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

968 篇 会议
259 篇 期刊文献
14 册 图书

馆藏范围

1,241 篇 电子文献
0 种 纸本馆藏

日期分布

学科分类号

645 篇 工学
- 499 篇 计算机科学与技术...
- 433 篇 软件工程
- 154 篇 信息与通信工程
- 109 篇 控制科学与工程
- 101 篇 生物工程
- 87 篇 生物医学工程（可授...
- 69 篇 光学工程
- 64 篇 电气工程
- 47 篇 电子科学与技术（可...
- 42 篇 动力工程及工程热...
- 40 篇 安全科学与工程
- 39 篇 交通运输工程
- 37 篇 机械工程
- 37 篇 网络空间安全
- 36 篇 化学工程与技术
356 篇 理学
- 158 篇 数学
- 110 篇 生物学
- 87 篇 物理学
- 71 篇 统计学（可授理学、...
- 31 篇 地球物理学
- 30 篇 化学
231 篇 管理学
- 144 篇 管理科学与工程(可...
- 101 篇 图书情报与档案管...
- 93 篇 工商管理
92 篇 医学
- 72 篇 临床医学
- 68 篇 基础医学(可授医学...
- 48 篇 公共卫生与预防医...
- 40 篇 药学(可授医学、理...
41 篇 经济学
- 41 篇 应用经济学
39 篇 法学
- 34 篇 社会学
22 篇 农学
10 篇 教育学
5 篇 文学
4 篇 军事学
1 篇 哲学

主题

121 篇 accuracy
63 篇 real-time system...
58 篇 computational mo...
52 篇 deep learning
49 篇 predictive model...
47 篇 machine learning
45 篇 training
41 篇 feature extracti...
39 篇 machine learning...
38 篇 convolutional ne...
34 篇 artificial intel...
32 篇 technological in...
32 篇 data models
26 篇 analytical model...
26 篇 adaptation model...
24 篇 prediction algor...
23 篇 reliability
21 篇 optimization
20 篇 internet of thin...
20 篇 medical services

机构

37 篇 lovely professio...
17 篇 institute of aer...
17 篇 institute of aer...
15 篇 lloyd institute ...
11 篇 computer science...
10 篇 dept. of compute...
10 篇 smart data & kno...
9 篇 st. martin's eng...
8 篇 knowledge park i...
7 篇 dept. of compute...
6 篇 college of healt...
6 篇 national univers...
6 篇 kalinga universi...
6 篇 data science and...
6 篇 dept. of informa...
6 篇 dept. of knowled...
6 篇 lloyd institute ...
5 篇 university of th...
5 篇 artificial intel...
5 篇 graphic era hill...

作者

12 篇 dengel andreas
12 篇 schröder markus
12 篇 jilek christian
11 篇 ashwini kodipall...
10 篇 kodipalli ashwin...
9 篇 nasraoui olfa
8 篇 watabe hirokazu
8 篇 tsuchiya seiji
8 篇 yuyun
7 篇 yoshimura eriko
7 篇 rao trupthi
6 篇 shoeibi afshin
6 篇 venu nookala
6 篇 praveen
6 篇 deepak upadhyay
6 篇 nookala venu
6 篇 ginni nijhawan
6 篇 alizadehsani roo...
6 篇 trupthi rao
5 篇 pradnya saval

语言

1,099 篇 英文
135 篇 其他
6 篇 朝鲜文
4 篇 日文

检索条件"机构=Dept. of Data Science and Knowledge Engineering"

共 1241 条记录，以下是461-470 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：

Secured Home Automation with Voice Recognition Using ML and IoT Devices

Secured Home Automation with Voice Recognition Using ML and ...

引用

Computer Vision and Machine Intelligence (CVMI), International Conference on

作者： Sovan Bhattacharya Anisha Singha Tanmoy Sural Rishi Raj Pandey Rohit Paul Shubhranshu Gorai Saibal Majumder Dola Sinha Chandan Bandyopadhyay Dept. CSE (Data Science) Dr. B. C. Roy Engineering College Durgapur India Dept. Electrical Engineering Dr. B. C. Roy Engineering College Durgapur India

ISBN: (数字)9798350376876

ISBN: (纸本)9798350376883

In home, We utilize Gaussian Mixture Model to train voice recognition, and subsequently implement it in Internet of Things devices. We utilize these machine learning frameworks to enhance the precision, adaptability, and robustness of the system in order to mitigate security breaches. Hence, the main objective of the study is to develop a secure authentication system that is on one hand is more precise and on its other is user-friendly, with speech recognition playing a significant role to develop a next level home automation technologies.

关键词： Computer vision Home automation Authentication Speech recognition Machine learning Robustness Internet of Things Security Machine intelligence Gaussian mixture model

来源：评论

学校读者我要写书评

暂无评论

Illumination Effects on Deep Fake Detection: Performance Comparison of CNN Architectures

Illumination Effects on Deep Fake Detection: Performance Com...

引用

Artificial Intelligence and Emerging Technology (Global AI Summit), International Conference on

作者： Sai Bhavya Yangoti Rohith Dumpala Vijay Punyamurthy Ravi Kumar Jatoth dept. of Artificial Intelligence and Data Science Indian Institute of Information Technology Design and Manufacturing Kurnool India dept. of Electronics and Communication Engineering National Institute of Technology Warangal Warangal India

ISBN: (数字)9798350379716

ISBN: (纸本)9798350379723

While AI has many advantages, it also has a few drawbacks associated with “deep fakes.” Deep fakes involve the creation of very realistic videos and images realized through technologies that work with facial and voice modalities for deceptive purposes. Researchers have developed various techniques to detect these manipulated videos and images, employing complex neural network models such as convolutional neural networks (CNNs). However, deep fakes are very difficult to identify due to lighting and shadow effects that may hide some signs of manipulation. No one technique of detection could have the ability of identifying the tampered images under all kinds of illumination conditions. This paper compares different CNN models-ResNet50, EfficientNet, and MobileNetV2-to improve detection accuracy so as to be more resistant to new deep fake techniques, in particular under different illumination conditions. The importance of the study lies in arriving at which of the considered CNN models turns out to be most accurate under a specific illumination effect. Such an understanding could, therefore, improve the results of detection even when applied to cases of tampered faces in fake Aadhaar detection and fake id detection, thereby clearly bringing out the usefulness of the research in practice.

关键词： Resistance Deepfakes Accuracy Lighting Computer architecture Software Convolutional neural networks Reliability Artificial intelligence Protection

来源：评论

学校读者我要写书评

暂无评论

Automatic Feature Extraction from High-Resolution Satellite Imagery using Deep Learning techniques

Automatic Feature Extraction from High-Resolution Satellite ...

引用

Recent Advances in Electrical, Electronics, Ubiquitous Communication, and Computational Intelligence (RAEEUCCI), International Conference on

作者： Kasarapu Ramani G S Suchith C Indrasena Reddy A Chinna G Reshma Dept. of Data Science Mohan Babu University (Erst. Sree Vidyanikethan Engineering College) Tirupati India Dept. of CSSE Mohan Babu University (Erst. Sree Vidyanikethan Engineering College) Tirupati India

ISBN: (数字)9798350354539

ISBN: (纸本)9798350354546

Automated feature extraction from high-resolution satellite data has great potential to locate lucrative resources on Earth. The main elements that are being extracted include Land, Buildings, Roads, Water bodies, and all other necessary elements seen in high-resolution satellite photography. The input dataset includes high-resolution satellite images of New York together with matching map pictures of buildings, roads, landscapes, and water bodies, all in common file formats ***. This paper introduces an innovative feature extraction approach utilizing Deep learning techniques such as Pix2Pix GAN (Generative Adversarial Network) for semantic segmentation and improving the object delineation, such as land, buildings, roads, and water features, in image-to-image translation tasks. U-Net enables precise semantic segmentation by retaining spatial information. Simple CNN (Convolutional Neural Netwok) processes image patches sequentially, extracting relevant features such as edges, textures, and patterns, enabling accurate classification and segmentation of objects in satellite imagery. Pix2Pix GAN is shown to perform better than other models based on Structural Similarity Index Measure (SSIM), a metric used to quantify the similarity between two pictures. It achieved the highest SSIM score of 0.904.

关键词： Deep learning Analytical models Roads Semantic segmentation Buildings Feature extraction Generative adversarial networks

来源：评论

学校读者我要写书评

暂无评论

DivLog: Log Parsing with Prompt Enhanced In-Context Learning

DivLog: Log Parsing with Prompt Enhanced In-Context Learning

引用

International Conference on Software engineering (ICSE)

作者： Junjielong Xu Ruichun Yang Yintong Huo Chengyu Zhang Pinjia He School of Data Science The Chinese University of Hong Kong Shenzhen China Dept. of Computer Science & Engineering The Chinese University of Hong Kong China ETH Zurich Switzerland Shenzhen Research Institute of Big Data China

ISBN: (数字)9798400702174

ISBN: (纸本)9798350382143

Log parsing, which involves log template extraction from semi-structured logs to produce structured logs, is the first and the most critical step in automated log analysis. However, current log parsers suffer from limited effectiveness for two reasons. First, traditional data-driven log parsers solely rely on heuristics or handcrafted features designed by domain experts, which may not consistently perform well on logs from diverse systems. Second, existing super-vised log parsers require model tuning, which is often limited to fixed training samples and causes sub-optimal performance across the entire log source. To address this limitation, we propose Di-vLog, an effective log parsing framework based on the in-context learning (ICL) ability of large language models (LLMs). Specifically, before log parsing, DivLog samples a small amount of offline logs as candidates by maximizing their diversity. Then, during log parsing, DivLog selects five appropriate labeled candidates as examples for each target log and constructs them into a prompt. By mining the semantics of examples in the prompt, DivLog generates a target log template in a training-free manner. In addition, we design a straightforward yet effective prompt format to extract the output and enhance the quality of the generated log templates. We conducted experiments on 16 widely-used public datasets. The results show that DivLog achieves (1) 98.1% Parsing Accuracy, (2) 92.1% Precision Template Accuracy, and (3) 92.9% Recall Template Accuracy on average, exhibiting state-of-the-art performance.

关键词： Training Measurement Analytical models Semantics Feature extraction Tuning Software engineering

来源：评论

学校读者我要写书评

暂无评论

Advancing Android Security: Leveraging Stacking Ensemble and Bioinspired Feature Selection for Efficient Malware Detection

Advancing Android Security: Leveraging Stacking Ensemble and...

引用

Emerging Technology (INCET), International Conference for

作者： V. Jyothsna Peddesugari Mokshitha Shaik Khulud Lakshmireddy Gari Premanath Reddy Nare Jagannath Reddy Bhasha Pydala Department of Data Science Mohan Babu University(Erstwhile Sree Vidyanikethan Engineering College(Autonomous) Tirupati India Dept. of Information Technology Sree Vidyanikethan Engineering College Tirupati India Department of Data Science Mohan Babu University Tirupati India

ISBN: (数字)9798350361155

ISBN: (纸本)9798350361162

Nowadays, the use of smartphones and related applications is increasing rapidly due to their “easy to use” features, the functionality of many applications, and the constant development of software and hardware of smart devices. Research in this field shows that 4.5 billion people will have mobile phones by 2024. The most used smartphone operating system among these devices is Android. Android accounts for 75.5% of the market. Because Android is so widely used, it is more vulnerable to viruses and malware, making it an ideal target for hackers. Android anti-malware technology, which can quickly detect and classify different malware to create a rapid response plan, has become popular in recent years. The usefulness of combining deep learning and machine learning to offer automated and self-learning services has been shown by numerous applications; nevertheless, the shortage of malware samples has been identified as a barrier to the development of deep learning-based solutions. To solve this problem, this work introduces new machine-learning techniques that can classify malware into different groups and identify malware attacks. The proposed method used the Drebin dataset divided into hazardous and non-hazardous substances.

关键词： Machine learning algorithms Accuracy Stacking Feature extraction Malware Classification algorithms Ensemble learning

来源：评论

学校读者我要写书评

暂无评论

Classification of Skin Disease using CNN

Classification of Skin Disease using CNN

引用

Evolutionary Algorithms and Soft Computing Techniques (EASCT), International Conference on

作者： Boddupelli Durgabhavani Bollampelly Chandana Sandhyarani G. Lavanya G. Srikanth Nuthanakanti Bhaskar Dept. of Computer Science and Engineering (AI&ML) CMR Technical Campus Hyderabad Telangana India Dept. of Computer Science and Engineering (Data Science) CMR Technical Campus Hyderabad Telangana India Dept. of Computer Science and Engineering CMR Technical Campus Hyderabad Telangana India Dept. of Electronics and Communication Engineering CMR Technical Campus Hyderabad Telangana India

The majority of people around the world suffer from skin conditions at some point in their lives. These conditions need to be identified and treated as soon as possible in order to prevent complications and improve the outcome of the patient. Skin diseases can be difficult to diagnose, even for dermatologists who are experts in the field. In order to identify and classify skin diseases, a computer algorithm known as a Convolutional Neural Network (CNN) can be used. Using CNN, artificial intelligence is able to learn from images and make predictions based on the information it gathers from them. In order to train CNN to classify skin conditions accurately, a large number of images of skin diseases can be used to train the CNN. This paper describes a method for classifying skin diseases using CNNs. As part of the training process, the system was taught a large collection of thermoscopic images, which show the distribution of heat patterns on the skin. As a result of this study, CNN was able to successfully classify different skin diseases with an accuracy of 90% in terms of validation, and 95% in terms of classification. In addition to dermatologists and primary care physicians, healthcare professionals can also use this system to make an accurate diagnosis of skin diseases by using this system. Furthermore, patients can use it as a means of identifying and understanding their skin conditions as well.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Systems Analysis of Bias and Risk in AI-Enabled Medical Diagnosis

Systems Analysis of Bias and Risk in AI-Enabled Medical Diag...

引用

IEEE Symposium Series on Computational Intelligence (SSCI)

作者： Negin Moghadasi Misagh Piran Stephen Baek Rupa S. Valdez Michael D. Porter DeAndre Johnson James H. Lambert Dept. of Systems and Information Engineering University of Virginia Johnson & Johnson Medtech Dept. of Radiology Nuclear Medicine and Molecular Imaging Heart and Diabetes Center North-Rhine Westphalia Ruhr University of Bochum School of Data Science University of Virginia Dept. of Systems and Information Engineering School of Data Science University of Virginia Dept. of Systems and Information Engineering University of Virginia

AI technologies have made significant advancements across various sectors, especially healthcare. Although AI algorithms in healthcare showcase remarkable predictive capabilities, apprehensions have emerged owing to errors, biases, and a lack of transparency. These concerns have led to a decline in trust among clinicians and patients, while also posing the risk of further accentuating pre-existing biases against marginalized groups and exacerbating inequities. This paper presents a scenario-based preferences risk register 1 1 Denotes a methodically arranged document or database detailing potential risks linked to particular scenarios or situations. framework for identifying and accounting AI algorithm biases in diagnosing diseases. The framework is demonstrated with a realistic case study on cardiac sarcoidosis. The framework identifies success criteria, initiatives, emergent conditions and the most and least disruptive scenarios. The success criteria align with the National Institute of Standards and Technology AI Risk Management Framework (NIST AI RMF) trustworthy AI characteristics, and the scenarios are based on various statistical/computational bias that causes algorithmic bias. The framework provides valuable guidance for leveraging AI in healthcare, enhancing objective designs, and mitigating risks by adopting a figure of merit to score the initiatives and measuring the disruptive order. By prioritizing transparency, trustworthy AI, and identifying the most and least disruptive scenarios/biases, the framework promotes responsible and effective use of AI technologies in healthcare.

关键词：

来源：评论

学校读者我要写书评

暂无评论

ICardo 2.0: A Smart Healthcare Framework for Cardiovascular Disease Accurate Prediction by Using T-Wave Morphology of ECG 8

ICardo 2.0: A Smart Healthcare Framework for Cardiovascular ...

引用

8th IEEE International Symposium on Smart Electronic Systems, iSES 2022

作者： Sinha, Nidhi Joshi, Amit M. Mohanty, Saraju P. MNIT Department of ECE Jaipur India Konverge.AI Department of Data Science and Engineering Pune India University of North Texas Dept. of CSE Denton United States

ISBN: (纸本)9798350399226

Potassium plays a vital role in the heart's normal functioning. Potassium homeostasis disorder can elevate the risk of heart failure, and acute treatment may not be tolerated in the long term. Hyperkalemia and cardiac failure are linked through a vicious cycle. In this study, the association of blood potassium level to heart failure has been scrutinized with the help of the BIDMC Congestive Heart Failure dataset. The dataset contains ECG recordings of 15 subjects of NYHA Class III-IV patients. Eleven of them were men between the ages of 22 and 71, while four were women between the ages of 54 and 63. T wave morphology of ECG recording can quantify the information of blood potassium level, and this concept is already well-validated. Here, in this work threshold for the amplitude of T was set to 10 mm of height, and the concept has been authenticated using the MIT-BIH Normal Sinus Rhythm database. Based on the T wave morphology, 12 out of 15 subjects of the BIDMS dataset were found to be hyperkalemic. There were two subjects which were hyperkalemic, whereas one subject did not exhibit a distinguishable T wave. There are around 90% f heart failure patients in the database are hyperkalemic, indicating a strong linkage of heart disease with potassium level. The proposed smart healthcare system would be integrated for hyperkalemia prediction through remote monitoring. The framework can be utilised to forecast the occurrence of hyperkalemia for CVD patients using recorded ECG. © 2022 IEEE.

关键词： Potassium

来源：评论

学校读者我要写书评

暂无评论

Delay Tolerant and Energy Reduced Task Allocation in Internet of Things with Cloud Systems 1

Delay Tolerant and Energy Reduced Task Allocation in Interne...

引用

1st IEEE International Interdisciplinary Humanitarian Conference for Sustainability, IIHC 2022

作者： Raghunath Patil, Dipak Borkar, Bharat Markad, Ashok Kadlag, Sunil Kumbhkar, Makhan Jamal, Ahmad Amrutvahini College of Engineering Dept. of Computer Engineering Pune Sangamner India Amrutvahini College of Engineering Dept. of Information Technology Pune Sangamner India Amrutvahini College of Engineering Department of Electrical Engineering Pune Sangamner India Christian Eminent College Indore & Visiting Faculty School of Data Science and Forecasting Devi Ahilya University Department of Computer Science & Electronics Indore India Tulas Institute Department of Computer Science and Engineering Uttarakhand Dehradun India

ISBN: (纸本)9781665456876

Through the utilization of the Internet, cloud computing supplies storage and computation resources to deliver services for many sectors. The speed of such systems suffers, though, since delay-sensitive systems, such as smart city and health applications, increasingly need for processing over massive volumes of data transmitted to centralised datacenters. When compared to cloud services, the paradigms of fog as well as edge computing provide innovative solutions by affecting the financial closer to the customer and by having low energy consumption and latency effectiveness. To optimise expense and resource efficiency, enhance QoS, and increase security and privacy, it is crucial to discover the best locations for services and assets inside the 3 IoT. The bipartite graph task scheduling method we provide in this research enhances cost effectiveness in real world applications with strict deadlines. The proposed method's performance in terms of delay, network congestion, as well as cost is deployed and tested to use the iFogSim simulator, an expanded version of CloudSim. The evaluation results demonstrate that the suggested algorithm outperforms Round-Robin and Minimum Response Time methods in terms of both cost as well as throughput. © 2022 IEEE.

关键词： Internet of things

来源：评论

学校读者我要写书评

暂无评论

Earthquake Prediction Through Machine Learning Approach

Earthquake Prediction Through Machine Learning Approach

引用

Technological Advancements in Computational sciences (ICTACS), International Conference on

作者： Pratik Shrote Priya Dasarwar Snehlata Dongre Prashant Khobragade Intern Center of Excellence Data Science GH Raisoni College of Engineering Nagpur India CSE Symbiosis Institute of Technology Nagpur Campus Symbiosis International (Deemed University) Pune India Dept. of Computer Science and Engineering GH Raisoni College of Engineering Nagpur India Dept. of Computer Science and Engineering H Raisoni College of Engineering Nagpur India

ISBN: (数字)9798350387490

ISBN: (纸本)9798350387506

The population of earthquake-prone areas is growing, as is the number of people killed and injured by earthquakes. The problem of the increasing number of populated regions that are vulnerable to earthquakes is being addressed by a shortage of experts in earthquake engineering. This implies the requirement for automated intelligence-monitored mitigation and warning systems. Predicting earthquakes is still a major problem for disaster management around the globe. The objective of this work is to build a machine learning (ML) approach that uses geographic coordinates (latitude, longitude) and elevation (height) as inputs to forecast earthquake magnitude. The estimated magnitude is used to classify the seismic risk level for a given site into high, low, or no risk categories using Richter's scale. The study offers a thorough analysis of the methodology, covering feature engineering, data collecting, preprocessing, and model construction. A variety of machine learning methods are investigated, and relevant measures are used to assess their effectiveness.

关键词： Seismic measurements Prevention and mitigation Earthquake engineering Disasters Earthquakes Machine learning Real-time systems Hazards Stakeholders Resilience

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125页 << < 43 44 45 46 47 48 49 50 51 52 > >>

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：