检索结果-内蒙古大学图书馆

An In-Depth Study of Handwritten Digit Recognition Methods: An Exploration of Deep Learning and Machine Learning Approaches

An In-Depth Study of Handwritten Digit Recognition Methods: ...

引用

2023 International Conference on Innovative Computing, Intelligent Communication and Smart Electrical Systems, ICSES 2023

作者： Singh, Nongmeikapam Thoiba Tiwary, Priyanshu Chanu, Asem Debala Chandigarh University Department of Computer Science and Engineering Punjab India Indian Institute of Information Technology Department of Computer Science and Engineering Assam Guwahati India

ISBN: (纸本)9798350319200

This article explains how deep learning and machine learning techniques are being utilized to replace humans in a variety of activities, like item classification and sound addition. It emphasizes handwritten text recognition (HTR), which involves computers interpreting handwritten content from sources like paper documents and touchscreens. For recognizing handwritten digits, the study analyzes three algorithms: support vector machines (SVM), multilayer perception (MLP), and convolutional neural networks (CNN). This comparison aims to evaluate the correctness and execution times of different approaches. The evaluation is based on parameters like the dataset used, the number of epochs, algorithm complexity, accuracy, and hardware specifications. The study compares the effectiveness of CNN, Multilayer Perception (MLP), and Support Vector Machines using handwritten digits from the MNIST dataset. It evaluates these algorithms based on criteria such as runtime, complexity, rate of precision, the count of epochs, and the quantity of hidden layers specifically within deep learning techniques. SVM had the highest training data accuracy, but CNN outperformed others on the test dataset. The article's primary goal is to identify the most precise model for recognizing handwritten digits. It achieves this by assessing the performance of different algorithms and comparing them based on various characteristics. © 2023 ieee.

关键词： convolutional neural networks execution time handwritten digits multilayer perceptron overfitting visualization

来源：评论

学校读者我要写书评

暂无评论

Air Monitoring with Cloud and IoT

Air Monitoring with Cloud and IoT

引用

2023 International Conference on Sustainable Computing and Smart Systems, ICSCSS 2023

作者： Kalaivani, K. Subramanian, S. Swedha, G.K.S. Vinoth, N. Vishnu Priya, V. Sns College of Engineering Department of Computer Science and Design Coimbatore India Sns College of Engineering Department of Computer Science and Engineering Coimbatore India

ISBN: (纸本)9798350333602

The air is an essential aspect of humans' daily lives as it helps in breathing. With the rise of air pollution, it is necessary to have an efficient air quality monitoring system that can detect the concentration of pollutants in the air. In this study, the design and implementation of air quality monitoring system is discussed which uses an MQ2 sensor and ESP32 microcontroller. The system detects the ppm levels in the air to classify whether it is fresh or poor air. The challenges include establishing reliable connectivity, visualizing data effectively, integrating multiple sensors, ensuring accurate measurements, and enabling real-time analysis. The ESP32 microcontroller addresses connectivity issues by providing built-in Wi-Fi and Bluetooth capabilities. The LCD display offers real-time visual feedback, enhancing data visualization. Integration of the DHT11 sensor for temperature and humidity measurement and the MQ2 sensor for gas detection enables comprehensive air quality monitoring. The ThingSpeak application acts as a cloud-based IoT platform, allowing data logging, remote monitoring, and real-time alerts and notifications. If the ppm levels are less than 1000, it is considered poor air, and a buzzer is triggered, along with an LCD I2C display that shows the levels using the I2C protocol. The system also uses a DHT11 sensor to detect temperature and humidity and passes all data to the cloud channel by using IoT, triggering a mail alert using Google sheet with an on and off button for ppm levels using Javascript extension and GPS. The system is designed to provide a real-time solution for monitoring air quality, making it an essential tool for public health and environmental protection. © 2023 ieee.

关键词： Microcontrollers

来源：评论

学校读者我要写书评

暂无评论

CE³USOD: Channel-Enhanced, Efficient, and Effective Network for Underwater Salient Object Detection

引用

ieee JOURNAL OF OCEANIC ENGINEERING 2025年第2期50卷 941-954页

作者： Wu, Qingyao Xie, Jiaxin Fu, Zhenqi Tu, Xiaotong Huang, Yue Ding, Xinghao Xiamen Univ Inst Artificial Intelligence Xiamen 361102 Peoples R China Xiamen Univ Sch Informat Xiamen 361102 Peoples R China Tsinghua Univ Dept Automation Beijing 100084 Peoples R China Jianghuai Adv Technol Ctr Sch Informat Hefei 230000 Peoples R China

Underwater salient object detection (USOD) aims to identify the most crucial elements in underwater environments, holding significant potential for underwater exploration. Existing methods often overlook light degradation or involve larger network sizes, which are unsuitable for underwater mobile platforms and pose challenges to implement in practice. Given the importance of low-complexity algorithms in underwater applications to optimize system efficiency, this article introduces (CEUSOD)-U-3-an efficient network tailored to deliver an effective solution for salient object detection in underwater scenarios. On the one hand, we reconsider long-range dependencies and feature computation from a neighborhood perspective, leading to the development of the long-range context-aware module. Specifically, we approximate local and global context awareness by incorporating the maximum and average values of neighboring pixels within varying window sizes, which allows our method to achieve high performance while maintaining low computational cost. On the other hand, light scattering and absorption during underwater imaging frequently result in channel intensity imbalances in captured underwater images. To address this, we propose the color-guided pyramid aggregation module, which utilizes the weaker color channels enhanced by underwater image enhancement techniques as guiders for multiscale feature fusion, finally facilitating the model to obtain underwater domain information. Extensive experiments on four public benchmarks demonstrate that our innovative network achieves state-of-the-art results while maintaining a low model size (Params of 0.546M) and computational complexity (FLOPs of 0.416G). Therefore, (CEUSOD)-U-3 proves to be effective and efficient, establishing its practicality, particularly for underwater applications.

关键词： Feature extraction visualization Object detection Image color analysis Electronic mail data mining Convolution Semantics Saliency detection Decoding Feature fusion lightweight model salient object detection (SOD) underwater image

来源：评论

学校读者我要写书评

暂无评论

Implementation of an Automated Vegetation Drought Monitoring System Based on Long-Term Satellite Remote Sensing 11

Implementation of an Automated Vegetation Drought Monitoring...

引用

11th International Conference on Agro-Geoinformatics, Agro-Geoinformatics 2023

作者： Yue, Zichen Mei, Xin Zhong, Shaobo Hubei University Faculty of Resources and Environmental Science Wuhan China Institute of Urban Systems Engineering Beijing Academy of Science and Technology Beijing China

ISBN: (纸本)9798350303513

Droughts are a severe problem globally, and although satellite remote sensing is an effective tool for monitoring drought, current methods require manual intervention and operation to detect drought. This paper proposes a full-automatic drought monitoring system(FADMS) consisting of four main phases: remote sensing data acquisition and preprocessing, drought index calculation and analysis, time-series image service publishing, and analysis and visualization. This system uses Python-based automation scripts, which can automatically download and preprocess satellite remote sensing data efficiently and reliably. We also employed Web Service technology to serve different vegetation drought index algorithms such as Normalized Difference Vegetation Index (NDVI), Vegetation Condition Index (VCI), Temperature Condition Index (TCI), and Temperature Vegetation Dryness Index (TVDI). Moreover, we designed a time-series image service publishing architecture based on GeoServer and ImageMosaic plug-in, enabling the rapid publication of long-term vegetation drought products. Lastly, we used the GIS spatial statistical analysis module to analyze and visualize drought characteristics such as grade, scope, and duration. To demonstrate the effectiveness of our approach, we conducted experiments using MODIS-derived products from 2000 to 2022 in China's northern region. The results confirmed that FADMS could detect and monitor vegetation droughts accurately and timely, identifying drought events' spatiotemporal distribution and evolution trends. FADMS significantly enhances the efficiency and accuracy of vegetation drought monitoring and is highly reliable and practical. © 2023 ieee.

关键词： Time series

来源：评论

学校读者我要写书评

暂无评论

Terminal-ileum Centerline Extraction from Magnetic Resonance Enterography data of Crohn's Disease Patients

Terminal-ileum Centerline Extraction from Magnetic Resonance...

引用

2023 ieee EMBS Special Topic Conference on data science and Engineering in Healthcare, Medicine and Biology, ieeeCONF 2023

作者： Benisty, Rotem Shinnawi, Faten Haj Ali Porat, Moshe Illivitzki, Anat Freiman, Moti Faculty of Electrical & Computer Engineering Technion - Israel Institute of Technology Haifa Israel Rambam Health Care Campus Department of Radiology Haifa Israel Faculty of Biomedical Engineering Technion Israel Institute of Technology Haifa Israel

ISBN: (纸本)9798350383386

Crohn's disease (CD), a chronic inflammatory bowel disorder, often affects the terminal ileum (TI) and leads to digestive tract inflammation and complications like bowel obstruction. Accurately determining the 3D extent of CD from 2D Magnetic Resonance Enterography (MRE) images requires approximations, as no automated 3D measurement system exists. We developed an intelligent MRE reading application for virtual unfolding and 3D visualization of MRE data. We introduce a semi-automatic algorithm to predict the TI centerline from MRE data to reduce radiologist interaction time. The algorithm involves constructing an orientation classifier and implementing a shortest path algorithm to determine the TI centerline. We evaluated the algorithm's effectiveness on a database of 123 MRE scans using a k-fold cross-validation experimental setup, comparing the predicted centerline with a radiologist-annotated centerline considered as ground-truth. The results showed good alignment with the ground-truth centerline with minimal interaction *** relevance: This study introduces a semi-automatic algorithm that accurately predicts the terminal ileum centerline from MRE data, streamlining the diagnostic process for Crohn's disease. By reducing radiologist interaction time in assessing the 3D extent of the disease from 2D images, the algorithm holds promise for improving early diagnosis and treatment strategies for affected patients. © 2023 ieee.

关键词： Magnetic resonance

来源：评论

学校读者我要写书评

暂无评论

Analyzing Credit Card Defaulters: A Comparative Study Using Kohonen Maps, Neural Networks, and Decision Trees

Analyzing Credit Card Defaulters: A Comparative Study Using ...

引用

2023 International Conference on Information Technology and Computing, ICITCOM 2023

作者： Degtyareva, Ksenia Borodulin, Aleksey Kukartsev, Vladislav Gantimurov, Andrei Nizameeva, Alena Reshetnev Siberian State University of Science and Technology Department of Information Economic System Krasnoyarsk Russia Artificial Intelligence Technology Scientific and Education Center Bauman Moscow State Technical University Moscow Russia Siberian Federal University Department of Business Informatics and Business Process Modeling Krasnoyarsk Russia

ISBN: (纸本)9798350359633

The text discusses the credit card debt crisis faced by credit card issuers in Taiwan, which has led to a decrease in consumer financial confidence and poses problems for both banks and cardholders. There is a study conducted using data on customers who took credit cards in order to identify the most important criteria for non-payers. The study aims to predict loan repayment ability using a neural network and selecting the most significant factors. The literature review highlights the use of neural networks in determining non-payers and the potential for creating systems to warn credit card owners about risk behavior. The methodology involves data processing using the Kohonen map, a type of neural network that uses unsupervised learning for visualization and clustering. Decision Trees and Neural Networks are also used in the analysis. Analysis using Kohonen maps did not provide the necessary information due to heterogeneous data in clusters. Analysis via a neural network resulted in a high error percentage of 17.6% and lacked accuracy in predicting average values. Analysis through the decision tree yielded a lower error percentage of 12.5% and identified repayment status in September and August as the most significant factors. An experiment was conducted by dividing factors into logical groups, resulting in a difference of 7% in error percentages for each group. The conclusion suggests that the decision tree method is the most suitable for this data model, with repayment status in September as the key factor in predicting defaulters. © 2023 ieee.

关键词： Decision trees

来源：评论

学校读者我要写书评

暂无评论

Harnessing Cloud Synergy for Streamlined Healthcare and Life sciences Ventures 2

Harnessing Cloud Synergy for Streamlined Healthcare and Life...

引用

2nd International Conference on Automation, Computing and Renewable Systems, ICACRS 2023

作者： Manhas, Prabal Hariharan, U. Department of Computer Science and Engineering Apex Institute of Technology Chandigarh University Punjab Mohali India

ISBN: (纸本)9798350340235

The healthcare and life sciences sectors are experiencing unprecedented growth in the era of digital transformation, demanding robust and scalable cloud computing solutions. In this research paper, we comprehensively analyze Amazon Web Services (AWS), Microsoft Azure, and Google Cloud Platform (GCP) to determine the optimal choice for healthcare and life sciences ventures. Our study reveals that GCP, with its extensive services, global infrastructure, security measures, and successful healthcare case studies, stands out as the preferred cloud solution. Additionally, we utilized Power BI for data visualization and analytics, enhancing our comprehensive analysis, and offering valuable insights for professionals in these fields. © 2023 ieee.

关键词： Amazon Web Services (AWS) Artificial Intelligence (AI) Cloud Synergy Extensible Markup Language (XML) Google Cloud Platform (GCP) Healthcare Innovation Hypertext Markup Language (HTML) Internet of Things (IoT) Machine Learning (ML) Microsoft Open XML Spreadsheet (XLSX) Microsoft Power Business Intelligence (BI) Python (py) Role Based Access Control (RBAC) Telemedicine

来源：评论

学校读者我要写书评

暂无评论

Large-Scale Mussel Farm Reconstruction with GPS Auxiliary 38

Large-Scale Mussel Farm Reconstruction with GPS Auxiliary

引用

38th International Conference on Image and Vision Computing New Zealand, IVCNZ 2023

作者： Zhao, Junhong Xue, Bing Vennell, Ross Zhang, Mengjie Victoria University of Wellington Centre for Data Science and Artificial Intelligence School of Engineering and Computer Science New Zealand Cawthron Institute Coastal and Freshwater Group Nelson New Zealand

ISBN: (纸本)9798350370515

The expanding mussel farming industry, especially in regions like New Zealand (NZ), necessitates advanced monitoring and management solutions for sustainable and efficient operations. Currently, manual labor and on-site operations limit real-time capabilities and overall efficiency. To address these challenges, large-scale 3D reconstruction offers a viable solution, enabling reproducible representations of mussel farm scenes based on captured video for off-site evaluation and precise decision-making. Conventional 3D reconstruction methods often require intricate manual camera calibration, posing challenges for real-world applications, particularly in marine scenarios. In contrast, this paper presents an innovative and practical approach for large-scale mussel farm reconstruction by integrating GPS auxiliary data without heavy camera calibration. The primary objective is to develop a comprehensive large-scale 3D visualization of mussel farms using video footage and simultaneous GPS information captured by a vessel-mounted camera. Our methodology involves a two-step process: First, making adaptive image sampling from captured video and applying Structure from Motion (SfM) for camera pose estimation and a dense 3D reconstruction, accurately reproducing local 3D scenes of partial mussel farms. Then, GPS data will be integrated for georeferencing and localization. This alignment empowers farm managers with geospatial accuracy for decision-making, resource allocation, and strategic planning. Experimental results validate the effectiveness of the proposed approach on reconstruction accuracy and completeness, and GPS geo-registration precision, highlighting its potential for advancing mussel farm monitoring. © 2023 ieee.

关键词： Decision making

来源：评论

学校读者我要写书评

暂无评论

A Reversible Framework for Efficient and Secure Visual Privacy Protection

引用

ieee TRANSACTIONS ON INFORMATION FORENSICS AND SECURITY 2023年 18卷 3334-3349页

作者： Zhang, Yushu Ye, Xi Xiao, Xiangli Xiang, Tao Li, Hongwei Cao, Xiaochun Nanjing Univ Aeronaut & Astronaut Coll Comp Sci & Technol Nanjing 211106 Peoples R China Zhengzhou Xinda Inst Adv Technol Zhengzhou 450001 Peoples R China Chongqing Univ Coll Comp Sci Chongqing 400044 Peoples R China Univ Elect Sci & Technol China Sch Comp Sci & Engn Chengdu 610054 Peoples R China Sun Yat sen Univ Sch Cyber Sci & Technol Shenzhen Campus Shenzhen 518107 Peoples R China

The number of images produced by people everyday is rapidly increasing in recent years and their local storage space may be not big enough for storing all these images. As a result, people are currently accustomed to uploading images to cloud platforms, which raises privacy concerns. Traditional image encryption is a way to protect image privacy without preserving visual usability, so that image owners fail to conveniently browse and manage their images stored in the cloud. Hence some visual privacy protection schemes were proposed to balance image privacy and usability, while many of them are irreversible. Recently, a novel reversible technology, called Thumbnail-Preserving Encryption (TPE), has been a hot topic. However, existing TPE schemes are either inefficient, or cannot perfectly restore the original image and meanwhile achieve Nonce-Respecting (NR) security. In view of this, we propose a reversible framework for efficient and secure visual privacy protection, which tunably preserves image visual usability for image owners with the idea of data hiding. In the framework, the original image is firstly divided into several regions by our proposed region division methods and one of the regions is vacated by data hiding. Then, the vacated region is utilized to preserve the original thumbnail by pixel adjustment after image encryption. Finally, pixels in each sub block are permuted for security. According to our theoretical analysis, the above processes are completely reversible and the processed image achieves NR security. Furthermore, we conduct extensive experiments, including recognition by various application programming interfaces, user surveys, and efficiency comparison, to demonstrate that our framework is efficient and strikes a good balance between privacy and usability.

关键词： Encryption Privacy Usability Security visualization Image restoration Image filtering Visual privacy protection thumbnail preserving reversible data hiding

来源：评论

学校读者我要写书评

暂无评论

An Intelligent Analysis Method for Multi-Stage Web Attack Forensics 20

An Intelligent Analysis Method for Multi-Stage Web Attack Fo...

引用

20th International Conference on Natural Computation, Fuzzy Systems and Knowledge Discovery, ICNC-FSKD 2024

作者： Liu, Yanhua Xu, Yijie Han, Yuting Liu, Zhihuang College of Computer and Data Science Fuzhou University Fuzhou China College of Computer National University of Defense Technology Fuzhou China

ISBN: (纸本)9798350356328

In this paper, we propose IVMWAF, a framework for intelligent analysis of multi-stage web attacks which uses artificial intelligence and visualization approaches. The IVMWAF framework is designed to provide a general and practical forensic process for investigating multi-stage web attacks. Using IVMWAF, digital forensics analysts can have a flexible and intuitive understanding of the overall situation of complex web security incidents. Specifically, in order to extract all web security incident related anomalies, we first propose a multi-level anomaly detection method, by dividing different levels based on different stages of the web attack chain. We also design methods for visualizing and making human-computer interactions for different levels of anomaly detection, to assist analysts in comprehending and providing feedback on the decisions made by intelligent methods. For forensic analysis of web attack incidents, we integrate multi-level anomaly detection and visualization for correlation analysis, and propose a method for constructing multi-level web attack scenarios. Finally, we developed a prototype system and validated the usability and superiority of the proposed IVMWAF with experimental results and expert evaluations on a dataset during a real enterprise security incident. © 2024 ieee.

关键词： Cyber attacks

来源：评论

学校读者我要写书评

暂无评论

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：

请选择收藏分类：

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

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：