Deep Learning and Mathematical Models in Dermatology

Iglesias‐Puzas, Álvaro; Boixeda, P.

doi:10.1016/j.adengl.2020.03.005

Cited by 4 publications

(3 citation statements)

References 19 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Previous studies have shown that convolutional neural networks (CNN) can extract deep features. The feature extractor at each layer can use the convolutional layer and the pooling layer to convert the input raw data to complex deep features, thereby reducing the data noise problem caused by external environmental interference [ 71 ]. Especially when traditional methods cannot collect enough features to support accurate detection, CNN can still extract more detailed features, which will help to increase the detection potential [ 23 ].…”

Section: Discussionmentioning

confidence: 99%

Estimation of Leaf Nitrogen Content in Wheat Based on Fusion of Spectral Features and Deep Features from Near Infrared Hyperspectral Imagery

Yang

Yao

et al. 2021

Sensors

View full text Add to dashboard Cite

Nitrogen is an important indicator for monitoring wheat growth. The rapid development and wide application of non-destructive detection provide many approaches for estimating leaf nitrogen content (LNC) in wheat. Previous studies have shown that better results have been obtained in the estimation of LNC in wheat based on spectral features. However, the lack of automatically extracted features leads to poor universality of the estimation model. Therefore, a feature fusion method for estimating LNC in wheat by combining spectral features with deep features (spatial features) was proposed. The deep features were automatically obtained with a convolutional neural network model based on the PyTorch framework. The spectral features were obtained using spectral information including position features (PFs) and vegetation indices (VIs). Different models based on feature combination for evaluating LNC in wheat were constructed: partial least squares regression (PLS), gradient boosting decision tree (GBDT), and support vector regression (SVR). The results indicate that the model based on the fusion feature from near-ground hyperspectral imagery has good estimation effect. In particular, the estimation accuracy of the GBDT model is the best (R2 = 0.975 for calibration set, R2 = 0.861 for validation set). These findings demonstrate that the approach proposed in this study improved the estimation performance of LNC in wheat, which could provide technical support in wheat growth monitoring.

show abstract

Section: Discussionmentioning

confidence: 99%

Estimation of Leaf Nitrogen Content in Wheat Based on Fusion of Spectral Features and Deep Features from Near Infrared Hyperspectral Imagery

Yang

Yao

et al. 2021

Sensors

View full text Add to dashboard Cite

show abstract

“…Since there is a necessity to learn and update different characteristics of biomedical signals as it varies for every time period a DCS will be much support to correct the raw data behavior ( 18 ). The process involved in DCS saves the learning time as multi-tasking is performed with automatic feature learning behavior as the structure of DCS is designed in an anatomical way ( 19 ). Deep learning methods are used for biomedical signal processing in this part because many significant features may be extracted within reasonable bounds.…”

Section: Optimization Algorithmmentioning

confidence: 99%

Deep Conviction Systems for Biomedical Applications Using Intuiting Procedures With Cross Point Approach

Manoharan¹,

Shitharth

Yafoz

et al. 2022

Front. Public Health

View full text Add to dashboard Cite

The production, testing, and processing of signals without any interpretation is a crucial task with time scale periods in today's biological applications. As a result, the proposed work attempts to use a deep learning model to handle difficulties that arise during the processing stage of biomedical information. Deep Conviction Systems (DCS) are employed at the integration step for this procedure, which uses classification processes with a large number of characteristics. In addition, a novel system model for analyzing the behavior of biomedical signals has been developed, complete with an output tracking mechanism that delivers transceiver results in a low-power implementation approach. Because low-power transceivers are integrated, the cost of implementation for designated output units will be decreased. To prove the effectiveness of DCS feasibility, convergence and robustness characteristics are observed by incorporating an interface system that is processed with a deep learning toolbox. They compared test results using DCS to prove that all experimental scenarios prove to be much more effective for about 79 percent for variations with time periods.

show abstract

“…DL can process more complex data and improve the algorithm of neural network performance, generalization ability, and cross-server distributed training ability, all of which are superior to the performance of shallow artificial neural networks (10). With the help of well-labeled, large data sets, DL can be used for accurate classification of medical images, and it has shown unique advantages in a variety of medical disciplines, including ultrasound (11), dermatology (12,13), pathology (14), radiology (15,16), and ophthalmology. In the field of ophthalmology, the DL system (DLS) has been developed for the detection of various diseases, such as diabetic retinopathy, age-related macular degeneration, glaucoma, and retinopathy of prematurity and cardiovascular diseases.…”

Section: Ai Machine Learning and DLmentioning

confidence: 99%