scholarly journals Factors affecting injury severity in vehicle-pedestrian crashes: A day-of-week analysis using random parameter ordered response models and Artificial Neural Networks

2020 ◽  
Vol 9 (2) ◽  
pp. 100-115 ◽  
Author(s):  
Seyedmirsajad Mokhtarimousavi ◽  
Jason C. Anderson ◽  
Atorod Azizinamini ◽  
Mohammed Hadi
Keyword(s):  
Neural Networks ◽  
Artificial Neural Networks ◽  
Injury Severity ◽  
Random Parameter ◽  
Response Models ◽  
Factors Affecting ◽  
Artificial Neural ◽  
Ordered Response ◽  
Pedestrian Crashes

scholarly journals The use of classical methods and neural networks in deformation studies of hydrotechnical objects

2020 ◽  
Vol 12 (1) ◽  
pp. 718-725
Author(s):  
Maria Mrówczyńska ◽  
Jacek Sztubecki ◽  
Małgorzata Sztubecka ◽  
Izabela Skrzypczak
Keyword(s):  
Neural Networks ◽  
Artificial Neural Networks ◽  
Cylinder Surface ◽  
Building Structures ◽  
Steel Cylinder ◽  
Factors Affecting ◽  
Initial Stage ◽  
Artificial Neural ◽  
Set Of Points

Abstract Objects’ measurements often boil down to the determination of changes due to external factors affecting on their structure. The estimation of changes in a tested object, in addition to proper measuring equipment, requires the use of appropriate measuring methods and experimental data result processing methods. This study presents a statement of results of geometrical measurements of a steel cylinder that constitutes the main structural component of the historical weir Czersko Polskie in Bydgoszcz. In the initial stage, the estimation of reliable changes taking place in the cylinder structure involved the selection of measuring points essential for mapping its geometry. Due to the continuous operation of the weir, the points covered only about one-third of the cylinder area. The set of points allowed us to determine the position of the cylinder axis as well as skews and deformations of the cylinder surface. In the next stage, the use of methods based on artificial neural networks allowed us to predict the changes in the tested object. Artificial neural networks have proved to be useful in determining displacements of building structures, particularly hydro-technical objects. The above-mentioned methods supplement classical measurements that create the opportunity for carrying out additional analyses of changes in a spatial position of such structures. The purpose of the tests is to confirm the suitability of artificial neural networks for predicting displacements of building structures, particularly hydro-technical objects.

Factors Affecting the Stability of Nanoemulsions—Use of Artificial Neural Networks

2009 ◽  
Vol 27 (1) ◽  
pp. 37-45 ◽  
Author(s):  
Amir Amani ◽  
Peter York ◽  
Henry Chrystyn ◽  
Brian J. Clark
Keyword(s):  
Neural Networks ◽  
Artificial Neural Networks ◽  
Factors Affecting ◽  
Artificial Neural ◽  
The Stability

Application of Artificial Neural Networks to Predict Cotton Production: A Case Study in Diyarbakır Province, Turkey

2020 ◽  
Author(s):  
Nazire Mikail ◽  
Mehmet Fırat BARAN
Keyword(s):  
Neural Network ◽  
Neural Networks ◽  
Artificial Neural Networks ◽  
Plant Production ◽  
Good Prediction ◽  
Ann Model ◽  
Cotton Production ◽  
Factors Affecting ◽  
Artificial Neural Network Method ◽  
Artificial Neural

Abstract Cultivators are always curious about the factors affecting yield in plant production. Determining these factors can provide information about the yield in the future. The reliability of information is dependent on a good prediction model. According to the operating process, artificial neural networks imitate the neural network in humans. The ability to make predictions for the current situation by combining the information people have gained from different experiences is designed in artificial neural networks. Therefore, in complex problems, it gives better results than artificial neural networks.In this study, we used an artificial neural network method to model the production of cotton. From a comprehensive datum collection spanning 73 farms in Diyarbakır, Turkey, the mean cotton production was 559.19 kg da-1. There are four factors that are selected as pivotal inputs into this model. As a result, the ultimate ANN model is able to forshow cotton production, which is built on elements such as farm states (cotton area and irrigation periodicity), machinery usage and fertilizer consumption.At the end of the study, cotton yield was estimated with 84% accuracy.

scholarly journals Building artificial neural networks to predict direction and magnitude of wind, current and wave for sailing vessels

2018 ◽  
Vol 8 (2) ◽  
pp. 55-61
Author(s):  
Timur Inan ◽  
Ahmet Fevzi Baba
Keyword(s):  
Neural Networks ◽  
Artificial Neural Networks ◽  
Wind Direction ◽  
Wind Wave ◽  
Current Direction ◽  
Wave Direction ◽  
Factors Affecting ◽  
Historical Information ◽  
Sea Current ◽  
Artificial Neural

Current, wind, wave direction and magnitude are important factors affecting the course of ships. These factors may act positively or negatively depending on the course of a vessel. In both cases, optimization of the route according to these conditions, will improve the factors such as labor, fuel and time. In order to estimate the wind, wave, current direction and magnitude for the region to be navigated, it is necessary to develop a system that can make predictions by using historical information. Our study uses historical information from the E1M3A float, which is a part of the POSEIDON system. With this information being used, artificial neural networks were trained and three separate artificial neural networks were created. Artificial neural networks can predict wind direction and speed, direction and speed of sea current, wave direction and heigth. The esmitations made by this system are only valid for the region where the float is located. For different regions, it is necessary to use artificial neural networks trained using the historical information of those regions. This study is an example for prospective studies.

scholarly journals A Comprehensive Comparison of Artificial Neural Networks and Some Regression Modeling Techniques on Dominant Height Predictions of Oriental Spruce in a Mixed Forest, the Northeast Turkey

2021 ◽  
Author(s):  
İlker ERCANLI ◽  
Ferhat Bolat ◽  
Hakkı Yavuz
Keyword(s):  
Neural Networks ◽  
Artificial Neural Networks ◽  
Mixed Forest ◽  
Random Parameter ◽  
Dominant Height ◽  
Modeling Techniques ◽  
Artificial Neural ◽  
Dominant Height Growth ◽  
Height Predictions ◽  
Oriental Spruce

Abstract Background: Dominant height is needed for assessing silvicultural practices in sustainable wood production management. Also, dominant height is used as an important explanatory variable in forest growth and yield models. This paper introduces the evaluation for Artificial Neural Networks and Some Regression Modeling Techniques on Dominant Height Predictions of Oriental Spruce in a Mixed Forest, the Northeast Turkey. Methods: In this study, 873 height-age pairs were obtained from oriental spruce trees in a mixed forest stand. Nonlinear mixed-effects models (NLMEs), autoregressive models (ARM), dummy variable method (DVM), and artificial neural networks (ANNs) were compared to predict dominant height growth. Results: The best predictive model was NLME with single random parameter (root mean square error, RMSE: 0.68 m). The results showed that NLMEs outperformed ARM (RMSE: 1.09 m), DVM in conjunction with ARM (RMSE: 1.09 m), and ANNs (RMSE: from 1.11 to 2.40 m) in majority of the cases. Whereas considering variations among observations by random parameter(s) significantly improved predictions of dominant height, taking into account correlated error terms by autoregressive correlation parameter(s) enhanced slightly the predictions. ANNs generally underperformed compared to NLMEs, ARM, and DVM with ARM. Conclusion: All regression techniques fulfilled the desirable characteristics such as sigmoidal pattern, polymorphism, multiple asymptote, base-age invariance, and inflection point. However, ANNs could not most of these features excluding sigmoidal pattern. Accordingly, ANNs seem to insufficient to assure biological growth assumptions regarding dominant height growth.

scholarly journals The Use of Artificial Neural Networks to Prioritize Impact Factors Affecting Thai Rural Village Development

2011 ◽  
Vol 2 (2) ◽  
pp. 89-93
Author(s):  
Wittaya Pornpatcharapong ◽  
Chuvej Chansa-ngavej . ◽  
Supachok Wiriyacosol . ◽  
Chanchai Bunchapattanasakda .
Keyword(s):  
Neural Networks ◽  
Artificial Neural Networks ◽  
Community Development ◽  
Impact Factors ◽  
Factors Affecting ◽  
Rural Village ◽  
Artificial Neural ◽  
Information Database ◽  
Development Department

This paper aims to prioritize impact factors which affect Thai rural village development. The basic village-leveled information database (NRD-2C) of the Community Development Department (CDD), Ministry of Interior, Thailand, was applied with Artificial Neural Networks (ANN) to measure the amount of impact for each factor affecting Thai rural village development. According to results, the top 5 impact factors are “Land Possession”, “Electricity”, “Communication”, “Educational Level”, and “Household Industry” with 17.88, 15.35, 14.02, 12.06, and 10.57 score of impact respectively with 95.60 percent of estimated accuracy.

Sign in / Sign up

Export Citation Format

Share Document