检索结果-内蒙古大学图书馆

4th International Conference on Sentiment Analysis and Deep Learning, ICSADL 2025

作者： Xu, Shaomei Fan, Yanling Lin, Bing Continuing Education Service Center Shandong Institute of Commerce and Technology Shandong Jinan250103 China

ISBN: (纸本)9798331523923

In intelligent systems, as the amount of data increases, how to analyse data and extract abnormal information is an important task. Based on this, in order to improve the detection efficiency and accuracy of abnormal data in intelligent systems, this study proposes a new and efficient abnormal data mining and detection algorithm. In the initial modelling process, this study introduced the minimum modification cost principle based on cross entropy for modelling. This algorithm optimizes the time series data cleaning process, thereby removing noise data while maintaining the integrity of the data sequence. Then, the extreme gradient boosting algorithm is combined with the Gaussian kernel function to achieve data dimension reduction. This operation can reduce data dimensions and feature redundancy. Finally, the overall anomaly detection operation by integrating the improved Ada boost algorithm with the sampling balance technology can improve the accuracy of the classifier while solving the problem of unbalanced data. The experimental results show that the proposed method is superior to the traditional algorithms in comprehensive indicators. © 2025 IEEE.

关键词： abnormal data detection data Mining Algorithms Efficiency Optimization Intelligent Systems

来源：评论

学校读者我要写书评

暂无评论

abnormal data detection Based on Adaptive Sliding Window and Weighted Multiscale Local Outlier Factor for Machinery Health Monitoring

引用

IEEE TRANSACTIONS ON INDUSTRIAL ELECTRONICS 2023年第11期70卷 11725-11734页

作者： Xie, Qinglin Tao, Gongquan Xie, Chenxi Wen, Zefeng Southwest Jiaotong Univ State Key Lab Tract Power Chengdu 610031 Peoples R China

Identifying abnormal data to improve data quality is of great importance for machinery health monitoring (MHM). Existing abnormal data detection methods generally depend on appropriate parameter settings and prior knowledge of data distribution, which result in relatively low adaptability to MHM data. To obtain more reliable MHM results, this article proposed a novel method to detect abnormal data. First, the concept of adaptive sliding window (ASW) is defined and the advantages of ASW in avoiding data leakage and data redundancy are derived. The ASW can optimally divide the overall data into several segments. Next, statistical factors in time- and frequency-domain are extracted from these segments to generate corresponding research objects. Then, an improved weighted multiscale local outlier factor (WMLOF) algorithm is proposed herein to evaluate the data anomaly degree of each object. The WMLOF has the ability to assess and fuse the local outlier factor characteristics at multiple scales, and eventually yields a more comprehensive WMLOF value to evaluate the anomaly degree of the MHM data. Finally, the effectiveness and superiority of the ASW and WMLOF are validated by a synthetic simulation of a faulty rolling bearing and two engineering projects pertaining to a railway vehicle gearbox, and bench test data. Comparative analysis shows that the proposed abnormal data detection method based on the ASW and WMLOF strategies outperforms five reported algorithms in outlier detection.

关键词： abnormal data detection adaptive sliding window (ASW) data quality structural health monitoring data weighted multiscale local outlier factor (WMLOF)

来源：评论

学校读者我要写书评

暂无评论

abnormal data detection Based on Dual-Factor Weighted SVDD for Multimode Batch Processes 20th

Abnormal Data Detection Based on Dual-Factor Weighted SVDD f...

引用

20th Chinese Intelligent Systems Conference

作者： Zhou, Xinjie Wang, Jianlin Wei, Qingxuan Li, Ji Sui, Enguang Xin, Wei Beijing Univ Chem Technol Beijing 100029 Peoples R China Beijing Inst Petrochem Technol Beijing 102617 Peoples R China

ISBN: (纸本)9789819786565;9789819786541;9789819786534

Current methods for detecting abnormal data in batch processes using Support Vector data Description (SVDD) overlook the varying importance of different training samples to the hypersphere. This always results in model overfitting, thereby affecting the accuracy of abnormal data detection. To address this issue, this paper proposes a dual-factor weighted SVDD (DFWSVDD) method for detecting abnormal data in multimode batch processes. First, density peak clustering is used to partition the process into different modes. On this basis, a distance calculation function for high-dimensional data samples is constructed to obtain the local density value of each sample point and calculate the relative distance of each sample to the center of its mode. By combining local density and relative distance as dual-factor weight for samples, a dual-factor weighted SVDD model is constructed to detect abnormal *** effectiveness of the proposed method is validated through experimental results from the penicillin fermentation process.

关键词： batch processes abnormal data detection support vector data description sample weighting

来源：评论

学校读者我要写书评

暂无评论

Towards trusted node selection using blockchain for crowdsourced abnormal data detection

引用

FUTURE GENERATION COMPUTER SYSTEMS-THE INTERNATIONAL JOURNAL OF ESCIENCE 2022年 133卷 320-330页

作者： He, Xin Yang, Haochen Wang, Guanghui Yu, Junyang Henan Univ Sch Software Kaifeng Peoples R China Henan Univ Henan Prov Engn Res Ctr Intelligent Data Proc Kaifeng Peoples R China Henan Univ Henan Int Joint Lab Intelligent Network Theory & Kaifeng Peoples R China

Node selection plays an important role to design and implement the crowdsourced abnormal data detection system with the purpose of completing complex tasks to meet the requirements of computing performance. Even though the blockchain-based trusted node selection approaches improve the reliability of the crowdsourcing task results, they still need to consider the crowdsourcing cost during the node selection process so as to embody a tradeoff between reliability and cost. In this paper, we propose to study the node selection problem for the crowdsourced abnormal data detection under both reliability and cost requirements. First, the working node selection is modeled as an inverse 0 - 1 knapsack problem in order to minimize the crowdsourcing cost under the budget constraints of the trustworthiness of the selected working nodes, where blockchain is used to calculate the trustworthiness of the working nodes. Then, a trusted working node selection (TWNS) algorithm is developed to select trusted working nodes with the minimum crowdsourcing cost for crowdsourced abnormal data detection, where the branch and bound method is utilized to efficiently solve the inverse 0 - 1 knapsack problem. Finally, extensive simulations are conducted based on three groups of real world datasets. The results show that the trust value evaluation is accurate by using blockchain and the TWNS algorithm can ensure the reliability of the detection result. The crowdsourcing cost is minimized in trusted working node selection process. Compared to existing approaches without considering the cost, the TWNS algorithm reduces the crowdsourcing cost by 64.6%. (C) 2022 Elsevier B.V. All rights reserved.

关键词： abnormal data detection Trusted node selection Blockchain Inverse 0-1 knapsack Crowdsourcing cost

来源：评论

学校读者我要写书评

暂无评论

abnormal data detection and Identification Method of Distribution Internet of Things Monitoring Terminal Based on Spatiotemporal Correlation

引用

ENERGIES 2022年第6期15卷 2151页

作者： Shao, Nan Chen, Yu Shandong Univ Technol Sch Elect & Elect Engn Zibo 255000 Peoples R China

As an important part of the ubiquitous power Internet of Things, the distribution Internet of Things can further improve the automation and informatization level of the distribution network. The reliability of the measurement data of the low-voltage terminal unit, as the sensing unit of the sensing layer of the distribution Internet of Things, has a great impact on the fault processing and advanced applications of the distribution Internet of Things. The self-check and the equipment working status monitoring of the main station of the low-voltage terminal unit struggle to identify the abnormality of measurement data. Aiming at this problem, an abnormal data detection and identification recognition method of a distribution Internet of Things monitoring terminal is proposed on the basis of spatiotemporal correlation. First, using the temporal correlation of monitoring terminal data, the proposed composite temporal series similarity measurement criterion is used to calculate the distance matrix between data, and the abnormal data detection is realized via combination with the improved DBSCAN algorithm. Then, using the spatial correlation of the data of the terminal unit, the geometric features of the spatial cross-correlation coefficient of the terminal nodes are extracted as the input of the cascaded fuzzy logic system to identify the abnormal source. Lastly, the effectiveness of the method is verified by a practical example.

关键词： distribution Internet of Things low-voltage terminal unit abnormal data detection density clustering fuzzy logic

来源：评论

学校读者我要写书评

暂无评论

abnormal data detection for structural health monitoring: State-of-the-art review

引用

DEVELOPMENTS IN THE BUILT ENVIRONMENT 2024年 17卷

作者： Deng, Yang Zhao, Yingjie Ju, Hanwen Yi, Ting-Hua Li, Aiqun Beijing Univ Civil Engn & Architecture Sch Civil Engn & Transportat Engn Beijing 100044 Peoples R China Minist Educ Int Joint Lab Safety & Energy Conservat Ancient Bl Beijing Peoples R China Dalian Univ Technol Sch Civil Engn Dalian Peoples R China

Structural health monitoring (SHM) is widely used to monitor and assess the condition and performance of engineering structures such as, buildings, bridges, dams, and tunnels. Owing to sensor defects, data acquisition errors, and environmental interference, abnormal data are often collected and stored in monitoring systems. The abnormal data in this study are essentially different from so-called "abnormal state data," which result from structural physical damage or performance degradation. abnormal data are totally related to the external interference rather than changes in the inherent structural features. However, abnormal data can significantly affect the performance assessment of engineering structures. It is imperative to detect and remove abnormal data from measurements to avoid misjudging structural performance in SHM. This paper summarizes abnormal data detection in the SHM field and discusses relevant challenges. Moreover, background knowledge regarding abnormal data detection is introduced. abnormal data detection methods are then classified into statistical probability methods, predictive models, and computer vision methods. The advantages, disadvantages, and scope of each method are investigated. An example of detecting abnormal monitoring data for a cable-stayed bridge is introduced. In addition, the issues of existing studies are summarized, and future study interests are discussed.

关键词： Structural health monitoring abnormal data detection Statistical probability method Predictive model Computer vision

来源：评论

学校读者我要写书评

暂无评论

A Deep Learning-Based Method for Automatic abnormal data detection: Case Study for Bridge Structural Health Monitoring

引用

INTERNATIONAL JOURNAL OF STRUCTURAL STABILITY AND DYNAMICS 2023年第11期23卷

作者： Ye, Xijun Wu, Peirong Liu, Airong Zhan, Xiaoyu Wang, Zeyu Zhao, Yinghao Guangzhou Univ Sch Civil Engn Guangzhou 510006 Peoples R China Guangzhou Univ Res Ctr Wind Engn & Engn Vibrat Guangzhou 510006 Peoples R China Shenzhen Transportat Design & Res Inst Co Ltd Shenzhen Peoples R China Tsinghua Univ Dept Civil Engn Beijing Peoples R China Guangzhou Inst Bldg Sci Grp Co Ltd Guangzhou 510440 Peoples R China South China Univ Technol Sch Civil Engn & Transportat Guangzhou 510641 Peoples R China Guangzhou Construction Engn Co Ltd Guangzhou 510030 Peoples R China

Ideally, the monitoring data collected by the Structural health monitoring (SHM) system should purely reflect the structure status. However, sensors deployed in the field can be very vulnerable to extreme conditions such as heavy rainfall, which results in large quantities of anomalous data and unavoidably leads to the inaccuracy of structural condition assessment and even false alarms. To automatically identify whether the collected data are abnormal or not, a novel deep learning-based data anomaly detection technique combining the time-frequency method and the Convolutional Neural Network (CNN) is proposed in this paper. First, the original time-series data of the SHM system were converted to the red green blue (RGB) images by using the wavelet scalograms. Subsequently, the GoogLeNet deep neural network is applied to construct a classification model by incorporating the generated 2D images. In order to evaluate the performance of the proposed technique, the SHM data (containing seven abnormal patterns) lasting for one month of a long-span cable-stayed bridge were utilized for experimental validation. The results indicate that compared with traditional deep neural network methods, the data anomaly identification accuracy can be improved by using the proposed technique. Different types of data anomaly patterns can be accurately identified, even in the case of small samples. The proposed technique exhibits good accuracy and can be integrated into advanced SHM systems with high fidelity and intelligence.

关键词： Structural health monitoring abnormal data detection wavelet transform GoogLeNet deep learning

来源：评论

学校读者我要写书评

暂无评论

Application of Change-Point Analysis to abnormal Wind Power data detection

Application of Change-Point Analysis to Abnormal Wind Power ...

引用

IEEE PES General Meeting

作者： Xu, Man Lu, Zongxiang Qiao, Ying Wang, Ningbo Zhou, Shiyuan Tsinghua Univ Dept Elect Engn Beijing 100084 Peoples R China

ISBN: (纸本)9781479964154

The abnormal data of wind power could be caused by many on-site situations, such as meteorological conditions, control strategies and communication environments, which must be detected before put into work. This paper presents data detection methods by taking the abnormal data as the change points in wind power, which means an unknown moment when there are some changes appearing to the studied system abruptly. Due to the fluctuate nature and auto-regressive features of wind power at different time scales, change-point analysis in this paper is discussed on perspectives of cumulative probability distribution, changes on regression modeling characteristics and hypothesis testing about influences brought by some special key factors. Historical data of a wind farm in western China are studied to explain and verify the proposed detection methods, which could help catch the abnormal moment or period of wind power effectively and clarify the causes of such data.

关键词： wind power abnormal data detection change point

来源：评论

学校读者我要写书评

暂无评论

Design of Online Monitoring Method for Distribution IoT Devices Based on DBSCAN Optimization Algorithm

Informatica (Slovenia)

引用

Informatica (Slovenia) 2025年第5期49卷 181-194页

作者： Hou, Chaofan Xu, Nan Liu, Siyu State Grid Beijing Electric Power Company Information and Communication Branch Beijing China

In response to the data mutation problem caused by equipment failures in the distribution Internet of Things, this study proposes a density-based clustering optimization algorithm for online monitoring of equipment data anomalies. This method considers the local and global similarity of high-dimensional measurement data and constructs a composite time series similarity measurement criterion. Improvements are made to the density-based clustering algorithm, which combines with preprocessed device historical measurement data to adaptively generate global density parameters. Through clustering training, core data points are obtained to detect abnormal changes in data. The experiment showed that compared to traditional density-based clustering algorithms, the improved algorithm had good clustering performance, with standardized mutual information and adjusted mutual information increased by about 2%. Compared to anomaly detection algorithms, the density-based clustering optimization algorithm for anomaly detection of equipment data in the distribution Internet of Things increased the detection rate by 38% and reduced the false detection rate by 65%. Therefore, the proposed online monitoring method for data anomalies can improve the data detection rate and has high practical value for the reliable operation of distribution Internet of Things systems. © 2025 Slovene Society Informatika. All rights reserved.

关键词： abnormal data detection clustering algorithm distribution internet of things parameter adaptation time correlation

来源：评论

学校读者我要写书评

暂无评论

Prediction Performance Improvement via Anomaly detection and Correction of Actual Production data in Iron Ore Sintering Process

引用

IEEE TRANSACTIONS ON INDUSTRIAL INFORMATICS 2020年第12期16卷 7602-7612页

作者： Hu, Jie Wu, Min Zhang, Pan Pedrycz, Witold China Univ Geosci Sch Automat Wuhan 430074 Peoples R China Hubei Key Lab Adv Control & Intelligent Automat C Wuhan 430074 Peoples R China Univ Alberta Dept Elect & Comp Engn Edmonton AB T6R 2V4 Canada King Abdulaziz Univ Dept Elect & Comp Engn Fac Engn Jeddah 21589 Saudi Arabia Polish Acad Sci Syst Res Inst PL-01447 Warsaw Poland

The accuracy and integrity of the actual production data influence the reliability and stability of sintering process in steel industry. However, the actual production data may encounter various outliers due to noise, sensor failure, and operator negligence existing in this process. To tackle this issue, this article develops an original framework for the detection and correction of abnormal production data in the sintering process. First, an improved kernel-based Fuzzy C-Means algorithm is developed to effectively divide normal production data under multiple operating conditions. Then, different one-class support vector machine (SVM) classifiers are constructed for different operating conditions. According to which operating condition the actual production data belongs to, the one-class SVM under this operating condition is called to accurately detect abnormal production data. Finally, the most similar normal historical data in the operating condition is obtained to correct the abnormal data by using k nearest neighbor algorithm based on the Mahalanobis distance. Simulation results involving actual production data illustrate the effectiveness of the proposed method. By taking two existing models of the sintering process as examples, their prediction performance becomes improved after detecting and correcting the abnormal production data, so that the proposed framework has important engineering application impact.

关键词： Support vector machines Anomaly detection Informatics data models Predictive models Bellows abnormal data detection actual production data iron ore sintering process kernel-based Fuzzy C-Means (KFCM) multiple operating conditions one-class support vector machine

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：