نویسندگان
چکیده
کلیدواژهها
عنوان مقاله [English]
نویسندگان [English]
Due to the possibility of mixing hard, semi soft and soft almonds with different market value after harvesting, using an effective separation system for supplying uniform products to market is essential. In order to classify almond varieties, an intelligent impact-acoustic system was used. The system operation was done by dropping almond nuts onto a steel impact plate through a pipe. Then features such as amplitude, phase and power spectral density (PSD) of almond nuts were extracted from analysis of sound signal captured by a microphone in both time and frequency domains by means of Fast Fourier Transform. Principal component analysis method was used to reduction of features. Two types of artificial intelligence techniques included Artificial Neural Networks (ANN's) and Adaptive Neuro-Fuzzy Inference System (ANFIS) were used to classify of almond nuts and their performance was compared. The neural network used, the multi-layer perceptron with back propagation algorithm and LM learning function. In ANFIS system, due to the limitation of inputs number, the three principal components of PSD feature that had higher priority were selected as inputs and hybrid optimization techniques were used for classification of almond classes as outputs. In comparing artificial intelligence techniques, ANN with about 96.2% accuracy had more performance to classify almond nuts than the ANFIS with 81% accuracy.
)