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

88,742 篇 会议
38,498 篇 期刊文献
1,188 册 图书

馆藏范围

128,428 篇 电子文献
1 种 纸本馆藏

日期分布

学科分类号

74,016 篇 工学
- 49,295 篇 计算机科学与技术...
- 40,101 篇 软件工程
- 18,838 篇 信息与通信工程
- 12,261 篇 控制科学与工程
- 10,816 篇 电气工程
- 10,160 篇 电子科学与技术（可...
- 9,167 篇 生物工程
- 7,272 篇 生物医学工程（可授...
- 6,820 篇 光学工程
- 5,198 篇 机械工程
- 4,696 篇 化学工程与技术
- 4,313 篇 仪器科学与技术
- 4,286 篇 动力工程及工程热...
- 4,078 篇 材料科学与工程（可...
- 3,674 篇 网络空间安全
- 3,205 篇 安全科学与工程
43,477 篇 理学
- 19,926 篇 数学
- 15,650 篇 物理学
- 10,405 篇 生物学
- 6,685 篇 统计学（可授理学、...
- 5,262 篇 化学
- 4,515 篇 系统科学
19,248 篇 管理学
- 12,058 篇 管理科学与工程(可...
- 8,116 篇 图书情报与档案管...
- 5,597 篇 工商管理
7,252 篇 医学
- 6,003 篇 临床医学
- 5,513 篇 基础医学(可授医学...
- 3,431 篇 药学(可授医学、理...
- 3,218 篇 公共卫生与预防医...
3,661 篇 法学
- 2,984 篇 社会学
2,279 篇 经济学
2,155 篇 农学
1,114 篇 教育学
554 篇 文学
294 篇 军事学
137 篇 艺术学
11 篇 哲学
9 篇 历史学

主题

4,777 篇 accuracy
3,887 篇 deep learning
3,465 篇 feature extracti...
3,358 篇 computer science
3,065 篇 computational mo...
3,023 篇 machine learning
2,876 篇 training
2,500 篇 convolutional ne...
2,290 篇 real-time system...
2,142 篇 predictive model...
2,132 篇 support vector m...
1,977 篇 internet of thin...
1,650 篇 artificial intel...
1,594 篇 data models
1,593 篇 optimization
1,460 篇 neural networks
1,404 篇 security
1,246 篇 data mining
1,188 篇 wireless sensor ...
1,136 篇 computer archite...

机构

2,180 篇 chitkara univers...
1,089 篇 cavendish labora...
1,023 篇 department of ph...
967 篇 physikalisches i...
959 篇 oliver lodge lab...
936 篇 university of ch...
603 篇 infn laboratori ...
600 篇 infn sezione di ...
575 篇 infn sezione di ...
559 篇 fakultät physik ...
554 篇 infn sezione di ...
544 篇 school of physic...
538 篇 horia hulubei na...
524 篇 school of physic...
524 篇 department of ph...
523 篇 school of comput...
513 篇 imperial college...
511 篇 h.h. wills physi...
497 篇 stfc rutherford ...
495 篇 nikhef national ...

作者

261 篇 barter w.
254 篇 a. gomes
244 篇 c. alexa
240 篇 j. m. izen
235 篇 blake t.
234 篇 c. amelung
234 篇 j. wang
233 篇 s. chen
232 篇 g. bella
232 篇 j. strandberg
232 篇 d. calvet
229 篇 beiter a.
226 篇 bellee v.
223 篇 amato s.
222 篇 betancourt c.
221 篇 boettcher t.
220 篇 borsato m.
219 篇 bowcock t.j.v.
218 篇 brundu d.
215 篇 g. spigo

语言

109,113 篇 英文
17,901 篇 其他
1,535 篇 中文
142 篇 日文
21 篇 德文
21 篇 法文
16 篇 斯洛文尼亚文
15 篇 朝鲜文
4 篇 阿拉伯文
3 篇 荷兰文
2 篇 波兰文
2 篇 俄文
1 篇 意大利文
1 篇 葡萄牙文

检索条件"机构=Computer Science and Engineering Gandhi Institute of Engineering and Technology"

共 128428 条记录，以下是4751-4760 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：

Classification of Mental Workload Using 1D-CNN with Transfer Learning 1

Classification of Mental Workload Using 1D-CNN with Transfer...

引用

1st International Conference on Pioneering Developments in computer science and Digital Technologies, IC2SDT 2024

作者： Chaturvedi, Sushil Ahirwal, Mitul Kumar Maulana Azad National Institute of Technology Dept. of Computer Science and Engineering Bhopal India

ISBN: (纸本)9798350365016

Mental workload (MWL) can be explained as the ratio of a participant's mental effort to their brain capability when performing activities. A significant challenge in the field of MWL classification for brain-computer interfaces (BCIs) based on electroencephalograms (EEGs) is the variability among individuals. It commonly takes unnecessary time to retrain the classification model from starting for a new subject. To address the individual variations among different subjects, a one-dimensional convolutional neural network along with transfer learning (1D CNN-TL) is proposed in this work. The end-to-end 1D-CNN learns the common features of EEG signals and, to tackle the problem of difference in EEG for individuals, a transfer learning technique is used that does fine-tuning on fully connected (FC) layers for a new participant having less training data. The average test accuracy (mean±stdv) of 65.18± 8.37 is achieved over the Cross-session mental workload dataset. The suggested method can achieve satisfying results for new unknown data with less time and fewer training 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

A CNN Transit Model for Object Detection using YOLOv5 2

A CNN Transit Model for Object Detection using YOLOv5

引用

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

作者： Natarajan, Yuvaraj Afra, J. Buvani Sankari, V. Gayathri, V. Malingan, Navaneeth KPR Institute of Engineering and Technology Department of Computer Science Engineering Coimbatore India Nunnari Labs Private Limited Coimbatore India

ISBN: (纸本)9798350327533

The rapid urbanization and burgeoning populations in cities worldwide have led to an increased demand for efficient and sustainable urban transit systems. In India, the pace of growth in the two-wheeler fleet is 30 times greater than the rate of growth in the population. The chance of mortality is 3.5 times higher for riders who don't wear helmets than for those who do. In view of this, developed an AI-based model for object detection to guarantee public safety and enable real-time monitoring of traffic law violations. The system uses a camera to capture images of bikes carrying three or more people who are not wearing helmets as well as to recognize the license plates of bikes. A CNN Transit model for traffic networks have been proposed. The model utilizes the Yolov5 backbone layer, which is fine-tuned by increasing hyperparameters. This results in the accuracy of 86 % and a significant reduction in training time, which enhances the model's performance. By addition of PANet and FPN to the Yolov5 Neck layer has improved the detection of far and tiny objects in traffic and roadways. This study emphasizes the potential of AI-ML technology to address urban transportation difficulties and foster a culture of safety by detecting objects. © 2024 IEEE.

关键词： Convolutional Neural Network (CNN) Transit Feature Pyramid Network (FPN) Object Detection Path Aggregation Network (PANet) Traffic law Violations Yolo v5

来源：评论

学校读者我要写书评

暂无评论

Remote Sensing Object Detection Based on Improved Detection Transformer 3

Remote Sensing Object Detection Based on Improved Detection ...

引用

3rd International Conference on Cloud Computing, Big Data Application and Software engineering, CBASE 2024

作者： Hu, Yuanzhong Hu, Po Wang, Haihui Wang, Yuzhuo School of Computer Science and Engineering School of Artificial Intelligence Wuhan Institute of Technology Wuhan China

ISBN: (纸本)9798331506582

Nowadays, the accuracy of remote sensing image target recognition has greatly improved. It enables humans to efficiently monitor crop growth, track climate changes and natural disasters, and even provide critical strategic intelligence for national defense. However, due to the challenges posed by the large number of objects and the immense size of remote sensing images, there is still considerable room for improvement in recognition accuracy and efficiency. Detection Transformer (DETR) framework utilizes the Transformer architecture, change the object detection task to a set prediction problem, thus simplifying the traditional post-processing workflow. Through its attention mechanisms, DETR effectively captures object features in intricate scenes by modeling global contextual information. Nonetheless, there is still potential for improvement in extracting fine-grained details. In this study, three modifications are proposed to the DETR framework to boost remote sensing object detection accuracy. First, a multi-scale feature extraction approach is employed to capture deeper and more detailed image features. Second, a bidirectional learning path is introduced to enhance the contextual relationships between image features. Experimental results demonstrate that our proposed method has achieved strong competitiveness compared to other approaches © 2024 IEEE.

关键词： Optical remote sensing

来源：评论

学校读者我要写书评

暂无评论

Improving Train Safety: computer Vision-Based Error Detection for Precise Upkeep

Improving Train Safety: Computer Vision-Based Error Detectio...

引用

2024 International Conference on Advances in Modern Age Technologies for Health and engineering science, AMATHE 2024

作者： Devi, Pothreddypally Jhansi Reddy, Parava Sathvika Dharani, Mandala Mandapati, Rahul Reddy, Pasunuri Soumith B V Raju Institute Of Technology Computer Science And Engineering Medak Telangana Narsapur India

ISBN: (纸本)9798350371567

Accidents on railroad tracks continue even with human inspections, which are often inaccurate and can lead to serious incidents. While artificial intelligence has found use in the railway sector, computer vision-based defect diagnosis has received less academic attention. In India and across the world, train travel is the most popular form of transportation because to its reasonable prices and comfortable accommodations for travelers. India possesses one of the largest rail networks globally, and it bears primary responsibility for maintaining these lines in excellent condition. One aspect of the maintenance job includes locating different types of track problems and putting corrective procedures in place for those that are found. This study uses novel data-driven approaches to identify railway track issues utilizing three object recognition models (Yolo series, RCNN, OpenCV, etc.). By detecting fractures, misalignment, loose fasteners, deterioration, and other issues, this model helps reduce incidents involving railway tracks. © 2024 IEEE.

关键词： computer vision

来源：评论

学校读者我要写书评

暂无评论

Hierarchical Approach for Multi-Class Models

Hierarchical Approach for Multi-Class Models

引用

2024 International Conference on Integrated Circuits, Communication, and Computing Systems, ICIC3S 2024

作者： Sanwal, Gaurav Sharma, Akshita Kumar, Satyam Chauhan, Shweta Sati, Dayal Chandra Chandigarh University Department of Computer Science and Engineering APEX Institute of Technology Punjab Mohali India

ISBN: (纸本)9798350364088

This research introduces a novel approach to multi-class classification, harnessing hierarchical architectures to enhance accuracy and interpretability. Specialized models are designed at each hierarchy level, capturing subcategoryspecific nuances using transfer learning. Decision paths are visualized for interpretability. Evaluations across diverse datasets highlight the superior performance of the hierarchical approach in accuracy and scalability. Cross-domain adaptability is demonstrated. This research offers a foundation for hierarchical multi-class classification, revolutionizing complex categorization tasks, and contributing to classification methodology advancements. © 2024 IEEE.

关键词： Learning systems

来源：评论

学校读者我要写书评

暂无评论

Evolution of Financial Question Answering Themes, Challenges, and Advances 6th

Evolution of Financial Question Answering Themes, Challenges...

引用

6th International Conference on Recent Innovations in Computing, ICRIC 2023

作者： Saini, Khyati Singh, Pardeep Department of Computer Science and Engineering National Institute of Technology Himachal Pradesh Hamirpur177005 India

ISBN: (纸本)9789819734412

Financial Question Answering (QA) has emerged as a critical area of research, aiming to develop intelligent systems capable of interpreting and answering complex queries within financial reports. This survey paper delves into the diverse landscape of Financial Question Answering (QA) research, grouping influential papers into thematic clusters to uncover varied perspectives and challenges within this evolving field through an in-depth analysis of the influential papers published over the decade. The survey begins by introducing the scope and significance of Financial QA, followed by a discussion on the evolution of datasets tailored for financial domain-specific QA tasks, focusing on conversational QA, numerical reasoning, and complex reasoning within financial reports. Subsequently, the survey delves into various model architectures and techniques employed in Financial QA. The exploration encompasses pivotal themes such as numerical reasoning and tabular data handling, conversational QA in finance, model architectures for financial QA, knowledge-infused QA, and datasets creation and introduction. These themes elucidate the challenges and possibilities inherent in Financial QA, emphasizing issues like numerical reasoning complexity, contextual understanding, hybrid data challenges, coreference, performance gaps, data limitations, and optimal context size. This survey offers a holistic view of the advancements, challenges, and future directions in Financial QA, fostering further innovation in this evolving field. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2024.

关键词： Question answering

来源：评论

学校读者我要写书评

暂无评论

Multi-Trajectory Drone Surveillance: Amplifying Monitoring Capabilities in Disaster Management

Multi-Trajectory Drone Surveillance: Amplifying Monitoring C...

引用

2024 IEEE International Students' Conference on Electrical, Electronics and computer science, SCEECS 2024

作者： Mourya, Gojja Sree Jami, Abhinav Ajith, Abhinav Seikh, Ayan Habib Kumar, J. Sathish Motilal Nehru National Institute of Technology Dept. of Computer Science and Engineering Allahabad India

ISBN: (纸本)9798350348460

In the disaster-affected area, whether it's a search and rescue operation, mock drill, managing food distribution, issuing warnings or anything else, the key to successfully carrying out these activities is preparation. To ensure that plans are accurate, one needs to know what actually happened in the disaster-affected area and for this purpose thoroughly and quickly the entire area need to be studied. To address this issue, we use UAV or drone navigation autonomously in required trajectories. By using UAVs you can cover surveillance across the vast acres of land quickly and know what happened and plan rescue operations accordingly. In this paper, we presented our work on moving the drones in multiple trajectories and swarm, thus amplifying surveillance capabilities. Each trajectory is maneuvered autonomously and a corresponding trajectory-algorithm running at the back end is presented along with the simulation results. © 2024 IEEE.

关键词： Disaster management Drones Multi-Agent Systems Surveillance Swarm Trajectories Unmanned Aerial Vehicles (UAV)

来源：评论

学校读者我要写书评

暂无评论

An Epileptic Seizure Detection System based on Mediapipe and Deep Learning 2

An Epileptic Seizure Detection System based on Mediapipe and...

引用

2nd IEEE International Conference on Interdisciplinary Approaches in technology and Management for Social Innovation, IATMSI 2024

作者： Venkatesh, Abhijit Sajini, S. Srm Institute of Science and Technology Department of Computer Science and Engineering RamapuramBharati Salai Chennai600089 India

ISBN: (纸本)9798350360523

Epilepsy, a neurological disorder characterized by recurrent seizures, poses significant challenges in timely intervention and patient safety, affecting millions of individuals worldwide. Early and accurate detection of seizures is crucial for timely medical intervention and improved patient outcomes. This system holds particular significance for the elderly demographic, wherein prompt assistance is imperative to safeguard their lives. This study integrates MediaPipe Pose Detection alongside Machine Learning and Deep Learning techniques to enable the identification of individuals experiencing generalized epileptic seizures within the confines of their residences. Moreover, hyperparameter tuning has been performed on the machine learning algorithms to find optimal combination of hyperparameters for each algorithm. Experimental results show that highest average accuracy among machine learning models is achieved by SVM Classifier and Gradient Boosting algorithms at 88.08%, while Time series classification implemented using 1DCNN performs at 84.77% accuracy. It is noted that more varied data samples and standardized datasets would likely improve current results. © 2024 IEEE.

关键词： Patient treatment

来源：评论

学校读者我要写书评

暂无评论

Revolutionizing Medical Inquiry Responses Harnessing Advanced Language Models for Enhanced Precision 2

Revolutionizing Medical Inquiry Responses Harnessing Advance...

引用

2nd IEEE International Conference on Emerging Research in Computational science, ICERCS 2024

作者： Keerthana, S.M. Kirthidevi, S. Nandhana, V. St. Joseph's Institute of Technology Department of Computer Science Engineering Chennai India

ISBN: (纸本)9798331534950

In the swiftly advancing domain of healthcare informatics, the exigency for intricately sophisticated and meticulously calibrated information retrieval systems has attained a critical juncture. This paper elucidates the development of an avant-garde question-answering (QA) system, meticulously engineered to tackle the multifaceted challenges of the healthcare sector through the deployment of advanced natural language processing (NLP) methodologies. The system incorporates BioBERT a specialized refinement of the BERT architecture, extensively fine-tuned on an expansive biomedical corpus to proficiently parse, interpret, and resolve complex medical inquiries with unparalleled precision and contextual acuity. Central to its innovation is an advanced attention mechanism that dynamically prioritizes pivotal components of a query, thereby substantially augmenting its capacity to extract highly specific and contextually relevant information from a vast medical knowledge repository. This methodological advancement adeptly addresses the entrenched limitations of contemporary QA systems, which often grapple with the specificity and complexity of medical content, thereby markedly enhancing response efficacy and reliability. Positioned to revolutionize clinical decision-making, elevate patient outcomes, and expedite research endeavours, this system provides considerable utility to clinicians, patients, and researchers. The paper accentuates the transformative impact of amalgamating BioBERT with sophisticated attention mechanisms, establishing a novel benchmark in medical QA systems that is both technically robust and exquisitely attuned to the nuanced demands of the healthcare sector. © 2024 IEEE.

关键词： Natural language processing systems

来源：评论

学校读者我要写书评

暂无评论

Satellite Images Classification by Using Artificial Intelligence Techniques

Satellite Images Classification by Using Artificial Intellig...

引用

2024 International Conference on Innovations and Challenges in Emerging Technologies, ICICET 2024

作者： Jaspin, K. Yogasundar, K. Shree Vishnu, S. St. Joseph's Institute of Technology Department of Computer Science and Engineering Chennai India

ISBN: (纸本)9798350319019

Satellite imagery plays a vital role in various fields, including agriculture, urban planning, disaster management, and environmental monitoring. Efficient and accurate classification of satellite images is essential for extracting valuable information and making informed decisions. In this work, the system proposes the use of artificial intelligence techniques for satellite image classification. A comprehensive dataset of labelled satellite images is collected, representing different land cover types or objects of interest. Data augmentation technique such as image augmentation is used where geometric transformations such as rotation, scaling, and flipping are applied to increase the dataset size and improve the model's generalization ability. The primary objective of the system is to develop and implement an AI-based solution for classifying satellite images into predefined categories or classes. The system's goal is to build a reliable and effective model that can automatically categorize satellite images, helping professionals and decision-makers across a range of industries. The five categories into which the algorithm divides the satellite images are cloudy, desert, green area, shipsnet, water, and wildfire. Utilizing the Xception net, Dense net, and Manual net algorithms, the system yields accuracy values of 94.79, 87.5 and 61.46. © 2024 IEEE.

关键词： Satellite imagery

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 << < 472 473 474 475 476 477 478 479 480 481 > >>

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：