http://chineseinput.net/에서 pinyin(병음)방식으로 중국어를 변환할 수 있습니다.
변환된 중국어를 복사하여 사용하시면 됩니다.
Face Expression Recognition Based on Motion Templates and 4-layer Deep Learning Neural Network
Jianzheng Liu,Xiaojing Wang,Jucheng Yang,Chao Wu,Lijun Liu 보안공학연구지원센터 2015 International Journal of Signal Processing, Image Vol.8 No.12
A human facial expression is the formation of facial muscle movement. In our previous research, we proposed a method of identifying facial muscle movement which based on motion templates and GentleBoost. But the method was not robust enough to recognize human expression due to insufficient learning stage. So in this paper, we proposed a new method based on motion templates and 4-layer deep learning neural network to identify human's facial expressions. We recognized Action Unit as a kind of features by using motion templates and adaboost firstly, and then the extracted features were used to feed a 4-layer deep learning neural network to recognize the facial expression. The experimental results have proved that the proposed method can solve the problem encountered in our previous research.
Binling Ai,Jianzheng Li,Xue Chi,Jia Meng,Ajay Kumar Jha,Chong Liu,En shi 한국생물공학회 2014 Biotechnology and Bioprocess Engineering Vol.19 No.4
This study was conducted to identify theoptimum pH range and the appropriate buffer for butyricacid production from rice straw by fermentation using anundefined mixed culture. A series of experiments conductedat pH levels of 5.0 ~ 7.0 showed that neutral pH improvedrice straw conversion and consequently carboxylic acidproduction. The highest butyric acid production (up to6.7 g/L) was achieved at pH of 6.0 ~ 6.5, while it was only1.7 g/L without pH control or at pH 5.0. Another series ofexperiments conducted at pH 6.0 ~ 6.5 buffered withCaCO3, NaHCO3, NH4HCO3 and their combinationsindicated that different buffers had different effects ontheproduct spectrum, and that CaCO3 combined with NaHCO3was an effective buffer for butyric acid production. Thehighest total volatile fatty acids (about 12.6 g/L) productionand one of the two highest butyric acid concentrations(about 7.6 g/L) were obtained by buffering with CaCO3combined with NaHCO3. PCR-DGGE analysis revealedthat different pH and buffers also influenced the microbialpopulation distribution. Bacteria were suppressed at lowpH , while the bacterial community structures at higher pHvaried slightly. Overall, this study presents an alternativemethod for butyric acid production from lignocellulosicbiomass without supplementary cellulolytic enzyme.
Butyric Acid Fermentation of Sodium Hydroxide Pretreated Rice Straw with Undefined Mixed Culture
( Binling Ai ),( Jianzheng Li ),( Xue Chi ),( Jia Meng ),( Chong Liu ),( En Shi ) 한국미생물 · 생명공학회 2014 Journal of microbiology and biotechnology Vol.24 No.5
This study describes an alternative mixed culture fermentation technology to anaerobically convert lignocellulosic biomass into butyric acid, a valuable product with wide application, without supplementary cellulolytic enzymes. Rice straw was soaked in 1% NaOH solution to increase digestibility. Among the tested pretreatment conditions, soaking rice straw at 50°C for 72 h removed ~66% of the lignin, but retained ~84% of the cellulose and ~71% of the hemicellulose. By using an undefined cellulose-degrading butyrate-producing microbial community as butyric acid producer in batch fermentation, about 6 g/l of butyric acid was produced from the pretreated rice straw, which accounted for ~76% of the total volatile fatty acids. In the repeated-batch operation, the butyric acid production declined batch by batch, which was most possibly caused by the shift of microbial community structure monitored by denaturing gradient gel electrophoresis. In this study, batch operation was observed to be more suitable for butyric acid production.