the first large enterprise in China to use RFID technology in all aspects of goods management and control, H Company has explored the use of RFID as an information carrier in the production, quality inspection, stock in and stock out of goods in the past nine years. Information system integration and data analysis in warehouse, warehousing management, product allocation, store product control, product attention collection and other aspects have helped enterprises achieve effective cost reduction and efficiency improvement. © 2023 ieee.

关键词： Supply chains

来源：评论

学校读者我要写书评

暂无评论

Bi-LSTM Based Real-Time Human Activity Recognition From Smartphone Sensor data

Bi-LSTM Based Real-Time Human Activity Recognition From Smar...

引用

2024 international conference on Artificial Intelligence and Emerging Technology, Global AI Summit 2024

作者： Modukuri, Sai Vyshnavi Mogaparthi, Neha Burri, Sahithi Kalangi, Ravi Kiran Venkatrama Phani Kumar, S. Vfstr Deemed to be University Dept. of Cse Guntur India

ISBN: (纸本)9798350379716

Human activity recognition (HAR) has emerged as a key field of research in pervasive computing due to its wide range of applications in addressing real-world, human-centric challenges. Three or more sensors that are affixed to various body areas are used in the majority of multi-sensor techniques used in human activity recognition research. But for certain moves, a lot of sensors were unnecessary. With noisy and missing data, a bi-directional LSTM parallel layer can speed up feature extraction. The proposed methodology introduces a Bidirectional Long Short-Term Memory (BiLSTM) model, which incorporates both Linear Discriminant Analysis (LDA) for feature extraction and a univariate filter method for feature selection. This comprehensive approach significantly enhances model performance. Leveraging the UCI HAR dataset, our model achieves an impressive accuracy rate of 97%. This underscores the effectiveness of synergizing deep learning techniques with sophisticated feature engineering strategies. By leveraging the BiLSTM's inherent ability to capture temporal dependencies, alongside LDA's discriminative feature extraction and the filter method's dimensionality reduction, our methodology ensures robust activity recognition across diverse scenarios. Notably, this approach improves accuracy and enhances the model's adaptability to real-world applications, making it well-suited for addressing complex activity recognition challenges efficiently. © 2024 ieee.

关键词： Active learning

来源：评论

学校读者我要写书评

暂无评论

StaR Maps: Unveiling Uncertainty in Geospatial Relations 27

StaR Maps: Unveiling Uncertainty in Geospatial Relations

引用

27th ieee international conference on Intelligent Transportation Systems, ITSC 2024

作者： Flade, Benedict Kohaut, Simon Eggert, Julian Dhami, Devendra Singh Kersting, Kristian Honda Research Institute Europe GmbH Offenbach63073 Germany Artificial Intelligence and Machine Learning Lab Department of Computer Science Tu Darmstadt Darmstadt64283 Germany Tu Eindhoven Uncertainty in Artificial Intelligence Group Department of Mathematics and Computer Science MB Eindhoven5600 Netherlands Hessian Ai Centre for Cognitive Science Germany

ISBN: (纸本)9798331505929

The growing complexity of intelligent transportation systems and their applications in public spaces has increased the demand for expressive and versatile knowledge representation. While various mapping efforts have achieved widespread coverage, including detailed annotation of features with semantic labels, it is essential to understand their inherent uncertainties, which are commonly underrepresented by the respective geographic information systems. Hence, it is critical to develop a representation that combines a statistical, probabilistic perspective with the relational nature of geospatial data. Further, such a representation should facilitate an honest view of the data's accuracy and provide an environment for high-level reasoning to obtain novel insights from task-dependent queries. Our work addresses this gap in two ways. First, we present Statistical Relational Maps (StaR Maps) as a representation of uncertain, semantic map data. Second, we demonstrate efficient computation of StaR Maps to scale the approach to wide urban spaces. Through experiments on real-world, crowd-sourced data, we underpin the application and utility of StaR Maps in terms of representing uncertain knowledge and reasoning for complex geospatial information. © 2024 ieee.

关键词： Knowledge representation

来源：评论

学校读者我要写书评

暂无评论

Research on Enterprise data Assets Based on Fusion Neural Network Algorithm

Research on Enterprise Data Assets Based on Fusion Neural Ne...

引用

cognitive computing and complex data (ICCD), international conference on the

作者： Lili Dong Ruishuang Qi Tiantian Yang Business School Beijing Polytechnic Beijing China

ISBN: (数字)9798350352894

ISBN: (纸本)9798350352900

This paper presents a comprehensive approach for enterprise data asset processing, based on the Random Forest (RF) algorithm integrated with Back Propagation (BP) neural networks, to address the challenge of large-scale, high reliability, and real-time requirements for power grid data asset information management that traditional methods are unable to meet. This method not only ensures the reliability and timeliness of data processing, but also enhances the efficiency of data processing, playing a significant role in the scientific and rational exploration of the value of big data for enterprises. By utilizing the Random Forest algorithm classifier to categorize data types of the power grid and inputting them into the BP neural network for analysis and learning, the proposed algorithm, when integrated into the construction of an enterprise digital asset management system, yields corresponding results for system service requirements. Experimental results demonstrate that the processing time of cloud-edge collaborative data is significantly shorter than that of cloud computing, and the classification accuracy of the proposed technology exceeds 92%. Moreover, the load forecasting results exhibit minimal errors, thereby substantiating the effectiveness and reliability of this technology.

关键词： Cloud computing Load forecasting Neural networks Collaboration data processing Power grids Classification algorithms Asset management Reliability Random forests

来源：评论

学校读者我要写书评

暂无评论

Multimodal Machine Learning for Early Detection of Autism in Children: Integrating Gestures and Mood Analysis 2

Multimodal Machine Learning for Early Detection of Autism in...

引用

2nd DMIHER international conference on Artificial Intelligence in Healthcare, Education and Industry, IDICAIEI 2024

作者： Puri, Chetan Ghodeswar, Ujwala Reddy, K.T.V. Sharma, Mansi Warudkar, Sahil Department of Computer Science and Design Wardha India Yeshwantrao Chavan College of Engineering Department of Electronics Engineering Nagpur India Department of Artificial Intelligence and Data Science Wardha India

ISBN: (纸本)9798331528713

Autism spectrum disorder (ASD) is characterized by neurological disorders and challenges with interpersonal communication, communication, and schedule behaviour. Early distinguishing proof of ASD is vital to optimize the intervention and progress long-term results. This paper analyses the potential of numerous machine learning procedures for early location of ASD in children. We propose a novel approach that combines gesture assessment with cognitive evaluation to capture a comprehensive picture of a child's behaviour. Side effect analysis will focus on highlights such as body language, hand movements, and eye contact, which can give profitable bits of knowledge into the social and communication designs of children with ASD. Therapy will utilize facial expressions, tone of voice, and body language to survey a child's emotional state. The combination of these strategies empowers the machine learning show to recognize complex structures that will be characteristic of ASD. This consider has the potential to move forward the exactness and productivity of ASD diagnosis in children. The proposed strategy can be connected in different situations, such as during routine testing or through a portable application. Early and precise conclusion can clear the way for convenient intervention and back for children with ASD, eventually driving to positive long-term results. © 2024 ieee.

关键词： Diseases

来源：评论

学校读者我要写书评

暂无评论

Vortex-induced Vibration of Two Rigidly Coupled Tandem Cylinders: A Numerical Study

Vortex-induced Vibration of Two Rigidly Coupled Tandem Cylin...

引用

cognitive computing and complex data (ICCD), international conference on the

作者： Weiya Zou Suxiang Guo Mengtian Song College of Mechanical and Marine Engineering Beibu Gulf University Qinzhou China

ISBN: (数字)9798350352894

ISBN: (纸本)9798350352900

This study explores the intricate mechanical mechanisms underlying vortex-induced vibrations by employing the multi-body force element theory. Numerical simulations are conducted on a 2-DOF rigidly coupled double-cylinder sys-tem, considering a uniform incoming flow with a Reynolds number of Re = 150, a mass ratio of m∗ = 2, a damping ratio of ζ = 0, and an aspect ratio L/D = 4. The vortex force analysis, which based on the force element theory and quantifies the contributions of all fluid elements with non-zero vorticity to the force exerted on the cylinders. The results indicate that the force contribution due to vortex-induced vibrations within the lock-in region differs from that outside of it. Moreover, as the vortex shedding pattern changes, the distribution of the force element components also varies.

关键词： Vibrations Damping Fluids Drag Force 2-DOF Numerical simulation Synchronization cognitive systems

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158页 << < 74 75 76 77 78 79 80 81 82 83 > >>

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：