Greenhouse planting is a key method for increasing the yield of agricultural products in China.The Academy of Agricultural Sciences has conducted extensive research on the water requirements of greenhouse crops during...Greenhouse planting is a key method for increasing the yield of agricultural products in China.The Academy of Agricultural Sciences has conducted extensive research on the water requirements of greenhouse crops during various growth stages.Studies indicate that crops in the germination stage,seedling stage,and other stages of their growth cycle have different water needs.Proper irrigation can significantly enhance both crop quality and yield.To apply the Academy of Agricultural Sciences’expertise on irrigation during different growth stages to practical farming,and to avoid improper irrigation at specific stages that could reduce crop production and quality,our team has designed an intelligent irrigation system for agricultural greenhouses.This system adapts to the growth patterns of crops by establishing an irrigation model based on characteristic images of each growth stage and irrigation data provided by the Academy.Using image recognition technology,the system accurately identifies the growth stage of crops.It then employs a pre-set irrigation curve and data from humidity sensors to execute precise irrigation through a closed-loop Proportion-Integral-Differential(PID)control system.This ensures optimal water management,leading to improved crop quality and yield.展开更多
Dynamic acquisition of crop morphology is beneficial to real-time variable decision of precise spraying operations in fields.However,the existing spraying quantity regulation has high tolerance on the statistical char...Dynamic acquisition of crop morphology is beneficial to real-time variable decision of precise spraying operations in fields.However,the existing spraying quantity regulation has high tolerance on the statistical characteristics of regional morphology,so expensive LiDAR and ultrasonic radar can’t make full use of their high accuracy,and can reduce decision speed because of too much detail of branches and leaves.Therefore,designing a novel recognition system embedded machine learning with low-cost monocular vision is more feasible,especially in China,where the agricultural implements are medium sizes and cost-sensitive.In addition,we found that the growth period of crops is an important reference index for guiding spraying.So,taking cotton as a case study,a cotton morphology acquisition by a single camera is established,and a cotton growth period recognition algorithm based on Convolution Neural Network(CNN)is proposed in this paper.Through the optimization process based on confusion matrix and recognition efficiency,an optimized CNN model structure is determined from 9 different model structures,and its reliability was verified by changing training sets and test sets many times based on the idea of kfold test.The accuracy,precision,recall,F1-score and recognition speed of this CNN model are 93.27%,95.39%,94.31%,94.76%and 71.46 ms per image,respectively.In addition,compared with the performance of VGG16 and AlexNet,the convolution neural network model proposed in this paper has better performance.Finally,in order to verify the reliability of the designed recognition system and the feasibility of the spray decision-making algorithm based on CNN,spraying deposition experiments were carried out with 3 different growthperiods of cotton.The experiments’results validate that after the optimal spray parameters were applied at different growth periods respectively,the average optimum index in 3 growth periods was 42.29%,which was increased up to 62.24%than the operations without distinguishing growth periods.展开更多
The founding conference of the Big Data Statistics Branch (BDSB) of the Chinese Association forApplied Statistics (CAAS) was held on 8 December 2018, at East China Normal University (ECNU),Shanghai, China. More than 6...The founding conference of the Big Data Statistics Branch (BDSB) of the Chinese Association forApplied Statistics (CAAS) was held on 8 December 2018, at East China Normal University (ECNU),Shanghai, China. More than 600 experts and scholars attended the conference. Professor ZhangRiquan was elected as the chairman of the first Board of Directors of the BDSB. Fang Xiangzhong,Chairman of the CAAS, delivered a speech. Professor Wang Zhaojun and Dr Liu Zhong delivered,respectively, keynote reports on the development of Big Data researches and practices, at theconference. The BDSB will be dedicated to building a high-level big data statistics exchange platform for experts and scholars in universities, governments, enterprises, and other fields to betterserve the society and serve the country’s major strategies.展开更多
Co-sponsored by East China Normal University(ECNU)and the Chinese Association for Applied Statistics(CAAS),the BDMS-2019 workshop was jointly hosted and organised by School of Statistics at ECNU,the Journal Statistica...Co-sponsored by East China Normal University(ECNU)and the Chinese Association for Applied Statistics(CAAS),the BDMS-2019 workshop was jointly hosted and organised by School of Statistics at ECNU,the Journal Statistical Theory and Related Fields(STARF),the Key Laboratory of Advanced Theory and Application in Statistics and Data ScienceMOE(KLATASDS-MOE),and the Big Data Statistics Branch of CAAS.展开更多
文摘Greenhouse planting is a key method for increasing the yield of agricultural products in China.The Academy of Agricultural Sciences has conducted extensive research on the water requirements of greenhouse crops during various growth stages.Studies indicate that crops in the germination stage,seedling stage,and other stages of their growth cycle have different water needs.Proper irrigation can significantly enhance both crop quality and yield.To apply the Academy of Agricultural Sciences’expertise on irrigation during different growth stages to practical farming,and to avoid improper irrigation at specific stages that could reduce crop production and quality,our team has designed an intelligent irrigation system for agricultural greenhouses.This system adapts to the growth patterns of crops by establishing an irrigation model based on characteristic images of each growth stage and irrigation data provided by the Academy.Using image recognition technology,the system accurately identifies the growth stage of crops.It then employs a pre-set irrigation curve and data from humidity sensors to execute precise irrigation through a closed-loop Proportion-Integral-Differential(PID)control system.This ensures optimal water management,leading to improved crop quality and yield.
基金supported by National Natural Science Foundation of China(51475278)China Shandong Province Agricultural Machinery Equipment Research and Development Innovation Project(2018YF002)+2 种基金China Natural Science Foundation of Shandong Province(ZR2019PC024)China Scientific Research and Development Projects of Universities in Shandong Province(J18KA128)China and the Funds of Shandong‘Double Tops’Program(SYL2017XTTD14),China.
文摘Dynamic acquisition of crop morphology is beneficial to real-time variable decision of precise spraying operations in fields.However,the existing spraying quantity regulation has high tolerance on the statistical characteristics of regional morphology,so expensive LiDAR and ultrasonic radar can’t make full use of their high accuracy,and can reduce decision speed because of too much detail of branches and leaves.Therefore,designing a novel recognition system embedded machine learning with low-cost monocular vision is more feasible,especially in China,where the agricultural implements are medium sizes and cost-sensitive.In addition,we found that the growth period of crops is an important reference index for guiding spraying.So,taking cotton as a case study,a cotton morphology acquisition by a single camera is established,and a cotton growth period recognition algorithm based on Convolution Neural Network(CNN)is proposed in this paper.Through the optimization process based on confusion matrix and recognition efficiency,an optimized CNN model structure is determined from 9 different model structures,and its reliability was verified by changing training sets and test sets many times based on the idea of kfold test.The accuracy,precision,recall,F1-score and recognition speed of this CNN model are 93.27%,95.39%,94.31%,94.76%and 71.46 ms per image,respectively.In addition,compared with the performance of VGG16 and AlexNet,the convolution neural network model proposed in this paper has better performance.Finally,in order to verify the reliability of the designed recognition system and the feasibility of the spray decision-making algorithm based on CNN,spraying deposition experiments were carried out with 3 different growthperiods of cotton.The experiments’results validate that after the optimal spray parameters were applied at different growth periods respectively,the average optimum index in 3 growth periods was 42.29%,which was increased up to 62.24%than the operations without distinguishing growth periods.
文摘The founding conference of the Big Data Statistics Branch (BDSB) of the Chinese Association forApplied Statistics (CAAS) was held on 8 December 2018, at East China Normal University (ECNU),Shanghai, China. More than 600 experts and scholars attended the conference. Professor ZhangRiquan was elected as the chairman of the first Board of Directors of the BDSB. Fang Xiangzhong,Chairman of the CAAS, delivered a speech. Professor Wang Zhaojun and Dr Liu Zhong delivered,respectively, keynote reports on the development of Big Data researches and practices, at theconference. The BDSB will be dedicated to building a high-level big data statistics exchange platform for experts and scholars in universities, governments, enterprises, and other fields to betterserve the society and serve the country’s major strategies.
文摘Co-sponsored by East China Normal University(ECNU)and the Chinese Association for Applied Statistics(CAAS),the BDMS-2019 workshop was jointly hosted and organised by School of Statistics at ECNU,the Journal Statistical Theory and Related Fields(STARF),the Key Laboratory of Advanced Theory and Application in Statistics and Data ScienceMOE(KLATASDS-MOE),and the Big Data Statistics Branch of CAAS.
