Filters
Three-Dimensional Convolutional Neural Networks (3D-CNN) in the Classification of Varieties and Quality Assessment of Soybean Seeds (Glycine max L. Merill)
The precise identification, classification, sorting, and rapid and accurate quality assessment of soybean seeds are extremely important in terms of the continuity of agricultural production, varietal purity, seed processing, protein extraction, and food safety. Currently, commonly used methods for the identification and quality assessment of soybean seeds include morphological analysis, chemical analysis, protein electrophoresis, liquid chromatography, spectral analysis, and image analysis. The use of image analysis and artificial intelligence is the aim of the presented research, in which a method for the automatic classification of soybean varieties, the assessment of the degree of damage, and the identification of geometric features of soybean seeds based on numerical models obtained using a 3D scanner has been proposed. Unlike traditional two-dimensional images, which only represent height and width, 3D imaging adds a third dimension, allowing for a more realistic representation of the shape of the seeds. The research was conducted on soybean seeds with a moisture content of 13%, and the seeds were stored in a room with a temperature of 20–23 °C and air humidity of 60%. Individual soybean seeds were scanned to create 3D models, allowing for the measurement of their geometric parameters, assessment of texture, evaluation of damage, and identification of characteristic varietal features. The developed 3D-CNN network model comprised an architecture consisting of an input layer, three hidden layers, and one output layer with a single neuron. The aim of the conducted research is to design a new, three-dimensional 3D-CNN architecture, the main task of which is the classification of soybean seeds. For the purposes of network analysis and testing, 22 input criteria were defined, with a hierarchy of their importance. The training, testing, and validation database of the SB3D-NET network consisted of 3D models obtained as a result of scanning individual soybean seeds, 100 for each variety. The accuracy of the training process of the proposed SB3D-NET model for the qualitative classification of 3D models of soybean seeds, based on the adopted criteria, was 95.54%, and the accuracy of its validation was 90.74%. The relative loss value during the training process of the SB3D-NET model was 18.53%, and during its validation process, it was 37.76%. The proposed SB3D-NET neural network model for all twenty-two criteria achieves values of global error (GE) of prediction and classification of seeds at the level of 0.0992.
Evaluation of the Quality and Possible Use of a New Generation of Agricultural Nets for Packing Bulk Materials in Terms of the Aspect of Reducing the Environmental Burden
In modern agriculture, packaging materials are becoming an important means of production in the technologies for harvesting bulk materials. The agricultural net currently used for this purpose is usually made of HDPE—high-density polyethylene. The aim of the study was to evaluate the agricultural net produced in light technology under the commercial name of Covernet. Based on the tests conducted for nine variants of different models of round balers and different bulk materials collected by them, it can be concluded that, in each case, the net (Tama LT) wrapped the cylindrical bales well or very well. The mean elongation of COVERNET during bale wrapping was over 8% for the tested machines and harvested materials. The tests confirmed the usefulness of the new generation of agricultural nets (Tama LT) for wrapping various agricultural bulk materials of various humidities. There is an urgent need to develop and implement in practice a technology for recovering used agricultural nets and converting them into granules that can be used again in their production.
Development and application of a model for the automatic evaluation and classification of onions (Allium cepa L.) using a Deep Neural Network (DNN)
Evaluation of the Operating Parameters of Self-Propelled Forage Harvesters During Maize Silage Harvest
Abstract This study aims to determine and evaluate the operating parameters of three modern self-propelled forage harvesters during maize silage harvest. The machines were equipped with operator assistance systems. Field tests were conducted for three self-propelled forage harvesters: Claas Jaguar 870, Claas Jaguar 950, KroneBiG X 650. The tests were conducted in large-scale farms located in Wielkopolskie and Pomorskie voivodeships. Maize was harvested at the beginning of the full-grain maturity stage. A complete time study covering four control shifts in accordance with BN-76/9195-01 was performed to determine operating ratios and indicators. Fuel consumption was determined using the full tank method. The Claas Jaguar 950 forage harvester had the highest effective mass performance: 141.3 Mg·h-1. The same machine also achieved the lowest fuel consumption per tonne of fresh matter (FM) harvested: 0.51 kg·Mg-1. Labour expenditure for the self-propelled forage harvesters tested during the total time of change ranged from 0.38 to 0.62 labour hour per hectare. The tested machines also had very high technical and technological reliability.
