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

30,898 篇 会议
4,719 篇 期刊文献
247 册 图书

馆藏范围

35,864 篇 电子文献
0 种 纸本馆藏

日期分布

学科分类号

22,226 篇 工学
- 16,162 篇 计算机科学与技术...
- 13,579 篇 软件工程
- 5,873 篇 信息与通信工程
- 3,524 篇 控制科学与工程
- 2,708 篇 电子科学与技术（可...
- 2,658 篇 电气工程
- 2,356 篇 生物工程
- 1,889 篇 生物医学工程（可授...
- 1,536 篇 光学工程
- 1,371 篇 机械工程
- 1,229 篇 动力工程及工程热...
- 1,205 篇 仪器科学与技术
- 1,024 篇 化学工程与技术
- 866 篇 安全科学与工程
- 727 篇 交通运输工程
11,359 篇 理学
- 6,206 篇 数学
- 3,065 篇 物理学
- 2,581 篇 生物学
- 2,049 篇 统计学（可授理学、...
- 1,357 篇 系统科学
- 1,092 篇 化学
5,788 篇 管理学
- 3,371 篇 管理科学与工程(可...
- 2,701 篇 图书情报与档案管...
- 1,876 篇 工商管理
1,595 篇 医学
- 1,387 篇 临床医学
- 1,293 篇 基础医学(可授医学...
- 850 篇 药学(可授医学、理...
- 670 篇 公共卫生与预防医...
1,064 篇 法学
- 858 篇 社会学
671 篇 经济学
- 671 篇 应用经济学
488 篇 农学
443 篇 教育学
160 篇 文学
77 篇 军事学
40 篇 艺术学
1 篇 哲学

主题

1,135 篇 accuracy
870 篇 computational mo...
854 篇 feature extracti...
738 篇 deep learning
717 篇 training
687 篇 computer science
555 篇 real-time system...
542 篇 machine learning
521 篇 support vector m...
469 篇 predictive model...
424 篇 internet of thin...
367 篇 data models
358 篇 convolutional ne...
345 篇 computer archite...
339 篇 reliability
322 篇 optimization
302 篇 data mining
278 篇 routing
260 篇 artificial intel...
253 篇 conferences

机构

83 篇 institut univers...
82 篇 north-west unive...
80 篇 national centre ...
79 篇 infn sezione di ...
77 篇 tno technical sc...
76 篇 infn sezione di ...
76 篇 institute of inf...
67 篇 université de st...
66 篇 università di ca...
64 篇 dept. of informa...
60 篇 dept. of informa...
57 篇 nikhef national ...
56 篇 dept. of compute...
54 篇 dept. of compute...
53 篇 dept. of compute...
52 篇 school of automa...
50 篇 leiden universit...
48 篇 dept. of compute...
44 篇 dept. of compute...
44 篇 dept. of electri...

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.
80 篇 kalekin o.
79 篇 díaz a.f.
76 篇 boumaaza j.
74 篇 coleiro a.
74 篇 gozzini s.r.
71 篇 huang f.
68 篇 dallier r.
61 篇 anguita m.
54 篇 kulikovskiy v.
42 篇 benoit d.m.
42 篇 eddymaoui a.
42 篇 labalme m.
41 篇 gagliardini s.
41 篇 del burgo r.

语言

32,095 篇 英文
3,365 篇 其他
300 篇 中文
57 篇 日文
51 篇 朝鲜文
2 篇 德文
2 篇 斯洛文尼亚文
1 篇 法文
1 篇 葡萄牙文

检索条件"机构=dept. Computer Science and Software Engineering"

共 35864 条记录，以下是401-410 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：

A Comprehensive Review of Media Forensics and Deepfake Detection Technique 10

A Comprehensive Review of Media Forensics and Deepfake Detec...

引用

17th INDIACom;2023 10th International Conference on Computing for Sustainable Global Development, INDIACom 2023

作者： Kandari, Megha Tripathi, Vikas Pant, Bhaskar Dept. of Computer Science and Engineering Dehradun India

ISBN: (纸本)9789380544472

In recent years, as the use of the internet and social media has advanced, so the number of fake media content also grows rapidly. Media forensic techniques are becoming essential to analyze and extract information from various types of media, such as images, videos, and audio recordings, to be used as evidence in legal proceedings. As of recent trends, social media is being flooded with sophisticated deepfakes. So evolving deepfake detection technique is required to curb the flow of misinformation via deepfake videos. This paper intends to present a review of evolving media forensics and deepfake detection techniques. © 2023 Bharati Vidyapeeth, New Delhi.

关键词： Social networking (online)

来源：评论

学校读者我要写书评

暂无评论

A CNN Based Ensemble Deep Learning Approach for Melanoma Detection

A CNN Based Ensemble Deep Learning Approach for Melanoma Det...

引用

2024 IEEE Region 10 Symposium, TENSYMP 2024

作者： Mullick, Mohammad Abu Obaida Khan, Nafi Sadman Fahid, Ahnaf Tahmid Mahmud, Mahin Rahman, Raiyan United International University Dept. of Computer Science & Engineering Dhaka Bangladesh

ISBN: (纸本)9798350364866

Melanoma, the most aggressive form of skin cancer, necessitates early detection for successful treatment. This paper proposes an ensemble Convolutional Neural Networks (CNNs) approach to classify dermoscopic images of Melanoma (MEL) and Melanocytic Nevi (NV), by systematically selecting and comparing various pre-trained models with different optimizers and preprocessors through trial and error, as well as optimizing loss functions. The ensemble method takes predictions from multiple pre-trained models and selects the most reliable outcome using a custom metric. The result presents an optimal CNN ensemble model built of DenseNet121 and VGG16 with cropping and scaling, contrast enhancing, and exposure adjusting as image preprocessors that achieved a notable accuracy of 97.5% on a customized and balanced version of the Kaggle HAM10000 dataset. This approach aims to improve patient outcomes by providing a valuable tool for early melanoma detection. © 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

Enhancing Supply Chain Efficiency through IoT Integration: A Detailed Examination of the Chances and Difficulties 2

Enhancing Supply Chain Efficiency through IoT Integration: A...

引用

2nd International Conference on Advances in Computation, Communication and Information Technology, ICAICCIT 2024

作者： Mehra, Chaitanya Sharma, Shaifali Arora, Jayant Sharma, Aakanksha Mahajan, Pranaya Manhotra, Aryan Dept. of Computer Science Engineering Chandigarh University Punjab Mohali India

ISBN: (纸本)9798331541217

The adoption of Internet of Things (IoT) technology in supply chain management has brought about noteworthy transformations, boosting productivity, visibility, and evidence- based decision-making. This research investigates the primary reasons for implementing IoT in contemporary supply chains, tackling issues such as limited real-time monitoring, suboptimal inventory control, and the necessity for preemptive risk manage- ment. The investigation delves into the capabilities of IoT-driven solutions, including sensor technology, RFID systems, and data analysis tools, to confront these obstacles by enabling constant surveillance and anticipatory maintenance, taking into account the impact of innovative technologies such as blockchain and artificial intelligence. The results underscore the considerable effect of IoT in establishing robust, flexible, and eco-friendly supply chains, providing valuable insights for businesses aiming to improve their operational effectiveness in an increasingly digital landscape. © 2024 IEEE.

关键词： Inventory control

来源：评论

学校读者我要写书评

暂无评论

A Random Forest Framework for Predicting Cardiovascular Disease in Diverse Populations' 2

A Random Forest Framework for Predicting Cardiovascular Dise...

引用

2nd International Conference on Advanced Computing and Communication Technologies, ICACCTech 2024

作者： Rahi, Parvez Kang, Sandeep Singh Singh, Ajay Pal Singh, Inderjeet Chandigarh University Dept. of Computer Science & Engineering Punjab Mohali India

ISBN: (纸本)9798331519056

According to the latest information from WHO, the World Health Organization, heart disease remains a major global health challenge, resulting in millions of deaths each year. Heart disease presents in various forms, including Hypertensive Heart Disease, Congestive Heart Failure (CHF), Coronary Artery Disease, Cardiomyopathy, and Arrhythmia. Accurate classification of these conditions is crucial for reducing mortality rates and improving patient outcomes. This study utilizes an enhanced Random Forest classifier to improve the accuracy of heart disease classification. The Synthetic Minority Oversampling Technique (SMOTE) was utilized to rectify the disparities in class. and Polynomial Feature engineering was employed to capture complex interactions within the data. The dataset underwent comprehensive preprocessing, including feature normalization and label encoding, followed by extensive hyperparameter tuning using GridSearchCV. The optimized model achieved a high accuracy of 92% and a Mean Squared Error (MSE) of 0.05. Key performance indicators, including an F1 score of 0.87, recall of 0.88, and accuracy of 0.92, highlight the model's efficacy in differentiating between various forms of heart disease. Future research could explore incorporating additional clinical data to further enhance the model's accuracy and applicability across diverse patient populations. © 2024 IEEE.

关键词： Clinical research

来源：评论

学校读者我要写书评

暂无评论

Multi-Objective Task Scheduling in Cloud Environments using Dynamic Velocity-Adaptive Particle Swarm Optimization

Multi-Objective Task Scheduling in Cloud Environments using ...

引用

2024 OPJU International Technology Conference on Smart Computing for Innovation and Advancement in Industry 4.0, OTCON 2024

作者： Kumar, Ravi Vardhan, Manu Natinal Institute of Technology Dept. of Computer Science and Engineering Raipur India

ISBN: (纸本)9798350373783

In the realm of cloud computing, tackling the multi-objective task scheduling problem means finding the best way to assign tasks to virtual machines, taking into account conflicting goals like minimizing execution time, load balance and cost. This intricate task demands smart algorithms to strike a balance between these competing objectives, ensuring the most efficient use of resources and meeting user expectations in the cloud. Different optimization techniques, such as Particle Swarm Optimization (PSO) and Ant Colony Optimization (ACO), have been explored to handle this challenge and optimize task scheduling in the cloud environment. In classical PSO, particles can move at varying speeds in each iteration. In this study, we apply Velocity Stagnation Particle Swarm Optimization (VSPSO) variants where velocity stagnation applied during particles movement. This approach provides particles with a third movement option, enabling them to maintain the same velocity as in the previous iteration. VSPSO has a greater capacity to balance the exploration and exploitation. VSPSO adjusts the initial term of the PSO velocity equation to prevent premature convergence. Furthermore, the population of VSPSO is split into two swarms to ensure *** the inherent capabilities of PSO, VSPSO algorithm dynamically updates particle velocities to attain 5-6% total execution time 6-10% reduced cost and optimal balance load. Through meticulous comparisons with other algorithms, including Genetic Algorithm and Ant Colony Optimization, this study scrutinizes the effectiveness of our enhanced PSO approach. The overarching goal is to push the boundaries of multi-objective task scheduling in cloud computing by attaining minimal execution time, reduce cost and optimal balance load on each virtual machines. © 2024 IEEE.

关键词： Particle swarm optimization (PSO)

来源：评论

学校读者我要写书评

暂无评论

Biomimetic and Biological Sensing Technologies for the Assessment of Water Contaminants 1

Biomimetic and Biological Sensing Technologies for the Asses...

引用

1st International Conference on Advanced Computing and Emerging Technologies, ACET 2024

作者： Thaluka, Mohan Raj Maheswari, K. Nuthanakanti, Bhaskar Srujan Raju, K. Jonnadula, Narasimharao Okali, Rakshita Dept. Computer science and engineering CMR Technical Campus Hyderabad India

ISBN: (纸本)9798350367720

Biological sensors, including biosensors and biomimetic sensors, have gained significant attention in recent years due to their exceptional capabilities in detecting and monitoring pollutants in water environments. These sensors employ biological components such as bacteria, Fungi, enzymes, antibodies, microbial cells, or biomimetic materials to recognize and quantify specific contaminants to pathogens, with high sensitivity and selectivity. This review provides an in-dept. analysis of the current state-of-the-art in biological sensor technology for water quality assessment. It discusses the underlying principles of biological sensing mechanisms and explores recent advances in sensor fabrication, including materials, immobilization techniques, and signal transduction methods. Moreover, the review examines the diverse applications of biological sensors in water monitoring, ranging from detecting chemical pollutants to assessing microbial contamination. Additionally, challenges such as stability, reproducibility, and field deployment are addressed, along with future directions for research and development to further enhance the performance and applicability of biological sensors in safeguarding water resources and public health. Here, we employed three models - SVM, logistic regression (LR), and random forest (RF) - to determine the biological and chemical components of water, such as bacteria, fungi, enzymes, antibodies, microbial cells, or biomimetic materials, in order to determine whether it is being utilized for drinking water. Because there are fewer datasets available for biological and chemical components, the dataset was created using machine learning (ML) models. Three machine learning models were used to calculate water pollutants percentages, with SVM proving most effective for irrigation and domestic water, and LR for drinking water, resulting in accurate water supply. © 2024 IEEE.

关键词： Antibodies

来源：评论

学校读者我要写书评

暂无评论

Leukaemia: A Comparative Analysis of Deep Learning Models Using ALL Dataset 6

Leukaemia: A Comparative Analysis of Deep Learning Models Us...

引用

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

作者： Sudheer, Rhea Vivek, Rapaka Ramesh, Richa Sarvade, Apoorva Kakarla, Sada Preethi, P. Pes University Dept. of Computer Science and Engineering Karnataka Bangalore India

ISBN: (纸本)9798350381689

White blood cells, also known as leukocytes, or WBCs, spread abnormally in the bone marrow and blood, resulting in leukaemia (blood cancer). Leukaemia can be identified by pathologists by examining a patient's blood sample under a microscope. By counting different blood cells and physical characteristics, they can identify and classify leukaemia. This method takes a lot of time to forecast leukaemia. The pathologist's professional qualifications and experiences may also have an impact on this process. Traditional machine learning and deep learning techniques in computer vision are useful road maps that improve the precision and speed of identifying and categorizing medical images, such as minuscule blood cells. This paper offers a thorough analysis of the different Deep CNN models for identification and classification of WBCs and acute leukaemia in microscopic blood cells. © 2024 IEEE.

关键词： Contrastive Learning

来源：评论

学校读者我要写书评

暂无评论

Automated Explanation Quality Assessment based on Similarity Calculations of Representative Explanations of Different Qualities 7

Automated Explanation Quality Assessment based on Similarity...

引用

7th IEEE Eurasian Conference on Educational Innovation, ECEI 2024

作者： Chou, Chih-Yueh Chou, Yu-Ting Huang, Yu-Cheng Yuan Ze University Dept. of Computer Science & Engineering Taoyuan Taiwan

ISBN: (纸本)9798350307207

Peer instruction is instructional in guiding students to learn by answering questions, and explaining and discussing their answers with peers. Researchers recommended asking students to write down their answers and explanations before discussion to prevent social loafing. In addition, text-based explanations can be recorded and analyzed. The quality of students' explanations varies, ranging from superficial and low-quality to detailed and in-dept. high-quality explanations. In tradition, the qualities of students' explanations were assessed by experts. Recently, machine learning classification models have been developed and applied to classify texts. However, the level of explanations of questions are question-dependent. Thus, each question needs its classification model. Therefore, a feature transformation was applied in this study so that the explanations of different questions could be combined and applied to train the same classification model. An automated explanation quality assessment mechanism was developed based on the similarity of representative explanations of different qualities. Students' text-based explanations were collected and assessed by experts into four levels, ranging from 0 (worst) to 3 (best). The four-level classifications were merged into binary classifications of low (0 and 1) and high (2 and 3). Different classification models, including Support Vector Machine (SVM), Naive Bayes (NB), K Nearest Neighbor (KNN), Logistic Regression (LR), Random Forest (RF), and Bidirectional Encoder Representations from Transformers (BERT) were applied to train models and evaluate the accuracy of the models. In addition, three ensemble learning algorithms, including voting, stacking, and boosting, were applied to combine models chosen from SVM, NB, KNN, LR, and RF. The results showed that RF and RF+KNN+NB with stacking model showed the best accuracy (75.3%) among all four-level classification models whereas RF with boosting model showed the best accuracy (9

关键词： Students

来源：评论

学校读者我要写书评

暂无评论

Prosecutorial Outcome Predication with LoRA and QLoRA 37

Prosecutorial Outcome Predication with LoRA and QLoRA

引用

37th Annual Conference on Legal Knowledge and Information Systems, JURIX 2024

作者： Chien, Kuo-Chun Chang, Chia-Hui Huang, Huai-Hsuan Kung, Jo-Chi Dept. of Computer Science & Information Engineering National Central University Taiwan

ISBN: (纸本)9781643685625

Our study on Legal Judgment Prediction (LJP) focuses on indictments, designing innovative tasks for prosecutors to predict reasons, imprisonment, fines, and penalty types. We investigated multi-task learning (MTL), Low-Rank Adaptation (LoRA), and its quantized version (QLoRA). Results show that the MTL framework, combined with LoRA and QLoRA, excels in prediction while optimizing resource use. Error analysis in the Reason field of TWPJD dataset was conducted to guide future predictions. Future work will focus on balancing sub-task performance and collecting more investigative data to enhance legal AI applications. © 2024 The Authors.

关键词： Multi-task learning

来源：评论

学校读者我要写书评

暂无评论

A Bengali Physics Chatbot Utilizing Sequence-to-Sequence Model with Beam Search

A Bengali Physics Chatbot Utilizing Sequence-to-Sequence Mod...

引用

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

作者： Hossain, Javed City University Dept. of Computer Science and Engineering Dhaka1216 Bangladesh

ISBN: (纸本)9798331529765

Chatbots, also known as talkbots or interactive agents, are software applications designed to facilitate communication between humans and machines. While most students in Bangladesh currently waste their valuable time engaging in casual conversations with each other, using a Bengali educational chatbot for such interactions would provide them with a more beneficial use of their time by providing hand note-wise answers for physics. The challenge faced by a Bengali chatbot lies in the necessity of creating a dataset in Bengali, given the scarcity of available Bengali datasets online. We have developed a physics-focused educational chatbot, akin to personalized hand notes, offering comprehensive answers to aid students in learning and revising complex physics concepts. The development of chatbots involves diverse techniques, including rule-based systems, machine learning-based approaches, and generative models. Our proposed system implements the seq2seq model with a beam search decoding algorithm, featuring BiLSTM layers for enhanced context understanding and efficient exploration of potential output sequences. This approach outperforms traditional seq2seq models, ensuring higher accuracy and delivering high-quality responses. Finally, we obtained the highest BLEU1, BLEU2, BLEU3, and BLEU4 scores, respectively, of 0.52, 0.41, 0.29, and 0.23. © 2024 IEEE.

关键词： Chatbots

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 << < 37 38 39 40 41 42 43 44 45 46 > >>

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：