University of Tehran PressIranian Journal of Biosystem Engineering2008-480356220250823Feasibility of using electronic nose and artificial intelligence to identify wheat varietiesFeasibility of using electronic nose and artificial intelligence to identify wheat varieties11210376710.22059/ijbse.2025.389976.665587FANahidAghili NateghDepartment of Agricultural Machinery Engineering, Sonqor Faculty of Agriculture, Razi University, Kermanshah, IranRashidGholamiDepartment of Agricultural Machinery Engineering, Sonqor Faculty of Agriculture, Razi University, Kermanshah, Iran.SanazSadriyanDepartment of Biosystem Mechanical Engineering, Faculty of Agriculture, Bu-Ali Sina University, Hamedan, Iran..Journal Article20250206Wheat is an important grain product that constitutes about 20% of the calories consumed by the human population around the world. Due to the strong dependence of wheat growth and yield on its variety, the choosing the right variety for cultivation in different soil and water conditions is very important. In this research, the feasibility of using an e-nose system along with artificial intelligence based on metal oxide semiconductor sensors (MOS) as a non-destructive tool for the separation and identification of three varieties of wheat with the names: Salari dry wheat, Quds blue wheat and local red wheat is evaluated. Support vector machine (SVM), artificial neural network (ANN) and principal component analysis (PCA) were the methods used to achieve this goal. The obtained results showed that TGS822 and TGS2620 sensors play the most role and TGS813 and TGS2610 sensors play the least role in wheat variety detection. ANN analysis method with 91.7% accuracy showed better result than SVM method (75% accuracy) in identifying and classifying wheat varieties. In the meantime, the PCA method showed a relatively good performance in separating and identifying wheat varieties with 77% of the total variance of the total data. Also, the results showed that wheat of Salari dry wheat variety had different aromatic compounds with other two varieties of Quds blue wheat and local red wheat. The proper performance of the e-nose in the separation of wheat varieties can indicate the promising application of this technology in the separation and identification of wheat varieties.Wheat is an important grain product that constitutes about 20% of the calories consumed by the human population around the world. Due to the strong dependence of wheat growth and yield on its variety, the choosing the right variety for cultivation in different soil and water conditions is very important. In this research, the feasibility of using an e-nose system along with artificial intelligence based on metal oxide semiconductor sensors (MOS) as a non-destructive tool for the separation and identification of three varieties of wheat with the names: Salari dry wheat, Quds blue wheat and local red wheat is evaluated. Support vector machine (SVM), artificial neural network (ANN) and principal component analysis (PCA) were the methods used to achieve this goal. The obtained results showed that TGS822 and TGS2620 sensors play the most role and TGS813 and TGS2610 sensors play the least role in wheat variety detection. ANN analysis method with 91.7% accuracy showed better result than SVM method (75% accuracy) in identifying and classifying wheat varieties. In the meantime, the PCA method showed a relatively good performance in separating and identifying wheat varieties with 77% of the total variance of the total data. Also, the results showed that wheat of Salari dry wheat variety had different aromatic compounds with other two varieties of Quds blue wheat and local red wheat. The proper performance of the e-nose in the separation of wheat varieties can indicate the promising application of this technology in the separation and identification of wheat varieties.https://ijbse.ut.ac.ir/article_103767_7101345b0d55159426dc041d68240c50.pdfUniversity of Tehran PressIranian Journal of Biosystem Engineering2008-480356220250823Investigating energy consumption and economic indicators of rose production using machine learning: A case study of Damghan CountyInvestigating energy consumption and economic indicators of rose production using machine learning: A case study of Damghan County133010376810.22059/ijbse.2025.393681.665595FASeyed OmidDavodalmosaviDepartment of Agricultural Machinery Mechanical Engineering, Faculty of Agriculture and Natural Resources, University of Tehran, Karaj, IranFarzanehBahadoriAssociate Professor, Agricultural Research and Education Center, Semnan Province, Agricultural Research, Education and Extension Organization, Semnan, IranShahinRafieeDepartment of Agricultural Machinery Mechanical Engineering, Faculty of Agriculture and Natural Resources, University of Tehran, Karaj, IranJournal Article20250423This study aimed to analyze the energy and economic aspects of rose production in Damghan County and model the optimal use of inputs using machine learning algorithms. The required data were collected through questionnaires and interviews. The results showed that the total energy consumed in rose production was 43,438 megajoules per hectare, with electricity accounting for 79.6 percent of the energy consumption. The energy efficiency index was 0.02 kg/megajoule, which indicates a significant energy loss in the production system. On the other hand, the economic analysis indicated a net profit of 44.395 million tomans per hectare and a benefit-to-cost ratio of 2.07, which indicates the appropriate economic justification for rose production despite high energy consumption. Gradient Booster (GBR), Enhanced Gradient Booster (XGBR), and Random Forest (RFR) algorithms were used to model and predict energy consumption and costs. The results showed that the GBR model with a coefficient of determination (R2) of 0.99 and a minimum error of 251.97 has the best performance in predicting energy and costs. Also, sensitivity analysis using the SHAP method revealed that animal manure and electricity have the greatest impact on energy consumption, while water management and chemical fertilizers play a key role in economic profitability. The results showed that optimizing energy consumption in rose production is possible by reducing electricity and fertilizer consumption, and the use of machine learning is also suggested as an efficient tool in predicting and managing agricultural inputs.This study aimed to analyze the energy and economic aspects of rose production in Damghan County and model the optimal use of inputs using machine learning algorithms. The required data were collected through questionnaires and interviews. The results showed that the total energy consumed in rose production was 43,438 megajoules per hectare, with electricity accounting for 79.6 percent of the energy consumption. The energy efficiency index was 0.02 kg/megajoule, which indicates a significant energy loss in the production system. On the other hand, the economic analysis indicated a net profit of 44.395 million tomans per hectare and a benefit-to-cost ratio of 2.07, which indicates the appropriate economic justification for rose production despite high energy consumption. Gradient Booster (GBR), Enhanced Gradient Booster (XGBR), and Random Forest (RFR) algorithms were used to model and predict energy consumption and costs. The results showed that the GBR model with a coefficient of determination (R2) of 0.99 and a minimum error of 251.97 has the best performance in predicting energy and costs. Also, sensitivity analysis using the SHAP method revealed that animal manure and electricity have the greatest impact on energy consumption, while water management and chemical fertilizers play a key role in economic profitability. The results showed that optimizing energy consumption in rose production is possible by reducing electricity and fertilizer consumption, and the use of machine learning is also suggested as an efficient tool in predicting and managing agricultural inputs.https://ijbse.ut.ac.ir/article_103768_7288731dfc2ae82c12e76480fe625545.pdfUniversity of Tehran PressIranian Journal of Biosystem Engineering2008-480356220250823Environmental Assessment of Olive Production in Traditional and Semi-Mechanized Scenarios Using Life Cycle AssessmentEnvironmental Assessment of Olive Production in Traditional and Semi-Mechanized Scenarios Using Life Cycle Assessment315010376910.22059/ijbse.2025.395620.665596FABehnamMohammadiDepartment of Plant Production and Genetics, Faculty of Agriculture, University of Zanjan, Zanjan, Iran.MajidNamdariDepartment of Plant Production and Genetics, Faculty of Agriculture, University of Zanjan, Zanjan, Iran.AlirezaYousefiDepartment of Plant Production and Genetics, Faculty of Agriculture, University of Zanjan, Zanjan, Iran.Journal Article20250519In recent years, Iran's olive sector has experienced significant changes in agricultural practices. The cultivation of olive orchards is transitioning from traditional systems towards semi-mechanized approaches. This research aimed to evaluate the environmental impacts of olive production in both traditional and semi-mechanized systems in the Tarom region of Zanjan Province, using the Life Cycle Assessment (LCA) methodology. The necessary data were collected through questionnaires completed by 50 olive growers and interviews with agricultural managers. The system boundary was defined from cradle-to-farm-gate, and the functional unit was considered as one tonne of olives. The results indicated that the semi-mechanized system demonstrated better environmental performance compared to the traditional system, with a 31% reduction in global warming potential (from 1286.11 to 888.66 kg CO2 eq.), a 23% reduction in energy consumption (from 14399.73 to 11094.61 MJ), and a 38% reduction in human toxicity (from 553.40 to 344.54 kg 1,4-DB eq.). Input contribution analysis revealed that electricity (58 to 74 percent) and chemical fertilizers (15 to 20 percent) had the most significant impact on the environmental burden. However, diesel fuel consumption in the semi-mechanized system, due to partial mechanization, led to a 20% increase in ozone layer depletion. This study suggests that improving irrigation efficiency and managing fertilizer consumption can enhance the environmental sustainability of olive production in both systems.In recent years, Iran's olive sector has experienced significant changes in agricultural practices. The cultivation of olive orchards is transitioning from traditional systems towards semi-mechanized approaches. This research aimed to evaluate the environmental impacts of olive production in both traditional and semi-mechanized systems in the Tarom region of Zanjan Province, using the Life Cycle Assessment (LCA) methodology. The necessary data were collected through questionnaires completed by 50 olive growers and interviews with agricultural managers. The system boundary was defined from cradle-to-farm-gate, and the functional unit was considered as one tonne of olives. The results indicated that the semi-mechanized system demonstrated better environmental performance compared to the traditional system, with a 31% reduction in global warming potential (from 1286.11 to 888.66 kg CO2 eq.), a 23% reduction in energy consumption (from 14399.73 to 11094.61 MJ), and a 38% reduction in human toxicity (from 553.40 to 344.54 kg 1,4-DB eq.). Input contribution analysis revealed that electricity (58 to 74 percent) and chemical fertilizers (15 to 20 percent) had the most significant impact on the environmental burden. However, diesel fuel consumption in the semi-mechanized system, due to partial mechanization, led to a 20% increase in ozone layer depletion. This study suggests that improving irrigation efficiency and managing fertilizer consumption can enhance the environmental sustainability of olive production in both systems.https://ijbse.ut.ac.ir/article_103769_695e317c253847d0446472b625392030.pdfUniversity of Tehran PressIranian Journal of Biosystem Engineering2008-480356220250823Identifying and classifying cow types based on spinal end deviation using machine learningIdentifying and classifying cow types based on spinal end deviation using machine learning516710394110.22059/ijbse.2025.398902.665603FAMohsenDaneshman VaziriResearcher, Agricultural Engineering Research Department, Isfahan Agricultural and Natural Resources Research and Education Center, AREEO, Isfahan, Iran..AbdollahImanmehrAssistant professor, Agricultural Engineering Research Department, Isfahan Agricultural and Natural Resources Research and Education Center, AREEO, Isfahan, Iran.MohsenHeidarisoltanabadiAssociated professor, Agricultural Engineering Research Department, Isfahan Agricultural and Natural Resources Research and Education Center, AREEO, Isfahan, Iran.Journal Article20250719In dairy farms, machine learning operations can be used to identify and classify cow types based on body condition scoring (BCS) using features extracted from images. In particular, machine learning algorithms can analyze the curvature of the spine, often by identifying key points and fitting a line or curve, to distinguish between different breeds of cattle and assess their condition. In this study, machine learning models that have been frequently used in computer science in recent years, including SVM, KNN, and CNN, were used in conjunction with a pre-trained deep learning network Resnet50 to enhance the success of the architectures. In each of the algorithms, image features were extracted, registered, and merged to identify the type of cows, and finally, the pre-trained CNN algorithm based on deep learning was able to correctly identify the type of cow with the highest accuracy (93 percent). Therefore, by combining this processing system with the imaging mechanism, it is possible to identify and classify cows based on various states and physical characteristics in cattle environments in a shorter, simpler, and more user-friendly time. This approach eliminates the need for manual extraction of livestock features, reduces the use of human resources, and achieves improved recognition accuracy.In dairy farms, machine learning operations can be used to identify and classify cow types based on body condition scoring (BCS) using features extracted from images. In particular, machine learning algorithms can analyze the curvature of the spine, often by identifying key points and fitting a line or curve, to distinguish between different breeds of cattle and assess their condition. In this study, machine learning models that have been frequently used in computer science in recent years, including SVM, KNN, and CNN, were used in conjunction with a pre-trained deep learning network Resnet50 to enhance the success of the architectures. In each of the algorithms, image features were extracted, registered, and merged to identify the type of cows, and finally, the pre-trained CNN algorithm based on deep learning was able to correctly identify the type of cow with the highest accuracy (93 percent). Therefore, by combining this processing system with the imaging mechanism, it is possible to identify and classify cows based on various states and physical characteristics in cattle environments in a shorter, simpler, and more user-friendly time. This approach eliminates the need for manual extraction of livestock features, reduces the use of human resources, and achieves improved recognition accuracy.https://ijbse.ut.ac.ir/article_103941_36fbd34f7d00dc2f69a33ba2354e4015.pdfUniversity of Tehran PressIranian Journal of Biosystem Engineering2008-480356220250823Economic-Environmental Assessment of Hazelnut Production in Guilan Province: Material Flow Cost Accounting (MFCA)Economic-Environmental Assessment of Hazelnut Production in Guilan Province: Material Flow Cost Accounting (MFCA)698910401110.22059/ijbse.2025.398197.665601FAHosseinRezaeiDepartment of (Water and) Soil Science, Faculty of Agriculture, Malayer University, Malayer, IranMajidDekaminDepartment of Plant Production and Genetics, Faculty of Agriculture, Malayer University, Malayer, IranAshkanNabavi-PelesaraeiDepartment of Environmental and Resource Engineering, Technical University of Denmark, 2800 Kongens Lyngby, DenmarkJournal Article20250708This study evaluates the economic and environmental performance of hazelnut production in Guilan Province using the Material Flow Cost Accounting (MFCA) method. The research compares traditional cost accounting (TCA) with MFCA, emphasizing that MFCA offers a more comprehensive assessment by considering the economic value of negative environmental outputs. The main product yield was 450 kg ha-1 of hazelnuts. However, negative outputs included ammonia (NH₃) and nitrous oxide (N₂O) emissions, water pollution caused by nitrate and phosphate runoff, and the release of pesticides into the soil, water, and air. Additionally, 22 kg ha-1 of hazelnuts were lost due to inefficiencies in the production process. The total cost of input resources was estimated at 242 $ ha-1, while the net income from hazelnut sales was 3341 $ ha-1. The cost of negative outputs, including emissions, runoff, and product loss, was calculated at 207 $ ha-1. Under the MFCA method, which incorporates these negative outputs into the calculations, the gross value of production (GVP) reached 3583 $ ha-1, compared to 3376 $ ha-1 under TCA, highlighting MFCA’s ability to reflect a more accurate economic value of production. Similarly, gross returns (GR) and the benefit-cost ratio (BCR) were higher under MFCA, primarily due to accounting for the 207 $ value of negative products. The results indicate that MFCA is an effective tool for identifying and reducing resource waste and increasing profitability, while simultaneously enhancing economic productivity and environmental sustainability in hazelnut production.This study evaluates the economic and environmental performance of hazelnut production in Guilan Province using the Material Flow Cost Accounting (MFCA) method. The research compares traditional cost accounting (TCA) with MFCA, emphasizing that MFCA offers a more comprehensive assessment by considering the economic value of negative environmental outputs. The main product yield was 450 kg ha-1 of hazelnuts. However, negative outputs included ammonia (NH₃) and nitrous oxide (N₂O) emissions, water pollution caused by nitrate and phosphate runoff, and the release of pesticides into the soil, water, and air. Additionally, 22 kg ha-1 of hazelnuts were lost due to inefficiencies in the production process. The total cost of input resources was estimated at 242 $ ha-1, while the net income from hazelnut sales was 3341 $ ha-1. The cost of negative outputs, including emissions, runoff, and product loss, was calculated at 207 $ ha-1. Under the MFCA method, which incorporates these negative outputs into the calculations, the gross value of production (GVP) reached 3583 $ ha-1, compared to 3376 $ ha-1 under TCA, highlighting MFCA’s ability to reflect a more accurate economic value of production. Similarly, gross returns (GR) and the benefit-cost ratio (BCR) were higher under MFCA, primarily due to accounting for the 207 $ value of negative products. The results indicate that MFCA is an effective tool for identifying and reducing resource waste and increasing profitability, while simultaneously enhancing economic productivity and environmental sustainability in hazelnut production.https://ijbse.ut.ac.ir/article_104011_da580b3cf72638f63f83e663dbd336d4.pdfUniversity of Tehran PressIranian Journal of Biosystem Engineering2008-480356220250823Development and Evaluation of an Intelligent Machine Vision System for Detecting Chicken Gizzard Adulteration in Minced Red MeatDevelopment and Evaluation of an Intelligent Machine Vision System for Detecting Chicken Gizzard Adulteration in Minced Red Meat9010510406510.22059/ijbse.2025.398182.665600FAMobinRezazadehMechanical Engineering of Biosystems Department, Faculty of Agriculture, Shahrekord University, Shahrekord, I.R.Iran0009-0008-7102-6060SajadKianiBiosystems Engineering Department,, Sari Agricultural Sciences and Natural Resources University, Sari, IranMahdiGhasemi VarnamkhastiMechanical Engineering of Biosystems Department, Faculty of Agriculture, Shahrekord
University, Shahrekord,ZahraIzadiMechanical Engineering of Biosystems Department, Faculty of Agriculture, Shahrekord
University, Shahrekord, I.R. Iran.Journal Article20250708In this study, an intelligent machine-vision system was developed and evaluated for detecting chicken gizzard adulteration in ground red mutton-veal meat, using digital images captured by a mobile phone. To this end, standard samples of minced red meat (55% mutton and 45% beef) with varying proportions of chicken gizzard (0 to 100%) were prepared, and images were captured in a laboratory environment both directly from the sample surface and through plastic wrap packaging. The color features (RGB) of the images were extracted using the MATLAB image processing toolbox, and modeling was performed employing statistical and machine learning methods, including Principal Component Analysis (PCA), Partial Least Squares Regression (PLSR), and Multilayer Perceptron (MLP) neural networks. The best performance of the linear PLSR model for estimating the adulteration percentage yielded an R²V=0.7 and RMSEV=16.51 under conditions without plastic wrap, whereas the nonlinear MLP model achieved an R²V=0.97 and RMSEV=6.673. These results were lower (0.9 and 12.54) for the data acquisition through plastic wrap due to the light reflections caused by the covering. Furthermore, the MLP classifier achieved classification accuracies of 85%, 96.4%, 92.6%, 73.7%, 76.2%, and 96.7% for adulteration levels 0-10%, 10–20%, 20–30%, 30–40%, 40–50%, and above 50%, respectively. The average precision, sensitivity, and F1 score for the developed model were obtained as 0.975, 0.974, and 0.975, respectively. The results showed that this non-destructive method is both fast and reliable for identifying gizzard fraud in ground meat, and can serve as a basis for developing meat quality control systems.In this study, an intelligent machine-vision system was developed and evaluated for detecting chicken gizzard adulteration in ground red mutton-veal meat, using digital images captured by a mobile phone. To this end, standard samples of minced red meat (55% mutton and 45% beef) with varying proportions of chicken gizzard (0 to 100%) were prepared, and images were captured in a laboratory environment both directly from the sample surface and through plastic wrap packaging. The color features (RGB) of the images were extracted using the MATLAB image processing toolbox, and modeling was performed employing statistical and machine learning methods, including Principal Component Analysis (PCA), Partial Least Squares Regression (PLSR), and Multilayer Perceptron (MLP) neural networks. The best performance of the linear PLSR model for estimating the adulteration percentage yielded an R²V=0.7 and RMSEV=16.51 under conditions without plastic wrap, whereas the nonlinear MLP model achieved an R²V=0.97 and RMSEV=6.673. These results were lower (0.9 and 12.54) for the data acquisition through plastic wrap due to the light reflections caused by the covering. Furthermore, the MLP classifier achieved classification accuracies of 85%, 96.4%, 92.6%, 73.7%, 76.2%, and 96.7% for adulteration levels 0-10%, 10–20%, 20–30%, 30–40%, 40–50%, and above 50%, respectively. The average precision, sensitivity, and F1 score for the developed model were obtained as 0.975, 0.974, and 0.975, respectively. The results showed that this non-destructive method is both fast and reliable for identifying gizzard fraud in ground meat, and can serve as a basis for developing meat quality control systems.https://ijbse.ut.ac.ir/article_104065_4cc27673cfc99671a54483f3d6d36cb9.pdf