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

705 篇 会议
8 篇 期刊文献
4 册 图书

馆藏范围

718 篇 电子文献
0 种 纸本馆藏

日期分布

学科分类号

340 篇 工学
- 282 篇 计算机科学与技术...
- 200 篇 软件工程
- 114 篇 信息与通信工程
- 57 篇 控制科学与工程
- 52 篇 生物医学工程（可授...
- 46 篇 生物工程
- 40 篇 电气工程
- 31 篇 电子科学与技术（可...
- 24 篇 光学工程
- 24 篇 安全科学与工程
- 23 篇 动力工程及工程热...
- 21 篇 机械工程
- 20 篇 交通运输工程
- 19 篇 网络空间安全
- 15 篇 仪器科学与技术
- 13 篇 建筑学
163 篇 理学
- 101 篇 数学
- 54 篇 生物学
- 41 篇 统计学（可授理学、...
- 34 篇 物理学
- 20 篇 化学
- 18 篇 系统科学
110 篇 管理学
- 70 篇 管理科学与工程(可...
- 55 篇 图书情报与档案管...
- 44 篇 工商管理
58 篇 医学
- 43 篇 基础医学(可授医学...
- 42 篇 临床医学
- 35 篇 药学(可授医学、理...
26 篇 法学
- 23 篇 社会学
17 篇 教育学
- 14 篇 教育学
11 篇 经济学
6 篇 农学
4 篇 文学

主题

35 篇 cognitive radio
22 篇 cognitive system...
15 篇 machine learning
13 篇 computational mo...
12 篇 deep learning
11 篇 feature extracti...
9 篇 big data
9 篇 accuracy
8 篇 internet of thin...
8 篇 decision making
7 篇 electroencephalo...
7 篇 neural networks
7 篇 semantics
7 篇 fuzzy cognitive ...
7 篇 data models
6 篇 object detection
6 篇 edge computing
5 篇 covid-19
5 篇 cognitive comput...
5 篇 data mining

机构

8 篇 college of intel...
6 篇 fraunhofer insti...
6 篇 tianjin key labo...
6 篇 uttaranchal inst...
5 篇 institute of art...
5 篇 anhui provincial...
5 篇 lovely professio...
5 篇 tianjin key labo...
5 篇 college of compu...
4 篇 school of comput...
4 篇 school of comput...
4 篇 centre for inter...
4 篇 college of mecha...
4 篇 collage of engin...
3 篇 symbiosis instit...
3 篇 anhui university...
3 篇 copelabs - cogni...
3 篇 school of comput...
3 篇 university of ch...
3 篇 univ connecticut...

作者

4 篇 zhao haifeng
4 篇 gayathri n.
4 篇 dutt varun
4 篇 haifeng zhao
3 篇 kanna r. kishore
3 篇 lorenz jeanette ...
3 篇 wang tao
3 篇 wenbin zhang
3 篇 jeanette miriam ...
3 篇 godinho antónio
3 篇 mankun zhao
3 篇 wang li
3 篇 yang jinzhu
3 篇 chao dong
3 篇 zhang kai
3 篇 qu yuben
3 篇 anandakumar h.
3 篇 r. kishore kanna
3 篇 anita gehlot
3 篇 bhasin harsh

语言

682 篇 英文
33 篇 其他
10 篇 中文

检索条件"任意字段=2023 International Conference on Cognitive Computing and Complex Data, ICCD 2023"

共 718 条记录，以下是341-350 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：

TGC-YOLO: Detection Model for Small Objects in UAV Image Scene

TGC-YOLO: Detection Model for Small Objects in UAV Image Sce...

引用

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

作者： Taoyang Jin Wenhao Wang Chenjin Sun Zhenyang Yu Yanlun Wu Xin Chen Faculty of Computer Engineering Huaiyin Institue of Technology Huaian China

ISBN: (数字)9798350352894

ISBN: (纸本)9798350352900

In the field of drone target detection, existing object detection models often have problems of missed detection and false detection when dealing with challenges such as scale changes, dense targets and irregular arrangement of small targets. Therefore, this paper proposes a new detection model TGC-YOLO. Firstly, the EMA attention mechanism module is introduced to encode global information, and pixel-level features are further aggregated through dimensional interaction, which effectively reduces the attention to irrelevant information and maintains good feature extraction capabilities. Secondly, in terms of network structure, the FasterBlock module is used to replace the traditional BottleNeck module in C2f in YOLOv8n, so as to design a lightweight FasterC2f module, which reduces the number of parameters while ensuring the accuracy of the model. Thirdly, the Slim-neck structure is adopted on the Neck layer, and the model's detection ability for small objects is enhanced through the combination of GSConv and VoV-GSCSP. Then, the TGC three-channel feature fusion structure is designed based on GSConv to effectively aggregate multi-scale feature maps, enhance the feature fusion ability of the model, and improve the performance of small target detection. Finally, the dynamic head (DyHead) based on the attention mechanism is introduced to further improve the accuracy of small target detection by combining the three attention mechanisms of scale, space and task. Compared with YOLOv8n, TGC-YOLO has achieved 7.7%, 6.8% and 7.4% improvement in mAp@50, Precision and Recall respectively. Meanwhile, the model size is reduced by 0.1MB, enabling fast and accurate detection of small targets.

关键词： Accuracy Attention mechanisms Head Aggregates Object detection Feature extraction Autonomous aerial vehicles Neck cognitive systems Drones

来源：评论

学校读者我要写书评

暂无评论

Chiplet Solution with FO-MCM Package in Edge and Cloud computing (IMPACT 2023) 18

Chiplet Solution with FO-MCM Package in Edge and Cloud Compu...

引用

18th international Microsystems, Packaging, Assembly and Circuits Technology conference, IMPACT 2023

作者： Ho, David James Su, Po Yuan Pu, Jacy Wang, Yu Po No. 123 Sec 3 Chung Shan Rd. Tantzu Taichung Taiwan

ISBN: (纸本)9798350384123

Since the Meta, Amazon, Google and Microsoft are the popular social media and search website related with our daily life, the artificial intelligence (AI) with cloud computing become one of the most important for semiconductor industry. The cloud computing, high performance computing and artificial intelligence solutions require big data analysis processing with faster connections than ever, and all of these will need to have advanced technology supporting. The rise in energy costs and the increasing demand for sustainability to reduce environmental impacts further increase people's desire for high performance and high efficiency computing. The complex dataset has been tremendously grown on commercial application and widespread adoption of deep learning and neural networks. The advanced Node with System on Chip (SoC) chip size extension may the simplest design solution for good electrical performance, but the low yield rate cause of very expensive cost. The split die integration in package is the best solution to increase gross die with wafer good yield rate for cost effective [1]. Please see the Figure 1. The advantage of Chiplet The demand for higher functionality devices drive integration technologies to overcome limitations in Moore's Law and the Fan Out Multi Chip Module (FO-MCM) package can take the role for Cloud computing to Edge computing. Please see the Figure 2. FO-MCM Package. Today, the consumer product always requests not only thiner and power stamina but also high speed and massive connectivity for data transmission. The FO-MCM package can do the homogeneous integration and heterogeneous integration for each of different application because the cloud computing and Edge computing need to met the high performance and good electronic performance design requirement. That is the reason FO-MCM package solution can be the representative for homogeneous integration and heterogeneous integration. In this paper, we would like to discuss what the advantage for F

关键词： System-on-chip

来源：评论

学校读者我要写书评

暂无评论

SLEEPWISE: A Continuous Sleep Monitoring and cognitive Evaluation Platform in Ambient Residential Environment 46

SLEEPWISE: A Continuous Sleep Monitoring and Cognitive Evalu...

引用

46th Annual international conference of the IEEE Engineering in Medicine and Biology Society, EMBC 2024

作者： Jin, Shuwen Wang, Danqiong Ma, Xiao Li, Tao Lin, Feng Yu, Lei Zhang, Qing Zhejiang Lab Research Center for Frontier Fundamental Studies Hangzhou China Third Hospital of Shanxi Medical University Shanxi Bethune Hospital Shanxi Academy of Medical Sciences Tongji Shanxi Hospital Taiyuan China Huazhong University of Science and Technology Tongji Hospital Tongji Medical College Wuhan China Complex Systems Research Center Shanxi University Key Laboratory of Complex Systems and Data Science of Ministry of Education Shanxi China

ISBN: (纸本)9798350371499

Age-related cognitive decline presents a significant health challenge for older adults, with no specific medication available to counteract it. Early detection of cognitive decline is crucial for timely intervention and effective management. Sleep status plays a vital role in evaluating cognitive function, as disrupted sleep patterns are associated with cognitive decline and increased risk of neurodegenerative conditions. Existing methods for assessing sleep status, such as self-report questionnaires, actigraphy, and polysomnography, lack the ability to consistently monitor sleep status over a long period. In this paper we introduced SLEEPWISE, an AI-powered platform deployed in residential environments for continuous ambient sleep monitoring to assess the cognitive well-being of older adults. SLEEPWISE utilizes non-contact pads with highly sensitive piezoelectric sensors to monitor sleep parameters such as duration and efficiency, which are transmitted daily to the server. Moreover, we have also developed a gamified module for SLEEPWISE, allowing an objective assessment of daily cognitive functions. This module aids SLEEPWISE in establishing the correlation models between sleep and cognitive health. To evaluate the effectiveness of SLEEP-WISE, a pilot study was conducted with participants recruited from a local hospital. During the 30-days trials, SLEEPWISE identified a negative impact on congnitive performance associated with increased nocturnal body movements and getting out of bad. These findings emphasize the potential of SLEEPWISE as an early screening tool for evaluating daily cognitive health and well-being. © 2024 IEEE.

关键词： Sleep research

来源：评论

学校读者我要写书评

暂无评论

Design and Research on international Market Demand Model of Construction Machinery Based on data Mining Technology 12th

Design and Research on International Market Demand Model of ...

引用

12th international conference on Frontier computing, FC 2022

作者： Jing, Zhang Shandong Institute of Commerce and Technology Shandong Jinan250103 China

ISBN: (纸本)9789819914272

With the gradual recognition of China’s construction machinery in the international market, more and more construction machinery manufacturing enterprises regard entering the international construction machinery market as one of the important contents of enterprise marketing. In 2004, China exported 1.852 billion US dollars of construction machinery main engines to 164 countries, an increase of 76.6% over 2003. There are 888 kinds of products, but there are still some problems. international trade is accompanied by risks. With China's construction machinery participating in the competition in the international market, construction machinery enterprises are facing an increasingly multilateral and complex trade environment, and the competition in the world is becoming increasingly fierce. Opening up the international construction machinery market has played an important role in product quality, product reliability and marketing strategy. Therefore, this paper studies the design of international market demand model of construction machinery based on data mining technology. © 2023, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

关键词： Competition

来源：评论

学校读者我要写书评

暂无评论

Robotic Packaging Optimization with Reinforcement Learning 19

Robotic Packaging Optimization with Reinforcement Learning

引用

19th IEEE international conference on Automation Science and Engineering, CASE 2023

作者： Drijver, Eveline Pérez-Dattari, Rodrigo Kober, Jens Santina, Cosimo Della Ajanovic, Zlatan Delft University of Technology Cognitive Robotics Department Delft2628 CD Netherlands

ISBN: (纸本)9798350320695

Intelligent manufacturing is becoming increasingly important due to the growing demand for maximizing productivity and flexibility while minimizing waste and lead times. This work investigates automated secondary robotic food packaging solutions that transfer food products from the conveyor belt into containers. A major problem in these solutions is varying product supply which can cause drastic productivity drops. Conventional rule-based approaches, used to address this issue, are often inadequate, leading to violation of the industry's requirements. Reinforcement learning, on the other hand, has the potential of solving this problem by learning responsive and predictive policy, based on experience. However, it is challenging to utilize it in highly complex control schemes. In this paper, we propose a reinforcement learning framework, designed to optimize the conveyor belt speed while minimizing interference with the rest of the control system. When tested on real-world data, the framework exceeds the performance requirements (99.8% packed products) and maintains quality (100% filled boxes). Compared to the existing solution, our proposed framework improves productivity, has smoother control, and reduces computation time. © 2023 IEEE.

关键词： Reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

Modeling Human Performance in complex Search and Retrieve Environment Using Supervised and Unsupervised Machine Learning Techniques 14th

Modeling Human Performance in Complex Search and Retrieve En...

引用

12th international Advanced computing conference, IACC 2022

作者： Uttrani, Shashank Sharma, Sakshi Dabas, Mahavir Kanekar, Bhavik Dutt, Varun Applied Cognitive Science Lab Indian Institute of Technology Mandi HP Mandi Kamand175075 India

ISBN: (纸本)9783031356438

Prior research has evaluated human performance in complex search-and-retrieve environment. However, little is known about how supervised and unsupervised machine learning techniques could account for human performance in such complex scenarios. The primary objective of this research is to develop supervised and unsupervised machine learning models to account for human actions in a complex search-and-retrieve environment. A total of 50 participants were recruited to participate in the study to perform as human agents in a simulation developed using Unity 3D. The environment consisted of four building with targets (having positive reward) and distractors (having negative reward) present inside those buildings. Participants were tasked to explore the environment and maximize their score by collecting as many target items while avoiding distractor items present in the environment. The experiment consisted of training and test phases which differed in the availability of feedback, items present in the environment, and the duration. Next, machine learning models were developed to account for human actions using supervised and unsupervised techniques such as Decision Tree, Random Forest, Support Vector Classifier (SVC), Multilayer Perceptron (MLP), and K-nearest neighbor (KNN). These models were trained using data collected in the training phase of the experiment and their performance was evaluated on data collected in the test phase. Results revealed that KNN, an unsupervised learning model, performed better in predicting human actions on the test dataset compared to supervised learning models such as decision tree, random forest, MLP, and SVC. We highlight the main implications of our findings for the human factors research community. © 2023, Springer Nature Switzerland AG.

关键词： Decision trees

来源：评论

学校读者我要写书评

暂无评论

An Overview of Making Decisions on Medical Problems Using Fuzzy cognitive Maps 14

An Overview of Making Decisions on Medical Problems Using Fu...

引用

14th international conference on Information, Intelligence, Systems and Applications, IISA 2023

作者： Krimpas, George A. Krimpas, Nikolaos A Groumpos, Peter P. University of Patras Department of Electrical Engineering Patras Greece

ISBN: (纸本)9798350318067

This paper provides an overview of how fuzzy logic can be applied to make decisions on medical problems. Fuzzy logic is a mathematical framework that can handle uncertainty and imprecision, making it a useful tool in the field of medicine. The process of using fuzzy logic to make medical decisions involves defining the problem, identifying relevant variables, assigning membership functions, defining rules, fuzzification, inference, and defuzzification. Fuzzy logic can be used to make decisions related to diagnosis, treatment, risk assessment, and prognosis. While fuzzy logic has several advantages, including the ability to handle uncertainty, it requires a high level of expertise to develop accurate models. Overall, fuzzy logic can provide valuable insights for medical professionals making decisions in situations where there is no clear-cut answer. We also highlight the advantages of FCMs in medicine, including their ability to model complex relationships and their ability to handle uncertainty and imprecision. They also discuss the limitations of FCMs, such as the difficulty in obtaining reliable data and the need for expert knowledge to develop accurate models. The methods presented can be used as a guideline for constructing FCMs in medical applications, while the applications discussed can serve as a source of inspiration for future research. © 2023 IEEE.

关键词： Decision making

来源：评论

学校读者我要写书评

暂无评论

Alignment at Pre-training! Towards Native Alignment for Arabic LLMs 38

Alignment at Pre-training! Towards Native Alignment for Arab...

引用

38th conference on Neural Information Processing Systems, NeurIPS 2024

作者： Liang, Juhao Cai, Zhenyang Zhu, Jianqing Huang, Huang Zong, Kewei An, Bang Alharthi, Abdulmohsen He, Juncai Zhang, Lian Li, Haizhou Wang, Benyou Xu, Jinchao Shenzhen Research Institue of Big Data Shenzhen China The Chinese University of Hong Kong Shenzhen China King Abdullah University of Science and Technology Thuwal Saudi Arabia Shenzhen International Center for Industrial and Applied Mathematics Shenzhen Research Institute of Big Data China

The alignment of large language models (LLMs) is critical for developing effective and safe language models. Traditional approaches focus on aligning models during the instruction tuning or reinforcement learning stages, referred to in this paper as 'post alignment'. We argue that alignment during the pre-training phase, which we term 'native alignment', warrants investigation. Native alignment aims to prevent unaligned content from the beginning, rather than relying on posthoc processing. This approach leverages extensively aligned pre-training data to enhance the effectiveness and usability of pre-trained models. Our study specifically explores the application of native alignment in the context of Arabic LLMs. We conduct comprehensive experiments and ablation studies to evaluate the impact of native alignment on model performance and alignment stability. Additionally, we release open-source Arabic LLMs that demonstrate state-of-the-art performance on various benchmarks, providing significant benefits to the Arabic LLM community. © 2024 Neural information processing systems foundation. All rights reserved.

关键词：

来源：评论

学校读者我要写书评

暂无评论

A cognitive Architecture Based Conversation Agent Technology for Secure Communication 1

引用

1st international conference on Intelligent computing for Sustainable Development, ICICSD 2023

作者： Preety Singh, Jagjit Yadav, Meenakshi Christ University Delhi NCR Ghaziabad India Department of Artificial Intelligence and Data Science Koneru Lakshmaiah Education Foundation Andhra Pradesh Vaddeswaram India Galgotias College of Engineering and Technology Uttar Pradesh Greater Noida India

ISBN: (数字)9783031612985

ISBN: (纸本)9783031612978

This paper outlines a multi-agent system-based approach to provider selection. Suppliers in the supply chain are different and the demand and supply levels are high. Buy agents will find the right supply agent in our approach. First, the multi-layer classification system is used to rationally arrange and overall selection on suppliers and buyers. Secondly, the purchase information is organized by the supplier agent to improve device performance. The assessment process is then used to select the suppliers initially. In addition to selecting the correct provider and maximizing the value of the purchaser, the time negotiating mechanism is implemented. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2024.

关键词： Multi agent systems

来源：评论

学校读者我要写书评

暂无评论

Interactive influence of urban heat island and urban pollution island in two major cities of India (Bangalore and Delhi)

Interactive influence of urban heat island and urban polluti...

引用

2024 international conference on Machine Intelligence for GeoAnalytics and Remote Sensing, MIGARS 2024

作者： Dasgupta, Anindita Kumar, Uttam International Institute of Information Technology Spatial Computing Laboratory Center For Data Sciences Bangalore India

ISBN: (纸本)9798350389678

Rapid urbanization with the changes in land use patterns has resulted in the human induced urban heat island (UHI). UHI is a well-known phenomenon in which urban environments retain more heat than nearby rural environments effecting the urban population. City-heat interacts with rising summer temperatures and heat-waves and emission produced placing additional pressure on infrastructure. This study investigates the impact of interactive influence of Urban Heat Island and Urban Pollution Island (UPI) in two major cities of India (Delhi and Bangalore). The seasonal study for summer was performed for the two cities and so that interactive influence of aerosol, Nitrogen dioxide (NO2) and Land Surface Temperature (LST) is measured when the effect of UHI is the most. The study is performed for five years (2019, 2020, 2021, 2022 and 2023) and it was observed that in Delhi the overall aerosol index is greater than Bangalore. There was a considerable difference in the concentration of pollutant in 2021(during lock down because of pandemic) and 2022 (post-pandemic). Study was carried at a ward level in order to find out the interaction of pollutant and LST. Regression analysis was done taking the spatial metrics such as mean patch size, patch density, edge density, and shape of built-up patches at ward level (micro scale) of the city to measure the effect of anthropogenic activities on LST. © 2024 IEEE.

关键词： Atmospheric temperature

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72页 << < 31 32 33 34 35 36 37 38 39 40 > >>

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：