An Integrated System of Artificial Intelligence and Signal Processing Techniques for the Sorting and Grading of Nuts

Abstract

The existence of conversion industries to sort and grade hazelnuts with modern technology plays a vital role in export. Since most of the hazelnuts produced in Iran are exported to domestic and foreign markets without sorting and grading, it is necessary to have a well-functioning smart system to create added value, reduce waste, increase shelf life, and provide a better product delivery. In this study, a method is introduced to sort and grade hazelnuts by integrating audio signal processing and artificial neural network techniques. A system was designed and developed in which the produced sound, due to the collision of the hazelnut with a steel disk, was taken by the microphone placed under the steel disk and transferred to a PC via a sound card. Then, it was stored and processed by a program written in MATLAB software. A piezoelectric sensor and a circuit were used to eliminate additional ambient noise. The time-domain and wavelet domain features of the data were extracted using MATLAB software and were analyzed using Artificial Neural Network Toolbox. Seventy percent of the extracted data signals were used for training, 15% for validation, and the rest of the data was used to test the artificial neural network (Multilayer Perceptron network with Levenberg-Marquardt Learning algorithm). The model optimization and the number of neurons in the hidden layer were conducted based on mean square error (MSE) and prediction accuracy (PA). A total of 2400 hazelnuts were used to evaluate the system. The optimal neural network structure for sorting and grading hazelnuts was 4-21-3 (four neurons in input layers, 21 neurons in the hidden layer, and three outputs which are the desired classification). This neural network (NN) was used to classify hazelnut as big, small, hollow, or damaged. Results showed 96.1%, 89.3%, and 93.1% accuracy for big/small, hollow, or damaged hazelnuts were obtained, respectively.

Comparison of Heat Demand Prediction Using Wavelet Analysis and Neural Network for a District Heating Network

“…The same or a very similar approach to signal processing via wavelet transformation is used in the work of Farhadi et al [40]. They used a proven procedure of data processing, like other authors.…”

Motion-based visual inspection of optically indiscernible defects on the example of hazelnuts

“…Means of processing the audio data are diverse and range from Fast Fourier Transform (FFT), Principle Component Analysis (PCA) to Deep Learning models [23,24]. Examples of detection tasks include the discrimination of different genotypes of walnuts [23], classification of chestnuts according to their moisture level [20], detection of damaged rice [22] and wheat [25,26] kernels, distinguishing almonds according to their thickness and hardness [27], and the detection of damaged [28] and hollow hazelnuts [29]. Besides the application in sorting and grading of agricultural products, impact acoustic is also used in the field of recycling, for instance for the discrimination of different plastic materials from automotive shredder residues [21] and sorting of municipal solid waste [24].…”

The pistachio quality detection based on deep features plus unsupervised clustering

“…However, as an agricultural product with small particles, pistachios have a relatively weak collision sound signal that is more susceptible to environmental noise. In addition, factors such as collision height, angle, and block material can also affect the collision sound signal, negatively impacting pistachio quality detection (Farhadi et al, 2020).…”