检索结果-内蒙古大学图书馆

stacked Denoising Extreme Learning Machine autoencoder Based on Graph Embedding for Feature Representation

IEEE ACCESS 2019年 7卷 13433-13444页

作者： Ge, Hongwei Sun, Weiting Zhao, Mingde Yao, Yao Dalian Univ Technol Coll Comp Sci & Technol Dalian 116023 Peoples R China McGill Univ Sch Comp Sci Montreal PQ H3A 0E9 Canada

Extreme learning machine is characterized by less training parameters, fast training speed, and strong generalization ability. It has been applied to obtain feature representations from the complex data in the tasks of data clustering or classification. In this paper, a graph embedding-based denoising extreme learning machine autoencoder (GDELM-AE) is proposed for capturing the structure of the inputs. Specifically, in GDELM-AE, a graph embedding framework that contains an intrinsic graph and a penalty graph constructed by local Fisher discrimination analysis is integrated into the autoencoder. So, it can exploit both local structure and global structure information in extreme learning machine (ELM) spaces. Further, we propose a stacked graph embedded denoising (SGD)-ELM by stacking several GDELM-AEs. The experimental results on several benchmarks validate that GDELM-AE can obtain efficient and robust feature representation of original data;moreover, the stacked GDELM-AE can obtain high-level and noise-robust representations. The comparative results with the state-of-the-art algorithms indicate that the proposed algorithm can obtain better accuracy as well as faster training speed.

关键词： Extreme learning machine stacked autoencoder denoising graph embedding

来源：评论

学校读者我要写书评

暂无评论

stacked autoencoders and extreme learning machine based hybrid model for electrical load prediction

引用

JOURNAL OF INTELLIGENT & FUZZY SYSTEMS 2019年第4期37卷 5403-5416页

作者： Peng, Wei Xu, Liwen Li, Chengdong Xie, Xiuying Zhang, Guiqing Shandong Jianzhu Univ Sch Informat & Elect Engn Jinan 250101 Shandong Peoples R China Shandong Coinnovat Ctr Green Bldg Jinan 250101 Shandong Peoples R China

Electrical load prediction plays an important role in power system management and economic development. However, because electrical load has non-linear relationships with several factors such as the political environment, the economic policy, the human activities, the irregular behaviors and the other factors, it is quite difficult to predict power load accurately. In order to further improve the electrical load forecasting performance, a hybrid model is proposed in this paper. The proposed hybrid model combines the stacked autoencoders (SAE) and extreme learning machines (ELMs) to learn the characteristics of the time series data of electrical load. In this proposed method, in order to utilize the characteristics of the electrical load in different depths, the outputs of each layer of the SAE are taken as the inputs of one specific ELM. Then, the obtained results from the constructed different ELMs are integrated by the linear regression to obtain the final output. The linear regression part is trained by the least square estimation method. In addition, the hybrid model is applied to predict two real-world electrical load time series. And, detailed comparisons with the SAE, ELM, the back propagation neural network (BPNN), the multiple linear regression (MLR) and the support vector regression (SVR) are done to show the advantages of the proposed forecasting model. Experimental and comparison results demonstrate that the proposed hybrid model can achieve much better performance than the comparative methods in electrical load forecasting application.

关键词： electrical load prediction hybrid model stacked autoencoder extreme learning machine

来源：评论

学校读者我要写书评

暂无评论

stacked autoencoders Using Low-Power Accelerated Architectures for Object Recognition in Autonomous Systems

引用

NEURAL PROCESSING LETTERS 2016年第2期43卷 445-458页

作者： Maria, Joao Amaro, Joao Falcao, Gabriel Alexandre, Luis A. Univ Coimbra Inst Telecomunicacoes Dept Elect & Comp Engn P-3030290 Coimbra Portugal Univ Beira Interior Dept Informat P-6201001 Covilha Portugal Univ Beira Interior Inst Telecomunicacoes P-6201001 Covilha Portugal

This paper investigates low-energy consumption and low-power hardware models and processor architectures for performing the real-time recognition of objects in power-constrained autonomous systems and robots. Most recent developments show that convolutional deep neural networks are currently the state-of-the-art in terms of classification accuracy. In this article we propose to use of a different type of deep neural network-stacked autoencoders-and show that within a limited number of layers and nodes, for accommodating the use of low-power accelerators such as mobile GPUs and FPGAs, we are still able to achieve both classification levels not far from the state-of-the-art and a high number of processed frames per second. We present experiments using the color CIFAR-10 dataset. This enables the adaptation of the architecture to a live feed camera. Another novelty equally proposed for the first time in this work suggests that the training phase can also be performed in these low-power devices, instead of the usual approach that uses a desktop CPU or a GPU to perform this task and only runs the trained network later on the FPGA. This allows incorporating new functionalities as, for example, a robot performing runtime learning.

关键词： Deep learning Neural networks stacked autoencoder Parallel computing FPGAs Mobile GPUs OpenCL Low-power Autonomous systems

来源：评论

学校读者我要写书评

暂无评论

HYPERSPECTRAL IMAGE CLASSIFICATION BASED ON stacked MARGINAL DISCRIMINATIVE autoencoder 37

HYPERSPECTRAL IMAGE CLASSIFICATION BASED ON STACKED MARGINAL...

引用

IEEE International Geoscience & Remote Sensing Symposium

作者： Feng, Jie Liu, Liguo Zhang, Xiangrong Wang, Rongfang Liu, Hongying Xidian Univ Key Lab Intelligent Percept & Image Undersatnding Minist Educ Xian 710071 Shaanxi Peoples R China

ISBN: (纸本)9781509049516

In this paper, a novel stacked marginal discriminative autoencoder (SMDAE) method is proposed for hyperspectral image classification. It uses a deep neural network to learn discriminative features from hyperspectral images automatically. In hyperspectral images, the collection of training samples is difficult. When the number of training samples is not enough, these training samples are difficult to estimate the statistical distribution of hyperspectral images accurately. In order to solve the small sample problem and improve the classification performance of the autoencoder, the marginal samples are selected through the distribution characteristics of samples. The marginal samples are searched based on k nearest neighbors between different classes. These samples are used to fine-tune the SMDAE network. The experimental results show that the proposed SMDAE method can achieve satisfying performance under small training set.

关键词： stacked autoencoder hyperspectral classification deep learning discriminative features marginal samples

来源：评论

学校读者我要写书评

暂无评论

stacked autoencoderS FOR MULTICLASS CHANGE DETECTION IN HYPERSPECTRAL IMAGES 38

STACKED AUTOENCODERS FOR MULTICLASS CHANGE DETECTION IN HYPE...

引用

38th IEEE International Geoscience and Remote Sensing Symposium (IGARSS)

作者： Lopez-Fandino, Javier Garea, Alberto S. Heras, Dora B. Arguello, Francisco Univ Santiago de Compostela Ctr Singular Invest Tecnol Informac CiTIUS Santiago De Compostela Spain

ISBN: (纸本)9781538671504

Change detection (CD) in multitemporal datasets is a key task in remote sensing. In this paper, a scheme to perform multiclass CD for remote sensing hyperspectral datasets extracting features by means of stacked autoencoders (SAEs) is introduced. The scheme combines multiclass and binary CD to obtain an accurate multiclass changemap. The multiclass CD begins with the fusion of the multitemporal data followed by Feature Extraction (FE) by SAEs. The binary CD is based on the spectral information by calculating pixel-wise distances and thresholding, and it also incorporates spatial information through watershed segmentation. The processed image is filtered by using the binary CD map and later classified by a Support VectorMachine or an Extreme LearningMachine algorithm. The scheme was evaluated over a multitemporal hyperspectral dataset obtained fromthe Hyperion sensor. Experimental results show the effectiveness of the proposed scheme using a SAE for extracting the relevant features of the fused information when compared to other published FE methods.

关键词： Hyperspectral Change Detection Feature Extraction stacked autoencoder Support Vector Machine Extreme Learning Machine

来源：评论

学校读者我要写书评

暂无评论

Machine learning-based analysis of multi-region bone fracture detection and classification using biomedical images

引用

Alexandria Engineering Journal 2025年 128卷 186-199页

作者： Alla M. Elsheikh Azhari A. Elhag Mathematics Department Faculty of Science and Arts Alkamil University of Jeddah Jeddah Saudi Arabia Department of Mathematics and Statistics College of Science Taif University Taif Saudi Arabia

Bone fractures are a prevalent medical concern that necessitates precise and prompt diagnosis. Interpreting X-ray pictures to detect fractures is a complex and time-intensive task that requires specialized radiological expertise. This process is further complicated in under-resourced or high-demand clinical settings, when access to proficient radiologists is restricted and diagnostic inaccuracies may occur owing to exhaustion or excessive workload. These issues underscore the pressing necessity for automated, intelligent solutions to aid in diagnosing and classifying bone fractures. This study proposes a Deep Learning-Driven Computer Vision Model for Multi-Region Bone Fracture Detection and Classification (DLCVM-MBFDC) technique. The proposed method commences with a Wiener Filtering (WF) preparation phase to diminish image noise. Subsequently, DenseNet201 is utilized to extract deep features from biological pictures. A stacked autoencoder (SAE) model is employed for fracture identification and classification, while the wild gibbon optimizer algorithm (WGOA) model is utilized for hyperparameter optimization of the SAE model. The efficacy of the DLCVM-MBFDC approach is examined under the Kaggle dataset. The comparison study of the DLCVM-MBFDC approach portrayed a superior accuracy value of 97.85 % over existing models.

关键词： Bone Fracture Detection Wild Gibbon Optimization Weiner Filtering DenseNet201 stacked autoencoder

来源：评论

学校读者我要写书评

暂无评论

LPItabformer: Enhancing generalization in predicting lncRNA-protein interactions via a tabular Transformer

引用

Computational and Structural Biotechnology Journal 2025年 27卷 2323-2335页

作者： Qin Lin Jie Sheng Chang Zhou Tao Xiao Yilei Meng Mingxin Lu Junfang Zhang Xueyun Yan Luying Peng Huaming Cao Li Li State Key Laboratory of Cardiovascular Diseases and Medical Innovation Center Shanghai East Hospital School of Medicine Tongji University Shanghai 200120 China Shanghai Arrhythmias Research Center Shanghai East Hospital Tongji University School of Medicine Shanghai 200120 China Stem Cell Research Center Medical School Tongji University Shanghai 200120 China Teaching Laboratory Center Tongji University School of Medicine Shanghai 200331 China Department of Cardiology Shibei Hospital Shanghai 200435 China

Long-noncoding RNAs (LncRNAs) play important roles in physiological and pathological processes. Accurately predicting lncRNA-protein interactions (LPIs) is vital strategy for clarify functions and pathogenic mechanisms of lncRNAs. Current computational methods for evaluating LPIs with their utility and generalization have significant room for improvement. In this study, data splitting by incorporating protein clusters as group information reveals that lots of LPI prediction methods suffer from generalization flaws due to data leakage caused by ignoring LPI biological properties. To address the issue, we present LPItabformer, a tabular Transformer framework for predicting LPIs, that incorporates a domain shifts with uncertainty (DSU) module for generalization enhancement. The LPItabformer demonstrates a capacity to alleviate the generalization challenges associated with biases in LPI data and preferences in protein binding patterns. In addition, LPItabformer shows greater robustness and generalization on human and mouse LPI datasets compared to state-of-the-art methods. Ultimately, we have verified that the LPItabformer is capable of predicting novel LPIs. Code is available at https://***/Ci-TJ/LPItabformer.

关键词： NcRNA Noncoding RNA LncRNA Long noncoding RNA RBP RNA-binding protein LPI LncRNA-protein interaction RPI RNA-protein interaction SVM Support Vector Machine RF Random Forest LGBM Light Gradient Boosting Machine CTF Conjoint triad feature CNN Convolutional Neural Network SAE stacked autoencoder CLIP-seq Crosslinking Immunoprecipitation Sequencing 5FCV 5-fold cross validation G5FCV Group 5-fold cross validation DSU Domain Shifts with Uncertainty LR Logistic Regression SGD Stochastic Gradient Descent TEDM Transformer Encoder with DSU Module ACC Accuracy AUC Area under the curve PRE Precision SEN Sensitivity SPE Specificity Long non-coding RNA LncRNA-protein interactions Tabular Transformer Generalization Deep learning

来源：评论

学校读者我要写书评

暂无评论

Mutual Information-Weighted Principle Components Identified From the Depth Features of stacked autoencoders and Original Variables for Oil Dry Point Soft Sensor

引用

IEEE ACCESS 2019年 7卷 1981-1990页

作者： Wang, Jie Yan, Xuefeng East China Univ Sci & Technol Minist Educ Key Lab Adv Control & Optimizat Chem Proc Shanghai 200237 Peoples R China

In modern chemical process control, the application of data-driven soft sensor has become increasingly extensive. Feature extraction is an important step in soft sensor. A novel feature extraction and integration method based on stacked autoencoders (SAE) and mutual information (MI)-weighted principle component analysis (PCA) was proposed to solve the loss of information on shallow depth features and original variables in neural network models. First, an SAE model was trained to extract the features of the original variables with varying depths. Second, through an MI indicator, the original variables and features with strong dependency on the outputs were selected. Then, MI was used to assign varied weights to the features and original variables, and the PCA method was used to remove any possible redundancy between the original variables and features of varying depths to obtain the principle components. Finally, the principle components were used to construct a regressor, such as a neural network. The model was first tested using the Boston housing dataset as a benchmark and then applied to the soft sensor of a constant top oil dry point. The proposed model achieved optimal results in terms of the root mean squared error and r indicators in the experiments and was thus proved feasible and useful.

关键词： Feature extraction mutual information soft sensor stacked autoencoder

来源：评论

学校读者我要写书评

暂无评论

Cross-lingual sentiment classification with stacked autoencoders

引用

KNOWLEDGE AND INFORMATION SYSTEMS 2016年第1期47卷 27-44页

作者： Zhou, Guangyou Zhu, Zhiyuan He, Tingting Hu, Xiaohua Tony Cent China Normal Univ Sch Comp Wuhan 430079 Peoples R China Cent China Normal Univ Sch Comp Nat Language Proc Lab Wuhan 430079 Peoples R China Chinese Inst Elect Beijing 100036 Peoples R China Drexel Univ Coll Comp & Informat Philadelphia PA 19104 USA

Cross-lingual sentiment classification is a popular research topic in natural language processing. The fundamental challenge of cross-lingual learning stems from a lack of overlap between the feature spaces of the source language data and the target language data. In this article, we propose a new model which uses stacked autoencoders to learn language-independent high-level feature representations for the both languages in an unsupervised fashion. The proposed framework aims to force the aligned input bilingual sentences into a common latent space, and the objective function is defined by minimizing the input and output vector representations as well as the distance of the common representations in the latent space. Sentiment classifiers trained on the source language can be adapted to predict sentiment polarity of the target language with the language-independent high-level feature representations. We conduct extensive experiments on English-Chinese sentiment classification tasks of multiple data sets. Our experimental results demonstrate the efficacy of the proposed cross-lingual approach.

关键词： Sentiment classification Cross-lingual stacked autoencoder

来源：评论

学校读者我要写书评

暂无评论

Micro-crack detection method of steel beam surface using stacked autoencoders on massive full-scale sensing strains

引用

STRUCTURAL HEALTH MONITORING-AN INTERNATIONAL JOURNAL 2020年第4期19卷 1175-1187页

作者： Song, Qingsong Chen, Yu Oskoui, Elias Abdoli Fang, Zheng Taylor, Todd Tang, Guangwu Zhao, Xiangmo Ansari, Farhad Changan Univ Sch Informat Engn Xian Peoples R China Univ Illinois Dept Civil & Mat Engn 842 W Taylor St Chicago IL 60607 USA China Merchants Chongqing Commun Technol Res & De State Key Lab Bridge Engn Struct Dynam Chongqing Peoples R China Hohai Univ Coll Water Conservancy & Hydropower Engn Nanjing Peoples R China

Accurate micro-crack detections on the whole surface of civil structures have great significance. Distributed optical fiber sensor based on Brillouin optical time-domain analysis technology exhibits great facility to measure strain distributions along the whole surface of structures with a high spatial resolution, thus providing a potential and competitive solution to the detection problem. However, mainly due to low signal-to-noise ratio in measurements, such sensor system is still limited in crack detection-based structural health monitoring applications. How to extract high-quality micro-crack feature representations from the low signal-to-noise ratio-distributed strain measurements is crucial to solve the problem. It has been demonstrated in field of pattern recognition that deep learning can automatically extract high-quality noise-robust feature representations from mass chaos data. Therefore, a micro-crack detection method is proposed herein based on deep learning to analyze the full-scale strain measurements. Each measurement is normalized and segmented into a set of equal-length subsequences. autoencoders, a typical kind of building block of deep neural network, are stacked layer-wise into a deep network and then exploited to automatically extract feature representations from the subsequences. Each extracted feature representation is labeled as one of the two categories by a Softmax regression. One category originates in the subsequences acquired from structure sections with crack defects and another from sections without any cracks. The micro-crack detections are achieved by solving such a crack/non-crack binary classification problem. A 15-m-long steel I-beam with artifact crack defects is built up in laboratory to verify the proposed method. Experimental results demonstrate that the minimum size of detectable crack opening width reaches to 23 mu m, and besides, the proposed method is significantly better than traditional Fisher linear discriminant analys

关键词： Structural health monitoring crack detection pattern recognition deep learning feature representation stacked autoencoder Brillouin optical time-domain analyzer

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：