Incremental Learning with Neural Network Algorithm for the Monitoring Pre-Convective Environments Using Geostationary Imager

Early warning of severe weather caused by intense convective weather systems is challenging. To help such activities, meteorological satellites with high temporal and spatial resolution have been utilized for the monitoring of instability trends along with water vapor variation. The current study proposes a retrieval algorithm based on an artificial neural network (ANN) model to quickly and efficiently derive total precipitable water (TPW) and convective available potential energy (CAPE) from Korea’s second geostationary satellite imagery measurements (GEO-KOMPSAT-2A/Advanced Meteorological Imager (AMI)). To overcome the limitations of the traditional static (ST) learning method such as exhaustive learning, impractical, and not matching in a sequence data, we applied an ANN model with incremental (INC) learning. The INC ANN uses a dynamic dataset that begins with the existing weight information transferred from a previously learned model when new samples emerge. To prevent sudden changes in the distribution of learning data, this method uses a sliding window that moves along the data with a window of a fixed size. Through an empirical test, the update cycle and the window size of the model are set to be one day and ten days, respectively. For the preparation of learning datasets, nine infrared brightness temperatures of AMI, six dual channel differences, temporal and geographic information, and a satellite zenith angle are used as input variables, and the TPW and CAPE from ECMWF model reanalysis (ERA5) data are used as the corresponding target values over the clear-sky conditions in the Northeast Asia region for about one year. Through the accuracy tests with radiosonde observation for one year, the INC NN results demonstrate improved performance (the accuracy of TPW and CAPE decreased by approximately 26% and 26% for bias and about 13% and 12% for RMSE, respectively) when compared to the ST learning. Evaluation results using ERA5 data also reveal more stable error statistics over time and overall reduced error distribution compared with ST ANN.

Download Full-text

Effect of Architectural Composition of MLP ANN in Neural Network Learning for Signal Power Loss Prediction

Journal of Communications ◽

10.12720/jcm.16.1.20-29 ◽

2021 ◽

pp. 20-29

Author(s):

Virginia C. Ebhota ◽

◽

Viranjay M. Srivastava

Keyword(s):

Neural Network ◽

Power Loss ◽

Prediction Errors ◽

Signal Power ◽

Training Algorithm ◽

Ann Model ◽

Training Time ◽

Mlp Neural Network ◽

Network Training ◽

Target Values

This work analyzes the architectural complexity of a Multi-Layer Perceptron (MLP) Artificial Neural Network (ANN) model suitable for modeling and predicting signal power loss in micro-cellular environments. The MLP neural network model with one, two, and three hidden layers respectively were trained using measurement datasets used as the target values collected from a micro-cell environment that is suitable to describe different propagation paths and conditions. The neural network training has been performed by applying different training techniques to ensure a well-trained network for good generalization and avoid over-fitting during network training. Bayesian regularization algorithm (that updates weights and biases during network training) following the Levenberg-Marquardt optimization training algorithm was used as the training algorithm. A comparative analysis of training results from one, two, and three hidden layers MLP neural networks show the best prediction result of the signal power loss using a neural network with one hidden layer. A complex architectural composition of the MLP neural network involved very high training time and higher prediction errors.

Download Full-text

Temperature Rise Prediction of Oil-Air Lubricated Angular Contact Ball Bearings Using Artificial Neural Network

Recent Patents on Mechanical Engineering ◽

10.2174/2212797612666190530115739 ◽

2019 ◽

Vol 12 (3) ◽

pp. 248-261

Author(s):

Baomin Wang ◽

Xiao Chang

Keyword(s):

Neural Network ◽

Artificial Neural Network ◽

Temperature Rise ◽

High Speed ◽

Ball Bearing ◽

Influence Factors ◽

Ball Bearings ◽

Ann Model ◽

Angular Contact Ball Bearing ◽

Artificial Neural

Background: Angular contact ball bearing is an important component of many high-speed rotating mechanical systems. Oil-air lubrication makes it possible for angular contact ball bearing to operate at high speed. So the lubrication state of angular contact ball bearing directly affects the performance of the mechanical systems. However, as bearing rotation speed increases, the temperature rise is still the dominant limiting factor for improving the performance and service life of angular contact ball bearings. Therefore, it is very necessary to predict the temperature rise of angular contact ball bearings lubricated with oil-air. Objective: The purpose of this study is to provide an overview of temperature calculation of bearing from many studies and patents, and propose a new prediction method for temperature rise of angular contact ball bearing. Methods: Based on the artificial neural network and genetic algorithm, a new prediction methodology for bearings temperature rise was proposed which capitalizes on the notion that the temperature rise of oil-air lubricated angular contact ball bearing is generally coupling. The influence factors of temperature rise in high-speed angular contact ball bearings were analyzed through grey relational analysis, and the key influence factors are determined. Combined with Genetic Algorithm (GA), the Artificial Neural Network (ANN) model based on these key influence factors was built up, two groups of experimental data were used to train and validate the ANN model. Results: Compared with the ANN model, the ANN-GA model has shorter training time, higher accuracy and better stability, the output of ANN-GA model shows a good agreement with the experimental data, above 92% of bearing temperature rise under varying conditions can be predicted using the ANNGA model. Conclusion: A new method was proposed to predict the temperature rise of oil-air lubricated angular contact ball bearings based on the artificial neural network and genetic algorithm. The results show that the prediction model has good accuracy, stability and robustness.

Download Full-text

Predicting the 14-Day Hospital Readmission of Patients with Pneumonia Using Artificial Neural Networks (ANN)

International Journal of Environmental Research and Public Health ◽

10.3390/ijerph18105110 ◽

2021 ◽

Vol 18 (10) ◽

pp. 5110

Author(s):

Shu-Farn Tey ◽

Chung-Feng Liu ◽

Tsair-Wei Chien ◽

Chin-Wei Hsu ◽

Kun-Chen Chan ◽

...

Keyword(s):

Neural Network ◽

Early Stage ◽

Characteristic Curve ◽

Patient Discharge ◽

Ann Model ◽

Healthcare Settings ◽

High Area ◽

Icd 10 ◽

Artificial Neural ◽

Artificial Neural Network Ann

Unplanned patient readmission (UPRA) is frequent and costly in healthcare settings. No indicators during hospitalization have been suggested to clinicians as useful for identifying patients at high risk of UPRA. This study aimed to create a prediction model for the early detection of 14-day UPRA of patients with pneumonia. We downloaded the data of patients with pneumonia as the primary disease (e.g., ICD-10:J12*-J18*) at three hospitals in Taiwan from 2016 to 2018. A total of 21,892 cases (1208 (6%) for UPRA) were collected. Two models, namely, artificial neural network (ANN) and convolutional neural network (CNN), were compared using the training (n = 15,324; ≅70%) and test (n = 6568; ≅30%) sets to verify the model accuracy. An app was developed for the prediction and classification of UPRA. We observed that (i) the 17 feature variables extracted in this study yielded a high area under the receiver operating characteristic curve of 0.75 using the ANN model and that (ii) the ANN exhibited better AUC (0.73) than the CNN (0.50), and (iii) a ready and available app for predicting UHA was developed. The app could help clinicians predict UPRA of patients with pneumonia at an early stage and enable them to formulate preparedness plans near or after patient discharge from hospitalization.

Download Full-text

Artificial neural network, predictor variables and sensitivity threshold for DNA methylation-based age prediction using blood samples

Scientific Reports ◽

10.1038/s41598-021-81556-2 ◽

2021 ◽

Vol 11 (1) ◽

Author(s):

Zhonghui Thong ◽

Jolena Ying Ying Tan ◽

Eileen Shuzhen Loo ◽

Yu Wei Phua ◽

Xavier Liang Shun Chan ◽

...

Keyword(s):

Neural Network ◽

Artificial Neural Network ◽

Regression Model ◽

Sensitivity Threshold ◽

Ann Model ◽

Blood Samples ◽

Ann Models ◽

Artificial Neural ◽

The Impact ◽

Age Prediction

AbstractRegression models are often used to predict age of an individual based on methylation patterns. Artificial neural network (ANN) however was recently shown to be more accurate for age prediction. Additionally, the impact of ethnicity and sex on our previous regression model have not been studied. Furthermore, there is currently no age prediction study investigating the lower limit of input DNA at the bisulfite treatment stage prior to pyrosequencing. Herein, we evaluated both regression and ANN models, and the impact of ethnicity and sex on age prediction for 333 local blood samples using three loci on the pyrosequencing platform. Subsequently, we trained a one locus-based ANN model to reduce the amount of DNA used. We demonstrated that the ANN model has a higher accuracy of age prediction than the regression model. Additionally, we showed that ethnicity did not affect age prediction among local Chinese, Malays and Indians. Although the predicted age of males were marginally overestimated, sex did not impact the accuracy of age prediction. Lastly, we present a one locus, dual CpG model using 25 ng of input DNA that is sufficient for forensic age prediction. In conclusion, the two ANN models validated would be useful for age prediction to provide forensic intelligence leads.

Download Full-text

Estimation of the Hot Swap Circulation Current of a Multiple Parallel Lithium Battery System with an Artificial Neural Network Model

Electronics ◽

10.3390/electronics10121448 ◽

2021 ◽

Vol 10 (12) ◽

pp. 1448

Author(s):

Nam-Gyu Lim ◽

Jae-Yeol Kim ◽

Seongjun Lee

Keyword(s):

Neural Network ◽

Artificial Neural Network ◽

Lithium Battery ◽

Battery Pack ◽

Battery Management ◽

Ann Model ◽

Battery System ◽

Load Current ◽

Circulating Current ◽

Artificial Neural

Battery applications, such as electric vehicles, electric propulsion ships, and energy storage systems, are developing rapidly, and battery management issues are gaining attention. In this application field, a battery system with a high capacity and high power in which numerous battery cells are connected in series and parallel is used. Therefore, research on a battery management system (BMS) to which various algorithms are applied for efficient use and safe operation of batteries is being conducted. In general, maintenance/replacement of multi-series/multiple parallel battery systems is only possible when there is no load current, or the entire system is shut down. However, if the circulating current generated by the voltage difference between the newly added battery and the existing battery pack is less than the allowable current of the system, the new battery can be connected while the system is running, which is called hot swapping. The circulating current generated during the hot-swap operation is determined by the battery’s state of charge (SOC), the parallel configuration of the battery system, temperature, aging, operating point, and differences in the load current. Therefore, since there is a limit to formulating a circulating current that changes in size according to these various conditions, this paper presents a circulating current estimation method, using an artificial neural network (ANN). The ANN model for estimating the hot-swap circulating current is designed for a 1S4P lithium battery pack system, consisting of one series and four parallel cells. The circulating current of the ANN model proposed in this paper is experimentally verified to be able to estimate the actual value within a 6% error range.

Download Full-text

Assessing the Natural Recovery of Mangroves after Human Disturbance Using Neural Network Classification and Sentinel-2 Imagery in Wunbaik Mangrove Forest, Myanmar

Remote Sensing ◽

10.3390/rs13010052 ◽

2020 ◽

Vol 13 (1) ◽

pp. 52

Author(s):

Win Sithu Maung ◽

Jun Sasaki

Keyword(s):

Neural Network ◽

Change Detection ◽

Transfer Learning ◽

Mangrove Forest ◽

Kappa Coefficient ◽

Mangrove Forests ◽

Ann Model ◽

Shrimp Ponds ◽

Natural Recovery ◽

Sentinel 2

In this study, we examined the natural recovery of mangroves in abandoned shrimp ponds located in the Wunbaik Mangrove Forest (WMF) in Myanmar using artificial neural network (ANN) classification and a change detection approach with Sentinel-2 satellite images. In 2020, we conducted various experiments related to mangrove classification by tuning input features and hyper-parameters. The selected ANN model was used with a transfer learning approach to predict the mangrove distribution in 2015. Changes were detected using classification results from 2015 and 2020. Naturally recovering mangroves were identified by extracting the change detection results of three abandoned shrimp ponds selected during field investigation. The proposed method yielded an overall accuracy of 95.98%, a kappa coefficient of 0.92, mangrove and non-mangrove precisions of 0.95 and 0.98, respectively, recalls of 0.96, and F1 scores of 0.96 for the 2020 classification. For the 2015 prediction, transfer learning improved model performance, resulting in an overall accuracy of 97.20%, a kappa coefficient of 0.94, mangrove and non-mangrove precisions of 0.98 and 0.96, respectively, recalls of 0.98 and 0.97, and F1 scores of 0.96. The change detection results showed that mangrove forests in the WMF slightly decreased between 2015 and 2020. Naturally recovering mangroves were detected at approximately 50% of each abandoned site within a short abandonment period. This study demonstrates that the ANN method using Sentinel-2 imagery and topographic and canopy height data can produce reliable results for mangrove classification. The natural recovery of mangroves presents a valuable opportunity for mangrove rehabilitation at human-disturbed sites in the WMF.

Download Full-text

The Passive Microwave Neural Network Precipitation Retrieval Algorithm for Climate Applications (PNPR-CLIM): Design and Verification

Remote Sensing ◽

10.3390/rs13091701 ◽

2021 ◽

Vol 13 (9) ◽

pp. 1701

Author(s):

Leonardo Bagaglini ◽

Paolo Sanò ◽

Daniele Casella ◽

Elsa Cattani ◽

Giulia Panegrossi

Keyword(s):

Neural Network ◽

Passive Microwave ◽

Retrieval Algorithm ◽

Climate Data ◽

High Quality ◽

Data Record ◽

Global Precipitation ◽

Climate Data Record

This paper describes the Passive microwave Neural network Precipitation Retrieval algorithm for climate applications (PNPR-CLIM), developed with funding from the Copernicus Climate Change Service (C3S), implemented by ECMWF on behalf of the European Union. The algorithm has been designed and developed to exploit the two cross-track scanning microwave radiometers, AMSU-B and MHS, towards the creation of a long-term (2000–2017) global precipitation climate data record (CDR) for the ECMWF Climate Data Store (CDS). The algorithm has been trained on an observational dataset built from one year of MHS and GPM-CO Dual-frequency Precipitation Radar (DPR) coincident observations. The dataset includes the Fundamental Climate Data Record (FCDR) of AMSU-B and MHS brightness temperatures, provided by the Fidelity and Uncertainty in Climate data records from Earth Observation (FIDUCEO) project, and the DPR-based surface precipitation rate estimates used as reference. The combined use of high quality, calibrated and harmonized long-term input data (provided by the FIDUCEO microwave brightness temperature Fundamental Climate Data Record) with the exploitation of the potential of neural networks (ability to learn and generalize) has made it possible to limit the use of ancillary model-derived environmental variables, thus reducing the model uncertainties’ influence on the PNPR-CLIM, which could compromise the accuracy of the estimates. The PNPR-CLIM estimated precipitation distribution is in good agreement with independent DPR-based estimates. A multiscale assessment of the algorithm’s performance is presented against high quality regional ground-based radar products and global precipitation datasets. The regional and global three-year (2015–2017) verification analysis shows that, despite the simplicity of the algorithm in terms of input variables and processing performance, the quality of PNPR-CLIM outperforms NASA GPROF in terms of rainfall detection, while in terms of rainfall quantification they are comparable. The global analysis evidences weaknesses at higher latitudes and in the winter at mid latitudes, mainly linked to the poorer quality of the precipitation retrieval in cold/dry conditions.

Download Full-text

Using Artificial Neural Networks in Predicting the Level of Stress among Military Conscripts

Mathematics ◽

10.3390/math9060626 ◽

2021 ◽

Vol 9 (6) ◽

pp. 626

Author(s):

Svajone Bekesiene ◽

Rasa Smaliukiene ◽

Ramute Vaicaitiene

Keyword(s):

Neural Network ◽

Transfer Functions ◽

Back Propagation ◽

Armed Forces ◽

Activation Function ◽

Optimal Number ◽

Ann Model ◽

Back Propagation Algorithm ◽

Classification Rate ◽

Artificial Neural

The present study aims to elucidate the main variables that increase the level of stress at the beginning of military conscription service using an artificial neural network (ANN)-based prediction model. Random sample data were obtained from one battalion of the Lithuanian Armed Forces, and a survey was conducted to generate data for the training and testing of the ANN models. Using nonlinearity in stress research, numerous ANN structures were constructed and verified to limit the optimal number of neurons, hidden layers, and transfer functions. The highest accuracy was obtained by the multilayer perceptron neural network (MLPNN) with a 6-2-2 partition. A standardized rescaling method was used for covariates. For the activation function, the hyperbolic tangent was used with 20 units in one hidden layer as well as the back-propagation algorithm. The best ANN model was determined as the model that showed the smallest cross-entropy error, the correct classification rate, and the area under the ROC curve. These findings show, with high precision, that cohesion in a team and adaptation to military routines are two critical elements that have the greatest impact on the stress level of conscripts.

Download Full-text

Modeling of lime production process using artificial neural network

Chemical Product and Process Modeling ◽

10.1515/cppm-2021-0032 ◽

2021 ◽

Vol 0 (0) ◽

Author(s):

Abolghasem Daeichian ◽

Rana Shahramfar ◽

Elham Heidari

Keyword(s):

Neural Network ◽

Artificial Neural Network ◽

Production Process ◽

High Energy ◽

Ann Model ◽

Artificial Neural ◽

Rotary Kilns ◽

Input Variables ◽

Artificial Neural Network Ann ◽

Lime Production

Abstract Lime is a significant material in many industrial processes, including steelmaking by blast furnace. Lime production through rotary kilns is a standard method in industries, yet it has depreciation, high energy consumption, and environmental pollution. A model of the lime production process can help to not only increase our knowledge and awareness but also can help reduce its disadvantages. This paper presents a black-box model by Artificial Neural Network (ANN) for the lime production process considering pre-heater, rotary kiln, and cooler parameters. To this end, actual data are collected from Zobahan Isfahan Steel Company, Iran, which consists of 746 data obtained in a duration of one year. The proposed model considers 23 input variables, predicting the amount of produced lime as an output variable. The ANN parameters such as number of hidden layers, number of neurons in each layer, activation functions, and training algorithm are optimized. Then, the sensitivity of the optimum model to the input variables is investigated. Top-three input variables are selected on the basis of one-group sensitivity analysis and their interactions are studied. Finally, an ANN model is developed considering the top-three most effective input variables. The mean square error of the proposed models with 23 and 3 inputs are equal to 0.000693 and 0.004061, respectively, which shows a high prediction capability of the two proposed models.

Download Full-text