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

1,973 篇 会议
600 篇 期刊文献
5 册 图书

馆藏范围

2,578 篇 电子文献
0 种 纸本馆藏

日期分布

学科分类号

1,407 篇 工学
- 1,130 篇 计算机科学与技术...
- 940 篇 软件工程
- 452 篇 信息与通信工程
- 281 篇 控制科学与工程
- 245 篇 生物工程
- 214 篇 生物医学工程（可授...
- 197 篇 电气工程
- 141 篇 光学工程
- 130 篇 电子科学与技术（可...
- 125 篇 网络空间安全
- 122 篇 机械工程
- 117 篇 安全科学与工程
- 112 篇 动力工程及工程热...
- 84 篇 仪器科学与技术
- 82 篇 交通运输工程
- 81 篇 化学工程与技术
929 篇 理学
- 384 篇 物理学
- 303 篇 数学
- 285 篇 生物学
- 114 篇 统计学（可授理学、...
- 99 篇 化学
- 79 篇 系统科学
479 篇 管理学
- 317 篇 管理科学与工程(可...
- 203 篇 图书情报与档案管...
- 169 篇 工商管理
264 篇 医学
- 235 篇 临床医学
- 219 篇 基础医学(可授医学...
- 136 篇 公共卫生与预防医...
- 126 篇 药学(可授医学、理...
112 篇 法学
- 91 篇 社会学
87 篇 农学
76 篇 经济学
23 篇 教育学
6 篇 文学
5 篇 军事学
1 篇 艺术学

主题

169 篇 deep learning
163 篇 accuracy
133 篇 real-time system...
111 篇 feature extracti...
110 篇 convolutional ne...
101 篇 internet of thin...
97 篇 machine learning
94 篇 predictive model...
88 篇 training
78 篇 support vector m...
68 篇 cloud computing
67 篇 computational mo...
57 篇 machine learning...
50 篇 technological in...
49 篇 security
49 篇 data models
44 篇 neural networks
43 篇 prediction algor...
41 篇 scalability
40 篇 optimization

机构

124 篇 department of co...
73 篇 srm institute of...
56 篇 department of co...
43 篇 department of bi...
41 篇 department of co...
28 篇 department of co...
28 篇 department of co...
27 篇 department of co...
26 篇 department of co...
25 篇 department of ne...
24 篇 school of comput...
23 篇 department of co...
23 篇 department of co...
21 篇 srm institute of...
21 篇 srm institute of...
18 篇 srm institute of...
17 篇 srm institute of...
17 篇 department of co...
16 篇 srm institute of...
16 篇 department of el...

作者

25 篇 srinivasan c.
25 篇 c. srinivasan
20 篇 neelam sanjeev k...
19 篇 murugan s.
19 篇 s. murugan
19 篇 mohankumar n.
19 篇 kumar neelam san...
18 篇 n. mohankumar
16 篇 mani deepak chou...
16 篇 maniraj s.p.
14 篇 sangeetha s.k.b.
13 篇 srinivasan s.
13 篇 yuvaraj s.
13 篇 s. sivakumar
12 篇 sivakumar s.
12 篇 s. srinivasan
12 篇 choudhry mani de...
12 篇 thamizhamuthu r.
12 篇 surendran r.
12 篇 deepa r.

语言

2,427 篇 英文
148 篇 其他
32 篇 中文

检索条件"机构=2Department of Computer Science and Engineering SRM Institute of Science and Technology Chennai"

共 2578 条记录，以下是81-90 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 Approach to Indian Sign Language Recognition 4th

Deep Learning Approach to Indian Sign Language Recognition

引用

4th International Research Conference on Machine Learning, Deep Learning, and Blockchain, IRCICD 2023

作者： Vilashni, N. Anju Uthika, B. Sanjana, A. Yegu Prabha, B. Department of Computer Science and Engineering SRM Institute of Science and Technology Vadapalani Chennai India

ISBN: (纸本)9783031882364

Communication is one of civilization’s fundamental demands. About 20% of the global population has disabling hearing loss. The deaf and hard-of-hearing people mostly use sign language. It may also be used by individuals who can listen but cannot speak and by those who have deaf family members. Our proposed method aims to convert real-time data of Indian Sign Language (ISL) into text and audio data. The equivalent American Sign Language (ASL) field has seen many studies. However, some obstacles hinder further analysis of ISL. The main obstacle preventing further ISL research has been the lack of standard datasets, hidden characteristics, and local language variance. The majority of the work is based on handcrafted facets. Indian Sign Language (ISL) has static and dynamic signs and various gestures for the same expression depending on the area of India. It makes constructing a standardized dataset very challenging. Furthermore, there is no standard collection accessible. Hence, we were forced to make our dataset which consists of alphabets (A-Z) and numbers (0–9). The proposed method uses a custom-made Convolution Neural Network (CNN) model to classify 36 signs. Once the CNN model recognizes the sign, the output label is printed as text. This proposed model achieves a validation accuracy of 99.4%. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2025.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Eye Fundus Disease Classification Using Artificial Intelligence 1st

Eye Fundus Disease Classification Using Artificial Intellige...

引用

1st International Research Conference on Computing Technologies for Sustainable Development, IRCCTSD 2024

作者： Harisudhan, A.S. Prasanna, Raghul Vaibavi, J. Sridhar, Sridevi Department of Computer Science and Engineering SRM Institute of Science and Technology Vadapalani Chennai India

ISBN: (纸本)9783031823886

Eye fundus conditions are dangerous and can cause significant visual impairment if not detected early. Diabetic retinopathy, cataracts, and glaucoma are among the conditions for which manual assessment is directly impacted by ophthalmologists’ experience. The study intends to use artificial intelligence to develop a diagnostic system that is concentrated on the precise and effective classification of eye fundus diseases in order to address this challenge. The research involves the curation of an extensive dataset, named Eye Diseases Classification, that consists of a variety of eye fundus images that illustrate different conditions, including cataracts, glaucoma, and diabetic retinopathy. Expert ophthalmologists have painstakingly annotated every image in the dataset, offering precise ground-truth information that is essential for segmentation tasks. The findings of the experiment demonstrate how well the suggested AI system performs in accurately classifying eye fundus diseases and recognizing impacted areas in the images. This study could potentially reduce the risk of blindness and severe vision impairment by revolutionizing the diagnosis of these diseases. The system expedites diagnosis by automating the classification process, enabling earlier intervention and treatment. Additionally, using AI lessens the workload for ophthalmologists, freeing up their time for more complicated cases and improving the effectiveness of healthcare as a whole. In the end, using AI to diagnose eye fundus illnesses is a huge step forward that will impact public and clinical health in many ways. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2025.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Block Chain Ballot: A Secure and Transparent E-Voting System 4th

Block Chain Ballot: A Secure and Transparent E-Voting System

引用

4th International Research Conference on Machine Learning, Deep Learning, and Blockchain, IRCICD 2023

作者： Ram, A.J. Job, Dijolin Y. P. Raj Prasath, R.R. Sangeetha, S.K.B. Department of Computer Science Engineering SRM Institute of Science and Technology Vadapalani Chennai India

ISBN: (纸本)9783031882364

Blockchain-based voting system that aims to address the key issues associated with traditional voting systems. The proposed system leverages the security and transparency of blockchain smart contract technology based on the Polygon framework to improve the overall integrity and efficiency of the voting process. The system incorporates an OTP (One Time Password) option for voter authentication and uses blockchain to securely store encrypted votes, ensuring anonymity for voters by preventing any connection between a voter’s identity and the ballot they cast. The system also utilizes an off-chain storage system to preserve the data for future use. Solidity is used for smart contract creation on the Mumbai Matic Testnet Network which is built based on the polygon framework, and MetaMask is used as a wallet to perform transactions. The implementation of this system is expected to improve voter participation, reduce the potential for voting fraud, and provide real-time results, making the voting process more efficient, secure, and transparent. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2025.

关键词： Anonymity

来源：评论

学校读者我要写书评

暂无评论

Optimizing Inventory Management using Demand Forecasting based Ensemble Stacking Model with Hyperparameter Tuning 1

Optimizing Inventory Management using Demand Forecasting bas...

引用

1st International Conference on Intelligent Systems and Computational Networks, ICISCN 2025

作者： Pavithra, V. Abbas, Haayder M. Manjula, B.M. Chidambaram, P.K. Jothilakshmi, S. Srm Institute of Science and Technology Faculty of Science and Humanities Department of Computer Science and Applications Ramapuram Chennai India The Islamic University of Al Diwaniyah College of Technical Engineering Department of Computers Techniques Engineering Al Diwaniyah Iraq Nitte Meenakshi Institute of Technology Department of Electronics and Communication Engineering Bengaluru India New Prince Shri Bhavani College of Engineering and Technology Department of Mechanical Engineering Chennai India Dhanalakshmi Srinivasan College of Engineering and Technology Department of Information Technology Mamallapuram India

ISBN: (纸本)9798331529246

In recent days, the effective inventory management relies on accurate demand forecasting for effective management of business balance stocks. However, the traditional forecasting methods often struggled with different complexities such as variability, overstocking and wasted resources. In this research, the Ensemble Stacking Model with Hyperparameter Tuning (En-Stacking-HT) is proposed for effective optimized inventory management. Initially, the data is collected from M5 accuracy completion dataset and further preprocessed with data imputation, z-score normalization. These preprocessing techniques handles the missing values in data and standardizes the data in significant range. Then, Seasonal and Trend Decomposition (STL) is employed for extracting seasonality and trend features from preprocessed data by using Locally Estimated Scatterplot Smoothing (LOESS). Finally, the proposed En-Stacking-HT is utilized for inventory management prediction and optimized through hyperparameter tuning for predicting effective optimized inventory management for demand forecasting. From the results, the proposed En-Stacking-HT attained better results in terms of Mean Absolute Error (MAE) (16.82), Root Mean Square Error (RMSE) (22.85) and Mean Absolute Percentage Error (MAPE) (4.97%) when compared to existing Random Forest (RF). © 2025 IEEE.

关键词： demand forecasting ensemble stacking model hyperparameter tuning optimized inventory management seasonality and trend decomposition

来源：评论

学校读者我要写书评

暂无评论

Forecasting Sustainability: A Study of Demand Prediction in Circular Economics 1st

Forecasting Sustainability: A Study of Demand Prediction in ...

引用

1st International Research Conference on Computing Technologies for Sustainable Development, IRCCTSD 2024

作者： Harshavardhini, C. Sarayu, K. Roshan, C.R. Sangeetha, S.K.B. Department of Computer Science and Engineering SRM Institute of Science and Technology Vadapalani Campus Chennai India SRM Institute of Science and Technology Vadapalani Campus Chennai India

ISBN: (纸本)9783031823824

The study explores the potential of AI enhanced demand prediction for recycled and upcycled products, aiming to bridge the gap between sustainable production and market adoption. We propose a study utilizing machine learning algorithms to analyze historical sales data, market trends, and consumer sentiment, thereby forecasting demand for eco-friendly products with unprecedented accuracy. Leveraging business analytics and social media influence data, we propose a novel framework to: (1) compare consumer preferences and purchase patterns for recycled and upcycled products against their traditional counterpart (2) identify key factors driving demand for sustainable products, (3) compare demand patterns between ARIMA and LSTM models, and (4) analyze the impact of social media influence on consumer preferences. By predicting future demand with enhanced accuracy, this framework aims to empower businesses to optimize production, pricing, and marketing strategies, ultimately enabling a more sustainable and circular economy. The study holds significant implications for both businesses and consumers seeking to minimize environmental impact while catering to evolving market trends. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2025.

关键词： Circular economy

来源：评论

学校读者我要写书评

暂无评论

Enhancing Product Review Understanding: Text Summarization with BART Large XSum 1st

Enhancing Product Review Understanding: Text Summarization w...

引用

1st International Research Conference on Computing Technologies for Sustainable Development, IRCCTSD 2024

作者： Gopika, S. Balaji, Mayuri Mahimaa Vishwanath, M. Karthikayani, K. Department of Computer Science and Engineering SRM Institute of Science and Technology Chennai Vadapalani India

ISBN: (纸本)9783031823824

Online shopping has revolutionized the way consumers make purchasing decisions. Customer reviews play a crucial role in this process, providing valuable insights into product quality and satisfaction. However, sifting through numerous reviews can be time-consuming for customers. This research aims to address this issue by proposing a novel method to generate a single summary for the overall reviews of each product across different years. The proposed approach utilizes the BART large xsum model to streamline the summarization process. Initially, the dataset is preprocessed to remove irrelevant reviews, such as those lacking product IDs or years. Subsequently, the dataset is divided into batches, each containing 1024 tokens, to facilitate efficient processing. Summaries are generated for each batch, and the output is then used as input for the next stage. Finally, a concise summary is produced for each product across different years. Experimental evaluations are conducted using the Amazon baby product reviews dataset, with the performance of the BART large xsum model assessed using confidence scores. The results demonstrate that the proposed method effectively generates concise summaries for the overall reviews of each product across different years, saving customers valuable time in decision-making. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2025.

关键词： Sales

来源：评论

学校读者我要写书评

暂无评论

Efficient Information Extraction from Medical Records 1st

Efficient Information Extraction from Medical Records

引用

1st International Research Conference on Computing Technologies for Sustainable Development, IRCCTSD 2024

作者： Anand, G. Paavai Sundaram, Rishi Raja, S. Karthikk Kalpana, P. Department of Computer Science and Engineering SRM Institute of Science and Technology Vadapalani Chennai India

ISBN: (纸本)9783031823886

Over the years, information extraction has undergone numerous significant changes. This also holds true for the medical field. Medical transcripts are valuable resources filled with information that can help medical professionals and patients with insights. However, extracting this data manually is not efficient. Automating or minimalizing the process is required to perform efficiently. We aim to achieve No Code data extraction from medical transcripts to achieve inclusivity. To achieve this, we fine-tune the model using curated datasets. LLMs are powerful learners, but lack specific knowledge. By feeding them medical data like research papers and clinical documents, we adjust their internal understanding towards the medical domain. This lets them recognize medical terms, grasp relationships between diseases and treatments, and understand the context of medical queries. So, when we ask a question, the fine-tuned LLM can search through the data it learned to give us an accurate and relevant answer [5, 6]. We evaluate the model’s performance using RAG metrics for data retrieval. Compared to Mixtral 7B, our proposed model shows 8% improvement in MMLU performance. Translation being the only weak section of our proposed model as it is trained for data retrieval and not translation. The fine-tuning process is carried out with fixed parameters listed in the PEFT section. Methodology of training is PEFT and for learning, reinforcement learning with a learning rate of 1e−4. This value is experimental and the relation between learning rate and results vary due to difference in nature and quality of the training data. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2025.

关键词： Reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

Safe URL Detection with Privacy Using Machine Learning and Cryptography Techniques

Safe URL Detection with Privacy Using Machine Learning and C...

引用

Disruptive Technologies (ICDT), International Conference on

作者： V. Madhavan G. Paavai Anand Sridevi Sridhar Department of Computer Science and Engineering SRM Institute of Science and Technology Chennai Tamilnadu India

ISBN: (数字)9798331519582

ISBN: (纸本)9798331519599

A malicious URL or website represents a serious cybersecurity threat. Search engines logically serve as the foundation for managing in order. However, the influx of many malicious websites on search engines has created a considerable threat to our users. Most existing systems designed to identify malicious websites concentrate on particular types of attacks. Simultaneously, available browser extensions relying on blacklists are ineffective against numerous websites. To stop the server from deriving any useful information from the masked data, any data supplied from the client side must be successfully hidden. We provide the first Privacy-Preserving Safe Browsing service in this regard. This service offers strong security guarantees now absent from other Safe Browsing services. In particular, it preserves the capacity to recognize dangerous URLs while safeguarding the user's privacy and the blacklist provider's proprietary assets. In this study, we provide a methodology that protects users' privacy from outside analysts and service providers by encrypting their perceptual data. Furthermore, while maintaining differential privacy, it fully enables selected aggregate operations for examining user behavior online. The AES (Advanced Encryption Standard) algorithm encrypts users' online search behavior data. Only authenticated users can decrypt their history with assistance from the secret key sharing and verification process. A user feedback system notifies the search engine administrator of any malicious URLs, enabling the administrator to update the malicious URL database frequently.

关键词： Uniform resource locators Support vector machines Privacy Accuracy Phishing Search engines Blocklists Encryption History Standards

来源：评论

学校读者我要写书评

暂无评论

Ultrasound Based Breast Cancer Segmentation and Classification with Deep Learning Techniques 1st

Ultrasound Based Breast Cancer Segmentation and Classificati...

引用

1st International Research Conference on Computing Technologies for Sustainable Development, IRCCTSD 2024

作者： Farheen, A. Suneha Dilip, Golda Department of Computer Science and Engineering SRM Institute of Science and Technology Vadapalani Chennai India

ISBN: (纸本)9783031823886

Breast cancer is the most prevalent kind of cancer among women. Conventional techniques frequently depend on radiologists manually interpreting ultrasound pictures, which may be laborious and prone to human error-related accuracy fluctuation. This study presents an integrated deep learning approach for ultrasound picture-based breast cancer detection. A U-Net model is employed for precise tumor segmentation, followed by a Resnet, AlexNet and DenseNet model as a classifier to determine malignancy. Through early diagnosis and better patient care in the realm of medical imaging, this strategy seeks to increase the efficacy and accuracy of breast cancer detection. Convolutional neural networks (CNNs) are among the methods most often employed in image processing for deep learning. The results showed that the achieved high accuracy, about 98% for DenseNet algorithm among the three CNN Algorithms. This research showcases the potential of combining segmentation and classification techniques in a clinical context, offering a valuable tool for healthcare professionals. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2025.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Secure Chat System: Harnessing the Power of Hybrid Encryption for Enhanced Security and Confidentiality 12th

Secure Chat System: Harnessing the Power of Hybrid Encryptio...

引用

12th International Conference on Recent Trends in Computing, ICRTC 2024

作者： Jerlin, M. Asha Shrivastav, Rochak Anusha, K. Devarajan, Ganesh Gopal Nagarajan, Senthil Murugan School of Computer Science and Engineering Vellore Institute of Technology Kelambakkam—Vandalur Rd Rajan Nagar Tamil Nadu Chennai600127 India Department of Computer Science and Engineering Faculty of Engineering and Technology SRM Institute of Science and Technology Delhi NCR Campus Delhi - Meerut Road Modinagar Uttar Pradesh Ghaziabad201204 India Department of Mathematics Faculty of Science Technology and Medicine University of Luxembourg Esch-Sur-Alzette Luxembourg

ISBN: (纸本)9789819788354

Strong and secure communication solutions are essential in a time when data breaches and privacy violations are becoming more common. The extensive design for a secure chat system is presented in this research study with the goal of protecting user privacy and guaranteeing the accuracy of data shared. The fundamental idea of this design is hybrid encryption, which carefully combines the strength of Rivest–Shamir–Adleman (RSA) asymmetric encryption with the effectiveness of Advanced Encryption Standard (AES) symmetric encryption. The system also includes advanced cryptographic features like Diffie–Hellman Key Exchange for symmetric key exchange and secure communication channels, Elliptic Curve Digital Signature Algorithm (ECDSA) for message authenticity, and HMAC-SHA-512 for message authentication. The secure distribution of RSA public keys is facilitated by Public Key Infrastructure (PKI), which enhances the confidentiality and authenticity of communication channels. JSON Web Tokens (JWT) are used to provide authentication, offering a scalable and secure method for user verification throughout login procedures. Furthermore, the system incorporates a bot element that proactively alerts users to occurrences related to entry and leave from chat rooms, hence enhancing transparency and privacy consciousness among users. The suggested architecture provides a solid answer to the problems of secure communication in modern digital settings by fusing these cryptographic primitives and features. This architecture has undergone extensive testing and validation, proving its effectiveness in protecting sensitive data and providing users with secure, frictionless communication experiences. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.

关键词： Authentication

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258页 << < 5 6 7 8 9 10 11 12 13 14 > >>

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：