Genetic Algorithms （GA） are a search techniques based on mechanics of nature selection and have already been successfully applied in many diverse areas. However, increasing samples show that GA＇s performance is not...Genetic Algorithms （GA） are a search techniques based on mechanics of nature selection and have already been successfully applied in many diverse areas. However, increasing samples show that GA＇s performance is not as good as it was expected to be. Criticism of this algorithm includes the slow speed and premature result during convergence procedure. In order to improve the performance, the population size and individuals＇ space is emphatically described. The influence of individuals＇ space and population size on the operators is analyzed. And a novel family genetic algorithm （FGA） is put forward based on this analysis. In this novel algorithm, the optimum solution families closed to quality individuals is constructed, which is exchanged found by a search in the world space. Search will be done in this microspace. The family that can search better genes in a limited period of time would win a new life. At the same time, the best gene of this micro space with the basic population in the world space is exchanged. Finally, the FGA is applied to the function optimization and image matching through several experiments. The results show that the FGA possessed high performance.展开更多
It remains unclear whether limitations in activities of daily living(ADL) increase the risk of stroke in older Chinese adults.This longitudinal study used data from the Chinese Longitudinal Healthy Longevity Survey to...It remains unclear whether limitations in activities of daily living(ADL) increase the risk of stroke in older Chinese adults.This longitudinal study used data from the Chinese Longitudinal Healthy Longevity Survey to investigate the effects of limitations in ADL on the incidence of stroke in older adults.Between 2002 and 2011,46,728 participants from 22 provinces in China were included in this study.Of participants,11,241 developed limitations in ADL at baseline.A 3-year follow-up was performed to determine the incidence of stroke.During the 3-year follow-up,929 participants(8.26%) and 2434 participants(6.86%) experienced stroke in the ADL limitations group and non-ADL limitations group,respectively.Logistic regression was used to analyze the effect of ADL limitations on the risk of stroke.The results showed that after adjusting for the confounding factors gender,age,weight,hypertension,diabetes,heart disease,natural teeth,hearing impairment,visual impairment,smoking,alcohol abuse,exercise,ethnicity,literacy,residential area,and poverty,the ADL limitations group had a 77% higher risk of developing stroke than the non-ADL limitations group.After propensity score matching,the ADL limitations group still had a 33% higher risk of developing stroke than the non-ADL limitations group(OR = 1.326,95% CI:1.174–1.497).These findings suggest that limitations in ADL are a stroke risk factor.展开更多
Individual identification of dairy cows is the prerequisite for automatic analysis and intelligent perception of dairy cows'behavior.At present,individual identification of dairy cows based on deep convolutional n...Individual identification of dairy cows is the prerequisite for automatic analysis and intelligent perception of dairy cows'behavior.At present,individual identification of dairy cows based on deep convolutional neural network had the disadvantages in prolonged training at the additions of new cows samples.Therefore,a cow individual identification framework was proposed based on deep feature extraction and matching,and the individual identification of dairy cows based on this framework could avoid repeated training.Firstly,the trained convolutional neural network model was used as the feature extractor;secondly,the feature extraction was used to extract features and stored the features into the template feature library to complete the enrollment;finally,the identifies of dairy cows were identified.Based on this framework,when new cows joined the herd,enrollment could be completed quickly.In order to evaluate the application performance of this method in closed-set and open-set individual identification of dairy cows,back images of 524 cows were collected,among which the back images of 150 cows were selected as the training data to train feature extractor.The data of the remaining 374 cows were used to generate the template data set and the data to be identified.The experiment results showed that in the closed-set individual identification of dairy cows,the highest identification accuracy of top-1 was 99.73%,the highest identification accuracy from top-2 to top-5 was 100%,and the identification time of a single cow was 0.601 s,this method was verified to be effective.In the open-set individual identification of dairy cows,the recall was 90.38%,and the accuracy was 89.46%.When false accept rate(FAR)=0.05,true accept rate(TAR)=84.07%,this method was verified that the application had certain research value in open-set individual identification of dairy cows,which provided a certain idea for the application of individual identification in the field of intelligent animal husbandry.展开更多
文摘Genetic Algorithms （GA） are a search techniques based on mechanics of nature selection and have already been successfully applied in many diverse areas. However, increasing samples show that GA＇s performance is not as good as it was expected to be. Criticism of this algorithm includes the slow speed and premature result during convergence procedure. In order to improve the performance, the population size and individuals＇ space is emphatically described. The influence of individuals＇ space and population size on the operators is analyzed. And a novel family genetic algorithm （FGA） is put forward based on this analysis. In this novel algorithm, the optimum solution families closed to quality individuals is constructed, which is exchanged found by a search in the world space. Search will be done in this microspace. The family that can search better genes in a limited period of time would win a new life. At the same time, the best gene of this micro space with the basic population in the world space is exchanged. Finally, the FGA is applied to the function optimization and image matching through several experiments. The results show that the FGA possessed high performance.
基金supported by a grant from the Clinical Research Project of Affiliated Hospital of Guangdong Medical University of China,Nos.LCYJ2018A00 (to ZL) and LCYJ2019C006 (to YSC)the Natural Science Foundation of Guangdong Province of China,No.2020A151501284 (to ZL)+1 种基金the Science and Technology Planning Project of Zhanjiang of China,No.2018A01021 (to ZL)a grant from the Characteristic Innovation Projects of Colleges and Universities in Guangdong Province of China,No.2019KTSCX045 (to ZL)。
文摘It remains unclear whether limitations in activities of daily living(ADL) increase the risk of stroke in older Chinese adults.This longitudinal study used data from the Chinese Longitudinal Healthy Longevity Survey to investigate the effects of limitations in ADL on the incidence of stroke in older adults.Between 2002 and 2011,46,728 participants from 22 provinces in China were included in this study.Of participants,11,241 developed limitations in ADL at baseline.A 3-year follow-up was performed to determine the incidence of stroke.During the 3-year follow-up,929 participants(8.26%) and 2434 participants(6.86%) experienced stroke in the ADL limitations group and non-ADL limitations group,respectively.Logistic regression was used to analyze the effect of ADL limitations on the risk of stroke.The results showed that after adjusting for the confounding factors gender,age,weight,hypertension,diabetes,heart disease,natural teeth,hearing impairment,visual impairment,smoking,alcohol abuse,exercise,ethnicity,literacy,residential area,and poverty,the ADL limitations group had a 77% higher risk of developing stroke than the non-ADL limitations group.After propensity score matching,the ADL limitations group still had a 33% higher risk of developing stroke than the non-ADL limitations group(OR = 1.326,95% CI:1.174–1.497).These findings suggest that limitations in ADL are a stroke risk factor.
基金Supported by the National Key Research and Development Program of China(2019YFE0125600)China Agriculture Research System(CARS-36)。
文摘Individual identification of dairy cows is the prerequisite for automatic analysis and intelligent perception of dairy cows'behavior.At present,individual identification of dairy cows based on deep convolutional neural network had the disadvantages in prolonged training at the additions of new cows samples.Therefore,a cow individual identification framework was proposed based on deep feature extraction and matching,and the individual identification of dairy cows based on this framework could avoid repeated training.Firstly,the trained convolutional neural network model was used as the feature extractor;secondly,the feature extraction was used to extract features and stored the features into the template feature library to complete the enrollment;finally,the identifies of dairy cows were identified.Based on this framework,when new cows joined the herd,enrollment could be completed quickly.In order to evaluate the application performance of this method in closed-set and open-set individual identification of dairy cows,back images of 524 cows were collected,among which the back images of 150 cows were selected as the training data to train feature extractor.The data of the remaining 374 cows were used to generate the template data set and the data to be identified.The experiment results showed that in the closed-set individual identification of dairy cows,the highest identification accuracy of top-1 was 99.73%,the highest identification accuracy from top-2 to top-5 was 100%,and the identification time of a single cow was 0.601 s,this method was verified to be effective.In the open-set individual identification of dairy cows,the recall was 90.38%,and the accuracy was 89.46%.When false accept rate(FAR)=0.05,true accept rate(TAR)=84.07%,this method was verified that the application had certain research value in open-set individual identification of dairy cows,which provided a certain idea for the application of individual identification in the field of intelligent animal husbandry.
