检索结果-内蒙古大学图书馆

IUAutoTimeSVD++: A Hybrid Temporal Recommender System Integrating Item and User Features Using a contractive autoencoder

引用

INFORMATION 2024年第4期15卷 204-204页

作者： Azri, Abdelghani Haddi, Adil Allali, Hakim Hassan First Univ Settat LAVETE Lab FST Settat 26000 Morocco Hassan First Univ Settat LAVETE Lab ENSA Berrechid 26100 Morocco

Collaborative filtering (CF), a fundamental technique in personalized Recommender Systems, operates by leveraging user-item preference interactions. Matrix factorization remains one of the most prevalent CF-based methods. However, recent advancements in deep learning have spurred the development of hybrid models, which extend matrix factorization, particularly with autoencoders, to capture nonlinear item relationships. Despite these advancements, many proposed models often neglect dynamic changes in the rating process and overlook user features. This paper introduces IUAutoTimeSVD++, a novel hybrid model that builds upon autoTimeSVD++. By incorporating item-user features into the timeSVD++ framework, the proposed model aims to address the static nature and sparsity issues inherent in existing models. Our model utilizes a contractive autoencoder (CAE) to enhance the capacity to capture a robust and stable representation of user-specific and item-specific features, accommodating temporal variations in user preferences and leveraging item characteristics. Experimental results on two public datasets demonstrate IUAutoTimeSVD++'s superiority over baseline models, affirming its effectiveness in capturing and utilizing user and item features for temporally adaptive recommendations.

关键词： recommendation collaborative filtering matrix factorization deep learning contractive autoencoder feature extraction temporal latent factors

来源：评论

学校读者我要写书评

暂无评论

Robust Anomaly Detection in IoT Networks using Deep SVDD and contractive autoencoder 18

Robust Anomaly Detection in IoT Networks using Deep SVDD and...

引用

18th Annual IEEE International Systems Conference (SysCon)

作者： Aktar, Sharmin Nur, Abdullah Yasin Univ New Orleans Dept Comp Sci New Orleans LA 70148 USA

ISBN: (纸本)9798350358810;9798350358803

Securing Internet of Things (IoT) devices against threats is crucial due to their significant impact on cyber-physical systems. Traditional intrusion detection systems often fall short in protecting the vast and diverse array of IoT devices. One key limitation is their lack of an anomaly detection objective, which is essential for identifying sophisticated threats that do not match known patterns. To address this critical gap, we have introduced a unique approach that utilizes an objective-based anomaly detection model. Our model, integrating a Deep Support Vector Data Description (DSVDD) with a contractive autoencoder (CAE), named DSVDD-CAE, enhances the relevance of latent representations for anomaly detection and thereby improves accuracy. This innovative combination has significantly outperformed popular anomaly detection algorithms like KMeans, OCSVM, and Isolation Forest. On the ToN-IoT dataset, our method achieved a precision of 98.77%, a recall of 99.74%, an F1-score of 99.25%, and an accuracy of 99.57%. Similarly, on the IoTID20 dataset, it reached a precision of 98.25%, a recall of 99.80%, an F1-score of 99.01%, and an accuracy of 99.64%. These results demonstrate that our model excels in accurately detecting both known and novel IoT attacks, thereby significantly advancing the field of IoT security and providing a more resilient cyber-physical ecosystem.

关键词： Internet of Things IoT Anomaly Detection Deep Learning autoencoder contractive autoencoder Support Vector Data Description DSVDD-CAE IoT Security Intrusion Detection

来源：评论

学校读者我要写书评

暂无评论

Fault Diagnosis Method of Rotating Machinery Based on contractive autoencoder 5

Fault Diagnosis Method of Rotating Machinery Based on Contra...

引用

5th International Conference on Power and Energy Technology, ICPET 2023

作者： Zhang, Teng An, Dou Xi'an Jiaotong University Faculty of Electronic and Information Engineering Xi'an China

ISBN: (纸本)9798350339673

As one of the essential equipment in the industrial production process, rotating machinery usually works in complex environments such as high temperature and heavy load. Critical components such as gears and bearings are very likely to fail. This will affect the stable operation of the entire rotating machinery. Therefore, we designed a method for diagnosing faults in rotating machinery based on contractive autoencoder in this paper. First, the loss function of the contractive autoencoder is designed. Using a lot of vibration signal fragments combined with a gradient descent algorithm to optimize network parameters. Then, slice a newly collected vibration signal. And use the trained contractive autoencoder to calculate the feature vector of each segment. Next, the feature vectors of all segments are averaged and pooled to obtain the feature vector of the vibration signal sample. Finally, the extracted feature vectors are used to train a Softmax regression classifier to achieve fault identification of key parts of rotating machinery. The experimental results show that the method in this paper can accurately and effectively diagnose motor bearing faults, which is better than traditional method. © 2023 IEEE.

关键词： contractive autoencoder intelligent fault diagnosis rotating machinery

来源：评论

学校读者我要写书评

暂无评论

Deep embedding clustering based on contractive autoencoder

引用

NEUROCOMPUTING 2021年 433卷 96-107页

作者： Diallo, Bassoma Hu, Jie Li, Tianrui Khan, Ghufran Ahmad Liang, Xinyan Zhao, Yimiao Southwest Jiaotong Univ Inst Artificial Intelligence Chengdu 611756 Peoples R China Shanxi Univ Inst Big Data Sci & Ind Taiyuan 030006 Shanxi Peoples R China

Clustering large and high-dimensional document data has got a great interest. However, current cluster ing algorithms lack efficient representation learning. Implementing deep learning techniques in document clustering can strengthen the learning processes. In this work, we simultaneously disentangle the problem of learned representation by preserving important information from the initial data while pushing the original samples and their augmentations together in one hand. Furthermore, we handle the cluster locality preservation issue by pushing neighboring data points together. To that end, we first introduce contractive autoencoders. Then we propose a deep embedding clustering framework based on contractive autoencoder (DECCA) to learn document representations. Furthermore, to grasp relevant document or word features, we append the Frobenius norm as penalty term to the conventional autoencoder framework, which helps the autoencoder to perform better. In this way, the contractive autoencoders apprehend the local manifold structure of the input data and compete with the representations learned by existing methods. Finally, we confirm the supremacy of our proposed algorithm over the state-of-the art results on six real-world images and text datasets. (c) 2021 Elsevier B.V. All rights reserved.

关键词： Document clustering Representation learning contractive autoencoder Deep learning Deep embedding clustering

来源：评论

学校读者我要写书评

暂无评论

A Hybrid Deep contractive autoencoder and Restricted Boltzmann Machine Approach to Differentiate Representation of Female Brain Disorder

引用

Procedia Computer Science 2020年 176卷 1033-1042页

作者： Abeer M.Mahmoud Fadwa Alrowais Hanen Karamti Computer Sciences Department Faculty of Computer and Information Sciences Ain Shams University Cairo Egypt. Computer Sciences Department College of Computer and Information Sciences Princess Nourah bint Abdulrahman University PO Box 84428 Riyadh Saudi Arabia. MIRACL Laboratory ISIMS University of Sfax B.P. 242 3021 Sakiet Ezzit Sfax Tunisia

Deep Learning approach dragged the full attention of researcher in medical images due to their superior literature reported success and promising directions. Concluding the most discriminative set of features greatly represents a valuable guide for achieving the satisfaction performance of a medical diagnosing system. Despite, many methods proposed for such objective, the restricted Boltzmann machines outperform as they learn features directly from data, however they lack the optimal classification performance due to data complexity. Additionally, the contractive au-toencoder offers regularized term that explicitly increases the robustness of features representation and enhancement in overall performance. This paper proposes a novel deep learning framework for diagnosing female brain disorder from fMRI scans. The configuration combines the contractive autoencoder and the discriminative restricted Boltz-mann machine (DRBM) as we seek an improvement for the classification of fMRI. The demonstrated effectiveness of the contractive autoencoder supports fitting the probability distribution model of the DRBM and transfer learning to a deeper level. Our experimental indicates that the proposed model is able to detect female brain disorder with an accuracy of 88.17% and improved literature reported results on common issues.

关键词： Deep Learning contractive autoencoder Restricted Boltzmann Machine

来源：评论

学校读者我要写书评

暂无评论

contractive autoencoder and SVM for Recognition of Handwritten Devanagari Numerals 1

Contractive Autoencoder and SVM for Recognition of Handwritt...

引用

1st International Conference on Intelligent Systems and Information Management (ICISIM)

作者： Kabra, Ruhi R. MSSs Coll Engn & Technol Dept Comp Sci & Engn Jalna India

ISBN: (纸本)9781509042647

Representation of data is very important in case of machine learning. Better the representation, the classifiers will give better results. contractive autoencoders are used to learn the representation of data which are robust to small changes in the input. This paper uses contractive autoencoder and SVM classifier for handwritten Devanagari numerals recognition. The accuracy obtained using CAE+SVM is 96 %.

关键词： contractive autoencoder SVM Handwritten numerals recognition

来源：评论

学校读者我要写书评

暂无评论

Unsupervised Multi-manifold Classification of Hyperspectral Remote Sensing Images with contractive autoencoder 20th

Unsupervised Multi-manifold Classification of Hyperspectral ...

引用

20th Scandinavian Conference on Image Analysis (SCIA)

作者： Hassanzadeh, Aidin Kaarna, Arto Kauranne, Tuomo Lappeenranta Univ Technol Sch Engn Sci Machine Vis & Pattern Recognit Lab Lappeenranta Finland Lappeenranta Univ Technol Sch Engn Sci Math Lab Lappeenranta Finland

ISBN: (纸本)9783319591292;9783319591285

Unsupervised classification is a crucial step in remote sensing hyperspectral image analysis where producing training labelled data is a laborious task. Hyperspectral imagery is basically of high-dimensions and indeed dimensionality reduction is considered a vital step in its preprocessing chain. A majority of conventional dimensionality reduction techniques rely on single global manifold assumptions and they can not handle data coming from a multi-manifold structure. In this paper, the unsupervised classification of hyperspectral imaging is addressed through a multi-manifold learning framework. To this end, this paper proposes a contractive autoencoder based multi-manifold spectral clustering algorithm for unsupervised classification of hyperspectral imagery. The proposed algorithm follows the same outline as the general multi-manifold clustering but exploits contractive autoencoder for tangent space estimation. We evaluate the proposed algorithm with two benchmark hyperspectral datasets, Salinas and Pavia Center Scene. The experimental results show the improvements made by the proposed method with respect to the conventional multi-manifold clustering based on local PCA and the basic autoencoder.

关键词： Hyperspectral image Multi-manifold learning Spectral Clustering Tangent space estimation contractive autoencoder

来源：评论

学校读者我要写书评

暂无评论

Robust feature learning using contractive autoencoders for multi-omics clustering in cancer subtyping

引用

METHODS 2025年 233卷 52-60页

作者： Guo, Mengke Ye, Xiucai Huang, Dong Sakurai, Tetsuya Univ Tsukuba Dept Comp Sci Tsukuba 3058577 Japan

Cancer can manifest in virtually any tissue or organ, necessitating precise subtyping of cancer patients to enhance diagnosis, treatment, and prognosis. With the accumulation of vast amounts of omics data, numerous studies have focused on integrating multi-omics data for cancer subtyping using clustering techniques. However, due to the heterogeneity of different omics data, extracting important features to effectively integrate these data for accurate clustering analysis remains a significant challenge. This study proposes a new multi-omics clustering framework for cancer subtyping, which utilizes contractive autoencoder to extract robust features. By encouraging the learned representation to be less sensitive to small changes, the contractive autoencoder learns robust feature representations from different omics. To incorporate survival information into the clustering analysis, Cox proportional hazards regression is used to further select the key features significantly associated with survival for integration. Finally, we utilize K-means clustering on the integrated feature to obtain the clustering result. The proposed framework is evaluated on ten different cancer datasets across four levels of omics data and compared to other existing methods. The experimental results indicate that the proposed framework effectively integrates the four omics datasets and outperforms other methods, achieving higher C-index scores and showing more significant differences between survival curves. Additionally, differential gene analysis and pathway enrichment analysis are performed to further demonstrate the effectiveness of the proposed method framework.

关键词： Multi-omics clustering contractive autoencoder Cancer subtyping

来源：评论

学校读者我要写书评

暂无评论

Advancing Network Anomaly Detection: An Ensemble Approach Combining Optimized contractive autoencoders and K-Means Clustering 3

Advancing Network Anomaly Detection: An Ensemble Approach Co...

引用

3rd International Conference on Computing and Machine Intelligence (ICMI)

作者： Aktar, Sharmin Nur, Abdullah Yasin Univ New Orleans Dept Comp Sci New Orleans LA 70148 USA

ISBN: (纸本)9798350372977;9798350372984

This paper introduces a new approach for detecting unusual activities in network traffic, a critical aspect in maintaining network security. We propose an innovative model that combines the strengths of contractive autoencoders (CAEs) and K-means clustering, specifically designed for effective anomaly detection in network environments. Our model employs CAEs for efficient data processing and K-means clustering to identify deviations from standard network patterns. The focus is on the exploration of CAE's latent space and the impact of various deep learning parameters on the model's detection capabilities. Tested on the NSL-KDD dataset, a standard in network security research, our best-tuned model achieves an F1 Score of 0.92, making it approximately 8.2% more effective than the basic autoencoder model and about 5.7% better than the standalone K-Means approach in terms of F1 Score. This significant improvement in performance highlights the advanced capabilities of our model in identifying potential threats in network traffic, marking a considerable advancement in the field of network security.

关键词： Network Security Anomaly Detection Deep Learning autoencoder contractive autoencoder K-means Clustering Network Traffic Analysis Intrusion Detection CAE-K-means Model Cybersecurity

来源：评论

学校读者我要写书评

暂无评论

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

引用

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

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：