检索结果-内蒙古大学图书馆

Effect of Text Augmentation and Adversarial Training on Fake News Detection

IEEE TRANSACTIONS ON COMPUTATIONAL SOCIAL SYSTEMS 2024年第4期11卷 4775-4789页

作者： Ahmed, Hadeer Traore, Issa Saad, Sherif Mamun, Mohammad Univ Victoria Dept Elect & Comp Engn Victoria BC V8P 5C2 Canada Univ Windsor Sch Comp Sci Windsor ON N9B 3P4 Canada Natl Res Council Canada Fredericton NB E3B 9W4 Canada

The action of spreading false information through fake news articles presents a significant danger to society because it has the ability to shape public opinion with inaccurate facts. This can lead to negative effects, such as reduced trust in institutions and the promotion of conflict, division, and even violence. In this article, a text augmentation technique is introduced as a means of generating new data from preexisting fake news datasets. This approach has the potential to enhance classifier performance by a range of 3%-11%. It can also be utilized to launch a successful attack on trained classifiers, with up to a 90% success rate. However, the success rate of these attacks decreased to less than 28% when the model was retrained with the generated adversarial examples. These results demonstrate the effectiveness of text augmentation as a viable method for detecting fake news and increasing classifier accuracy and performance, as well as its ability to be utilized to perform adversarial machine learning (ML) and improve the resilience of ML algorithms.

关键词： Abstract meaning representation (AMR) adversarial training clonal selection algorithm cyberattack fake news graph representation text generation

来源：评论

学校读者我要写书评

暂无评论

A Hybridization of CSA DEA Approach for Detection of Multiple Transverse Crack Rotor Shaft Rotating in Fluid Environment under Axial and Bending Loading

引用

MECHANICS OF SOLIDS 2024年第4期59卷 2100-2126页

作者： Yadao, Adik Mishra, Kundan G H Raisoni Coll Engn & Management Pune 412207 Maharashtra India MIT Acad Engn Sch Mech Engn Pune India

Rotor shaft cracks can be acknowledged as a substantial issue regulating the reliable and safe machines operation. When the crack has grown and is not discovered, unexpected catastrophe may happen, ultimately resulting the plant being shut down with numerous losses attached. When the rotor shaft is revolving in a viscous fluid environment, it becomes exceedingly challenging to analyze the size and position of the crack. In the present research work, a novel hybridized technique a clonal selection algorithm (CSA) with a differential evolution algorithm (DEA) is proposed for early detection of multiple transverse cracks and its position in the rotor shaft rotating under altered viscous fluid environment in an acceptable amount of time limit. Relative natural frequency at x-axis, relative natural frequency at y-axis, relative amplitude of vibration at x-axis, relative amplitude at y-axis and viscosity of fluid are use as input parameter and relative crack depth and crack location are used as a output parameter in the hybrid technique. To compute the amplitude and natural frequency of the cracked rotor shaft rotating under different fluid environment utilizing the stiffness matrices of crack element. An external force of fluid is computed by Navier-Stokes equation. Theoretical evaluation was executed using Matlab. To authenticate the theoretical and experimental value of natural frequency and amplitude, perform the finite element analysis by using ANSYS. For training the hybrid system, the amplitude and natural frequencies are found out using theoretical, experimental and finite element analysis for different crack depth and positions. The test results of the recommended hybrid technique are compared with finite element analysis and experimental analysis for validation, and satisfactory outcomes have been observed. Therefore the recommended hybridized CSA-DEA technique would establish an effective tool for real-time crack detection in rotor.

关键词： rotor dynamics vibration signature crack depth crack location finite element analysis clonal selection algorithm differential evolution algorithm hybrid CSA-DEA

来源：评论

学校读者我要写书评

暂无评论

Multi-Layer Perceptron Training Optimization Using Nature Inspired Computing

引用

IEEE ACCESS 2022年 10卷 36963-36977页

作者： Al Bataineh, Ali Kaur, Devinder Jalali, Seyed Mohammad J. Norwich Univ Dept Elect & Comp Engn Northfield VT 05663 USA Univ Toledo Dept Elect Engn & Comp Sci Toledo OH 43606 USA Deakin Univ Inst Intelligent Syst Res & Innovat Burwood Vic 3125 Australia

Although the multi-layer perceptron (MLP) neural networks provide a lot of flexibility and have proven useful and reliable in a wide range of classification and regression problems, they still have limitations. One of the most common is associated with the optimization algorithm used to train them. The most commonly used training method is stochastic gradient descent with backpropagation (or backpropagation for short) because it is mathematically tractable (given that the activation functions are differentiable). However, backpropagation is not guaranteed to find the globally optimal set of weights and biases. As a result, the MLP is often incapable of obtaining a desirable solution to the problem. clonal selection algorithms (CSA) are optimization procedures that effectively explore a complex and large space to find values near the global optimum. Consequently, CSA can be used to solve the problem of training MLP networks. This paper presents a novel implementation of CSA for training MLP architectures to solve real-world problems such as breast cancer diagnosis, active sonar target classification, wheat classification, and flower classification. The CSA is used to find the optimal weights and biases that will significantly increase the classification accuracy of the MLP. The performance of our proposed approach is compared with other popular training methods: genetic algorithm (GA), ant colony optimization (ACO), particle swarm optimization (PSO), Harris hawks optimization (HHO), moth-flame optimization (MFO), flower pollination algorithm (FPA), and backpropagation (BP). The comparison is benchmarked using five classification datasets: Iris Flower, Sonar, Wheat Seeds, Breast Cancer Wisconsin, and Haberman's Survival. Comparative study results illustrate the improvements in MLP performance gained by using CSA over other training methods, and hence it can be considered a competitive approach to training MLP networks when solving real-world applications in various di

关键词： Optimization Training Immune system Classification algorithms Backpropagation Artificial intelligence Computational modeling Breast cancer clonal selection algorithm multi-layer perceptron nature inspired computing neural networks optimization sonar target classification

来源：评论

学校读者我要写书评

暂无评论

Assessing hypermutation operators of a clonal selection algorithm for the unequal area facility layout problem

引用

ENGINEERING OPTIMIZATION 2013年第3期45卷 375-395页

作者： Ulutas, Berna Haktanirlar Kulturel-Konak, Sadan Eskisehir Osmangazi Univ Dept Ind Engn Meselik Eskisehir Turkey Penn State Berks Management Informat Syst Reading PA USA

A mutation operator is critical for the performance of a clonal selection algorithm (CSA) since it diversifies the search directions and avoids early convergence to local optima. This article introduces a CSA approach for the unequal area facility layout problem (UAFLP) with flexible bay structure. A new encoding, the use of mutation types with different combinations, and different static and dynamic mutation application strategies are also proposed. In addition, a guideline in parameter optimization of the CSA is provided. An experimental study is performed on five cases of the UAFLP. It is concluded that the hypermutation types studied in this article, especially the inverse mutation followed by pairwise mutation, can be used to obtain good results within short computation times.

关键词： clonal selection algorithm flexible bay structure hypermutation operators unequal area facility layout problem

来源：评论

学校读者我要写书评

暂无评论

Integrated parameter inversion analysis method of a CFRD based on multi-output support vector machines and the clonal selection algorithm

引用

COMPUTERS AND GEOTECHNICS 2013年 47卷 68-77页

作者： Zheng, Dongjian Cheng, Lin Bao, Tengfei Lv, Beibei Hohai Univ State Key Lab Hydrol Water Resources & Hydraul En Nanjing 210098 Jiangsu Peoples R China Hohai Univ Natl Engn Res Ctr Water Resources Efficient Utili Nanjing 210098 Jiangsu Peoples R China Hohai Univ Coll Water Conservancy & Hydropower Nanjing 210098 Jiangsu Peoples R China

A geotechnical parameter identification method based on multi-output support vector machines (M-SVMs) and the clonal selection algorithm (CSA) is proposed. Using this method, the rockfill material parameters of a concrete-faced rockfill dam (CFRD) are identified. Based on the Taguchi design, some possible combinations of material parameters are generated within the admissible ranges of material parameters. Then, using these combinations, the displacement of all the observation points of the CFRD is calculated using the finite element method (FEM). Next, different combinations of material parameters are used as input, and the calculated displacement is used as output to train some M-SVM models to simulate the complex relationship between the material parameters and the dam displacement. Integrated inversion analysis, which takes the static and creep properties of rockfill material into account simultaneously, is implemented to achieve a comprehensive understanding of the mechanical properties of the rockfill material. The optimization problem corresponding to the integrated inversion analysis is solved by the CSA, which has global convergence and is robust. During the process of searching for optimal material parameters, the dam displacement is calculated by the M-SVM mapping instead of the FEM, which may greatly reduce the computation time. Based on the observed settlement and finite element model of the CFRD, the inversion analysis method described above is implemented. The results indicate that the parameter identification method for rock-fill material proposed in this article is accurate, has a fast convergence rate and can be applied in practical engineering applications. (C) 2012 Elsevier Ltd. All rights reserved.

关键词： Concrete-faced rockfill dam Multi-output support vector machines clonal selection algorithm Integrated inversion analysis

来源：评论

学校读者我要写书评

暂无评论

Directed clonal selection algorithm for associative classification

引用

INTERNATIONAL JOURNAL OF MODELLING IDENTIFICATION AND CONTROL 2013年第3期18卷 218-225页

作者： Zhao, Lihua Pan, Jin Xidian Univ Minist Educ Key Lab Intelligent Percept & Image Understanding Xian 710106 Shaanxi Peoples R China Xian Commun Inst Xian 710106 Shaanxi Peoples R China

In this paper, we present an directed clonal selection algorithm (DclonalG) for mining association rules. Different from the traditional evolutionary algorithms, DclonalG firstly scans dataset one time to find frequent rules with only one item. Then, these items were used to generate new rules and the mutation operation was limited in it. We evaluate the performance of the proposed DclonalG approach for AC and the performance results have shown that the proposed approach is efficient in dealing with the problem on the complexity of the rule search space. At the same time, good classification accuracy has been achieved. This is especially important for mining association rules from large datasets in which the search space of rules is huge.

关键词： clonal selection algorithm clonalG artificial immune system AIS associative classification AC evolutionary computations

来源：评论

学校读者我要写书评

暂无评论

Convergence of Elitist clonal selection algorithm Based on Martingale Theory

引用

ENGINEERING LETTERS 2013年第4期21卷 181-184页

作者： Hong, Lu Kamruzzaman, Joarder Huaihai Inst Technol Sch Elect Engn Lianyungang 222005 Jiangsu Peoples R China Monash Univ Gippsland Sch Informat Technol Churchill Vic 3842 Australia

In recent years, progress has been made in the analysis of global convergence of clonal selection algorithms (CSA), but most analyses are based on the theory of Markov chain, which depend on the description of the transition matrix and eigenvalues. However, such analyses are very complicated, especially when the population size is large, and are presented for particular implementations of CSA. In this paper, instead of the traditional Markov chain theory, we introduce martingale theory to prove the convergence of a class of CSA, called elitist clonal selection algorithm (ECSA). Using the submartingale convergence theorem, the best individual affinity evolutionary sequence is described as a submartingale, and the almost everywhere convergence of ECSA is derived. Particularly, the algorithm is proved convergent with probability 1 in finite steps when the state space of population is finite. This new proof of global convergence analysis of ECSA is more simplified and effective, and not implementation specific.

关键词： clonal selection algorithm Elitist strategy Martingale theory Almost everywhere convergence

来源：评论

学校读者我要写书评

暂无评论

Immunocomputing-Based Approach for Optimizing the Topologies of LSTM Networks

引用

IEEE ACCESS 2021年 9卷 78993-79004页

作者： Al Bataineh, Ali Kaur, Devinder Univ Toledo Elect Engn & Comp Sci Dept Toledo OH 43606 USA

This paper aims to automatically design optimal LSTM topologies using the clonal selection algorithm (CSA) to solve text classification tasks such as sentiment analysis and SMS spam classification. Designing optimal topologies involves determining the best configuration of hyperparameters that will give the best performance. The current state-of-the-art LSTM topologies are often designed using trial and error approaches which are incredibly time-consuming and require domain experts. Our proposed method, referred to as CSA-LSTM, is evaluated using the Large Movie Review Dataset (IMDB). Furthermore, to verify the robustness of the hyperparameters discovered by CSA for the IMDB dataset, we have used them for the other datasets, viz. the Twitter US Airline Sentiment and the SMS Spam Collection. Additionally, the discovered hyperparameters for the LSTM are combined with pre-determined convolutional neural network (CNN) layers to achieve the same or better results to fast the training time and fewer trainable parameters. For further verification and evaluation of the generalization ability and effectiveness of the proposed approach, it is compared with four machine learning algorithms widely used for text classification tasks: (1) random forest (RF), (2) logistic regression (LR), (3) support vector machine (SVM), and (4) multinomial naive Bayes (NB). The results of our experiments show that the LSTM topologies automatically designed by our CSA method are less expensive, reusable and outperform the machine learning algorithms and other models in the literature evaluated on the same three datasets. Through our proposed method, LSTM's best topology can be self-determined without any human intervention, making CSA-based algorithms a promising approach to automatically design optimal LSTM topologies that provide the best performance for a given task.

关键词： Topology Logic gates Network topology Deep learning Genetic algorithms Training Task analysis clonal selection algorithm deep learning hyperparameters optimization IMDB immunocomputing long short-term memory

来源：评论

学校读者我要写书评

暂无评论

A clonal selection algorithm with Levenshtein Distance based Image Similarity in Multidimensional Subjective Tourist Information and Discovery of Cryptic Spots by Interactive GHSOM

A Clonal Selection Algorithm with Levenshtein Distance based...

引用

IEEE International Conference on Systems, Man, and Cybernetics (SMC)

作者： Ichimura, Takumi Kamada, Shin Prefectural Univ Hiroshima Fac Management & Informat Syst Minami Ku 1-1-71 Ujina Higashi Hiroshima 7348559 Japan Prefectural Univ Hiroshima Grad Sch Comprehens Sci Res Minami Ku Hiroshima 7348559 Japan

ISBN: (纸本)9781479906529

Mobile Phone based Participatory Sensing (MPPS) system involves a community of users sending personal information and participating in autonomous sensing through their mobile phones. Sensed data can also be obtained from external sensing devices that can communicate wirelessly to the phone. Our developed tourist subjective data collection system with Android smartphone can determine the filtering rules to provide the important information of sightseeing spot. The rules are automatically generated by Interactive Growing Hierarchical SOM. However, the filtering rules related to photograph were not generated, because the extraction of the specified characteristics from images cannot be realized. We propose the effective method of the Levenshtein distance to deduce the spatial proximity of image viewpoints and thus determine the specified pattern in which images should be processed. To verify the proposed method, some experiments to classify the subjective data with images are executed by Interactive GHSOM and clonal selection algorithm with Immunological Memory Cells in this paper.

关键词： Levenshtein Distance clonal selection algorithm Image Analysis Immunological Memory Cells Growing Hierarchical SOM Interactive GHSOM Smartphone based Participatory Sensing System Tourist Informatics Knowledge Discovery

来源：评论

学校读者我要写书评

暂无评论

PATH PLANNING FOR MOBILE ROBOT WITH clonal selection algorithm

PATH PLANNING FOR MOBILE ROBOT WITH CLONAL SELECTION ALGORIT...

引用

2nd International Conference on Civil Engineering and Transportation (ICCET 2012)

作者： Li, Yi Song, Zhen-Hui Zhao, Li ShiJiaZhuang Vocat Technol Inst Shijiazhuang 050000 Peoples R China

ISBN: (纸本)9783037855652

Aiming at the problem of path planning for a mobile robot, an oriented clonal selection algorithm is proposed. Firstly, the static environment was expressed by a map with nodes and links. Secondly, the locations of target and obstacles were defined. Thirdly, an oriented mutation operator was used to accelerate the evolutionary progress. In this way, we can find an optimal solution with proposed oriented clonal algorithm. Experiment results demonstrate that the algorithm is simple, effective, to solve the problem of robot path planning in a static environment.

关键词： Mobile robot Path planning clonal selection algorithm

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：