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

40,143 篇 会议
2,935 册 图书

馆藏范围

43,077 篇 电子文献
3 种 纸本馆藏

日期分布

学科分类号

39,395 篇 工学
- 38,033 篇 计算机科学与技术...
- 7,083 篇 软件工程
- 3,883 篇 信息与通信工程
- 3,046 篇 电气工程
- 2,277 篇 控制科学与工程
- 764 篇 生物医学工程（可授...
- 436 篇 生物工程
- 300 篇 机械工程
- 266 篇 交通运输工程
- 158 篇 测绘科学与技术
- 157 篇 土木工程
- 143 篇 光学工程
- 137 篇 建筑学
3,313 篇 管理学
- 1,840 篇 管理科学与工程(可...
- 1,148 篇 图书情报与档案管...
- 845 篇 工商管理
2,859 篇 理学
- 1,701 篇 数学
- 820 篇 生物学
- 456 篇 统计学（可授理学、...
- 309 篇 物理学
- 177 篇 系统科学
1,479 篇 教育学
- 1,397 篇 教育学
1,471 篇 医学
- 940 篇 临床医学
- 666 篇 基础医学(可授医学...
- 235 篇 特种医学
- 140 篇 药学(可授医学、理...
531 篇 文学
- 352 篇 外国语言文学
- 178 篇 新闻传播学
416 篇 经济学
- 317 篇 理论经济学
376 篇 法学
- 342 篇 社会学
177 篇 艺术学
95 篇 历史学
59 篇 农学
11 篇 军事学

主题

1,849 篇 artificial intel...
1,152 篇 machine learning
876 篇 deep learning
777 篇 computer communi...
666 篇 information syst...
550 篇 computer applica...
328 篇 computer systems...
308 篇 cloud computing
300 篇 clustering
297 篇 security
284 篇 internet of thin...
283 篇 software enginee...
269 篇 classification
235 篇 information syst...
235 篇 data mining
229 篇 computer imaging...
220 篇 software enginee...
199 篇 data mining and ...
199 篇 ontology
180 篇 computers and ed...

机构

80 篇 univ chinese aca...
76 篇 univ dist franci...
69 篇 chinese acad sci...
67 篇 shanghai univ sc...
48 篇 tsinghua univers...
43 篇 natl res univ hi...
39 篇 huazhong univers...
34 篇 harbin inst tech...
33 篇 tsinghua univ de...
30 篇 shanghai jiao to...
29 篇 pontificia univ ...
29 篇 harbin universit...
27 篇 polytechnic inst...
27 篇 chinese acad sci...
26 篇 lomonosov moscow...
25 篇 chongqing univ s...
25 篇 beijing jiaotong...
24 篇 university of cr...
24 篇 hunan univ coll ...
24 篇 harbin inst tech...

作者

58 篇 kim tai-hoon
53 篇 lima jose
43 篇 o'connor rory v.
36 篇 wang lei
34 篇 liu yang
33 篇 zhang lin
31 篇 kim seoksoo
29 篇 wang jing
28 篇 sabu m. thampi
26 篇 zhang lei
25 篇 li li
25 篇 crawford broderi...
24 篇 li yang
24 篇 wang jian
20 篇 hassanien aboul ...
19 篇 li peng
19 篇 serra roberto
18 篇 wang hui
18 篇 iliadis lazaros
17 篇 mbarki samir

语言

42,912 篇 英文
605 篇 中文
1 篇 丹麦文

检索条件"丛书名=Communications in Computer and Information Science"

共 43078 条记录，以下是751-760 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 Learning-Based Leukemia Diagnosis from Bone Marrow Images 12th

Deep Learning-Based Leukemia Diagnosis from Bone Marrow Imag...

引用

12th Ecuadorian Conference on information and Communication Technologies

作者： Zhinin-Vera, Luis Moya, Alejandro Pretel, Elena Astudillo, Jaime Jimenez-Ruescas, Javier Univ Castilla La Mancha LoUISE Res Grp Albacete 02071 Spain Yachay Tech Univ Sch Math & Computat Sci Urcuqui 100650 Ecuador Model Intelligent Networks Dev MIND Res Group Urcuqui Ecuador

ISBN: (纸本)9783031754302;9783031754319

Identifying and classifying features in Bone Marrow Aspirate Smear (BMAS) images is essential for diagnosing various leukemias, such as Acute Myeloid Leukemia. The complexity of microscopy image analysis necessitates a computational tool to automate this process, reducing the workload on hematologists. Our study introduces a Deep Learning-based method designed to efficiently detect and classify cell characteristics in BMAS images. Current systems struggle with cell and nucleus segmentation due to variations in cell size, appearance, texture, and overlapping cells, often influenced by different microscopy conditions. We addressed these challenges by experimenting with the Munich AML Morphology Dataset and a custom dataset from Hospital 12 de Octubre in Madrid. The proposed system achieved over 90% accuracy and 92% precision in identifying and classifying leukemia cells, marking a substantial advancement in supporting clinical specialists in their decision-making processes when traditional analysis methods are insufficient.

关键词： deep learning image classification leukemia cells bone marrow aspirate smear

来源：评论

学校读者我要写书评

暂无评论

Is ChatGPT Ready for Indian-Language Speakers? Findings From a Preliminary Mixed Methods Study 15th

Is ChatGPT Ready for Indian-Language Speakers? Findings From...

引用

15th Indian Conference on Human-computer Interaction Design and Research

作者： Chaitra, C. R. Upadhyay, Prajna Chakraborty, Dipanjan BITS Pilani Hyderabad Campus Secunderabad India

ISBN: (纸本)9783031808289;9783031808296

Recent developments in Artificial Intelligence (AI) technology, especially Generative AI (GenAI), are helping individuals in content generation and collaborative work, thus enhancing the quality of the work. In this paper, we investigate if ChatGPT, one of the most popular GenAI tools, is ready to cater to the capabilities, expectations and needs of the non-English speaking, emergent users of digital technologies. To understand this space among non-English speakers, we conducted a user study with 15 non-English speakers in the state of Telangana, India. To assess the experience of emergent users using ChatGPT, we set them tasks of querying ChatGPT, and contrasted it with the same tasks on Google, a traditional search engine. We asked them to rate the platforms for ease of use and the understanding of the users' language. We draw insights from the study through user ratings of the interactions and logging user observations during the interactions. We derive a few design recommendations for designers and researchers working on voice-based conversational GenAI tools.

关键词： ChatGPT Google Indian Language

来源：评论

学校读者我要写书评

暂无评论

Examining Smart Contracts Within Mauritian Contract Law: Assessing Their Compatibility with Existing Legal Frameworks 4th

Examining Smart Contracts Within Mauritian Contract Law: Ass...

引用

4th International Conference on Society 5.0

作者： Fulena, Viraj Univ Technol Port Louis Mauritius

ISBN: (纸本)9783031714115;9783031714122

This research paper explores the complexities surrounding smart contracts, computer code designed to automate contractual processes, thus bypassing the need for intermediary enforcement. As smart contracts gain traction, jurisdictions worldwide grapple with regulating them. Challenges arise from the novel nature of these contracts, as their enforcement poses unique dilemmas within legal frameworks. While some believe regulation is feasible, others question the enforceability of code-based agreements. Mauritius, aspiring to be Africa's Fintech hub, is addressing these issues through the Virtual Asset and Initial Token Offering Services Act 2021. However, uncertainties persist regarding the enforceability of smart contracts. This research examines smart contracts comprehensively, exploring technical and legal dimensions to unravel their complexity. It scrutinises Mauritius' legal landscape to ascertain the compatibility of smart contracts with existing contract laws and the effectiveness of the 2021 Act in regulating them.

关键词： Smart Contract Contract Law Civil Code CCM VAITOS

来源：评论

学校读者我要写书评

暂无评论

Algorithm for Circuit Covering the Euclidean Complete Graph 2nd

Algorithm for Circuit Covering the Euclidean Complete Graph

引用

2nd International Conference on information Technologies and Their Applications

作者： Nuriyeva, Fidan Dokuz Eylul Univ Izmir Turkiye Minist Sci & Educ Republ Azerbaijan Inst Control Syst Baku Azerbaijan

ISBN: (纸本)9783031734168;9783031734175

Computational Geometry is a branch of computer science that focuses on algorithms solving geometric problems. Computational Geometry has applications in various fields such as Modern Engineering and Mathematics, computer Graphics, Robotics, VLSI Design, computer-Aided Design, Molecular Modeling, Metallurgy, Manufacturing, Textile Design, Forestry, and Statistics. Graph theory is useful in defining problems and determining structural relationships. Hundreds of interesting computational problems are stated in graphs. In this study, the term of a circuit that more tightly covers the vertex set of the Euclidean complete graph has been defined, and an algorithm has been proposed to find this circuit. The complexity of the proposed algorithm is O(n). The proposed Boundary Point term in our presented work given in [5] allows for the expansion of the defined set of Boundary Vertices, enabling a more tightly construction of the Circuit Covering the Graph. The proposed algorithm can be applied to geometric design problems.

关键词： Graph Circuit Covering the Graph Convex Hull Geometric Design Problem

来源：评论

学校读者我要写书评

暂无评论

SINR Analysis of Cell-Free Massive MIMO Systems Assisted by Intelligent Reflecting Surface 5th

SINR Analysis of Cell-Free Massive MIMO Systems Assisted by ...

引用

5th China Intelligent Robotics Academic Conference

作者： Jin, Si-Nian Zhao, Shihang Song, Yu Ma, Jitong Ju, Moran Dalian Maritime Univ Dalian 116026 Peoples R China China Southern Power Grid Co Ltd Guangzhou Bur Extra High Voltage Transmiss Co Guangzhou 510663 Peoples R China

ISBN: (纸本)9789819616138;9789819616145

In 6th generation (6G) mobile networks, cell-free massive multiple-input multiple-output (MIMO) and intelligent reflecting surfaces (IRS) play a crucial role. Integrating these technologies can significantly enhance communication network performance. This paper explores cell-free massive MIMO systems augmented by IRS, where M multi-antenna base stations (BSs) communicate with K single-antenna users, aided by N IRSs with many passive reflecting elements located within the BSs' line of sight. Using the maximum ratio combined under perfect channel state information, we begin by examining the probability density function (PDF) of both the desired signal and the interference generated by other users. From these analyses, we then derive the PDF of the signal-to-interference-plus-noise ratio (SINR) for each individual user. Numerical results confirm the accuracy of the SINR PDF.

关键词： Intelligent reflecting surface cell-free massive multiple-input multiple-output SINR

来源：评论

学校读者我要写书评

暂无评论

Biologically-Inspired Algorithms for Adaptive Non-Player Character Behavior in Video Games 7th

Biologically-Inspired Algorithms for Adaptive Non-Player Cha...

引用

7th International Conference on Optimization and Learning

作者： Alizadeh, Sina Mouhoub, Malek Univ Regina Dept Comp Sci Regina SK Canada

ISBN: (纸本)9783031779404;9783031779411

Video game designers frequently employ different movement algorithms to give players the impression of the intelligent and unpredictable motions of non-player characters or enemy agents. This paper explores the application of metaheuristic biological algorithms in video games to enhance the unpredictability and realism of enemy characters, moving away from traditional pre-programmed NPC behaviors. Developing the bespoke game "Run and Catch" incorporates the utilization of Particle Swarm Optimization (PSO) and Ant Colony Optimization (ACO) for directing the movement of non-player characters. We tackle the premature convergence challenge by introducing an adaptive Finder - Tracker agent approach. This mechanism maintains diversity in enemy movements to ensure responsiveness to real-time player character activities. The findings illustrate the adverse effects of early convergence on both immersion and the variety of non-player character movements within a 2D game environment. Moreover, the study underscores the success of ACO and PSO, equipped with the Finder- Tracker agent framework, in reshaping group movements of non-player characters and effectively dealing with the convergence challenge.

关键词： Bio-inspired Algorithms Video Games Non-Player Characters (NPCs)

来源：评论

学校读者我要写书评

暂无评论

Enhancing Software Requirements Classification with Machine Learning and Feature Selection Techniques 33rd

Enhancing Software Requirements Classification with Machine ...

引用

33rd International Conference on Software and Data Engineering

作者： Lanfear, Daniel Maleki, Mina Banitaan, Shadi Univ Detroit Mercy Dept Elect & Comp Engn & Comp Sci 4001 W McNichols Rd Detroit MI 48221 USA

ISBN: (纸本)9783031752001;9783031752018

Requirements engineers have the responsibility for classifying software requirements into functional and nonfunctional variants. As software architects need quality requirements to be known to get their job done, machine learning is employed to speed up and add consistency to the process of identifying and categorizing requirements so that effort may be spent more effectively. We experimented with the effects of different machine learning algorithms, as well as different pre-processing and feature selection techniques. It was determined that, for this application, stop words should not be removed and that performing lemmatization on words provides the most effective features for classification. Furthermore, after finalizing our choices of pre-processing techniques and algorithm to use, we proposed a modification to the Extensive Feature Selector by gathering the most distinctive words in each category and using a list of those as our main features. By using a threshold of 0.013, we obtained an F1 score of 0.787, which is an improvement on the base Enhanced Feature Selector's F1 score of 0.761 with the same number of word features.

关键词： Machine learning Requirements engineering Supervised learning Classification Feature selection Natural language processing

来源：评论

学校读者我要写书评

暂无评论

Pre-training a Transformer-Based Generative Model Using a Small Sepedi Dataset 5th

Pre-training a Transformer-Based Generative Model Using a Sm...

引用

5th Southern African Conference for Artificial Intelligence Research

作者： Ramalepe, Simon Phetole Modipa, Thipe I. Davel, Marelie H. Univ Limpopo Dept Comp Sci Polokwane South Africa Northwest Univ Fac Engn Potchefstroom South Africa Ctr Artificial Intelligence Res Pretoria South Africa Natl Inst Theoret & Computat Sci Stellenbosch South Africa

ISBN: (纸本)9783031782541;9783031782558

Due to the scarcity of data in low-resourced languages, the development of language models for these languages has been very slow. Currently, pre-trained language models have gained popularity in natural language processing, especially, in developing domain-specific models for low-resourced languages. In this study, we experiment with the impact of using occlusion-based techniques when training a language model for a text generation task. We curate 2 new datasets, the Sepedi monolingual (SepMono) dataset from several South African resources and the Sepedi radio news (SepNews) dataset from the radio news domain. We use the SepMono dataset to pre-train transformer-based models using the occlusion and non-occlusion pre-training techniques and compare performance. The SepNews dataset is specifically used for fine-tuning. Our results show that the non-occlusion models perform better compared to the occlusion-based models when measuring validation loss and perplexity. However, analysis of the generated text using the BLEU score metric, which measures the quality of the generated text, shows a slightly higher BLEU score for the occlusion-based models compared to the non-occlusion models.

关键词： Transformers Text generation Pre-training Occlusion-based training Datasets

来源：评论

学校读者我要写书评

暂无评论

DRLN: Disentangled Representation Learning Network for Multimodal Sentiment Analysis 5th

DRLN: Disentangled Representation Learning Network for Multi...

引用

5th International Conference on Neural Computing for Advanced Applications (NCAA)

作者： Hou, Jingming Omar, Nazlia Tiun, Sabrina Saad, Saidah He, Qian Univ Kebangsaan Malaysia Fac Informat Sci & Technol Ctr Artificial Intelligence Technol Bangi 43650 Selangor Malaysia Guilin Univ Elect Technol State & Local Joint Engn Res Ctr Satellite Nav & Guangxi Key Lab Cryptog & Informat Secur Guilin Peoples R China

ISBN: (纸本)9789819770069;9789819770076

Multimodal sentiment analysis (MSA) involves the analysis of human emotions by integrating emotional features from text, audio, and visual modalities. Previously, a considerable amount of research had commonly focused on fusing these three modalities equally, neglecting the importance of text modality and the influence of modal heterogeneity on fusion. To address this issue, we propose the Disentangled Representation Learning Network (DRLN) which decomposes representations from different modalities into separate sub-spaces centered around text modality to capture similarity and dissimilarity features among modalities. Meanwhile, we utilize contrastive learning loss and reconstruction loss to better learn representations within each sub-space. Finally, extensive experiments on two benchmark datasets demonstrate that our model outperforms state-of-the-art methods on various metrics.

关键词： Multimodal Sentiment Analysis Multimodal Representation Learning Contrastive Learning Text-Centric

来源：评论

学校读者我要写书评

暂无评论

Comprehensive Evaluation of Pythia Model Efficiency in De-identification and Normalization for Enhanced Medical Data Management

Comprehensive Evaluation of Pythia Model Efficiency in De-id...

引用

2024 International Workshop on Deidentification of Electronic Medical Record Notes

作者： Cho, Yen-Cheng Yang, Yu-Jie Liu, Yu-De Tsao, Tung-Sheng Lee, Min-Jain Natl Kaohsiung Univ Sci & Technol Appl Intelligence Lab Dept Elect Engn Kaohsiung 807618 Taiwan Natl Kaohsiung Univ Sci & Technol Dept Elect Engn Elect Sensing Control & AI Comp Syst Lab Kaohsiung 807618 Taiwan Natl Kaohsiung Univ Sci & Technol Dept Elect Engn Multimedia Protect & Interact Lab Kaohsiung 807618 Taiwan Natl Kaohsiung Univ Sci & Technol Dept Elect Engn GPS Image Satellite Applicat Lab Kaohsiung 807618 Taiwan

ISBN: (纸本)9789819779659;9789819779666

This study presents our work developed for the AICUP2023-privacy protection and standardization of electronic medical record text notes. Our work focuses on exploring the efficiency of the Pythia model developed by the EleutherAI community applying it to the de-identification and normalization problems. The core objective of the research outcome is to achieve a dual purpose: on one hand, to protect patient privacy, and on the other hand, to enhance the automation and efficiency of medical data management, while striving to reduce manual de-identification errors caused by human factors. To this end, we will not only examine the standard configuration of the Pythia model but also delve into its performance under different parameter settings, to comprehensively evaluate and compare its effectiveness and results in handling sensitive medical data. Our experiment results highlight that merely increasing the model size might not be sufficient to yield the expected benefit for recognizing protected health information from text. However, for the task of temporal information normalization, the large language model demonstrates a significant performance improvement after fine-tuning.

关键词： Pythia Model protect patient privacy De-Identification

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 << < 72 73 74 75 76 77 78 79 80 81 > >>

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：