Prediction of human assessments of dairy odor utilizing a fast gas chromatograph and neural networks

doi:10.1016/j.compag.2019.01.037

	Prediction of human assessments of dairy odor utilizing a fast gas chromatograph and neural networks
	Chang, Fangle 1,2; Heinemann, Paul H.3
刊名	COMPUTERS AND ELECTRONICS IN AGRICULTURE
	2019-02-01
卷号	157 页码:541-548
关键词	Dairy Human assessments Hedonic tone zNose Artificial Neural Networks
ISSN号	0168-1699
DOI	10.1016/j.compag.2019.01.037
通讯作者	Heinemann, Paul H.(hzh@psu.edu)
英文摘要	A method based on hedonic tone was developed and applied to evaluate human assessments of odor emitted from dairy operations using a fast gas chromatograph and neural networks. A general pleasantness scale ranging from -11 (extremely unpleasant) to +11 (extremely pleasant) was used to collect human responses. The panelists were able to identify the difference between various samples, and gave individually consistent responses for the same sample. The measurements of a fast gas chromatograph, called the zNose, were trained using Artificial Neural Networks (ANNs) to predict the human assessments. Three ANNs, Levenberg-Marquardt Back-propagation Neural Network (LMBNN), Scaled Conjugate Gradient Back-propagation (CGBNN), and Resilient Back-propagation Neural Network (RPBNN), were applied to connect human assessments and instrument measurements. In separate validation, zNose-LMBNN model showed superiority in four criteria, Mean Square Error (MSE), Correlation Coefficient (R), probability within 10% range to target, and probability within 5% range to target. The optimal model outputs represented human response as high as 67% within the 10% range and 44% within the 5% range of the targets. In addition, the model outputs have a good linear relationship with the targets (R = 0.53).
资助项目	USDA National Institute of Food and Agriculture Federal Appropriations[PEN04547] ; USDA National Institute of Food and Agriculture Federal Appropriations[1001036]
WOS关键词	ELECTRONIC NOSE ; HEDONIC TONE ; QUANTIFICATION ; CLASSIFICATION ; INTENSITY
WOS研究方向	Agriculture ; Computer Science
语种	英语
出版者	ELSEVIER SCI LTD
WOS记录号	WOS:000459358400053
资助机构	USDA National Institute of Food and Agriculture Federal Appropriations
内容类型	期刊论文
源URL	[http://ir.ia.ac.cn/handle/173211/25044]
专题	中国科学院自动化研究所
通讯作者	Heinemann, Paul H.
作者单位	1.Chinese Acad Sci, Inst Automat, State Key Lab Management & Control Complex Syst, Beijing 100190, Peoples R China 2.Qingdao Acad Intelligent Ind, Innovat Ctr Parallel Agr, Qingdao 266109, Peoples R China 3.Penn State Univ, Dept Agr & Biol Engn, 105 Agr Engn Bldg, University Pk, PA 16802 USA
推荐引用方式 GB/T 7714	Chang, Fangle,Heinemann, Paul H.. Prediction of human assessments of dairy odor utilizing a fast gas chromatograph and neural networks[J]. COMPUTERS AND ELECTRONICS IN AGRICULTURE,2019,157:541-548.
APA	Chang, Fangle,&Heinemann, Paul H..(2019).Prediction of human assessments of dairy odor utilizing a fast gas chromatograph and neural networks.COMPUTERS AND ELECTRONICS IN AGRICULTURE,157,541-548.
MLA	Chang, Fangle,et al."Prediction of human assessments of dairy odor utilizing a fast gas chromatograph and neural networks".COMPUTERS AND ELECTRONICS IN AGRICULTURE 157(2019):541-548.