检索结果-内蒙古大学图书馆

dual autoencoder Network with Separable Convolutional Layers for Denoising and Deblurring Images

JOURNAL OF IMAGING 2022年第9期8卷 250-250页

作者： Solovyeva, Elena Abdullah, Ali St Petersburg Electrotech Univ LETI Dept Elect Engn Theory St Petersburg 197022 Russia

A dual autoencoder employing separable convolutional layers for image denoising and deblurring is represented. Combining two autoencoders is presented to gain higher accuracy and simultaneously reduce the complexity of neural network parameters by using separable convolutional layers. In the proposed structure of the dual autoencoder, the first autoencoder aims to denoise the image, while the second one aims to enhance the quality of the denoised image. The research includes Gaussian noise (Gaussian blur), Poisson noise, speckle noise, and random impulse noise. The advantages of the proposed neural network are the number reduction in the trainable parameters and the increase in the similarity between the denoised or deblurred image and the original one. The similarity is increased by decreasing the main square error and increasing the structural similarity index. The advantages of a dual autoencoder network with separable convolutional layers are demonstrated by a comparison of the proposed network with a convolutional autoencoder and dual convolutional autoencoder.

关键词： machine learning image processing computer vision image denoising autoencoder dual autoencoder convolutional neural network separable convolutional neural network deep learning non-linear model

来源：评论

学校读者我要写书评

暂无评论

dual autoencoder-Based Joint Learning: Enhancing Depth Classification of Hard Inclusions in Soft Tissue for Robotic Palpation

引用

IEEE-ASME TRANSACTIONS ON MECHATRONICS 2025年

作者： Wang, Jingnan Zhou, Zhenning Cui, Yunduan Cui, Jian Qin, Longhui Xu, Tiantian Yi, Zhengkun Wu, Xinyu Chinese Acad Sci Guangdong Prov Key Lab Robot & Intelligent Syst Shenzhen Inst Adv Technol Shenzhen 518055 Peoples R China Shenzhen Univ Adv Technol Inst Artificial Intelligence Ctr Neurocognit & Social Behav Shenzhen 518107 Peoples R China Zhejiang Lab Res Inst Artificial Intelligence Res Ctr Augmented Intelligence Hangzhou 310000 Zhejiang Peoples R China Southeast Univ Sch Mech Engn Nanjing 211189 Peoples R China City Univ Macau Fac Data Sci Macau 999078 Peoples R China Chinese Acad Sci Key Lab Biomed Imaging Sci & Syst Beijing 100864 Peoples R China Shenzhen Univ Adv Technol Shenzhen 518107 Peoples R China

In robot-assisted minimally invasive surgery (RMIS), robotic palpation is vital for enhancing tissue assessment accuracy, especially for tumor depth detection, which is crucial for precise resections and improved treatment outcomes. By complementing and leveraging the strengths of data from multiple tactile sensors, the tumor detection task can realize significant improvements in accuracy and reliability, thereby enhancing overall performance in robotic palpation in RMIS. However, challenges arise due to differences in sensor modalities and the lack of unified data representation. To address this, we fabricate silicone-based phantom tissue to simulate soft tissue and embedded simulated tumors with hard inclusions at depths ranging from 0-11 mm, treating it as a 12-class classification problem. We conduct two robotic palpation experiments: one with the BarrettHand capacitive sensor and the other with the Digit sensor, collecting two tactile datasets. To explore the joint learnability of datasets collected from different tactile sensors, we design a dual autoencoder-based joint learning framework that integrates two recurrent autoencoders to process the two different tactile datasets. By applying a joint loss mechanism to connect their latent spaces, the autoencoders are trained jointly together, with the latent representation used for supervised classification. Extensive experiments show that joint learning enables sharing of features learned from different tactile datasets, thereby enhancing learning efficiency and classification accuracy for tactile datasets with different modalities and improving the performance of both autoencoders compared to independent training.

关键词： Classification task dual autoencoder joint learning robotic palpation tactile sensor Classification task dual autoencoder joint learning robotic palpation tactile sensor

来源：评论

学校读者我要写书评

暂无评论

Abnormality Detection of Retinal Images Using dual autoencoder 21

Abnormality Detection of Retinal Images Using Dual Autoencod...

引用

21st IEEE India Council International Conference, INDICON 2024

作者： Karthikayan Nagarajan, P. Bairwa, Sachin Kumar Lakshmi Priya, A. Jayaraman, Umarani Indian Institute of Information Technology Design and Manufacturing Department of Computer Science and Engineering Kancheepuram Chennai India Psg College of Technology Department of Biomedical Engineering Coimbatore India

ISBN: (纸本)9798350391282

This paper presents a dual autoencoder model for abnormality detection from retinal fundus images. In this paper, the dual autoencoder along with (Kernal Density Estimation) KDE is used to improve the result as compared to a single autoencoder with MSE for disease classification. The proposed model makes use of an autoencoder because it can be trained on unlabeled data. It is a good fit for abnormality detection scenarios in which access to labeled data may be limited or costly. It is useful to have a model that does not require labeled examples of abnormalities because abnormalities are usually rare and diverse. dual autoencoders combined with Kernel Density Estimation (KDE) offer a powerful framework for abnormality detection by leveraging the complementary strengths of both techniques. The dataset used in this research is the Ocular Disease Intelligent Recognition (ODIR) which is a structured ophthalmic database with seven classes of abnormal covering most of the common retinal eye diseases. The evaluation criteria used in this work include MSE for reconstruction error and accuracy for abnormality detection. © 2024 IEEE.

关键词： Abnormality Detection Disease Classification dual autoencoder Eye Disease ODIR Dataset Retinal Images

来源：评论

学校读者我要写书评

暂无评论

CFDA: Collaborative Filtering with dual autoencoder for Recommender System

CFDA: Collaborative Filtering with Dual Autoencoder for Reco...

引用

IEEE International Conference on Fuzzy Systems (FUZZ-IEEE) / IEEE World Congress on Computational Intelligence (IEEE WCCI) / International Joint Conference on Neural Networks (IJCNN) / IEEE Congress on Evolutionary Computation (IEEE CEC)

作者： Liu, Xinyu Wang, Zengmao Wuhan Univ Sch Comp Sci Wuhan Peoples R China

ISBN: (数字)9781728186719

ISBN: (纸本)9781728186719

In recent years, deep neural networks have been widely used in recommender systems. Neural collaborative filtering is a popular work to model complex interactions between users and items with deep learning. However, methods that are based on collaborative filtering usually focus on learning embedding with the factorization of pairwise interactions, thereby causing embedding to be insufficient in capturing the complex relationships between users and items. To alleviate the above problem, in this paper, we propose a novel recommendation method based on collaborative filtering with dual autoencoder (CFDA). In the proposed method, we use dual autoencoder to learn hidden representations of users and items simultaneously, and we minimize the deviation of the training data by learning the user and item representations. Extensive experiments on several datasets demonstrate that the proposed method outperforms the baseline methods that are based on neural collaborative filtering.

关键词： Deep Learning Neural Network dual autoencoder Collaborative Filtering

来源：评论

学校读者我要写书评

暂无评论

Representation Learning With dual autoencoder for Multi-Label Classification

引用

IEEE ACCESS 2021年 9卷 98939-98947页

作者： Zhu, Yi Yang, Yang Li, Yun Qiang, Jipeng Yuan, Yunhao Zhang, Runmei Yangzhou Univ Sch Informat Engn Yangzhou 225009 Jiangsu Peoples R China Hefei Univ Technol Key Lab Knowledge Engn Big Data Minist Educ Hefei 230009 Peoples R China Hefei Univ Technol Sch Comp Sci & Informat Engn Hefei 230009 Peoples R China Anhui Jianzhu Univ Sch Elect & Informat Engn Hefei 230022 Peoples R China

Multi-label classification aims to deal with the problem that an object may be associated with one or more labels, which is a more difficult task due to the complex nature of multi-label data. The crucial problem of multi-label classification is the more robust and higher-level feature representation learning, which can reduce non-helpful feature attributes from the input space prior to training. In recent years, deep learning methods based on autoencoders have achieved excellent performance in multi-label classification for the advantages of powerful representations learning ability and fast convergence speed. However, most existing autoencoder-based methods only rely on the single autoencoder model, which pose challenges for multi-label feature representations learning and fail to measure similarities between data spaces. To address this problem, in this paper, we propose a novel representation learning method with dual autoencoder for multi-label classification. Compared to the existing autoencoder-based methods, our proposed method can capture different characteristics and more abstract features from data by the serially connection of two different types of autoencoders. More specifically, firstly, the algorithm of Reconstruction Independent Component Analysis (RICA) in sparse autoencoder is trained on patches on all training and test dataset for robust global feature representations learning. Secondly, with the output of RICA, stacked autoencoder with manifold regularization (SAMR) is introduced to ameliorate the quality of multi-label features learning. Comprehensive experiments on several real-world data sets demonstrate the effectiveness of our proposed approach compared with several competing state-of-the-art methods.

关键词： Training Manifolds Independent component analysis Data models Correlation Linear programming Licenses Multi-label classification dual autoencoder RICA manifold regularization representation learning

来源：评论

学校读者我要写书评

暂无评论

ANOMALYDAE: dual autoencoder FOR ANOMALY DETECTION ON ATTRIBUTED NETWORKS

ANOMALYDAE: DUAL AUTOENCODER FOR ANOMALY DETECTION ON ATTRIB...

引用

IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP)

作者： Fan, Haoyi Zhang, Fengbin Li, Zuoyong Harbin Univ Sci & Technol Sch Comp Sci & Technol Harbin 150080 Peoples R China Minjiang Univ Fujian Prov Key Lab Informat Proc & Intelligent C Fuzhou 350121 Peoples R China

ISBN: (纸本)9781509066315

Anomaly detection on attributed networks aims at finding nodes whose patterns deviate significantly from the majority of reference nodes, which is pervasive in many applications such as network intrusion detection and social spammer detection. However, most existing methods neglect the complex cross-modality interactions between network structure and node attribute. In this paper, we propose a deep joint representation learning framework for anomaly detection through a dual autoencoder (AnomalyDAE), which captures the complex interactions between network structure and node attribute for high-quality embeddings. Specifically, AnomalyDAE consists of a structure autoencoder and an attribute autoencoder to learn both node embedding and attribute embedding jointly in latent space. Moreover, attention mechanism is employed in structure encoder to learn the importance between a node and its neighbors for an effective capturing of structure pattern, which is important to anomaly detection. Besides, by taking both the node embedding and attribute embedding as inputs of attribute decoder, the cross-modality interactions between network structure and node attribute are learned during the reconstruction of node attribute. Finally, anomalies can be detected by measuring the reconstruction errors of nodes from both the structure and attribute perspectives. Extensive experiments on real-world datasets demonstrate the effectiveness of the proposed method.

关键词： Anomaly detection attributed networks dual autoencoder graph signal processing

来源：评论

学校读者我要写书评

暂无评论

autoencoders as a Characterization Technique and Aid in the Classification of Volcanic Earthquakes

引用

IEEE JOURNAL OF SELECTED TOPICS IN APPLIED EARTH OBSERVATIONS AND REMOTE SENSING 2023年 16卷 8408-8417页

作者： Montenegro, C. Paula Andrea Cadena, I. Oscar Ernesto Lotufo, Anna Diva P. Sao Paulo State Univ UNESP Dept Elect Engn BR-01049010 Ilha Solteira Brazil Colombian Geol Survey Volcanol & Seismol Observ Pasto Pasto 111321 Colombia

Volcanic seismicity is one of the most relevant parameters for the evaluation of volcanic activity and consequently the prognosis of eruptions. Earthquakes of volcanic origin are of different classes, directly related to the physical process that generates them. The distribution of the data between classes of seismic-volcanic signals generally presents an unbalanced profile (imbalanced datasets), which can hinder the performance of the classification in machine learning models. Therefore, this research presents a characterization technique (feature extract) that, in addition to reducing the dimension of each seismic record, allows a representation of the signals with the most relevant and significant information. This work proposes the use of a dual autoencoder feature, which is compared with conventional characterization techniques, such as linear prediction coefficients and principal component analysis. The training of the model was performed with a dataset containing volcano-tectonic (VT) earthquakes, long period events, and Tornillo-type events of the Galeras volcano, one of the most active volcanoes in Colombia. The classification results reach 99% of the classification of the mentioned classes.

关键词： Characterization techniques classification dual autoencoder lower dimensional representation unbalanced dataset volcano-seismic signals

来源：评论

学校读者我要写书评

暂无评论

Integration of deep learning models for mineral prospectivity mapping: a novel Bayesian index approach to reducing uncertainty in exploration

引用

MODELING EARTH SYSTEMS AND ENVIRONMENT 2025年第3期11卷 1-18页

作者： Hoseinzade, Zohre Shojaei, Mojgan Khademi, Farkhondeh Mokhtari, Ahmad Reza Saremi, Mobin Isfahan Univ Technol Dept Min Engn Esfahan *** Iran Farhangian Univ Dept Sci Educ Tehran 14665889 Iran Geol Survey Iran Res Inst Earth Sci Tehran 131851494 Iran Univ Tehran Coll Sci Sch Geol Tehran *** Iran Laurentian Univ Harquail Sch Earth Sci 933 Ramsey Lake Rd Sudbury ON P3E 6H5 Canada Amirkabir Univ Technol Dept Min Engn Tehran *** Iran

Mineral prospectivity mapping (MPM) through the identification of prospective areas, by analyzing various exploration data and integrating them, plays a crucial role in reducing risk and improving decision-making in mineral exploration. However, this process is complex and faces many challenges due to the uncertainties inherent in the data and the various models used. In this study, our aim is to integrate several advanced methods to identify anomalies and use a new method to evaluate the performance of the developed models. To this end, five deep learning algorithms were employed for MPM, and their results were combined using a new method based on Bayesian statistics. This method was applied to five different models, resulting in a final composite model with a high level of confidence. The evaluation of results was performed using the Prediction Area plot (P-A plot). The final model demonstrated 6% higher accuracy compared to individual models and identified a smaller area as high-potential regions. Geologically, the results of the final model showed good alignment with microgranite, granodiorite to diorite, quartz diorite, and quartz monzodiorite units, indicating the success of this method in forward-looking modeling. The findings of this research suggest that combining models using this index can help reduce uncertainty and improve predictions in the identification of exploration targets, leading to more accurate decision-making and reduced exploration risks. This approach can be effectively applied in future exploration efforts.

关键词： Deep learning Embedded autoencoder Convolutional neural network dual autoencoder Variable autoencoder Uncertainty Bayesian statistics

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：