scholarly journals Image fusion based on shift invariant shearlet transform and stacked sparse autoencoder

2018 ◽  
Vol 12 (2) ◽  
pp. 73-84 ◽  
Author(s):  
Peng-Fei Wang ◽  
Xiao-Qing Luo ◽  
Xin-Yi Li ◽  
Zhan-Cheng Zhang
Keyword(s):  
Feature Extraction ◽  
Image Fusion ◽  
High Frequency ◽  
Extraction Method ◽  
Fusion Rule ◽  
Complex Data ◽  
Shearlet Transform ◽  
Feature Extraction Method ◽  
Sparse Autoencoder ◽  
Stacked Sparse Autoencoder

Stacked sparse autoencoder is an efficient unsupervised feature extraction method, which has excellent ability in representation of complex data. Besides, shift invariant shearlet transform is a state-of-the-art multiscale decomposition tool, which is superior to traditional tools in many aspects. Motivated by the advantages mentioned above, a novel stacked sparse autoencoder and shift invariant shearlet transform-based image fusion method is proposed. First, the source images are decomposed into low- and high-frequency subbands by shift invariant shearlet transform; second, a two-layer stacked sparse autoencoder is adopted as a feature extraction method to get deep and sparse representation of high-frequency subbands; third, a stacked sparse autoencoder feature-based choose-max fusion rule is proposed to fuse the high-frequency subband coefficients; then, a weighted average fusion rule is adopted to merge the low-frequency subband coefficients; finally, the fused image is obtained by inverse shift invariant shearlet transform. Experimental results show the proposed method is superior to the conventional methods both in terms of subjective and objective evaluations.

scholarly journals A Hybrid Wi-Fi Fingerprint-Based Localization Scheme Achieved by Combining Fisher Score and Stacked Sparse Autoencoder Algorithms

2020 ◽  
Vol 2020 ◽  
pp. 1-14
Author(s):  
Zhongyuan Wang ◽  
Zijian Wang ◽  
Li Fan ◽  
Zhihao Yu
Keyword(s):  
Feature Extraction ◽  
Indoor Localization ◽  
Support Vector ◽  
Fisher Score ◽  
Feature Extraction Method ◽  
Localization Scheme ◽  
Localization Model ◽  
Localization Errors ◽  
Sparse Autoencoder ◽  
Stacked Sparse Autoencoder

Along with the advancement of wireless technology, indoor localization technology based on Wi-Fi has received considerable attention from academia and industry. The fingerprint-based method is the mainstream approach for Wi-Fi indoor localization and can be easily implemented without additional hardware. However, signal fluctuations constitute a critical issue pertaining to the extraction of robust features to achieve the required localization performance. This study presents a fingerprint feature extraction method commonly referred to as the Fisher score–stacked sparse autoencoder (Fisher–SSAE) method. Some features with low Fisher scores were eliminated, and the representative features were then extracted by the SSAE. Furthermore, this study establishes a hybrid localization model constructed with the use of the global model and the submodel to avoid significant coordinate localization errors attributed to subregional localization errors. Combined with three accessible fingerprint-based positioning methods, namely, the support vector regression, random forest regression, and the multiplayer perceptron classification, the experimental results demonstrate that the proposed methods improve the localization accuracy and response time compared to other feature extraction methods and the single localization model. Compared with some state-of-the-art methods, the proposed methods have better localization performances when large number of features are used.

A Novel Prediction of Quaternary Structural Type of Proteins with Gene Ontology

2020 ◽  
Vol 27 (4) ◽  
pp. 313-320 ◽  
Author(s):  
Xuan Xiao ◽  
Wei-Jie Chen ◽  
Wang-Ren Qiu
Keyword(s):  
Gene Ontology ◽  
Feature Extraction ◽  
Extraction Method ◽  
Quaternary Structure ◽  
Structural Type ◽  
Sequence Information ◽  
Prediction System ◽  
Data Set ◽  
Feature Extraction Method ◽  
Prediction Rate

Background: The information of quaternary structure attributes of proteins is very important because it is closely related to the biological functions of proteins. With the rapid development of new generation sequencing technology, we are facing a challenge: how to automatically identify the four-level attributes of new polypeptide chains according to their sequence information (i.e., whether they are formed as just as a monomer, or as a hetero-oligomer, or a homo-oligomer). Objective: In this article, our goal is to find a new way to represent protein sequences, thereby improving the prediction rate of protein quaternary structure. Methods: In this article, we developed a prediction system for protein quaternary structural type in which a protein sequence was expressed by combining the Pfam functional-domain and gene ontology. turn protein features into digital sequences, and complete the prediction of quaternary structure through specific machine learning algorithms and verification algorithm. Results: Our data set contains 5495 protein samples. Through the method provided in this paper, we classify proteins into monomer, or as a hetero-oligomer, or a homo-oligomer, and the prediction rate is 74.38%, which is 3.24% higher than that of previous studies. Through this new feature extraction method, we can further classify the four-level structure of proteins, and the results are also correspondingly improved. Conclusion: After the applying the new prediction system, compared with the previous results, we have successfully improved the prediction rate. We have reason to believe that the feature extraction method in this paper has better practicability and can be used as a reference for other protein classification problems.

Sign in / Sign up

Export Citation Format

Share Document