Ensemble Model
Recently Published Documents





2021 ◽  
Vol 96 ◽  
pp. 107484
Nonita Sharma ◽  
Monika Mangla ◽  
Sourabh Yadav ◽  
Nitin Goyal ◽  
Aman Singh ◽  

2021 ◽  
Vol 193 (11) ◽  
Shruti Sachdeva ◽  
Bijendra Kumar

2021 ◽  
Vol ahead-of-print (ahead-of-print) ◽  
Sharanabasappa ◽  
Suvarna Nandyal

PurposeIn order to prevent accidents during driving, driver drowsiness detection systems have become a hot topic for researchers. There are various types of features that can be used to detect drowsiness. Detection can be done by utilizing behavioral data, physiological measurements and vehicle-based data. The existing deep convolutional neural network (CNN) models-based ensemble approach analyzed the behavioral data comprises eye or face or head movement captured by using a camera images or videos. However, the developed model suffered from the limitation of high computational cost because of the application of approximately 140 million parameters.Design/methodology/approachThe proposed model uses significant feature parameters from the feature extraction process such as ReliefF, Infinite, Correlation, Term Variance are used for feature selection. The features that are selected are undergone for classification using ensemble classifier.FindingsThe output of these models is classified into non-drowsiness or drowsiness categories.Research limitations/implicationsIn this research work higher end camera are required to collect videos as it is cost-effective. Therefore, researches are encouraged to use the existing datasets.Practical implicationsThis paper overcomes the earlier approach. The developed model used complex deep learning models on small dataset which would also extract additional features, thereby provided a more satisfying result.Originality/valueDrowsiness can be detected at the earliest using ensemble model which restricts the number of accidents.

2021 ◽  
Jiali Nie ◽  
Wenke Tan ◽  
Houmei Zhang

Abstract Automatic modulation classification (AMC) plays an increasingly vital role in cognitive radio (CR), cognitive electronic warfare, and other areas. It aims at classifying the modulated modes of the received signals accurately and provides a guarantee for the subsequent detailed parameter identification. Deep learning (DL) methods allow the computer to automatically learn the pattern features and integrate features into the process of building the model, thereby reducing the incompleteness caused by artificial design features. At the same time, the DL methods have been applied in the AMC field as its powerful ability to process complex data and have achieved excellent performance in recent years. In this paper, we propose a deep ensemble learning AMC network, which uses a multi-model ensemble method to fuse multiple DL features. Specifically, different DL models are integrated by ensemble learning, which enhances the learning ability of the single model. With the proposed ensemble model trained on a measured wireless signal dataset, we conclude that the ensemble structure of Inception and CLDNN can fuse spatial features and temporal features, and achieve state-of-the-art performance in AMC tasks. Besides, the impact of the inphase/quadrature (I/Q) sample-length on wireless signals is further investigated, and find that the classification accuracy of the deep ensemble model is improved by 0.7% to 10% compared to the single model under various sample-length. Simultaneously, we visualize convergence clustering with t-distributed stochastic neighbor embedding (t-SNE), and the visualization results prove that the deep ensemble model has a stronger clustering ability than a single model.

2021 ◽  
Rovshan Mollayev ◽  
Aghamehdi Aliyev

Abstract Study was conducted to evaluate development of gas-bearing formations in the Azerbaijan sector of the Caspian Sea. Study considered subsea wellheads tied into subsea manifold, and that manifold tied to offshore facility. Flow Assurance required the calculation of subsea Flowing Wellhead Temperature (FWHT) and Pressures (FWHP). 242 subsurface scenarios were conducted with reservoir model. To accommodate all subsurface scenarios in flow assurance assessments, it was required to carry out FWHT/P calculations for all. Reservoir model was equipped with vertical lift performance curves for pressure loss calculations in tubing and logic for pressure loss estimation in subsea system. If correctly calculated, [FWHP >= dP(subsea) + Pseparator] logic should have been satisfied. As the reservoir model was not set for FWHT calculations, an external tool was required to cope with that task. Both nodal analysis software and dynamic flow modeling were considered as appropriate tools. However, as nodal modelling allowed much more automation, it was decided to use nodal analysis over dynamic modelling. To improve FWHP calculations: the logic was built into the reservoir model to: ○  estimate dP(subsea) from gas rate vs pressure drop curves ○  confirm validity of [minFWHP(wells 1, 2…n) >= dP(subsea) + Pseparator] statement: step was re-iterated until the statement was satisfied To improve FWHT calculations: Enthalpy Balance method was tested for gas wells with 1-2% error against actual data Then, nodal analysis models with the same method were built for the project wells Code was developed to calculate FWHT as part of the ensemble model predictions in following steps: ○  Well properties of each prediction step were transferred to nodal analysis software. ○  kH was varied until nodal analysis software calculated gas rate matched to ensemble model output within 1mmscf/d error Summary: Described methods allowed to significantly increase accuracy in FWHT and FWHP calculations and accommodate all possible subsurface scenarios in Flow Assurance evaluation Integration of subsea and topside hydraulics in subsurface modelling is important to develop flow assured design for development Enthalpy Balance temperature prediction method provides good match to actual data Use of coding provides huge opportunities to automate data analysis Paper will present different approach to calculation of FWHT and FWHP in subsurface modelling, integration of subsea and topside hydraulics in subsurface modelling via alternatives ways, use enthalpy balance temperature modelling, integration between nodal analysis and subsurface modelling and coding can prove analysis of large subsurface data set.

2021 ◽  
Vol 5 (5) ◽  
pp. 619-635
Harya Widiputra

The primary factor that contributes to the transmission of COVID-19 infection is human mobility. Positive instances added on a daily basis have a substantial positive association with the pace of human mobility, and the reverse is true. Thus, having the ability to predict human mobility trend during a pandemic is critical for policymakers to help in decreasing the rate of transmission in the future. In this regard, one approach that is commonly used for time-series data prediction is to build an ensemble with the aim of getting the best performance. However, building an ensemble often causes the performance of the model to decrease, due to the increasing number of parameters that are not being optimized properly. Consequently, the purpose of this study is to develop and evaluate a deep learning ensemble model, which is optimized using a genetic algorithm (GA) that incorporates a convolutional neural network (CNN) and a long short-term memory (LSTM). A CNN is used to conduct feature extraction from mobility time-series data, while an LSTM is used to do mobility prediction. The parameters of both layers are adjusted using GA. As a result of the experiments conducted with data from the Google Community Mobility Reports in Indonesia that ranges from the beginning of February 2020 to the end of December 2020, the GA-Optimized Multivariate CNN-LSTM ensemble outperforms stand-alone CNN and LSTM models, as well as the non-optimized CNN-LSTM model, in terms of predicting human movement in the future. This may be useful in assisting policymakers in anticipating future human mobility trends. Doi: 10.28991/esj-2021-01300 Full Text: PDF

2021 ◽  
Vol 2021 ◽  
pp. 1-10
Syed Nisar Hussain Bukhari ◽  
Amit Jain ◽  
Ehtishamul Haq ◽  
Moaiad Ahmad Khder ◽  
Rahul Neware ◽  

Zika virus (ZIKV), the causative agent of Zika fever in humans, is an RNA virus that belongs to the genus Flavivirus. Currently, there is no approved vaccine for clinical use to combat the ZIKV infection and contain the epidemic. Epitope-based peptide vaccines have a large untapped potential for boosting vaccination safety, cross-reactivity, and immunogenicity. Though many attempts have been made to develop vaccines for ZIKV, none of these have proved to be successful. Epitope-based peptide vaccines can act as powerful alternatives to conventional vaccines due to their low production cost, less reactogenic, and allergenic responses. For designing an effective and viable epitope-based peptide vaccine against this deadly virus, it is essential to select the antigenic T-cell epitopes since epitope-based vaccines are considered safe. The in silico machine-learning-based approach for ZIKV T-cell epitope prediction would save a lot of physical experimental time and efforts for speedy vaccine development compared to in vivo approaches. We hereby have trained a machine-learning-based computational model to predict novel ZIKV T-cell epitopes by employing physicochemical properties of amino acids. The proposed ensemble model based on a voting mechanism works by blending the predictions for each class (epitope or nonepitope) from each base classifier. Predictions obtained for each class by the individual classifier are summed up, and the class with the majority vote is predicted upon. An odd number of classifiers have been used to avoid the occurrence of ties in the voting. Experimentally determined ZIKV peptide sequences data set was collected from Immune Epitope Database and Analysis Resource (IEDB) repository. The data set consists of 3,519 sequences, of which 1,762 are epitopes and 1,757 are nonepitopes. The length of sequences ranges from 6 to 30 meter. For each sequence, we extracted 13 physicochemical features. The proposed ensemble model achieved sensitivity, specificity, Gini coefficient, AUC, precision, F-score, and accuracy of 0.976, 0.959, 0.993, 0.994, 0.989, 0.985, and 97.13%, respectively. To check the consistency of the model, we carried out five-fold cross-validation and an average accuracy of 96.072% is reported. Finally, a comparative analysis of the proposed model with existing methods has been carried out using a separate validation data set, suggesting the proposed ensemble model as a better model. The proposed ensemble model will help predict novel ZIKV vaccine candidates to save lives globally and prevent future epidemic-scale outbreaks.

2021 ◽  
Vol 14 (3) ◽  
pp. 1633-1645
Dhyan Chandra Yadav ◽  
Saurabh Pal

In medical data science, data classification, pattern generation, data analysis and improving classification accuracy are the important issues in the recent scenario. The main objective of this research to enhanced classification accuracyby four combinations of features technique separately with Neural Network classifier approach.The neural network is analyzed for chronic kidney disease with the help of features reduction and relevanttechniques.In experiment, we used neural network as ensemble model with different features techniques as: Pearson Correlation, Chi-Square, Extra Tree and Lasso regularization. In this research paper, we have prepared training model on 300(75%) instances of chronic kidney disease attributes and testing on 100 (25%) instances.We test the dataset on different applied epochs and calculated accuracy with error rate. The summary of this experiment, we used400 instances with 26 attributes of Chronic Kidney Disease and evaluated highest accuracy calculated (99.98%) with less error rate on passing several epochs by Neural Network ensemble with Lasso model.

2021 ◽  
Vol 48 (9) ◽  
pp. 1035-1043
Jungwon Kim ◽  
Ho-Jin Choi

Sign in / Sign up

Export Citation Format

Share Document