检索结果-内蒙古大学图书馆

24th Asia-Pacific Network Operations and Management Symposium, APNOMS 2023

作者： Lee, Beom-Su Kim, Jong-Wouk Choi, Mi-Jung Dept. of Data Science Kangwon National University Gangwon24341 Korea Republic of Dept. of Computer Science Kangwon National University Gangwon24341 Korea Republic of IGP. in Medical Bigdata Convergence Kangwon National University Gangwon24341 Korea Republic of

ISBN: (纸本)9788995004395

The advancement of information technology is closely associated with various aspects of daily life, providing people with services for a comfortable life. As the network infrastructure expands to accommodate these services, it inevitably creates several vulnerable points susceptible to cyberattacks. Researchers have gained significant momentum by focusing on deep learning-based network intrusion detection. The development of a robust network intrusion detection system based on deep learning necessitates a substantial volume of data. Traditionally, collected data for centralized learning were transmitted to a central server for training the model. However, this approach causes concern regarding the potential compromise of the personal information contained within the raw data, thereby precipitating legal implications for vendors. Therefore, this paper proposes an ImprovedFedAvg, which enhances the existing FedAvg algorithm for network intrusion detection model. This method uses the full advantages of federated learning for data privacy preservation and significantly reduces the transmission of model weights while improving the performance of the model. Copyright 2023 KICS.

关键词： Network security

来源：评论

学校读者我要写书评

暂无评论

Deep Learning Driven - Pest Classification and Sustainable Agriculture 3

Deep Learning Driven - Pest Classification and Sustainable A...

引用

3rd International Conference on Electronics and Renewable Systems, ICEARS 2025

作者： Kumar, M. Sirish Usha, R. Reddy, B. Rama Kantha Ramachandra, S. Prakash, P. Jaya Swetha, B. Mohan Babu University School of Computing Dept. of Data Science India Madanapalle Institute of Technology and Science Madanapalle India Sri Venkateswara College of Engineering Tirupati India Mother Theresa Institute of Engineering and Technology Palamaner India Sri Venkateswara College of Engineering Department of It Tirupati India Mohan Babu University Dept. of Master of Computer Applications India

ISBN: (纸本)9798331509675

This study introduces a system designed to identify pests in crops and classify them as either beneficial or harmful. The project begins by providing a comprehensive overview of various pest identification methods, analyzing their strengths and limitations. To address the problem, a categorization approach is proposed that incorporates convolutional neural networks (CNN) to build the pest identification and classification model. The model was trained using a dataset containing images of different pest species. Extensive testing was conducted on a large dataset, and the system's performance was validated against multiple traditional classification models. The proposed framework achieved a classification accuracy of 90%, outperforming conventional methods. This research highlights agriculture's vital role in the economy and underscores the potential of advanced technologies in supporting sustainable farming practices. © 2025 IEEE.

关键词： Agriculture Sustainability Classification Accuracy Classification Model Convolutional Neural Network (CNN) Pest Classification

来源：评论

学校读者我要写书评

暂无评论

Recognition of American sign language using modified deep residual CNN with modified canny edge segmentation

引用

Multimedia Tools and Applications 2025年 1-28页

作者： Hariharan, U. Devarajan, Devikanniga Kumar, P. Santhosh Rajkumar, K. Meena, M. Akilan, T. Department of Computer Science and Engineering Apex Institute of Technology Chandigarh University Punjab Mohali140413 India Department of Computer Science and Engineering GITAM University Karnataka Bengaluru561203 India Department of Information Technology Faculty of Engineering and technology SRM Institute of Science and Technology Ramapuram Tamil Nadu Chennai600089 India Department of Data Science and Business Systems School of Computing Faculty of Engineering and Technology SRM Institute of Science and Technology Kattankulathur Tamil Nadu Chennai603203 India Department of Computer Science and Engineering Sri Sairam Engineering College Tamil Nadu Tambaram602109 India Research Coordinator Dept. of IQAC Amity University Kolkata West Bengal 700135 India

American Sign Language (ASL) recognition aims to recognize hand gestures, and it is a crucial solution to communicating between the deaf community and hearing people. However, existing sign language recognition algorithms still have some drawbacks, such as difficulty recognizing hand movements and low recognition accuracy for most sign language recognition. A Modified Convolutional Neural Network (MCNN) deep residual 101 classifier-based American Sign Language identification system has been developed to address this problem. There are three main parts presents in the method. The first part is pre-processing the images to remove the noise, enhance the contrast of the picture, adjust the contrast level and smoothen the picture using various filters. The second part is the segmentation, and it’s used to partition the image using a modified canny edge detection method by removing all weak edges present in the image. Finally, classification will be done using the Modified CNN deep residual 101 classifiers. By classifying the image, the American Sign Language is accurately identified. This process is conducted through images. The outcome shows that the suggested approach has a 0.97% accuracy and a 0.05% False Positive Rate. Other CNN architectures such as resNet 50 and resNet 18 reached 0.90% and 0.80% accuracy, respectively, which is lower than our proposed method. In addition, the resNet 101 classifier effectively recognizes the difficult hand gestures through the image data. It obtains high recognition accuracy for 36 signs is 0 to 9 numbers and a to z alphabets from American Sign Language. © The Author(s), under exclusive licence to Springer science+Business Media, LLC, part of Springer Nature 2025.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Guarantees of a Preconditioned Subgradient Algorithm for Overparameterized Asymmetric Low-rank Matrix Recovery

arXiv

引用

arXiv 2024年

作者： Giampouras, Paris Cai, HanQin Vidal, René Dept. of Computer Science University of Warwick United Kingdom Dept. of Statistics and Data Science Dept. of Computer Science University of Central Florida United States ESE Radiology and IDEAS University of Pennsylvania United States

In this paper, we focus on a matrix factorization-based approach for robust low-rank and asymmetric matrix recovery from corrupted measurements. We address the challenging scenario where the rank of the sought matrix is unknown and employ an overparameterized approach using the variational form of the nuclear norm as a regularizer. We propose a subgradient algorithm that inherits the merits of preconditioned algorithms, whose rate of convergence does not depend on the condition number of the sought matrix, and addresses their current limitation, i.e., the lack of convergence guarantees in the case of asymmetric matrices with unknown rank. In this setting, we provide, for the first time in the literature, linear convergence guarantees for the derived overparameterized preconditioned subgradient algorithm in the presence of gross corruptions. Additionally, by applying our approach to matrix sensing, we highlight its merits when the measurement operator satisfies the mixed-norm restricted isometry properties. Lastly, we present numerical experiments that validate our theoretical results and demonstrate the effectiveness of our approach. © 2024, CC BY.

关键词： Matrix factorization

来源：评论

学校读者我要写书评

暂无评论

Land Valuation Using an Innovative Model Combining Machine Learning and Spatial Context

Land Valuation Using an Innovative Model Combining Machine L...

引用

IEEE International Symposium on Geoscience and Remote Sensing (IGARSS)

作者： Feride Tanrikulu Timothy L. Haithcoat Grant J. Scott Matthew Foulkes Ilker Ersoy Institute for Data Science and Informatics University of Missouri Dept. Electrical Engineering and Computer Science University of Missouri Dept. of Geography University of Missouri

ISBN: (数字)9798350360325

ISBN: (纸本)9798350360332

Land valuations are used by buyers, sellers, regulators, and authorities to assess fair value. Urbanization demands a modern and efficient land valuation system. An alternative method that integrates geographic information systems and machine learning can produce more reliable, repeatable, and accurate valuations. The land’s value can vary significantly based on the parcel’s neighborhood and context. Geospatial analytics, remote sensing and vector information were integrated to predict land values in Springfield, Missouri, USA. A point geodatabase was assembled using calculated proximities, accessibility, and various index measures. Supervised machine learning models were trained using government-provided appraised land values as ground truth. The database approach integrated spatial context and socioeconomic data. Slight differences in performance between random forest (98%, 0.13) and gradient boosting (98%, 0.15) algorithms were found (Adj. R 2 , STD).

关键词： Regulators Machine learning algorithms Urban areas Spatial databases Vectors Reliability Socioeconomics

来源：评论

学校读者我要写书评

暂无评论

Virtual Sales Assistant: A Chrome Extension for E-commerce Websites

Virtual Sales Assistant: A Chrome Extension for E-commerce W...

引用

Advances in Computing, Communication and Networking (ICAC2N), International Conference on

作者： Naman Chheda Pradnya Saval Dept. of Computer Science and Engineering(Data Science) Dwarkadas J Sanghvi College of Engineering Mumbai India

ISBN: (数字)9798350356816

ISBN: (纸本)9798350356823

The research presents an innovative browser extension that serves as a virtual sales assistant for shoppers across e-commerce platforms. Designed to foster trust and enhance the online shopping experience, this extension enables detailed product inquiries and provides immediate access to comprehensive specifications, empowering customers to make informed purchasing decisions. By seamlessly integrating with browsing sessions and leveraging natural language processing techniques, the virtual assistant generates accurate and informative responses to product-related queries, positioning e-commerce platforms as authoritative and responsive sources. Beyond functional capabilities, the extension aims to transform user engagement by acting as a personalized guide, akin to an in-store representative, thereby heightening satisfaction through tailored service and fostering deeper customer relationships. The research is motivated by factors such as increasing customer engagement, providing round-the-clock support, facilitating product differentiation and comparison, harnessing machine learning for enhanced experiences, building trust through expert guidance, ensuring unique integration with e-commerce platforms, iterating through feedback loops for continuous improvement, and supporting small businesses in enhancing customer interactions.

关键词： Feedback loop Virtual assistants Transforms Chatbots Mobile handsets Real-time systems Browsers Electronic commerce Continuous improvement Business

来源：评论

学校读者我要写书评

暂无评论

Unified Mechanism-Specific Amplification by Subsampling and Group Privacy Amplification

arXiv

引用

arXiv 2024年

作者： Schuchardt, Jan Stoian, Mihail Kosmala, Arthur Günnemann, Stephan Dept. of Computer Science Munich Data Science Institute Technical University of Munich Germany Dept. of Engineering University of Technology Nuremberg Germany

Amplification by subsampling is one of the main primitives in machine learning with differential privacy (DP): Training a model on random batches instead of complete datasets results in stronger privacy. This is traditionally formalized via mechanism-agnostic subsampling guarantees that express the privacy parameters of a subsampled mechanism as a function of the original mechanism’s privacy parameters. We propose the first general framework for deriving mechanism-specific guarantees, which leverage additional information beyond these parameters to more tightly characterize the subsampled mechanism’s privacy. Such guarantees are of particular importance for privacy accounting, i.e., tracking privacy over multiple iterations. Overall, our framework based on conditional optimal transport lets us derive existing and novel guarantees for approximate DP, accounting with Rényi DP, and accounting with dominating pairs in a unified, principled manner. As an application, we analyze how subsampling affects the privacy of groups of multiple users. Our tight mechanism-specific bounds outperform tight mechanism-agnostic bounds and classic group privacy results. Copyright © 2024, The Authors. All rights reserved.

关键词： Differential privacy

来源：评论

学校读者我要写书评

暂无评论

A Face Pre-Processing Approach to Evade Deepfake Detector 1

A Face Pre-Processing Approach to Evade Deepfake Detector

引用

1st ACM Workshop on Security Implications of Deepfakes and Cheapfakes, WDC 2022, co-located with ACM AsiaCCS 2022

作者： Kim, Taejune Kim, Jeongho Kim, Jeonghyeon Woo, Simon S. Computer Science & Engineering Dept. Sungkyunkwan University Suwon Korea Republic of Dept. of Artificial Intelligence Sungkyunkwan University Suwon Korea Republic of Applied Data Science Dept. Sungkyunkwan University Suwon Korea Republic of

ISBN: (纸本)9781450391788

Recently, various image synthesis technologies have increased the prevalence of impersonation attacks. With the development of such technologies, damages to people such as defamation or fake news have also increased. Deepfakes have already evolved to the point, where people cannot easily distinguish fake from real. This leads to an urgent need for developing detection methods. Currently, in order to detect deepfakes, many deepfake datasets are widely used in deep neural networks. And several methods have been proposed and demonstrated to be effective in detecting deepfakes. In this work, we present pre-processing techniques such as face restoration, edge smoothing, face beautification to mitigate the artifacts of deepfakes and makes them appear more natural to humans, while lowering the deepfake detection performance. Through extensive experiments, our method can significantly lower the performance of the state-of-The-Art deepfake detectors and expose the vulnerability of deployed detectors. © 2022 ACM.

关键词： Deep neural networks

来源：评论

学校读者我要写书评

暂无评论

Indoor Navigation System for KCT Using AR Techniques

Indoor Navigation System for KCT Using AR Techniques

引用

Advancements in Electrical, Electronics, Communication, Computing and Automation (ICAECA), International Conference on

作者： Anitha P Madhav S Nishanth M V GowriShankar S Sanjai Kumar S Jaidev M V Dept. of Computer Science and Engineering Kumaraguru College of Technology Coimbatore TamilNadu Dept. of Artificial Intelligence and Data Science Kumaraguru College of Technology Coimbatore TamilNadu

ISBN: (数字)9798331525439

ISBN: (纸本)9798331525446

Moving around in confusing indoor spaces like malls, airport, campuses is very difficult if the setting is unknown. This system gives real-time turn-by-turn guidance on mobile phones using Unity with AR Foundation and NavMesh. LiDAR cameras enable accurate 3D mapping, and a GPS, Wi-Fi and Bluetooth beacon hybrid positioning system enables accurate pinpoint positioning in GPS-denied environments. The study seeks to improve user experience by simple, real-time guidance and context information as AR visualization. The system improves user disorientation and speeds up navigation speed by superimposition of directional signs over the real-world environment. Major conclusions highlight the precision and consistency of the system, specifically in vast indoor environments. The power of the system is that it can substitute conventional maps and signs to make the process of navigating seamless. Scalability and leveraging AI for smart routing and natural interaction will be addressed in subsequent work, a revolution of AR navigation technology. The study opens up a possibility for indoor navigation solutions to become more intuitive and user-centric.

关键词： Three-dimensional displays Laser radar Accuracy Indoor navigation Routing Airports Real-time systems Augmented reality Wireless fidelity Global Positioning System

来源：评论

学校读者我要写书评

暂无评论

Interactive Augmented Reality System for Real- Time Pre-Car Inspection and Maintenance Assistance

Interactive Augmented Reality System for Real- Time Pre-Car ...

引用

Advancements in Electrical, Electronics, Communication, Computing and Automation (ICAECA), International Conference on

作者： Anitha P DevaVirdha M Dinesh K Akilesh S Abishek R S Jayanitha Jayaprakash Jayadharani Dept. of Computer Science and Engineering Kumaraguru College of Technology Coimbatore TamilNadu Dept. of Artificial Intelligence and Data Science Kumaraguru College of Technology Coimbatore TamilNadu

ISBN: (数字)9798331525439

ISBN: (纸本)9798331525446

Vehicle checking along with upkeep are essential in order to assure safety as well as efficiency, but conventional examination techniques may prove to be cumbersome and need technical knowledge. In order to address this issue, an Interactive Augmented Reality (AR) System is proposed to facilitate pre-car real-time inspection and maintenance assistance. The system utilizes AR technology to monitor as well as examine numerous vehicle parts, such as the horn, dashboard lights, sunroof, cruise control, personal memory options, information display, gear system, air conditioning control, and audio control. With an interactive UI, every component is linked to a virtual button with visual and audio cues, as users receive information and instructions in real time. The system also includes comprehensive animated instructions for engine oil changes, providing accurate step-by-step guidance during required maintenance procedures on it. With the inclusion of real-time monitoring and interactive UI elements, the system enhances user understanding. Also, with audiovisual feedback, the system raises engagement, leading to better educated decisions when testing vehicles. The potential result is pretty much a streamlined inspection procedure, totally guaranteeing core vehicle systems remain in full operating condition prior to usage. This process doesn't only boost vehicle maintenance knowledge, it improves strength and performance, which makes it an effective tool for both work and personal use.

关键词： Visualization Manuals Inspection User interfaces Real-time systems User experience Maintenance Automobiles Augmented reality Automotive engineering

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：