Pankaj Tyagi, R. Semwal, Anju Sharma, U. Tiwary, P. Varadwaj
All fruits emit some specific volatile organic compounds (VOCs) during their life cycle. These VOCs have specific characteristics, by using these characteristics fruit ripening stage can be identified without destructing the fruit. In this study, an application-specific electronic nose device was designed for monitoring fruit ripeness.The proposed electronic nose is cost-efficient and does not require any modern or costly laboratory instruments. Metal oxide semiconductor (MOS) sensors were used for designing the proposed electronic nose. These MOS sensors were integrated with a microcontroller board to detect and extract the meaningful features of VOCs, and an artificial neural network (ANN) algorithm was used for pattern recognition. Measurements were done with apples, bananas, oranges, grapes, and pomegranates. The designed electronic nose proved to be reliable in classifying fruit samples into three different fruit ripening stage (unripe, ripe, and over-ripe) with high precision and recall. The proposed electronic nose performed uniformly on all three fruit ripening stages with an average accuracy of ≥ 95%.
{"title":"E-nose: A low-cost fruit ripeness monitoring system","authors":"Pankaj Tyagi, R. Semwal, Anju Sharma, U. Tiwary, P. Varadwaj","doi":"10.4081/jae.2022.1389","DOIUrl":"https://doi.org/10.4081/jae.2022.1389","url":null,"abstract":"All fruits emit some specific volatile organic compounds (VOCs) during their life cycle. These VOCs have specific characteristics, by using these characteristics fruit ripening stage can be identified without destructing the fruit. \u0000In this study, an application-specific electronic nose device was designed for monitoring fruit ripeness.The proposed electronic nose is cost-efficient and does not require any modern or costly laboratory instruments. Metal oxide semiconductor (MOS) sensors were used for designing the proposed electronic nose. These MOS sensors were integrated with a microcontroller board to detect and extract the meaningful features of VOCs, and an artificial neural network (ANN) algorithm was used for pattern recognition. Measurements were done with apples, bananas, oranges, grapes, and pomegranates. The designed electronic nose proved to be reliable in classifying fruit samples into three different fruit ripening stage (unripe, ripe, and over-ripe) with high precision and recall. The proposed electronic nose performed uniformly on all three fruit ripening stages with an average accuracy of ≥ 95%.","PeriodicalId":48507,"journal":{"name":"Journal of Agricultural Engineering","volume":"34 1 1","pages":""},"PeriodicalIF":1.8,"publicationDate":"2022-11-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"81171829","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}
Albert Min, N. Nguyễn, L.M. Howatt, Marlowe Tavares, Jaho Seo
Controlled Environment Agriculture (CEA) holds promise as a way to intensify current agricultural production systems while limiting pressures on land, water, and energy resources. However, its use has not yet been widely adopted, in part because the engineering design considerations and associated challenges are not well known. This is even more apparent for aeroponics, where the additional cost and complexities in controlling atomization have yet to establish an advantage in scale over simpler hydroponic systems To shed light on these considerations and challenges, an instrumented aeroponic system was prototyped with the goal of creating a quantitative model of growth for various species of leafy greens. As the first consideration, pressure swirl atomizers were paired with a diaphragm-type pressure tank to supply the necessary pressures needed for effective atomization. Secondly, nutrient solution was mixed on-demand from Reverse Osmosis (RO) water and concentrated nutrient stock then pumped into the pressure tank using a positive displacement pump. A bamboo-based substrate that allowed both germination and extended vegetative growth was supported on a stainless steel mesh and PVC frame acting as a grow tray. Finally, a camera microservice platform was developed to quantify plant growth using a computer vision pixel-based segmentation method.
{"title":"Aeroponic systems design: considerations and challenges","authors":"Albert Min, N. Nguyễn, L.M. Howatt, Marlowe Tavares, Jaho Seo","doi":"10.4081/jae.2022.1387","DOIUrl":"https://doi.org/10.4081/jae.2022.1387","url":null,"abstract":"Controlled Environment Agriculture (CEA) holds promise as a way to intensify current agricultural production systems while limiting pressures on land, water, and energy resources. However, its use has not yet been widely adopted, in part because the engineering design considerations and associated challenges are not well known. This is even more apparent for aeroponics, where the additional cost and complexities in controlling atomization have yet to establish an advantage in scale over simpler hydroponic systems To shed light on these considerations and challenges, an instrumented aeroponic system was prototyped with the goal of creating a quantitative model of growth for various species of leafy greens. As the first consideration, pressure swirl atomizers were paired with a diaphragm-type pressure tank to supply the necessary pressures needed for effective atomization. Secondly, nutrient solution was mixed on-demand from Reverse Osmosis (RO) water and concentrated nutrient stock then pumped into the pressure tank using a positive displacement pump. A bamboo-based substrate that allowed both germination and extended vegetative growth was supported on a stainless steel mesh and PVC frame acting as a grow tray. Finally, a camera microservice platform was developed to quantify plant growth using a computer vision pixel-based segmentation method.","PeriodicalId":48507,"journal":{"name":"Journal of Agricultural Engineering","volume":"8 1","pages":""},"PeriodicalIF":1.8,"publicationDate":"2022-09-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"84175811","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}
Fan Cui, Guoqi Dong, B. Chen, Penglin Yong, S. Peng
How to detect grain moisture content storage inefficiently, non-destructively, and quickly is a critical task in the storage process of the modern grain industry. The influence of media with different moisture content on the propagation and attenuation of electromagnetic wave energy is the premise and basis for applying electromagnetic wave technology in detecting grain moisture content. To explore the applicability of electromagnetic wave technology in detecting grain moisture content, we used ground penetrating radar (GPR) technology and auto regressive and moving average (ARMA) power spectrum analysis method to detect and study the moisture content of the typical national grain depots and local grain depots. The results show that GPR technology could realize the moisture content of stored grains and solve the problems of detection distance, non-destructive, and detection dead ends. Compared with the actual test data, the correlation is above 90%, the error can be controlled within 0.5%, and the measurement accuracy is higher, within ±0.3%. The continuous distribution profile of stored grain moisture content was obtained using the ARMA method. The moisture content distribution range of the rice barn was 10-14%, showing the regularity of the moisture content distribution in the middle layer > upper-middle layer > lower-middle layer > bottom layer > grain surface layer. It indicates that the GPR technology has particular advantages in food safety detection and provides data support for real-time detection of food storage safety.
{"title":"Application of GPR technology in moisture content detection of stored grain","authors":"Fan Cui, Guoqi Dong, B. Chen, Penglin Yong, S. Peng","doi":"10.4081/jae.2022.1472","DOIUrl":"https://doi.org/10.4081/jae.2022.1472","url":null,"abstract":"How to detect grain moisture content storage inefficiently, non-destructively, and quickly is a critical task in the storage process of the modern grain industry. The influence of media with different moisture content on the propagation and attenuation of electromagnetic wave energy is the premise and basis for applying electromagnetic wave technology in detecting grain moisture content. To explore the applicability of electromagnetic wave technology in detecting grain moisture content, we used ground penetrating radar (GPR) technology and auto regressive and moving average (ARMA) power spectrum analysis method to detect and study the moisture content of the typical national grain depots and local grain depots. The results show that GPR technology could realize the moisture content of stored grains and solve the problems of detection distance, non-destructive, and detection dead ends. Compared with the actual test data, the correlation is above 90%, the error can be controlled within 0.5%, and the measurement accuracy is higher, within ±0.3%. The continuous distribution profile of stored grain moisture content was obtained using the ARMA method. The moisture content distribution range of the rice barn was 10-14%, showing the regularity of the moisture content distribution in the middle layer > upper-middle layer > lower-middle layer > bottom layer > grain surface layer. It indicates that the GPR technology has particular advantages in food safety detection and provides data support for real-time detection of food storage safety.","PeriodicalId":48507,"journal":{"name":"Journal of Agricultural Engineering","volume":"45 1","pages":""},"PeriodicalIF":1.8,"publicationDate":"2022-09-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"88901607","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}
In Italy the agricultural residues resulting from pruning of vineyards represent a potential energy resource, in particular for the Veneto region which is the second Italian region by vineyard area. This study is aimed at analyzing the main physical and chemical characteristics of vine shoots from the annual pruning of vineyards. This is for their possible use as wood chips in small-medium size power plants. International and European standards for the analysis of biofuels were used to determine the moisture content, heat value, ash content, micro and macro elemental and fibrous fraction (lignin, cellulose, hemicellulose and extractives). The samples were collected from three different vineyards in the Vicenza area. The varieties analyzed were Chardonnay, Glera and Merlot. For each variety, the three different components of vine shoots were compared: internode, node and pith, to investigate in which part of the vine shoot the greatest accumulation of metallic elements deriving from plant protection products occurs. The results show significant differences among the energy parameters of the three varieties and three vine shoot components. In particular, the pith shows low heat value and high ash content while the woody components are characterized by higher energy values. Analysis of the chemical elements showed a high content of Cu and Zn in the wood components, node and internode, causing the high ash content found. In particular, Cu content exceeds the limits set by the reference standard. As regards the analysis of the fibrous fraction, a high content of extractives was found in the pith. These extractives could be one of the explanations why the pith of the three varieties analyzed, especially in Chardonnay, have less lower heat value on dry basis (LHV0) values and high ash contents. On the contrary, the node and internode components have a higher content of cellulose, hemicellulose and lignin. Overall, the vine shoots analyzed have characteristics suitable for a possible energy use. However, due to the high ash and Cu content, according to EN ISO 17225-9:2021 standard these can only be used as wood chips for industrial purposes in large power plants.
在意大利，葡萄园修剪产生的农业残留物代表了一种潜在的能源资源，特别是对于葡萄园面积第二的意大利地区威尼托地区。本研究旨在分析葡萄园一年生修剪后的葡萄枝的主要理化特性。这是为了它们可能在中小型发电厂中用作木屑。生物燃料分析的国际和欧洲标准用于测定水分含量、热值、灰分含量、微观和宏观元素和纤维组分(木质素、纤维素、半纤维素和提取物)。这些样品是从维琴察地区三个不同的葡萄园采集的。分析的品种包括霞多丽、嘉莱拉和梅洛。对每个品种的藤茎的三个不同组成部分:节间、节和髓进行了比较，以研究藤茎的哪个部分最容易积累来自植保产品的金属元素。结果表明，3个品种的能量参数和3个藤茎成分之间存在显著差异。其中，髓质热值低，灰分含量高，而木质组分具有较高的能值。化学元素分析表明，木材成分、节段和节间中Cu和Zn含量高，导致灰分含量高。特别是铜的含量超过了参考标准规定的限值。关于纤维部分的分析，在髓中发现了高含量的提取物。这些提取物可以解释为什么所分析的三个品种，特别是霞多丽的髓具有较低的干基热值(LHV0)值和较高的灰分含量。相反，节段和节间组分的纤维素、半纤维素和木质素含量较高。总的来说，分析的藤芽具有适合可能的能源利用的特征。然而，由于灰分和铜含量高，根据EN ISO 17225- 9:21 21标准，这些只能用作大型发电厂工业用途的木屑。
{"title":"Analysis of the main physical and chemical characteristics of the vine shoots of three vine varieties from Veneto (Italy)","authors":"A. Mencarelli, R. Cavalli, R. Greco","doi":"10.4081/jae.2022.1396","DOIUrl":"https://doi.org/10.4081/jae.2022.1396","url":null,"abstract":"In Italy the agricultural residues resulting from pruning of vineyards represent a potential energy resource, in particular for the Veneto region which is the second Italian region by vineyard area. This study is aimed at analyzing the main physical and chemical characteristics of vine shoots from the annual pruning of vineyards. This is for their possible use as wood chips in small-medium size power plants. International and European standards for the analysis of biofuels were used to determine the moisture content, heat value, ash content, micro and macro elemental and fibrous fraction (lignin, cellulose, hemicellulose and extractives). The samples were collected from three different vineyards in the Vicenza area. The varieties analyzed were Chardonnay, Glera and Merlot. For each variety, the three different components of vine shoots were compared: internode, node and pith, to investigate in which part of the vine shoot the greatest accumulation of metallic elements deriving from plant protection products occurs. The results show significant differences among the energy parameters of the three varieties and three vine shoot components. In particular, the pith shows low heat value and high ash content while the woody components are characterized by higher energy values. Analysis of the chemical elements showed a high content of Cu and Zn in the wood components, node and internode, causing the high ash content found. In particular, Cu content exceeds the limits set by the reference standard. As regards the analysis of the fibrous fraction, a high content of extractives was found in the pith. These extractives could be one of the explanations why the pith of the three varieties analyzed, especially in Chardonnay, have less lower heat value on dry basis (LHV0) values and high ash contents. On the contrary, the node and internode components have a higher content of cellulose, hemicellulose and lignin. Overall, the vine shoots analyzed have characteristics suitable for a possible energy use. However, due to the high ash and Cu content, according to EN ISO 17225-9:2021 standard these can only be used as wood chips for industrial purposes in large power plants.","PeriodicalId":48507,"journal":{"name":"Journal of Agricultural Engineering","volume":"11 1","pages":""},"PeriodicalIF":1.8,"publicationDate":"2022-09-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"82089566","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}
A. N. Oyedeji, Umar Ali Umar, Laminu Shettima Kuburi, A. A. Edet, Y. Mukhtar
This study was aimed at developing and evaluating the performance of an oil palm fresh fruit bunch harvesting robot that will eliminate the possible risks associated with oil palm harvesting. The result of this study showed that the average height of oil palm trees in the study area was 5.531 m, which shows the unsuitability of the existing traditional methods in the harvesting process. This study also used a geared DC motor to develop an oil palm harvester, solving the stability issue encountered by previous researchers during the harvesting process without necessarily reducing the climbing speed by a wide margin. In addition, the use of geared DC motor help in the production of high torque for the climbing process, and due to this high torque, instability during the harvesting process was reduced.
{"title":"Development and performance evaluation of an oil palm harvesting robot for the elimination of ergonomic risks associated with oil palm harvesting","authors":"A. N. Oyedeji, Umar Ali Umar, Laminu Shettima Kuburi, A. A. Edet, Y. Mukhtar","doi":"10.4081/jae.2022.1388","DOIUrl":"https://doi.org/10.4081/jae.2022.1388","url":null,"abstract":"This study was aimed at developing and evaluating the performance of an oil palm fresh fruit bunch harvesting robot that will eliminate the possible risks associated with oil palm harvesting. The result of this study showed that the average height of oil palm trees in the study area was 5.531 m, which shows the unsuitability of the existing traditional methods in the harvesting process. This study also used a geared DC motor to develop an oil palm harvester, solving the stability issue encountered by previous researchers during the harvesting process without necessarily reducing the climbing speed by a wide margin. In addition, the use of geared DC motor help in the production of high torque for the climbing process, and due to this high torque, instability during the harvesting process was reduced.","PeriodicalId":48507,"journal":{"name":"Journal of Agricultural Engineering","volume":"33 1","pages":""},"PeriodicalIF":1.8,"publicationDate":"2022-09-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"76999762","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}
Maile Zhou, Jiajia Yang, Tingbo Xu, Jianjun Ying, Xinzhong Wang
This study aimed at the problems of unequal speed transmission ratio mutual restriction and side gap accumulation of the transplanting mechanism with single-degree-of-freedom K-H-V non-circular planetary gear train, which leads to poor trajectory and attitude, and poor precision of movement. This study has proposed a simple structure of transplanting mechanism with differential internal engagement non-circular planetary gear trains, which reconstructs the complex transplanting trajectory and attitude of the planting arm through single-stage unequal speed transmission. The working principle of the transplanting mechanism was analysed, and the kinematic theoretical model of the transplanting mechanism was established. The optimal design software for the transplanting mechanism was developed based on the visual platform. The dimensions optimisation on the transplanting mechanism was completed considering the requirements with strong coupling, and multi-objective and a set of superior mechanism parameters were obtained. The design theory and method of the internal engagement non-circular gear pair were proposed based on the generating principle. The correctness and accuracy of the trajectory and attitude of the transplanting mechanism were verified through virtual simulation experiments. The experiments show that the designed transplanting mechanism with internal engagement non-circular planetary gear trains was compact in structure, the trajectory meets the requirements of multi-objective transplanting, and the trajectory and attitude can be accurately reproduced, which provides a new feasible solution for the innovative design of the transplanting mechanism.
{"title":"Optimal design of transplanting mechanism with differential internal engagement non-circular gear trains","authors":"Maile Zhou, Jiajia Yang, Tingbo Xu, Jianjun Ying, Xinzhong Wang","doi":"10.4081/jae.2022.1412","DOIUrl":"https://doi.org/10.4081/jae.2022.1412","url":null,"abstract":"This study aimed at the problems of unequal speed transmission ratio mutual restriction and side gap accumulation of the transplanting mechanism with single-degree-of-freedom K-H-V non-circular planetary gear train, which leads to poor trajectory and attitude, and poor precision of movement. This study has proposed a simple structure of transplanting mechanism with differential internal engagement non-circular planetary gear trains, which reconstructs the complex transplanting trajectory and attitude of the planting arm through single-stage unequal speed transmission. The working principle of the transplanting mechanism was analysed, and the kinematic theoretical model of the transplanting mechanism was established. The optimal design software for the transplanting mechanism was developed based on the visual platform. The dimensions optimisation on the transplanting mechanism was completed considering the requirements with strong coupling, and multi-objective and a set of superior mechanism parameters were obtained. The design theory and method of the internal engagement non-circular gear pair were proposed based on the generating principle. The correctness and accuracy of the trajectory and attitude of the transplanting mechanism were verified through virtual simulation experiments. The experiments show that the designed transplanting mechanism with internal engagement non-circular planetary gear trains was compact in structure, the trajectory meets the requirements of multi-objective transplanting, and the trajectory and attitude can be accurately reproduced, which provides a new feasible solution for the innovative design of the transplanting mechanism.","PeriodicalId":48507,"journal":{"name":"Journal of Agricultural Engineering","volume":"16 1","pages":""},"PeriodicalIF":1.8,"publicationDate":"2022-09-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"80883347","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}
Fernando Ferreira Abreu, Luiz Henrique Antunes Rodrigues
Yield is the most often used metric of crop performance, and it can be defined as the ratio between production, expressed as a function of mass or volume, and the cultivated area. Estimating fruit’s volume often relies on manual measurements, and the procedure precision can change from one person to another. Measuring fruits’ mass will also destroy the samples; consequently, the variation will be measured with different samples. Monitoring fruit’s growth is either based on destructive tests, limited by human labour, or too expensive to be scaled. In this work, we showed that the cluster visible area could be used to describe the growth of mini tomatoes in a greenhouse using image processing in a natural environment with a complex background. The proposed method is based on deep learning algorithms and allows continuous monitoring with no contact with the cluster. The images are collected and delivered from the greenhouse using low-cost equipment with minimal parameterisation. Our results demonstrate that the cluster visible area accumulation is highly correlated (R²=0.97) with growth described by a parameterised Gompertz curve, which is a well-known growth function. This work may also be a starting point for alternative growth monitoring methods based on image segmentation. The proposed U-Net architecture, the discussion about its architecture, and the challenges of the natural environment may be used for other tasks in the agricultural context.
{"title":"Monitoring mini-tomatoes growth: A non-destructive machine vision-based alternative","authors":"Fernando Ferreira Abreu, Luiz Henrique Antunes Rodrigues","doi":"10.4081/jae.2022.1366","DOIUrl":"https://doi.org/10.4081/jae.2022.1366","url":null,"abstract":"Yield is the most often used metric of crop performance, and it can be defined as the ratio between production, expressed as a function of mass or volume, and the cultivated area. Estimating fruit’s volume often relies on manual measurements, and the procedure precision can change from one person to another. Measuring fruits’ mass will also destroy the samples; consequently, the variation will be measured with different samples. Monitoring fruit’s growth is either based on destructive tests, limited by human labour, or too expensive to be scaled. In this work, we showed that the cluster visible area could be used to describe the growth of mini tomatoes in a greenhouse using image processing in a natural environment with a complex background. The proposed method is based on deep learning algorithms and allows continuous monitoring with no contact with the cluster. The images are collected and delivered from the greenhouse using low-cost equipment with minimal parameterisation. Our results demonstrate that the cluster visible area accumulation is highly correlated (R²=0.97) with growth described by a parameterised Gompertz curve, which is a well-known growth function. This work may also be a starting point for alternative growth monitoring methods based on image segmentation. The proposed U-Net architecture, the discussion about its architecture, and the challenges of the natural environment may be used for other tasks in the agricultural context.","PeriodicalId":48507,"journal":{"name":"Journal of Agricultural Engineering","volume":"6 1","pages":""},"PeriodicalIF":1.8,"publicationDate":"2022-09-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"79725151","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}
Wenjun Wang, Sihao Zhang, Jingyu Li, P. Zhang, Yulong Chen
Twin-row ridge cultivation is widely used in soybean planting in northern China. In order to find the optimal parameters of soybean agronomy, the twin-row planter with subsoiling was designed. Field experiments were conducted to evaluate the effects of plant arrangements and cluster densities on soybean growth and grain yield under different tillage treatments. The experiment used a randomised complete block design consisting of 20 treatments in a 2×2×5 factorial arrangement. Two tillage treatments were inter-row subsoiling and no subsoiling. Each tillage treatment included the combination of plant arrangements (side-by-side arrangement and triangular arrangement) and cluster densities (one, two, three, four, and five plants). The variables measured included soil moisture content, seedling emergence, biomass accumulation and allocation, and grain yield. We have concluded that the performance of inter-row subsoiling treatment was much better than that of no subsoiling treatment. Meanwhile, the triangular arrangement and two plants per cluster were the best choices for soybean biomass accumulation and grain yield in northern China. This study provided a reference for the innovative design of the twin-row planter with subsoiling and the optimisation of soybean agronomy.
{"title":"Effects of the twin-row planter with subsoiling on soybean growth and yield in northern China","authors":"Wenjun Wang, Sihao Zhang, Jingyu Li, P. Zhang, Yulong Chen","doi":"10.4081/jae.2022.1359","DOIUrl":"https://doi.org/10.4081/jae.2022.1359","url":null,"abstract":"Twin-row ridge cultivation is widely used in soybean planting in northern China. In order to find the optimal parameters of soybean agronomy, the twin-row planter with subsoiling was designed. Field experiments were conducted to evaluate the effects of plant arrangements and cluster densities on soybean growth and grain yield under different tillage treatments. The experiment used a randomised complete block design consisting of 20 treatments in a 2×2×5 factorial arrangement. Two tillage treatments were inter-row subsoiling and no subsoiling. Each tillage treatment included the combination of plant arrangements (side-by-side arrangement and triangular arrangement) and cluster densities (one, two, three, four, and five plants). The variables measured included soil moisture content, seedling emergence, biomass accumulation and allocation, and grain yield. We have concluded that the performance of inter-row subsoiling treatment was much better than that of no subsoiling treatment. Meanwhile, the triangular arrangement and two plants per cluster were the best choices for soybean biomass accumulation and grain yield in northern China. This study provided a reference for the innovative design of the twin-row planter with subsoiling and the optimisation of soybean agronomy.","PeriodicalId":48507,"journal":{"name":"Journal of Agricultural Engineering","volume":"15 1","pages":""},"PeriodicalIF":1.8,"publicationDate":"2022-09-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"86584549","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}
In the process of precision planting of crops, due to many external environmental interference factors, low precision of sowing technology and large relative errors, the growth of crops is seriously affected. To solve this problem, machine vision technology is introduced to study the key technology of crop precision sowing based on vision principle. After preprocessing the crop image, the corresponding histogram is established. The segmentation threshold method is used to gray the image and determine the best threshold, so that the image has a good recognition effect. According to the growth height and color analysis of crops in the image, predict the growth of crops and realize the precision sowing of crops. The comparative experimental results show that under the application of the new sowing technology, the estimation accuracy of crop planting area is high, the recognition accuracy of planting position is also high, and the fertilization uniformity is close to the actual data, which can provide an important basis for improving the quality of crop sowing.
{"title":"Key technology of crop precision sowing based on vision principle","authors":"Bing-chuan Li, Jiyun Li","doi":"10.4081/jae.2022.1453","DOIUrl":"https://doi.org/10.4081/jae.2022.1453","url":null,"abstract":"In the process of precision planting of crops, due to many external environmental interference factors, low precision of sowing technology and large relative errors, the growth of crops is seriously affected. To solve this problem, machine vision technology is introduced to study the key technology of crop precision sowing based on vision principle. After preprocessing the crop image, the corresponding histogram is established. The segmentation threshold method is used to gray the image and determine the best threshold, so that the image has a good recognition effect. According to the growth height and color analysis of crops in the image, predict the growth of crops and realize the precision sowing of crops. The comparative experimental results show that under the application of the new sowing technology, the estimation accuracy of crop planting area is high, the recognition accuracy of planting position is also high, and the fertilization uniformity is close to the actual data, which can provide an important basis for improving the quality of crop sowing.","PeriodicalId":48507,"journal":{"name":"Journal of Agricultural Engineering","volume":"46 1","pages":""},"PeriodicalIF":1.8,"publicationDate":"2022-08-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"73424597","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}
Kai Tian, Jiefeng Zeng, Tianci Song, Zhuliu Li, Asenso Evans, Jiuhao Li
Tomato disease control remains a major challenge in the agriculture sector. Early stage recognition of these diseases is critical to reduce pesticide usage and mitigate economic losses. While many research works have been inspired by the success of deep learning in computer vision to improve the performance of recognition systems for crop diseases, few of these studies optimized the deep learning models to generalize their findings to practical use in the field. In this work, we proposed a model for identifying tomato leaf diseases based on both in-house data and public tomato leaf images databases. Three deep learning network architectures (VGG16, Inception_v3, and Resnet50) were trained and tested. We packaged the trained model into an Android application named TomatoGuard to identify nine kinds of tomato leaf diseases and healthy tomato leaf. The results showed that TomatoGuard could be adopted as a model for identifying tomato diseases with a 99% test accuracy, showing significantly better performance compared with APP Plantix, a widely used APP for general purpose plant disease detection.
{"title":"Tomato leaf diseases recognition based on deep convolutional neural networks","authors":"Kai Tian, Jiefeng Zeng, Tianci Song, Zhuliu Li, Asenso Evans, Jiuhao Li","doi":"10.4081/jae.2022.1432","DOIUrl":"https://doi.org/10.4081/jae.2022.1432","url":null,"abstract":"Tomato disease control remains a major challenge in the agriculture sector. Early stage recognition of these diseases is critical to reduce pesticide usage and mitigate economic losses. While many research works have been inspired by the success of deep learning in computer vision to improve the performance of recognition systems for crop diseases, few of these studies optimized the deep learning models to generalize their findings to practical use in the field. In this work, we proposed a model for identifying tomato leaf diseases based on both in-house data and public tomato leaf images databases. Three deep learning network architectures (VGG16, Inception_v3, and Resnet50) were trained and tested. We packaged the trained model into an Android application named TomatoGuard to identify nine kinds of tomato leaf diseases and healthy tomato leaf. The results showed that TomatoGuard could be adopted as a model for identifying tomato diseases with a 99% test accuracy, showing significantly better performance compared with APP Plantix, a widely used APP for general purpose plant disease detection.","PeriodicalId":48507,"journal":{"name":"Journal of Agricultural Engineering","volume":"9 1","pages":""},"PeriodicalIF":1.8,"publicationDate":"2022-08-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"90747176","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：