检索结果-内蒙古大学图书馆

International Conference on Software engineering (ICSE)

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

ISBN: (数字)9798331505691

ISBN: (纸本)9798331505707

Accurately diagnosing the fault that causes the failure is crucial for maintaining the reliability of a microservice system after a failure occurs. Mainstream fault diagnosis approaches are data-driven and mainly rely on three modalities of runtime data: traces, logs, and metrics. Diagnosing faults with multiple modalities of data in microservice systems has been a clear trend in recent years because different types of faults and corresponding failures tend to manifest in data of various modalities. Accurately diagnosing faults by fully leveraging multiple modalities of data is confronted with two challenges: 1) how to minimize information loss when extracting features for data of each modality; 2) how to correctly capture and utilize the relationships among data of different modalities. To address these challenges, we propose FAMOS, a Fault diagnosis Approach for MicrOservice Systems through effective multi-modal data fusion. On the one hand, FAMOS employs independent feature extractors to preserve the intrinsic features for each modality. On the other hand, FAMOS introduces a new Gaussian-attention mechanism to accurately correlate data of different modalities and then captures the inter-modality relationship with a crossattention mechanism. We evaluated FAMOS on two datasets constructed by injecting comprehensive and abundant faults into an open-source microservice system and a real-world industrial microservice system. Experimental results demonstrate the FAMOS's effectiveness in fault diagnosis, achieving significant improvements in F1 scores compared to state-of-the-art (SOTA) methods, with an increase of 20.33 %.

关键词： Fault diagnosis Measurement Hands Runtime Semantics Microservice architectures data integration Feature extraction Market research data mining

来源：评论

学校读者我要写书评

暂无评论

Implementation of Mining Frequent Patterns on big data Using new Version of Algorithm 1

Implementation of Mining Frequent Patterns on big data Using...

引用

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

作者： Prashanth, M.V. Shambhubhardwaj Raju, Ramana Pramanik, Kundan Kumar Mohanty, Swaroop Barua, Kuntal Vidyavardhaka College of Engineering Information Science and Engineering India Teer Thanker Mahaveer University Faculty of Engineering Department of Computing Sciences & IT Uttar Pradesh Moradabad India Department of Data Science & Mathematics Bangalore India ARKA Jain University Department of School of Engg. &iT Jharkhand Jamshedpur India Management Cv Raman Global University Bhubaneswar India SAGE University Madhya Pradesh Indore India

ISBN: (纸本)9781665456876

Pattern analysis is one of the most important tasks for strong data and useful data from unstructured data. The item-sets for this work must include the aforementioned homogeneity, but rather frequency in the data. Despite the fact that numerous efficient algorithms have been developed in this field, the rising demand for information has led to deterioration in the effectiveness of present pattern mining techniques. The goal of this study is to provide fresh, efficient methods for mining huge data patterns. To accomplish this, a variety of methods based on the Map reduction algorithm as well as the Apache expansive implementation have been proposed. The recommended algorithms may be divided into three main groups. The Attribute Mapper (AprioriMR) and recurrent AprioriMR techniques, which eliminate any previous objects in data without employing a pruning methodology, are the first two described. Second, two recommended approaches (space cutting AprioriMR or top AprioriMR) to improve the search space leverage certain well-generalized pro property. The last approach for mining compressed versions of frequent patterns is the maximum AprioriMR algorithm. To evaluate the efficacy of the offered strategies, up to 3 1018 interactions and more than 5 million distinct ones have been examined in a range of big data datasets. Evaluations of well-known and efficient pattern mining algorithms are part of the testing process. The results show both the benefit of employing Dremel versions when taking into consideration intricate issues and the insufficiency of this strategy when dealing with little amounts of data. © 2022 IEEE.

关键词： Deterioration

来源：评论

学校读者我要写书评

暂无评论

EagerLog: Active Learning Enhanced Retrieval Augmented Generation for Log-based Anomaly Detection

EagerLog: Active Learning Enhanced Retrieval Augmented Gener...

引用

International Conference on Acoustics, Speech, and Signal Processing (ICASSP)

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

ISBN: (数字)9798350368741

ISBN: (纸本)9798350368758

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%.

关键词： Training Industries Systems operation Large language models Retrieval augmented generation Active learning Noise Software systems Speech processing Anomaly detection

来源：评论

学校读者我要写书评

暂无评论

A Novel Approach for Driver Drowsiness Detection using Deep Neural Networks

A Novel Approach for Driver Drowsiness Detection using Deep ...

引用

Women in Innovation, Technology & Entrepreneurship (ICWITE), IEEE International Conference for

作者： Sharon K V Natarajan B P. Madhumitha A Dhanamathi Prabu S S Saranya Dept. of Computer Science and Engineering Amrita School of Computing Amrita Vishwa Vidyapeetham Chennai India School of Computer Science and Engineering VIT University Chennai Tamilnadu India Dept. of Artificial Intell. and Data Science Panimalar Engineering College Chennai India Department of Computer Science and Engineering Roever Engineering College Perambalur Tamilnadu India Dept. of CSE K. Ramakrishnan College of Engineering Tiruchirappalli Tamil Nadu India

One major problem that contributes to many traffic accidents that cause injuries and fatalities all over the world is drowsy driving. This research introduces the novel approach for detecting driver drowsiness using deep networks and computer vision techniques aims to solve this issue and improve road safety. The Proposed system employs an InceptionV3-based Convolutional Neural Network (CNN) model to precisely determine whether the driver’s eyes are open or closed. A sizable dataset of eye images taken in actual driving situations is used to train the CNN model. Whenever the indicators of drowsiness are detected, the proposed system will identify them in real time and promptly notify the driver. The proposed model not only has strong real-time capabilities but also exhibits superior accuracy based on stringent evaluation metrics, which makes a significant contribution to efforts aimed at promoting road safety. The performance and adaptability of the system are improved and further integrates alarm activation for drowsiness detection in a variety of driving conditions.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Predicting Academic Performance of Students Using Modified Decision Tree based Genetic Algorithm

Predicting Academic Performance of Students Using Modified D...

引用

data Science and Information System (ICDSIS), IEEE International Conference on

作者： Harikumar Nagarajan Zaid Alsalami Shweta Dhareshwar K. Sandhya Punitha Palanisamy Global Data Mart Inc (GDM) New Jersey USA Department of Computers Techniques Engineering College of Technical Engineering The Islamic University Najaf Iraq Department of MCA Nitte Meenakshi Institute of Technology Bengaluru India Dept. of CSE(AI&ML) School of Computing Mohan Babu University Tirupati India Department of Artificial Intelligent and Data Science Tagore Institute of Engineering & Technology Deviyakurichi Salem India

ISBN: (数字)9798350381665

ISBN: (纸本)9798350381672

Students’ academic performance prediction has been a significant area of research in educational data mining, in which machine learning (ML) techniques are used to examine data from educational institutions. The research project uses supervised machine learning techniques to forecast students’ grades and marks. The purpose of this study is to investigate the standard of learning as it relates to the objectives of sustainability. The system has produced a large amount of data, which must be carefully examined in order to extract the most important information for planned and future development. One well-known and useful use in the EDM is the forecasting of students’ grades and marks based on their prior educational records. It turns into a fantastic source of information that can be used in a variety of ways to raise the national education level. The regression framework and Decision Tree (DT)-classifier are trained using the labeled academic history data of the student (30 optimal characteristics). In order to maximize the decision tree algorithm’s output, the research proposes a modified version of the method that uses a Genetic Algorithm (GA) to assess students’ academic achievement. The outcomes demonstrate the effectiveness and relevance of the improved decision tree method for more straightforward and accurate student performance prediction.

关键词： Accuracy Education Machine learning Predictive models Prediction algorithms Classification algorithms History

来源：评论

学校读者我要写书评

暂无评论

Enhancing the Long-Term Sustainability of Healthcare data Optimization Through Deep Federated Learning

Enhancing the Long-Term Sustainability of Healthcare Data Op...

引用

IEEE International Conference on Intelligent Techniques in Control, Optimization and Signal Processing (INCOS)

作者： Balraj Kumar Munni Evin Haewon Byeon M. Sivaprakash P. Maria Sheeba Sunil J School of Computer Application Lovely Professional University Phagwara Punjab India School of Engineering and Computing American International University Kuwait Department of AI-Big Data College of AI Convergence Inje University Gimhae Republic of Korea Department of Mechanical Engineering Stella Mary's College of Engineering Tamil Nadu India Department of Electronics and Communication Engineering St. Mother Theresa Engineering College Thoothukudi India Annai Vailankanni College of Engineering Kanyakumari Tamil Nadu India

ISBN: (数字)9798350361186

ISBN: (纸本)9798350361193

The medical industry regards the prevention and detection of skin diseases as a top priority. The number of people suffering from skin diseases is increasing faster than ever before due to increased levels of pollution and poor diet. Although it's not the major priority, having bad skin makes us less certain. Regularly inspecting your skin is an important step in identifying any degenerative or early changes in your skin that could lead to skin disease. Machine learning algorithms can be utilized to create robust models that can categorize a wide range of skin conditions. First, the skin and non-skin must be distinguished in order to identify skin conditions. In order to determine the unambiguous a group of skin conditions A selection of five distinct machine learning algorithms has been employed to compile a dataset of skin infections. These algorithms include Kernel Self- pattern, Random Forest, Naive Bayes, Logistic Regression, and CNN, among others. A comparable investigation based on training accuracy and skepticism matrix criterion has been carried out and illustrated with graphs. It has been determined that, of all the applicants, CNN offers the highest level of training accuracy for the appropriate assumption of skin disorders.

关键词： Training Machine learning algorithms Pollution Signal processing algorithms Signal processing Skin Sustainable development

来源：评论

学校读者我要写书评

暂无评论

Blockchain-assisted Puncturable Signcryption for Cloud and Fog-Hosted Industrial Cyber-Physical Systems

引用

IEEE Network 2025年

作者： Ma, Qingru Shen, Jian Pandi, Vijayakumar Gupta, Brij B. Arya, Varsha Mahalinghum, Maheswari Zhejiang Sci-Tech University School of Computer Science and Technology School of Artificial Intelligence Hangzhou310018 China Zhejiang Sci-Tech University School of Information Science and Engineering School of Cyber Science and Technology Zhejiang Key Laboratory of Digital Fashion and Data Governance Zhejiang Provincial International Cooperation Base for Science and Technology on Cloud Computing Security and Data Aggregation Hangzhou310018 China Department of Computer Science and Engineering Tamil Nadu Tiruchirappalli620009 India Asia University Department of Computer Science and Information Engineering Taichung413 Taiwan China Medical University Hospital China Medical University Department of Medical Research Taichung Taiwan Pune412115 India School of Cybersecurity Korea University Seoul Korea Republic of Kyung Hee University Seoul02447 Korea Republic of Lebanese American University Beirut1102 Lebanon Center for Interdisciplinary Research Dehradun India Sathyabama Institute of Science and Technology School of Computing Department of Computer Science and Engineering Tamil Nadu Chennai India

The widespread adoption of emerging technologies, such as interconnected sensors and advanced automation systems, has led to rapid advancements in smart industrial environments. While industrial cyber-physical systems (ICPSs) bring efficiency and innovation to industrial processes, the security risks are also of great concern. The existing work provides many methods for data security and authentication for ICPSs. However, since the authentication status of ICPSs is changeable, the up-to-date methods can hardly meet the requirements for rapid authentication and secure data transmission. What’s more, largescale message revocation incurs significant communication and computational costs. This paper proposes a blockchain-assisted identity-based puncturable signcryption (BC-IBPSC) scheme for cloud and fog-hosted ICPSs. First, based on the concepts of puncturable encryption and signature, a novel identity-based puncturable signcryption method is presented to achieve efficient verifiable data encryption. Second, the blockchain is utilized to record all valid and punctured messages, to achieve evidence storage and traceability. The results of the analysis indicate that the scheme ensures security and operates efficiently. In addition, experiments show that the size of the signcrypted files does not affect the value of Gas consumption on the blockchain when uploading proofs. © 2025 IEEE. All rights reserved.

关键词： Authentication

来源：评论

学校读者我要写书评

暂无评论

Timing-Driven High-Level Synthesis for Continuous-Flow Microfluidic Biochips

Timing-Driven High-Level Synthesis for Continuous-Flow Micro...

引用

IEEE International Symposium on Quality Electronic Design

作者： Zhengyang Ye Zhisheng Chen Youlin Pan Genggeng Liu Wenzhong Guo Tsung-Yi Ho Xing Huang College of Computer and Data Science Fuzhou University Fuzhou China Engineering Research Center of Big Data Intelligence Ministry of Education Fuzhou China Fujian Key Laboratory of Network Computing and Intelligent Information Processing Fuzhou University Fuzhou China School of Informatics Xiamen University Xiamen China Department of Computer Science and Engineering The Chinese University of Hong Kong Hong Kong China School of Computer Science Northwestern Polytechnical University Xi’an China

ISBN: (数字)9798350309270

ISBN: (纸本)9798350309287

As continuous-flow microfluidic biochips technology rapidly advances, its automated synthesis methods require adapting to increasingly complex and stringent biochemical applications. In particular, with the introduction of time-sensitive bioassays, in this work, we present a timing-driven high-level synthesis method to optimize the resource efficiency of bioassays considering the time constraints. Specifically, we investigate the existing forms of time constraints and propose a corresponding flexible modeling approach based on reaction-control which can achieve downward compatibility for physical design. Additionally, we also analyze the impact of storage and wash on time constraints. The experimental results show that our method achieves efficient execution and low devices cost while satisfying time constraints.

关键词： Costs Biochips Time factors Microfluidics Physical design

来源：评论

学校读者我要写书评

暂无评论

Task-Aware Dynamic Transformer for Efficient Arbitrary-Scale Image Super-Resolution

arXiv

引用

arXiv 2024年

作者： Xu, Tianyi Zhou, Yijie Hu, Xiaotao Zhang, Kai Zhang, Anran Qiu, Xingye Xu, Jun School of Statistics and Data Science Nankai University Tianjin China College of Computer Science Nankai University Tianjin China School of Intelligence Science and Technology Nanjing University Suzhou China Tencent Data Platform Beijing China Zhejiang University Hangzhou China Systems Engineering Research Institute China State Shipbuilding Corporation Limited Beijing China Guangdong Provincial Key Laboratory of Big Data Computing The Chinese University of Hong Kong Shenzhen China

Arbitrary-scale super-resolution (ASSR) aims to learn a single model for image super-resolution at arbitrary magnifying scales. Existing ASSR networks typically comprise an off-the-shelf scale-agnostic feature extractor and an arbitrary scale upsampler. These feature extractors often use fixed network architectures to address different ASSR inference tasks, each of which is characterized by an input image and an upsampling scale. However, this overlooks the difficulty variance of super-resolution on different inference scenarios, where simple images or small SR scales could be resolved with less computational effort than difficult images or large SR scales. To tackle this difficulty variability, in this paper, we propose a Task-Aware Dynamic Transformer (TADT) as an input-adaptive feature extractor for efficient image ASSR. Our TADT consists of a multi-scale feature extraction backbone built upon groups of Multi-Scale Transformer Blocks (MSTBs) and a Task-Aware Routing Controller (TARC). The TARC predicts the inference paths within feature extraction backbone, specifically selecting MSTBs based on the input images and SR scales. The prediction of inference path is guided by a new loss function to trade-off the SR accuracy and efficiency. Experiments demonstrate that, when working with three popular arbitrary-scale upsamplers, our TADT achieves state-of-the-art ASSR performance when compared with mainstream feature extractors, but with relatively fewer computational costs. The code will be publicly released. © 2024, CC BY.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Decay Regularized Stochastic Configuration Networks with Multi-Level data Processing for Uav Battery Rul Prediction

SSRN

引用

SSRN 2024年

作者： Liao, Zihao Li, Shaobo Li, Qian Li, Shengping State Key Laboratory of Public Big Data Guizhou University Guizhou Guiyang550025 China Guizhou lnstitute of Technology Guizhou Guiyang550003 China School of Electrical Engineering Computing and Mathematical Sciences Curtin University Perth Australia School of Design and the Built Environment Curtin University Perth Australia

A precise and durable health management strategy for battery power systems is crucial to maintaining the reliable operation of Unmanned Aerial Vehicles(UAVs).This paper introduces an adaptive Decay Regularized Stochastic Configuration Networks(DRSCN) with Multi-level data processing for UAVs Battery Remaining Useful Life(RUL) Prediction. Firstly, a Multi source Signal Enhancement Analysis Framework (MSEAF) is effectively presented to criticalbattery health indicators from complex signals. Moreover, a significant innovation is enhancing the SCN model’s output layer, which introduces Decay Regularization to sparsify the layer’s weights, significantly reducing the risk of overfitting in later prediction stages. To further re fine and optimize DRSCN, a Convex Lens and Dual-Mechanism Enhanced Sand Cat Swarm Optimization (CLDM-SCSO) algorithm is employed for precise hyperparameter tuning, fur ther improving prediction accuracy. Finally, extensive control and ablation experiments on the NASA HIRF battery dataset validate the framework’s superior prediction accuracy and relia bility over existing methods, offering an efficient and reliable UAV battery health monitoring solution. © 2024, The Authors. All rights reserved.

关键词： Forecasting

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：