检索结果-内蒙古大学图书馆

deep multiple non-negative matrix factorization for multi-view clustering

INTELLIGENT DATA ANALYSIS 2021年第2期25卷 339-357页

作者： Du, Guowang Zhou, Lihua Lu, Kevin Ding, Haiyan Yunnan Univ Sch Informat Kunming 650091 Yunnan Peoples R China Brunel Univ Uxbridge Middx England

Multi-view clustering aims to group similar samples into the same clusters and dissimilar samples into different clusters by integrating heterogeneous information from multi-view data. Non-negative matrix factorization (NMF) has been widely applied to multi-view clustering owing to its interpretability. However, most NMF-based algorithms only factorize multi-view data based on the shallow structure, neglecting complex hierarchical and heterogeneous information in multi-view data. In this paper, we propose a deep multiple non-negative matrix factorization (DMNMF) framework based on autoencoder for multi-view clustering. DMNMF consists of multiple Encoder Components and Decoder Components with deep structures. Each pair of Encoder Component and Decoder Component are used to hierarchically factorize the input data from a view for capturing the hierarchical information, and all Encoder and Decoder Components are integrated into an abstract level to learn a common low-dimensional representation for combining the heterogeneous information across multi-view data. Furthermore, graph regularizers are also introduced to preserve the local geometric information of each view. To optimize the proposed framework, an iterative updating scheme is developed. Besides, the corresponding algorithm called MVC-DMNMF is also proposed and implemented. Extensive experiments on six benchmark datasets have been conducted, and the experimental results demonstrate the superior performance of our proposed MVC-DMNMF for multi-view clustering compared to other baseline algorithms.

关键词： deep non-negative matrix factorization multi-view clustering deep autoencoder graph regularization constraints

来源：评论

学校读者我要写书评

暂无评论

Self-Supervised Speech Enhancement for Arabic Speech Recognition in Real-World Environments

引用

TRAITEMENT DU SIGNAL 2021年第2期38卷 349-358页

作者： Dendani, Bilal Bahi, Halima Sari, Toufik Univ Badji Mokhtar Annaba Comp Sci Dept Annaba 23000 Algeria Univ Badji Mokhtar Annaba Labged Lab Annaba 23000 Algeria

Mobile speech recognition attracts much attention in the ubiquitous context, however, background noises, speech coding, and transmission errors are prone to corrupt the incoming speech. Therein, building a robust speech recognizer requires the availability of a large number of real-world speech samples. Arabic language, like many other languages, lacks such resources;to overcome this limitation, we propose a speech enhancement step, before the recognition begins. For the speech enhancement purpose, we suggest the use of a deep autoencoder (DAE) algorithm. A two-step procedure is suggested: in the first step, an overcomplete DAE is trained in an unsupervised way, and in the second one, a denoising DAE is trained in a supervised way leveraging the clean speech produced in the previous step. Experimental results performed on a real-life mobile database confirmed the potentials of the proposed approach and show a reduction of the WER (Word Error Rate) of a ubiquitous Arabic speech recognizer. Further experiments show an improvement of the perceptual evaluation of speech quality (PESQ), and the short-time objective intelligibility (STOI) as well.

关键词： Arabic language deep autoencoder deep learning self-supervised speech enhancement speech recognition ubiquitous systems

来源：评论

学校读者我要写书评

暂无评论

DMC-Fusion: deep Multi-Cascade Fusion With Classifier-Based Feature Synthesis for Medical Multi-Modal Images

引用

IEEE JOURNAL OF BIOMEDICAL AND HEALTH INFORMATICS 2021年第9期25卷 3438-3449页

作者： Zuo, Qing Zhang, Jianping Yang, Yin Xiangtan Univ Sch Math & Comp Sci Xiangtan 411105 Peoples R China

Multi-modal medical image fusion is a challenging yet important task for precision diagnosis and surgical planning in clinical practice. Although single feature fusion strategy such as Densefuse has achieved inspiring performance, it tends to be not fully preserved for the source image features. In this paper, a deep multi-fusion framework with classifier-based feature synthesis is proposed to automatically fuse multi-modal medical images. It consists of a pre-trained autoencoder based on dense connections, a feature classifier and a multi-cascade fusion decoder with separately fusing high-frequency and low-frequency. The encoder and decoder are transferred from MS-COCO datasets and pre-trained simultaneously on multi-modal medical image public datasets to extract features. The feature classification is conducted through Gaussian high-pass filtering and the peak signal to noise ratio thresholding, then feature maps in each layer of the pre-trained Dense-Block and decoder are divided into high-frequency and low-frequency sequences. Specifically, in proposed feature fusion block, parameter-adaptive pulse coupled neural network and l(1) -weighted are employed to fuse high-frequency and low-frequency, respectively. Finally, we design a novel multi-cascade fusion decoder on total decoding feature stage to selectively fuse useful information from different modalities. We also validate our approach for the brain disease classification using the fused images, and a statistical significance test is performed to illustrate that the improvement in classification performance is due to the fusion. Experimental results demonstrate that the proposed method achieves the state-of-the-art performance in both qualitative and quantitative evaluations.

关键词： deep autoencoder Feature classifier Medical image fusion Multi-cascade fusion

来源：评论

学校读者我要写书评

暂无评论

An SSA-LC-DAE Method for Extracting Network Security Elements

引用

IEEE TRANSACTIONS ON NETWORK SCIENCE AND ENGINEERING 2023年第2期10卷 1175-1185页

作者： Tao, Xiaoling Liu, Ziyi Zhao, Feng Lan, Rushi Liu, Runrong Fu, Lianyou Ouyang, Yifu Guilin Univ Elect Technol Sch Comp Sci & Informat Secur Guilin 541004 Peoples R China Guilin Univ Elect Technol Sch Informat & Commun Guilin 541004 Peoples R China

In the current network environment, the original network data present the characteristics of multiple features and high dimensions. Furthermore, in the existing element extraction methods based on deep neural networks, the loss of feature information layer by layer increases as the data dimensions decrease, which greatly affects the retention of network data information elements and brings a huge challenge to effective network security protection. This paper refers to a residual neural network to improve the deep autoencoder (DAE) and then utilizes them to propose a novel element extraction method named the layer-by-layer loss compensation deep autoencoder (LC-DAE) based on the sparrow search algorithm (SSA). In the proposed method, a loss compensation module is added to each encoding layer of the DAE. Specifically, this module first restores the data by using the decoding layer corresponding to the encoding layer. Then, the loss value of the calculated characteristic information is compensated using the output of the corresponding encoding layer. Subsequently, the SSA is used to optimize the LC-DAE in the training process. Finally, the experimental results show that compared with the existing methods, this method retains more sufficient element information, and significantly improves the classification performance of data using neural networks.

关键词： Feature extraction Data mining Network security Encoding Decoding Neural networks deep learning deep autoencoder element extraction Index Terms network data sparrow search algorithm

来源：评论

学校读者我要写书评

暂无评论

Learning autoencoder ensembles for detecting malware hidden communications in IoT ecosystems

引用

JOURNAL OF INTELLIGENT INFORMATION SYSTEMS 2024年第4期62卷 925-949页

作者： Cassavia, Nunziato Caviglione, Luca Guarascio, Massimo Liguori, Angelica Zuppelli, Marco Inst High Performance Comp & Networking Via Pietro Bucci 8-9-C I-87036 Arcavacata Di Rende Italy Inst Appl Math & Informat Technol Via Marini 6 I-16149 Genoa Italy Univ Calabria Via Pietro Bucci I-87036 Arcavacata Di Rende Italy

Modern IoT ecosystems are the preferred target of threat actors wanting to incorporate resource-constrained devices within a botnet or leak sensitive information. A major research effort is then devoted to create countermeasures for mitigating attacks, for instance, hardware-level verification mechanisms or effective network intrusion detection frameworks. Unfortunately, advanced malware is often endowed with the ability of cloaking communications within network traffic, e.g., to orchestrate compromised IoT nodes or exfiltrate data without being noticed. Therefore, this paper showcases how different autoencoder-based architectures can spot the presence of malicious communications hidden in conversations, especially in the TTL of IPv4 traffic. To conduct tests, this work considers IoT traffic traces gathered in a real setting and the presence of an attacker deploying two hiding schemes (i.e., naive and "elusive" approaches). Collected results showcase the effectiveness of our method as well as the feasibility of deploying autoencoders in production-quality IoT settings.

关键词： deep autoencoder Ensemble method Covert channel Intelligent cyber attack detection system

来源：评论

学校读者我要写书评

暂无评论

Multiview Summarization and Activity Recognition Meet Edge Computing in IoT Environments

引用

IEEE INTERNET OF THINGS JOURNAL 2021年第12期8卷 9634-9644页

作者： Hussain, Tanveer Muhammad, Khan Ullah, Amin Del Ser, Javier Gandomi, Amir H. Sajjad, Muhammad Baik, Sung Wook de Albuquerque, Victor Hugo C. Sejong Univ Seoul 143747 South Korea Sejong Univ Dept Software Seoul 143747 South Korea Univ Basque Res & Technol Alliance BRTA TECNALIA Derio 48160 Spain Univ Basque Country UPV EHU Dept Commun Engn Bilbao 48940 Spain Basque Ctr Appl Math BCAM Bilbao 48009 Spain Univ Technol Sydney Fac Engn & Informat Technol Ultimo NSW 2007 Australia Islamia Coll Peshawar Dept Comp Sci Peshawar 25000 Pakistan Univ Fortaleza Grad Program Appl Informat BR-60811905 Fortaleza Ceara Brazil Fed Inst Educ Sci & Technol Ceara LAPISCO Fortaleza Ceara Brazil ARMTEC Tecnol Robot Fortaleza Ceara Brazil

Multiview video summarization (MVS) has not received much attention from the research community due to inter-view correlations and views' overlapping, etc. The majority of previous MVS works are offline, relying on only summary, and require additional communication bandwidth and transmission time, with no focus on foggy environments. We propose an edge intelligence-based MVS and activity recognition framework that combines artificial intelligence with Internet of Things (IoT) devices. In our framework, resource-constrained devices with cameras use a lightweight CNN-based object detection model to segment multiview videos into shots, followed by mutual information computation that helps in a summary generation. Our system does not rely solely on a summary, but encodes and transmits it to a master device using a neural computing stick for inter-view correlations computation and efficient activity recognition, an approach which saves computation resources, communication bandwidth, and transmission time. Experiments show an increase of 0.4 unit in F-measure on an MVS Office dateset and 0.2% and 2% improved accuracy for UCF-50 and YouTube 11 datesets, respectively, with lower storage and transmission times. The processing time is reduced from 1.23 to 0.45 s for a single frame and optimally 0.75 seconds faster MVS. A new dateset is constructed by synthetically adding fog to an MVS dateset to show the adaptability of our system for both certain and uncertain IoT surveillance environments.

关键词： Activity recognition deep autoencoder deep learning Internet of Things (IoT) multiview video summarization (MVS) sequential learning video data analytics video summarization

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

Face Hallucination From New Perspective of Non-Linear Learning Compressed Sensing

引用

IEEE ACCESS 2020年 8卷 9434-9440页

作者： Yang, Shuyuan Hao, Xiaoyang Liu, Zhi Yang, Chen Wang, Min Xidian Univ Sch Artificial Intelligence Xian 710071 Peoples R China Xidian Univ Key Lab Radar Signal Proc Xian 710071 Peoples R China

The past decade has witnessed a prosperity of sparsity-inspired face hallucination methods that use sparse prior and instances to generate High-Resolution (HR) faces. However, they need numerous Low-Resolution (LR) and HR instance pairs and adopt approximate sparse coding, which will bring bias to the recovery and suffer from high computational burden. In this paper we advance a Single Face Image Hallucination (SFIH) method from a new perspective of Non-linear Learning Compressive Sensing (NLCS), which can recover HR faces from a surprisingly small number of HR faces. The nonlinear sparse coding of facial images is explored, and a deep autoencoder (DAE) network is constructed for learning a kernel function from a single HR instance set. SFIH is then reduced to an analytic compressive recovery problem by reformulating linear sparse coding as a nonlinear DAE model. By exploring the nonlinear sparsity in the feature space, NLCS can accurately and rapidly recover HR facial images with large magnification factor and exhibit robustness to LR-HR instance pairs mapping. Some experiments are taken on realizing 3X, 6X, 9X amplification of face images, and the results prove its efficiency and superiority to its counterparts.

关键词： Face hallucination nonlinear sparse coding non-linear learning compressed sensing deep autoencoder

来源：评论

学校读者我要写书评

暂无评论

Adaptive fish school search optimized resnet for multi-view 3D objects reconstruction

引用

MULTIMEDIA TOOLS AND APPLICATIONS 2024年第32期83卷 77639-77666页

作者： Premalatha, V. Parveen, Nikhat Koneru Lakshmaiah Educ Fdn Dept Comp Sci & Engn Guntur Andhra Pradesh India

Reconstruction of multi-view 3-dimensional images is essential in robotics and computer vision to obtain an accurate 3-dimensional representation of objects by analyzing the 2-dimensional input data. For reconstructing the 3-dimensional image, it is mandatory to analyze the 3-dimensional geometry features from multiple viewpoints. It includes feature extraction and transformation from 2-dimensional features to 3-dimensional volumetric meshes. However, the existing research cannot produce consistent reconstruction results for the same input images with different orders. Therefore, the deep learning-based Residual Network-50 model is developed for 3-dimensional image reconstruction from multi-view images in the present work. The proposed system model comprises a 2-dimensional and 3-dimensional network and a backpropagation layer. From the input image, 2-dimensional features are computed using a 2-dimensional network. Then, the metaheuristic Adaptive School of Fish Optimization is used to improve the neural network's output, determining the optimal weight that gives less classification error. Then, the testing process uses the deep autoencoder, which decodes the output of the training model. Residual Network-50 is used to reconstruct 2-dimensional images to 3-dimensional using single or multi-views. Finally, the experimental analysis is performed in Python. The experiment is performed on the ShapeNet dataset and compared with the existing works. The proposed model yields better accuracy, F-score and Intersection-over-Union values of 99.3%, 0.893 and 0.734, respectively, which is more efficient than other existing models.

关键词： Object reconstruction Fish school search optimization deep autoencoder Back projection layer 3D reconstructed images ResNet-50

来源：评论

学校读者我要写书评

暂无评论

DASVDD: deep Autoencoding Support Vector Data Descriptor for Anomaly Detection

引用

IEEE TRANSACTIONS ON KNOWLEDGE AND DATA ENGINEERING 2024年第8期36卷 3739-3750页

作者： Hojjati, Hadi Armanfard, Narges McGill Univ Dept Elect & Comp Engn Montreal PQ H3A 0C3 Canada Mila Quebec AI Inst QC H2S Montreal PQ Canada

One-Class anomaly detection aims to detect anomalies from normal samples using a model trained on normal data. With recent advancements in deep learning, researchers have designed efficient one-class anomaly detection methods. Existing works commonly use neural networks to map the data into a more informative representation and then apply an anomaly detection algorithm. In this paper, we propose a method, DASVDD, that jointly learns the parameters of an autoencoder while minimizing the volume of an enclosing hypersphere on its latent representation. We propose a novel anomaly score that combines the autoencoder's reconstruction error and the distance from the center of the enclosing hypersphere in the latent representation. Minimizing this anomaly score aids us in learning the underlying distribution of the normal class during training. Including the reconstruction error in the anomaly score ensures that DASVDD does not suffer from the hypersphere collapse issue since the DASVDD model does not converge to the trivial solution of mapping all inputs to a constant point in the latent representation. Experimental evaluations on several benchmark datasets show that the proposed method outperforms the commonly used state-of-the-art anomaly detection algorithms while maintaining robust performance across different anomaly classes.

关键词： Anomaly detection deep autoencoder deep learning support vector data descriptor deep autoencoder deep learning support vector data descriptor

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：