scholarly journals Estimation of Botanical Composition in Mixed Clover–Grass Fields Using Machine Learning-Based Image Analysis

2021 ◽  
Vol 12 ◽  
Author(s):  
Sashuang Sun ◽  
Ning Liang ◽  
Zhiyu Zuo ◽  
David Parsons ◽  
Julien Morel ◽  
...  
Keyword(s):  
Image Analysis ◽  
Transfer Learning ◽  
Back Propagation ◽  
Back Propagation Neural Network ◽  
Botanical Composition ◽  
Estimation Model ◽  
Learning Methods ◽  
Convolutional Network ◽  
Forage Management ◽  
Bpnn Model

This study aims to provide an effective image analysis method for clover detection and botanical composition (BC) estimation in clover–grass mixture fields. Three transfer learning methods, namely, fine-tuned DeepLab V3+, SegNet, and fully convolutional network-8s (FCN-8s), were utilized to detect clover fractions (on an area basis). The detected clover fraction (CFdetected), together with auxiliary variables, viz., measured clover height (Hclover) and grass height (Hgrass), were used to build multiple linear regression (MLR) and back propagation neural network (BPNN) models for BC estimation. A total of 347 clover–grass images were used to build the estimation model on clover fraction and BC. Of the 347 samples, 226 images were augmented to 904 images for training, 25 were selected for validation, and the remaining 96 samples were used as an independent dataset for testing. Testing results showed that the intersection-over-union (IoU) values based on the DeepLab V3+, SegNet, and FCN-8s were 0.73, 0.57, and 0.60, respectively. The root mean square error (RMSE) values for the three transfer learning methods were 8.5, 10.6, and 10.0%. Subsequently, models based on BPNN and MLR were built to estimate BC, by using either CFdetected only or CFdetected, grass height, and clover height all together. Results showed that BPNN was generally superior to MLR in terms of estimating BC. The BPNN model only using CFdetected had a RMSE of 8.7%. In contrast, the BPNN model using all three variables (CFdetected, Hclover, and Hgrass) as inputs had an RMSE of 6.6%, implying that DeepLab V3+ together with BPNN can provide good estimation of BC and can offer a promising method for improving forage management.

Integrated AHP-BPNN Model for Wind Farm Investment Evaluation

2014 ◽  
Vol 541-542 ◽  
pp. 966-971
Author(s):  
Xiang Feng Zhang ◽  
Tian Yu Liu ◽  
Bin Jiao
Keyword(s):  
Wind Farm ◽  
Evaluation Method ◽  
Back Propagation ◽  
Wind Farms ◽  
Back Propagation Neural Network ◽  
Analytic Hierarchy ◽  
Farm Investment ◽  
Hierarchy Process ◽  
Power Project ◽  
Bpnn Model

The construction of wind farms grows quickly in China. It is necessary for stakeholders to estimate investment costs and to make good decisions about a wind power project by making a budget for the investment. This paper proposed an evaluation method by integrating the analytic hierarchy process (AHP) with back-propagation neural network (BPNN) to evaluate wind farm investment. In the AHP-BPNN model, the AHP method is used to determine the factors of wind farm investment. The factors with high importance are reserved while those with low importance are eliminated, which can decrease the number of inputs of the BPNN. The experiment results show that the integrated model is feasible and effective.

A comparative study of different prediction models in predicting human resource demands

2021 ◽  
pp. 1-11
Author(s):  
Bo Huang
Keyword(s):  
Neural Network ◽  
Human Resources ◽  
Comparative Study ◽  
Human Resource ◽  
Prediction Models ◽  
Back Propagation ◽  
Back Propagation Neural Network ◽  
Prediction Methods ◽  
Bpnn Model ◽  
Good Agreement

This study analyzed three prediction models: ID model, GM (1,1) model and back-propagation neural network (BPNN) model. Firstly, the principles of the three models were introduced, and the prediction methods of the three models were analyzed. Then, taking enterprise A as an example, the demand for human resources was predicted, and the prediction results of the three models were compared. The results showed that the maximum and minimum errors were 240 people and 12 people respectively in the prediction results of the ID3 model and 64 people and 37 people respectively in the prediction results of the GM (1, 1) model; the errors of the BPNN model were smaller than ten people, and the minimum value of the BPNN model was three people, which was in good agreement with the actual value. The prediction of the human resource demand of enterprise A in the future five years with the BPNN model suggested that the demand for employees would growing rapidly. The results show that the BPNN model has better reliability and can be popularized and applied in practice.

scholarly journals An Estimation Model on Electricity Consumption of New Metro Stations

2020 ◽  
Vol 2020 ◽  
pp. 1-11
Author(s):  
Zhao Yu ◽  
Yun Bai ◽  
Qian Fu ◽  
Yao Chen ◽  
Baohua Mao
Keyword(s):  
Interior Design ◽  
Back Propagation ◽  
Electricity Consumption ◽  
Back Propagation Neural Network ◽  
Support Vector ◽  
Estimation Model ◽  
Metro Station ◽  
New Energy ◽  
Passenger Volume ◽  
Major Factors

Electricity consumption of metro stations increases sharply with expansion of a metro network and this has been a growing cause for concern. Based on relevant historical data from existing metro stations, this paper proposes a support vector regression (SVR) model to estimate daily electricity consumption of a newly constructed metro station. The model considers some major factors influencing the electricity consumption of metro station in terms of both the interior design scheme of a station (e.g., layout of the station and allocation of facilities) and external factors (e.g., passenger volume, air temperature and relative humidity). A genetic algorithm with five-fold cross-validation is used to optimize the hyper-parameters of the SVR model in order to improve its accuracy in estimating the electricity consumption of a metro station (ECMS). With the optimized hyper-parameters, results from case studies on the Beijing Subway showed that the estimating accuracy of the proposed SVR model could reach up to 95% and the correlation coefficient was 0.89. It was demonstrated that the proposed model could outperform the traditional methods which use a back-propagation neural network or multivariate linear regression. The method presented in this paper can be an adequate tool for estimating the ECMS and should further assist in the delivery of new, energy-efficient metro stations.

Prediction of Surface Roughness Using Back-Propagation Neural Network in End Milling Ti-6Al-4V Alloy

2011 ◽  
Vol 325 ◽  
pp. 418-423 ◽  
Author(s):  
Song Zhang ◽  
Jian Feng Li
Keyword(s):  
Neural Network ◽  
Surface Roughness ◽  
End Milling ◽  
Back Propagation ◽  
Cutting Speed ◽  
Cutting Parameters ◽  
Back Propagation Neural Network ◽  
Depth Of Cut ◽  
Radial Depth ◽  
Bpnn Model

Surface roughness plays a significant role in machining industry for proper planning of process system and optimizing the cutting conditions. In this paper, a back-propagation neural network (BPNN) model has been developed for the prediction of surface roughness in end milling process. A large number of milling experiments were conducted on Ti-6Al-4V alloy using the uncoated carbide tools. Four cutting parameters including cutting speed, feed per tooth, radial depth of cut, and axial depth of cut are used as the inputs to develop the BPNN model, while surface roughness corresponding to these combinations of different cutting parameters is the output of the neural network model. The performance of the trained BPNN model has been verified with the experimental results, and it is found that the BPNN predicted and the experimental values are very close to each other.

scholarly journals Forecasting Method for Urban Rail Transit Ridership at Station Level Using Back Propagation Neural Network

2016 ◽  
Vol 2016 ◽  
pp. 1-9 ◽  
Author(s):  
Junfang Li ◽  
Minfeng Yao ◽  
Qian Fu
Keyword(s):  
Relative Error ◽  
Total Population ◽  
Back Propagation ◽  
Back Propagation Neural Network ◽  
Urban Rail Transit ◽  
Rail Transit ◽  
Contribution Rate ◽  
Urban Rail ◽  
Forecasting Method ◽  
Bpnn Model

Direct forecasting method for Urban Rail Transit (URT) ridership at the station level is not able to reflect nonlinear relationship between ridership and its predictors. Also, population is inappropriately expressed in this method since it is not uniformly distributed by area. In this paper, a new variable, population per distance band, is considered and a back propagation neural network (BPNN) model which can reflect nonlinear relationship between ridership and its predictors is proposed to forecast ridership. Key predictors are obtained through partial correlation analysis. The performance of the proposed model is compared with three other benchmark models, which are linear model with population per distance band, BPNN model with total population, and linear model with total population, using four measures of effectiveness (MOEs), maximum relative error (MRE), smallest relative error (SRE), average relative error (ARE), and mean square root of relative error (MSRRE). Also, another model for contribution rate of population per distance band to ridership is formulated based on the BPNN model with nonpopulation variables fixed. Case studies with Japanese data show that BPNN model with population per distance band outperforms other three models and the contribution rate of population within special distance band to ridership calculated through the contribution rate model is 70%~92.9% close to actual statistical value. The result confirms the effectiveness of models proposed in this paper.

scholarly journals Porosity Prediction of Granular Materials through Discrete Element Method and Back Propagation Neural Network Algorithm

2020 ◽  
Vol 10 (5) ◽  
pp. 1693
Author(s):  
Yu Liu ◽  
Miaomiao Li ◽  
Peifeng Su ◽  
Biao Ma ◽  
Zhanping You
Keyword(s):  
Neural Network ◽  
Granular Material ◽  
Granular Materials ◽  
Particle Shape ◽  
Back Propagation ◽  
Discrete Element ◽  
Back Propagation Neural Network ◽  
Network Algorithm ◽  
Neural Network Algorithm ◽  
Bpnn Model

Granular materials are used directly or as the primary ingredients of the mixtures in industrial manufacturing, agricultural production and civil engineering. It has been a challenging task to compute the porosity of a granular material which contains a wide range of particle sizes or shapes. Against this background, this paper presents a newly developed method for the porosity prediction of granular materials through Discrete Element Modeling (DEM) and the Back Propagation Neural Network algorithm (BPNN). In DEM, ball elements were used to simulate particles in granular materials. According to the Chinese specifications, a total of 400 specimens in different gradations were built and compacted under the static pressure of 600 kPa. The porosity values of those specimens were recorded and applied to train the BPNN model. The primary parameters of the BPNN model were recommended for predicting the porosity of a granular material. Verification was performed by a self-designed experimental test and it was found that the prediction accuracy could reach 98%. Meanwhile, considering the influence of particle shape, a shape reduction factor was proposed to achieve the porosity reduction from sphere to real particle shape.

Sign in / Sign up

Export Citation Format

Share Document