检索结果-内蒙古大学图书馆

2025 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2025

作者： Duan, Chiming Jia, Tong Yang, Yong Liu, Guiyang Liu, Jinbu Zhang, Huxing Zhou, Qi Li, Ying Huang, Gang School of Software and Microelectronics Peking University Beijing China Institute for Artificial Intelligence Peking University Beijing China National Engineering Research Center for Software Engineering Peking University Beijing China National Key Laboratory of Data Space Technology and System Beijing China Alibaba Cloud Computing Company Hangzhou China

ISBN: (纸本)9798350368741

Logs record essential information about system operations and serve as a critical source for anomaly detection, which has generated growing research interest. Utilizing large language models (LLMs) within a retrieval-augmented generation (RAG) framework for log-based anomaly detection is an effective approach due to its strong generalization capabilities and efficient few-shot performance. However, the effectiveness of this method hinges on the quality of the knowledge source, which can be impacted by noise and changes within the software systems. Facing these problems, in this paper, we propose a novel log-based anomaly detection method named EagerLog, employing active learning to choose the logs for humans to label, thereby adding them to the knowledge source, thus enhancing the knowledge source and maintaining its quality. Our experiments on three open datasets (BGL, Thunderbird, Zookeeper) and one industrial dataset demonstrate that EagerLog can achieve 93.65% F1 score with approximately 10 labeled log sequences, surpassing existing methods by 15.32%. © 2025 IEEE.

关键词： Active Learning Anomaly Detection Log Analysis Retrieval Augmented Generation

来源：评论

学校读者我要写书评

暂无评论

SMART UI: Crop Classification in Karnataka Nippani Using Ensemble Random Forest

SMART UI: Crop Classification in Karnataka Nippani Using Ens...

引用

Advances in Computation, Communication and Information technology (ICAICCIT), International Conference on

作者： Jagarlamudi Susanth Soubraylu Sivakumar Selvanayaki Kolandapalayam Shanmugam R. Sivakumar S. S. Sridhar S. Ganesh Kumar Computing Technologies School of Computing SRM Institute of Science and Technology Kattankulathur Chennai India Mathematics and Computer Science Ashland University OH United States of America Earthquake Research Cell Civil Engineering SRM Institute of Science and Technology Kattankulathur Chennai India Data Science and Business Systems School of Computing SRM Institute of Science and Technology Kattankulathur Chennai India

ISBN: (数字)9798331541217

ISBN: (纸本)9798331541224

This study helped in enhancing agricultural management, predicting yields, tracking crop health which are all dependent on accurate crop classification. But the conventional methods are labor intensive and time consuming. The goal of this study is to automate crop classification system that uses machine learning and satellite image to accurately classify the crops. Ground Truth data is gathered from *** website and Random Forest classifier is used to train on data. To be more accurate the algorithm is verified using dataset from specific regions. The Random Forest effectively classified crops with an accuracy of $79 \%$. The outcome shows how well crop classification works when used with machine learning and satellite image together. This study provides scalable algorithm for crop classification, which helps in various agricultural related works like crop health. The future studies should investigate alternative use of real-time data for dynamic classification.

关键词： Accuracy Machine learning algorithms Heuristic algorithms Scalability Crops Real-time systems Satellite images Classification algorithms Random forests Monitoring

来源：评论

学校读者我要写书评

暂无评论

A Multi-Source Domain Generalization Network for Rotating Machinery Fault Diagnosis under Unseen Operating Conditions

A Multi-Source Domain Generalization Network for Rotating Ma...

引用

IEEE International Conference on Industrial Informatics (INDIN)

作者： Tianyu Gao Jingli Yang Weiwei Hao Xiaopeng Fan School of Electronics and Information Engineering Harbin Institute of Technology Harbin China China Institute of Marine Technology and Economy Beijing China Faculty of Computing Harbin Institute of Technology Harbin China

ISBN: (数字)9798331527471

ISBN: (纸本)9798331527488

With the rapid development or industrial intelligence, domain adaptation technology depending on the availability of the target domain has gradually become a reliable solution to address the performance degradation of fault diagnosis due to the variation of operating conditions or rotating machinery. However, the fault diagnosis scenarios under unseen operating condition are commonly confronted in practical engineering. In response to the above limitations, novel multi-source domain generalization network (MDGN) is proposed in this paper to enhance the fault diagnosis performance of rotating machinery under unseen operating conditions by decoupling the domain-relevant feature information for obtaining domain-invariant diagnosis knowledge. First, a temporal convolutional autoencoder (TCAE) is developed as a feature extraction module to fully capture the effective spatio-temporal information of the sample data. Then, a domain classification module is designed for adversarial transfer learning to facilitate the acquisition of domain-invariant features. Finally, domain divergence loss and boundary margin loss are constructed for MDGN to supervise the feature distribution, alignment among domains and feature distinction among classes. The mechanical comprehensive diagnosis simulation platform (MCDSP) bearing dataset collected in our laboratory is employed to evaluate the domain generalization performance or the proposed method. The experimental results demonstrate that the method achieves an average fault diagnosis is accuracy of 94.50%, which is better than the comparison algorithms.

关键词： Fault diagnosis Knowledge engineering Degradation Accuracy Transfer learning Feature extraction Machinery Informatics

来源：评论

学校读者我要写书评

暂无评论

System Architecture and Software Design of a Handheld High Throughput Phenotyping Device: AgRECA

System Architecture and Software Design of a Handheld High T...

引用

Applied Sensing Conference (APSCON), IEEE

作者： Kartik E. Cholachgudda Rajashekhar C. Biradar Kouame Yann Olivier Akansie Aditya A. Sannabhadti Geetha D. Devanagavi School of Electronics and Communication Engineering REVA University Bengaluru India School of Computing and Information Technology REVA University Bengaluru India

High-throughput phenotyping using imaging techniques allows for non-destructive, automated assessments of plant morphological and physiological traits. Currently, these techniques require intricate hardware and software to generate factual data. This paper presents a unique data acquisition system, AgRECA (Agricultural REsearch CAmera), with hardware and software design for high throughput phenotyping using RGB, multispectral and thermal imaging and environmental sensors; due to its compact size and ability to be used as a standalone device, it is developed and integrated into any ground-based platform or can be used handheld. The authors also propose a new data format, called NTME, containing all the information captured by AgRECA embedded into a single file.

关键词： Image sensors Software design Data acquisition Systems architecture Thermal sensors Throughput Hardware

来源：评论

学校读者我要写书评

暂无评论

Learning to Predict Short-Term Volatility with Order Flow Image Representation

arXiv

引用

arXiv 2023年

作者： Lensky, Artem Hao, Mingyu School of Engineering and Technology University of New South Wales Canberra Australia School of Computing Australian National University Canberra Australia

Introduction: The paper addresses the challenging problem of predicting the short-term realized volatility of the Bitcoin price using order flow information. The inherent stochastic nature and anti-persistence of price pose difficulties in accurate prediction. Methods: To address this, we propose a method that transforms order flow data over a fixed time interval (snapshots) into images. The order flow includes trade sizes, trade directions, and limit order book, and is mapped into image colour channels. These images are then used to train both a simple 3-layer Convolutional Neural Network (CNN) and more advanced ResNet-18 and ConvMixer, with additionally supplementing them with handcrafted features. The models are evaluated against classical GARCH, Multilayer Perceptron trained on raw data, and a naive guess method that considers current volatility as a prediction. Results: The experiments are conducted using price data from January 2021 and evaluate model performance in terms of root mean square error (RMSPE). The results show that our order flow representation with a CNN as a predictive model achieves the best performance, with an RMSPE of 0.85 ± 1.1 for the model with aggregated features and 1.0 ± 1.4 for the model without feature supplementation. ConvMixer with feature supplementation follows closely. In comparison, the RMSPE for the naive guess method was 1.4 ± 3.0. Copyright © 2023, The Authors. All rights reserved.

关键词： Commerce

来源：评论

学校读者我要写书评

暂无评论

A Survey on Cyber Attack Detection: Techniques, Datasets, and Challenge

A Survey on Cyber Attack Detection: Techniques, Datasets, an...

引用

Research Methodologies in Knowledge Management, Artificial Intelligence and Telecommunication engineering (RMKMATE), International Conference on

作者： G Geetha Manjula Rajagopal K Purna Chand Department of Computing Technologies School of Computing (Research Scholor) SRM Institute of Science and Technology Kattankulathur Tamilnadu Department of Computing Technologies School of Computing (Assistant Professor) SRM Institute of Science and Technology Kattankulathur Tamilnadu Department of Computer Science and Engineering(Data Science) (Professor) B V Raju Institute of Technology Narsapur India

Networking technology is expanded along with cyber threats. Cyber threats are the instances which adversely influences the functional operations of the system or network. It results in various issues such as illegal access, data leakage, data stolen, DDoS attacks, etc. To overcome such issues, several intrusion detection systems are implemented over the past years. Though, these intrusion detection systems exhibit several limitations while trying to achieve excellent efficiency in attack detection. In this survey, totally 50 cyber-attack detection based research works are analysed under several perspectives. The analysis is done on several IDS techniques implemented in existing works. The reviewed learning-based approaches are explained in two major categories as ML and DL approaches. Here, the ML algorithms are further classified into three types: supervised, unsupervised and reinforcement learning approaches. Moreover, the existing works are also analysed in accordance with optimization algorithms and it is classified as metaheuristic and stochastic algorithms. In which, population-based algorithms and swarm-based algorithms are the categories classified under metaheuristic algorithms. In addition, the analyses are also performed on datasets usage and cyber-attack mitigation models. Furthermore, the analysis on existing works is done on performance analysis. And it is analysed under performance of cyber-attack detection models with specific description about maximum and minimum performance attained by recent works on cyber-attack detection models. Finally, the chronological review and challenges involved in existing cyber-attack detection models are discussed.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Unconditionally optimal convergence of an energy-conserving and linearly implicit scheme for nonlinear wave equations

引用

Science China Mathematics 2022年第8期65卷 1731-1748页

作者： Waixiang Cao Dongfang Li Zhimin Zhang School of Mathematical Sciences Beijing Normal UniversityBeijing 100875China School of Mathematics and Statistics Huazhong University of Science and TechnologyWuhan 430074China Hubei Key Laboratory of Engineering Modeling and Scientific Computing Huazhong University of Science and TechnologyWuhan 430074China Beijing Computational Science Research Center Beijing 100193China Department of Mathematics Wayne State UniversityDetroitMI 48202USA

In this paper,we present and analyze an energy-conserving and linearly implicit scheme for solving the nonlinear wave *** error estimates in time and superconvergent error estimates in space are established without certain time-step *** key is to estimate directly the solution bounds in the H-norm for both the nonlinear wave equation and the corresponding fully discrete scheme,while the previous investigations rely on the temporal-spatial error splitting *** examples are presented to confirm energy-conserving properties,unconditional convergence and optimal error estimates,respectively,of the proposed fully discrete schemes.

关键词： scalar auxiliary variable wave equations stability error estimate superconvergence

来源：评论

学校读者我要写书评

暂无评论

Networked Active Suspension Control of In-Wheel Motor Driven Electric Vehicles Under Aperiodic Sampling and Transmission Delays 7th

Networked Active Suspension Control of In-Wheel Motor Driven...

引用

7th International Conference on Life System Modeling and Simulation, LSMS 2021, and 7th International Conference on Intelligent computing for Sustainable Energy and Environment, ICSEE 2021

作者： Ahmad, Iftikhar Ge, Xiaohua Han, Qing-Long Cao, Zhenwei School of Science Computing and Engineering Technologies Swinburne University of Technology HawthornVIC3122 Australia

ISBN: (纸本)9789811672095

This paper addresses the networked H∞ control problem for active suspension systems equipped with dynamic dampers. First, a networked active suspension control model of a 6-DOF half in-wheel motor driven electric vehicle is proposed to account for the effects of time-varying transmission delays, aperiodic sampling periods, and uncertain masses. Then, a delicate networked H∞ state-feedback controller is developed to guarantee the asymptotic stability as well as simultaneously preserving the expected suspension performance and H∞ disturbance attenuation performance requirements of proposed closed-loop suspension system. Finally, simulation results are provided to validate the effectiveness of the designed networked active suspension control method in both time and frequency domains. © 2021, Springer Nature Singapore Pte Ltd.

关键词： Automobile suspensions

来源：评论

学校读者我要写书评

暂无评论

Cryptographic Protocols for Securing Internet of Things (IoT) 15

Cryptographic Protocols for Securing Internet of Things (IoT...

引用

15th International Conference on computing Communication and Networking Technologies, ICCCNT 2024

作者： Manimekala, B. Aravind, T. Sounderrajan, T. Rajakumareswaran, V. Kondreddi, Krishnaveni Mohanambal, K. Christ University Department of Computer Science Yeshwanthpur Bengaluru India Vel TecRangarajanDr.Sagunthala R&d Institute of Science and Technology Department of Cse School of Computing India Erode Sengunthar Engineering College Department of Ai and Data Science Tamil Nadu Thuduppathi India Erode Sengunthar Engineering College Department of Computer Science and Design Tamil Nadu Thuduppathi India Chaitanya Bharathi Institute of Technology Electrical and Electronics Engineering Ranga Reddy Telangana Gandipet500075 India Bannariamman Institute of Technology Department of Computer Science and Engineering Sathyamangalam India

ISBN: (纸本)9798350370249

Cryptographic protocols are used to relax the ever-developing quantity of linked gadgets that make up the net of things (IoT). Those cryptographic protocols have been designed to make certain that IoT tool traffic stays cozy and personal, even while nevertheless allowing tool-to-device and cloud-to-tool communications. Examples of these protocols consist of TLS/SSL, PGP/GPG, IPsec, SSL VPN, and AES encryption. Every one of these protocols enables authentication, message integrity, and confidentiality via encryption and key trade. Moreover, a lot of these protocols are carried out in the form of diverse hardware and software answers, such as smart playing cards and gateways, to make certain that IoT traffic is secured. With the appropriate implementation of those cryptographic protocols, establishments can ensure that their IoT facts are blanketed and securely transmitted. © 2024 IEEE.

关键词： Authentication Communications Cryptographic EverDeveloping Gadgets Protocols

来源：评论

学校读者我要写书评

暂无评论

How learning evolved from offline classroom to online platforms with its amplifier, Edu-KOLs: A systematic literature review 32

How learning evolved from offline classroom to online platfo...

引用

32nd Australasian Conference on Information Systems: Information Systems for a Sustainable Future, Connectedness, and Social Good, ACIS 2021

作者： Zhang, Susan Shen, Jun Yan, Jun School of Computing & Information Technology Faculty of Engineering and Information Sciences University of Wollongong Wollongong Australia

Key Opinion Leaders (KOLs) gradually emerged on e-commerce platforms with their influencing power on global audience. E-learning platforms followed suit on drawing the influence of educational KOLs (Edu-KOLs) for perceived learning outcome, customer retention and branding. This paper presents a systematic literature review on the thematic of traditional learning and its transformation into e-learning platforms. We seek to achieve a preliminary analysis into current development and trend on educational digitalization and its effectiveness, particularly with its amplifier, Edu-KOLs who lead new waves of learning for Gen Alpha1 and beyond. This literature review summarizes terminologies on Edu-KOLs, and prudently reviews the locus of past research on e-commerce platforms with extracted KOLs’ analysis. The findings indicate a wide research gap given few research directly yielded into Edu-KOLs’ impact, whereas mounting empirical evidence for e-commerce platforms with perceived outcome through KOLs. Copyright © 2021 authors.

关键词： E-learning

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：