肉类研究
肉類研究
육류연구
MEAT RESEARCH
2015年
5期
27-30
,共4页
王智凝%郑丽敏%方雄武%杨璐
王智凝%鄭麗敏%方雄武%楊璐
왕지응%정려민%방웅무%양로
猪肉新鲜度%传感器阵列%阵列优化%电子鼻%相关系数%逐步判别法
豬肉新鮮度%傳感器陣列%陣列優化%電子鼻%相關繫數%逐步判彆法
저육신선도%전감기진렬%진렬우화%전자비%상관계수%축보판별법
pork freshness%sensor array%array optimization%electronic nose%correlation coefficient%stepwise discriminant analysis
用电子鼻检测猪肉新鲜度时，传感器阵列的冗余信息会带来负面影响。为了提高识别的准确性，根据猪肉散发的气味选择初始的传感器阵列，利用方差分析方法剔除重复性和区分度不明显的传感器；再通过变异系数分析、相关系数绝对值累加和最小分析、主成分分析（principal component analysis，PCA）第2主成分系数分析，筛选出了适合检测猪肉新鲜度的传感器阵列的优化阵列。本研究采用逐步判别法筛选出合适的特征值，并用贝叶斯判别方法对传感器阵列优化前后的数据进行对比分析。结果表明：通过对传感器阵列的优化，识别率由优化前的86.8%提高到优化后的98.9%。研究表明，本实验的传感器阵列优化方法可以大大提高电子鼻对猪肉新鲜度的识别准确性。
用電子鼻檢測豬肉新鮮度時，傳感器陣列的冗餘信息會帶來負麵影響。為瞭提高識彆的準確性，根據豬肉散髮的氣味選擇初始的傳感器陣列，利用方差分析方法剔除重複性和區分度不明顯的傳感器；再通過變異繫數分析、相關繫數絕對值纍加和最小分析、主成分分析（principal component analysis，PCA）第2主成分繫數分析，篩選齣瞭適閤檢測豬肉新鮮度的傳感器陣列的優化陣列。本研究採用逐步判彆法篩選齣閤適的特徵值，併用貝葉斯判彆方法對傳感器陣列優化前後的數據進行對比分析。結果錶明：通過對傳感器陣列的優化，識彆率由優化前的86.8%提高到優化後的98.9%。研究錶明，本實驗的傳感器陣列優化方法可以大大提高電子鼻對豬肉新鮮度的識彆準確性。
용전자비검측저육신선도시，전감기진렬적용여신식회대래부면영향。위료제고식별적준학성，근거저육산발적기미선택초시적전감기진렬，이용방차분석방법척제중복성화구분도불명현적전감기；재통과변이계수분석、상관계수절대치루가화최소분석、주성분분석（principal component analysis，PCA）제2주성분계수분석，사선출료괄합검측저육신선도적전감기진렬적우화진렬。본연구채용축보판별법사선출합괄적특정치，병용패협사판별방법대전감기진렬우화전후적수거진행대비분석。결과표명：통과대전감기진렬적우화，식별솔유우화전적86.8%제고도우화후적98.9%。연구표명，본실험적전감기진렬우화방법가이대대제고전자비대저육신선도적식별준학성。
When electronic nose is used for detecting pork freshness, sensor array optimization has a great influence on improving the accuracy by eliminating the negative effects brought about by the redundant information. The initial sensor array was determined by the odor released from pork. Then the sensors with poor repeatability and differentiation were excluded by analysis of variance (ANOVA). By coefficient of variation, minimum cumulation of absolute correlation coefficient and the second principal component of principal component analysis (PCA), an optimized sensor array was selected for the detection of pork freshness. This study adopted stepwise discriminant analysis to optimize features and compare the data before and after optimization by using Bayes discriminant method. Results showed that by sensor optimization and feature optimization, the accuracy was increased from 86.8% to 98.9%. This study indicates that sensor array optimization and feature optimization can greatly improve the detection accuracy of pork freshness.
