CancelOut: A Layer for Feature Selection in Deep Neural Networks

2019 ◽  
pp. 72-83
Author(s):  
Vadim Borisov ◽  
Johannes Haug ◽  
Gjergji Kasneci
Keyword(s):  
Neural Networks ◽  
Feature Selection ◽  
Deep Neural Networks

Deep-gKnock: Nonlinear group-feature selection with deep neural networks

2021 ◽  
Vol 135 ◽  
pp. 139-147
Author(s):  
Guangyu Zhu ◽  
Tingting Zhao
Keyword(s):  
Neural Networks ◽  
Feature Selection ◽  
Deep Neural Networks

scholarly journals An Automated ECG Beat Classification System Using Deep Neural Networks with an Unsupervised Feature Extraction Technique

2019 ◽  
Vol 9 (14) ◽  
pp. 2921 ◽  
Author(s):  
Siti Nurmaini ◽  
Radiyati Umi Partan ◽  
Wahyu Caesarendra ◽  
Tresna Dewi ◽  
Muhammad Naufal Rahmatullah ◽  
...  
Keyword(s):  
Machine Learning ◽  
Neural Networks ◽  
Feature Extraction ◽  
Feature Selection ◽  
Deep Neural Networks ◽  
Machine Learning Technique ◽  
Proposed Model ◽  
Learning Technique ◽  
Processing Steps ◽  
Unsupervised Feature Extraction

An automated classification system based on a Deep Learning (DL) technique for Cardiac Disease (CD) monitoring and detection is proposed in this paper. The proposed DL architecture is divided into Deep Auto-Encoders (DAEs) as an unsupervised form of feature learning and Deep Neural Networks (DNNs) as a classifier. The objective of this study is to improve on the previous machine learning technique that consists of several data processing steps such as feature extraction and feature selection or feature reduction. It is also noticed that the previously used machine learning technique required human interference and expertise in determining robust features, yet was time-consuming in the labeling and data processing steps. In contrast, DL enables an embedded feature extraction and feature selection in DAEs pre-training and DNNs fine-tuning process directly from raw data. Hence, DAEs is able to extract high-level of features not only from the training data but also from unseen data. The proposed model uses 10 classes of imbalanced data from ECG signals. Since it is related to the cardiac region, abnormality is usually considered for an early diagnosis of CD. In order to validate the result, the proposed model is compared with the shallow models and DL approaches. Results found that the proposed method achieved a promising performance with 99.73% accuracy, 91.20% sensitivity, 93.60% precision, 99.80% specificity, and a 91.80% F1-Score. Moreover, both the Receiver Operating Characteristic (ROC) curve and the Precision-Recall (PR) curve from the confusion matrix showed that the developed model is a good classifier. The developed model based on unsupervised feature extraction and deep neural network is ready to be used on a large population before its installation for clinical usage.

scholarly journals Classifying Breast Cancer Subtypes Using Deep Neural Networks Based on Multi-Omics Data

Genes ◽  
2020 ◽  
Vol 11 (8) ◽  
pp. 888
Author(s):  
Yuqi Lin ◽  
Wen Zhang ◽  
Huanshen Cao ◽  
Gaoyang Li ◽  
Wei Du
Keyword(s):  
Breast Cancer ◽  
Neural Networks ◽  
Feature Selection ◽  
Deep Neural Networks ◽  
Selection Process ◽  
Breast Cancer Subtype ◽  
The Cancer Genome Atlas ◽  
Breast Cancer Subtypes ◽  
Omics Data ◽  
Cancer Subtypes

With the high prevalence of breast cancer, it is urgent to find out the intrinsic difference between various subtypes, so as to infer the underlying mechanisms. Given the available multi-omics data, their proper integration can improve the accuracy of breast cancer subtype recognition. In this study, DeepMO, a model using deep neural networks based on multi-omics data, was employed for classifying breast cancer subtypes. Three types of omics data including mRNA data, DNA methylation data, and copy number variation (CNV) data were collected from The Cancer Genome Atlas (TCGA). After data preprocessing and feature selection, each type of omics data was input into the deep neural network, which consists of an encoding subnetwork and a classification subnetwork. The results of DeepMO based on multi-omics on binary classification are better than other methods in terms of accuracy and area under the curve (AUC). Moreover, compared with other methods using single omics data and multi-omics data, DeepMO also had a higher prediction accuracy on multi-classification. We also validated the effect of feature selection on DeepMO. Finally, we analyzed the enrichment gene ontology (GO) terms and biological pathways of these significant genes, which were discovered during the feature selection process. We believe that the proposed model is useful for multi-omics data analysis.

Sign in / Sign up

Export Citation Format

Share Document