华东交通大学学报2017，Vol.34Issue(2)：105-111,7.
基于LS-SVM高光谱成像鱼新鲜度鉴别
Classification of Fish Freshness Based on LS-SVM and Hyperspectra Imaging Technology
摘要
Abstract
This study investigated the feasibility of using near infrared hyperspectral imaging system (NIR-HIS) technique for non-destructive identification of fresh and frozen-thawed fish fillets . Hyperspectral images of freshness, storage time, and frozen-thawed times of fillets for turbot flesh were obtained in the spectral region of 381~1023 nm. Reflectance values were extracted from each region of interest (ROI) of each sample. Monte Car-lo free information variable elimination (MCVE) algorithm, successive projections algorithm (SPA) and random frog (RF) were carried out to identify the most significant wavelengths. Based on the ninety, thirty-one and forty-nine wavelengths suggested by MCVE, SPA and RF, respectively, two classified models (least squares-support vector machine, LS-SVM and SIMCA) were established. Among the established models, SPA-LS-SVM model performed well with the highest classification rate (100%) in calibration and 98% in prediction sets. SPA-LS-SVM and MCVE-LS-SVM models obtained better results 98%of classification rate in prediction set with thirty-one and ninety effective wavelengths respectively. The RF-LS-SVM model obtained poor results with 88% of classification rate in prediction set. The results showed that NIR-HIS technique can be used to identify the vari-eties of fresh and frozen-thawed fish fillets rapidly and non-destructively, and SPA was effective wavelengths selection method.关键词
蒙特卡罗无信息变量消除/连续投影/随机青蛙/LS-SVMKey words
monte carlo free information variable elimination(MCVE)/successive projections algorithm(SPA)/random frog(RF)/least squares-support vector machine(LS-SVM)分类
数理科学引用本文复制引用
章海亮,叶青,罗微,刘雪梅..基于LS-SVM高光谱成像鱼新鲜度鉴别[J].华东交通大学学报,2017,34(2):105-111,7.基金项目
国家自然科学基金项目(61565005) （61565005）
江西省科技支撑项目(20142BDH80021) （20142BDH80021）
