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

33,297 篇 会议
5,134 篇 期刊文献
270 册 图书

馆藏范围

38,701 篇 电子文献
0 种 纸本馆藏

日期分布

学科分类号

23,827 篇 工学
- 17,229 篇 计算机科学与技术...
- 14,496 篇 软件工程
- 6,363 篇 信息与通信工程
- 3,832 篇 控制科学与工程
- 2,914 篇 电子科学与技术（可...
- 2,820 篇 电气工程
- 2,609 篇 生物工程
- 2,096 篇 生物医学工程（可授...
- 1,646 篇 光学工程
- 1,509 篇 机械工程
- 1,357 篇 仪器科学与技术
- 1,347 篇 动力工程及工程热...
- 1,105 篇 化学工程与技术
- 964 篇 安全科学与工程
- 798 篇 交通运输工程
12,117 篇 理学
- 6,500 篇 数学
- 3,288 篇 物理学
- 2,862 篇 生物学
- 2,166 篇 统计学（可授理学、...
- 1,491 篇 系统科学
- 1,175 篇 化学
6,226 篇 管理学
- 3,667 篇 管理科学与工程(可...
- 2,870 篇 图书情报与档案管...
- 1,985 篇 工商管理
1,822 篇 医学
- 1,564 篇 临床医学
- 1,459 篇 基础医学(可授医学...
- 945 篇 药学(可授医学、理...
- 785 篇 公共卫生与预防医...
1,182 篇 法学
- 965 篇 社会学
715 篇 经济学
- 715 篇 应用经济学
559 篇 农学
475 篇 教育学
184 篇 文学
92 篇 军事学
45 篇 艺术学
1 篇 哲学

主题

1,222 篇 accuracy
970 篇 feature extracti...
926 篇 computational mo...
834 篇 deep learning
781 篇 training
768 篇 computer science
624 篇 real-time system...
616 篇 machine learning
601 篇 support vector m...
525 篇 predictive model...
485 篇 internet of thin...
436 篇 convolutional ne...
414 篇 data models
366 篇 reliability
346 篇 computer archite...
340 篇 data mining
325 篇 optimization
306 篇 routing
303 篇 wireless sensor ...
302 篇 artificial intel...

机构

82 篇 north-west unive...
82 篇 institut univers...
80 篇 national centre ...
79 篇 infn sezione di ...
76 篇 infn sezione di ...
76 篇 institute of inf...
71 篇 tno technical sc...
66 篇 università di ca...
63 篇 université de st...
58 篇 dept. of informa...
56 篇 dept. of compute...
53 篇 nikhef national ...
53 篇 dept. of informa...
52 篇 school of automa...
52 篇 leiden universit...
51 篇 dept. of compute...
47 篇 dept. of compute...
43 篇 dept. of electri...
42 篇 infn lnf via enr...
42 篇 in2p3 lpc campus...

作者

85 篇 ferrara g.
85 篇 ardid m.
84 篇 calvo d.
84 篇 gal t.
84 篇 bozza c.
81 篇 chen a.
81 篇 kalekin o.
79 篇 boumaaza j.
78 篇 díaz a.f.
78 篇 coleiro a.
70 篇 gozzini s.r.
68 篇 huang f.
61 篇 dallier r.
54 篇 anguita m.
51 篇 kulikovskiy v.
44 篇 del burgo r.
41 篇 benoit d.m.
41 篇 eddymaoui a.
40 篇 gagliardini s.
40 篇 labalme m.

语言

37,301 篇 英文
962 篇 其他
336 篇 中文
54 篇 日文
47 篇 朝鲜文
2 篇 德文
1 篇 法文
1 篇 葡萄牙文
1 篇 斯洛文尼亚文

检索条件"机构=Dept of Computer Science and Computer Engineering"

共 38701 条记录，以下是191-200 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：

Species Density Analysis Using Deep Learning

Species Density Analysis Using Deep Learning

引用

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

作者： Rekha, K.S. Shamlin, A Harini Saveetha Engineering College Dept. of Computer Science and Engineering Chennai India

ISBN: (纸本)9798350309140

The primary objective of this project is to develop a machine learning model, specifically Convolutional Neural Network (CNN), to count the density of several particular species in an audio clip. The model is trained on a dataset containing calls of the specified species and other species. This innovation has significant implications for wildlife monitoring and ecological research, as it can help researchers track and understand the behavior of organisms in forest regions more efficiently. Manual effort in audio analysis can be reduced by machine learning, thereby saving time. By improving and broadening techniques, algorithms, and training methodologies, researchers can uncover more about animal behavior and contribute to our collective understanding of ecosystems. The application of this technology can be useful for analyzing the total number of species in a certain rainforest region, eventually reducing the burden on researchers and streamlining the entire process. Overall, this project has immense potential to pave the way for more efficient and accurate wildlife monitoring and ecological research that can ultimately benefit our planet's biodiversity. © 2024 IEEE.

关键词： Forest ecology

来源：评论

学校读者我要写书评

暂无评论

Automated Weed Detection and Removal using Deep Learning 4

Automated Weed Detection and Removal using Deep Learning

引用

4th IEEE Asian Conference on Innovation in Technology, ASIANCON 2024

作者： Thenmozhi, T. Subashini, S. Pradeepa, K. Pooja, E. Sri Ramakrishna Engineering College Dept of Computer Science and Engineering Coimbatore India

ISBN: (数字)9798350354218

ISBN: (纸本)9798350354218

Precision agriculture uses cutting-edge technology to improve farming operations, increase crop yields, and reduce resource use. This study focuses on developing an autonomous weed and crop detection system that leverages the cutting-edge You Only Look Once (YOLO) *** purpose is to equip farmers with a real-time solution to identify and distinguish crops fromweeds in agricultural fields. The process entails creating a well-annotated dataset with photos of both crops and weeds. A pre- trained YOLO model, such as YOLOv3 or YOLOv4, is chosen and fine-tuned with the annotated dataset. The YOLO configuration file is changed to meet the unique crop and weed detection needs. The training procedure continues until adequate convergence is obtained. The trained YOLO model is then connectedwith agricultural equipment, such as drone-mounted cameras or other sensing devices, allowing for real- time detection in the field. Post-processing techniques are used to improve detection results while minimizing false positives. Decision-making algorithms are developed to direct activities based on the detected crops and weeds, allowing for focused interventions such as precision herbicide administration. © 2024 IEEE.

关键词： Precision agriculture

来源：评论

学校读者我要写书评

暂无评论

Segmentation and Classification of Skin Lesions Using Ensemble of Convolutional Neural Networks

Segmentation and Classification of Skin Lesions Using Ensemb...

引用

2024 IEEE International Conference on Computing, Applications and Systems, COMPAS 2024

作者： Rahman, Md. Mahfuzur Chandra Shill, Pintu Khulna University of Engineering and Technology Dept of Computer Science and Engineering Khulna Bangladesh

ISBN: (纸本)9798331529765

This research proposes an advanced ensemble model based on Convolutional Neural Networks (CNNs) designed to enhance the segmentation and classification of skin lesions, a critical step in the early detection of melanoma and other skin cancers. The study explores ensemble strategies, including bagging, boosting, and stacking, to identify the most effective approach for combining multiple CNN models. A novel ensemble method incorporating pre-trained dual encoders is introduced to improve segmentation accuracy by extracting critical features and precisely delineating lesion boundaries. The dual encoders are configured with different encoder-decoder architectures, activation functions, and optimization algorithms to optimize feature extraction and segmentation performance. The suggested model was tested on the ISIC 2019 and HAM10000 datasets, attaining an accuracy rate of 95.3%, with sensitivity at 93.7%, specificity at 96.8%, and an F1-score of 94.5%. The findings demonstrate a significant improvement over current leading techniques, confirming the robustness and reliability of the proposed ensemble strategy. The superior performance of the model suggests its potential for integration into clinical practice, providing dermatologists with a valuable tool for early skin cancer detection and improving patient outcomes through timely intervention. © 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

Predictive Precision: A Comparative Study of ML in Alzheimer's Diagnosis 1

Predictive Precision: A Comparative Study of ML in Alzheimer...

引用

1st International Conference on Trends in engineering Systems and Technologies, ICTEST 2024

作者： Sujatha, E. Subiksha, M. Saveetha Engineering College Dept.of Computer Science and Engineering Chennai India

ISBN: (纸本)9798350307795

Alzheimer's disease has become a significant contemporary health concern, impacting approximately 45 million individuals. This degenerative brain condition, prevalent among the elderly, lacks a well-defined etiology and pathogenesis. Dementia serves as the primary instigator, progressively inflicting damage upon brain cells and leading to a decline in cognitive functions such as thinking and reading. Those afflicted typically experience an average of 8 years of lifespan after the discernible onset of symptoms. However, this duration may vary, spanning from four to 20 years, contingent upon factors such as age and overall health. Addressing this critical issue, the integration of ML systems gives a great solution for disease prediction. The primary objective is to identify Dementia in diverse patient populations. This study encapsulates the outcomes and analyses derived from the detection of Dementia from many ML algorithms. The dataset collected from the Open Access Series of Imaging Studies (OASIS) serves as the foundational resource for system development. Comprising MRI data from 150 patients from the age gap of 60 to 96, this also undergoes comprehensive scrutiny and application across multiple machine learning *** ensuing comparative analysis seeks to ascertain the efficacy of different models in delivering optimal results. Through this investigation, the aim is to delineate the model that exhibits superior performance for the detection of Alzheimer's disease within the context of the OASIS dataset. © 2024 IEEE.

关键词： Diagnosis

来源：评论

学校读者我要写书评

暂无评论

A Study of Various Optimization Algorithms and Entropy Measures for Image Segmentation 18

A Study of Various Optimization Algorithms and Entropy Measu...

引用

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

作者： Gonthina, Nagamani Prasad, L. V. Narasimha Institute of Aeronautical Engineering Dept. of Computer Science and Engineering Hyderabad India

ISBN: (纸本)9789380544519

One of the most challenging jobs in image processing techniques is image segmentation. To identify the objects of interest in an image, we segment the image into different parts and extract the interesting objects. Previous studies have addressed various techniques for image segmentation, like clustering, thresholding, watershed, neural networks, etc. However, a segmentation technique alone cannot achieve better-segmented results. Much research is being carried out by combining the segmentation technique with either an optimization algorithm or entropy measures to enhance the efficiency of segmented results in the segmentation process. So, there is a need to study various segmentation techniques combined with optimization algorithms or entropy measures. Recent studies focused only on segmentation techniques, entropy measures, or optimization algorithms rather than on these combinations. This paper presents various works based on optimization techniques and entropy measures combined with clustering and thresholding techniques of image segmentation. From the study it is observed that most of the work is carried out in combining thresholding-based image segmentation techniques with optimization algorithms and entropy measures. © 2024 Bharati Vidyapeeth, New Delhi.

关键词： Entropy measures Image segmentation Optimization algorithms Segmentation techniques

来源：评论

学校读者我要写书评

暂无评论

VisualBlend - A Mixed Approach on Forensic Image Generation and Recognition 6

VisualBlend - A Mixed Approach on Forensic Image Generation ...

引用

6th IEEE International Conference on Recent Advances in Intelligent Computational Systems, RAICS 2024

作者： Unnikrishna, Pillai Midhun Pulkuzhiyil, Vinayak Krishna, Jyothika Wilson, Naveen Kumar, Veena A. Saintgits College Of Engineering Dept. of Computer Science and Engineering Kottayam India

ISBN: (纸本)9798350381689

An extensive use case of Generative Adversarial Networks (GANs) that not only combines artistic creativity with technological innovation but also significantly improves identification precision, filling in critical gaps in the smooth integration of textual descriptions with visual representations. The motivation is rooted on the difficulties that currently exist in accurately identifying human face sketches by directly transforming them into images, an area where prior approaches were inadequate. Our special dual-function technology is designed to get beyond these obstacles and provides a fresh approach for forensic investigators, artists, and sculptors. It has the ability to convert text to image as well as sketch to image. This easy transformation of textual and drawing data represents an integrated combination of creativity and technology that is set to have an impact on a number of disciplines, such as suspect identification and crime scene reconstruction. © 2024 IEEE.

关键词： Generative adversarial networks

来源：评论

学校读者我要写书评

暂无评论

Face Generation and Recognition in Forensic science 11

Face Generation and Recognition in Forensic Science

引用

11th IEEE International Conference on Advances in Computing and Communications, ICACC 2024

作者： Ravi, Gayathri Joy, Heynes Jitto, Jeffin Joshy, Jocelyn Jose, Jisha Mary Rajagiri School of Engineering & Technology Dept. of Computer Science and Engineering India

ISBN: (纸本)9798350379136

Suspect identification can be challenging for forensic investigations since standard procedures are time-consuming and prone to mistakes. This calls for the creation of novel approaches utilizing developments in machine learning (ML) and artificial intelligence (AI). In order to overcome these obstacles, the proposed Face Generation and Recognition in Forensic science will make use of sophisticated recognition algorithms and AI-based face generation models. Fully trained Stable Diffusion model is applied to generate high-quality face images from textual descriptions. Image Generation, Text Guided Image Manipulation using Denoising Diffusion Probabilistic Models (DDPMs), and Dataset Matching are the three primary components of the process. Using a stable diffusion model, Image Generation quickly creates high-resolution images from word prompts by combining an autoencoder (VAE), U-Net, and text encoder. With the introduction of an alternate noise space for DDPMs, Text Guided picture Manipulation makes it possible to do meaningful picture altering tasks in response to text prompts. VGG-16 , a convolutional neural network architecture is used in dataset matching to extract features and calculate similarity, which makes dataset alignment and comparison easier. The suggested methodology gives law enforcement authorities effective tools for identifying suspects, which represents a substantial development in forensic investigations. The project intends to increase the efficiency of criminal investigations, accelerate the matching process with large datasets, and enhance the accuracy of facial sketches by utilizing AI and ML approaches. The approach's ability to produce coherent and contextually relevant face images is validated by experimental results, which also show the approach's potential for speeding up the conclusion of criminal cases, particularly unsolved cold cases. All things considered, Face Generation and Recognition in Forensic science is a promising step in st

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

An Approach for XAI Visualizations for Explainability of Alzheimer's Detection 2

An Approach for XAI Visualizations for Explainability of Alz...

引用

2nd International Conference on Networking, Embedded and Wireless Systems, ICNEWS 2024

作者： Khanapur, Shraddha Bharadwaj, Chirag B. Bhardwaj, Raghav Nayak, Jyothi S. BMS College of Engineering Dept. of Computer Science and Engineering Bengaluru India

ISBN: (纸本)9798350367461

In the field of medical image analysis, the integration of machine learning (ML) models has significantly enhanced the process of identifying and diagnosing Alzheimer's disease. However, the opacity of these models, often termed as "black boxes,"raises concerns regarding their interpretability and reliability in clinical settings. Explainable artificial intelligence (XAI) techniques have emerged as crucial tools to address these challenges by clarifying the reasoning behind model outputs. This paper offers an extensive review of literature concerning the employment of Explainable Artificial Intelligence (XAI) methodologies, such as SHAP, LIME, GradCAM, DeepLIFT, Saliency Maps, and LRP to augment the comprehensibility of ML models applied in the detection of Alzheimer's disease. © 2024 IEEE.

关键词： Neurodegenerative diseases

来源：评论

学校读者我要写书评

暂无评论

Streamline Pro Next-Gen Recruitment Solution

Streamline Pro Next-Gen Recruitment Solution

引用

2024 International Conference on Innovative Computing, Intelligent Communication and Smart Electrical Systems, ICSES 2024

作者： Kumar, Vinod Sangeetha, G. Gopal, K. Kumar, P. Rajalakshmi Engineering College Dept. of Computer Science and Engineering Chennai India

ISBN: (纸本)9798331543617

An innovative full-stack project called 'StreamlinePro Next-Gen Recruitment Solution' aimsto transform the hiring process. With its modern technologies, this fully inclusive platform enhances the hiring process to satisfy the demands of administrators, HR professionals, and job seekers. The Job Board Application is developed around a powerful system for posting jobs and accepting applications. Experts in human resources can readily post job openings, andneed to offer corporate papers to validate their skills. This ensures that reliable sources are used to publish job openings. Conversely, candidates can use the website to look for jobs that fit their qualifications and apply immediately. Posting resumes is required, and an applicant tracking system (ATS) reviews them after are uploaded. After reviewing the entries, the ATS rates the resumes according to theirquality and applicability. One of the primary aspects of the StreamlinePro Next-Gen Recruitment Solution is its exclusive referral mechanism. Employees in a company may indicate that are willing to suggest others. Job searchers can contact these references, and if accepted, both parties can communicate through an integrated chat system. This recommendation system encourages networking and enhances job-seeking opportunities by leveraging existing staff networks. The application also offers the capability of real-time job status tracking. Applicants can monitor the progress of their applications and receive alerts regarding their receipt, review, and acceptance by employers. This tool helps clarity and informs job seekers during the hiring process. © 2024 IEEE.

关键词： Apprentices

来源：评论

学校读者我要写书评

暂无评论

Forecasting Stock Price by LSTM-CNN Hybrid Model and Compares Deep Learning Models 1

Forecasting Stock Price by LSTM-CNN Hybrid Model and Compare...

引用

1st IEEE International Conference on Smart Power Control and Renewable Energy, ICSPCRE 2024

作者： Arora, Aditi Upadhyay, Yashaswi Shukla, Satvik Saket Abes Engineering College Dept. of Computer Science and Engineering Ghaziabad India

ISBN: (纸本)9798350377002

The The accurate forecasting of stock prices holds significant importance in devising effective trading strategies and making informed decisions about stock transactions. The inherent volatility in stock prices, driven by factors like geopolitical tensions, corporate earnings, and commodity costs, underscores the need for precise predictions. Domestic factors such as central bank policies, governmental decisions, inflation, and global market uncertainties also trigger stock price fluctuations. Estimating this volatility is a complex challenge for traders. A novel approach is presented in this research, proposing a hybrid model that integrates two distinct algorithms - Long Short-Term Memory-Convolutional Neural Network (LSTM-CNN). This model harnesses diverse data representations from stock time series to enhance price prediction accuracy. Comparative analyses are performed with alternative models like LSTM (Long Short-Term Memory), CNN (Convolutional Neural Networks) and Naïve Bayes to ascertain the most effective prediction paradigm with minimal error. The study demonstrates that combining temporal and image features extracted from the same dataset diminishes prediction errors compared to using these features independently. The hybrid model outperforms singular prediction models, highlighting a high enhancement. Among the individual models, the LSTM model exhibits superior performance in terms of prediction accuracy. © 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 << < 16 17 18 19 20 21 22 23 24 25 > >>

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：