检索结果-内蒙古大学图书馆

Enhanced autoencoder-based fraud detection: a novel approach with noise factor encoding and SMOTE

KNOWLEDGE AND INFORMATION SYSTEMS 2024年第1期66卷 635-652页

作者： Cakir, Mert Yilmaz Sirin, Yahya Istanbul Sabahattin Zaim Univ Comp Sci & Engn TR-34303 Istanbul Turkiye

Fraud detection is a critical task across various domains, requiring accurate identification of fraudulent activities within vast arrays of transactional data. The significant challenges in effectively detecting fraud stem from the inherent class imbalance between normal and fraudulent instances. To address this issue, we propose a novel approach that combines autoencoder-based noise factor encoding (NFE) with the synthetic minority oversampling technique (SMOTE). Our study evaluates the efficacy of this approach using three datasets with severe class imbalance. We compare three autoencoder variants-autoencoder (AE), variational autoencoder (VAE), and contractive autoencoder (CAE)-enhanced by the NFE technique. This technique involves training autoencoder models on real fraud data with an added noise factor during the encoding process, followed by combining this altered data with genuine fraud data. Subsequently, SMOTE is employed for oversampling. Through extensive experimentation, we assess various evaluation metrics. Our results demonstrate the superiority of the autoencoder-based NFE approach over the use of traditional oversampling methods like SMOTE alone. Specifically, the AE-NFE method outperforms other techniques in most cases, although the VAE-NFE and CAE-NFE methods also exhibit promising results in specific scenarios. This study highlights the effectiveness of leveraging autoencoder-based NFE and SMOTE for fraud detection. By addressing class imbalance and enhancing the performance of fraud detection models, our approach enables more accurate identification and prevention of fraudulent activities in real-world applications.

关键词： Fraud detection Noise factor encoding autoencoder Variational autoencoder Contractive autoencoder SMOTE

来源：评论

学校读者我要写书评

暂无评论

A Debiasing autoencoder for Recommender System

引用

IEEE TRANSACTIONS ON CONSUMER ELECTRONICS 2024年第1期70卷 3603-3613页

作者： Huang, Teng Liang, Cheng Wu, Di He, Yi Guangzhou Univ Inst Artificial Intelligence & Blockchain Guangzhou 510002 Peoples R China Southwest Univ Coll Comp & Informat Sci Chongqing 400715 Peoples R China Old Dominion Univ Dept Comp Sci Norfolk VA 23529 USA

The deep neural network (DNN)-based recommender system (RS) has drawn much attention recently and provided state-of-the-art results. Although many DNN-based RSs have been achieved, most focus on inventing a sophisticated DNN with a single-metric loss function to fit user behavior data. However, user behavior data are commonly collected from numerous users in complex scenarios, making various biases and outliers (outliers can be seen as the special bias) widely exist in the data. Unfortunately, prior DNN-based RSs only considered rather fragmented biases and lacked a comprehensive solution. To fill this gap, this paper proposes an AutoRec++ model to comprehensively address the various biases existed in user behavior data. Its main idea is to employ different combinations of preprocessing bias (PB) and training bias (TB) as well as L-1 -norm and L-2 -norm to form a multi-metric loss function-oriented autoencoder. As such, AutoRec++ possesses the multi-merits of the PB's and TB's debiasing ability, the L-1 -norm's robustness, and the L-2 -norm's stability. By conducting extensive experiments on five benchmark datasets, we demonstrate that: 1) the incorporation of PB and TB can significantly boost autoencoder's prediction accuracy and computational efficiency without structural change, and 2) our AutoRec++ achieves better prediction accuracy and robustness than both DNN-based and non-DNN-based state-of-the-art models. Besides, our AutoRec++ is more effective in processing sparser user behavior data.

关键词： Manganese Behavioral sciences Robustness Training Task analysis Deep learning Data models Recommender system debias methods representation learning deep neural network biased data representation autoencoder

来源：评论

学校读者我要写书评

暂无评论

Attention augmented residual autoencoder for efficient polyp segmentation

引用

INTERNATIONAL JOURNAL OF IMAGING SYSTEMS AND TECHNOLOGY 2023年第2期33卷 701-713页

作者： Sushama, Geetha Menon, Gopakumar Chandrasekhara Coll Engn Chengannur Dept Comp Sci & Engn Alappuzha India Coll Engn Karunagappally Dept Elect & Commun Engn Kollam India APJ Abdul Kalam Technol Univ Thiruvananthapuram Kerala India

Colon cancer has been reported to be one of the frequently diagnosed cancers and the leading cause of cancer deaths. Early detection and removal of malicious polyps, which are precursors of colon cancer, can enormously lessen the fatality rate. The detection and segmentation of polyps in colonoscopy is a challenging task even for an experienced colonoscopist, due to divergences in the size, shape, texture, and the close resemblance of polyps with the colon lining. Machine-assisted detection, localization, and segmentation of polyps in the screening procedure can profoundly help the clinicians. autoencoder-based architectures used in polyp segmentation lack the efficiency in incorporating both local and long-range pixel dependencies. To address the challenges in the automatic segmentation of colon polyps we propose an autoencoder architecture, augmented with a feature attention module in the decoder part. The salient features from RGB colonoscopic images are extracted using the residual skip-connected autoencoder. The decoder attention module joins spatial subspace with feature subspace extracted from the deep residual convolutional neural network and enhances the feature weight for precise segmentation of polyp regions. Extensive experiments on four publicly available polyp datasets demonstrate that the proposed architecture provides very impressive performance in terms of segmentation metrics (Dice scores and Jaccard scores) when compared with the state-of-the-art polyp segmentation approaches.

关键词： attention module autoencoder colon polyps residual skip-connected CNN semantic segmentation

来源：评论

学校读者我要写书评

暂无评论

Spatial-prior generalized fuzziness extreme learning machine autoencoder-based active learning for hyperspectral image classification

引用

OPTIK 2020年 206卷 163712-000页

作者： Ahmad, Muhammad Shabbir, Sidrah Oliva, Diego Mazzara, Manuel Distefano, Salvatore Univ Messina Dipartimento Matemat & Informat MIFT I-98121 Messina Italy Khwaja Fareed Univ Engn & Informat Technol Rahim Yar Khan 64200 Pakistan Univ Guadalajara Dept Comp Sci Guadalajara Jalisco Mexico Innopolis Univ Inst Software Dev & Engn Innopolis 420500 Russia

Hyperspectral imaging has been extensively utilized in several fields, and it benefits from detailed spectral information contained in each pixel, generating a thematic map for classification to assign a unique label to each sample. However, the acquisition of labeled data for classification is expensive in terms of time and cost. Moreover, manual selection and labeling are often subjective and tend to induce redundancy into the classifier. In this paper, a spatial prior generalized fuzziness extreme learning machine autoencoder (GFELM-AE) based active learning is proposed, which contextualizes the manifold regularization to the objective of ELM-AE. Experiments on a benchmark dataset confirmed that the GFELM-AE presents competitive results compared to the state-of-the-art, leading to the improved statistical significance in terms of F1-score, precision, and recall.

关键词： Extreme learning machine autoencoder Active learning Spatial spectral information Fuzziness

来源：评论

学校读者我要写书评

暂无评论

Distributed autoencoder classifier network for small-scale and scattered COVID-19 dataset classification

引用

INTERNATIONAL JOURNAL OF IMAGING SYSTEMS AND TECHNOLOGY 2023年第6期33卷 1870-1881页

作者： Yang, Yuan Zhang, Lin Ren, Lei Wang, Xiaohan Sch Med & Engn Beijing Adv Innovat Ctr Big Data Based Precis Med 37 Xueyuan Rd Beijing Peoples R China Beihang Univ Minist Ind & Informat Technol Key Lab Big Data Based Precis Med Beijing Peoples R China Beihang Univ Sch Automat Sci & Elect Engn Beijing Peoples R China

In healthcare, small-scare data are stored with individual entities, such as hospitals, and they are not shared. However, data with one entity are not sufficient for training a machine learning model and therefore cannot be fully utilized. Given that a large amount of small-scale data is widely distributed between hospitals/individuals, it is necessary to deploy an easy, scalable, and secure distributed computational framework. We aim to aggregate these scattered and small-scale data to train neural networks and achieve classification and detection on coronavirus disease 2019 (COVID-19) datasets. We propose a distributed autoencoder (AE) classifier network for this purpose. It contains a central classifier and multiple distributed AEs. The AEs are used as generators. A local generator uses an actual COVID-19 computed tomography image as the input and outputs a synthetic image. The well-trained generator provides an image to train the central classifier model. The central classifier network model learns information from all the generated COVID-19 data using the distributed AE. Experiments are performed using some COVID-19 datasets. The distributed AE classifier network outperforms all the models that use a single subset, and its performance is similar to that of a regular classifier. The proposed network solves the problem of using small-scale and scattered COVID-19 data to train neural networks while ensuring data privacy. The accuracy of the network is the same as that achieved using the entire data.

关键词： autoencoder COVID-19 dataset deep learning small-scale

来源：评论

学校读者我要写书评

暂无评论

Low PAPR MIMO-OFDM Design Based on Convolutional autoencoder

引用

IEEE TRANSACTIONS ON COMMUNICATIONS 2024年第5期72卷 2779-2792页

作者： Huleihel, Yara Permuter, Haim H. Ben Gurion Univ Negev Dept Elect Engn IL-8486208 Beer Sheva Israel Ben Gurion Univ Negev Dept Elect & Comp Engn IL-84105 Beer Sheva Israel

An enhanced framework for peak-to-average power ratio (PAPR) reduction and waveform design for Multiple-Input-Multiple-Output (MIMO) orthogonal frequency-division multiplexing (OFDM) systems, based on a convolutional-autoencoder (CAE) architecture, is presented. The end-to-end learning-based autoencoder (AE) for communication networks represents the network by an encoder and decoder, where in between, the learned latent representation goes through a physical communication channel. We introduce a joint learning scheme based on projected gradient descent iteration to optimize the spectral mask behavior and MIMO detection under the influence of a non-linear high power amplifier (HPA) and a multipath fading channel. The offered efficient implementation novel waveform design technique utilizes only a single PAPR reduction block for all antennas. It is throughput-lossless, as no side information is required at the decoder. Performance is analyzed by examining the bit error rate (BER), the PAPR, and the spectral response and compared with classical PAPR reduction MIMO detector methods on 5G simulated data. The suggested system exhibits competitive performance when considering all optimization criteria simultaneously. We apply gradual loss learning for multi-objective optimization and show empirically that a single trained model covers the tasks of PAPR reduction, spectrum design, and MIMO detection together over a wide range of SNR levels.

关键词： Peak to average power ratio MIMO communication Optimization Wireless communication Transmitting antennas Symbols Antennas Deep learning autoencoder multiple-input-multiple-output orthogonal frequency-division multiplexing peak-to-average power ratio wireless signal processing

来源：评论

学校读者我要写书评

暂无评论

AENEA: A novel autoencoder-based network embedding algorithm

引用

PEER-TO-PEER NETWORKING AND APPLICATIONS 2021年第3期14卷 1829-1840页

作者： Xu, Xiaolong Xu, Haoyan Wang, Yang Zhang, Jing Nanjing Univ Posts & Telecommun Sch Comp Sci Nanjing Jiangsu Peoples R China Nanjing Univ Posts & Telecommun Jiangsu Key Lab Big Data Secur & Intelligent Proc Nanjing Jiangsu Peoples R China Shanghai Business Sch Fac Business Informat Shanghai Peoples R China

Network embedding aims to represent vertices in the network with low-dimensional dense real number vectors, so that the attained vertices can acquire the ability of representation and inference in vector space. With the expansion of the scale of complex networks, how to make the high-dimensional network represented in low-dimensional vector space through network becomes an important issue. The typical algorithms of current autoencoder-based network embedding methods include DNGR and SDNE. DNGR method trains the Positive Pointwise Mutual Information (PPMI) matrix with the Stacked Denosing autoencoder (SDAE), which is lacking in depth thereby attaining less satisfactory representation of network. Besides, SDNE used a semi-supervised autoencoder for embedding the adjacency matrix, whose sparsity may generate more cost in the learning process. In order to solve these problems, we propose a novel autoencoder-based Network Embedding Algorithm (AENEA). AENEA is mainly divided into three steps. First, the random surfing model is used to process the original network to obtain the Probabilistic Co-occurrence (PCO) matrix between the nodes. Secondly, the Probabilistic Co-occurrence (PCO) matrix is processed to generate the corresponding Positive Pointwise Mutual Information (PPMI) matrix. Finally, the PPMI matrix is used to learn the representation of vertices in the network by using a semi-supervised autoencoder. We implemented a series of experiments to test the performance of AENEA, DNGR, SDNE and so on, on the standardized datasets 20-NewsGroup and Wine. The experimental results show that the performance of AENEA is obviously superior to the existing algorithms in clustering, classification and visualization tasks.

关键词： Network embedding Deep learning Semi-supervised learning autoencoder

来源：评论

学校读者我要写书评

暂无评论

A Fast Deep autoencoder for high-dimensional and sparse matrices in recommender systems

引用

NEUROCOMPUTING 2020年 412卷 381-391页

作者： Jiang, Jiajia Li, Weiling Dong, Ani Gou, Quanhui Luo, Xin Dongguan Univ Technol Sch Comp Sci & Technol Dongguan 523808 Guangdong Peoples R China Dongguan Univ Technol Dept Comp & Informat Sci City Coll Dongguan 523419 Guangdong Peoples R China Lenovo US Morrisville NC 27560 USA CloudWalk Dept Big Data Anal Tech Hengrui Chongqing Artificial Intelligence Res Ctr Chongqing 401331 Peoples R China

A latent factor analysis (LFA)-based model has outstanding performance in extracting desired patterns from High-dimensional and Sparse (HiDS) data for building a recommender systems. However, they mostly fail in acquiring non-linear features from an HiDS matrix. An autoencoder (AE)-based model can address this issue efficiently, but it requires filling unknown data of an HiDS matrix with pre assumptions that leads to the following limitations: a) prefilling unknown data of an HiDS matrix might skew its known data distribution to generate ridiculous recommendations;and b) incorporating a deep AE-style structure to improve its representative learning ability. Experimental results on three HiDS matrices from real recommender systems show that an FDAE-based model significantly outperforms state-of-the-art recommenders in terms of recommendation accuracy. Meanwhile, its computational efficiency is comparable with the most efficient recommenders with the help of parallelization. (c) 2020 Elsevier B.V. All rights reserved.

关键词： Recommender System Collaborative Filtering Latent Factor Analysis autoencoder Parallelization High-dimensional and Sparse Matrix Deep Neural Network

来源：评论

学校读者我要写书评

暂无评论

Domain Adaptation for Localization Using Combined autoencoder and Gradient Reversal Layer in Dynamic IoT Environment

引用

IEEE TRANSACTIONS ON NETWORK SCIENCE AND ENGINEERING 2024年第1期11卷 685-695页

作者： Prasad, Gaurav Pandey, Ankur Kumar, Sudhir Indian Inst Technol Patna Dept Elect Engn Patna 801106 Bihar India Rajiv Gandhi Inst Petr Technol Dept Elect & Elect Engn Amethi 229304 India

The popularity of Received Signal Strength (RSS) fingerprint-based indoor localization is mainly due to ubiquitous nature of Wi-Fi signals. However, environment changes, device heterogeneity and change in Access Points (APs) results in domain shift between offline and online RSS fingerprints. This article proposes a novel Domain Adversarial Neural Network for Regression (DANN-R) over a compressed RSS representation derived from autoencoders used as a dimension reduction technique to alleviate the challenges of a dynamic IoT environment. In addition, adversarially learn domain-invariant representation in DANN-R using gradient reversal layer (GRL) mitigates these RSS fluctuations by learning a common representation, where source domain (offline RSS data) and target domain (online RSS data) cannot be distinguished. The proposed method outperforms both state-of-art machine learning algorithms and deep domain adaptation frameworks on two public localization testbeds.

关键词： Feature extraction Location awareness Fingerprint recognition Measurement Task analysis Estimation Training Localization deep learning unsupervised domain adaptation autoencoder

来源：评论

学校读者我要写书评

暂无评论

Optimal Sparse autoencoder Based Sleep Stage Classification Using Biomedical Signals

引用

Computer Systems Science & Engineering 2023年第2期44卷 1517-1529页

作者： Ashit Kumar Dutta Yasser Albagory Manal Al Faraj Yasir A.M.Eltahir Abdul Rahaman Wahab Sait Department of Computer Science and Information Systems College of Applied SciencesAlMaarefa UniversityAd DiriyahRiyadh13713Kingdom of Saudi Arabia Department of Computer Engineering College of Computers and Information TechnologyTaif UniversityTaif21944Kingdom of Saudi Arabia Department of Respiratory Care College of Applied SciencesAlMaarefa UniversityAd DiriyahRiyadh13713Kingdom of Saudi Arabia Department of Archives and Communication King Faisal UniversityAl AhsaHofuf31982Kingdom of Saudi Arabia

The recently developed machine learning(ML)models have the ability to obtain high detection rate using biomedical ***,this article develops an Optimal Sparse autoencoder based Sleep Stage Classiﬁcation Model on Electroencephalography(EEG)Biomedical Signals,named OSAE-SSCEEG *** major intention of the OSAE-SSCEEG technique is toﬁnd the sleep stage disorders using the EEG biomedical *** OSAE-SSCEEG technique primarily undergoes preprocessing using min-max data normalization ***,the classiﬁcation of sleep stages takes place using the Sparse autoencoder with Smoothed Regularization(SAE-SR)with softmax(SM)***,the parameter optimization of the SAE-SR technique is carried out by the use of Coyote Optimization Algorithm(COA)and it leads to boosted classiﬁcation efﬁ*** order to ensure the enhanced performance of the OSAE-SSCEEG technique,a wide ranging simulation analysis is performed and the obtained results demonstrate the betterment of the OSAE-SSCEEG tech-nique over the recent methods.

关键词： Biomedical signals EEG sleep stage classiﬁcation machine learning autoencoder softmax parameter tuning

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：