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

22,002 篇 会议
3,552 篇 期刊文献
208 册 图书

馆藏范围

25,762 篇 电子文献
0 种 纸本馆藏

日期分布

学科分类号

15,810 篇 工学
- 11,148 篇 计算机科学与技术...
- 9,355 篇 软件工程
- 4,296 篇 信息与通信工程
- 2,504 篇 控制科学与工程
- 2,154 篇 电子科学与技术（可...
- 2,139 篇 电气工程
- 1,539 篇 生物工程
- 1,321 篇 生物医学工程（可授...
- 1,135 篇 光学工程
- 1,029 篇 机械工程
- 884 篇 仪器科学与技术
- 834 篇 动力工程及工程热...
- 744 篇 化学工程与技术
- 624 篇 安全科学与工程
- 524 篇 交通运输工程
- 467 篇 材料科学与工程（可...
- 445 篇 建筑学
8,214 篇 理学
- 4,524 篇 数学
- 2,415 篇 物理学
- 1,705 篇 生物学
- 1,374 篇 统计学（可授理学、...
- 916 篇 系统科学
- 760 篇 化学
3,990 篇 管理学
- 2,397 篇 管理科学与工程(可...
- 1,826 篇 图书情报与档案管...
- 1,258 篇 工商管理
1,071 篇 医学
- 948 篇 临床医学
- 882 篇 基础医学(可授医学...
- 574 篇 药学(可授医学、理...
713 篇 法学
- 561 篇 社会学
445 篇 经济学
346 篇 教育学
316 篇 农学
110 篇 文学
73 篇 军事学
26 篇 艺术学
4 篇 哲学
3 篇 历史学

主题

681 篇 accuracy
529 篇 feature extracti...
474 篇 deep learning
473 篇 computational mo...
376 篇 support vector m...
370 篇 training
365 篇 computer science
319 篇 internet of thin...
283 篇 machine learning
281 篇 real-time system...
278 篇 computer archite...
235 篇 predictive model...
221 篇 routing
220 篇 reliability
218 篇 optimization
212 篇 data mining
210 篇 neural networks
207 篇 convolutional ne...
199 篇 throughput
193 篇 image segmentati...

机构

85 篇 dept. of compute...
84 篇 institut univers...
83 篇 north-west unive...
83 篇 université de st...
82 篇 infn sezione di ...
82 篇 tno technical sc...
81 篇 national centre ...
79 篇 nikhef national ...
76 篇 infn sezione di ...
69 篇 university würzb...
66 篇 università di ca...
53 篇 leiden universit...
51 篇 dept. of compute...
50 篇 school of automa...
50 篇 university of jo...
48 篇 university moham...
44 篇 university moham...
43 篇 in2p3 lpc campus...
42 篇 infn lnf via enr...
42 篇 university of gr...

作者

95 篇 ardid m.
93 篇 ferrara g.
92 篇 kalekin o.
92 篇 díaz a.f.
91 篇 boumaaza j.
90 篇 coleiro a.
89 篇 calvo d.
83 篇 gal t.
82 篇 bozza c.
80 篇 chen a.
78 篇 gozzini s.r.
76 篇 huang f.
76 篇 dallier r.
72 篇 anguita m.
63 篇 enzenhöfer a.
60 篇 kulikovskiy v.
58 篇 boettcher m.
57 篇 celli s.
54 篇 aly z.
52 篇 dornic d.

语言

24,761 篇 英文
608 篇 其他
295 篇 中文
75 篇 日文
21 篇 朝鲜文
1 篇 阿拉伯文
1 篇 德文
1 篇 法文
1 篇 斯洛文尼亚文
1 篇 土耳其文

检索条件"机构=Dept. Computer Technology and Computer Graphics"

共 25762 条记录，以下是201-210 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：

Revolutionizing Road Safety for Advanced Vehicular Accident Prediction 2

Revolutionizing Road Safety for Advanced Vehicular Accident ...

引用

2nd International Conference on Intelligent Data Communication Technologies and Internet of Things, IDCIoT 2024

作者： Deepika, T. Yuvaraj, N. Sri Preethaa, K.R. KPR Institute of Engineering and Technology Dept. of Computer Science and Engineering Coimbatore India

ISBN: (纸本)9798350327533

The detection and tracking of vehicle speed are crucial for ensuring the safety of civilians and preventing accidents. Speed tracking plays a pivotal role in traffic surveillance, where effective management and the well-being of citizens take precedence. The approach leverages computer vision-based models, specifically Multi-scale Detector for object detection, and a fusion of the DeepSORT and Centroid Sort algorithms for vehicle tracking from streaming video. To cater to the requirements of these algorithms, a custom dataset was developed within a controlled setting. Dataset augmentation was employed to prevent overfitting, thereby enhancing the dataset's diversity and the model's ability to generalize. The method demonstrates the capacity to accurately detect and track vehicles, maintaining performance even in high-traffic conditions. Cross-validation at every epoch during the training phase was implemented to increase the model's accuracy. In addition to the technical aspects, an LED display board was integrated to provide real-time data to oncoming vehicles at road curves. This display showcases information such as vehicle types, passage time, and the number of vehicles within the curvy road. The proposed Multi-Scale Detector model, a customized version of the You Only Look Once (YOLO) architecture, achieved a mean average precision (mAP) of 0.954 at a confidence interval of 0.5. This overall research provides an effective and accurate solution for optimizing vehicle tracking, enhancing transportation safety, and enabling a variety of practical applications in traffic management and monitoring. © 2024 IEEE.

关键词： DeepSORT Euclidean Distance and Vehicle Intelligence Multi-scale Detector Object Detection Speed Tacking

来源：评论

学校读者我要写书评

暂无评论

Tuberculosis Diagnosis in Chest X-Rays via Transfer Learning Techniques

Tuberculosis Diagnosis in Chest X-Rays via Transfer Learning...

引用

2024 IEEE International Women in Engineering (WIE) Conference on Electrical and computer Engineering, WIECON-ECE 2024

作者： Keerthana, T. Jayakumar, K. Iyyappan, V. Shopika, S. Sowmiya, X.L. Ponnusamy, R. Chennai Institute of Technology Dept. of Computer Science and Engineering Tamilnadu Chennai India

ISBN: (数字)9798331535476

ISBN: (纸本)9798331535476

Tuberculosis (TB) remains one of the world's major health problems. Detection with Chest X-rays is a mainstay tool in the early diagnosis of TB. Traditional methods used in the conventional detection of TB are very slow and susceptible to human errors. Thus, there is a need for an automated technique. The paper discusses the possibility of using advanced deep learning techniques, particularly techniques stemming from transfer learning, to enhance the detectability as well as efficiency of TB. Fine-tuned pre-trained convolutional neural networks, such as ResNet and VGG, on a dataset of chest X-ray images extracted high-level features relevant to the detection of TB. Superhuman performance was achieved with limited medical imaging data by transferring learned representations from large-scale image classification tasks. Experimental results illustrate high accuracy, precision, and recall rates, confirming that transfer learning is adequate for automating TB detection. This approach reduces the need for manual intervention and offers a scalable, cost-effective solution to enable rapid TB screening, particularly in low-resource settings. The novelty of the work comes from using transfer learning with fine-tuned pre-trained models (ResNet and VGG) in getting high generalization accuracy for tuberculosis detection from chest X-rays, even with limited data. © 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

MeQANet: Deep Learning-based Framework for Classifying Medical Query Answering in Bengali

MeQANet: Deep Learning-based Framework for Classifying Medic...

引用

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

作者： Tasnia, Fairooz Hoque, Mohammed Moshiul Chittagong University of Engineering and Technology Dept. of Computer Science and Engineering Chattagram Bangladesh

ISBN: (纸本)9798331529765

The automatic classification of medical QA pairs is crucial for improving healthcare efficiency, allocating specialized care, optimizing resource distribution, and facilitating robust data analysis. Bengali, the 7th most widely spoken language globally, has a growing volume of health-related queries. However, unlike English, there is no benchmark large-scale medical QA dataset, pre-trained language model, or human baseline score for medical QA in Bengali. This paper introduces a deep learning-based framework called MeQANet that leverages CNN and BiLSTM techniques for classifying medical QA texts in Bengali. It also presents a novel medical QA corpus in Bengali (BnMedQA), consisting of approximately 4500 medical QA pairs across eight domains: Orthopedic, ENT, Gastroenterology and Hepatology, Gynecology, Pediatrics, General Medicine, Dermatology, and Cardiology. Various techniques (including LR, SVM, RF, MNB, AdaBoost (AB), CNN, BiL-STM, and CNN+BiLSTM) are employed to perform the classification tasks. Experimental results indicate that the CNN+BiLSTM approach achieved the highest F1-score of 0.85 among all employed techniques. © 2024 IEEE.

关键词： Query languages

来源：评论

学校读者我要写书评

暂无评论

Deep Feature Fusion Based Brain Tumor Classification From Imbalance MRI Dataset Using Weighted Loss Functions 2

Deep Feature Fusion Based Brain Tumor Classification From Im...

引用

2nd International Conference on Power, Electrical, Electronics and Industrial Applications, PEEIACON 2024

作者： Tasnim, Taieba Parvin, Farjana Rajshahi University of Engineering & Technology Dept. of Computer Science & Engineering Rajshahi Bangladesh

ISBN: (纸本)9798331517984

Deep learning using MRI images to classify brain tumours presents a significant challenge due to imbalanced training datasets, where one tumor type may have far more samples than others. The overrepresented class may perform worse in classifiers as a result of this imbalance. In order to tackle this issue, the paper examines how feature learning in CNNs is affected by weighted loss functions to manage data imbalance. The article propose deep feature fusion, where particular CNN model features that were trained using three distinct loss functions are fused and classified using softmax classifier. This approach lead to notable improvements in brain tumor classification compared to a CNN trained with standard cross-entropy loss. Notably, the proposed methods substantially reduce classification errors between uneven class samples. The proposed model achieved an impressive 94.5% classification accuracy, accompanied by an average Fl-score of 94.6%, average precision of 94.6 %, and average recall of 95%. These findings underscore the effectiveness of our methodology in improving brain tumor classification accuracy, offering a promising avenue for more reliable diagnosis and treatment planning in clinical settings, © 2024 IEEE.

关键词： Deep learning

来源：评论

学校读者我要写书评

暂无评论

Skin Lesion Classification using Deep Learning Architectures 2

Skin Lesion Classification using Deep Learning Architectures

引用

2nd IEEE International Conference on Networks, Multimedia and Information technology, NMITCON 2024

作者： Gothivrekar, Siddhi Khanvilkar, Anuj Nandi, Utsab Singh, Kamal Maktum, Tabassum Ramrao Adik Institute of Technology Dept. of Computer Engineering Navi Mumbai India

ISBN: (纸本)9798350372892

Skin cancer, originating from diverse dermatological conditions, can be classified based on texture, structure, and color. Identifying lesions from images aids in pre-diagnosis;expanding beyond melanoma, early detection of lesions like Actinic Keratosis and basal cell carcinoma is crucial for timely intervention. Recently, deep convolutional neural networks (DCNNs) have shown promising results in dermatological analysis. This paper presents a comparative study of various DCNNs for the categorization of skin lesions. The proposed method involves fine-tuning the popular architectures such as the VGG16, Inception V3, Inception ResNet V2, and DenseNet 201 trained using the HAM10000 dataset. The paper investigates fine-tuning just the top layers and all the layers of the models, aiming to identify the most effective approach. According to the work's experimental findings, fine-tuning the complete trained model performs significantly better. Moreover, the study finds that fewer epochs and less computational time are required for fine-tuning the entire model while achieving higher 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

Hate Speech Detection in Roman Urdu using Machine Learning Techniques 5

Hate Speech Detection in Roman Urdu using Machine Learning T...

引用

5th International Conference on Advancements in Computational Sciences, ICACS 2024

作者： Nasir, Sarah Seerat, Ayesha Wasim, Muhammad University of Management and Technology Dept. of Computer Science Sialkot Campus Lahore Pakistan

ISBN: (纸本)9798350394764

In recent years, the spread of hate speech on social media has been a major source of discomfort. Hate speech may be extremely harmful, resulting in violence, discrimination, and even genocide. The problem is particularly acute in the case of the Roman Urdu language, where the use of hate speech is widespread. To address this issue, there's a growing demand for effective methods to identify hate speech on social media. While many researchers have focused on European languages, few have worked on South Asian languages, such as Roman Urdu, which are widely used in the subcontinent. In this study, we contribute by developing a methodology to detect hate speech in Roman Urdu at two levels. First, we classify the social media content into neutral and hostile categories. Secondly, we classify the hostile content as offensive and hate speech. We use a benchmark corpus (HS-RU-20) to evaluate the proposed methodology and the two-level classification. Furthermore, we analyze the word and character level features along with six supervised learning models (logistic regression, multinomial bias, KNN, random forest, SVM, and convolutional neural network (CNN)). The results show that logistic regression performed better in terms of accuracy, at 81% on neutral-hostile, and outperformed offensive-hate speech classification with an accuracy of 87%. © 2024 IEEE.

关键词： Logistic regression

来源：评论

学校读者我要写书评

暂无评论

LiCT-Net: Lightweight Convolutional Transformer Network for Multiclass Breast Cancer Classification

LiCT-Net: Lightweight Convolutional Transformer Network for ...

引用

2024 IEEE Region 10 Conference, TENCON 2024

作者： Babita Nayak, Deepak Ranjan Malaviya National Institute of Technology Dept. of Computer Science and Engineering Jaipur India

ISBN: (纸本)9798350350821

Classification of multiclass breast cancer through histopathological images is indispensable and poses daunting challenges due to color inconsistencies, high appearance variations, and large inter-class similarities. Regardless of the success of traditional convolutional neural networks (CNNs) and vision transformers (ViTs), they often fail to capture intricate patterns and local contextual information, respectively, while demanding high computational resources and data requirements. To mitigate these issues, this paper proposes a lightweight convo-lutional transformer network named LiCT-Net for multiclass breast cancer classification. The LiCT-Net introduces a local-global spatially-aware transformer layer and integrates it with a pre-trained FastViT model to effectively capture global and local contextual features, thereby facilitating learning fine-grained and intricate lesion patterns from histopathological images. The LiCT-Net is validated on a benchmark dataset and the experimental results and comparative analysis demonstrate its effectiveness. In specific, it achieves a higher accuracy of 96.16 %, 95.62 %, 95.25 %, and 94.21 % on 40×, 100×, 200×, and 400× magniflcations respectively, © 2024 IEEE.

关键词： Convolution

来源：评论

学校读者我要写书评

暂无评论

Enhancing Traffic Control Strategies through Dynamic Simulation and Reinforcement Learning 3

Enhancing Traffic Control Strategies through Dynamic Simulat...

引用

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

作者： Sebastian, Alona Mary Athulram, K.R. Michael, Colin Sunil, Diya Anna Preetha, K.G. Rajagiri School of Engineering and Technology Dept. of Computer Science and Engineering Ernakulam India

ISBN: (纸本)9798350375190

In urban areas, traffic congestion is a major problem causing increased travel times, higher consumption of fuel, and environmental pollution. The traditional traffic control systems cannot adapt to dynamic traffic conditions, causing inefficient traffic flow and inefficient use of road infrastructure. In this paper, we propose a novel method to enhance traffic management strategies through dynamic simulation and reinforcement learning (RL). A simulation framework is presented that models the complex interactions among vehicles, traffic signals, and infrastructure in a realistic urban environment. Within this framework, RL agents are deployed to learn adaptive traffic control policies that minimize congestion and optimize traffic flow. This approach uses the ability of RL to continuously learn and adjust to shifting traffic circumstances, which results in improved efficiency and responsiveness compared to static or rule-based control systems. Finally, evaluate the effectiveness of the approach through extensive simulations and demonstrate its capability to significantly reduce congestion, decrease travel times, decrease average waiting time and enhance overall traffic management. By integrating dynamic simulation and RL-based control strategies, the proposed approach offers a guaranteed solution for addressing the challenges of urban traffic congestion and advancing the field of intelligent transportation systems. © 2024 IEEE.

关键词： Reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

A Study on Apriori based Movie Recommendation 2

A Study on Apriori based Movie Recommendation

引用

2nd International Conference on Advancements in Smart, Secure and Intelligent Computing, ASSIC 2024

作者： Behera, Tapas Mahapatra, Sarita Mohanty, Kritik Ranjan Farhan, Mohammad Tripathy, Sachidananda Priyadarshini, Sushree Bibhuprada B. Siksha 'o' Anusandhan Dept. of Computer Science & Information Technology Bhubaneswar India

ISBN: (纸本)9798350370188

With so many movies available nowadays, it might be challenging for people to choose one that suit their preferences and tastes. We have created a system for suggesting movies to users based on their viewing interests and history. A dataset of user movie viewing history and preferences is first gathered and preprocessed by the movie recommendation system followed by employing an Apriori technique to find the common item sets from frequently watched movies. The recommendations are created using these item sets as a foundation. A real-world movie dataset is applied in extended trials for movie recommendation system while considering evaluation metrics like recall, precision, and accuracy. The experimental findings show that the suggested approach is capable of giving users precise and individualized movie suggestions by utilizing the Apriori algorithm. © 2024 IEEE.

关键词： Recommender systems

来源：评论

学校读者我要写书评

暂无评论

Hybrid Music Recommendation System combining Neo4j GraphDB based and ML-based Approach 4

Hybrid Music Recommendation System combining Neo4j GraphDB b...

引用

4th International Conference on Emerging Systems and Intelligent Computing, ESIC 2024

作者： Sathyajit, Prithviraj Thakur, Pallavi Sardar Patel Institute of Technology Dept. of Master of Computer Applications Mumbai India

ISBN: (纸本)9798350349856

Due to the significant expansion of the internet, particularly the World Wide Web, there is now an extensive collection of music accessible online. Recognizing the vastness of this musical landscape, it has become imperative to go beyond traditional search functionalities and introduce a service that not only facilitates user searches but also provides tailored music recommendations. This research paper presents an innovative approach to music recommendation by combining machine learning (ML) techniques with graph database technology. The proposed system utilizes ML to generate recommendations based on audio features extracted from a vast music dataset. The recommendation engine employs a clustering pipeline and cosine distance metrics to identify songs with similar characteristics. Additionally, the system leverages the capabilities of Neo4j, a graph database, to store and query relationships between songs deemed similar by their audio features. The integration of Neo4j enhances the recommendation process by allowing the system to consider not only audio feature similarities but also graph-based relationships. This hybrid approach aims to provide users with more diverse and contextually relevant music recommendations. The paper outlines the architecture of the system, including data preprocessing, ML model training, and the incorporation of Neo4j for storing and querying music relationships. Evaluation results demonstrate the effectiveness of the combined ML and graph-based recommendation system, offering a promising direction for advancing personalized music recommendation systems. This research contributes to the intersection of ML and graph databases in the field of music recommendation, offering a novel perspective on enhancing recommendation quality through diverse data representations. © 2024 IEEE.

关键词： Music

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 << < 17 18 19 20 21 22 23 24 25 26 > >>

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：