检索结果-内蒙古大学图书馆

Robust deep image clustering using convolutional autoencoder with separable discrete Krawtchouk and Hahn orthogonal moments

引用

INTELLIGENT SYSTEMS WITH APPLICATIONS 2024年 22卷

作者： Bouali, Aymane El Ouariachi, Ilham Zahi, Azeddine Zenkouar, Khalid Univ Sidi Mohamed Ben Abdellah Fac Sci & Technol Lab Intelligent Syst & Applicat LSIA Fes Morocco Univ Moulay Ismail Fac Sci Dept Comp Sci Meknes Morocco

By cooperatively learning features and assigning clusters, deep clustering is superior to conventional clustering algorithms. Numerous deep clustering algorithms have been developed for a variety of application levels;however, the majority are still incapable of learning robust noise-resistant latent features, which limits the clustering performance. To address this open research challenge, we introduce, for the first time, a new approach called: Robust Deep Embedded Image Clustering algorithm with Separable Krawtchouk and Hahn Moments (RDEICSKHM). Our approach leverages the advantages of Krawtchouk and Hahn moments, such as local feature extraction, discrete orthogonality, and noise tolerance, to obtain a meaningful and robust image representation. Moreover, we employ LayerNormalization to further improve the latent space quality and facilitate the clustering process. We evaluate our approach on four image datasets: MNIST, MNIST-test, USPS, and Fashion-MNIST. We compare our method with several deep clustering methods based on two metrics: clustering accuracy (ACC) and normalized mutual information (NMI). The experimental results show that our method achieves superior or competitive performance on all datasets, demonstrating its effectiveness and robustness for deep image clustering.

关键词： Deep clustering autoencoder Discrete separable orthogonal moments Hahn moments Krawtchouk moments Image clustering

来源：评论

学校读者我要写书评

暂无评论

Prototype-Guided autoencoder for OCT-Based Fingerprint Presentation Attack Detection

引用

IEEE TRANSACTIONS ON INFORMATION FORENSICS AND SECURITY 2023年 18卷 3461-3475页

作者： Liu, Yi-Peng Zuo, Wangyang Liang, Ronghua Sun, Haohao Li, Zhanqing Zhejiang Univ Technol Coll Comp Sci & Technol Hangzhou 310023 Peoples R China

Anti-spoofing ability is vital for fingerprint identification systems. Conventional fingerprint scanning devices can only obtain information from the fingertip surfaces, and their performance is susceptible to skin conditions and presentation attacks (PAs). However, optical coherence tomography (OCT) can scan subcutaneous tissue and obtain 3D fingerprint structures, naturally enhancing its PA detection (PAD) ability from the perspective of hardware. Existing unsupervised PAD methods are based on image reconstruction. However, the reconstruction error is easily affected by OCT noise and the rich details of OCT images. Therefore we propose feature-based reconstruction to alleviate this problem, called the prototype-guided autoencoder. The model consists of a memory module and a denoising autoencoder without the requirement of PA fingerprints. As only bona fide fingerprints are available during the training phase, the memory module contains the prototype features of the bona fide fingerprints. During the inference phase, as the prototype memory module is frozen, the reconstructed representation of the bona fide input is close to the bona fide fingerprint features. Calculating the distance between the original features and the prototype reconstructed representation of the sample can achieve PAD. To obtain a better decision making boundary, we propose a representation consistency constraint, which reduces the bona fide representation reconstruction distance closer, so that it is easier to differentiate between fingerprints and PAs.

关键词： Fingerprint recognition Feature extraction Image reconstruction Prototypes Memory modules Training Noise reduction Presentation attack detection optical coherence tomography autoencoder prototype

来源：评论

学校读者我要写书评

暂无评论

Evolving Domain Generalization via Latent Structure-Aware Sequential autoencoder

引用

IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE 2023年第12期45卷 14514-14527页

作者： Qin, Tiexin Wang, Shiqi Li, Haoliang City Univ Hong Kong Dept Elect & Engn Kowloon Hong Kong Peoples R China City Univ Hong Kong Sch Comp Sci Kowloon Hong Kong Peoples R China

Domain generalization (DG) refers to the problem of generalizing machine learning systems to out-of-distribution (OOD) data with knowledge learned from several provided source domains. Most prior works confine themselves to stationary and discrete environments to tackle such generalization issue arising fromOODdata. However, in practice, manytasks in non-stationary environments (e.g., autonomous-driving car system, sensor measurement) involve more complex and continuously evolving domain drift, emerging new challenges for model deployment. In this paper, we first formulate this setting as the problem of evolving domain generalization. To deal with the continuously changing domains, we propose MMD-LSAE, a novel framework that learns to capture the evolving patterns among domains for better generalization. Specifically, MMD-LSAE characterizes OOD data in non-stationary environments with two types of distribution shifts: covariate shift and concept shift, and employs deep autoencoder modules to infer their dynamics in latent space separately. In these modules, the inferred posterior distributions of latent codes are optimized to align with their corresponding prior distributions via minimizing maximum mean discrepancy (MMD). We theoretically verify that MMD-LSAE has the inherent capability to implicitly facilitate mutual information maximization, which can promote superior representation learning and improved generalization of themodel. Furthermore, the experimental results on both synthetic and real-world datasets show that our proposed approach can consistently achieve favorable performance based on the evolving domain generalization setting.

关键词： Domain generalization non-stationary environments autoencoder kernel methods

来源：评论

学校读者我要写书评

暂无评论

Novel method for the detection of adulterants in coffee and the determination of a coffee's geographical origin using near infrared spectroscopy complemented by an autoencoder

引用

INTERNATIONAL JOURNAL OF FOOD SCIENCE AND TECHNOLOGY 2023年第3期58卷 1284-1298页

作者： Munyendo, Leah Njoroge, Daniel Zhang, Yanyan Hitzmann, Bernd Univ Hohenheim Dept Proc Analyt & Cereal Sci Garbenstr 23 D-70599 Stuttgart Germany Dedan Kimathi Univ Technol Inst Food Bioresources Technol Dedan Kimathi 10143 Nyeri Kenya Univ Hohenheim Dept Flavor Chem Fruwirthstr 12 D-70599 Stuttgart Germany

Coffee authenticity is a foundational aspect of quality when considering coffee's market value. This has become important given frequent adulteration and mislabelling for economic gains. Therefore, this research aimed to investigate the ability of a deep autoencoder neural network to detect adulterants in roasted coffee and to determine a coffee's geographical origin (roasted) using near infrared (NIR) spectroscopy. Arabica coffee was adulterated with robusta coffee or chicory at adulteration levels ranging from 2.5% to 30% in increments of 2.5% at light, medium and dark roast levels. First, the autoencoder was trained using pure arabica coffee before being used to detect the presence of adulterants in the samples. Furthermore, it was used to determine the geographical origin of coffee. All samples adulterated with chicory were detectable by the autoencoder at all roast levels. In the case of robusta-adulterated samples, detection was possible at adulteration levels above 7.5% at medium and dark roasts. Additionally, it was possible to differentiate coffee samples from different geographical origins. PCA analysis of adulterated samples showed grouping based on the type and concentration of the adulterant. In conclusion, using an autoencoder neural network in conjunction with NIR spectroscopy could be a reliable technique to ensure coffee authenticity.

关键词： adulteration autoencoder chicory coffee geographical origin NIR spectroscopy

来源：评论

学校读者我要写书评

暂无评论

An interpretable health indicator for bearing condition monitoring based on semi-supervised autoencoder latent space variance maximization

引用

MEASUREMENT SCIENCE AND TECHNOLOGY 2023年第12期34卷 125135-125135页

作者： Chen, Xieyi Wang, Yi Meng, Lihua Qin, Yi Tang, Baoping Chongqing Univ Coll Mech & Vehicle Engn Chongqing 400044 Peoples R China Chongqing Univ State Key Lab Mech Transmiss Chongqing 400044 Peoples R China

Effective health indicator (HI) construction can help equipment managers detect the abnormal state of rotating machinery quickly. However, although the current deep learning-based HI construction methods have good life prediction value, most of them lose the ability to detect device anomalies and little work has been done on model interpretability. Therefore, an interpretable HI construction method based on semi-supervised autoencoder (AE) latent space variance maximization (SSALSVM) was proposed to monitor the health status of bearings. In order to fully excavate degradation features inside the device and make the model focus on the encoding process, a deep convolutional neural network (DCNN) is used as the encoding layer, while only a layer of fully-connected layer is used as the decoding layer. In addition, to enable the latent space to capture the device early degradation point (EDP) successfully, an auxiliary layer is added to the output of the encoder layer. Simultaneously, for improving the sensitivity of the indicator to capture equipment abnormal state and highlight the difference between equipment health state and degradation state, the constraint of variance maximization is added into the latent space. The model optimizing process was presented by observing the projected variance of the test set in latent space of each epoch model. The validity of the proposed HI was verified by comparison experiments on two datasets.

关键词： interpretable health indicator semi-supervised autoencoder hidden space variance maximization autoencoder early degradation point

来源：评论

学校读者我要写书评

暂无评论

Application of Extreme Learning Machine- autoencoder to Medium Term Electricity Price Forecasting

引用

IEEE TRANSACTIONS ON INDUSTRY APPLICATIONS 2023年第6期59卷 7214-7223页

作者： Najafi, Arsalan Homaee, Omid Golshan, Mehdi Jasinski, Michal Leonowicz, Zbigniew Wroclaw Univ Sci & Technol Fac Elect Engn Dept Elect Engn Fundamentals PL-50370 Wroclaw Poland Islamic Azad Univ Dept Comp Engn Sepidan Branch Sepidan *** Iran VSB Tech Univ Ostrava Fac Elect Engn & Comp Sci Dept Elect Power Engn Ostrava 70800 Czech Republic

Electricity market prices are highly volatile, highly frequent, non-linear, and non-stationary which makes forecasting very complicated. Although accurate forecasting plays a crucial role in the electricity market for traders, retailers, large consumers as well as generation companies in terms of economic efficiency and power systems safety. Hence, this article proposes a new forecasting approach for medium-term electricity market prices based on an extreme learning machine-autoencoder (ELM-AE). The main idea behind this is to use trained weights for hidden layers instead of randomly generated weights. The input hidden layer weights are obtained by solving a network with the same input outputs by the autoencoder method. Then, the obtained output weights are used again as the input weights for a new ELM network. To do so, a data-set is created using input data, where the ahead 24 hours are forecasted based on the previous 168 data. The simulations have been performed on New York Independent System Operator prices and compared with the classic ELM demonstrating the high accuracy of the proposed method in both training and testing.

关键词： Forecasting electricity price extreme learning machine autoencoder electricity market

来源：评论

学校读者我要写书评

暂无评论

Perturbation AUTOVC: Voice Conversion From Perturbation and autoencoder Loss

引用

IEEE ACCESS 2023年 11卷 140174-140185页

作者： Park, Hwa-Young Lee, Young Han Chun, Chanjun Chosun Univ Dept Comp Engn Gwangju 61452 South Korea Korea Elect Technol Inst KETI Intelligent Image Proc Res Ctr Seongnam 13509 South Korea

AUTOVC is a voice-conversion method that performs self-reconstruction using an autoencoder structure for zero-shot voice conversion. AUTOVC has the advantage of being easy and simple to learn because it only uses the autoencoder loss for learning. However, it performs voice conversion by disentangling speech information from speakers and linguistic information by adjusting the bottleneck dimension;this requires highly meticulous fine tuning of the bottleneck dimension and involves a tradeoff between speech quality and speaker similarity. To address these issues, neural analysis and synthesis (NANSY)-a fully self-supervised learning system that uses perturbations to extract speech features-is proposed. NANSY solves the problem of the adjustment of the bottleneck dimension by utilizing perturbation and exhibits high-reconstruction performance. In this study, we propose perturbation AUTOVC, a voice conversion method that utilizes the structure of AUTOVC and the perturbation of NANSY. The proposed method applies perturbations to speech signals (such as NANSY signals) to solve the problem of the voice conversion method using bottleneck dimensions. Perturbation is applied to remove the speaker-dependent information present in the speech, leaving only the linguistic information, which is then passed through a content encoder and modeled as a content embedding containing only the linguistic information. To obtain speaker information, we used x-vectors, which are extensively used in pretrained speaker recognition. The concatenated linguistic and speaker information extracted from the encoder and additional energy information is used as input to the decoder to perform self-reconstruction. Similar to AUTOVC, it is easy and simple to learn using only the autoencoder loss. For the evaluation, we measured three objective evaluation metrics: character error rate (%), cosine similarity, and short-time objective intelligibility, as well as a subjective evaluation metric: mean opinio

关键词： autoencoder information perturbation speech signal processing voice conversion

来源：评论

学校读者我要写书评

暂无评论

Multi-Channel Weight-Sharing autoencoder Based on Cascade Multi-Head Attention for Multimodal Emotion Recognition

引用

IEEE TRANSACTIONS ON MULTIMEDIA 2023年 25卷 2213-2225页

作者： Zheng, Jiahao Zhang, Sen Wang, Zilu Wang, Xiaoping Zeng, Zhigang Huazhong Univ Sci & Technol Sch Artificial Intelligence & Automat Wuhan 430074 Peoples R China Huazhong Univ Sci & Technol Key Lab Image Proc & Intelligent Control Educ Minist China Wuhan 430074 Peoples R China

Multimodal Emotion Recognition is challenging because of the heterogeneity gap among different modalities. Due to the powerful ability of feature abstraction, Deep Neural Networks (DNNs) have exhibited significant success in bridging the heterogeneity gap in cross-modal retrieval and generation tasks. In this work, a DNNs-based Multi-channel Weight-sharing autoencoder with Cascade Multi-head Attention (MCWSA-CMHA) is proposed to generically address the affective heterogeneity gap in MER. Specifically, multimodal heterogeneity features are extracted by multiple independent encoders, and then a scalable heterogeneous feature fusion module (CMHA) is realized by connecting multiple multi-head attention modules in series. The core of the proposed algorithm is to reduce the heterogeneity between the output features of different encoders through the unsupervised training of MCWSA, and then to model the affective interactions between different modal features through the supervised training of CMHA. Experimental results demonstrate that the proposed MCWSA-CMHA achieves outperformance on two publicly available datasets compared with the state-of-the-art techniques. In addition, visualization experiments and approximation experiments are used to verify the effectiveness of each module in the proposed algorithm, and the experimental results show that the proposed MCWSA-CMHA can mine more emotion-related information among multimodal features compared with other fusion methods.

关键词： Multimodal emotion recognition (MER) autoencoder multi-head attention mechanism

来源：评论

学校读者我要写书评

暂无评论

Skin cancer detection through attention guided dual autoencoder approach with extreme learning machine

引用

SCIENTIFIC REPORTS 2024年第1期14卷 1-15页

作者： Maurya, Ritesh Mahapatra, Satyajit Dutta, Malay Kishore Singh, Vibhav Prakash Karnati, Mohan Sahu, Geet Pandey, Nageshwar Nath Amity Univ Amity Ctr Artificial Intelligence Noida India Manipal Acad Higher Educ Manipal Inst Technol Dept Informat & Commun Technol Manipal 576104 India Motilal Nehru Natl Inst Technol Allahabad Dept Comp Sci & Engn Allahabad India Natl Inst Technol Raipur Comp Sci & Engn Dept Raipur 492010 Chhattisgarh India ITER Siksha O Anusandhan Dept Comp Sci & Engn Bhubaneswar Odisha India

Skin cancer is a lethal disease, and its early detection plays a pivotal role in preventing its spread to other body organs and tissues. Artificial Intelligence (AI)-based automated methods can play a significant role in its early detection. This study presents an AI-based novel approach, termed 'DualAutoELM' for the effective identification of various types of skin cancers. The proposed method leverages a network of autoencoders, comprising two distinct autoencoders: the spatial autoencoder and the FFT (Fast Fourier Transform)-autoencoder. The spatial-autoencoder specializes in learning spatial features within input lesion images whereas the FFT-autoencoder learns to capture textural and distinguishing frequency patterns within transformed input skin lesion images through the reconstruction process. The use of attention modules at various levels within the encoder part of these autoencoders significantly improves their discriminative feature learning capabilities. An Extreme Learning Machine (ELM) with a single layer of feedforward is trained to classify skin malignancies using the characteristics that were recovered from the bottleneck layers of these autoencoders. The 'HAM10000' and 'ISIC-2017' are two publicly available datasets used to thoroughly assess the suggested approach. The experimental findings demonstrate the accuracy and robustness of the proposed technique, with AUC, precision, and accuracy values for the 'HAM10000' dataset being 0.98, 97.68% and 97.66%, and for the 'ISIC-2017' dataset being 0.95, 86.75% and 86.68%, respectively. This study highlights the possibility of the suggested approach for accurate detection of skin cancer.

关键词： Convolution neural networks Skin lesion classification Deep learning autoencoder Extreme learning machine

来源：评论

学校读者我要写书评

暂无评论

Enhancing feature learning of hyperspectral imaging using shallow autoencoder by adding parallel paths encoding

引用

SCIENTIFIC REPORTS 2025年第1期15卷 1-21页

作者： Noor Asmat, Bibi Syed Muhammad Bilal, Hafiz Uddin, M. Irfan Khalid Karim, Faten Mostafa, Samih M. Varela-Aldas, Jose Natl Univ Sci & Technol Sch Elect Engn & Comp Sci Islamabad Pakistan Kohat Univ Sci & Technol Inst Comp Kohat Pakistan Princess Nourah bint Abdulrahman Univ Coll Comp & Informat Sci Dept Comp Sci POB 84428 Riyadh 11671 Saudi Arabia South Valley Univ Fac Comp & Informat Comp Sci Dept Qena 83523 Egypt Univ Tecnol Indoamer Fac Ingn Ctr Invest MIST Ambato 180103 Ecuador

Conventional image formats have limited information conveyance, while Hyperspectral Imaging (HSI) offers a broader representation through continuous spectral bands, capturing hundreds of spectral features. However, this abundance leads to redundant information, posing a computational challenge for deep learning models. Thus, models must effectively extract indicative features. HSI's non-linear nature, influenced by environmental factors, necessitates both linear and non-linear modeling techniques for feature extraction. While PCA and ICA, being linear methods, may overlook complex patterns, autoencoders (AE) can capture and represent non-linear features. Yet, AEs can be biased by unbalanced datasets, emphasizing majority class features and neglecting minority class characteristics, highlighting the need for careful dataset preparation. To address this, the Dual-Path AE (D-Path-AE) model has been proposed, which enhances non-linear feature acquisition through concurrent encoding pathways. This model also employs a down-sampling strategy to reduce bias towards majority classes. The study compared the efficacy of dimensionality reduction using the Na & iuml;ve autoencoder (Na & iuml;ve AE) and D-Path-AE. Classification capabilities were assessed using Decision Tree, Support Vector Machine, and K-Nearest Neighbors (KNN) classifiers on datasets from Pavia Center, Salinas, and Kennedy Space Center. Results demonstrate that the D-Path-AE outperforms both linear dimensionality reduction models and Na & iuml;ve AE, achieving an Overall Accuracy of up to 98.31% on the Pavia Center dataset using the KNN classifier, indicating superior classification capabilities.

关键词： Classification autoencoder CNN Feature learning Hyperspectral imaging Remote sensing Land cover 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

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：