Soybean is a crop with a long cultivation history that occupies an important position in agricultural production.Soybean mosaic virus disease(SMV)has caused a rapid decline in soybean yields,causing huge losses to the...Soybean is a crop with a long cultivation history that occupies an important position in agricultural production.Soybean mosaic virus disease(SMV)has caused a rapid decline in soybean yields,causing huge losses to the soybean industry,wherefrom its early detec-tion is particularly important.This study proposes a new classification method for the early SMV,dividing its severity into grades 0,1 and 2.In the case of a small number of experi-mental samples of soybeans,this study proposes a combined convolutional neural network and support vector machine(CNN-SVM)method for the early detection of SMV.Experimen-tal results showed that the accuracy of the training set of the CNN-SVM model reached 96.67%,and the accuracy rate of the test set reached 94.17%.The experiment proved the feasibility of using the proposed CNN-SVM model to classify early SMV under the new clas-sification method,and provided a new direction for early SMV detection based on hyper-spectral images.展开更多
In this work,we consider community detection in blockchain networks.We specifically take the Bitcoin network and Ethereum network as two examples,where community detection serves in different ways.For the Bitcoin netw...In this work,we consider community detection in blockchain networks.We specifically take the Bitcoin network and Ethereum network as two examples,where community detection serves in different ways.For the Bitcoin network,we modify the traditional community detection method and apply it to the transaction social network to cluster users with similar characteristics.For the Ethereum network,on the other hand,we define a bipartite social graph based on the smart contract transactions.A novel community detection algorithm which is designed for low-rank signals on graph can help find users’communities based on user-token subscription.Based on these results,two strategies are devised to deliver on-chain advertisements to those users in the same community.We implement the proposed algorithms on real data.By adopting the modified clustering algorithm,the community results in the Bitcoin network are basically consistent with the ground-truth of the betting site community which has been announced to the public.Meanwhile,we run the proposed strategy on real Ethereum data,visualize the results and implement an advertisement delivery on the Ropsten test net.展开更多
基金This work is supported by National Natural Science Founda-tion of China(NSFC)(32071904)。
文摘Soybean is a crop with a long cultivation history that occupies an important position in agricultural production.Soybean mosaic virus disease(SMV)has caused a rapid decline in soybean yields,causing huge losses to the soybean industry,wherefrom its early detec-tion is particularly important.This study proposes a new classification method for the early SMV,dividing its severity into grades 0,1 and 2.In the case of a small number of experi-mental samples of soybeans,this study proposes a combined convolutional neural network and support vector machine(CNN-SVM)method for the early detection of SMV.Experimen-tal results showed that the accuracy of the training set of the CNN-SVM model reached 96.67%,and the accuracy rate of the test set reached 94.17%.The experiment proved the feasibility of using the proposed CNN-SVM model to classify early SMV under the new clas-sification method,and provided a new direction for early SMV detection based on hyper-spectral images.
基金National Natural Science Foundation of China(61701315)Shenzhen Technology Research and Development Fund(JCYJ20170302145906843)。
文摘In this work,we consider community detection in blockchain networks.We specifically take the Bitcoin network and Ethereum network as two examples,where community detection serves in different ways.For the Bitcoin network,we modify the traditional community detection method and apply it to the transaction social network to cluster users with similar characteristics.For the Ethereum network,on the other hand,we define a bipartite social graph based on the smart contract transactions.A novel community detection algorithm which is designed for low-rank signals on graph can help find users’communities based on user-token subscription.Based on these results,two strategies are devised to deliver on-chain advertisements to those users in the same community.We implement the proposed algorithms on real data.By adopting the modified clustering algorithm,the community results in the Bitcoin network are basically consistent with the ground-truth of the betting site community which has been announced to the public.Meanwhile,we run the proposed strategy on real Ethereum data,visualize the results and implement an advertisement delivery on the Ropsten test net.
