meta-heuristic algorithms

Introduction :

Sugarcane is a tropical, perennial grass that forms lateral shoots at the base to produce multiple stems. It is the main source of sugar production and one of the most important sources of energy production in the world. Today, the use of artificial intelligence and data mining findings to help predict product production is considered. Determining the relationship between inputs and outputs of production process using artificial intelligence (AI) has drawn more attention rather than mathematical models to find the relationships between input and output variables by training, and producing results without any prior assumptions. The adaptive neuro-fuzzy inference system (ANFIS), as a form of AI, is a combination of artificial neural network (ANN) and fuzzy systems that uses the learning capability of the ANN to derive the fuzzy if-then rules with appropriate membership functions worked out from the training pairs, which in turn leads to the inference.Particle swarm optimization (PSO) is an algorithm modeled on swarm intelligence, in a search space, or model it finds a solution to an optimization problem and predict social behavior in the presence of objectives. The PSO is a population-based stochastic computer algorithm, modeled on swarm intelligence. Swarm intelligence is based on social psychological principles and it provides insights into social behavior, also helps to many engineering applications. Feature selection is becoming very important in predictive analytics. Indeed, many data sets contain a large number of features, so we have to select the most useful ones. One of the most advanced methods to do that is the genetic algorithm (GA). Genetic algorithms can select the best subset of variables for predictive model. The purpose of this research is to evaluate the applicability of one artificial intelligence technique including adaptive neuro-fuzzy inference system and also combining this technique with particle swarm optimization to increase the accuracy and speed of training of the neuro-fuzzy system in prediction of yield and recoverable sugar percentage (R.S%) of sugarcane.

Materials and Methods:

 In this paper, one main pattern of adaptive neuro-fuzzy inference system (ANFIS) and one synthetic model of adaptive neuro-fuzzy inference system with particle swarm optimization (PSO) were used to predict the studied properties by MATLAB version 2017. Initial data for this study were collected from Debal-Khozaie Agro-industry Company in Khouzestan province, Iran. The actual data for the seven periods of sugarcane harvest from 2010 to 2017 were used for modeling. The studied parameters included a set of agronomic factors, soil characteristics, irrigation and climate in the study area. The test data sets were used for comparison of selected ANFIS and ANFIS with PSO, as well as for the observation values. This comparison was performed by using three statistical indices: Determination Coefficient (R2), Root Mean Square Error (RMSE) and Mean Absolute Percentage Error (MAPE).

Results and Discussion:

From all of the studied parameters, eleven parameters were selected as the effective features by the binary genetic algorithm (BGA). In feature selection, the function to optimize is the generalization performance of a predictive model. More specifically, in this method, purpose was to minimize the error of the model on an independent data set not used to create the model. The data were randomly divided into two groups: training and testing. Each pattern was modeled separately and then the results were compared. The results showed that the combination of adaptive neuro-fuzzy inference system with particle swarm optimization algorithm (ANFIS-PSO) had better performance in predicting cane yield and recoverable sugar percentage. In ANFIS-PSO model the root mean square error, mean absolute percentage error and coefficient of determination values were found 0.0181, 0.0217, 0.9237 and 0.0086, 0.0138, 0.9847 respectively for two variables of cane yield and recoverable sugar percentage. In relation to the predicted cane yield by the neuro-fuzzy network with particle swarm algorithm, it can be concluded that among the effective factors, with increasing plant age and use of resistant varieties, the amount of yield was decreased and increased, respectively.

Conclusion:

 The hybrid pattern of adaptive neuro-fuzzy inference system with the particle swarm optimization has been directed against the mere neuro-fuzzy system to a more accurate and stronger solution. Indeed, it can be concluded that ANFIS model with the PSO has the ability for precise estimation of sugarcane yield and recoverable sugar percentage.

In this study, to predict sugarcane yield, an Artificial Neural Network based on meta-heuristic algorithms is used as an efficient method to estimate crop yield based on actual data. In order to predict sugarcane yield, effective parameters such as plant characteristics, electrical conductivity of soil and water, maximum temperature and average hours of sunshine during the growing season and on a time scale of seven years were used. Accordingly, four hybrid models were used to build neural networks which including of artificial neural network based on Back Propagation (BP) algorithm, combining neural network with Genetic Algorithm (GA), combining neural network with Particle Swarm Optimization (PSO) algorithm and finally a new approach as combining neural network with GA-PSO. The results show that the neural network performance can be improved using meta-heuristic algorithms and can be increased significantly the prediction power. The Mean Square Error (MSE) and correlation coefficient (R) in the hybrid method of neural network with GA-PSO were obtained 0.00057 and 0.91457 respectively on the test data, which show the superiority of this method to other patterns. In addition, cross validation test of the proposed model by K-Nearest Neighbors showed the accuracy of training and test data to predict sugarcane yield has been equal to 98.5% and 95.5%, respectively.

The weeds must be removed from the field due to their competition with principal crops to use water, nutrients, sunlight, etc. There are different methods to remove the weeds: mechanically, manually or chemically (applying herbicides). For farmers, applying herbicides is a usual way, but brings some concerns, from the point of environmental issues, due to equal application of chemicals all over fields, regardless the presence or absence of weed. For this reason, a machine vision system based on video processing was proposed to recognize Secale cereale L. (as a weed) from potato plant (as principal crop) to make herbicide application more accurate. Nine hundred sixty five objects were recognized after taking videos, pre-processing and segmentation. Fourteen features were extracted from each object. Using the hybrid artificial neural network-genetic algorithm, of 14 extracting features, only 6 features were selected as effective ones: average, the third moment, autocorrelation, correlation, dissimilarity, and entropy. Data were classified into two groups: training data (70% of the total data) and testing data (30% of the total data). The classification was performed using hybrid of artificial neural network - Bio-geography Based Optimization (BBO) algorithm. Performance of classification system was evaluated through analysis of confusion matrix and Receiver Operating Characteristic (ROC). Sensitivity, specificity, and accuracy were calculated using confusion matrix. The results showed that the sensitivity, accuracy and specificity of classification system reached to an acceptable level: 99.49 %, 99.65% and 98.91%, respectively. Our conclusion is that it is possible to manufacture the machine vision system with mentioned aims that work as online.