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

13,794 篇 会议
7,684 篇 期刊文献
257 册 图书

馆藏范围

21,735 篇 电子文献
0 种 纸本馆藏

日期分布

学科分类号

13,436 篇 工学
- 10,390 篇 计算机科学与技术...
- 8,665 篇 软件工程
- 3,411 篇 信息与通信工程
- 2,162 篇 控制科学与工程
- 1,904 篇 生物工程
- 1,594 篇 电气工程
- 1,407 篇 生物医学工程（可授...
- 1,175 篇 光学工程
- 1,170 篇 电子科学与技术（可...
- 834 篇 网络空间安全
- 791 篇 机械工程
- 677 篇 安全科学与工程
- 633 篇 动力工程及工程热...
- 592 篇 交通运输工程
- 584 篇 仪器科学与技术
- 556 篇 化学工程与技术
6,839 篇 理学
- 3,489 篇 数学
- 2,090 篇 生物学
- 1,772 篇 物理学
- 1,216 篇 统计学（可授理学、...
- 742 篇 系统科学
- 653 篇 化学
4,015 篇 管理学
- 2,427 篇 管理科学与工程(可...
- 1,769 篇 图书情报与档案管...
- 1,067 篇 工商管理
1,565 篇 医学
- 1,223 篇 临床医学
- 1,120 篇 基础医学(可授医学...
- 820 篇 公共卫生与预防医...
- 655 篇 药学(可授医学、理...
849 篇 法学
- 701 篇 社会学
373 篇 经济学
334 篇 农学
236 篇 教育学
183 篇 文学
32 篇 军事学
28 篇 艺术学
5 篇 哲学
3 篇 历史学

主题

922 篇 deep learning
848 篇 accuracy
539 篇 computational mo...
491 篇 machine learning
459 篇 feature extracti...
443 篇 training
394 篇 real-time system...
382 篇 predictive model...
371 篇 internet of thin...
321 篇 convolutional ne...
316 篇 support vector m...
285 篇 computer science
269 篇 data models
264 篇 semantics
259 篇 optimization
231 篇 neural networks
220 篇 computer archite...
214 篇 reliability
214 篇 scalability
204 篇 image segmentati...

机构

261 篇 department of co...
166 篇 school of comput...
138 篇 school of comput...
136 篇 school of comput...
122 篇 department of co...
118 篇 school of comput...
112 篇 school of comput...
106 篇 department of co...
105 篇 department of co...
103 篇 school of comput...
101 篇 college of compu...
101 篇 national enginee...
99 篇 department of co...
98 篇 school of comput...
94 篇 department of co...
93 篇 north-west unive...
93 篇 institut univers...
87 篇 infn sezione di ...
87 篇 national centre ...
82 篇 tno technical sc...

作者

122 篇 niyato dusit
96 篇 ferrara g.
96 篇 ardid m.
95 篇 calvo d.
92 篇 chen a.
88 篇 gal t.
88 篇 bozza c.
88 篇 díaz a.f.
88 篇 boumaaza j.
86 篇 coleiro a.
85 篇 gozzini s.r.
84 篇 zheng wei-shi
82 篇 anjali t.
81 篇 dallier r.
73 篇 kalekin o.
65 篇 anguita m.
64 篇 boettcher m.
61 篇 huang f.
56 篇 kulikovskiy v.
53 篇 benoit d.m.

语言

17,458 篇 英文
4,166 篇 其他
168 篇 中文
2 篇 法文
1 篇 德文
1 篇 日文
1 篇 朝鲜文
1 篇 斯洛文尼亚文

检索条件"机构=MTech Computer Science and Engineering School of Computing Science and Engineering"

共 21735 条记录，以下是741-750 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：

Hierarchical Data Storage Model Representation in MongoDB for a Resume Ranking Application 8

Hierarchical Data Storage Model Representation in MongoDB fo...

引用

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

作者： Gupta, Sahil Kumar Gupta, Raushan Kumar Acharya, Ishwor Rauniyar, Mohit Kumar Divya, K.V. Amrita school of Computing Department of Computer Science and Engineering Amrita Vishwa Vidyapeetham Bengaluru India

ISBN: (纸本)9798331505462

Introducing an innovative resume ranking website, representing Hierarchical Data Storage in MongoDB. By allowing candidates to fill out job-specific forms, the project assess their skills against customized criteria set by each company. Each skill criteria is stored in MongoDB in parent-child node formation making it easy for retrieval with minimum time complexity. Utilizing a point-based system, primary, secondary, and least priority skills are prioritized tailored to the requirements of each job opening. The goal is to make candidate selection, ensuring that the most qualified individuals rise to the top, facilitating efficient and effective hiring decisions for businesses. © 2024 IEEE.

关键词： Forestry

来源：评论

学校读者我要写书评

暂无评论

Efficiency Analysis of Conventional and Weighted Grid-Based Pathfinding Algorithms: A Performance Comparative Study 3

Efficiency Analysis of Conventional and Weighted Grid-Based ...

引用

3rd International Conference on Electrical, Electronics, Information and Communication Technologies, ICEEICT 2024

作者： Yasasree Lasya, A. Kuushalie, Asi Yerukola, Gayatri Aiswariya Milan, K. Amrita Vishwa Vidyapeetham Department of Computer Science and Engineering Amrita School of Computing Bengaluru India

ISBN: (纸本)9798350369083

In many computing applications, grid-based algorithms are essential, particularly in the gaming industry where performance, shortest path and efficiency are crucial. In order to find the best algorithm for gaming settings, this research emphasizes the importance of grid-based algorithms. The primary objective is to evaluate and contrast the various grid-based algorithms' performances while taking into account both weighted and conventional grid configurations. The implementation of the Dijkstra's, A∗, and Breadth-First Search (BFS) algorithms for both normal and weighted grids will provide insights into their applicability for gaming applications. Also, in weighted grid factors, the method known as Jump Point Search with weight will be incorporated for additional comparison. A number of measures, such as cost analysis, time complexity, space complexity, and weight complexity, will be used to conduct the evaluation process. By comparing these algorithms to one another through the process of benchmarking, the aim is to identify which algorithm offers the highest performance across all of these measures. The results of this investigation will offer significant recommendations for game designers looking to improve the performance of pathfinding algorithms in their works. © 2024 IEEE.

关键词： Peer to peer networks

来源：评论

学校读者我要写书评

暂无评论

Solar Irradiance Forecasting using Improved Sample Convolution and Interactive learning 5

Solar Irradiance Forecasting using Improved Sample Convoluti...

引用

5th International Conference on Innovative Data Communication Technologies and Application, ICIDCA 2024

作者： Subair, Ansil Gopakumar, G. Department of computer science and engineering Amrita School of Computing Amrita Viswa Vidyapeetham Amritapuri India

Renewable energy sources, driven by the global concern for climate change and the urgent need to reduce greenhouse gas emissions, are gaining increasing importance. Among them, solar energy stands out as a crucial renewable source and accurate solar irradiance forecasting is vital for its effective utilisation. Deep learning (DL) techniques have emerged as state-of-the-art solar irradiance forecasting methods in past years. However, traditional models that are widely used have inferior accuracy in forecasting. To bridge this gap, this paper presents an improved state-of-the-art model that leverages the convolutional property to forecast the time series data. We got a reduction of 8.32% in MAE compared to the base model. The paper's findings highlight the potential of DL-based approaches to significantly improve the accuracy of solar irradiance forecasts. © 2024 The Authors. Published by Elsevier B.V.

关键词： Forecasting

来源：评论

学校读者我要写书评

暂无评论

Smart Steps to Sporting Success: IoT-Driven Footwear Innovations 15

Smart Steps to Sporting Success: IoT-Driven Footwear Innovat...

引用

15th International Conference on computing Communication and Networking Technologies, ICCCNT 2024

作者： Thangam, S. Joshith, Gadi Santhosh, S. Harish, V. Jesy Janet Kumari, J. Amrita Vishwa Vidyapeetham Amrita School of Computing Department of Computer Science and Engineering Bengaluru India

ISBN: (纸本)9798350370249

Using the cloud platform Blynk IoT, smart sneakers with built-in step and calorie monitoring were created with athletes in mind. The primary characteristic of the smart shoe is its ability to detect early signals of cramping in the muscles during athletic exercises. This allows for prompt response to protect the athlete's foot and performance. It also acknowledges the vulnerabilities that athletes may encounter during training;this feature guarantees that athletes can notify the user by sending them messages in the event of any potential hazard. Beyond features for health and safety, the smart shoe calculates steps and tracks activity, giving athletes useful information for their training and recuperation regimens. With a focus on safety first, this project tackles important issues like sensor accuracy, device longevity, user comfort, and data security to produce a solution that improves athletic performance. By providing athletes with a comprehensive tool for health monitoring and personal safety, the smart shoe seeks to redefine wearable technology in sports. © 2024 IEEE.

关键词： Wearable sensors

来源：评论

学校读者我要写书评

暂无评论

Matrix Factorization for Augmented Deep Learning Model Generation 2

Matrix Factorization for Augmented Deep Learning Model Gener...

引用

2nd International Conference on Machine Learning and Data engineering, ICMLDE 2023

作者： Nived, P.A. Harikumar, Sandhya Anil, Aditya Department of Computer Science and Engineering Amrita School of Computing Amrita Vishwa Vidyapeetham Amritapuri India

This paper aims to address two significant challenges of Deep Learning(DL) model generation, high computational cost involved during the training phase and data interpretability from high dimensional data. The computational cost is curbed using centralized as well as distributed matrix factorization technique known as CUR decomposition. CUR decomposition has the advantage of reducing the dimensions of the dataset without data transformation and minimal information loss. Though Singular Value De-composition(SVD) is the best matrix decomposition technique with least reconstruction error, it transforms the data and hence the original data cannot be interpreted from the decomposed matrices while applying DL technique. So CUR decomposition is leveraged to reduce the number of features in high-dimensional data while preserving the essential information. Extensive experimental analysis is conducted to evaluate and compare the performance of CUR and SVD techniques based on reconstruction error and time complexity in centralized as well as distributed setting. The results exhibit that CUR outperforms SVD in terms of computational efficiency, especially in a distributed setting where the decomposition time for CUR was a fraction compared to SVD. At the same time DL models generated from this reduced dataset exhibit comparable accuracy with the original high dimensional dataset as well as reduced dataset obtained through SVD. This work also enhances the accessibility of the CUR algorithm to users, for which an application is developed that enables users to execute the algorithm on any dataset. The user-friendly interface of the application facilitates the upload of datasets, configuration of desired decomposition rank, and execution of the algorithm with a single click. © 2024 Elsevier B.V.. All rights reserved.

关键词： Deep learning

来源：评论

学校读者我要写书评

暂无评论

An Ensemble based Convolutional Neural Network modelling for Classifying Marine Animal types 15

An Ensemble based Convolutional Neural Network modelling for...

引用

15th International Conference on computing Communication and Networking Technologies, ICCCNT 2024

作者： Talluri, Charitha Sagi, Shriya Samitha, V. Kavitha, C.R. Amrita Vishwa Vidyapeetham Amrita School of Computing Dept of Computer Science and Engineering Bengaluru India

ISBN: (纸本)9798350370249

Studying Biodiversity and ecological monitoring, in classification of marine animal's category is important. This paper tells how comprehensive analysis and comparison is done among the deep learning models that have been implemented. InceptionV3, MobileNetv1, EfficientNetB0 and Vision Transformer(ViT) are the four convolutional neural network models used in this process. DataSet was taken from kaggle with 13,512 images of 23 different categories in different environmental conditions. Each model is trained independently with dataset and evaluated with the marine animal images. After comparing all these four individual models using their metrics, we considered to build an ensemble approach that sums up the advantages of these models which helps in enhancing the performance. This study not only showcases how advance the models are, but also the explains the use of ensemble approaches for increasing the efficiency. © 2024 IEEE.

关键词： Classification CNN Dropout layers EfficientNetB0 InceptionV3 MobileNetV1 Optimizer Vision Transformer(ViT) Ensemble model

来源：评论

学校读者我要写书评

暂无评论

TripleACrypt: Cryptography and Steganography for the Preservation of Ancient Discoveries 8

TripleACrypt: Cryptography and Steganography for the Preserv...

引用

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

作者： George, Angelina Ashik, F. Jose, Alphonsa Kavitha, C.R. Amrita School of Computing Department of Computer Science & Engineering Amrita Vishwa Vidyapeetham Bengaluru India

ISBN: (纸本)9798331505462

'Steganocryptic Repositories' is an idea that incorporates cryptographic techniques with steganographic ones to preserve India's manuscript heritage in the digital age. Ancient manuscripts are encrypted with the AES technique, guaranteeing their security. An additional degree of protection is added by using the RSA technique to encrypt the key used in the AES encryption process. Additionally, this combination requires encoding the colors of high-resolution digital scans with the RSA encryption key including the encrypted manuscript, which is accomplished by hiding detailed metadata related to the manuscripts using the Least Significant Bit (LSB) approach. Use of Streamlit and ngrok allow for safe and easy to use frontend for the application. While Streamlit creates an interactive Graphical User Interface (GUI) for the application, ngrok ensures secure access to it. This method preserves and makes available the vast cultural knowledge contained in India's manuscripts by giving researchers and scholars access to decryption keys, ensuring secure access. This also preserves and reveals the mysteries of India's literary and historical heritage for the benefit of future generations. © 2024 IEEE.

关键词： AES Encryption Digital Preservation Least Significant Bit (LSB) Approach Manuscript Heritage Metadata Encryption ngrok RSA Encryption Steganography Streamlit

来源：评论

学校读者我要写书评

暂无评论

Enhanced Alzheimer's Disease Classification: A Stacked Model Fusion with Brain MRI Imaging 2

Enhanced Alzheimer's Disease Classification: A Stacked Model...

引用

2nd IEEE International Conference on Contemporary computing and Communications, InC4 2024

作者： Chaitanya, Tekumudi Vivek Sai Surya Annamalai, R. Amrita School of Computing Amrita Vishwa Vidyapeetham Department of Computer Science and Engineering Chennai India

ISBN: (纸本)9798350383652

Alzheimer's disease (AD) is still a major global health issue that requires sophisticated staging and classification techniques. This paper introduces a novel approach to AD categorization, employing a stacked network architecture and feature extractions from InceptionV3, EfficientNetB0, and MobileNet models. The primary objective is to address the challenge of imbalanced datasets while minimizing the risk of overfitting. The proposed method utilizes brain MRI scans, extracting features and incorporating a Global Average Pooling (GAP) layer to improve the identification of critical features that correspond to AD phases. Combining the retrieved features results in a single set that helps with stage discrimination, followed by finishing via a SoftMax classifier. Model evaluation and validation are essential steps in determining the ideal model to minimize the risk of overfitting. A comprehensive evaluation is ensured by cross-validation (CV) using a 3-fold technique, which shows that the suggested Stacked Model has a better accuracy of 94.58%, closely followed by EfficientNetB0 at 90.70%. Both InceptionV3 and MobileNet exhibit competitive results, with accuracy rates of 89.46% and 87.60%, respectively. By presenting a strong approach to AD classification, this study advances the field of early detection and staging of AD by demonstrating the effectiveness of the Stacked network in identifying complex features that are indicative of different stages of AD progression within brain MRI datasets. © 2024 IEEE.

关键词： Neurodegenerative diseases

来源：评论

学校读者我要写书评

暂无评论

Exploring Compiler Optimization: A Survey of ML, DL and RL Techniques 8

Exploring Compiler Optimization: A Survey of ML, DL and RL T...

引用

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

作者： Mithul, C. Abdulla, D. Mohammad Virinchi, M. Hari Sathvik, M. Belwal, Meena Amrita School of Computing Amrita Vishwa Vidyapeetham Department of Computer Science and Engineering Bengaluru India

ISBN: (纸本)9798331505462

The past few years, traditional compiler optimization methods have been found to be further enhanced by machine learning (ML), deep learning (DL) and reinforcement learning (RL). These differ from classical techniques that often use rule of thumb based decision making. Rather, ML/DL/RL based approaches provide a means for learning from data thus improving performance in different dimensions such as code generation, resource allocation and runtime. In this paper we give an overview of current research and methodologies utilizing ML, DL and RL for compiler optimization purposes. We analyze the major models in terms of their employed learning strategies and desired optimizations within a compiler framework. Moreover, we highlight some of the difficulties faced when these compilers are embedded with these learning models such as adaptability, generalization and overhead trade-offs. Additionally, our survey presents case studies demonstrating Quantitative improvements on well-known benchmarks mainly focusing on models' adaptability to different architectures and their role in supporting the decision-making process of compilers. We conclude outlining open research questions as well as possible future directions for further investigations into this emerging interdisciplinary field. © 2024 IEEE.

关键词： Program compilers

来源：评论

学校读者我要写书评

暂无评论

E-Sangrahan: A Sustainable Paradigm and comprehensive framework for efficient E-Waste Management towards a Greener Future

E-Sangrahan: A Sustainable Paradigm and comprehensive framew...

引用

2024 International Conference on Recent Innovation in Smart and Sustainable Technology, ICRISST 2024

作者： Malagati, Nischal S. Rajesh, M. Sreevidya, B. Amrita Vishwa Vidyapeetham Amrita School of Computing Department of Computer Science and Engineering Bengaluru India

ISBN: (纸本)9798350309140

According to experts, E-Waste is one of the most dangerous environmental concern India is facing. According to ASSOCHAM an industrial body predicts that by 2020, India will generate 5.2 million tons of E-Waste. E-waste stands for Electronic waste that has been discarded. computers, monitors, and other electronic appliances contain electronic items harmful to nature if not recycled properly. E-waste plays a major role in polluting soil, and air which is caused due to irregular ways of disposing of E-Waste. There are many governments driven initiatives for E-Waste management, but the awareness and the significance of W-Waste management is still not reached to the larger community. The proposed work - E-Sangrahan is an effort to tackle the problems faced while dealing with E-Waste. A web application is developed to handle the E-Waste management process in a much ease and user-friendly way. E-Sangrahan is the future of recycling E-Waste, which helps create a sustainable future. E-Sangrahan offers a dynamic website that is simple to use and everybody can access. The website includes a live user-friendly E-Waste warehouse locator, that helps dispose of E-Waste by yourself. The locator even tells you about the directions to be taken and how to get there by road. The novelty or uniqueness of E-Sangrahan is the fact that the website also consists of a machine learning model that helps people to identify the type of E-Waste it belongs to. The objective of this machine learning model is to remove the confusion between E-Waste items and non-E-Waste items because if any E-Waste item is not recycled, the environmental impact is large. E-Sangrahan would be the next revolution in the theme of E-Waste. © 2024 IEEE.

关键词： Waste management

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 << < 71 72 73 74 75 76 77 78 79 80 > >>

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：