Detecting Local Manifold Structure for Unsupervised Feature Selection

Feng, Dingcheng; Chen, Feng; Wang, Xu

doi:10.1016/s1874-1029(14)60362-1

Cited by 8 publications

(4 citation statements)

References 10 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Thus, both sensory experience and mental imagery of space have an impact on spatial activity. Behavioral geography also emphasizes the influence of spatial cognition on spatial decision-making behavior, and this theory has been widely used to explain specific issues in daily life, including traffic prediction (Theo and Harry, 2004), shopping spatial behavior (Wang and Zhang, 2001;Feng et al, 2007), and commuting behavior (Liu and Hou, 2014). From the library perspective, spatial cognition is also crucial to readers' behavior in using library space, and the influence of both the objective environment and subjective preferences on spatial behavior can be realized through the mediating role of spatial cognition.…”

Section: Theoretical Background and Research Modelmentioning

confidence: 99%

A theoretical model and empirical analysis of university library readers' spatial cognition

Jiang

Chen

Chi

2022

LHT

View full text Add to dashboard Cite

PurposeThe practice of renovation and construction of university libraries is flourishing, but how to attract readers to use the library is an issue that urgently needs to be explored. Spatial cognition is a subjective judgment of a person's tendency to take action in the future and implies behavioral intention. Based on the sensory–image–cognition relationship, a theoretical model of university library readers' spatial cognition is conducted, and the influencing factors and mechanisms of spatial cognition are explored based on empirical data to provide theoretical references for spatial practices in university libraries.Design/methodology/approachA visual and art-based mental map approach is introduced based on a questionnaire survey. The questionnaire is mainly used for the specific evaluation of spatial use and the breakdown of the detailed elements, while the mental map method is mainly used for the evaluation of readers' spatial cognition. Relevant empirical data are collected from the library of the Zhejiang University of Technology.FindingsThe results indicate that readers' spatial sensory experience and mental imagery have positive effects on readers' behavior via the mediator spatial cognition, readers' spatial sensory experience and mental imagery have a positive effect on readers' spatial cognition and spatial cognition has a significant effect on readers' behavior.Originality/valueThe main contribution of this study is to construct a theoretical model of readers' spatial cognition and to explore the factors that have an impact on spatial cognition and the influence of cognition on behavior. This provides a more rational and in-depth thinking paradigm for the study of university library space and provides theoretical references for library practice.

show abstract

Section: Theoretical Background and Research Modelmentioning

confidence: 99%

A theoretical model and empirical analysis of university library readers' spatial cognition

Jiang

Chen

Chi

2022

LHT

View full text Add to dashboard Cite

show abstract

“…The formula ( 6) is used to determine the probability of 1 of the visible layer, and then to obtain a reconstruction of the visible layer. The RBM parameters are updated by maximize the log likelihood function of stochastic gradient ascent method with reconstruction data of visible layer and the original visible layer data, the main basis of the weights updating is the correlation difference between the hidden layer activation unit and the visual layer inputs, as in equation (7)(8)(9).…”

Section: B Contrast Divergence Gradient Approximationmentioning

confidence: 99%

“…The kernel principal component analysis (Kernel PCA, KPCA) [7] and Kernel Discriminant Analysis (KLDA) [8] are representative kernel method. The manifold learning algorithms applied to hyperspectral image dimensionality reduction mainly include local linear embedding (LLE), isometric mapping (Isomap), Laplacian Eigenmaps (LE), local tangent space alignment(LTSA) [9][10][11][12] and so on.…”

Section: Introductionmentioning

confidence: 99%

Hyperspectral Data Feature Extraction Using Deep Belief Network

Jiang

Xue

Zhang

et al. 2016

International Journal on Smart Sensing and Intelligent Systems

View full text Add to dashboard Cite

Abstract-Hyperspectral data has rich spectrum information, strong correlation between bands and high data redundancy. Feature band extraction of hyperspectral data is a prerequisite and an important basis for the subsequent study of classification and target recognition. Deep belief network is a kind of deep learning model, the paper proposed a deep belief network to realize the characteristics band extraction of hyperspectral data, and use the advantages of unsupervised and supervised learning of deep belief network, and to extract feature bands of spectral data from low level to high-level gradually.The extracted feature band has a stronger discriminant performance, so that it can better to classify hyperspectral data. Finally, the AVIRIS data is used to extract the feature band, and the SVM classifier is used to classify the data, which verifies the effectiveness of the method.

show abstract

“…However, most of these methods adopt a linear model and smoothing threshold function for feature extraction. Other approaches such as a Kernel-based transformation [32] and manifold learning algorithm [33] are based on nonlinear models.…”

Section: Introductionmentioning

confidence: 99%

Quantification of Hydrocarbon Abundance in Soils Using Deep Learning with Dropout and Hyperspectral Data

et al. 2019

View full text Add to dashboard Cite

Terrestrial hydrocarbon spills have the potential to cause significant soil degradation across large areas. Identification and remedial measures taken at an early stage are therefore important. Reflectance spectroscopy is a rapid remote sensing method that has proven capable of characterizing hydrocarbon-contaminated soils. In this paper, we develop a deep learning approach to estimate the amount of Hydrocarbon (HC) mixed with different soil samples using a three-term backpropagation algorithm with dropout. The dropout was used to avoid overfitting and reduce computational complexity. A Hyspex SWIR 384 m camera measured the reflectance of the samples obtained by mixing and homogenizing four different soil types with four different HC substances, respectively. The datasets were fed into the proposed deep learning neural network to quantify the amount of HCs in each dataset. Individual validation of all the dataset shows excellent prediction estimation of the HC content with an average mean square error of ~ 2 . 2 × 10 - 4 . The results with remote sensed data captured by an airborne system validate the approach. This demonstrates that a deep learning approach coupled with hyperspectral imaging techniques can be used for rapid identification and estimation of HCs in soils, which could be useful in estimating the quantity of HC spills at an early stage.

show abstract

Detecting Local Manifold Structure for Unsupervised Feature Selection

Cited by 8 publications

References 10 publications

A theoretical model and empirical analysis of university library readers' spatial cognition

A theoretical model and empirical analysis of university library readers' spatial cognition

Hyperspectral Data Feature Extraction Using Deep Belief Network

Quantification of Hydrocarbon Abundance in Soils Using Deep Learning with Dropout and Hyperspectral Data

Contact Info

Product

Resources

About