Deep Neural Network-based Prediction Research Articles

Deep neural network-based prediction of tsunami wave attenuation by mangrove forests

The goal of this research is to develop a model employing deep neural networks (DNNs) to predict the effectiveness of mangrove forests in attenuating the impact of tsunami waves. The dataset for the DNN model is obtained by simulating tsunami wave attenuation using the Boussinesq model with a staggered grid approximation. The Boussinesq model for wave attenuation is validated using laboratory experiments exhibiting a mean absolute error (MAE) ranging from 0.003 to 0.01. We employ over 40,000 data points generated from the Boussinesq numerical simulations to train the DNN. Efforts are made to optimize hyperparameters and determine the neural network architecture to attain optimal performance during the training process. The prediction results of the DNN model exhibit a coefficient of determination (R2) of 0.99560, an MAE of 0.00118, a root mean squared error (RMSE) of 0.00151, and a mean absolute percentage error (MAPE) of 3 %. When comparing the DNN model with three alternative machine learning models— support vector regression (SVR), multiple linear regression (MLR), and extreme gradient boosting (XGBoost)— the performance of DNN is superior to that of SVR and MLR, but it is similar to XGBoost.•High-accuracy DNN models require hyperparameter optimization and neural network architecture selection.•The error of DNN models in predicting the attenuation of tsunami waves by mangrove forests is less than 3 %.•DNN can serve as an alternate predictive model to empirical formulas or classical numerical models.

Effect of Conformational Variability on the Drug Resistance of Candida auris ERG11p and FKS1.

Candida auris infection has been recognized as an urgent threat to antifungal drug resistance, and the Eagle effect of C. auris FKS1 (1,3-β-d-glucan synthase) wild-type isolates has also been noted. The Eagle effect, namely, where higher concentrations of antifungals reduce fungicidal activity relative to lower concentrations, is a confounding factor of apparent antifungal resistance, but the detailed mechanism remains unclear. Here, we present the conformational variability of mutation sites for ERG11p (lanosterol 14α-demethylase) and FKS1 from deep neural network-based prediction along with the reported X-ray crystallographic and cryo-electron microscopy (cryo-EM) structures of antifungals. The sequence variability maps provide valuable insights into the inconsistent correlation between azole resistance and the mysterious Eagle effect with the dispersion of minimal inhibitory concentration (MIC) for echinocandin resistance. The conformational variability prediction supports the hypothesis that mutations K143R of clade I, VF125AL of clade III, and Y132F of clade IV for C. auris ERG11p make the corresponding site variable and that an increased population of invisible variable conformations potentially contributes to triazole resistance. In contrast, the predicted rigid conformation by the S639F mutation of hot spot region 1 (HS1) for FKS1 suggests that caspofungin (CAS) is involved in an uncompetitive inhibition, and a decreased population of the CAS-bound state of FKS1 with Rho1 leads to drug resistance. The predicted variable HS1 region for FKS1 WT isolates and the rigid one for FKS1 S639F mutants support the in vivo drug response and the in vitro MIC dispersion. A plausible mechanism of the Eagle effect is hereby proposed, namely, that a high concentration of CAS with a high membrane affinity reduces the population of the CAS-bound state of FKS1 with Rho1, as well as accompanying events such as aggregation or association depending on the conformational variability of HS1.

A cost-sensitive deep neural network-based prediction model for the mortality in acute myocardial infarction patients with hypertension on imbalanced data.

Hypertension is one of the most serious risk factors and the leading cause of mortality in patients with cardiovascular diseases (CVDs). It is necessary to accurately predict the mortality of patients suffering from CVDs with hypertension. Therefore, this paper proposes a novel cost-sensitive deep neural network (CSDNN)-based mortality prediction model for out-of-hospital acute myocardial infarction (AMI) patients with hypertension on imbalanced data. The synopsis of our research is as follows. First, the experimental data is extracted from the Korea Acute Myocardial Infarction Registry-National Institutes of Health (KAMIR-NIH) and preprocessed with several approaches. Then the imbalanced experimental dataset is divided into training data (80%) and test data (20%). After that, we design the proposed CSDNN-based mortality prediction model, which can solve the skewed class distribution between the majority and minority classes in the training data. The threshold moving technique is also employed to enhance the performance of the proposed model. Finally, we evaluate the performance of the proposed model using the test data and compare it with other commonly used machine learning (ML) and data sampling-based ensemble models. Moreover, the hyperparameters of all models are optimized through random search strategies with a 5-fold cross-validation approach. In the result, the proposed CSDNN model with the threshold moving technique yielded the best results on imbalanced data. Additionally, our proposed model outperformed the best ML model and the classic data sampling-based ensemble model with an AUC of 2.58% and 2.55% improvement, respectively. It aids in decision-making and offers a precise mortality prediction for AMI patients with hypertension.

A physics merged deep neural network-based prediction method for jet turbulent mixing noise

Turbulent mixing noise is a vital component of jet noise, and its rapid, accurate prediction has always been persistently pursued. Recent advancement in machine learning has been applied to jet noise prediction. However, these applications are pure curve fitting and lack physical constraints. In this study, a physics-merged deep neural network (PMNN)-based prediction method was developed for turbulent mixing jet noise by merging the physics of the jet noise. This deep neural network (DNN)-based method employed recent advancements in jet turbulent mixing noise containing large- and fine-scale turbulence structures. Two simple rational functions for large- and fine-scale turbulent noise similarity spectra were proposed to replace the original complex similarity spectra functions and incorporated into the DNN-based prediction method. For comparison, we present two data-driven DNN-based prediction methods (DDNN). The first DDNN method used the sound pressure level (SPL) as the output of neural networks, directly establishing the nonlinear relationship between the input features and SPL. In the second DDNN method, the dominant modes of the jet noise spectra extracted using the proper orthogonal decomposition method were merged with DNN. These DNN-based methods were then trained using a set of experimental data over a wide range of jet operating conditions. Their performance was evaluated and compared. It was evident that all these DNN-based methods were capable of predicting turbulent mixing noise reasonably well. In contrast to the DDNN methods, the PMNN method could provide insights into the jet turbulent mixing noise components. It demonstrates that the turbulent mixing jet noise spectra at the mid polar angle is generated by the large-scale noise component at low-frequency range and by the fine-scale noise component at high-frequency range.

Deep neural network-based prediction for low-energy beam transport tuning

Deep neural network-based prediction for low-energy beam transport tuning

Effect of Conformational Variability on Seasonable Thermal Stability and Cell Entry of Omicron Variants.

The Omicron BA.1 variant of SARS-CoV-2 preferentially infects through the cathepsin-mediated endocytic pathway, but the mechanism of cell entry has not been solved yet because BA.4/5 is more fusogenic and more efficiently spread in human lung cells than BA.2. It has been unclear why the Omicron spike is inefficiently cleaved in virions compared with Delta, and how the relatively effective reproduction proceeds without the cell entry through plasma membrane fusion. Conformational variability from deep neural network-based prediction correlates well with the thermodynamic stability of variants. The difference of seasonable pandemic variants in summer and those in winter is distinguishable by this conformational stability, and the geographical optimization of variants is also traceable. Further, the predicted conformational variability maps rationalize the less efficient S1/S2 cleavage of Omicron variants and provide a valuable insight into the cell entry through the endocytic pathway. It is concluded that conformational variability prediction is able to complement transformation information on motifs in protein structures for drug discovery.

An Exhaustive Study on Deep Neural Network-based Prediction of Heart Diseases and its Interpretations

Cardiovascular disease prediction is important in day-to-day life. A tool to diagnose cardiovascular diseases is an Electrocardiogram (ECG), which records electrical activities happening in the heart through a wave. A determination is made by checking the wave changes in an ECG. Predicting wave changes and diagnosing the disease requires domain expertise like cardiologists/physicians. Deep Neural Network techniques extract the features accurately and automatically predict the type of disease. This article lists different types of cardiac disorders, and parallelly different disease interpretations of all types of diseases are discussed to manually identify the disease type; segmentation of leads, pre-trained models, and different detection techniques are discussed to predict the type of diseases from an ECG image. Finally, this article discussed the different challenges in predicting heart diseases, and solutions to some of the challenges are given.

Deep Neural Network-Based Prediction and Early Warning of Student Grades and Recommendations for Similar Learning Approaches

Studies reported that if teachers can accurately predict students’ follow-up learning effects via data mining and other means, as per their current performances, and explore the difficulty level of students’ mastery of future-related courses in advance, it will help improve students’ scores in future exams. Although educational data mining and learning analytics have experienced an increase in exploration and use, they are still difficult to precisely define. The usage of deep learning methods to predict academic performances and recommend optimal learning methods has not received considerable attention from researchers. This study aims to predict unknown course grades based on students’ previous learning situations and use clustering algorithms to identify similar learning situations, thereby improving students’ academic performance. In this study, the methods of linear regression, random forest, back-propagation neural network, and deep neural network are compared; the prediction and early warning of students’ academic performances based on deep neural network are proposed, in addition to the improved K-nearest neighbor clustering based on association rules (Pearson correlation coefficient). The algorithm performs a similar category clustering for early-warning students. Using the mean square error, standard deviation, mean absolute percentage error, and prediction of ups-and-downs accuracy as evaluation indicators, the proposed method achieves a steady improvement of 20% in the prediction of ups-and-downs accuracy, and demonstrates improved prediction results when compared under similar conditions.

Prediction of CO2 capture capability of 0.5 MW MEA demo plant using three different deep learning pipelines

Efficient CO2 capture from off-gas power plant is attracting increased attention due to its significant effects on global warming and climate change. In this study, three deep learning pipelines (DLPs), namely, Spearman DLP (S-DLP), stepwise backward elimination DLP (SBE-DLP), and Lasso DLP (L-DLP), were developed to predict the CO2 capture potential of amine-based capture processes. Raw operating data, obtained under various conditions in a 0.5 MW MEA demo plant, were used for the DLP, which mainly comprised data gathering and cleaning, feature selection, and deep neural network-based prediction. The outliers, which strongly influence the prediction accuracy, were eliminated from the initial raw data. The clean data was then used to predict the CO2 concentration of treated gas and capture rate using the three DLPs. Based on accuracy and computation cost, L-DLP was selected as the best pipeline to predict the CO2 capture rate and CO2 concentration of the treated gas from the 0.5 MW MEA demo plant. The L-DLP was then used to predict the temperature variation in the absorber and stripper, which is a significant control variable to save energy. The deep learning pipeline represents a feasible strategy to predict the CO2 capture potential of the 0.5 MW MEA demo plant, even though the operation of the plant varied from unsteady to steady states under various conditions. The developed pipeline has a great potential for the utilization for other chemical processes with high accuracy in a low computation time.

Monitoring Population Phenology of Asian Citrus Psyllid Using Deep Learning

Asian citrus psyllid, Diaphorina citri Kuwayama (Liviidae: Hemiptera) is a menacing and notorious pest of citrus plants. It vectors a phloem vessel-dwelling bacterium Candidatus Liberibacter asiaticus, which is a causative pathogen of the serious citrus disease known as Huanglongbing. Huanglongbing disease is a major bottleneck in the export of citrus fruits from Pakistan. It is being responsible for huge citrus economic losses globally. In the current study, several prediction models were developed based on regression algorithms of machine learning to monitor different phenological stages of Asian citrus psyllid to predict its population about different abiotic variables (average maximum temperature, average minimum temperature, average weekly temperature, average weekly relative humidity, and average weekly rainfall) and biotic variable (host plant phenological patterns) in citrus-growing regions of Pakistan. The pest prediction models can be used for proper applications of pesticides only when needed for reducing the environmental and cost impacts of pesticides. Pearson’s correlation analysis was performed to find the relationship between different predictor (abiotic and biotic) variables and pest infestation rate on citrus plants. Multiple linear regression, random forest regressor, and deep neural network approaches were compared to predict population dynamics of Asian citrus psyllid. In comparison with other regression techniques, a deep neural network-based prediction model resulted in the least root mean squared error values while predicting egg, nymph, and adult populations.

Validating the impact of accounting disclosures on stock market: A deep neural network approach

Firms disclose information either voluntarily or due to the regulator's mandatory requirements, and such disclosures form good sources to know the prospects of a firm. Information in the disclosures and analysts' opinions influence investor-trading behavior, and consequently, affects the asset prices. As sentiments factored in disclosures are a source of market action, this study aims to capture the sentiments from disclosure information to assess asset prices' impact. The paper adopts a deep neural network-based prediction model for conducting sentiment analysis on heterogeneous datasets. We construct a sentiment simulation model of voluntary disclosures to know whether the managers can use the market sentiment as a strategic input to boost market performance by suitably drafting the tone and content of disclosures without compromising their quality and veracity. The Deep Neural Networks with LSTM algorithm is found to outperform the Deep Neural Networks with RNN and other baseline machine learning classifiers in terms of predictive accuracy of the NSE NIFTY50. The variable importance computed also validates that market news, combined with historical indicators, predicts the stock market trend closer to the actual trend.

Deep Neural Network-Based Prediction of the COVID-19 Spread in India

Deep Neural Network-Based Prediction of the COVID-19 Spread in India

Deep Neural Network-Based Prediction of the Risk of Advanced Colorectal Neoplasia.

Background/AimsRisk prediction models using a deep neural network (DNN) have not been reported to predict the risk of advanced colorectal neoplasia (ACRN). The aim of this study was to compare DNN models with simple clinical score models to predict the risk of ACRN in colorectal cancer screening.MethodsDatabases of screening colonoscopy from Kangbuk Samsung Hospital (n=121,794) and Kyung Hee University Hospital at Gangdong (n=3,728) were used to develop DNN-based prediction models. Two DNN models, the Asian-Pacific Colorectal Screening (APCS) model and the Korean Colorectal Screening (KCS) model, were developed and compared with two simple score models using logistic regression methods to predict the risk of ACRN. The areas under the receiver operating characteristic curves (AUCs) of the models were compared in internal and external validation databases.ResultsIn the internal validation set, the AUCs of DNN model 1 and the APCS score model were 0.713 and 0.662 (p<0.001), respectively, and the AUCs of DNN model 2 and the KCS score model were 0.730 and 0.667 (p<0.001), respectively. However, in the external validation set, the prediction performances were not significantly different between the two DNN models and the corresponding APCS and KCS score models (both p>0.1).ConclusionsSimple score models for the risk prediction of ACRN are as useful as DNN-based models when input variables are limited. However, further studies on this issue are warranted to predict the risk of ACRN in colorectal cancer screening because DNN-based models are currently under improvement.

SSSCPreds: Deep Neural Network-Based Software for the Prediction of Conformational Variability and Application to SARS-CoV-2.

Amino acid mutations that improve protein stability and rigidity can accompany increases in binding affinity. Therefore, conserved amino acids located on a protein surface may be successfully targeted by antibodies. The quantitative deep mutational scanning approach is an excellent technique to understand viral evolution, and the obtained data can be utilized to develop a vaccine. However, the application of the approach to all of the proteins in general is difficult in terms of cost. To address this need, we report the construction of a deep neural network-based program for sequence-based prediction of supersecondary structure codes (SSSCs), called SSSCPrediction (SSSCPred). Further, to predict conformational flexibility or rigidity in proteins, a comparison program called SSSCPreds that consists of three deep neural network-based prediction systems (SSSCPred, SSSCPred100, and SSSCPred200) has also been developed. Using our algorithms we calculated here shows the degree of flexibility for the receptor-binding motif of SARS-CoV-2 spike protein and the rigidity of the unique motif (SSSC: SSSHSSHHHH) at the S2 subunit and has a value independent of the X-ray and Cryo-EM structures. The fact that the sequence flexibility/rigidity map of SARS-CoV-2 RBD resembles the sequence-to-phenotype maps of ACE2-binding affinity and expression, which were experimentally obtained by deep mutational scanning, suggests that the identical SSSC sequences among the ones predicted by three deep neural network-based systems correlate well with the sequences with both lower ACE2-binding affinity and lower expression. The combined analysis of predicted and observed SSSCs with keyword-tagged datasets would be helpful in understanding the structural correlation to the examined system.

Prediction of Alzheimer's disease based on deep neural network by integrating gene expression and DNA methylation dataset

MotivationThe molecular mechanism of Alzheimer's disease (AD) has not been clearly revealed and there is no clinically reliable genetic risk factor. Therefore, diagnosis of AD has been mostly performed by analyzing brain images such as magnetic resonance imaging and neuropsychological tests. Identifying the molecular-level mechanism of AD has been lacking data owing to the difficulty of sampling in the posterior brains of normal and AD patients; however, recent studies have produced and analyzed large-scale omics data for brain areas such as prefrontal cortex. Therefore, it is necessary to develop AD diagnosis or prediction methods based on these data. ResultsThis paper proposed a deep learning-based model that can predict AD using large-scale gene expression and DNA methylation data. The most challenging problem in constructing a model to diagnose AD based on the multi-omics dataset is how to integrate different omics data and how to deal with high-dimensional and low-sample-size data. To solve this problem, we proposed a novel but simple approach to reduce the number of features based on a differentially expressed gene and a differentially methylated position in the multi-omics dataset. Moreover, we developed a deep neural network-based prediction model that improves performance compared to that of conventional machine learning algorithms. The feature selection method and the prediction model presented in this paper outperformed conventional machine learning algorithms, which utilize typical dimension reduction methods. In addition, we demonstrated that integrating gene expression and DNA methylation data could improve the prediction accuracy. Availabilityhttps://github.com/ChihyunPark/DNN_for_ADprediction.

Deep Learning-Based Corporate Performance Prediction Model Considering Technical Capability

Many studies have predicted the future performance of companies for the purpose of making investment decisions. Most of these are based on the qualitative judgments of experts in related industries, who consider various financial and firm performance information. With recent developments in data processing technology, studies have started to use machine learning techniques to predict corporate performance. For example, deep neural network-based prediction models are again attracting attention, and are now widely used in constructing prediction and classification models. In this study, we propose a deep neural network-based corporate performance prediction model that uses a company’s financial and patent indicators as predictors. The proposed model includes an unsupervised learning phase and a fine-tuning phase. The learning phase uses a restricted Boltzmann machine. The fine-tuning phase uses a backpropagation algorithm and a relatively up-to-date training data set that reflects the latest trends in the relationship between predictors and corporate performance.