Weeds are mainly spread by weed seeds being mixed with agricultural and forestry crop seeds,grain,animal hair,and other plant products,and disturb the growing environment of target plants such as crops and wild native...Weeds are mainly spread by weed seeds being mixed with agricultural and forestry crop seeds,grain,animal hair,and other plant products,and disturb the growing environment of target plants such as crops and wild native plants.The accurate and efficient classification of weed seeds is important for the effective management and control of weeds.However,classification remains mainly dependent on destructive sampling-based manual inspection,which has a high cost and rather low flux.We considered that this problem could be solved using a nondestructive intelligent image recognition method.First,on the basis of the establishment of the image acquisition system for weed seeds,images of single weed seeds were rapidly and completely segmented,and a total of 47696 samples of 140 species of weed seeds and foreign materials remained.Then,six popular and novel deep Convolutional Neural Network(CNN)models are compared to identify the best method for intelligently identifying 140 species of weed seeds.Of these samples,33600 samples are randomly selected as the training dataset for model training,and the remaining 14096 samples are used as the testing dataset for model testing.AlexNet and GoogLeNet emerged from the quantitative evaluation as the best methods.AlexNet has strong classification accuracy and efficiency(low time consumption),and GoogLeNet has the best classification accuracy.A suitable CNN model for weed seed classification could be selected according to specific identification accuracy requirements and time costs of applications.This research is beneficial for developing a detection system for weed seeds in various applications.The resolution of taxonomic issues and problems associated with the identi-fication of these weed seeds may allow for more effective management and control.展开更多
A novel physical layer data encryption scheme using two-level constellation masking in three-dimensional(3D)carrier-less amplitude and phase modulation(CAP)passive optical network(PON)is proposed in this Letter.The ch...A novel physical layer data encryption scheme using two-level constellation masking in three-dimensional(3D)carrier-less amplitude and phase modulation(CAP)passive optical network(PON)is proposed in this Letter.The chaotic sequence generated by Chua’s circuit model realizes two-level encryption of displacement masking and constellation rotation for3 D constellations.We successfully conduct an experiment demonstrating 8.7 Gb/s 3 D-CAP-8 data transmission over25 km standard single-mode fiber.With two-level constellation masking,a key space size of 2.1×1085 is achieved to bring about high security and good encryption performance,suggesting broad application prospects in future short-range secure communications.展开更多
基金the National Natural Science Foundation for Young Scientists of China(No.31801804)the projects subsidized by the Special Funds for Science Technology Innovation and Industrial Development of Shenzhen Dapeng New District(No.PT202001-06)+1 种基金the Key Research and Development Program of Nanning(No.20192065)Science Foundation of Nanjing Customs District P.R.China(No.2020KJ10).
文摘Weeds are mainly spread by weed seeds being mixed with agricultural and forestry crop seeds,grain,animal hair,and other plant products,and disturb the growing environment of target plants such as crops and wild native plants.The accurate and efficient classification of weed seeds is important for the effective management and control of weeds.However,classification remains mainly dependent on destructive sampling-based manual inspection,which has a high cost and rather low flux.We considered that this problem could be solved using a nondestructive intelligent image recognition method.First,on the basis of the establishment of the image acquisition system for weed seeds,images of single weed seeds were rapidly and completely segmented,and a total of 47696 samples of 140 species of weed seeds and foreign materials remained.Then,six popular and novel deep Convolutional Neural Network(CNN)models are compared to identify the best method for intelligently identifying 140 species of weed seeds.Of these samples,33600 samples are randomly selected as the training dataset for model training,and the remaining 14096 samples are used as the testing dataset for model testing.AlexNet and GoogLeNet emerged from the quantitative evaluation as the best methods.AlexNet has strong classification accuracy and efficiency(low time consumption),and GoogLeNet has the best classification accuracy.A suitable CNN model for weed seed classification could be selected according to specific identification accuracy requirements and time costs of applications.This research is beneficial for developing a detection system for weed seeds in various applications.The resolution of taxonomic issues and problems associated with the identi-fication of these weed seeds may allow for more effective management and control.
基金the National Key Research and Development Program of China(No.2018YFB1801302)National Natural Science Foundation of China(Nos.61835005,61822507,61522501,61475024,61675004,61705107,61727817,61775098,61720106015,and 61875248)+2 种基金Beijing Young Talent(No.2016000026833ZK15)Open Fund of IPOC(BUPT)(No.IPOC2019A011)Jiangsu Talent of Innovation and Entrepreneurship,Jiangsu Team of Innovation and Entrepreneurship,and Postgraduate Research&Practice Innovation Program of Jiangsu Province(No.KYCX200963)。
文摘A novel physical layer data encryption scheme using two-level constellation masking in three-dimensional(3D)carrier-less amplitude and phase modulation(CAP)passive optical network(PON)is proposed in this Letter.The chaotic sequence generated by Chua’s circuit model realizes two-level encryption of displacement masking and constellation rotation for3 D constellations.We successfully conduct an experiment demonstrating 8.7 Gb/s 3 D-CAP-8 data transmission over25 km standard single-mode fiber.With two-level constellation masking,a key space size of 2.1×1085 is achieved to bring about high security and good encryption performance,suggesting broad application prospects in future short-range secure communications.