Classification of Varieties of Grain Species by Artificial Neural Networks

Artificial neural network approach for predicting the sesame (Sesamum indicum L.) leaf area: A non-destructive and accurate method

The estimative of the leaf area using a nondestructive method is paramount for successive evaluations in the same plant with precision and speed, not requiring high-cost equipment. Thus, the objective of this work was to construct models to estimate leaf area using artificial neural network models (ANN) and regression and to compare which model is the most effective model for predicting leaf area in sesame culture. A total of 11,000 leaves of four sesame cultivars were collected. Then, the length (L) and leaf width (W), and the actual leaf area (LA) were quantified. For the ANN model, the parameters of the length and width of the leaf were used as input variables of the network, with hidden layers and leaf area as the desired output parameter. For the linear regression models, leaf dimensions were considered independent variables, and the actual leaf area was the dependent variable. The criteria for choosing the best models were: the lowest root of the mean squared error (RMSE), mean absolute error (MAE), and absolute mean percentage error (MAPE), and higher coefficients of determination (R²). Among the linear regression models, the equation yˆ=0.515+0.584*LW was considered the most indicated to estimate the leaf area of the sesame. In modeling with ANNs, the best results were found for model 2-3-1, with two input variables (L and W), three hidden variables, and an output variable (LA). The ANN model was more accurate than the regression models, recording the lowest errors and higher R² in the training phase (RMSE: 0.0040; MAE: 0.0027; MAPE: 0.0587; and R²: 0.9834) and in the test phase (RMSE: 0.0106; MAE: 0.0029; MAPE: 0.0611; and R²: 0.9828). Thus, the ANN method is the most indicated and accurate for predicting the leaf area of the sesame.

Significance of different milling methods on white proso millet flour physicochemical, rheological, and baking properties

Proso millet is a nutritious, sustainable, and gluten free food which is currently underutilized. They can be incorporated into the grain industry and provide much needed healthy alternatives. Efficient grinding method should be adopted for easy incorporation. This study aimed to investigate the effect of three different methods of grinding namely, roller milling (RM), pin milling (PM), and hammer milling (HM) on proso millet flour rheology and baking properties for food application. The milling flow sheet was developed toward the production of the quality whole grain flour. The particle size distribution of all the flours showed bi-modal distribution except for the RM flour. The PM produced the flour with the finest particles with geometric mean diameter of 82 μm. The study also revealed that starch damage in the PM flour (4.64%) was higher than RM (2.46%) and HM flour (2.51%). The nutritional composition was not significantly affected by different grinding methods. Pasting properties of the flour were also affected by the grinding method applied. Rapid Visco Analysis profile showed pin mill flour to have a higher peak viscosity (PV) (2,295 cP) compared to HM (2,065 cP) and RM flour (2,130 cP). Finally, this study demonstrated that the production of bread from proso millet flour with desirable quality and texture is possible. The grinding method did not affect the specific volume of bread loaves and C-cell characteristics. The specific volume of the breads ranged from 2.40 to 2.52 cm³ /g. This study will help in promoting and producing value-added proso millet food products with enhanced nutritional quality.

Texture analysis and artificial neural networks for identification of cereals-case study: wheat, barley and rape seeds

The scope of the research comprises an analysis and evaluation of samples of rape, barley and wheat seeds. The experiments were carried out using the author's original research object. The air flow velocities to transport seeds, were set at 15, 20 and 25 m s-1. A database consisting of images was created, which allowed to determine 3 classes of kernels on the basis of 6 research variants, including their transportation way via pipe and the speed of sowing. The process of creating neural models was based on multilayer perceptron networks (MLPN) in Statistica (machine learning). It should be added that the use of MLPN also allowed identification of rape seeds, wheat seeds and barley seeds transported via pipe II at 20 m s-1, for which the lowest RMS was 0.05 and the coefficient of classification accuracy was 0.94.

Valorization of poultry slaughterhouse waste for fertilizer purposes as an alternative for thermal utilization methods

Slaughterhouse waste and dead animals are mainly disposed of by incineration, which generates greenhouse gases and NO_x. These wastes are a source of nutrients that can be recovered by circular economy techniques if material recycling is given a priority over energy recovery. To valorize high-protein animal waste (containing bones, meat, feather) for fertilizer purposes, the waste was processed by acid solubilization and neutralized with potassium hydroxide solution, which yielded a liquid fertilizer with plant growth biostimulating properties (due to the amino acids presence). The composition analysis showed that new fertilizers met all quality requirements set by the law, contain ~0.5% m/m amino acids and are microbiologically pure. The fertilizer was enriched with microelements to the level of 0.2% m/m and tested for biological effectiveness in germination tests and field studies. Compared with the commercial formulation, the fertilizer increased stem length and chlorophyll content (by 8.2% and 27.0%, respectively), wheat crop yield and grain micronutrients density (Cu by 31.2%, Mn by 10.5%, Zn by 33.9%) and improved the wheat flour baking properties. The described solution propose a safe way to utilize hazardous waste via technological mobile installation, enabling no transportation of waste, which is an important aspect of sanitary-epidemiological risk minimization.

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

Samples of triticale seeds of various qualities were assessed in the study. The seeds were obtained during experiments, reflecting the actual sowing conditions. The experiments were conducted on an original test facility designed by the authors of this study. The speed of the air (15, 20, 25 m/s) transporting seeds in the pneumatic conduit was adjusted to sowing. The resulting graphic database enabled the distinction of six classes of seeds according to their quality and sowing speed. The database was prepared to build training, validation and test sets. The neural model generation process was based on multi-layer perceptron networks (MLPN) and statistical (machine training). When the MLPN was used to identify contaminants in seeds sown at a speed of 15 m/s, the lowest RMS error of 0.052 was noted, whereas the classification correctness coefficient amounted to 0.99.

Objective grading of eye muscle area, intramuscular fat and marbling in Australian beef and lamb

The objective of this study was to test the performance of a prototype vision system in phenotypically diverse beef and lamb carcasses against visual grading of eye muscle area (EMA), marbling and chemical intramuscular fat (IMF%). Validation in beef demonstrated that the camera prototype in combination with analytical techniques enabled prediction of EMA (r² = 0.83, RMSEP = 6.4 cm²), MSA marbling (r² = 0.76, RMSEP = 66.1), AUS-MEAT marbling (r² = 0.70, RMSEP = 0.74) and chemical IMF% (r² = 0.78, RMSEP = 1.85%). Accuracy was also maintained on validation with all four traits displaying minimal bias of -3.6, 6.3, 0.07 and - 0.01, for EMA, MSA marbling, AUS-MEAT marbling and IMF% respectively. Preliminary analysis in lamb indicates potential of the system for the prediction of EMA (r² = 0.41, RMSEP = 1.87) and IMF% (r² = 0.28, RMSEP = 1.10), however further work to standardise image acquisition and environmental conditions is required.