http://chineseinput.net/에서 pinyin(병음)방식으로 중국어를 변환할 수 있습니다.
변환된 중국어를 복사하여 사용하시면 됩니다.
Comparison of Different CNN Models in Tuberculosis Detecting
( Jian Liu ),( Yidi Huang ) 한국인터넷정보학회 2020 KSII Transactions on Internet and Information Syst Vol.14 No.8
Tuberculosis is a chronic and delayed infection which is easily experienced by young people. According to the statistics of the World Health Organization (WHO), there are nearly ten million fell ill with tuberculosis and a total of 1.5 million people died from tuberculosis in 2018 (including 251000 people with HIV). Tuberculosis is the largest single infectious pathogen that leads to death. In order to help doctors with tuberculosis diagnosis, we compare the tuberculosis classification abilities of six popular convolutional neural network (CNN) models in the same data set to find the best model. Before training, we optimize three parts of CNN to achieve better results. We employ sigmoid function to replace the step function as the activation function. What’s more, we use binary cross entropy function as the cost function to replace traditional quadratic cost function. Finally, we choose stochastic gradient descent (SGD) as gradient descent algorithm. From the results of our experiments, we find that Densenet121 is most suitable for tuberculosis diagnosis and achieve a highest accuracy of 0.835. The optimization and expansion depend on the increase of data set and the improvements of Densenet121.
Fang Hao,Yuan Sun,Yidi Wang,Yang Lv,Pingle Liu,Xiong Wei,Hean Luo 한국화학공학회 2021 Korean Journal of Chemical Engineering Vol.38 No.8
Selective aerobic oxidation of cyclohexane to cyclohexanone and cyclohexanol (KA oil) with high yield under mild and green conditions is still a significant challenge in the current chemical industry. Herein, nitrogen doped graphene loaded non-noble Co (Co-N-rGO) catalysts, prepared by a facile post-impregnation method, exhibited a high catalytic performance and stability in liquid phase cyclohexane oxidation with molecular oxygen. The experiment and characterization results show that N doping in the catalysts promotes Co metal particle dispersion and induces carbon film coating on Co to prevent leaching and agglomeration. Besides, density functional theory (DFT) calculations show that N doping is beneficial to the O-O bonds breaking in cyclohexyl-hydroperoxides (CHHP), thereby promoting the dissociation of CHHP and enhancing the yield to KA oil. In addition, the catalyst can be easily separated without appreciable loss of catalytic activity after recycling for five times, and show potential industrial application value for the catalytic oxidation of cyclohexane to KA oil in the chemical industry.