Deep Learning Methods Research Articles

Atmospheric NO2 concentration prediction with statistical and hybrid deep learning methods

Atmospheric NO2 concentration prediction with statistical and hybrid deep learning methods

A deep learning method for bias correction of wind field in the South China Sea

A deep learning method for bias correction of wind field in the South China Sea

Multimodal data deep learning method for predicting symptomatic pneumonitis caused by lung cancer radiotherapy combined with immunotherapy

Multimodal data deep learning method for predicting symptomatic pneumonitis caused by lung cancer radiotherapy combined with immunotherapy

A hybrid CNN model for classification of motor tasks obtained from hybrid BCI system

The Hybrid-Brain Computer Interface (BCI) has shown improved performance, especially in classifying multi-class data. Two non-invasive BCI modules are combined to achieve an improved classification which are Electroencephalogram (EEG) and functional Near Infra-red Spectroscopy (fNIRS). Classifying contralateral and ipsilateral motor movements is found challenging among the other mental activity signals. The current work focuses on the performance of deep learning methods like – Convolutional Neural Networks (CNN) and Bidirectional Long-Short term memory (Bi-LSTM) in classifying a four-class motor execution of Right Hand, Left Hand, Right Arm and Left Arm taken from the CORE dataset. The model performance was evaluated using metrics such as Accuracy, F1 – score, Precision, Recall, AUC and ROC curve. The CNN and Hybrid CNN models have resulted in 98.3% and 99% accuracy respectively.

A Deep Learning Method for Identifying G-Protein Coupled Receptors based on a Feature Pyramid Network and Attention Mechanism

A Deep Learning Method for Identifying G-Protein Coupled Receptors based on a Feature Pyramid Network and Attention Mechanism

NRGCNMDA: Microbe-Drug Association Prediction Based on Residual Graph Convolutional Networks and Conditional Random Fields.

The process of discovering new drugs related to microbes through traditional biological methods is lengthy and costly. In response to these issues, a new computational model (NRGCNMDA) is proposed to predict microbe-drug associations. First, Node2vec is used to extract potential associations between microorganisms and drugs, and a heterogeneous network of microbes and drugs is constructed. Then, a Graph Convolutional Network incorporating a fusion residual network mechanism (REGCN) is utilized to learn meaningful high-order similarity features. In addition, conditional random fields (CRF) are applied to ensure that microbes and drugs have similar feature embeddings. Finally, unobserved microbe-drug associations are scored based on combined embeddings. The experimental findings demonstrate that the NRGCNMDA approach outperforms several existing deep learning methods, and its AUC and AUPR values are 95.16% and 93.02%, respectively. The case study demonstrates that NRGCNMDA accurately predicts drugs associated with Enterococcus faecalis and Listeria monocytogenes, as well as microbes associated with ibuprofen and tetracycline.

Deep learning-based differential gut flora for prediction of Parkinson's.

There had been extensive research on the role of the gut microbiota in human health and disease. Increasing evidence suggested that the gut-brain axis played a crucial role in Parkinson's disease, with changes in the gut microbiota speculated to be involved in the pathogenesis of Parkinson's disease or interfere with its treatment. However, studies utilizing deep learning methods to predict Parkinson's disease through the gut microbiota were still limited. Therefore, the goal of this study was to develop an efficient and accurate prediction method based on deep learning by thoroughly analyzing gut microbiota data to achieve the diagnosis of Parkinson's disease. This study proposed a method for predicting Parkinson's disease using differential gut microbiota, named the Parkinson Gut Prediction Method (PGPM). Initially, differential gut microbiota data were extracted from 39 Parkinson's disease (PD) patients and their corresponding 39 healthy spouses. Subsequently, a preprocessing method called CRFS (combined ranking using random forest scores and principal component analysis contributions) was introduced for feature selection. Following this, the proposed LSIM (LSTM-penultimate to SVM Input Method) approach was utilized for classifying Parkinson's patients. Finally, a soft voting mechanism was employed to predict Parkinson's disease patients. The research results demonstrated that the Parkinson gut prediction method (PGPM), which utilized differential gut microbiota, performed excellently. The method achieved a mean accuracy (ACC) of 0.85, an area under the curve (AUC) of 0.92, and a receiver operating characteristic (ROC) score of 0.92. In summary, this method demonstrated excellent performance in predicting Parkinson's disease, allowing for more accurate predictions of Parkinson's disease.

Munsell Soil Colour Prediction from the Soil and Soil Colour Book Using Patching Method and Deep Learning Techniques.

Soil colour is a key indicator of soil health and the associated properties. In agriculture, soil colour provides farmers and advises with a visual guide to interpret soil functions and performance. Munsell colour charts have been used to determine soil colour for many years, but the process is fallible, as it depends on the user's perception. As smartphones are widely used and come with high-quality cameras, a popular one was used for capturing images for this study. This study aims to predict Munsell soil colour (MSC) from the Munsell soil colour book (MSCB) by using deep learning techniques on mobile-captured images. MSCB contains 14 pages and 443 colour chips. So, the number of classes for chip-by-chip prediction is very high, and the captured images are inadequate to train and validate using deep learning methods; thus, a patch-based mechanism was proposed to enrich the dataset. So, the course of action is to find the prediction accuracy of MSC for both page level and chip level by evaluating multiple deep learning methods combined with a patch-based mechanism. The analysis also provides knowledge about the best deep learning technique for MSC prediction. Without patching, the accuracy for chip-level prediction is below 40%, the page-level prediction is below 65%, and the accuracy with patching is around 95% for both, which is significant. Lastly, this study provides insights into the application of the proposed techniques and analysis within real-world soil and provides results with higher accuracy with a limited number of soil samples, indicating the proposed method's potential scalability and effectiveness with larger datasets.

Ensemble learning-based predictor for driver synonymous mutation with sequence representation.

Synonymous mutations, once considered neutral, are now understood to have significant implications for a variety of diseases, particularly cancer. It is indispensable to identify these driver synonymous mutations in human cancers, yet current methods are constrained by data limitations. In this study, we initially investigate the impact of sequence-based features, including DNA shape, physicochemical properties and one-hot encoding of nucleotides, and deep learning-derived features from pre-trained chemical molecule language models based on BERT. Subsequently, we propose EPEL, an effect predictor for synonymous mutations employing ensemble learning. EPEL combines five tree-based models and optimizes feature selection to enhance predictive accuracy. Notably, the incorporation of DNA shape features and deep learning-derived features from chemical molecule represents a pioneering effect in assessing the impact of synonymous mutations in cancer. Compared to existing state-of-the-art methods, EPEL demonstrates superior performance on independent test datasets. Furthermore, our analysis reveals a significant correlation between effect scores and patient outcomes across various cancer types. Interestingly, while deep learning methods have shown promise in other fields, their DNA sequence representations do not significantly enhance the identification of driver synonymous mutations in this study. Overall, we anticipate that EPEL will facilitate researchers to more precisely target driver synonymous mutations. EPEL is designed with flexibility, allowing users to retrain the prediction model and generate effect scores for synonymous mutations in human cancers. A user-friendly web server for EPEL is available at http://ahmu.EPEL.bio/.

Lightweight Deep Learning Model, ConvNeXt-U: An Improved U-Net Network for Extracting Cropland in Complex Landscapes from Gaofen-2 Images.

Extracting fragmented cropland is essential for effective cropland management and sustainable agricultural development. However, extracting fragmented cropland presents significant challenges due to its irregular and blurred boundaries, as well as the diversity in crop types and distribution. Deep learning methods are widely used for land cover classification. This paper proposes ConvNeXt-U, a lightweight deep learning network that efficiently extracts fragmented cropland while reducing computational requirements and saving costs. ConvNeXt-U retains the U-shaped structure of U-Net but replaces the encoder with a simplified ConvNeXt architecture. The decoder remains unchanged from U-Net, and the lightweight CBAM (Convolutional Block Attention Module) is integrated. This module adaptively adjusts the channel and spatial dimensions of feature maps, emphasizing key features and suppressing redundant information, which enhances the capture of edge features and improves extraction accuracy. The case study area is Hengyang County, Hunan Province, China, using GF-2 remote sensing imagery. The results show that ConvNeXt-U outperforms existing methods, such as Swin Transformer (Acc = 85.1%, IoU = 79.1%), MobileNetV3 (Acc = 83.4%, IoU = 77.6%), VGG16 (Acc = 80.5%, IoU = 74.6%), and ResUnet (Acc = 81.8%, IoU = 76.1%), achieving an IoU of 79.5% and Acc of 85.2%. Under the same conditions, ConvNeXt-U has a faster inference speed of 37 images/s, compared to 28 images/s for Swin Transformer, 35 images/s for MobileNetV3, and 0.43 and 0.44 images/s for VGG16 and ResUnet, respectively. Moreover, ConvNeXt-U outperforms other methods in processing the boundaries of fragmented cropland, producing clearer and more complete boundaries. The results indicate that the ConvNeXt and CBAM modules significantly enhance the accuracy of fragmented cropland extraction. ConvNeXt-U is also an effective method for extracting fragmented cropland from remote sensing imagery.

A New Deep Learning-Based Method for Automated Identification of Thoracic Lymph Node Stations in Endobronchial Ultrasound (EBUS): A Proof-of-Concept Study

Endobronchial ultrasound-guided transbronchial needle aspiration (EBUS-TBNA) is a cornerstone in minimally invasive thoracic lymph node sampling. In lung cancer staging, precise assessment of lymph node position is crucial for clinical decision-making. This study aimed to demonstrate a new deep learning method to classify thoracic lymph nodes based on their anatomical location using EBUS images. Bronchoscopists labeled lymph node stations in real-time according to the Mountain Dressler nomenclature. EBUS images were then used to train and test a deep neural network (DNN) model, with intraoperative labels as ground truth. In total, 28,134 EBUS images were acquired from 56 patients. The model achieved an overall classification accuracy of 59.5 ± 5.2%. The highest precision, sensitivity, and F1 score were observed in station 4L, 77.6 ± 13.1%, 77.6 ± 15.4%, and 77.6 ± 15.4%, respectively. The lowest precision, sensitivity, and F1 score were observed in station 10L. The average processing and prediction time for a sequence of ten images was 0.65 ± 0.04 s, demonstrating the feasibility of real-time applications. In conclusion, the new DNN-based model could be used to classify lymph node stations from EBUS images. The method performance was promising with a potential for clinical use.

A deep learning method based on multi-scale fusion for noise-resistant coal-gangue recognition

Coal-gangue recognition technology plays an important role in the intelligent realization of integrated working faces and coal quality improvement. However, the existing methods are easily affected by high dust, noise, and other disturbances, resulting in unstable recognition results that make it difficult to meet the needs of industrial applications. To realize accurate recognition of coal-gangue in noisy environments, this paper proposes an end-to-end multi-scale feature fusion convolutional neural network (MCNN-BILSTM) based gangue recognition method, which can automatically learn and fuse complementary information from multiple signal components of vibration signals. It combines traditional filtering methods and the idea of multi-scale learning, which can expand the breadth and depth of the feature learning process. the breadth and depth of the feature learning process. Moreover, to strengthen the expression of key features, a feature weighting method based on the attention mechanism is combined to give adaptive weights to different features. Finally, the experimental platform of a tail beam of coal-gangue impact hydraulic support is built, and several comparative experiments are carried out. The comprehensive comparison experiments show that the method shows strong adaptability, robustness, and noise resistance under various complex noise environments, and is suitable for complex practical industrial sites.

Epilepsy Diagnosis from EEG Signals Using Continuous Wavelet Transform-Based Depthwise Convolutional Neural Network Model.

Background/Objectives: Epilepsy is a prevalent neurological disorder characterized by seizures that significantly impact individuals and their social environments. Given the unpredictable nature of epileptic seizures, developing automated epilepsy diagnosis systems is increasingly important. Epilepsy diagnosis traditionally relies on analyzing EEG signals, with recent deep learning methods gaining prominence due to their ability to bypass manual feature extraction. Methods: This study proposes a continuous wavelet transform-based depthwise convolutional neural network (DCNN) for epilepsy diagnosis. The 35-channel EEG signals were transformed into 35-channel images using continuous wavelet transform. These images were then concatenated horizontally and vertically into a single image (seven rows by five columns) using Python's PIL library, which served as input for training the DCNN model. Results: The proposed model achieved impressive performance metrics on unseen test data: 95.99% accuracy, 94.27% sensitivity, 97.29% specificity, and 96.34% precision. Comparative analyses with previous studies and state-of-the-art models demonstrated the superior performance of the DCNN model and image concatenation technique. Conclusions: Unlike earlier works, this approach did not employ additional classifiers or feature selection algorithms. The developed model and image concatenation method offer a novel methodology for epilepsy diagnosis that can be extended to different datasets, potentially providing a valuable tool to support neurologists globally.

Predicting noncoding RNA and disease associations using multigraph contrastive learning

MiRNAs and lncRNAs are two essential noncoding RNAs. Predicting associations between noncoding RNAs and diseases can significantly improve the accuracy of early diagnosis.With the continuous breakthroughs in artificial intelligence, researchers increasingly use deep learning methods to predict associations. Nevertheless, most existing methods face two major issues: low prediction accuracy and the limitation of only being able to predict a single type of noncoding RNA-disease association. To address these challenges, this paper proposes a method called K-Means and multigraph Contrastive Learning for predicting associations among miRNAs, lncRNAs, and diseases (K-MGCMLD). The K-MGCMLD model is divided into four main steps. The first step is the construction of a heterogeneous graph. The second step involves down sampling using the K-means clustering algorithm to balance the positive and negative samples. The third step is to use an encoder with a Graph Convolutional Network (GCN) architecture to extract embedding vectors. Multigraph contrastive learning, including both local and global graph contrastive learning, is used to help the embedding vectors better capture the latent topological features of the graph. The fourth step involves feature reconstruction using the balanced positive and negative samples and the embedding vectors fed into an XGBoost classifier for multi-association classification prediction. Experimental results have shown that AUC value for miRNA-disease association is 0.9542, lncRNA-disease association is 0.9603, and lncRNA-miRNA association is 0.9687. Additionally, this study has conducted case analyses using K-MGCMLD, which has validated the associations of all the top 30 miRNAs predicted to be associated with lung cancer and Alzheimer’s diseases.

Impulsive thrust strategy for orbital pursuit-evasion games based on impulse-like constraint

This paper proposes a novel impulsive thrust strategy guided by optimal continuous thrust strategy to address two-player orbital pursuit-evasion game under impulsive thrust control. The strategy seeks to enhance the interpretability of impulsive thrust strategy by integrating it within the framework of differential game in traditional continuous systems. First, this paper introduces an impulse-like constraint, with periodical changes in thrust amplitude, to characterize the impulsive thrust control. Then, the game with the impulse-like constraint is converted into the two-point boundary value problem, which is solved by the combined shooting and deep learning method proposed in this paper. Deep learning and numerical optimization are employed to obtain the guesses for unknown terminal adjoint variables and the game terminal time. Subsequently, the accurate values are solved by the shooting method to yield the optimal continuous thrust strategy with the impulse-like constraint. Finally, the shooting method is iteratively employed at each impulse decision moment to derive the impulsive thrust strategy guided by the optimal continuous thrust strategy. Numerical examples demonstrate the convergence of the combined shooting and deep learning method, even if the strongly nonlinear impulse-like constraint is introduced. The effect of the impulsive thrust strategy guided by the optimal continuous thrust strategy is also discussed.

A novel model for detecting web defacement attacks transformer using plain text features

Over the last decade, web defacements and other types of web attacks have been considered serious security threats to web-based services and systems of many enterprises and organizations. A website defacement attack can bring severe repercussions to the website owner, such as immediate discontinuance of the website operations and damage to the owner’s reputation, which may lead to enormous monetary losses. Several solutions and tools for monitoring and detecting web defacements have been designed and developed. Some solutions and tools are limited to static web pages, while others can handle dynamic ones but demand significant computational power. The existing proposals’ other issues are relatively low detection rates and high false alarm rates because many crucial elements of web pages, including embedded code and images are not properly processed. This paper proposes a novel model for detecting web defacements to address these issues. The model is based on the bidirectional long-short term memory (Bi-LSTM) deep learning method using features of the plain text content extracted from web pages. Comprehensive testing on over 96,000 web pages dataset demonstrates that the proposed Bi-LSTM-based web defacement detection model outperforms earlier methods, achieving a 96.04% overall accuracy and a 2.03% false positive rate.

TorchQC - A framework for efficiently integrating machine and deep learning methods in quantum dynamics and control

TorchQC - A framework for efficiently integrating machine and deep learning methods in quantum dynamics and control

Prediction of melt pool morphology of Ti alloy based on deep learning method

This paper utilizes an artificial neural network (ANN) model to predict the melt pool morphology (including melt pool width, height and depth) of Titanium (Ti) alloy by adjusting welding process parameters (laser power, welding current, and welding speed). The correlation between welding process parameters and melt pool morphology are analyzed using the Pearson correlation coefficient, which the result indicates that the input features are directly related to the output features. Four deep learning (DL) models are evaluated, which ANN model has higher coefficient of determination (0.8725 and 0.9691), lower root mean square error (RMSE) (0.4322mm and 0.1405mm) and lower mean absolute error (MAE) (0.025mm and 0.112mm). When the number of hidden layers is five, the R2 and RMSE values of ANN model are 0.8024, 0.9838, 0.5356mm and 0.1019mm, respectively. To assess the accuracy of the model, experiments are conducted to validate the predicted values, and the errors between the experimental and predicted values are 0.01mm, 0.10mm, and 0.02mm, respectively.

Automated quantification of Enchytraeus crypticus juveniles in different soil types using RootPainter.

The manual counting of juveniles in enchytraeid soil toxicity tests is time-consuming, labour-intensive, repetitive, prone to subjectivity, but can potentially be automated through deep learning methods using convolutional neural networks. This study investigated if RootPainter can be used as a tool to automatically quantify Enchytraeus crypticus juveniles in toxicity tests using different soil types. Toxicity tests were performed following OECD guideline 220 using five different pesticides (two fungicides and three insecticides) and four different soil types (three OECD artificial soils and one natural LUFA 2.2 soil). Manual counts were done by three different operators, with each operator counting images for one pesticide. Correlations between automated and manual counts were strong and significant in all four soils for all operators, with Pearson's correlation coefficients ≥ 0.955 and intraclass comparability coefficients ≥ 0.936. Toxicity values (EC50 and EC10) calculated from the manual and automated counts were within a factor of 0.85 - 1.30. Overall, the results show that RootPainter is a suitable tool for a reliable, repeatable and accurate quantification of enchytraeid juveniles, and can eliminate the time-consuming manual counting process.

A Systematic Review on Effectiveness and Contributions of Machine Learning and Deep Learning Methods in Lung Cancer Diagnosis and Classifications

A Systematic Review on Effectiveness and Contributions of Machine Learning and Deep Learning Methods in Lung Cancer Diagnosis and Classifications