Artificial Neural Network Prediction of Ischemic Tissue Fate in Acute Stroke Imaging

Multimodal magnetic resonance imaging of acute stroke provides predictive value that can be used to guide stroke therapy. A flexible artificial neural network (ANN) algorithm was developed and applied to predict ischemic tissue fate on three stroke groups: 30-, 60-minute, and permanent middle cerebral artery occlusion in rats. Cerebral blood flow (CBF), apparent diffusion coefficient (ADC), and spin–spin relaxation time constant (T2) were acquired during the acute phase up to 3 hours and again at 24 hours followed by histology. Infarct was predicted on a pixel-by-pixel basis using only acute (30-minute) stroke data. In addition, neighboring pixel information and infarction incidence were also incorporated into the ANN model to improve prediction accuracy. Receiver-operating characteristic analysis was used to quantify prediction accuracy. The major findings were the following: (1) CBF alone poorly predicted the final infarct across three experimental groups; (2) ADC alone adequately predicted the infarct; (3) CBF+ADC improved the prediction accuracy; (4) inclusion of neighboring pixel information and infarction incidence further improved the prediction accuracy; and (5) prediction was more accurate for permanent occlusion, followed by 60- and 30-minute occlusion. The ANN predictive model could thus provide a flexible and objective framework for clinicians to evaluate stroke treatment options on an individual patient basis.

Download Full-text

Mapping soil nail loads using Federal Highway Administration (FHWA) simplified models and artificial neural network technique

Canadian Geotechnical Journal ◽

10.1139/cgj-2019-0440 ◽

2020 ◽

Vol 57 (10) ◽

pp. 1453-1471 ◽

Cited By ~ 1

Author(s):

Peiyuan Lin ◽

Pengpeng Ni ◽

Chengchao Guo ◽

Guoxiong Mei

Keyword(s):

Neural Network ◽

Artificial Neural Network ◽

Prediction Accuracy ◽

Ann Model ◽

Limit States ◽

Operational Conditions ◽

Soil Nail ◽

Federal Highway ◽

Artificial Neural ◽

Artificial Neural Network Ann

This study compiles a broad database containing 312 measured maximum soil nail loads under operational conditions. The database is used to re-assess the prediction accuracies of the default Federal Highway Administration (FHWA) nail load model and its modified version previously reported in the literature. Predictions using the default and modified FHWA models are found to be highly dispersive. Moreover, the prediction accuracy is statistically dependent on the magnitudes of the predicted nail load and several model input parameters. The modified FHWA model is then recalibrated by introducing extra empirical terms to account for the influences of wall geometry, nail design configuration, and soil shear strength parameters on the evolvement of nail loads. The recalibrated FHWA model is demonstrated to have much better prediction accuracy compared to the default and modified models. Next, an artificial neural network (ANN) model is developed for mapping soil nail loads, which is shown to be the most advantageous one as it is accurate on average and the dispersion in prediction is low. The abovementioned dependency issue is also not present in the ANN model. The practical value of the ANN model is highlighted by applying it to reliability-based designs of soil nails against internal limit states.

Download Full-text

ESTIMATING THE RUNNING COSTS OF COMMERCIAL BUILDINGS: ARTIFICIAL NEURAL NETWORK MODELING

Proceedings of International Structural Engineering and Construction ◽

10.14455/isec.res.2019.70 ◽

2019 ◽

Vol 6 (1) ◽

Author(s):

Devindi Geekiyanage ◽

Thanuja Ramachandra

Keyword(s):

Neural Network ◽

Artificial Neural Network ◽

Life Cycle Cost ◽

Prediction Accuracy ◽

Building Design ◽

Commercial Buildings ◽

Neural Network Modeling ◽

Ann Model ◽

Design Variables ◽

Artificial Neural

Running costs of a building is a substantial share of its total life-cycle cost (LCC) and it ranges between 70-80% in commercial buildings. Despite its significant contribution to LCC, investors and construction industry practitioners tend to mostly rely on construction cost exclusively. Though the early stage estimation of running costs is limited due to the unavailability of historical cost data, several efforts have been taken to estimate the running costs of buildings using different cost estimation techniques. However, the prediction accuracy of those models is still challenged due to less quality and amount of data employed. This study, therefore, developed an artificial neural network (ANN) model for running costs estimation of commercial buildings with the use of building design variables. The study was quantitively approached and running costs data together with 13 building design variables were collected from 35 commercial buildings. The ANN model developed resulted in a 96.6% perfect correlation between the running cost and building design variables. The testing and validation of the model developed indicate that there is greater prediction accuracy. These findings will enable industry practitioners to make informed cost decisions on implications of running costs in commercial buildings at its early stages, eliminating excessive costs to be incurred during the operational phase.

Download Full-text

Optimization of Position and Number of Hotspot Detectors Using Artificial Neural Network and Genetic Algorithm to Estimate Material Levels Inside a Silo

Sensors ◽

10.3390/s21134427 ◽

2021 ◽

Vol 21 (13) ◽

pp. 4427

Author(s):

Jeong Hoon Rhee ◽

Sang Il Kim ◽

Kang Min Lee ◽

Moon Kyum Kim ◽

Yun Mook Lim

Keyword(s):

Neural Network ◽

Genetic Algorithm ◽

Artificial Neural Network ◽

Prediction Accuracy ◽

Economic Feasibility ◽

Ann Model ◽

Ground Truth Data ◽

Efficient Operation ◽

Internal Storage ◽

Artificial Neural

To realize efficient operation of a silo, level management of internal storage is crucial. In this study, to address the existing measurement limitations, a silo hotspot detector, which is typically utilized for internal silo temperature monitoring, was employed. The internal temperature data measured using the hotspot detectors were used to train an artificial neural network (ANN) algorithm to predict the level of the internal storage of the silo. The prediction accuracy was evaluated by comparing the predicted data with ground truth data. We combined the ANN model with the genetic algorithm (GA) to improve the prediction accuracy and establish efficient sensor installation positions and number to proceed with optimization. Simulation results demonstrated that the best predictive performance (up to 97% accuracy) was achieved when the ANN structure was 9-19-19-1. Furthermore, the numbers of efficient sensors and sensors positions determined using the proposed ANN-GA technique were reduced from seven to five or four, thereby ensuring economic feasibility.

Download Full-text

An Empirical Comparison of Multiple Linear Regression and Artificial Neural Network for Concrete Dam Deformation Modelling

Mathematical Problems in Engineering ◽

10.1155/2019/7620948 ◽

2019 ◽

Vol 2019 ◽

pp. 1-13 ◽

Cited By ~ 2

Author(s):

Mingjun Li ◽

Junxing Wang

Keyword(s):

Neural Network ◽

Artificial Neural Network ◽

Linear Regression ◽

Multiple Linear Regression ◽

Prediction Accuracy ◽

Ann Model ◽

Concrete Dam ◽

Artificial Neural ◽

Dam Deformation ◽

Artificial Neural Network Ann

Deformation predicting models are essential for evaluating the health status of concrete dams. Nevertheless, the application of the conventional multiple linear regression model has been limited due to the particular structure, random loading, and strong nonlinear deformation of concrete dams. Conversely, the artificial neural network (ANN) model shows good adaptability to complex and highly nonlinear behaviors. This paper aims to evaluate the specific performance of the multiple linear regression (MLR) and artificial neural network (ANN) model in characterizing concrete dam deformation under environmental loads. In this study, four models, namely, the multiple linear regression (MLR), stepwise regression (SR), backpropagation (BP) neural network, and extreme learning machine (ELM) model, are employed to simulate dam deformation from two aspects: single measurement point and multiple measurement points, approximately 11 years of historical dam operation records. Results showed that the prediction accuracy of the multipoint model was higher than that of the single point model except the MLR model. Moreover, the prediction accuracy of the ELM model was always higher than the other three models. All discussions would be conducted in conjunction with a gravity dam study.

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

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

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