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

分类表

所选分类

>> <<

限定检索结果

标题

标题
作者
主题词
出版物名称
出版社
机构
学科分类号
摘要
ISBN
ISSN
基金资助
索书号

作者

作者
标题
主题词
出版物名称
出版社
机构
学科分类号
摘要
ISBN
ISSN
基金资助
索书号

文献类型

255,818 篇 会议
107,184 篇 期刊文献
2,796 册 图书
5 篇 学位论文

馆藏范围

365,801 篇 电子文献
10 种 纸本馆藏

日期分布

学科分类号

207,647 篇 工学
- 129,559 篇 计算机科学与技术...
- 104,130 篇 软件工程
- 50,925 篇 信息与通信工程
- 33,337 篇 控制科学与工程
- 32,885 篇 电子科学与技术（可...
- 32,771 篇 电气工程
- 22,521 篇 生物工程
- 18,147 篇 生物医学工程（可授...
- 17,740 篇 光学工程
- 14,888 篇 机械工程
- 12,936 篇 化学工程与技术
- 12,367 篇 仪器科学与技术
- 11,946 篇 动力工程及工程热...
- 11,375 篇 材料科学与工程（可...
- 7,434 篇 安全科学与工程
- 7,081 篇 网络空间安全
- 6,781 篇 交通运输工程
120,815 篇 理学
- 58,140 篇 数学
- 43,374 篇 物理学
- 25,615 篇 生物学
- 18,851 篇 统计学（可授理学、...
- 13,866 篇 化学
- 13,689 篇 系统科学
49,787 篇 管理学
- 31,107 篇 管理科学与工程(可...
- 20,646 篇 图书情报与档案管...
- 14,691 篇 工商管理
17,355 篇 医学
- 14,455 篇 临床医学
- 12,868 篇 基础医学(可授医学...
- 8,116 篇 药学(可授医学、理...
9,018 篇 法学
- 7,428 篇 社会学
5,928 篇 经济学
4,677 篇 农学
3,525 篇 教育学
1,661 篇 文学
846 篇 军事学
458 篇 艺术学
66 篇 哲学
38 篇 历史学

主题

9,981 篇 computer science
9,092 篇 accuracy
7,980 篇 computational mo...
7,818 篇 feature extracti...
7,125 篇 deep learning
6,432 篇 machine learning
6,296 篇 training
4,672 篇 predictive model...
4,627 篇 support vector m...
4,470 篇 optimization
4,244 篇 data mining
4,202 篇 convolutional ne...
4,150 篇 real-time system...
4,134 篇 neural networks
4,081 篇 computer archite...
4,064 篇 wireless sensor ...
3,934 篇 bandwidth
3,804 篇 artificial intel...
3,769 篇 testing
3,733 篇 robustness

机构

3,278 篇 school of electr...
2,250 篇 chitkara univers...
2,027 篇 department of el...
1,738 篇 department of co...
1,277 篇 university of ch...
1,054 篇 cavendish labora...
985 篇 department of ph...
865 篇 oliver lodge lab...
858 篇 physikalisches i...
808 篇 department of el...
714 篇 department of co...
637 篇 department of co...
632 篇 school of comput...
610 篇 school of comput...
574 篇 school of electr...
533 篇 infn sezione di ...
516 篇 infn laboratori ...
504 篇 infn sezione di ...
495 篇 horia hulubei na...
492 篇 infn sezione di ...

作者

258 篇 barter w.
238 篇 j. wang
237 篇 s. chen
231 篇 blake t.
230 篇 a. gomes
222 篇 bellee v.
222 篇 betancourt c.
222 篇 amato s.
220 篇 bowcock t.j.v.
220 篇 borsato m.
216 篇 brundu d.
216 篇 boettcher t.
214 篇 c. alexa
210 篇 j. m. izen
207 篇 bencivenni g.
205 篇 beiter a.
196 篇 bay a.
194 篇 c. amelung
192 篇 g. bella
192 篇 j. strandberg

语言

322,639 篇 英文
38,704 篇 其他
4,513 篇 中文
279 篇 日文
56 篇 德文
42 篇 朝鲜文
40 篇 法文
40 篇 斯洛文尼亚文
20 篇 土耳其文
16 篇 俄文
13 篇 阿拉伯文
4 篇 荷兰文
4 篇 葡萄牙文
3 篇 西班牙文
3 篇 爱沙尼亚文
3 篇 意大利文
3 篇 波兰文
2 篇 捷克文
1 篇 泰文

检索条件"机构=Computer Engineering Department and Computer Technology Institute"

共 365803 条记录，以下是4911-4920 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：

相关度排序

相关度排序
时效性降序
时效性升序

SOINTER: A NOVEL DEEP ENERGY BASED INTERPRETATION METHOD FOR EXPLAINING STRUCTURED OUTPUT MODELS 12

SOINTER: A NOVEL DEEP ENERGY BASED INTERPRETATION METHOD FOR...

引用

12th International Conference on Learning Representations, ICLR 2024

作者： Seyyedsalehi, S. Fatemeh Soleymani, Mahdieh Rabiee, Hamid R. Department of Computer Engineering Sharif University of Technology Tehran Iran

This paper proposes a novel interpretation technique to explain the behavior of structured output models, which simultaneously learn mappings between an input vector and a set of output variables. As a result of the complex relationships between the computational path of output variables in structured models, a feature may impact an output value via other output variables. We focus on one of the outputs as the target and try to find the most important features adopted by the structured model to decide on the target in each locality of the input space. We consider an arbitrary structured output model available as a black-box and argue that considering correlations among output variables can improve explanation quality. The goal is to train a function as an interpreter for the target output variable over the input space. We introduce an energy-based training process for the interpreter function, which effectively considers the structural information incorporated into the model to be explained. The proposed method's effectiveness is confirmed using various simulated and real data sets. © 2024 12th International Conference on Learning Representations, ICLR 2024. All rights reserved.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Financial Time Series Prediction on Apple Stocks Using Machine and Deep Learning Models 4

Financial Time Series Prediction on Apple Stocks Using Machi...

引用

4th IEEE International Conference on Electrical, computer, and Energy Technologies, ICECET 2024

作者： Saini, Agampreet Singh, Nisha Singh, Rahul Kumar Sachan, Manoj Kumar School of Computer Science University of Petroleum and Energy Studies Uttarakhand Dehradun India Sant Longowal Institute of Engineering and Technology Department of Computer Engineering Punjab Longowal India

ISBN: (纸本)9798350395914

The scope of financial time series prediction has evolved significantly, driven by the surging availability of data and computational advancements. This transition has seen the traditional statistical methods give way to present-day machine learning and deep learning techniques. Despite these strides, challenges continue to exist, with market unpredictability, dimensionality issues, and overfitting in high-frequency data standing as primary obstacles. Newer machine learning models are better than old ones at predicting stocks. When electronic trading and yield optimisation come together, they make these models even better. Deep learning has completely changed machine learning, especially in forecasting financial trends over time. Complex deep learning models lack interpretability, hindering real-world adoption. Considering this we have used two deep learning models which are Long Short-Term Memory and Convolutional Neural Network and trained these on apple stock market data over the years along with one machine learning model i.e. Linear Regression. Then we have compared the accuracy of all the models based on their R-squared Score value. © 2024 IEEE.

关键词： Adversarial machine learning

来源：评论

学校读者我要写书评

暂无评论

IoT based Pet Health Monitoring System for Sick Pets 3

IoT based Pet Health Monitoring System for Sick Pets

引用

3rd International Conference on Applied Artificial Intelligence and Computing, ICAAIC 2024

作者： Nithin Wilfred Reyu, S. Pearly Princess, J. Karunya Institute of Technology and Sciences Computer Science and Engineering Coimbatore India

ISBN: (纸本)9798350375190

An inventive way to monitor a pet's health is the utilization of a pet health monitoring system. The proposed system's objective is to provide pet owners with current health information so they may take preventative actions. The wearable device that is part of the pet health monitoring system collects data from pets, including heart rate, temperature, and activity levels, and sends it to a central platform. It is programmed to examine this data in order to look for any irregularities or possible health problems. The system uses Blynk application that makes it easy for pet owners to view and understand the health information about their animals. Pet owners can seek veterinarian care by contacting them if the application notify them to any alarming shifts in their pet's health. By using it, pet owners can take an active role in promoting the health and wellbeing of their animals. Among the primary benefits of the pet health monitoring system are early detection of health issues, improved preventative treatment, remote monitoring capabilities, and more veterinarian-to-veterinarian communication. To sum up, the pet health monitoring system is a revolutionary instrument that helps pet owners effectively keep an eye on and control the health of their animals, ensuring that their beloved companions enjoy longer, healthier lives. © 2024 IEEE.

关键词： Animals

来源：评论

学校读者我要写书评

暂无评论

eDermaCare: Enhancing Skin Disease Classification with ResNet50 18

eDermaCare: Enhancing Skin Disease Classification with ResNe...

引用

18th INDIAcom;11th International Conference on Computing for Sustainable Global Development, INDIACom 2024

作者： Karambele, Aakanksha Tamhane, Mrunal Jayanty, Pranati Patil, Rutuja Shirsat, Kavita Vidyalankar Institute of Technology Dept. of Computer Engineering Mumbai India

ISBN: (纸本)9789380544519

In today's world, skin diseases are caused by various factors and affect a person's mental and physical wellbeing. Particularly in private areas, there is considerable reluctance to disclose skin diseases, especially among female patients, which further intensifies the challenge of early detection and treatment. To tackle this issue, the study proposes the implementation of eDermaCare, a novel approach leveraging the advanced Residual Network-50 (ResNet-50) convolutional neural network architecture. Several convolutional neural network (CNN) architectures were explored, but unsatisfactory results were obtained. ResNet-50 has the ability to capture complex features from skin images. The goal is to improve skin disease classification using ResNet-50's deep learning capabilities. This model uses the rest of the course to explain training and retention issues. Block balances allow training deep networks without suffering from degradation in performance. As a result, the model achieves a classification accuracy of 76.07%. The proposed system wm help improve early detection and treatment of skin diseases, address societal challenges, and support effective healthcare. © 2024 Bharati Vidyapeeth, New Delhi.

关键词： classification CNN Deep Learning Resnet50 Skin disease

来源：评论

学校读者我要写书评

暂无评论

Enhancing Context-Aware Hybrid Collaborative Filtering Using DBSCAN Clustering Approach 1

引用

1st International Conference on Machine Intelligence for Research and Innovations, MAiTRI 2023

作者： Abinaya, S. Sharma, Ayush School of Computer Science and Engineering Vellore Institute of Technology Chennai India

ISBN: (数字)9789819981359

ISBN: (纸本)9789819981342

With the increasing availability of travel-related data and the rising demand for personalized travel recommendations, context-aware recommender systems (CARS) are crucial for assisting travelers in discovering relevant and better experience. The technique known as density-based spatial clustering of application with noise (DBSCAN) is utilized by the framework that has been proposed to locate user clusters that have similar travel preferences and contextual signals. In addition to that, it utilizes a hybrid collaborative filtering strategy, which combines collaborative filtering. This combination improves the precision and variety of the recommendations, providing users with a wider array of pertinent options. By incorporating contextual data such as location, time, and user behavior, the proposed system CHCF_DBSCAN is able to generate recommendations that are specific to the user’s context and current circumstance. Experiments were conducted using Flicker City Platform travel dataset. The outcomes demonstrate the approach’s efficacy in enhancing the recommendations’ precision and relevance. © 2024, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

关键词： Collaborative filtering

来源：评论

学校读者我要写书评

暂无评论

Securing Patient Health Records Using Blockchain

Securing Patient Health Records Using Blockchain

引用

2024 International Conference on Electrical, Electronics and Computing Technologies, ICEECT 2024

作者： Geethan, Daniel Anandha Arjun, P. Sanjay, K.S. Kanniga Devi, R. Vellore Institute of Technology School of Computer Science and Engineering Chennai India

ISBN: (纸本)9798350378092

Traditional Electronic Health Records (EHRs) raise red flags about data privacy, security, and patient control. This research tackles these issues by proposing a new system where patients call the shots on their medical information. Our blockchain and InterPlanetary File System (IPFS) system puts patients in the driver's seat, granting them complete ownership and oversight of their health data. Patients securely submit their formatted medical history through a dedicated website, where it's stored on IPFS using a decentralized platform like Pinata. A unique code (Content Identifier or CID) acts like a key, linking the data to the patient's blockchain address via a smart contract (coded rules) for guaranteed accuracy and tracking. Our design prioritizes patient-controlled access. Healthcare providers can't access the data without the patient's explicit go-ahead. Access requests are sent directly to the patient, who has the final say on approval, ensuring their data privacy is always protected. Approved requests include the CID, allowing authorized physicians to retrieve the patient's data directly from IPFS storage. But patient control goes beyond just reacting to access requests. Our system empowers patients to be proactive. Using their unique login credentials, they can grab their CID directly from the blockchain. This retrieval process can be integrated into a secure patient portal or mobile app. With their CID in hand, patients can directly share it with chosen physicians, fostering collaboration in care without relying on intermediary platforms. This streamlined data exchange empowers patients and fosters a more collaborative healthcare environment where they actively manage their health information. © 2024 IEEE.

关键词： Electronic health record

来源：评论

学校读者我要写书评

暂无评论

Healthcare Supply Chain Security with ZeroKnowledge Proof Authentication in Blockchain for Personalized Healthcare Monitoring 3

Healthcare Supply Chain Security with ZeroKnowledge Proof Au...

引用

3rd IEEE International Conference on Distributed Computing and Electrical Circuits and Electronics, ICDCECE 2024

作者： Aluri, Yuva Krishna Katlagunta, Sravani Musunuru, Thanusri Mylarapu, Anusha Kuruba, Kiran Venkat Satya Sai Raj Esther Jyothi, V. Pvp Siddhartha Institute Of Technology Computer Science And Engineering Vijayawada India

ISBN: (纸本)9798350318609

The current healthcare ecosystem often faces challenges such as data breaches, unauthorized access, data silos, and difficulties in tracking and verifying medical device supply chains. These issues pose a threat to patient confidentiality, trust in healthcare data, and the efficiency of healthcare operations. To address these challenges, a proposed model introduces a unique approach to bolstering the security and efficiency of Internet of Things (IoT) devices in healthcare through the use of advanced cryptographic techniques. Specifically, the model utilizes a heavy computation algorithm known as Elliptic Curve Cryptography (ECC) for packet verification in IoT devices. In addition to ECC, the model incorporates Zero Knowledge Proof (ZKP) for verification, providing a lighter alternative to ECC. ZKP works by signing the input messages and subsequently verifying the data, offering a robust security measure. The implementation strategy involves simulating IoT sensors, each equipped with ECC and Zero Knowledge proof capabilities for enhanced security. © 2024 IEEE.

关键词： Smart contract

来源：评论

学校读者我要写书评

暂无评论

Personalized Treatment Classification for Breast Cancer Patients using Random Forest Algorithm 2

Personalized Treatment Classification for Breast Cancer Pati...

引用

2nd DMIHER International Conference on Artificial Intelligence in Healthcare, Education and Industry, IDICAIEI 2024

作者： Fadnavis, Rupa A. Kshirsagar, M.M. Yeshwantrao Chavan College of Engineering Department of Computer Science and Engineering Nagpur India Yeshwantrao Chavan College of Engineering Department of Computer Technology Nagpur India

ISBN: (纸本)9798331528713

In traditional treatments of breast cancer patients, people get the similar treatment that means it follows a "one-size-fits-all"approach. Over a while, doctors have noticed that some treatments have given better results for some people than others. Everyone has their own unique identifying features, and so the treatment to the individual patients also needs to be tailor made. Personalized medicine (PM) for breast cancer considers individual differences in people's lifestyle, surroundings, and genetics, and it provides medicos with the information they need to target disease specific treatments. (ML)Machine learning plays an important role in personalized medicine (PM). It uses computational algorithms to analyze large amounts of data from different input sources such as medical records, molecular, genetic information, and data from clinical trials for finding patterns and predict outcomes. This information can then be used to tailor treatments specifically to an individual's characteristics and assist doctor in finding risk of disease and finding optimal treatments. The paper discusses about application of supervised machine learning (ML)algorithm: Random Forest algorithms for classification of three treatments of breast cancer patients namely chemotherapy, hormonal therapy and amputation. © 2024 IEEE.

关键词： Random forests

来源：评论

学校读者我要写书评

暂无评论

Enhancing Q&A Systems with Multilingual Text Conversion and Speech Integration: Harnessing the Power of LangChain and Large Language Models 8

Enhancing Q&A Systems with Multilingual Text Conversion and ...

引用

8th IEEE International Conference on Computational System and Information technology for Sustainable Solutions, CSITSS 2024

作者： Priya, K. Kamath, Akshatha Chandan, K.M. Praveen, C. Omkar, S.N. Aaditya, S.J. Ramaiah Institute of Technology Dept of Computer Science and Engineering Bangalore India

ISBN: (纸本)9798331505462

Searching through URLs and PDFs can be tedious and time-consuming because of the unstructured nature of these documents and the challenge of finding accurate and, relevant information. LangChain addressed these issues using advanced natural language processing algorithms to extract pertinent data from URLs and PDFs. With its user-friendly search interface, customizable filters, and efficient indexing and retrieval mechanisms, LangChain significantly enhances the search experience. Users can annotate important sections, store queries, and create bookmarks, making information retrieval from URLs and PDFs more efficient and improving the overall productivity. Traditional text analysis systems often struggle with interactivity, flexibility, and data integration, making it difficult for users to gain meaningful insights from diverse data sources such as websites and PDFs. Our research combines state-of-the-art technologies, including Dash, LangChain, Google Generative AI, and FAISS, to provide a comprehensive solution for extracting, analysing, and interacting with textual data from various sources. This includes handling both PDFs and the data uploaded via URLs. Our research demonstrates significant improvements in the efficiency and accuracy of information retrieval, paving the way for more complex applications such as text summarization and question-answering. Our system is also capable of converting text into speech and translating it into 10 different languages. © 2024 IEEE.

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

Metal Surface Defect Detection Using Deep Learning Techniques

Metal Surface Defect Detection Using Deep Learning Technique...

引用

2024 International Conference on Signal Processing, Computation, Electronics, Power and Telecommunication, IConSCEPT 2024

作者： Abhinav, S. Elakiya, E. School of Computer Science and Engineering Vellore Institute of Technology Chennai India

ISBN: (纸本)9798331540685

Metal defect detection plays a crucial role in ensuring the quality and safety of industrial manufacturing processes. Traditional methods of defect detection often rely on manual inspection, which can be time-consuming and prone to human error. In recent years, the application of deep learning techniques, particularly Convolutional Neural Networks (CNNs), has shown promising results in automating defect detection tasks. This research explores the effectiveness of using CNN architectures, specifically InceptionNet, ResNet34, and VGG16, for automated metal defect detection. The study involves training and evaluating these models on a dataset of metal surface images containing various types of defects. The performance metrics such as accuracy, precision, recall, and F1-score are analysed to assess the robustness and efficacy of each model in defect classification. Additionally, the research investigates the impact of transfer learning by fine-tuning pre-trained CNN models on the defect detection task. The experimental results demonstrate the superior performance of deep CNNs compared to traditional methods, highlighting the potential of these techniques for real-world applications in industrial quality control and inspection. © 2024 IEEE.

关键词： Convolutional neural networks

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 << < 488 489 490 491 492 493 494 495 496 497 > >>

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

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：