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

40,746 篇 会议
2,947 册 图书

馆藏范围

43,692 篇 电子文献
3 种 纸本馆藏

日期分布

学科分类号

40,000 篇 工学
- 38,643 篇 计算机科学与技术...
- 7,089 篇 软件工程
- 3,996 篇 信息与通信工程
- 3,136 篇 电气工程
- 2,304 篇 控制科学与工程
- 761 篇 生物医学工程（可授...
- 431 篇 生物工程
- 320 篇 机械工程
- 293 篇 交通运输工程
- 158 篇 测绘科学与技术
- 156 篇 土木工程
- 145 篇 光学工程
- 136 篇 建筑学
3,350 篇 管理学
- 1,879 篇 管理科学与工程(可...
- 1,145 篇 图书情报与档案管...
- 860 篇 工商管理
3,075 篇 理学
- 1,889 篇 数学
- 815 篇 生物学
- 456 篇 统计学（可授理学、...
- 340 篇 物理学
- 178 篇 系统科学
1,487 篇 医学
- 937 篇 临床医学
- 683 篇 基础医学(可授医学...
- 235 篇 特种医学
- 138 篇 药学(可授医学、理...
1,478 篇 教育学
- 1,396 篇 教育学
550 篇 文学
- 371 篇 外国语言文学
- 178 篇 新闻传播学
415 篇 经济学
- 317 篇 理论经济学
374 篇 法学
- 340 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

1,862 篇 artificial intel...
1,187 篇 machine learning
898 篇 deep learning
779 篇 computer communi...
668 篇 information syst...
558 篇 computer applica...
328 篇 computer systems...
314 篇 cloud computing
304 篇 clustering
299 篇 security
288 篇 internet of thin...
276 篇 classification
264 篇 software enginee...
235 篇 information syst...
229 篇 computer imaging...
224 篇 data mining
218 篇 software enginee...
208 篇 data mining and ...
205 篇 ontology
180 篇 computers and ed...

机构

83 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...
35 篇 harbin inst tech...
33 篇 tsinghua univ de...
30 篇 shanghai jiao to...
30 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 univ pos...
24 篇 university of cr...
24 篇 hunan univ coll ...
23 篇 univ nacl colomb...

作者

58 篇 kim tai-hoon
53 篇 lima jose
43 篇 o'connor rory v.
37 篇 wang lei
34 篇 liu yang
33 篇 zhang lin
31 篇 kim seoksoo
30 篇 wang jing
28 篇 sabu m. thampi
28 篇 crawford broderi...
26 篇 zhang lei
25 篇 li yang
25 篇 li li
24 篇 wang jian
21 篇 zhang min
20 篇 hassanien aboul ...
19 篇 li peng
19 篇 serra roberto
18 篇 valencia-garcia ...
18 篇 li xin

语言

43,527 篇 英文
655 篇 中文
1 篇 丹麦文

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

共 43693 条记录，以下是1301-1310 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：

Quantized SG-MCMC for Bayesian Deep Posterior Compression 11th

Quantized SG-MCMC for Bayesian Deep Posterior Compression

引用

11th Latin American Conference on High Performance Computing

作者： Hernandez, Sergio Lopez-Cortes, Xaviera Univ Catolica Maule Facultad Ciencias Ingn Dept Computac Ind Talca Chile

ISBN: (纸本)9783031800832;9783031800849

In this paper, we propose a novel quantization technique for Bayesian deep learning aimed at enhancing efficiency without compromising performance. Our approach leverages post-training quantization to significantly reduce the memory footprint of stochastic gradient samplers, particularly Stochastic Gradient Markov Chain Monte Carlo (SGMCMC) methods. This technique achieves a level of compression comparable to optimal thinning, which traditionally necessitates not only the original samples in single precision floating-point representation but also the gradients, resulting in substantial computational overhead. In contrast, our quantization method requires only the original samples and can accurately recover posterior modes through a simple affine transformation. This process incurs minimal additional memory or computational costs, making it a highly efficient alternative for Bayesian deep learning applications.

关键词： Bayesian Deep Learning Markov Chain Monte Carlo Quantization

来源：评论

学校读者我要写书评

暂无评论

Automating Turkish Educational Quiz Generation Using Large Language Models 4th

Automating Turkish Educational Quiz Generation Using Large L...

引用

4th International Conference on Intelligent Systems and Pattern Recognition-ISPR

作者： Zeinalipour, Kamyar Keptig, Yusuf Gokberk Maggini, Marco Gori, Marco Univ Siena Siena Italy

ISBN: (纸本)9783031821493;9783031821509

Crafting quizzes from educational content is a pivotal activity that benefits both teachers and students by reinforcing learning and evaluating understanding. In this study, we introduce a novel approach to generate quizzes from Turkish educational texts, marking a pioneering endeavor in educational technology specifically tailored to the Turkish educational context. We present a specialized dataset, named the Turkish-Quiz-Instruct, comprising an extensive collection of Turkish educational texts accompanied by multiple-choice and short-answer quizzes. This research leverages the capabilities of Large Language Models (LLMs), including GPT-4-Turbo, GPT-3.5-Turbo, Llama-2-7b-chat-hf, and Llama-2-13b-chat-hf, to automatically generate quiz questions and answers from the Turkish educational content. Our work delineates the methodology for employing these LLMs in the context of Turkish educational material, thereby opening new avenues for automated Turkish quiz generation. The study not only demonstrates the efficacy of using such models for generating coherent and relevant quiz content but also sets a precedent for future research in the domain of automated educational content creation for languages other than English. The Turkish-Quiz-Instruct dataset is introduced as a valuable resource for researchers and practitioners aiming to explore the boundaries of educational technology and language-specific applications of LLMs in Turkish. By addressing the challenges of quiz generation in a non-English context specifically Turkish, this study contributes significantly to the field of Turkish educational technology, providing insights into the potential of leveraging LLMs for educational purposes across diverse linguistic landscapes.

关键词： Turkish Quiz Generator Large Language Models LLMs Automatic Generation Question Generation Multiple-Choice Questions Short-Answer Questions Quize Generation

来源：评论

学校读者我要写书评

暂无评论

Selection of Exploratory or Goal-Directed Behavior by a Physical Robot Implementing Deep Active Inference 5th

Selection of Exploratory or Goal-Directed Behavior by a Phys...

引用

5th International Workshop on Active Inference

作者： Igari, Ko Fujii, Kentaro Haddon-Hill, Gabriel W. Murata, Shingo Keio Univ Yokohama Kanagawa Japan

ISBN: (纸本)9783031771378;9783031771385

Intelligent robots are being developed with the expectation that they will perform various tasks in diverse environments. Such robots need to autonomously engage in both exploratory behavior to reduce environmental uncertainty and goal-directed behavior to achieve their preferred observations (or goals). In this study, we focus on active inference, which provides a unified scheme for these distinct behavioral modes. Policy selection in active inference is based on minimizing expected free energy (EFE), which consists of one term representing epistemic value and another representing extrinsic value. Specifically, we investigate the influence of preference precision, which controls the balance between these two terms, on policy selection by a physical robot receiving high-dimensional and uncertain observations. We developed a deep active inference framework comprising a world model and a policy suggester. The world model predicts future hidden states and observations based on candidate policies from the policy suggester. The EFE for each policy is approximated using the predicted future hidden states and observations as well as the preferred observation. We implemented our proposed framework in a robot, requiring it to select a policy that minimizes EFE and then generate actions accordingly. The experimental results showed that the robot implementing the proposed framework selected exploratory or goal-directed behavior depending on the level of preference precision. These findings suggest that adjusting preference precision plays a crucial role in the autonomous selection of exploratory or goal-directed behavior in real-world situations with potential uncertainty.

关键词： Deep Active Inference Free Energy Principle World Model Robot Learning

来源：评论

学校读者我要写书评

暂无评论

Enhancing Maize Crop Health: Deep Learning Approach for Disease Detection and Classification Using Leaf Images 4th

Enhancing Maize Crop Health: Deep Learning Approach for Dise...

引用

4th International Conference on Artificial Intelligence and Knowledge Processing

作者： Nyange, Roseline Chipofya, Mapopa Gota Goel, Srishti Ashoka, S. B. Chola, Channabasava Jeonbuk Natl Univ Dept Comp Sci & Artificial Intelligence Jeonju Si 54896 South Korea Jeonbuk Natl Univ Dept Elect & Informat Engn Jeonju Si 54896 South Korea Kyung Hee Univ Dept Chem Engn Integrated Engn 1732 Deogyeong Daero Yongin 17104 Gyeonggi Do South Korea Maharani Cluster Univ Dept Comp Sci Maharani Sci Coll Women Bangalore Karnataka India Univ Mysore Dept Studies Comp Sci Mysore 570006 Karnataka India Univ Mysore Mysore Univ Sch Engn MUSE Dept Artificial Intelligence & Machine Learning Mysore 570006 Karnataka India

ISBN: (纸本)9783031734762;9783031734779

The agriculture sector in sub-Saharan Africa faces significant challenges in growing vital food security crops like maize due to crop diseases. In response, we introduce a robust deep learning model for accurately identifying diseased and healthy maize leaves using leaf images. Specifically, our model distinguishes betweenmaize leaves affected by Maize LethalNecrosis (MLN), Maize Streak Virus (MLV) and healthy ones. We utilize the ResNet architecture, a well-established convolutional neural network known for its exceptional performance in computer vision tasks. Our experiments demonstrate that using a pretrained ResNet model achieves remarkable accuracy, exceeding 99%, in distinguishing between diseased and healthy maize leaves. Importantly, we find that employing a pre-trained Deep Learning (DL) model eliminates the need for extensive training from scratch, affirming the effectiveness of Transfer Learning (TL) in this field. Furthermore, our model proves its robustness by effectively handling diverse variations in leaf appearance, lighting conditions, and disease symptoms. This research offers practical tools for early disease detection, aiding farmers, and agricultural experts, ultimately enhancing maize production. Our results highlight the potential of harnessing DL techniques to address critical challenges in agriculture and food security.

关键词： maize streak virus maize lethal necrosis convolutional neural networks deep learning

来源：评论

学校读者我要写书评

暂无评论

Assessing the Impact of Data Augmentation Techniques on YOLO's Performance in PV Anomaly Detection 5th

Assessing the Impact of Data Augmentation Techniques on YOLO...

引用

5th International Symposium on Intelligent Computing Systems

作者： Skaf, Zakwan Zyout, Imad Albanna, Mansoor Alshareif, Abdulla Al Ali, Abulla Higher Coll Technol Sharjah Campuses Sharjah U Arab Emirates

ISBN: (纸本)9783031829307;9783031829314

Solar energy has become of specific interest since it is more affordable than any other energy source, causing less environmental hazard. With improved analytics and monitoring, anomalies in solar energy systems will be detected and resolved with speed, enhancing the overall prevention of failures, lengthening the periods of effective maintenance, and ensuring system dependability and efficiency. According to recent research, You Only Look Once (YOLO), one of the most advanced target detection algorithms available for multiple defects in solar panels, depends heavily on the training dataset for the best accuracy results. Therefore, its performance will be poor if the number of samples with defects is low. Using data augmentation to raise the quantity of training samples is a practical way to improve YOLO performance. This paper assesses the impact of various data augmentation techniques on the performance of the YOLOv5 model using precision, recall, and mAP50. The results reveal that the mAP50 of the YOLOv5 algorithm with the scaling data augmentation technique improves by 2.9% over that obtained with the original dataset. The combined YOLOv5 and scale data augmentation method gives precisions, recalls, and mAP50 scores attained for PV panel defect detection as 88.3%, 89.2%, and 89.9%, respectively.

关键词： PV Panels YOLO Data Augmentation Anomaly Detection

来源：评论

学校读者我要写书评

暂无评论

Real-Time Bearing Health Monitoring Using Diffusion-Based Spectral Analysis: A Self-adaptive Approach to Predictive Maintenance 5th

Real-Time Bearing Health Monitoring Using Diffusion-Based Sp...

引用

5th International Conference on Innovative Intelligent Industrial Production and Logistics

作者： Prevost, Guillaume Boutet, Jerome Cabanillas, Esteban Ioana, Cornel Univ Grenoble Alpes CEA Leti F-38000 Grenoble France Univ Grenoble Alpes Gipsa Lab Grenoble France

ISBN: (纸本)9783031807749;9783031807756

This paper introduces a novel approach to real-time health monitoring of rolling bearings using a diffusion-based model. We propose a method that leverages Denoising Diffusion Implicit Models (DDIM), exploiting their intrinsic denoising capability, to process frequency spectra of vibration signals and construct a health index without prior system information. Our approach employs a continuous-time DDIM to model the complex distribution of frequencies in bearing vibration signals, enabling the detection of subtle spectral changes indicative of incipient faults. The method operates in real-time, adapting to specific bearing characteristics and learning normality over time. The health index (HI) is constructed using the reconstruction error between input features and their denoised versions and standardized using Welford's algorithm for online mean and variance estimation. We validate our method on the XJTU-SY bearing dataset. Results demonstrate the efficacy of our diffusion-based indicator, particularly in complex degradation scenarios. The method's ability to capture complex distributions and early degradation signs without prior system information presents a promising tool for predictive maintenance.

关键词： Predictive maintenance Health index Diffusion models Real-time monitoring Health stage division Prognostic health management

来源：评论

学校读者我要写书评

暂无评论

An Empirical Method for Processing I/O Traces to Analyze the Performance of DL Applications 12th

An Empirical Method for Processing I/O Traces to Analyze the...

引用

12th Conference on Cloud Computing, Big Data and Emerging Topics

作者： Parraga, Edixon Leon, Betzabeth Mendez, Sandra Rexachs, Dolores Suppi, Remo Luque, Emilio Univ Autonoma Barcelona Comp Architecture & Operating Syst Dept Campus UAB Bellaterra 08193 Spain Barcelona Supercomputing Ctr BSC Dept Comp Sci Barcelona 08034 Spain

ISBN: (纸本)9783031708060;9783031708077

The exponential growth of data handled by Deep Learning (DL) applications has led to an unprecedented demand for computational resources, necessitating their execution on High Performance Computing (HPC) systems. However, understanding and optimizing Input/Output (I/O) of the DL applications can be challenging due to the complexity and scale of DL workloads and the heterogeneous nature of I/O operations. This paper addresses this issue by proposing an I/O traces processing method that simplifies the generation of reports on global I/O patterns and performance to aid in I/O performance analysis. Our approach focuses on understanding the temporal and spatial distributions of I/O operations and related with the behavior at I/O system level. The proposed method enables us to synthesize and extract key information from the reports generated by tools such as Darshan tool and the seff command. These reports offer a detailed view of I/O performance, providing a set of metrics that deepen our understanding of the I/O behavior of DL applications.

关键词： DL I/O Analysis HPC I/O behavior patterns

来源：评论

学校读者我要写书评

暂无评论

Training Operator in VR: A Scalable Solution for the Creation of VR Training Scenes 5th

Training Operator in VR: A Scalable Solution for the Creatio...

引用

5th International Conference on Innovative Intelligent Industrial Production and Logistics

作者： Melzani, Geoffrey Quach, Tony Soderlund, Henrik Li, Dan Mugur, Puranjay Johansson, Bjorn Chalmers Univ Technol Chalmersplatsen 4 S-41296 Gothenburg Sweden Volvo Car Corp Gunnar Engellaus Vag 8 S-41878 Gothenburg Sweden

ISBN: (纸本)9783031807749;9783031807756

In the automotive industry, just like in other complex product-based industries, fierce competition is ongoing, and companies must cope with the challenges. In such industries, operator training is a cornerstone, as many of the most important product manufacturing processes rely on human-performed assembly. Thus, with the factory environments that are getting increasingly complex, and efficiency-dedicated, the importance of training is enhanced. With the generalization of Virtual Reality (VR) technologies, VR operator training emerges more rapidly. However, the many advantages of VR training, such as safety, cost, and flexibility, have not yet been fully realized in the industry as large-scale implementations still have not been reached. Creating VR training scenes is still time-consuming, and therefore expensive, hindering large-scale implementation and adaptation. This paper first recapitulates the data needed to populate such VR training scenes, then it exemplifies the automatic generation of VR training scenes through an industry use case, enabling large-scale automated implementation. Finally, it highlights the challenges related to data availability and handling and that companies can encounter on the way to the large-scale implementation of VR training.

关键词： Assembly Operator 5.0 Training Virtual reality Automated Scalable PLM IPS

来源：评论

学校读者我要写书评

暂无评论

A Voxel-Representation-Based Data Generator of Adversarial Objects for Robotic Manipulators 8th

A Voxel-Representation-Based Data Generator of Adversarial O...

引用

2024 World Congress in computer science, computer Engineering and Applied Computing-CSCE

作者： Akshay Katz, Garrett E. Mohan, Chilukuri K. Syracuse Univ Syracuse NY 13244 USA

ISBN: (纸本)9783031856273;9783031856280

In order to develop robust grasping AI algorithms, it is important to generate objects that become progressively more adversarial and complex with each iteration, as in curriculum learning, in a manner agnostic to the particular visual processing method used by the robot. We present a data generator of voxel-based 3D adversarial object geometries for training grasping algorithms, which operates independently of any particular visual encoding/decoding pipeline. Our novel approach uses genetic algorithms and can generate arbitrarily many samples, bounded only by the user-specified voxel resolution. The success of our approach is demonstrated in terms of the number of adversarial objects generated, how difficult they are to grasp, and how similar they are to more easily graspable objects.

关键词： Adversarial machine learning

来源：评论

学校读者我要写书评

暂无评论

Could You Hear That? Identifying Marathi Phrases Suitable for Aural Transcription Tasks 15th

Could You Hear That? Identifying Marathi Phrases Suitable fo...

引用

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

作者： Shetye, Saloni Amar Joshi, Anirudha Indian Inst Technol IDC Sch Design Mumbai Maharashtra India

ISBN: (纸本)9783031808289;9783031808296

Predetermined phrase sets are commonly used to carry out transcription tasks in evaluating text input methods. We examine the aural reliability of a set of 299 Marathi phrases that have been used in transcription studies in the past. We present a study in which 80 native Marathi speakers heard 30 randomly chosen phrases each and transcribed them, leading to 2,392 transcriptions (a repetition factor of eight per phrase). After an initial categorisation of transcription errors, we conducted a workshop with Marathi experts and arrived at an error tagging taxonomy consisting of 17 major error tags and 50 error subtags. After analysis of the transcriptions, we assigned 4,152 error subtags. Though the proportion of errors was higher than those reported in a similar study in English, surprisingly, we had a much smaller proportion of comprehension errors. We recommend 142 phrases that are aurally reliable for transcription studies but report the number and types of error subtags so that researchers can make their own assessments. The 157 phrases that we do not recommend have a value of their own, as they can inform future HCI research in Indian languages. Our contributions have potential applications in improving Marathi aural transcription tasks, spellcheck and auto-correct, synthetic speech, scripting for spoken interfaces and accessibility studies.

关键词： Transcription studies Phrase set Synthetic speech Marathi Error analysis Error tagging taxonomy

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 << < 127 128 129 130 131 132 133 134 135 136 > >>

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：