Pub Date : 2023-06-26DOI: 10.1590/1809-4430-eng.agric.v43n2e20210103/2023
D. K. Villa, E. C. Melo, J. V. Nicacio, T. Pizziolo
This study proposes automating an air conditioning system for drying and storing agricultural products. The main objective is to precisely control key parameters of the air, namely temperature, relative humidity, and air velocity, to optimize the drying process. The framework required for constructing and operating the automated air conditioner is explained in detail. Specifically, we describe the conditioning unit, the automation hardware, the control strategies employed to regulate temperature, relative humidity, and air velocity, and discuss the safety measures and human-machine interfaces of the system. Experimental validation of the proposed system is presented, along with results and discussions demonstrating its successful control of drying air parameters across a wide range of desired conditions.
{"title":"AUTOMATED AIR CONDITIONING SYSTEM FOR AGRICULTURAL PRODUCT DRYING AND STORAGE","authors":"D. K. Villa, E. C. Melo, J. V. Nicacio, T. Pizziolo","doi":"10.1590/1809-4430-eng.agric.v43n2e20210103/2023","DOIUrl":"https://doi.org/10.1590/1809-4430-eng.agric.v43n2e20210103/2023","url":null,"abstract":"This study proposes automating an air conditioning system for drying and storing agricultural products. The main objective is to precisely control key parameters of the air, namely temperature, relative humidity, and air velocity, to optimize the drying process. The framework required for constructing and operating the automated air conditioner is explained in detail. Specifically, we describe the conditioning unit, the automation hardware, the control strategies employed to regulate temperature, relative humidity, and air velocity, and discuss the safety measures and human-machine interfaces of the system. Experimental validation of the proposed system is presented, along with results and discussions demonstrating its successful control of drying air parameters across a wide range of desired conditions.","PeriodicalId":49078,"journal":{"name":"Engenharia Agricola","volume":null,"pages":null},"PeriodicalIF":1.0,"publicationDate":"2023-06-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"67257325","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"农林科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2023-06-26DOI: 10.1590/1809-4430-eng.agric.v43n2e20220127/2023
Yi-mei Yuan, Jiayi Wang, Xin Zhang, Shu-kai Zhao
The issue of reducing tillage resistance and lowering energy consumption has become increasingly relevant. Strip tillage has a positive impact on soil protection and energy consumption reduction. This study analysed the tillage resistance components of rotary blades and their relationship with operating parameters and developed a mathematical relationship between tillage resistance and energy consumption (power and fuel consumption). We summarised tillage resistance into three parts: air resistance, lateral rotational friction resistance (divided into horizontal and vertical resistance), and shear force. By theoretical analysis and coupled simulation tests 11 (DEM-CFD), we obtained an air resistance, lateral rotational friction, and shear force of 0.0883 N, 97.21 N, and 893.496 N, respectively, accounting for 0.01%, 9.81%, and 90.18% of tillage resistance. Meanwhile, we found that horizontal resistance decreased linearly with the increase of angular speed, which was the opposite of vertical resistance. Horizontal and vertical resistance increased linearly with the increase in contact area. Shear force increased significantly with angular speed. Fuel consumption in the field test and tillage resistance and power consumption in coupled simulation was formed to build a correspondence point, and a mathematical relationship between tillage resistance, torque, and power and fuel consumption was established.
{"title":"STUDY ON TILLAGE RESISTANCE AND ENERGY CONSUMPTION OF A PLAIN STRAIGHT ROTARY BLADE FOR STRIP TILLAGE","authors":"Yi-mei Yuan, Jiayi Wang, Xin Zhang, Shu-kai Zhao","doi":"10.1590/1809-4430-eng.agric.v43n2e20220127/2023","DOIUrl":"https://doi.org/10.1590/1809-4430-eng.agric.v43n2e20220127/2023","url":null,"abstract":"The issue of reducing tillage resistance and lowering energy consumption has become increasingly relevant. Strip tillage has a positive impact on soil protection and energy consumption reduction. This study analysed the tillage resistance components of rotary blades and their relationship with operating parameters and developed a mathematical relationship between tillage resistance and energy consumption (power and fuel consumption). We summarised tillage resistance into three parts: air resistance, lateral rotational friction resistance (divided into horizontal and vertical resistance), and shear force. By theoretical analysis and coupled simulation tests 11 (DEM-CFD), we obtained an air resistance, lateral rotational friction, and shear force of 0.0883 N, 97.21 N, and 893.496 N, respectively, accounting for 0.01%, 9.81%, and 90.18% of tillage resistance. Meanwhile, we found that horizontal resistance decreased linearly with the increase of angular speed, which was the opposite of vertical resistance. Horizontal and vertical resistance increased linearly with the increase in contact area. Shear force increased significantly with angular speed. Fuel consumption in the field test and tillage resistance and power consumption in coupled simulation was formed to build a correspondence point, and a mathematical relationship between tillage resistance, torque, and power and fuel consumption was established.","PeriodicalId":49078,"journal":{"name":"Engenharia Agricola","volume":null,"pages":null},"PeriodicalIF":1.0,"publicationDate":"2023-06-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"67257195","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"农林科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2023-06-19DOI: 10.1590/1809-4430-eng.agric.v43n2e20220198/2023
Daniele F. Filippini, Alfredo Petrauski, S. M. C. Petrauski, Eduardo P. dos Santos, R. Jordan
Materials from renewable sources have been increasingly used in construction to assist in sustainable development. Therefore, the use of timber becomes an environmentally advantageous solution, especially if used for long-term purposes, such as in structures. In this sense, this study aimed to evaluate the performance of glued-laminated timber frames reinforced in their main connections. The structures were made using timber from the Araucaria angustifolia species and polyurethane adhesive based on vegetable oils. The frames, on a reduced scale, had a pillar height and free span of 2 m and were reinforced in the connections between the roof beams and pillars. The rupture strength values of the structures averaged 38.02 kN, approximately 5.47 times the design load, and represented a 32% increase in strength compared to non-reinforced structures. The displacements
{"title":"FABRICATION AND TESTING OF GLUED-LAMINATED TIMBER FRAMES WITH REINFORCED CONNECTIONS","authors":"Daniele F. Filippini, Alfredo Petrauski, S. M. C. Petrauski, Eduardo P. dos Santos, R. Jordan","doi":"10.1590/1809-4430-eng.agric.v43n2e20220198/2023","DOIUrl":"https://doi.org/10.1590/1809-4430-eng.agric.v43n2e20220198/2023","url":null,"abstract":"Materials from renewable sources have been increasingly used in construction to assist in sustainable development. Therefore, the use of timber becomes an environmentally advantageous solution, especially if used for long-term purposes, such as in structures. In this sense, this study aimed to evaluate the performance of glued-laminated timber frames reinforced in their main connections. The structures were made using timber from the Araucaria angustifolia species and polyurethane adhesive based on vegetable oils. The frames, on a reduced scale, had a pillar height and free span of 2 m and were reinforced in the connections between the roof beams and pillars. The rupture strength values of the structures averaged 38.02 kN, approximately 5.47 times the design load, and represented a 32% increase in strength compared to non-reinforced structures. The displacements","PeriodicalId":49078,"journal":{"name":"Engenharia Agricola","volume":null,"pages":null},"PeriodicalIF":1.0,"publicationDate":"2023-06-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"67257649","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"农林科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2023-06-02DOI: 10.1590/1809-4430-eng.agric.v43n2e20220014/2023
Min-Suk Jin, Bowen Yang, Chunguang Wang
To address the problem of the low accuracy and poor robustness of modeling methods for imbalanced data sets of pig behavior identification and classification, the three commonly used re-sampling methods of under-sampling, SMOTE and Borderline-SMOTE are compared, and an adaptive boundary data augmentation algorithm AD-BL-SMOTE is proposed. The activity of the pigs was measured using triaxial accelerometers, which were fixed on the backs of the pigs. A multilayer feed-forward neural network was trained and validated with 21 input features to classify four pig activities: lying, standing, walking, and exploring. The results showed that re-sampling methods are an effective way to improve the performance of pig behavior identification and classification. Moreover, AD-BL-SMOTE could yield greater improvements in classification performance than the other three methods for balancing the training data set. The overall major mean accuracy of lying, standing, walking, and exploring by pigs A, B
{"title":"RESEARCH ON IDENTIFICATION AND CLASSIFICATION METHOD OF IMBALANCED DATA SET OF PIG BEHAVIOR","authors":"Min-Suk Jin, Bowen Yang, Chunguang Wang","doi":"10.1590/1809-4430-eng.agric.v43n2e20220014/2023","DOIUrl":"https://doi.org/10.1590/1809-4430-eng.agric.v43n2e20220014/2023","url":null,"abstract":"To address the problem of the low accuracy and poor robustness of modeling methods for imbalanced data sets of pig behavior identification and classification, the three commonly used re-sampling methods of under-sampling, SMOTE and Borderline-SMOTE are compared, and an adaptive boundary data augmentation algorithm AD-BL-SMOTE is proposed. The activity of the pigs was measured using triaxial accelerometers, which were fixed on the backs of the pigs. A multilayer feed-forward neural network was trained and validated with 21 input features to classify four pig activities: lying, standing, walking, and exploring. The results showed that re-sampling methods are an effective way to improve the performance of pig behavior identification and classification. Moreover, AD-BL-SMOTE could yield greater improvements in classification performance than the other three methods for balancing the training data set. The overall major mean accuracy of lying, standing, walking, and exploring by pigs A, B","PeriodicalId":49078,"journal":{"name":"Engenharia Agricola","volume":null,"pages":null},"PeriodicalIF":1.0,"publicationDate":"2023-06-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"67257090","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"农林科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2023-06-01DOI: 10.1590/1809-4430-eng.agric.v43n2e20220138/2023
Erica de F. Cabral, O. Resende, D. C. D. Oliveira, Lílian M. Costa, Jonathas L. R. dos Santos
Sorghum ( Sorghum bicolor L. Moench) is a crop of paramount importance for Brazil, used in human and animal food. Considering the reduced number of studies on the influence of using a densimetric table in seed processing and its respective reprocessing to the equipment, this study aimed to evaluate the physiological quality of processed sorghum seeds reprocessed in a densimetric table and stored for three months. The treatments consisted of four collection points in the terminal part of the densimetric table, representing the processing material: upper part (P1), upper middle part (P2), middle part (P3), and lower part (D). Subsequently, the
{"title":"PHYSIOLOGICAL QUALITY OF PROCESSED, REPROCESSED, AND STORED SORGHUM SEEDS: IMPACT OF A DENSIMETRIC TABLE","authors":"Erica de F. Cabral, O. Resende, D. C. D. Oliveira, Lílian M. Costa, Jonathas L. R. dos Santos","doi":"10.1590/1809-4430-eng.agric.v43n2e20220138/2023","DOIUrl":"https://doi.org/10.1590/1809-4430-eng.agric.v43n2e20220138/2023","url":null,"abstract":"Sorghum ( Sorghum bicolor L. Moench) is a crop of paramount importance for Brazil, used in human and animal food. Considering the reduced number of studies on the influence of using a densimetric table in seed processing and its respective reprocessing to the equipment, this study aimed to evaluate the physiological quality of processed sorghum seeds reprocessed in a densimetric table and stored for three months. The treatments consisted of four collection points in the terminal part of the densimetric table, representing the processing material: upper part (P1), upper middle part (P2), middle part (P3), and lower part (D). Subsequently, the","PeriodicalId":49078,"journal":{"name":"Engenharia Agricola","volume":null,"pages":null},"PeriodicalIF":1.0,"publicationDate":"2023-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"67257373","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"农林科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2023-05-08DOI: 10.1590/1809-4430-eng.agric.v43n2e20220193/2023
Ruan Bernardy, G. I. Gadotti, R. D. C. M. Monteiro, Karine Von Ahn Pinto, R. D. Pinheiro
To enhance speed and agility in interpreting physiological quality tests of seeds, The use of algorithms has emerged. This study aimed to identify suitable machine learning models to assist in the precise management of seed lot quality. Soybean lots from two companies were assessed using the Supplied Test Set, Cross-Validation (with 8, 10, and 12 folds), and Percentage Split (with 66% and 70%) methods. Variables analyzed through Tetrazolium tests included vigor, viability, mechanical damage, moisture damage, bed bug damage, and water content. Method performance was determined by Kappa, Precision, and ROC Area metrics. Classification Via Regression and J48 algorithms were employed. The technique utilizing 66% of data for training achieved 93.55% accuracy, with Precision and ROC Area reaching
{"title":"FITTING Data Mining Settings for Ranking Seed Lots","authors":"Ruan Bernardy, G. I. Gadotti, R. D. C. M. Monteiro, Karine Von Ahn Pinto, R. D. Pinheiro","doi":"10.1590/1809-4430-eng.agric.v43n2e20220193/2023","DOIUrl":"https://doi.org/10.1590/1809-4430-eng.agric.v43n2e20220193/2023","url":null,"abstract":"To enhance speed and agility in interpreting physiological quality tests of seeds, The use of algorithms has emerged. This study aimed to identify suitable machine learning models to assist in the precise management of seed lot quality. Soybean lots from two companies were assessed using the Supplied Test Set, Cross-Validation (with 8, 10, and 12 folds), and Percentage Split (with 66% and 70%) methods. Variables analyzed through Tetrazolium tests included vigor, viability, mechanical damage, moisture damage, bed bug damage, and water content. Method performance was determined by Kappa, Precision, and ROC Area metrics. Classification Via Regression and J48 algorithms were employed. The technique utilizing 66% of data for training achieved 93.55% accuracy, with Precision and ROC Area reaching","PeriodicalId":49078,"journal":{"name":"Engenharia Agricola","volume":null,"pages":null},"PeriodicalIF":1.0,"publicationDate":"2023-05-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"67257051","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"农林科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2023-05-08DOI: 10.1590/1809-4430-eng.agric.v43n2e20220195/2023
Han Jiangyi, W. Fan
An electric orchard tractor with a power battery and transmission driven by dual motors was developed. The output shafts of the walking and power take-off (PTO) motors are connected by a wet clutch, which controls whether the two motors are coupled or independent. When the load of the walking or PTO motor exceeds its output torque, the two motors are driven by power coupled by the wet clutch to meet the power demand. According to the heavy-load working conditions of ploughing and rototilling, the power battery capacity and working duration targets of 15 kW and 4 hours/charge were set. A prototype 15 kW electric orchard tractor was manufactured and assembled, and its performance was assessed. A bench test showed that the tractor’s maximum PTO output power was 13.9 kW and a field rototilling test showed that its maximum continuous working time was 4.5 hours. Thus, the prototype electric orchard tractor met the design goals and requirements of for orchard operations.
{"title":"DESIGN AND TESTING OF A SMALL ORCHARD TRACTOR DRIVEN BY A POWER BATTERY","authors":"Han Jiangyi, W. Fan","doi":"10.1590/1809-4430-eng.agric.v43n2e20220195/2023","DOIUrl":"https://doi.org/10.1590/1809-4430-eng.agric.v43n2e20220195/2023","url":null,"abstract":"An electric orchard tractor with a power battery and transmission driven by dual motors was developed. The output shafts of the walking and power take-off (PTO) motors are connected by a wet clutch, which controls whether the two motors are coupled or independent. When the load of the walking or PTO motor exceeds its output torque, the two motors are driven by power coupled by the wet clutch to meet the power demand. According to the heavy-load working conditions of ploughing and rototilling, the power battery capacity and working duration targets of 15 kW and 4 hours/charge were set. A prototype 15 kW electric orchard tractor was manufactured and assembled, and its performance was assessed. A bench test showed that the tractor’s maximum PTO output power was 13.9 kW and a field rototilling test showed that its maximum continuous working time was 4.5 hours. Thus, the prototype electric orchard tractor met the design goals and requirements of for orchard operations.","PeriodicalId":49078,"journal":{"name":"Engenharia Agricola","volume":null,"pages":null},"PeriodicalIF":1.0,"publicationDate":"2023-05-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"67257630","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"农林科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2023-05-01DOI: 10.1590/1809-4430-eng.agric.v43n2e20230068/2023
M. M. Baesso, Luisa Leveghin, Edson Sardinha, G. P. D. C. N. Oliveira, R. Sousa
,
{"title":"DEEP LEARNING-BASED MODEL FOR CLASSIFICATION OF BEAN NITROGEN STATUS USING DIGITAL CANOPY IMAGING","authors":"M. M. Baesso, Luisa Leveghin, Edson Sardinha, G. P. D. C. N. Oliveira, R. Sousa","doi":"10.1590/1809-4430-eng.agric.v43n2e20230068/2023","DOIUrl":"https://doi.org/10.1590/1809-4430-eng.agric.v43n2e20230068/2023","url":null,"abstract":",","PeriodicalId":49078,"journal":{"name":"Engenharia Agricola","volume":null,"pages":null},"PeriodicalIF":1.0,"publicationDate":"2023-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"67257798","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"农林科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2023-04-21DOI: 10.1590/1809-4430-eng.agric.v43n2e20210238/2023
Guomin Gao, Hui Guo, Wei Zhou, Dan Luo, J. Zhang
This paper discusses the design of a safflower picking robot control system and focuses on a navigation control subsystem based on multisensor fusion. A navigation subsystem, an identification and positioning subsystem, a picking subsystem, and a levelling subsystem are designed. The hardware and software of the navigation subsystem are designed in detail, and a multisensor fusion positioning method based on extended Kalman fusion technology is proposed. The accuracy and stability levels of different combined navigation methods are compared. To test the effectiveness and accuracy of the proposed method, an outdoor test is carried out. The test results show that the outdoor fusion positioning accuracy of the robot is less than 8 cm, and when the satellite signal is lost, the navigation control subsystem can still provide high positioning accuracy. The final positioning result obtained using the integrated positioning method of the
{"title":"DESIGN OF A CONTROL SYSTEM FOR A SAFFLOWER PICKING ROBOT AND RESEARCH ON MULTISENSOR FUSION POSITIONING","authors":"Guomin Gao, Hui Guo, Wei Zhou, Dan Luo, J. Zhang","doi":"10.1590/1809-4430-eng.agric.v43n2e20210238/2023","DOIUrl":"https://doi.org/10.1590/1809-4430-eng.agric.v43n2e20210238/2023","url":null,"abstract":"This paper discusses the design of a safflower picking robot control system and focuses on a navigation control subsystem based on multisensor fusion. A navigation subsystem, an identification and positioning subsystem, a picking subsystem, and a levelling subsystem are designed. The hardware and software of the navigation subsystem are designed in detail, and a multisensor fusion positioning method based on extended Kalman fusion technology is proposed. The accuracy and stability levels of different combined navigation methods are compared. To test the effectiveness and accuracy of the proposed method, an outdoor test is carried out. The test results show that the outdoor fusion positioning accuracy of the robot is less than 8 cm, and when the satellite signal is lost, the navigation control subsystem can still provide high positioning accuracy. The final positioning result obtained using the integrated positioning method of the","PeriodicalId":49078,"journal":{"name":"Engenharia Agricola","volume":null,"pages":null},"PeriodicalIF":1.0,"publicationDate":"2023-04-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"67257359","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"农林科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2023-04-21DOI: 10.1590/1809-4430-eng.agric.v43n2e20220180/2023
Y. Chen, Lulu Zheng, Hongxing Peng
In China, low levels of accuracy in predicting when pineapple crops will reach maturity can result from environmental variation such as light changes, fruit overlap, and shading. Therefore, this study proposed the use of an improved RetinaNet algorithm (ECA-Retinanet) based on the ECA attention mechanism. The ECA attention mechanism was embedded into the classification subnet of RetinaNet to improve accuracy in detecting different levels of maturity in pineapples. A new pineapple dataset was collected comprising four different growth stages under mild and severe complex scenarios. The experimental results have shown that the mAP (Mean Average Precision) and F 1 score (Balanced Score) of the ECA-Retinanet model were 97.69%, 94.75%, 93.2%, and 90% for identification in mild and severe complex scenarios. These values are 0.42%, 2%, 1.78%, and 1.5% higher than the original RetinaNet model which exceeds those of the six existing state-of-the-art detection models. The results have indicated that the proposed algorithm could be used for accurate identification of pineapple fruit and can detect fruit maturity using ground color images in the natural environment. The study findings provide a technical reference for automatic picking robots and early yield estimation.
{"title":"ASSESSING PINEAPPLE MATURITY IN COMPLEX SCENARIOS USING AN IMPROVED RETINANET ALGORITHM","authors":"Y. Chen, Lulu Zheng, Hongxing Peng","doi":"10.1590/1809-4430-eng.agric.v43n2e20220180/2023","DOIUrl":"https://doi.org/10.1590/1809-4430-eng.agric.v43n2e20220180/2023","url":null,"abstract":"In China, low levels of accuracy in predicting when pineapple crops will reach maturity can result from environmental variation such as light changes, fruit overlap, and shading. Therefore, this study proposed the use of an improved RetinaNet algorithm (ECA-Retinanet) based on the ECA attention mechanism. The ECA attention mechanism was embedded into the classification subnet of RetinaNet to improve accuracy in detecting different levels of maturity in pineapples. A new pineapple dataset was collected comprising four different growth stages under mild and severe complex scenarios. The experimental results have shown that the mAP (Mean Average Precision) and F 1 score (Balanced Score) of the ECA-Retinanet model were 97.69%, 94.75%, 93.2%, and 90% for identification in mild and severe complex scenarios. These values are 0.42%, 2%, 1.78%, and 1.5% higher than the original RetinaNet model which exceeds those of the six existing state-of-the-art detection models. The results have indicated that the proposed algorithm could be used for accurate identification of pineapple fruit and can detect fruit maturity using ground color images in the natural environment. The study findings provide a technical reference for automatic picking robots and early yield estimation.","PeriodicalId":49078,"journal":{"name":"Engenharia Agricola","volume":null,"pages":null},"PeriodicalIF":1.0,"publicationDate":"2023-04-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"67257036","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"农林科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：