Enhanced multivariate data fusion and optimized algorithm for comprehensive quality profiling and origin traceability of Chinese jujube
2025
Peng Chen | Xiaoli Wang | Rao Fu | Xiaoyan Xiao | Yu Li | Tulin Lu | Tao Wang | Qiaosheng Guo | Peina Zhou | Chenghao Fei
Chinese jujube (CJ) is a nutritious food. Its authenticity has received increasing attention. This research utilized computer vision, ultrafast gas-phase electronic nose, and GC–MS technologies to collect jujube samples from various regions in China, including Xinjiang, Gansu, Shaanxi, Henan, Shandong, and Hebei. Multidimensional trait data, encompassing spectra, texture, and odour, were gathered. By employing multivariate statistical methods, 46 trait characteristic factors (VIP > 1, P < 0.05) were identified and utilized to rapidly differentiate jujube samples originating from different regions. The multivariate statistical analysis and support vector machine (SVM) classification were also combined to develop a novel artificial intelligence algorithm. The accuracy of this innovative method was significantly higher than that of conventional discriminant analysis methods, achieving a perfect 100.0 % accuracy. As a consequence of this research, more intelligent algorithms can be developed that trace the origin of food based on multidimensional data.
Afficher plus [+] Moins [-]Mots clés AGROVOC
Informations bibliographiques
Cette notice bibliographique a été fournie par Directory of Open Access Journals
Découvrez la collection de ce fournisseur de données dans AGRIS