检索结果-内蒙古大学图书馆

Intelligent intrusion detection based on fuzzy big data classification

CLUSTER COMPUTING-THE JOURNAL OF NETWORKS SOFTWARE TOOLS AND APPLICATIONS 2023年第6期26卷 3719-3736页

作者： Jemili, Farah Univ Sousse MARS Res Lab ISITCom LR17ES05 Hammam Sousse 4011 Tunisia

To cope with the rapid evolution of various attacks and the computer networks' increase, an intelligent intrusion detection system is considered as a promising emerging technique for the security of computer networks. Individual classification approaches have not provided complete protection. Indeed, it has been shown that none of them is efficient enough to provide good detection rates and reduce the false alarms rates. In previous works, a comparative study was conducted between the neuro-fuzzy and the genetic-fuzzy approaches. In this study, a hybrid approach is proposed based on the stacking scheme. This approach offers a solution to combine the two basic classifiers in order to take advantage of each one of them. The experimental results have shown the effectiveness of the proposed approach in terms of maximizing the detection rates and reducing the false alarm rates.

关键词： Intrusion detection Fuzzy ensemble classifier big data classification

来源：评论

学校读者我要写书评

暂无评论

Meta-heuristic endured deep learning model for big data classification: image analytics

引用

KNOWLEDGE AND INFORMATION SYSTEMS 2023年第11期65卷 4655-4685页

作者： Naveen, P. Diwan, B. Anna Univ Dept Informat Commun & Engn Sardar Patel Rd Chennai 600025 Tamil Nadu India St Josephs Coll Engn Dept Comp Sci & Engn Chennai 600119 Tamilnadu India

Image processing is currently developing as a unique and the inventive field in computer research and applications in the modern area. Most image processing algorithms produce a large quantity of data as an outcome, which is termed as big-data. These algorithms process and store bulky information either as structured or unstructured data. The use of big data analytics to mine the data produced by image processing technology has huge potential in areas like education, governments, medical establishments, production units, finance and banking, and retail business centers. This paper well defined the innovations made in big data analytics and image processing. In this study, a novel data classification approach especially for image analytics is proposed. To improve image quality, pre-processing is applied to huge data that has been gathered. Then, most relevant features like spatial information, texture GLCM, and color and shape features are extracted from the pre-processed image. Since the dimensions of the features are huge in size, an adaptive map-reduce framework with Improved Shannon Entropy has been introduced to lessen the dimensionality of the extracted features. Then, in the big data classification phase, an optimized deep learning classifier deep convolutional neural network (DCNN) is introduced to classify the images accurately. The weight function of the DCNN is fine-tuned using the newly proposed dragonfly updated mothsearch (DAUMS) Algorithm to enhance the classification accuracy and to solve the optimization problems of the research work. The moth search algorithm and dragonfly algorithm are both concepts in this hybrid algorithm DAUMS.

关键词： Image processing big data big data classification DCNN DAUMS

来源：评论

学校读者我要写书评

暂无评论

SSPO-DQN spark: shuffled student psychology optimization based deep Q network with spark architecture for big data classification

引用

WIRELESS NETWORKS 2023年第1期29卷 369-385页

作者： Kantapalli, Bhaskar Markapudi, Babu Rao Jawaharlal Nehru Technol Univ Kakinada Dept Comp Sci & Engn Kakinada Andhra Pradesh India Sheshadri Rao Gudlavalleru Engn Coll Dept Comp Sci & Engn Gudlavalleru 521356 Andhra Pradesh India

In information analysis and systematic extraction of complex or huge dataset, big data plays a vital role. The massive growth of large-scale data causes a major issue in big data and hence it is required to classify the big data to solve data imbalance issues. The huge data can be explored in an efficient way by converting it into valuable knowledge and this data can be processed in the distributed environment with different application framework. In recent decades, spark framework gained more significance in big data domain due to its increasing achievement in incremental and iterative approaches. Due to imbalance of data distribution, big data classification with large sized dataset results a challenging task with the conventional methods as it leads wrong decision in generating classification result. In this paper, an efficient Shuffled Student Psychology Optimization_Deep Q network is proposed for big data classification with spark framework in order to overcome the issues faced by the traditional methods. Here, master and slave sets are used to perform unique operations, like data partitioning, feature fusion and data augmentation process in order to accomplish the task of data classification by proposed approach. The developed technique attained the maximum TPR of 0.960, accuracy of 0.942, and TNR of 0.929.

关键词： big data classification data augmentation Spark framework Deep residual network Deep Q network

来源：评论

学校读者我要写书评

暂无评论

big data classification with optimization driven MapReduce framework

引用

INTERNATIONAL JOURNAL OF KNOWLEDGE-BASED AND INTELLIGENT ENGINEERING SYSTEMS 2021年第2期25卷 173-183页

作者： Mohammed, Mujeeb Shaik Rachapudy, Praveen Sam Kasa, Madhavi Jawaharlal Nehru Technol Univ Anantapur Dept CSE Ananthapuramu Andhra Pradesh India G Pulla Reddy Engn Coll Kurnool India JNTUA Coll Engn Dept CSE Ananthapuramu Andhra Pradesh India

With the technical advances, the amount of big data is increasing day-by-day such that the traditional software tools face burden in handling them. Additionally, the presence of the imbalance data in the big data is a huge concern to the research industry. In order to assure the effective management of big data and to deal with the imbalanced data, this paper proposes a new optimization algorithm. Here, the big data classification is performed using the MapReduce framework, wherein the map and reduce functions are based on the proposed optimization algorithm. The optimization algorithm is named as Exponential Bat algorithm (E-Bat), which is the integration of the Exponential Weighted Moving Average (EWMA) and Bat Algorithm (BA). The function of map function is to select the features that are presented to the classification in the reducer module using the Neural Network (NN). Thus, the classification of big data is performed using the proposed E-Bat algorithm-based MapReduce Framework and the experimentation is performed using four standard databases, such as Breast cancer, Hepatitis, Pima Indian diabetes dataset, and Heart disease dataset. From, the experimental results, it can be shown that the proposed method acquired a maximal accuracy of 0.8829 and True Positive Rate (TPR) of 0.9090, respectively.

关键词： MapReduce framework big data classification EWMA BA NN

来源：评论

学校读者我要写书评

暂无评论

Rider Chicken Optimization Algorithm-Based Recurrent Neural Network for big data classification in Spark Architecture

引用

COMPUTER JOURNAL 2022年第8期65卷 2183-2196页

作者： Vinoth, R. Ananth, J. P. Agni Coll Technol Dept Informat Technol Omr Chennai 600130 India Sri Krishna Coll Engn & Technol Dept Comp Sci & Engn Coimbatore 641008 Tamil Nadu India

This paper proposes an effective classification method named Rider Chicken Optimization Algorithm-based Recurrent Neural Network (RCOA-based RNN) to perform big data classification in spark architecture. Initially, the input data are collected from the network by the master node and then forwarded to the slave node. These nodes are responsible for storing the data and performing computations. The features are effectively selected in the slave node using the proposed RCOA. The selected features are forwarded to the master node. The big data classification is achieved in the master node by using the RNN classifier, and the training of the classifier is done using the proposed RCOA algorithm, which is the integration of the Rider optimization algorithm (ROA) with the standard Chicken Swarm Optimization (CSO). The experimentation is done by using the Switzerland dataset, Cleveland dataset, Hungarian dataset and Skin disease dataset, in which the proposed RCOA-based RNN attained better performance based on the quantitative properties, such as sensitivity, accuracy and specificity with the values of 9.3E+01%, 9.4E+01% and 9.3E+01% using Hungarian dataset. The existing learning methods failed to address the complex classification problems at a reasonable time, which is overcome by the proposed method.

关键词： Recurrent neural network (RNN) Rider optimization algorithm (ROA) Chicken Swarm Optimization (CSO) big data classification fictional computing

来源：评论

学校读者我要写书评

暂无评论

Ant Cat Swarm Optimization-Enabled Deep Recurrent Neural Network for big data classification Based on Map Reduce Framework

引用

COMPUTER JOURNAL 2022年第12期65卷 3167-3180页

作者： Narayana, Satyala Chandanapalli, Suresh Babu Rao, Mekala Srinivasa Srinivas, Kalyanapu Seshadri Rao Gudlavalleru Engn Coll Dept Comp Sci & Engn Gudlavalleru 521356 Andhra Pradesh India Lakireddy Bali Reddy Coll Engn Dept Informat Technol Mylavaram 521230 Andhra Pradesh India

The amount of data generated is increasing day by day due to the development in remote sensors, and thus it needs concern to increase the accuracy in the classification of the big data. Many classification methods are in practice;however, they limit due to many reasons like its nature for data loss, time complexity, efficiency and accuracy. This paper proposes an effective and optimal data classification approach using the proposed Ant Cat Swarm Optimization-enabled Deep Recurrent Neural Network (ACSO-enabled Deep RNN) by Map Reduce framework, which is the incorporation of Ant Lion Optimization approach and the Cat Swarm Optimization technique. To process feature selection and big data classification, Map Reduce framework is used. The feature selection is performed using Pearson correlation-based Black hole entropy fuzzy clustering. The classification in reducer part is performed using Deep RNN that is trained using a developed ACSO scheme. It classifies the big data based on the reduced dimension features to produce a satisfactory result. The proposed ACSO-based Deep RNN showed improved results with maximal specificity of 0.884, highest accuracy of 0.893, maximal sensitivity of 0.900 and the maximum threat score of 0.827 based on the Cleveland dataset.

关键词： Map Reduce framework big data classification deep recurrent neural network Pearson correlation-based Black hole entropy fuzzy clustering Ant Lion Optimization algorithm

来源：评论

学校读者我要写书评

暂无评论

Improved cost-sensitive representation of data for solving the imbalanced big data classification problem

引用

JOURNAL OF big data 2022年第1期9卷 1-24页

作者： Fattahi, Mahboubeh Moattar, Mohammad Hossein Forghani, Yahya Islamic Azad Univ Dept Comp Engn Mashhad Branch Mashhad Razavi Khorasan Iran

Dimension reduction is a preprocessing step in machine learning for eliminating undesirable features and increasing learning accuracy. In order to reduce the redundant features, there are data representation methods, each of which has its own advantages. On the other hand, big data with imbalanced classes is one of the most important issues in pattern recognition and machine learning. In this paper, a method is proposed in the form of a cost-sensitive optimization problem which implements the process of selecting and extracting the features simultaneously. The feature extraction phase is based on reducing error and maintaining geometric relationships between data by solving a manifold learning optimization problem. In the feature selection phase, the cost-sensitive optimization problem is adopted based on minimizing the upper limit of the generalization error. Finally, the optimization problem which is constituted from the above two problems is solved by adding a cost-sensitive term to create a balance between classes without manipulating the data. To evaluate the results of the feature reduction, the multi-class linear SVM classifier is used on the reduced data. The proposed method is compared with some other approaches on 21 datasets from the UCI learning repository, microarrays and high-dimensional datasets, as well as imbalanced datasets from the KEEL repository. The results indicate the significant efficiency of the proposed method compared to some similar approaches.

关键词： Feature selection Feature extraction Imbalanced data big data classification Cost sensitive Optimization

来源：评论

学校读者我要写书评

暂无评论

Water atom search algorithm-based deep recurrent neural network for the big data classification based on spark architecture

引用

INTERNATIONAL JOURNAL OF MACHINE LEARNING AND CYBERNETICS 2022年第8期13卷 2297-2312页

作者： Dabbu, Murali Karuppusamy, Loheswaran Pulugu, Dileep Vootla, Subba Ramaiah Reddyvari, Venkateswar Reddy CMR Coll Engn & Technol Comp Sci & Engn Medchal Rd Hyderabad 501401 India Malla Reddy Coll Engn & Technol Comp Sci & Engn Hyderabad 500100 Telangana India Mahatma Gandhi Inst Technol Comp Sci & Engn Hyderabad Telangana India

The innovation of big data has an intense impact on data context analytics. The big data processing platforms have gained immense popularity in evaluating big data as they offer low latency needed for big data applications. This paper introduces a novel method for big data classification using spark architecture that follows master-slave nodes. The input data is initially partitioned by data griding in the master node using Black Hole Entropy Fuzzy Clustering (BHEFC). Then, the feature selection is executed for each slave node based on Renyi entropy for choosing better features for further processing. Finally, the features selected from each slave node are concatenated together to form the feature vector. Consequently, obtained features from the slave node are passed to the classification module in the master node for performing the classification of big data. In this case, classification is carried out using the Deep Recurrent Neural network (DeepRNN), tuned by the novel Water Atom Search Optimization (WASO). The WASO is newly designed by integrating the Water Wave Optimization (WWO) algorithm and Atom Search Optimization (ASO) characteristics. Thus, the proposed WASO-based DeepRNN method effectively classifies big data using reduced dimension features to produce satisfactory results. Therefore, the output of developed WASO enabled DeepRNN is employed for big data classification. The proposed method is compared with Neural Network (NN), Support Vector Machine (SVM), Edited Nearest Neighbor for big data (ENN-BD), Speed-up Dendritic Cell Algorithm (Sp-DCA), Compact Fuzzy Models in big data (CFM-BD), and DeepRNN. The proposed method obtained improved results with a high specificity of 0.979, accuracy of 0.951, sensitivity of 0.963, and precision of 0.988 based on the skin disease dataset.

关键词： big data classification Deep recurrent neural network Renyi entropy Black hole entropy fuzzy clustering Water wave optimization

来源：评论

学校读者我要写书评

暂无评论

An Integration of Archerfish Hunter Spotted Hyena Optimization and Improved ELM Classifier for Multicollinear big data classification Tasks

引用

NEURAL PROCESSING LETTERS 2022年第3期54卷 2049-2077页

作者： Chidambaram, S. Gowthul Alam, M. M. Natl Engn Coll Dept Informat Technol Kovilpatti India Presidency Univ Dept Comp Sci & Engn Bengaluru India

big data mining has emerged as an active field of interest, and traditional data mining approaches frequently fail to handle the complexities associated with massive datasets. One of the most extensively used strategies for big data classification is MapReduce, which combines the map and reduce processes. For filtering and sorting, the mapping approach is employed, and the reduction technique is used to combine the final classification results. A novel Archerfish Hunter Spotted Hyena Optimization-based Improved Extreme Learning Machine (AHSHO-IELM) classifier-based MapReduce framework is proposed in this paper for big data classification. The IELM algorithm is formed by integrating the ELM technique with Principal Component Analysis to overcome the multicollinear problem and enhance the training and testing time. The AHSHO method combines the archerfish hunter optimization and Spotted Hyena Optimization algorithms to improve the optimal parameter selection of the IELM classifier, which increases classification accuracy and reduces the error rate. The performance of the proposed AHSHO-IELM classifier-based MapReduce framework is evaluated using different performance metrics such as Accuracy, Sensitivity, Specificity, Computational time, F1-Score, Mathews correlation coefficient, and scale-up factor. For the rotten tomatoes movie review dataset and the Dermatology dataset, the proposed approach yields accuracy, specificity, and sensitivity values of 99%, 99%, 98.3%, and 99.3%, 99%, 98%, respectively for a mapper value (X) of 5. The proposed big data classifier is effective for both single-class and multi-class classification, according to the results of the analysis.

关键词： big data classification Improved extreme learning machine Principal component analysis Archerfish Hunter Optimization Map Reduce technique Spotted hyena optimization

来源：评论

学校读者我要写书评

暂无评论

Hyper-heuristic salp swarm optimization of multi-kernel support vector machines for big data classification

引用

International Journal of Information Technology (Singapore) 2023年第2期15卷 651-663页

作者： Ali, Issa Mohammed Saeed Hariprasad, D. Sri Ramakrishna College of Arts and Science Coimbatore India

big data classification is a challenging assignment for the knowledge processing of relevant information in various domains. Many advanced machine learning (ML) and metaheuristic algorithms have been introduced to provide effective big data classification. Support vector machine (SVM) has been the extensively utilized ML algorithm for data classification problems due to its higher capability and simplicity. However, for big data problems, the SVM classifier suffers from high computational time, which can be resolved through optimal feature subset selection and effective tuning of the SVM kernels and other parameters. This paper develops a novel, advanced classification model by an optimized multi-kernel SVM (MKSVM) classifier in which the parameters are tuned using hyper-heuristic salp swarm optimization (HHSSO). Initially, an improved optimization algorithm named Population and Global Search Improved Squirrel Search Algorithm (PGS-ISSA) was used to obtain the most informative features to train the HHSSO-MKSVM classifier. Then the proposed HHSSO-MKSVM is utilized to classify the big data based on the selected features. The novelty of the HHSSO algorithm is integrating the hyper-heuristic framework with the standard salp swarm optimization (SSO) to select the best kernel function and the optimal values of the margin parameter and the kernel parameters of MKSVM. This model uses four kernel functions: linear, Polynomial, Gaussian, and radial basis function (RBF). HHSSO chooses the best kernel for each dataset based on accuracy and model complexity as objective parameters. This optimized model of HHSSO-MKSVM is implemented in MATLAB and evaluated on benchmark datasets. The results showed that the proposed HHSSO-MKSVM model had provided a better solution to the big data classification problem with high accuracy and less computational time. © 2023, The Author(s), under exclusive licence to Bharati Vidyapeeth's Institute of Computer Applications and Management.

关键词： big data classification Feature selection Higgs data High dimensional data Hyper-heuristic salp swarm optimization Improved squirrel search algorithm MATLAB Multi-kernel 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：