检索结果-内蒙古大学图书馆

The Usage of Template Mining in Log File classification

IEEE ACCESS 2024年 12卷 96378-96386页

作者： Marjai, Peter Kiss, Attila Eotvos Lorand Univ Dept Informat Syst H-1117 Budapest Hungary J Selye Univ Dept Informat Komarno 94501 Slovakia

The continuing growth of large-scale and complex software systems has led to growing interest in examining the possibilities of using the log files that were created during the runtime of the software. These files can be used for various purposes like error prediction, performance evaluation, learning of usage patterns, improving reliability, and so on. With software systems continuously becoming more and more complicated, the distinction of log files that were generated by different components of the software becomes a new task. The classification of log files is important for several reasons like resource optimization, compliance and auditing, automation and analysis, or understanding the general system health. By classifying log files, organizations can better understand the health and performance of their systems. They can identify patterns, potential security threats, anomalies, errors, and malicious behaviors and storage can also be optimized. In the log files, each line represents a specific event that has occurred. Such events can be identified with the use of template miners that assign a unique ID for each event. In our paper, instead of using the full-sized log files, we change each line to its corresponding event ID and use the resulting smaller file for classification purposes. We use numerous classifying algorithms like Random Forest, K-NN, Ada Boost Classifier, and Decision Tree to assign the files to groups corresponding to their origin types. 75% of the data is used for learning purposes while the remaining 25% is used for testing. We conduct numerous different experiments to verify the effectiveness of our method like evaluating the precision, recall, f-score, and accuracy values and measuring the time it takes to classify the files. Our results yielded that while there is a small fallback in the case of the performance of some of the investigated methods used with the proposed algorithm, it takes significantly less time to classify the log files,

关键词： classification algorithms Task analysis Security Random forests Monitoring Machine learning algorithms Decision trees Document handling Document classification log file template miner

来源：评论

学校读者我要写书评

暂无评论

MGNR: A Multi-Granularity Neighbor Relationship and Its Application in KNN classification and Clustering Methods

引用

IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE 2024年第12期46卷 7956-7972页

作者： Xie, Jiang Xiang, Xuexin Xia, Shuyin Jiang, Lian Wang, Guoyin Gao, Xinbo Chongqing Univ Telecommun & Posts Chongqing Key Lab Computat Intelligence Chongqing 400065 Peoples R China

In the real world, data distributions often exhibit multiple granularities. However, the majority of existing neighbor-based machine-learning methods rely on manually setting a single-granularity for neighbor relationships. These methods typically handle each data point using a single-granularity approach, which severely affects their accuracy and efficiency. This paper adopts a dual-pronged approach: it constructs a multi-granularity representation of the data using the granular-ball computing model, thereby boosting the algorithm's time efficiency. It leverages the multi-granularity representation of the data to create tailored, multi-granularity neighborhood relationships for different task scenarios, resulting in improved algorithmic accuracy. The experimental results convincingly demonstrate that the proposed multi-granularity neighbor relationship effectively enhances KNN classification and clustering methods.

关键词： Computational modeling Data models Clustering methods Machine learning Clustering algorithms classification algorithms Task analysis Clustering granular-ball computing KNN multi-granularity neighbor relationship

来源：评论

学校读者我要写书评

暂无评论

Pedestrian Dead Reckoning Based on Complex Motion Mode Recognition Using Hierarchical classification

引用

IEEE SENSORS JOURNAL 2024年第4期24卷 4935-4947页

作者： Niu, Ze Cong, Li Qin, Honglei Cao, Shuo Beihang Univ Sch Elect Informat Engn Beijing 100083 Peoples R China Beijing Inst Control & Elect Technol Beijing 100038 Peoples R China

The pedestrian positioning algorithm based on inertial measurement unit (IMU) has been widely applied in scenarios such as firefighting and counterterrorism where global navigation satellite system (GNSS) performance is limited. However, most existing systems do not take into account crawling-type motions. Additionally, the zero velocity update error constraint method often used in pedestrian navigation is not applicable to crawling-type motions. As a result, errors introduced by crawling-type motions become the primary source of error in complex motion scenarios. In order to enhance pedestrian positioning accuracy during complex motion modes, this study analyzed data across various motion modes and developed specific positioning algorithms based on a hierarchical classification. First, we observe that data patterns for standing mode and crawling-type mode are distinct based on the analysis of motion mode. Therefore, to improve step detection accuracy, support vector machine (SVM) is employed to classify motion modes into three coarse categories: standing mode (forward/lateral/backward walking, and running), crawling mode (baby/military crawling), and one side crawling mode (one side military crawling). Specific step detection algorithms are designed for each category. Furthermore, the step lengths of standing motions and crawling-type motions exhibit relatively strong correlations with data characteristics and height, respectively. Hence, different step length models are designed. Fine classification of motion modes is accomplished using the minimally random convolutional kernel transform (MINIROCKET), optimizing step length model parameters and heading correction for various fine motion modes. Finally, precise position estimation is achieved. Experimental results demonstrate that this algorithm exhibits stronger adaptability and superior performance in complex motion scenarios.

关键词： Legged locomotion classification algorithms Pedestrians Sensors Estimation Support vector machines Location awareness Complex motion modes crawling hierarchical classification pedestrian dead reckoning (PDR)

来源：评论

学校读者我要写书评

暂无评论

DTCM: Deep Transformer Capsule Mutual Distillation for Multivariate Time Series classification

引用

IEEE TRANSACTIONS ON COGNITIVE AND DEVELOPMENTAL SYSTEMS 2024年第4期16卷 1445-1461页

作者： Xiao, Zhiwen Xu, Xin Xing, Huanlai Zhao, Bowen Wang, Xinhan Song, Fuhong Qu, Rong Feng, Li Southwest Jiaotong Univ Sch Comp & Artificial Intelligence Chengdu Peoples R China Southwest Jiaotong Univ Tangshan Inst Tangshan 063000 Peoples R China Minist Educ Engn Res Ctr Sustainable Urban Intelligent Transpo Chengdu 611756 Peoples R China China Univ Min & Technol Sch Comp Sci & Technol Xuzhou 221166 Peoples R China Guizhou Univ Finance & Econ Sch Informat Guiyang 550025 Peoples R China Univ Nottingham Sch Comp Sci Nottingham NG7 2RD England

This article proposes a dual-network-based feature extractor, perceptive capsule network (PCapN), for multivariate time series classification (MTSC), including a local feature network (LFN) and a global relation network (GRN). The LFN has two heads (i.e., Head_A and Head_B), each containing two squash convolutional neural network (CNN) blocks and one dynamic routing block to extract the local features from the data and mine the connections among them. The GRN consists of two capsule-based transformer blocks and one dynamic routing block to capture the global patterns of each variable and correlate the useful information of multiple variables. Unfortunately, it is difficult to directly deploy PCapN on mobile devices due to its strict requirement for computing resources. So, this article designs a lightweight capsule network (LCapN) to mimic the cumbersome PCapN. To promote knowledge transfer from PCapN to LCapN, this article proposes a deep transformer capsule mutual (DTCM) distillation method. It is targeted and offline, using one- and two-way operations to supervise the knowledge distillation (KD) process for the dual-network-based student and teacher models. Experimental results show that the proposed PCapN and DTCM achieve excellent performance on University of East Anglia 2018 (UEA2018) datasets regarding top-1 accuracy.

关键词： Feature extraction classification algorithms Time series analysis Data mining Transformers Routing Knowledge transfer Capsule network data mining deep learning knowledge distillation (KD) multivariate time series classification (MTSC) mutual learning

来源：评论

学校读者我要写书评

暂无评论

Fake News classification Methodology With Enhanced BERT

引用

IEEE ACCESS 2024年 12卷 164491-164502页

作者： Oad, Ammar Farooq, Muhammad Hamza Zafar, Amna Akram, Beenish Ayesha Zhou, Ruogu Dong, Feng Shaoyang Univ Fac Informat Engn Shaoyang 422000 Peoples R China Univ Engn & Technol Lahore UET Lahore Natl Ctr Artificial Intelligence KICS Lahore Pakistan Univ Engn & Technol Lahore Dept Comp Sci Lahore 54890 Pakistan Univ Engn & Technol Dept Comp Engn Lahore 54890 Pakistan Hunan Vocat Coll Commerce Changsha 410205 Peoples R China

News serves as a vital source of information for staying updated on various aspects of life worldwide. However, massive volume of information available on social media platforms makes it challenging to extract meaningful insights. Additionally, dispersion of false information has grown broader, often serving specific agendas. In this work, we present a novel fake news classification methodology based on an enhanced BERT deep learning model which is trained on self-developed PolitiTweet datasets along with benchmarked Buzzfeed dataset. The PolitiTweet dataset is augmented to solve class imbalance problem and improve data diversity to capture regional language nuances, cultural references that help in more accurate detection of fake news. For this purpose, We enhance BERTbase model by adding 3 additional layers namely Linear Layer, Dropout Layer, Activation Layer and fine tuned the model to train enhanced BERT classifier. The fine tuned BERT model trained on augmented dataset is capable of capturing patterns and nuances within the data, giving better classification results. Subsequently, the enhanced BERT model is evaluated against BERTbase model for further elaboration on the generalisibility and effective performance of the fine tuned model for real-world cases. The enhanced BERT model achieved an accuracy of 85% on Buzzfeed and 98% on PolitiTweet. In comparison the baseline BERT models achieved an average accuracy of 81% and 88%, respectively. The proposed Enhanced BERT model uses a mix of pre-training strategies with fine-tuning techniques to achieve better performance. The developed research data is available online at: https://***/datasets/ameerhamza123/pak-tweets.

关键词： Fake news Accuracy Social networking (online) Support vector machines Long short term memory Encoding Bidirectional control Cultural differences classification algorithms Transformers Bidirectional encoder representations from transformers (BERT) natural language processing transformers fake news classification gradient boosting classifier machine learning (ML) deep learning (DL) large language model (LLM)

来源：评论

学校读者我要写书评

暂无评论

classification and prediction-based data mining algorithms to predict visitors to the museum

Classification and prediction-based data mining algorithms t...

引用

algorithms, Computing and Machine Learning (CACML), Asia Conference on

作者： Yingrui Chi Jiaran Zhang International School of Advanced Studies University of Camerino Ascoli Piceno Italy

ISBN: (数字)9798331543143

ISBN: (纸本)9798331543150

The perception that museums are often perceived as disconnected from everyday life has resulted in a notable reluctance among a substantial segment of the population to visit these institutions. To enhance visitor attendance, it is essential to conduct an analysis of social survey databases. The objective of this study is to identify potential museum visitors within a given population and to predict their likelihood of visiting through the application of a data mining model utilizing classification algorithms. The dataset employed in this research was sourced from the "2021 China General Social Survey." We implemented five classification algorithms using the opensource software WEKA to classify and predict the dataset, specifically Naive Bayes, Logistic, J48, Random Trees, and KStar. Among these algorithms, the J48 classification method yielded the highest accuracy in predicting potential visitors, achieving a success rate of 78.7012%. The findings suggest that lifestyle habits and individual preferences play a significant role in determining the frequency of museum visits. This study demonstrates the effectiveness of classification and prediction algorithms in the context of museum visitor research and proposes several promising avenues for future investigation.

关键词： Surveys Accuracy Computational modeling Software algorithms Prediction algorithms Museums Data models classification algorithms Data mining Standards

来源：评论

学校读者我要写书评

暂无评论

Enhanced Image-Based Malware classification Using Snake Optimization Algorithm With Deep Convolutional Neural Network

引用

IEEE ACCESS 2024年 12卷 95047-95057页

作者： Duraibi, Salahaldeen Jazan Univ Coll Engn & Comp Sci Jazan 45142 Saudi Arabia

Malware is a malicious software intended to cause damage to computer systems. In recent times, significant proliferation of malware utilized for illegal and malicious goals has been recorded. Several machine and deep learning methods are widely used for the detection and classification of malwares. Image-based malware detection includes the usage of machine learning and computer vision models for analyzing the visual representation of malware, including binary images or screenshots, for the purpose of detecting malicious behaviors. This techniques provides the potential to identify previously hidden or polymorphic malware variants based on the visual features, which provide a further layer of defense against emerging cyber-attacks. This study introduces a new Snake Optimization Algorithm with Deep Convolutional Neural Network for Image-Based Malware classification technique. The primary intention of the proposed technique is to apply a hyperparameter-tuned deep learning method for identifying and classifying malware images. Primarily, the ShuffleNet method is mainly used to derivate the feature vectors. Besides, the snake optimization algorithm can be deployed to boost the choice of hyperparameters for the ShuffleNet algorithm. For the recognition and classification of malware images, attention-based bi-directional long short-term memory model. The simulation evaluation of the proposed algorithm has been examined using the Malimg malware dataset. The experimental values inferred that the proposed methodology achieves promising performance with a maximum accuracy of 98.42% compared to existing models.

关键词： Malware classification algorithms Feature extraction Convolutional neural networks Computer architecture Computational modeling Optimization Deep learning Malware detection Snake Optimization Algorithm deep learning ShuffleNet convolutional neural network

来源：评论

学校读者我要写书评

暂无评论

An Attention-Based Feature Processing Method for Cross-Domain Hyperspectral Image classification

引用

IEEE SIGNAL PROCESSING LETTERS 2025年 32卷 196-200页

作者： Wang, Yazhen Liu, Guojun Yang, Lixia Liu, Junmin Wei, Lili Ningxia Univ Sch Math & Stat Yinchuan 750021 Ningxia Peoples R China Xi An Jiao Tong Univ Sch Math & Stat Xian 710049 Peoples R China

Cross-domain classification of hyperspectral remote sensing images is one of the hotspots of research in recent years, and its main problem is insufficient training samples. To address this issue, few-shot learning (FSL) has emerged as a promising paradigm in cross-domain classification tasks. However, a notable limitation of most existing FSL methods is that they focus only on local information and less on the critical role of global information. Based on this, this paper proposes a new feature processing method with adaptive band selection, which takes into account the global nature of image features. Firstly, adaptive band analysis is performed in the target domain, and threshold analysis is used to determine the number of selected bands. Secondly, a band selection method is employed to select representative bands from the spectral bands of the high-dimensional data according to the determined band count. Finally, the weights of the selected bands are analyzed, fully considering the importance of pixel weight, and then the results are used as inputs for the classification model. The experimental results on various datasets show that this method can effectively improve the classification accuracy and generalization ability. Meanwhile, the results of the objective accuracy index of the proposed method in different databases improved by 3.9%, 4.7% and 5.4%.

关键词： Support vector machines Hyperspectral imaging Attention mechanisms Accuracy Signal processing algorithms Image classification classification algorithms Visualization Training Sensors Adaptive analysis attention mechanism band selection hyperspectral image classification

来源：评论

学校读者我要写书评

暂无评论

Feature Subset Selection for High-Dimensional, Low Sampling Size Data classification Using Ensemble Feature Selection With a Wrapper-Based Search

引用

IEEE ACCESS 2024年 12卷 62341-62357页

作者： Mandal, Ashis Kumar Nadim, MD. Saha, Hasi Sultana, Tangina Hossain, Md. Delowar Huh, Eui-Nam Univ Saskatchewan Dept Comp Sci Saskatoon SK S7N 5A2 Canada Hajee Mohammad Danesh Sci & Technol Univ Dept Comp Sci & Engn Dinajpur 5200 Bangladesh Hajee Mohammad Danesh Sci & Technol Univ Dept Elect & Commun Engn Dinajpur 5200 Bangladesh Kyung Hee Univ Dept Comp Sci & Engn Yongin 17104 South Korea

The identification of suitable feature subsets from High-Dimensional Low-Sample-Size (HDLSS) data is of paramount importance because this dataset often contains numerous redundant and irrelevant features, leading to poor classification performance. However, the selection of an optimal feature subset from a vast feature space creates a significant computational challenge. In the domain of HDLSS data, conventional feature selection methods often face challenges in achieving a balance between reducing the number of features and preserving high classification accuracy. Addressing these issues, the study introduces an effective framework that employs a filter and wrapper-based strategy specifically designed to address the classification challenges inherent in HDLSS data. The framework adopts a multi-step approach where ensemble feature selection integrates five filter ranking approaches: Chi-square ( chi(2) ), Gini index (GI), F-score, Mutual Information (MI), and Symmetric uncertainty (SU) to identify the top-ranking features. In the subsequent stage, a wrapper-based search method is utilized, which employs the Differential Evaluation (DE) metaheuristic algorithm as the search strategy. The fitness of feature subsets during this search is assessed based on a weighted combination of the error rate of the Support Vector Machine (SVM) classifier and the ratio of feature cardinality. The datasets, after undergoing dimensionality reduction, are then utilized to construct classification models using SVM, K-Nearest Neighbors (KNN), and Logistic Regression (LR). The approach was evaluated on 13 HDLSS datasets to assess its efficacy in selecting appropriate feature subsets and improving classification Accuracy (ACC) analog with Area Under the Curve (AUC). Results show that the proposed ensemble with wrapper-based approach produces a smaller number of features (ranging between 2 and 9 for all datasets), while maintaining a commendable average AUC and ACC (between 98% and 100%). T

关键词： Feature extraction Support vector machines Metaheuristics Search problems Filtering algorithms Information filters classification algorithms classification differential evaluation feature selection filter approach HDLSS data wrapper approach

来源：评论

学校读者我要写书评

暂无评论

Infrared Image classification and Detection Algorithm for Power Equipment Based on Improved YOLOv10

引用

IEEE ACCESS 2024年 12卷 184976-184988页

作者： Ji, Xiu Yue, Zheyu Yang, Hongliu Zhang, Zehong Changchun Inst Technol Natl Local Joint Engn Res Ctr Smart Distribut Grid Changchun 130000 Peoples R China State Grid Tonghua Power Supply Co Tonghua 134000 Jilin Peoples R China

Real-time target detection has important applications in industry. Identifying the type of power equipment in massive infrared image data for heat fault diagnosis has emerged as a crucial issue that needs to be addressed in this field. However, infrared imaging technology has shortcomings such as poor signal clarity and serious background noise interference. To address this problem, this paper proposes an infrared image classification and detection algorithm for power equipment based on the improved YOLOv10, named YOLOv10plus. Firstly, a lightweight convolution technique (GSConv) is implemented within the central network system to maximize the retention of target features. Secondly, a Slim Neck design structure is used in the neck network and combined with a dual convolution module (DualConv) to achieve a lightweight model. Finally, a Multi Cavity Channel Refiner (MDCR) module is implemented at the foundational level of the network to enhance the target feature recognition. To better handle the imbalance in sample distribution, the original Binary Cross-Entropy (BCE) loss function is modified to incorporate Focal Loss, aiming to enhance model performance by focusing more on hard-to-classify examples. The experimental findings indicate that the enhanced model achieves a substantial improvement in detection performance on power equipment infrared image data. Its FPS value reaches 588 and mAP value reaches 85.3%, which are 361 and 13.3% higher than the original model, respectively.

关键词： Feature extraction Convolution Accuracy Computational modeling YOLO Convolutional neural networks Real-time systems Infrared imaging classification algorithms Neck Infrared imaging of power equipment improvement of YOLOv10 Slim Neck-GSConv MDCR

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：