检索结果-内蒙古大学图书馆

An intelligent sequential fraud detection model based on deep learning

JOURNAL OF SUPERCOMPUTING 2024年第10期80卷 14824-14847页

作者： Zioviris, Georgios Kolomvatsos, Kostas Stamoulis, George Univ Thessaly Dept Elect & Comp Engn Glavani 37 Volos 38221 Thessaly Greece Univ Thessaly Dept Informat & Telecommun Papasiopoulou 2-4 Lamia 35131 Thessaly Greece

Fraud detection and prevention has received a lot of attention from the research community due to its high impact on financial institutions' revenues and reputation. The increased use of the web and the provision of online services open up the pathway for exposing these systems to numerous threats and jeopardizing their effective functioning. Naturally, financial frauds are increased in number and form imposing various requirements for their efficient and immediate detection. These requirements are related to the performance of the adopted models as well as the timely response of the decision-making mechanism. Machine learning and data mining are two research domains that can provide a number of techniques/algorithms for fraud detection and setup the road for mitigation actions. However, these methods still need to be improved with respect to the detection of unknown fraud patterns and the incorporation of big data processing mechanisms. This paper presents our attempt to build a hybrid system, i.e., a sequential scheme for combining two deep learning models and efficiently detecting potential financial frauds. We elaborate on the combination of an autoencoder and a Long Short-Term Memory Recurrent Neural Network trained upon datasets which are processed through the use of an oversampling technique. Oversampling is adopted to handle heavily imbalanced datasets which is the 'natural' scenario due to the limited number of frauds compared to the humongous volumes of transactions. The proposed approach tends to capture much more fraud events in comparison with other conventional ML techniques. Our experimental evaluation exposes that our model exhibits a good performance in terms of recall and precision.

关键词： Fraud detection autoencoder variational autoencoder Dimensionality reduction Oversampling Recurrent Neural Networks Long Short-Term Memory networks

来源：评论

学校读者我要写书评

暂无评论

Deep learning-based efficient drone-borne sensing of cyanobacterial blooms using a clique-based feature extraction approach

引用

SCIENCE OF THE TOTAL ENVIRONMENT 2024年 912卷 169540页

作者： Shin, Jihoon Lee, Gunhyeong Kim, Taeho Cho, Kyung Hwa Hong, Seok Min Kwon, Do Hyuck Pyo, Jongcheol Cha, Yoonkyung Univ Seoul Sch Environm Engn Seoul 02504 South Korea Univ Michigan Dept Civil & Environm Engn Ann Arbor MI USA Korea Univ Sch Civil Environm & Architectural Engn Seoul 02841 South Korea Ulsan Natl Inst Sci & Technol Sch Urban & Environm Engn Ulsan 44919 South Korea Pusan Natl Univ Dept Environm Engn Busan 46241 South Korea

Recent advances in remote sensing techniques provide a new horizon for monitoring the spatiotemporal variations of harmful algal blooms (HABs) using hyperspectral data in inland water. In this study, a hierarchical concatenated variational autoencoder (HCVAE) is proposed as an efficient and accurate deep learning (DL) based bio-optical model. To demonstrate its usefulness in retrieving algal pigments, the HCVAE is applied to bloom -prone regions in Daecheong Lake, South Korea. By abstracting the similarity between highly related features using layer-wise clique-based latent-feature extraction, HCVAE reduces the computational loads in deriving outputs while preventing performance degradation. Graph-based clique-detection uses information theory-based criteria to group the related reflectance spectra. Consequently, six latent features were extracted from 79 spectral bands to consist of a multilevel hierarchy of HCVAE that can simultaneously estimate concentrations of chlorophyll-a (Chl-a) and phycocyanin (PC). Despite the parsimonious model architecture, the Chl-a and PC concentrations estimated by HCVAE closely agree with the measured concentrations, with test R2 values of 0.76 and 0.82, respectively. In addition, spatial distribution maps of algal pigments obtained from HCVAE using drone-borne reflectance successfully capture the blooming spots. Based on its multilevel hierarchical architecture, HCVAE can provide the importance of latent features along with their individual wavelengths using Shapley additive explanations. The most important latent features covered the spectral regions associated with both Chl-a and PC. The lightweight neural network DNNsel, which uses only the spectral bands of highest importance in latent-feature extraction, performed comparably to HCVAE. The study results demonstrate the utility of the multilevel hierarchical architecture as a comprehensive assessment model for near-real-time drone-borne sensing of HABs. Moreover, HCVAE is applica

关键词： Explainable artificial intelligence variational autoencoder Latent -feature extraction Hyperspectral imagery Drone -borne sensing Algal pigment

来源：评论

学校读者我要写书评

暂无评论

Vehicular Social Dynamic Anomaly Detection With Recurrent Multi-Mask Aggregator Enabled VAE

引用

IEEE TRANSACTIONS ON INTELLIGENT TRANSPORTATION SYSTEMS 2024年第12期25卷 21709-21722页

作者： Hu, Zehao He, Yuwei Shen, Yuqi Jo, Minho Collotta, Mario Shen, Guojiang Kong, Xiangjie Zhejiang Univ Technol Coll Comp Sci & Technol Hangzhou 310023 Peoples R China Korea Univ Dept Comp Convergence Software Sejong City 30019 South Korea Kore Univ Enna Fac Engn & Architecture I-94100 Enna Italy

Vehicle driving behavior analysis and detection tasks have become an indispensable part of intelligent transportation systems. Accurate pattern recognition of potential anomalies during the movement of entities is crucial for improving transportation efficiency. Current methods typically analyze vehicle trajectories independently without considering potential interactions among vehicles. To address this limitation, some studies have integrated graph attention mechanisms to capture the influence of neighboring vehicles during the aggregation process. However, Graph Attention Networks (GATs) are constrained by the univariate nature of attention heads and coefficients, thus lacking flexibility. In this work, we not only consider the social dynamics among neighboring vehicles but also delve into the limitations of GAT models. We propose a Vehicular Social Dynamics Anomaly Detection (VSD-AD) model based on the Recurrent Multi-Mask Aggregator (MMA) enabled variational autoencoder (VAE) architecture to maximize the learning of relational embeddings among neighbors in a highway vehicle network. Furthermore, we apply Node Feature Quantisation (NFQ) to the encoder output to mitigate the complexity of neighbor relationships. Our model is flexible and customizable for different highway scenarios, suitable for large-scale highway vehicle video data. To validate real-world applicability, we further assess its performance on both the simulated dataset and real-world traffic dataset, where our model outperforms other mainstream methods in terms of detection performance.

关键词： Anomaly detection variational autoencoder graph aggregation intelligent transportation

来源：评论

学校读者我要写书评

暂无评论

Towards inverse microstructure-centered materials design using generative phase-field modeling and deep variational autoencoders

引用

ACTA MATERIALIA 2023年第1期259卷

作者： Attari, Vahid Khatamsaz, Danial Allaire, Douglas Arroyave, Raymundo Texas A&M Univ Mat Sci & Engn Dept College Stn TX 77840 USA Texas A&M Univ Mech Engn Dept College Stn TX 77840 USA

The field of Integrated Computational Materials Engineering (ICME) combines a broad range of methods to study materials' responses over a spectrum of length scales. A relatively unexplored aspect of microstructure -sensitive materials design is uncertainty propagation and quantification (UP/UQ) of materials' microstructure, as well as establishing process-structure-property (PSP) relationships for inverse material design. In this study, an efficient UP technique built on the idea of changing probability measures and a deep generative unsupervised representative machine learning method for microstructure-based design of thermal conductivity of materials is proposed. Probability measures are used to represent microstructure space, and Wasserstein metrics are used to test the efficiency of the UP method. By using deep variational autoencoder (VAE), we identify the correlations between the material/process parameters and the thermal conductivity of heterogeneous dual-phase microstructures. Through high-throughput screening, UP, and the deep-generative VAE method, PSP relationships that are too complex can be revealed by exploiting the materials' design space with an emphasis on microstructures. As a last point, we demonstrate generative machine learning serves as a useful tool for inverse microstructure-centered materials design, and we demonstrate this by examining the inverse design of thermal conductivity in nano-structured materials. The results reveal the effects of morphology, volume fraction, characteristic length scale, and the individual thermal diffusivity of phases on the thermal conductivity of dual-phase alloys. Our findings emphasize the advantages of high-throughput phase -field modeling and generative deep learning for linking PSP and inverse microstructure-centered materials design.

关键词： Computational materials design Process-structure-property linkage Microstructure Generative modeling Phase-field modeling Uncertainty quantification variational autoencoder

来源：评论

学校读者我要写书评

暂无评论

Developing semi-supervised latent dynamic variational autoencoders to enhance prediction performance of product quality

引用

CHEMICAL ENGINEERING SCIENCE 2023年 265卷

作者： Lee, Yi Shan Chen, Junghui Chung Yuan Christian Univ Dept Chem Engn Taoyuan 32023 Taiwan

The online quality variables of soft sensors contribute greatly to obtaining immediate process information. The complex correlations between a large number of process variables inherited from the dynamic and nonlinear characteristics of chemical processes put more challenges on constructing soft-sensor models. Past developed steady-state soft sensors are not reliable for dynamic operating systems. Unequal sampling rates for the process and quality data cause missing values of quality data at some time points. This paper proposes a semi-supervised latent dynamic variational autoencoder to learn features between the process and quality data. A prediction network is constructed to generate artificial quality values for model training. Then the process and quality data are compressed into the latent space and the temporal relation is modeled in the clean latent space. The proposed method is compared with the conventional method for quality prediction in a numerical case and an industrial case. CO 2022 Elsevier Ltd. All rights reserved.

关键词： Bayes inference Dynamic process Quality prediction Semi -supervised State -space model variational autoencoder

来源：评论

学校读者我要写书评

暂无评论

Exploring the chemical space of ionic liquids for CO_(2)dissolution through generative machine learning models

引用

Green Chemical Engineering 2025年第3期6卷 335-343页

作者： Xiuxian Chen Guzhong Chen Kunchi Xie Jie Cheng Jiahui Chen Zhen Song Zhiwen Qi State Key Laboratory of Chemical Engineering School of Chemical EngineeringEast China University of Science and TechnologyShanghai200237China

For discovering uncharted chemical space of ionic liquids(ILs)for CO_(2)dissolution,a reliable generative framework combining re-balanced variational autoencoder(VAE),artificial neural network(ANN),and particle swarm optimization(PSO)is developed based on a comprehensive experimental solubility database from *** re-balanced VAE transforms the chemical space of ILs into continuous latent space,which is demonstrated by tdistributed stochastic neighbor embedding(t-SNE)visualization and sampled ions of the latent *** is connected with the re-balanced VAE to predict the CO_(2)solubility and the resultant VAE-ANN model achieves a low mean absolute error(MAE)of 0.022 on the test ***,the PSO algorithm is employed to search the latent space for optimal IL structures with the highest predicted solubility.A total of 5120 ILs are generated and optimized through 10 parallel runs of *** CO_(2)solubilities are predicted and compared to those of the 3735 ILs combined with the already-known cations and anions in the CO_(2)solubility database under 298.15 K and 100 *** results demonstrate a notably larger distribution of higher CO_(2)solubility in optimized ILs after PSO,which effectively points out the significance and directions for exploring the wide IL chemical space.

关键词： Ionic liquids CO_(2)solubility variational autoencoder Particle swarm optimization Chemical space exploration

来源：评论

学校读者我要写书评

暂无评论

A novel soft sensor modeling method based on gated stacked target-supervised VAE with variable weights

引用

CONTROL ENGINEERING PRACTICE 2025年 155卷

作者： Xu, Liang Xie, Li Sun, Le Cao, Yuqing Jiangnan Univ Sch Internet Things Engn Wuxi 214122 Peoples R China Wuxi Adv Technol Inc Wuxi 214161 Peoples R China

The variational autoencoder (VAE) has garnered extensive attention in the field of soft sensor modeling due to its superior capabilities in probabilistic data description and feature extraction. However, a single-layer VAE is challenging to extract higher-level features in the face of strong nonlinear process data. This paper proposes a gated stacked target-supervised VAE with variable weights (W-GSTVAE) to improve the modeling prediction performance of VAE. First, a stacked VAE is employed to enhance the feature extraction capability. In the pretraining phase, to enhance the correlation between the features and the target variable, feature learning is guided by incorporating the prediction error of target values into the loss function as well as calculating the maximum information coefficient between input and target variables. Meanwhile, in the fine-tuning phase, to make full use of shallow features, gated linear units are used to integrate the output features of each layer, fully exploiting the information from all layers. Finally, the effectiveness and superiority of the proposed model is demonstrated through two real industrial cases.

关键词： variational autoencoder Soft sensor modeling Target-supervised learning Maximum information coefficient Gated linear unit

来源：评论

学校读者我要写书评

暂无评论

Synthetic data for enhanced privacy: A VAE-GAN approach against membership inference attacks

引用

KNOWLEDGE-BASED SYSTEMS 2025年 309卷

作者： Yan, Jian'en Huang, Haihui Yang, Kairan Xu, Haiyan Li, Yanling Harbin Inst Technol Fac Comp Harbin 150001 Heilongjiang Peoples R China Inner Mongolia Normal Univ Coll Comp Sci & Technol Hohhot 010022 Peoples R China

The raw data utilized in training machine learning models faces a potential threat from membership inference attacks. To mitigate this risk, employing synthetic data instead of real data is proved effective in desensitizing the information. We introduce a novel generative model, combining variational autoencoder and Generative Adversarial Network, to enhance privacy protection by generating synthetic data. In our approach, discrete variables are encoded by conditional generators, and sampling training is employed to ensure the distribution of synthetic data closely aligning with the real data. The modification of the model structure prompts a refinement of the loss function. We leverage Wasserstein distance with gradient penalty and SNorm to keep the stability of the model training process. Experimental results demonstrate that the efficacy of our model surpasses existing state-of-the-art models in terms of data utility metrics. Notably, in the face of membership inference attacks, the similarity from the results indicates the difficulty when distinguish the real data from synthetic data. It means our model have highlighting capabilities for the privacy protection.

关键词： Membership privacy Synthetic data variational autoencoder Generative Adversarial Network Tabular data

来源：评论

学校读者我要写书评

暂无评论

scCAT: Single-cell Combined graph Attentional clustering for scRNA-seq analysis

引用

BIOMEDICAL SIGNAL PROCESSING AND CONTROL 2025年 105卷

作者： Gao, Yufei Zhang, Wenbo Zhang, Yameng Shi, Yujie Shi, Lei Wang, Hailing Cheng, Guozhen Henan Prov Peoples Hosp Dept Pathol Zhengzhou 450003 Henan Peoples R China Zhengzhou Univ Peoples Hosp Zhengzhou 450003 Henan Peoples R China Zhengzhou Univ Sch Cyber Sci & Engn Zhengzhou 450001 Henan Peoples R China SongShan Lab Zhengzhou 450001 Henan Peoples R China Shanghai Univ Engn Sci Sch Elect & Elect Engn Shanghai 201600 Peoples R China Informat Engn Univ Inst Informat Technol Zhengzhou 450002 Henan Peoples R China

The advent of single-cell RNA sequencing (scRNA-seq) has revolutionized gene expression research at the single-cell level, enabling the study of cellular heterogeneity and identification of rare cell populations. Deep clustering is crucial for analyzing scRNA-seq datasets by assigning cells into subpopulations. However, inherent sparsity and variability in gene expression pose challenges to clustering accuracy. To address these issues, a novel unsupervised deep clustering approach named single-cell Combined graph Attentional clustering (scCAT) is introduced. The method designs a dual-branch joint dimensionality reduction (JDR) module to learn gene expression. This strategy preserves key variance while capturing complex nonlinear relationships, effectively addressing the high-dimensionality challenges of single-cell data. Additionally, a Zero-inflated negative binomial (ZINB) distribution is integrated within the JDR to tackle significant noise, sparsity, and zero-inflation challenges. A graph attention autoencoder (GATE) then processes the graph-structured data, enhancing the integration of integrating cellular topological relationships and gene expressions. Finally, a kmeans-based self-optimization technique refines clustering while synchronizing with representation learning. Experimental evaluations on eight scRNA-seq datasets demonstrate that scCAT significantly improves clustering performance, mitigates the impact of inherent data defects. The embeddings learned from both linear and non-linear perspectives eliminate inter-component interactions, uncovering complex underlying structures and enhancing the recognition of cellular topological relationships when combined with graph neural networks.

关键词： scRNA-seq Deep clustering Graph attention autoencoder variational autoencoder Zero-inflated negative binomial model

来源：评论

学校读者我要写书评

暂无评论

Adaptive deep learning framework for robust unsupervised underwater image enhancement

引用

EXPERT SYSTEMS WITH APPLICATIONS 2025年 268卷

作者： Saleh, Alzayat Sheaves, Marcus Jerry, Dean Azghadi, Mostafa Rahimi James Cook Univ Coll Sci & Engn 1 James Cook Dr Townsville Qld 4814 Australia James Cook Univ ARC Hub Supercharging Trop Aquaculture Genet Solut Townsville Qld Australia

One of the main challenges in deep learning-based underwater image enhancement is the limited availability of high-quality training data. Underwater images are often difficult to capture and typically suffer from distortion, colour loss, and reduced contrast, complicating the training of supervised deep learning models on large and diverse datasets. This limitation can adversely affect the performance of the model. In this paper, we propose an alternative approach to supervised underwater image enhancement. Specifically, we introduce a novel framework called Uncertainty Distribution Network (UDnet), which adapts to uncertainty distribution during its unsupervised reference map (label) generation to produce enhanced output images. UDnet enhances underwater images by adjusting contrast, saturation, and gamma correction. It incorporates a statistically guided multicolour space stretch module (SGMCSS) to generate a reference map, which is utilized by a U-Net-like conditional variational autoencoder module (cVAE) for feature extraction. These features are then processed by a Probabilistic Adaptive Instance Normalization (PAdaIN) block that encodes the feature uncertainties for the final image enhancement. The SGMCSS module ensures visual consistency with the input image and eliminates the need for manual human annotation. Consequently, UDnet can learn effectively with limited data and achieve state-of-the-art results. We evaluated UDnet on eight publicly available datasets, and the results demonstrate that it achieves competitive performance compared to other state-of-the-art methods in both quantitative and qualitative metrics. Our code is publicly available at https://***/alzayats/UDnet.

关键词： Computer vision Convolutional neural networks Underwater image enhancement variational autoencoder Machine learning Deep learning

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

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

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：