检索结果-内蒙古大学图书馆

Integrating deep Learning and Reinforcement Learning for Enhanced Financial Risk Forecasting in Supply Chain Management

引用

JOURNAL OF THE KNOWLEDGE ECONOMY 2024年第4期15卷 20091-20110页

作者： Cui, Yuanfei Yao, Fengtong Inner Mongolia Agr Univ Coll Econ & Management Hohhot 010018 Peoples R China

In today's dynamic business landscape, the integration of supply chain management and financial risk forecasting is imperative for sustained success. This research paper introduces a groundbreaking approach that seamlessly merges deep autoencoder (DAE) models with reinforcement learning (RL) techniques to enhance financial risk forecasting within the realm of supply chain management. The primary objective of this research is to optimize financial decision-making processes by extracting key feature representations from financial data and leveraging RL for decision optimization. To achieve this, the paper presents the PSO-SDAE model, a novel and sophisticated approach to financial risk forecasting. By incorporating advanced noise reduction features and optimization algorithms, the PSO-SDAE model significantly enhances the accuracy and reliability of financial risk predictions. Notably, the PSO-SDAE model goes beyond traditional forecasting methods by addressing the need for real-time decision-making in the rapidly evolving landscape of financial risk management. This is achieved through the utilization of a distributed RL algorithm, which expedites the processing of supply chain data while maintaining both efficiency and accuracy. The results of our study showcase the exceptional precision of the PSO-SDAE model in predicting financial risks, underscoring its efficacy for proactive risk management within supply chain operations. Moreover, the augmented processing speed of the model enables real-time analysis and decision-making - a critical capability in today's fast-paced business environment.

关键词： Financial risk forecasting Supply chain management deep autoencoder Reinforcement learning Data mining

来源：评论

学校读者我要写书评

暂无评论

A Hybrid Anomaly Detection Approach for Obfuscated Malware

A Hybrid Anomaly Detection Approach for Obfuscated Malware

引用

4th IEEE Annual International Conference on Cyber Security and Resilience (IEEE CSR)

作者： Fuhnwi, Gerard Shu Revelle, Matthew Izurieta, Clemente Montana State Univ Gianforte Sch Comp Bozeman MT 59717 USA Pacific Northwest Natl Lab Richland WA 99352 USA Idaho Natl Lab Idaho Falls ID USA

ISBN: (纸本)9798350375367

With the rapid evolution of malicious software, cyber threats have become increasingly sophisticated, employing advanced obfuscation techniques to evade traditional detection methods. This study presents a hybrid anomaly detection approach applied to obfuscated malware. Even though there is a large body of research in this field, existing malware detection techniques have drawbacks, such as requiring large amounts of data, trustworthiness (imprecise results) of algorithms, and advanced obfuscation. There is a need to employ solid and efficient techniques for malware detection to overcome these challenges. This paper proposes a hybrid approach, combining an autoencoder with traditional machine-learning methods to create an efficient malware detection framework. We used the malware memory dataset (MalMemAnalysis-2022) to evaluate this framework. The experimental results show our proposed approach can detect obfuscated malware when a deep autoencoder used for feature learning is combined with logistic regression. It is extremely fast with an Accuracy, Detection Rate (DR), Matthew Correlation Coefficient(MCC), and Statistical Parity Difference (SPD) of 99.97%, 99.98%, 99.93%, and 0.03%, respectively.

关键词： Malware Detection Hybrid Anomaly Detection Obfuscated Malware deep autoencoder Logistic Regression

来源：评论

学校读者我要写书评

暂无评论

U-FLEX: Unsupervised Feature Learning with Evolutionary eXploration 9th

U-FLEX: Unsupervised Feature Learning with Evolutionary eXpl...

引用

9th Annual Conference on Machine Learning, Optimization and Data science (LOD)

作者： Bellarmino, Nicolo' Cantoro, Riccardo Squillero, Giovanni Politecn Torino CAD Res Grp Corso Duca Abruzzi 24 I-10129 Turin Italy

ISBN: (纸本)9783031539688;9783031539695

Feature selection is an essential task in machine learning and data mining that involves identifying a subset of relevant features from a larger set. This paper proposes a novel technique for unsupervised feature selection based on a Neural Network in conjunction with an evolutionary algorithm. The proposed method aims to extract subsets of the most discriminative and relevant features from high-dimensional data, which can be eventually used for efficient and accurate machine learning. An evolutionary algorithm is employed to generate the feature subsets, and the goodness of a feature subset is evaluated through the ability of a neural network to reconstruct the whole original input space by mean squared error minimization (in an auto-encoder fashion). Experimental results demonstrate the effectiveness of the proposed approach in finding relevant feature subsets for successive learning tasks, achieving better classification and regression accuracy compared to state-of-the-art feature selection methods.

关键词： Unsupervised Learning Feature Selection Genetic Algorithm deep autoencoder Supervised Learning

来源：评论

学校读者我要写书评

暂无评论

deep Multiview Clustering via Iteratively Self-Supervised Universal and Specific Space Learning

引用

IEEE TRANSACTIONS ON CYBERNETICS 2022年第11期52卷 11734-11746页

作者： Zhang, Yue Huang, Qinjian Zhang, Bin He, Shengfeng Dan, Tingting Peng, Hong Cai, Hongmin Guangdong Polytech Normal Univ Sch Comp Sci Guangzhou 510665 Peoples R China South China Univ Technol Sch Comp Sci & Engn Guangzhou 510006 Peoples R China

Multiview clustering seeks to partition objects via leveraging cross-view relations to provide a comprehensive description of the same objects. Most existing methods assume that different views are linear transformable or merely sampling from a common latent space. Such rigid assumptions betray reality, thus leading to unsatisfactory performance. To tackle the issue, we propose to learn both common and specific sampling spaces for each view to fully exploit their collaborative representations. The common space corresponds to the universal self-representation basis for all views, while the specific spaces are the view-specific basis accordingly. An iterative self-supervision scheme is conducted to strengthen the learned affinity matrix. The clustering is modeled by a convex optimization. We first solve its linear formulation by the popular scheme. Then, we employ the deep autoencoder structure to exploit its deep nonlinear formulation. The extensive experimental results on six real-world datasets demonstrate that the proposed model achieves uniform superiority over the benchmark methods.

关键词： Feature extraction Tensors Kernel Correlation Task analysis Numerical models Training deep autoencoder multiview clustering self-supervised universal and specific space learning

来源：评论

学校读者我要写书评

暂无评论

D³FC: deep feature-extractor discriminative dictionary-learning fuzzy classifier for medical imaging

引用

APPLIED INTELLIGENCE 2022年第7期52卷 7201-7217页

作者： Ghasemi, Majid Kelarestaghi, Manoochehr Eshghi, Farshad Sharifi, Arash Islamic Azad Univ Dept Comp Engn Farsan Branch Farsan *** Iran Kharazmi Univ Dept Elect & Comp Engn Tehran *** Iran

Providing accurate and speedy diagnosis and, in turn, treatment, automated medical image analysis plays a significant role in survival rate improvement. Inherent different kinds of uncertainties and complexities prove machine learning-based, particularly dictionary-learning-based classification approaches, very promisingly. This work concerns class-specific fuzzy discriminative dictionary learning using deep features on the continuum of our machine-learning-based medical image classifiers' evolution path. In (DFC)-F-3, a deep autoencoder generates a more relevant, representative, and compact features set. The distinctive-hidden information and inherent complexity and uncertainty of medical images are addressed using fuzzy-discriminative terms in the optimization function, simultaneously improving the inter-class-representation distance and intra-class-representation similarity. A comprehensive set of experiments on cancer tumor images from three different databases shows the outperformance of (DFC)-F-3 over related state-of-the-art competitions in accuracy, sensitivity, specificity, precision, convergence speed, and noise resilience. The meaningfulness of the experiments' results is statistically verified.

关键词： Class-specific deep autoencoder Discriminative sparse representation Fuzzy dictionary learning Intra- Inter-class distance

来源：评论

学校读者我要写书评

暂无评论

A robust unsupervised anomaly detection framework

引用

APPLIED INTELLIGENCE 2022年第6期52卷 6022-6036页

作者： Luo, Zhengyu He, Kejing Yu, Zhixing South China Univ Technol Guangzhou Guangdong Peoples R China

Anomaly detection plays an essential role in monitoring dependable systems and networks such as computer clusters, water treatment systems, sensor networks, etc. However, anomaly detection nowadays remains a big challenge since previous researches suffer from inaccessible anomaly labels and inconsistent data types. Therefore, we propose a robust unsupervised anomaly detection framework (RUAD) to tackle the above problems. RUAD combines a deep autoencoder and a robust layer to extract the latent representations of data and separate normal data from abnormal data respectively, then utilizes Gaussian Mixture Model (GMM) to learn the distribution of normal data. In addition, our model can adapt to different types of data by simply modifying the structure of the deep autoencoder. Extensive experiments show that RUAD outperforms state-of-art anomaly detection techniques.

关键词： Robust unsupervised anomaly detection deep autoencoder Robust layer GMM

来源：评论

学校读者我要写书评

暂无评论

Predictive anomaly detection for marine diesel engine based on echo state network and autoencoder

引用

ENERGY REPORTS 2022年 8卷 998-1003页

作者： Qu, Chong Zhou, Zhiguo Liu, Zhiwen Jia, Shuli Beijing Inst Technol Sch Informat & Elect Beijing 100081 Peoples R China Shanghai Marine Diesel Engine Res Inst Automat Engn Dept Shanghai 201108 Peoples R China

Marine diesel engine with high thermal efficiency and good economy has become the main power of ships. Anomaly detection is an important method to improve the operation reliability of marine diesel engine. Most anomaly detection research focuses on failures that have occurred, and few studies consider anomaly prediction. A predictive anomaly detection method based on echo state network (ESN) and deep autoencoder is proposed. Historical sample data is collected and used to train the prediction network ESN and the anomaly detection network deep auto-encoder. After training, the prediction network ESN is used to predict the sensor data sequence in the future. And the predicted sequence is input into the anomaly detection network deep auto-encoder to obtain the predictive anomaly detection result. The relative error and root mean square error of the proposed method are at least 0.089 and 1.002 lower than other methods, respectively. Compared with other anomaly detection methods, the proposed autoencoder method obtains the best precision, accurate, recall indicators. Experiments show that it is feasible to establish a predictive anomaly detection method. More experiments under different conditions need to be studied, and higher performance algorithms need to be developed in the future. (C) 2022 Published by Elsevier Ltd.

关键词： Anomaly detection Prediction Marine diesel engine Echo state network deep autoencoder

来源：评论

学校读者我要写书评

暂无评论

Research on unsupervised anomaly data detection method based on improved automatic encoder and Gaussian mixture model

引用

JOURNAL OF CLOUD COMPUTING-ADVANCES SYSTEMS AND APPLICATIONS 2022年第1期11卷 1-16页

作者： Liu, Xiangyu Zhu, Shibing Yang, Fan Liang, Shengjun Univ Space Engn Beijing 101416 Peoples R China Beijing Informat Sci & Technol Univ Beijing 100026 Peoples R China

With the development of cloud computing, more and more security problems like "fuzzy boundary" are exposed. To solve such problems, unsupervised anomaly detection is increasingly used in cloud security, where density estimation is commonly used in anomaly detection clustering tasks. However, in practical use, the excessive amount of data and high dimensionality of data features can lead to difficulties in data calibration, data redundancy, and reduced effectiveness of density estimation algorithms. Although auto-encoders have made fruitful progress in data dimensionality reduction, using auto-encoders alone may still cause the model to be too generalized and unable to detect specific anomalies. In this paper, a new unsupervised anomaly detection method, MemAe-gmm-ma, is proposed. MemAe-gmm-ma generates a low-dimensional representation and reconstruction error for each input sample by a deep auto-encoder. It adds a memory module inside the auto-encoder to better learn the inner meaning of the training samples, and finally puts the low-dimensional information of the samples into a Gaussian mixture model (GMM) for density estimation. MemAe-gmm-ma demonstrates better performance on the public benchmark dataset, with a 4.47% improvement over the MemAe model standard F1 score on the NSL-KDD dataset, and a 9.77% improvement over the CAE-GMM model standard F1 score on the CIC-IDS-2017 dataset.

关键词： Cloud security Unsupervised machine learning Anomalous data detection Memory module deep autoencoder Gaussian mixture model

来源：评论

学校读者我要写书评

暂无评论

deep Rating and Review Neural Network for Item Recommendation

引用

IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS 2022年第11期33卷 6726-6736页

作者： Xi, Wu-Dong Huang, Ling Wang, Chang-Dong Zheng, Yin-Yu Lai, Jian-Huang Sun Yat Sen Univ Sch Comp Sci & Engn Guangzhou 510006 Peoples R China Guangdong Prov Key Lab Computat Sci Guangzhou 518055 Peoples R China Minist Educ Key Lab Machine Intelligence & Adv Comp Guangzhou 510006 Peoples R China South China Agr Univ Coll Math & Informat Guangzhou 510642 Peoples R China Sun Yat Sen Univ Lingnan Univ Coll Guangzhou 510275 Peoples R China

To alleviate the sparsity issue, many recommender systems have been proposed to consider the review text as the auxiliary information to improve the recommendation quality. Despite success, they only use the ratings as the ground truth for error backpropagation. However, the rating information can only indicate the users' overall preference for the items, while the review text contains rich information about the users' preferences and the attributes of the items. In real life, reviews with the same rating may have completely opposite semantic information. If only the ratings are used for error backpropagation, the latent factors of these reviews will tend to be consistent, resulting in the loss of a large amount of review information. In this article, we propose a novel deep model termed deep rating and review neural network (DRRNN) for recommendation. Specifically, compared with the existing models that adopt the review text as the auxiliary information, DRRNN additionally considers both the target rating and target review of the given user-item pair as ground truth for error backpropagation in the training stage. Therefore, we can keep more semantic information of the reviews while making rating predictions. Extensive experiments on four publicly available datasets demonstrate the effectiveness of the proposed DRRNN model in terms of rating prediction.

关键词： Predictive models Semantics Recommender systems Collaboration Backpropagation Neural networks Electronic mail deep autoencoder deep neural networks (DNNs) ratings and reviews recommender systems

来源：评论

学校读者我要写书评

暂无评论

REPRESENTATIVE FUNCTIONAL CONNECTIVITY LEARNING FOR MULTIPLE CLINICAL GROUPS IN ALZHEIMER'S DISEASE 20

REPRESENTATIVE FUNCTIONAL CONNECTIVITY LEARNING FOR MULTIPLE...

引用

20th IEEE International Symposium on Biomedical Imaging (ISBI)

作者： Zhang, Lu Yu, Xiaowei Lyu, Yanjun Liu, Tianming Zhu, Dajiang Univ Texas Arlington Comp Sci & Engn Arlington TX 76019 USA Univ Georgia Comp Sci Athens GA USA

ISBN: (纸本)9781665473583

Mild cognitive impairment (MCI) is a high-risk dementia condition which progresses to probable Alzheimer's disease (AD) at approximately 10% to 15% per year. Characterization of group-level differences between two sub-types of MCI - stable MCI (sMCI) and progressive MCI (pMCI) is the key step to understand the mechanisms of MCI progression and enable possible delay of transition from MCI to AD. Functional connectivity (FC) is considered as a promising way to study MCI progression since which may show alterations even in preclinical stages and provide substrates for AD progression. However, the representative FC patterns during AD development for different clinical groups, especially for sMCI and pMCI, have been understudied. In this work, we integrated autoencoder and multi-class classification into a single deep model and successfully learned a set of clinical group related feature vectors. Specifically, we trained two non-linear mappings which realized the mutual transformations between the original FC space and the feature space. By mapping the learned clinical group related feature vectors to the original FC space, representative FCs were constructed for each group. Moreover, based on these feature vectors, our model achieves a high classification accuracy - 68% for multi-class classification (NC vs SMC vs sMCI vs pMCI vs AD). Code has been released(1).

关键词： MCI progression Representative group related FC deep autoencoder

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：