Classification of Dried Strawberry by the Analysis of the Acoustic Sound with Artificial Neural Networks

Abstract

In this paper, the authors used an acoustic wave acting as a disturbance (acoustic vibration), which travelled in all directions on the whole surface of a dried strawberry fruit in its specified area. The area of space in which the acoustic wave occurs is defined as the acoustic field. When the vibrating surface—for example, the surface of the belt—becomes the source, then one can observe the travelling of surface waves. For any shape of the surface of the dried strawberry fruit, the signal of travelling waves takes the form that is imposed by this irregular surface. The aim of this work was to research the effectiveness of recognizing the two trials in the process of convection drying on the basis of the acoustic signal backed up by neural networks. The input variables determined descriptors such as frequency (Hz) and the level of luminosity (dB). During the research, the degree of crispiness relative to the degree of maturity was compared. The results showed that the optimal neural model in respect of the lowest value of the root mean square turned out to be the Multi-Layer Perceptron network with the technique of dropping single fruits into water (data included in the learning data set Z2). The results confirm that the choice of method can have an influence on the effectives of recognizing dried strawberry fruits, and also this can be a basis for creating an effective and fast analysis tool which is capable of analyzing the degree of ripeness of fruits including their crispness in the industrial process of drying fruits.

The Use of Image Analysis to Detect Seed Contamination—A Case Study of Triticale

“…As a result of the progress made in the research area concentrating on classification issues [ 26 , 30 , 40 ] with Artificial Neural Networks (ANN, quality changes were observed in relation to farm and food products, which are dictated by consumer expectations [ 26 , 34 ]. This method is based on neural models supported by computer analysis of images, which is faster and more efficient in comparison to the traditional calculating methods.…”

“…Next, the training sets were imported into Statistica. Each training set represented a set of the aforementioned descriptors and was divided into training, validation and test subsets at a 2:1:1 ratio [ 30 ]. The subsets were not used in the creation of artificial neural networks.…”

“…Recently, artificial neural networks (ANN) have been used to classify [ 26 ], analyze data [ 27 ], predict [ 28 , 29 , 30 ], control [ 31 ] and assess the quality of biomaterials [ 32 , 33 ]. What is an important practical feature of ANN is the fact that trained neural models work online.…”

“…The principle of operation of the unidirectional network is based on training, which uses a backpropagation algorithm. This means that the method enables the selection of modulating variables (weights) so that the data error (i.e., Root Mean Square Error) is as low as possible [ 30 ]. The set of modulating variables enables the acquisition of information from other neurons.…”

“…The weights determine the values of the matched data by connecting nodes between individual neurons. The activation function for hidden neurons is non-linear (sigmoidal) [ 30 , 37 , 38 ].…”