scholarly journals Spatial Variability of Aroma Profiles of Cocoa Trees Obtained through Computer Vision and Machine Learning Modelling: A Cover Photography and High Spatial Remote Sensing Application

Sensors ◽  
2019 ◽  
Vol 19 (14) ◽  
pp. 3054 ◽  
Author(s):  
Sigfredo Fuentes ◽  
Gabriela Chacon ◽  
Damir D. Torrico ◽  
Andrea Zarate ◽  
Claudia Gonzalez Viejo
Keyword(s):  
Management Practices ◽  
Mean Squared Error ◽  
Computer Application ◽  
Aerial Image ◽  
Canopy Architecture ◽  
Ann Model ◽  
Aroma Profile ◽  
Squared Error ◽  
Artificial Neural Network Ann ◽  
The Tropics

Cocoa is an important commodity crop, not only to produce chocolate, one of the most complex products from the sensory perspective, but one that commonly grows in developing countries close to the tropics. This paper presents novel techniques applied using cover photography and a novel computer application (VitiCanopy) to assess the canopy architecture of cocoa trees in a commercial plantation in Queensland, Australia. From the cocoa trees monitored, pod samples were collected, fermented, dried, and ground to obtain the aroma profile per tree using gas chromatography. The canopy architecture data were used as inputs in an artificial neural network (ANN) algorithm, with the aroma profile, considering six main aromas, as targets. The ANN model rendered high accuracy (correlation coefficient (R) = 0.82; mean squared error (MSE) = 0.09) with no overfitting. The model was then applied to an aerial image of the whole cocoa field studied to produce canopy vigor, and aroma profile maps up to the tree-by-tree scale. The tool developed could significantly aid the canopy management practices in cocoa trees, which have a direct effect on cocoa quality.

scholarly journals Spatial Variability of Aroma Profiles of Cocoa Trees Obtained Through Computer Vision and Machine Learning Modelling: A Cover Photography and Satellite Imagery Application

2019 ◽  
Author(s):  
Sigfredo Fuentes ◽  
Gabriela Chacon ◽  
Damir D. Torrico ◽  
Andrea Zarate ◽  
Claudia Gonzalez Viejo
Keyword(s):  
Management Practices ◽  
Satellite Image ◽  
High Accuracy ◽  
Computer Application ◽  
Canopy Architecture ◽  
Ann Model ◽  
Aroma Profile ◽  
Complex Products ◽  
Artificial Neural Network Ann ◽  
The Tropics

Cocoa is an important commodity crop not only to produce one of the most complex products such as chocolate from the sensory perspective, but one that commonly grows in developing countries close to the tropics. This paper presents novel techniques applied using cover photography and a novel computer application (VitiCanopy) to assess the canopy architecture of cocoa trees in a commercial plantation in Queensland, Australia. From the cocoa trees monitored, pod samples were collected, fermented, dried and grinded to obtain the aroma profile per tree using gas chromatography. The canopy architecture data were used as inputs in an artificial neural network (ANN) algorithm and the aroma profile considering six main aromas as targets. The ANN model rendered high accuracy (R = 0.82; MSE = 0.09) with no overfitting. The model was then applied to a satellite image from the whole cocoa field studied to produce canopy vigor and aroma profile maps up to the tree-by-tree scale. The tool developed could aid significantly the canopy management practices in cocoa trees that have a direct effect on cocoa quality.

scholarly journals Estimation Of Mechanical Properties Of Sandstones From Petrographic Characteristics Using Artificial Neural Networks (ANNs)

2021 ◽  
Vol 71 ◽  
pp. 13-22
Author(s):  
Yasin Abdi ◽  
◽  
Bijan Yusefi-Yegane ◽  
Amin Jamshidi
Keyword(s):  
Mean Squared Error ◽  
Accurate Determination ◽  
Dry Density ◽  
Ann Model ◽  
Laboratory Methods ◽  
Squared Error ◽  
Artificial Neural ◽  
Artificial Neural Network Ann ◽  
Mlr Model

The accurate determination of strength parameters of rocks such as uniaxial compressive strength (UCS) and elastic modulus (E) using direct and laboratory methods require substantial time and cost. Therefore, the production of predictive relationships and models to forecast the UCS and E is of critical necessity in rock engineering. This study deals with the estimation of UCS and E of sandstones from petrographic characteristics by an artificial neural network (ANN) and multiple regression. For this purpose, 130 core specimens were prepared from sandstones in different locations in Iran. The specimens were tested to determine UCS, E, dry density, and porosity. Also, the petrographic studies including the determination of 11 textural and mineralogy parameters were performed on selected samples. The performance of the ANN model and regression analysis was evaluated using the criteria such as correlation coefficient (R), root mean squared error (RMSE), and variance account for (VAF). According to the ANN results, values of R, RMSE, and VAF were obtained to be 0.925, 0.089, and 97% for UCS and 0.876, 0.094, and 96% for E, respectively. In comparison, for the MLR model, the obtained R, RMSE, and VAF were 0.845, 0.101, and 95% for UCS and 0.797, 0.116, and 93% for E, respectively. A comparison between the findings illustrated that the ANN model was more suitable for forecasting the UCS and E compared with the MLR method.

scholarly journals Metaheuristic Approaches Integrated with ANN in Forecasting Daily Emergency Department Visits

2021 ◽  
Vol 2021 ◽  
pp. 1-14
Author(s):  
Engin Pekel ◽  
Muhammet Gul ◽  
Erkan Celik ◽  
Samuel Yousefi
Keyword(s):  
Mean Squared Error ◽  
Absolute Error ◽  
Emergency Department Visits ◽  
Training Dataset ◽  
Percentage Error ◽  
Quality Level ◽  
Ann Model ◽  
Squared Error ◽  
Ed Visits ◽  
Artificial Neural Network Ann

The overall service quality level of Emergency Departments (EDs) can be improved by accurate forecasting of patient visits. Accordingly, this study aims to evaluate the use of three metaheuristic approaches integrated with Artificial Neural Network (ANN) in forecasting daily ED visits. To do this, five performance measures are used for evaluating the accuracy of the proposed approaches, including Bayesian ANN, Genetic Algorithm-based ANN (GA-ANN), and Particle Swarm Optimization algorithm-based ANN (PSO-ANN). The outputs of this study show that the PSO-ANN model provides the most dominant performance in both the training and testing process. The lowest error is obtained with a mean absolute percentage error (MAPE) of 6.3%, Mean Absolute Error (MAE) of 42.797, Mean Squared Error (MSE) of 2499.340, Root Mean Square Error (RMSE) of 49.933, and R-squared (R2) of 0.824 on the training dataset. The lowest error with an MAPE of 6.0%, MAE of 40.888, MSE of 2839.998, RMSE of 53.292, and R2 of 0.791 is also obtained on the testing process.

scholarly journals Evaluation of coupled ANN-GA model to prioritize flood source areas in ungauged watersheds

2020 ◽  
Vol 51 (3) ◽  
pp. 423-442
Author(s):  
Naser Dehghanian ◽  
S. Saeid Mousavi Nadoushani ◽  
Bahram Saghafian ◽  
Morteza Rayati Damavandi
Keyword(s):  
Flood Control ◽  
Mean Squared Error ◽  
Absolute Error ◽  
Ann Model ◽  
Runoff Generation ◽  
Source Areas ◽  
Walnut Gulch ◽  
Artificial Neural Network Ann ◽  
Semi Arid ◽  
Flood Source

Abstract An important step in flood control planning is identification of flood source areas (FSAs). This study presents a methodology for identifying FSAs. Unit flood response (UFR) approach has been proposed to quantify FSAs at subwatershed and/or cell scale. In this study, a distributed ModClark model linked with Muskingum flow routing was used for hydrological simulations. Furthermore, a fuzzy hybrid clustering method was adopted to identify hydrological homogenous regions (HHRs) resulting in clusters involving the most effective variables in runoff generation as selected through factor analysis (FA). The selected variables along with 50-year rainfall were entered into an artificial neural network (ANN) model optimized via genetic algorithm (GA) to predict flood index (FI) at cell scale. The case studies were two semi-arid watersheds, Tangrah in northeastern Iran and Walnut Gulch Experimental Watershed in Arizona. The results revealed that the predicted values of FI via ANN-GA were slightly different from those derived via UFR in terms of mean squared error (MSE), mean absolute error (MAE), and relative error (RE). Also, the prioritized FSAs via ANN-GA were almost similar to those of UFR. The proposed methodology may be applicable in prioritization of HHRs with respect to flood generation in ungauged semi-arid watersheds.

scholarly journals Detection of Epilepsy based on EEG Signals using PCA with ANN Model

2021 ◽  
Vol 2070 (1) ◽  
pp. 012145
Author(s):  
R Shiva Shankar ◽  
CH Raminaidu ◽  
VV Sivarama Raju ◽  
J Rajanikanth
Keyword(s):  
Machine Learning ◽  
Epileptic Seizure ◽  
Mean Squared Error ◽  
Ann Model ◽  
Eeg Signals ◽  
Hinge Loss ◽  
Squared Error ◽  
Neurological Illness ◽  
The World

Abstract Epilepsy is a chronic neurological illness that affects millions of people throughout the world. Epilepsy affects around 50 million people globally. It is estimated that if epilepsy is correctly diagnosed and treated, up to 70% of people with the condition will be seizure-free. There is a need to detect epilepsy at the initial stages to reduce symptoms by medications and other strategies. We use Epileptic Seizure Recognition dataset to train the model which is provided by UCI Machine Learning Repository. There are 179 attributes and 11,500 unique values in this dataset. MLP, PCA with RF, QDA, LDA, and PCA with ANN were applied among them; PCA with ANN provided the better metrics. For the metrics, we received the following findings. It is 97.55% Accuracy, 94.24% Precision, 91.48% recall, 83.38% hinge loss, and 2.32% mean squared error.

scholarly journals Use of Empirical Mode Decomposition in Improving Neural Network Forecasting of Paddy Price

MATEMATIKA ◽  
2019 ◽  
Vol 35 (4) ◽  
pp. 53-64
Author(s):  
Siti Nabilah Syuhada Abdullah ◽  
Ani Shabri ◽  
Ruhaidah Samsudin
Keyword(s):  
Neural Network ◽  
Empirical Mode Decomposition ◽  
Mean Squared Error ◽  
Absolute Error ◽  
Percentage Error ◽  
Forecast Errors ◽  
Ann Model ◽  
Mode Decomposition ◽  
The Neural Network ◽  
Artificial Neural Network Ann

Since rice is a staple food in Malaysia, its price fluctuations pose risks to the producers, suppliers and consumers. Hence, an accurate prediction of paddy price is essential to aid the planning and decision-making in related organizations. The artificial neural network (ANN) has been widely used as a promising method for time series forecasting. In this paper, the effectiveness of integrating empirical mode decomposition (EMD) into an ANN model to forecast paddy price is investigated. The hybrid method is applied on a series of monthly paddy prices fromFebruary 1999 up toMay 2018 as recorded in the Malaysian Ringgit (MYR) per metric tons. The performance of the simple ANN model and the EMD-ANN model was measured and compared based on their root mean squared Error (RMSE), mean absolute error (MAE) and mean percentage error (MPE). This study finds that the integration of EMD into the neural network model improves the forecasting capabilities. The use of EMD in the ANN model made the forecast errors reduced significantly, and the RMSE was reduced by 0.012, MAE by 0.0002 and MPE by 0.0448.

Development of a Neural Statistical Model for the Relative Humidity Levels Prediction in the Region of Rabat-Kenitra (Morocco)

2021 ◽  
Author(s):  
Kaoutar Elazhari ◽  
Badreddine ABDALLAOUI ◽  
Ali DEHBI ◽  
Abdelaziz ABDALLAOUI ◽  
Hamid ZINEDDINE
Keyword(s):  
Relative Humidity ◽  
Meteorological Parameters ◽  
Transfer Functions ◽  
Mean Squared Error ◽  
Neural Model ◽  
Ann Model ◽  
History Of ◽  
Artificial Neural Network Ann ◽  
Hidden Layer ◽  
Mlp Model

Abstract This work provides the development of a powerful artificial neural network (ANN) model, for the prediction of relative humidity levels, using other meteorological parameters of the Rabat-Kenitra region. The treatment was applied to a database containing a daily history of five meteorological parameters of 9 stations covering this region for a period from 1979 to mid-2014. We have shown that for the prediction of relative humidity in this region, the best performing three-layer ANN (input, hidden and output) mathematical model is the multi-layer perceptron (MLP) model. This neural model using the Levenberg-Marquard algorithm, having an architecture [5-11-1] and the transfer functions Tansig in the hidden layer and Purelin in the output layer was able to estimate values for relative humidity very close to those observed. Indeed, this was affirmed by a low mean squared error (MSE) and a fairly high correlation coefficient (R), compared to the statistical indicators relating to the other models developed as part of this study.

scholarly journals Prediction of rubber vulcanization using an artificial neural network

2021 ◽  
Vol 75 (5) ◽  
pp. 277-283
Author(s):  
Jelena Lubura ◽  
Predrag Kojic ◽  
Jelena Pavlicevic ◽  
Bojana Ikonic ◽  
Radovan Omorjan ◽  
...  
Keyword(s):  
Neural Network ◽  
Artificial Neural Network ◽  
Large Scale ◽  
Mean Squared Error ◽  
Percentage Error ◽  
Dense Layer ◽  
Ann Model ◽  
Different Temperatures ◽  
Artificial Neural ◽  
Artificial Neural Network Ann

Determination of rubber rheological properties is indispensable in order to conduct efficient vulcanization process in rubber industry. The main goal of this study was development of an advanced artificial neural network (ANN) for quick and accurate vulcanization data prediction of commercially available rubber gum for tire production. The ANN was developed by using the platform for large-scale machine learning TensorFlow with the Sequential Keras-Dense layer model, in a Python framework. The ANN was trained and validated on previously determined experimental data of torque on time at five different temperatures, in the range from 140 to 180 oC, with a step of 10 oC. The activation functions, ReLU, Sigmoid and Softplus, were used to minimize error, where the ANN model with Softplus showed the most accurate predictions. Numbers of neurons and layers were varied, where the ANN with two layers and 20 neurons in each layer showed the most valid results. The proposed ANN was trained at temperatures of 140, 160 and 180 oC and used to predict the torque dependence on time for two test temperatures (150 and 170 oC). The obtained solutions were confirmed as accurate predictions, showing the mean absolute percentage error (MAPE) and mean squared error (MSE) values were less than 1.99 % and 0.032 dN2 m2, respectively.

scholarly journals Preliminary Researches Regarding the Use of Ann to Predict the Wheel-Soil Interaction

2013 ◽  
Vol 46 (1) ◽  
pp. 5-13
Author(s):  
H. Taghavifar ◽  
A. Mardani ◽  
I. Elahi
Keyword(s):  
Contact Area ◽  
Mean Squared Error ◽  
Back Propagation ◽  
Ann Model ◽  
Back Propagation Algorithm ◽  
Feed Forward Neural Network ◽  
Complex Relation ◽  
Squared Error ◽  
Conventional Models ◽  
Complex Relationships

Abstract Soil-wheel interactions as a phenomenon in which both components are behaving nonlinearly has been considered a sophisticated and complex relation to be modeled. A well-trained artificial neural networks as a useful tool is widely used in variety of science and engineering fields. We inspired to use this facility for application of some soil-wheel interaction products since nonlinear and complex relationships between wheel and soil necessitate more precise and reliable calculations. A 2-14-2 feed forward neural network with back propagation algorithm was found to have acceptable performance with mean squared error of 0.020. This model was used to predict two output variables of rut depth and contact area with regression correlations of 0.99961 and 0.99996 for rut depth and contact area, respectively. Furthermore, the results were compared with conventional models proposed for predicting the contact area and rut depth. The promising results of ANN model give higher privilege over conventional models. The findings also introduce the potential of ANN for modeling. However, the authors recommend further studies to be conducted in this realm of computing due to its great potential and capability.

PREDICTING THE RHEOLOGICAL PROPERTIES OF BITUMEN-FILLER MASTIC USING ARTIFICIAL NEURAL NETWORK METHODS

2017 ◽  
Vol 80 (1) ◽  
Author(s):  
Nursyahirah Khamis ◽  
Muhamad Razuhanafi Mat Yazid ◽  
Asmah Hamim ◽  
Sri Atmaja P. Rosyidi ◽  
Nur Izzi Md. Yusoff ◽  
...  
Keyword(s):  
Neural Network ◽  
Rheological Properties ◽  
Network Model ◽  
Mean Squared Error ◽  
Complex Modulus ◽  
Radial Basis Function Network ◽  
Ann Model ◽  
Feed Forward Neural Network ◽  
Squared Error ◽  
Function Network

This study was conducted to develop two types of artificial neural network (ANN) model to predict the rheological properties of bitumen-filler mastic in terms of the complex modulus and phase angle. Two types of ANN models were developed namely; (i) a multilayer feed-forward neural network model and (ii) a radial basis function network model. This study was also conducted to evaluate the accuracy of both types of models in predicting the rheological properties of bitumen-filler mastics by means of statistical parameters such as the coefficient of determination (R2), mean absolute error (MAE), mean squared error (MSE) and root mean squared error (RMSE) for every developed model. A set of dynamic shear rheometer (DSR) test data was used on a range of the bitumen-filler mastics with three filler types (limestone, cement and grit stone) and two filler concentrations (35 and 65% by mass). Based on the analysis performed, it was found that both models were able to predict the complex modulus and phase angle of bitumen-filler mastics with the average R2 value exceeding 0.98. A comparison between the two types of models showed that the radial basis function network model has a higher accuracy than multilayer feed-forward neural network model with a higher value of R2 and lower value of MAE, MSE and RMSE. It can be concluded that the ANN model can be used as an alternative method to predict the rheological properties of bitumen-filler mastic. 

Sign in / Sign up

Export Citation Format

Share Document