Automatic feature extraction in large fusion databases by using deep learning approach

Farías, Gonzalo; Dormido-Canto, S.; Vega, J.; Rattá, G.A.; Vargas, Héctor; Hermosilla, Gabriel; Alfaro, Luis; Valencia, Agustín

doi:10.1016/j.fusengdes.2016.06.016

Cited by 29 publications

(12 citation statements)

References 2 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The processing and feature extraction of large amounts of hyperspectral data requires appropriate methods. Deep learning (DL) is effective and popular for handling complex classification problems in large-capacity data [22]. CNN is one of the most popular deep learning models, employing local receptive fields, weight sharing, and subsampling [23], [24].…”

Section: Related Workmentioning

confidence: 99%

Rapid Vitality Estimation and Prediction of Corn Seeds Based on Spectra and Images Using Deep Learning and Hyperspectral Imaging Techniques

et al. 2020

View full text Add to dashboard Cite

Highly viable seeds are of great significance for agricultural development, and the traditional corn seed vigor detection method is time-consuming and laborious. In this paper, the spectral and image information of hyperspectral imaging was used, and a distinction between seed vigor detection and prediction was proposed. The potential of hyperspectral imaging technology and convolutional neural networks (CNNs) to identify and predict maize seed vitality was evaluated. The hyperspectral information in 10 hours before the germination of four vigor level seeds (144 samples each) was collected. A support vector machine, extreme learning machine, and one-dimensional convolutional neural network (1DCNN) were used to model the spectral data set, comparing the effects of multidimensional scattering correction and principal component analysis. 1DCNN performed best on the original spectral data, reaching an accurate recognition of 90.11%. According to the spectral changes of the seed germination, the first three hours of data were selected for prediction, which had higher recognition accuracy than the test set. The image-based 2DCNN model achieved 99.96% accurate recognition at a fast convergence speed. By differentiating the spectra and image information, the various CNN models can achieve accurate detection and prediction, providing a framework to advance research on seed germination.

show abstract

Section: Related Workmentioning

confidence: 99%

Rapid Vitality Estimation and Prediction of Corn Seeds Based on Spectra and Images Using Deep Learning and Hyperspectral Imaging Techniques

et al. 2020

View full text Add to dashboard Cite

show abstract

“…This study is necessary to delete irrelevant or unimportant attributes to eliminate the interference of irrelevant features when using the data with higher dimensions [15]; (3) Effective feature extraction in deep learning: Data-driven deep learning analysis has been developed and applied in many fields. The ability to fit and extract features has been improved by combining multiple processing layers in a variety of data analysis tasks [16]; (4) The attribute reduction of rough set theory is an extension of the theory of modeling ambiguity and imprecision [17]. The designed attribute table is composed of multiple, highly reliable symmetric attributes in the adopted theoretical model.…”

Section: Introductionmentioning

confidence: 99%

Using Neighborhood Rough Set Theory to Address the Smart Elderly Care in Multi-Level Attributes

Zhou

Tan

et al. 2020

Symmetry

View full text Add to dashboard Cite

The neighborhood rough set theory was adopted for attributes reduction and the weight distribution of condition attributes based on the concept of importance level. Smart elderly care coverage rate is low in China. A decisive role in the adoption of smart elderly care is still a problem that needs to be addressed. This study contributes to the adoption of smart elderly care was selected as the decision attribute. The remaining attributes are used as conditional attributes and the multi-level symmetric attribute set for assessing acceptance of smart elderly care. Prior studies are not included smart elderly care adoption attributes in multi-levels; hence, this problem needs to be addressed. The results of this study indicate that the condition attribute of gender has the greatest influence on the decision attribute. The condition attribute of living expenses for smart elderly care has the second largest impact on decision attribute. Children’s support for the elderly decency of the novel elderly care system and the acceptance of non-traditional elderly care methods belong to the primary condition attribute of traditional concept. The result indicates traditional concepts have a certain impact on the adoption of smart elderly care and a condition attribute of residence also has a slight influence on the symmetric decision attribute. The sensitivity analysis shows the insights for uncertainties and provides as a basis for the analysis of the attributes in the smart elderly care service adoption.

show abstract

“…As an automatic feature extraction process, deep learning can learn high-level abstract features from original inputs (Farias et al, 2016 ). To further explore the effectiveness of convolutional BiLSTM, Principal Component Analysis (PCA) (Shlens, 2014 ) was utilized to visualize the input features and each LSTM unit's output in the last bidirectional layer with TEST50.…”

Section: Resultsmentioning

confidence: 99%

TMPSS: A Deep Learning-Based Predictor for Secondary Structure and Topology Structure Prediction of Alpha-Helical Transmembrane Proteins

Liu

Gong

Bao

et al. 2021

Front. Bioeng. Biotechnol.

View full text Add to dashboard Cite

Alpha transmembrane proteins (αTMPs) profoundly affect many critical biological processes and are major drug targets due to their pivotal protein functions. At present, even though the non-transmembrane secondary structures are highly relevant to the biological functions of αTMPs along with their transmembrane structures, they have not been unified to be studied yet. In this study, we present a novel computational method, TMPSS, to predict the secondary structures in non-transmembrane parts and the topology structures in transmembrane parts of αTMPs. TMPSS applied a Convolutional Neural Network (CNN), combined with an attention-enhanced Bidirectional Long Short-Term Memory (BiLSTM) network, to extract the local contexts and long-distance interdependencies from primary sequences. In addition, a multi-task learning strategy was used to predict the secondary structures and the transmembrane helixes. TMPSS was thoroughly trained and tested against a non-redundant independent dataset, where the Q3 secondary structure prediction accuracy achieved 78% in the non-transmembrane region, and the accuracy of the transmembrane region prediction achieved 90%. In sum, our method showcased a unified model for predicting the secondary structure and topology structure of αTMPs by only utilizing features generated from primary sequences and provided a steady and fast prediction, which promisingly improves the structural studies on αTMPs.

show abstract

Automatic feature extraction in large fusion databases by using deep learning approach

Cited by 29 publications

References 2 publications

Rapid Vitality Estimation and Prediction of Corn Seeds Based on Spectra and Images Using Deep Learning and Hyperspectral Imaging Techniques

Rapid Vitality Estimation and Prediction of Corn Seeds Based on Spectra and Images Using Deep Learning and Hyperspectral Imaging Techniques

Using Neighborhood Rough Set Theory to Address the Smart Elderly Care in Multi-Level Attributes

TMPSS: A Deep Learning-Based Predictor for Secondary Structure and Topology Structure Prediction of Alpha-Helical Transmembrane Proteins

Contact Info

Product

Resources

About