Novel Dictionary Pair Learning Through Locality-Constrained Profiles for the Identification of Chili Pepper Varieties via E-Noses
文献类型： 外文期刊
作者： Chen, Liang 1 ; Peng, Guihua 2 ; Zhang, Changfu 1 ; Wang, Xueya 2 ; Chen, Ju 2 ; Yin, Yong 2 ; Yan, Jia 1 ;
作者机构： 1.Southwest Univ, Coll Artificial Intelligence, Chongqing 400715, Peoples R China
2.Guizhou Acad Agr Sci, Chili Pepper Res Inst, Guiyang 550006, Peoples R China
3.Chongqing Key Lab Brain Inspired Comp & Intelligen, Chongqing 400715, Peoples R China
关键词： Dictionaries; Machine learning; Analytical models; Accuracy; Signal processing algorithms; Sensors; Data models; Training; Atoms; Intelligent sensors; Chili pepper; dictionary pair learning (DPL); electronic nose (E-nose); locality constraint of profiles (LCPs); variety identification
期刊名称：IEEE SENSORS JOURNAL （ 影响因子：4.5； 五年影响因子：4.7 ）
ISSN： 1530-437X
年卷期： 2025 年 25 卷 10 期
页码：
收录情况： SCI
摘要： In modern society, to make it easier for customers to assess product quality and regularize distribution and supply, almost all crops are sorted and labeled. This sorting and labeling process also facilitates packaging and transportation of products and benefits farmers. As an emerging technology, electronic noses (E-noses) can be applied to food quality control. In this study, we proposed a novel dictionary pair learning (DPL) model named DPL based on locality constraint of profiles (DPL-LCPs), which achieved better performance in the identification of chili pepper varieties using E-noses. This model incorporates profile vectors to define a profile locality constraint term and integrates it with a dictionary reconstruction error term into a unified dictionary learning (DL) model to fully learn the characteristics of samples from various aspects. This approach not only reduces the similarity between dictionary atoms but also avoids the problem of weakening the connections between characteristics of different classes of samples caused by using the block diagonal constraint. In addition, the model utilizes the l(2,1) norm to regularize the analysis dictionary matrix, enhancing the sparsity of features and thereby enhancing the flexibility and robustness of the model. The experimental results show that the proposed model can achieve better classification results and higher stability than other advanced DL models can. With this method, it is possible to reliably identify 13 varieties of chili peppers based on flavor assessment.
- 相关文献
作者其他论文 更多>>
-
Impact of different drying methods on the quality and flavor of two chili peppers (Capsicum annuum L.) varieties: Chemical composition and volatile compounds
作者：Wu, Di;Yang, Wanrong;Chen, Ju;Wang, Nanyi;He, Jianwen;Fu, Wenting;Zhu, Zhangsheng;Chen, Changming;Wu, Kangyun
关键词：Pepper; Drying; Volatiles; Chemical components; Correlation analysis
-
Guiding chili variety selection for Zao chili in Guizhou: Based on a systematic study of sensory, physicochemical, and volatile characteristics
作者：Wang, Xueya;Li, Wenxin;Chen, Ju;Yin, Yong;Sun, Xiaojing;Lu, Min;He, Jianwen;Lu, Kuan
关键词：Correlation analysis; Fermented chili; Key aroma substances; Processing adaptability; Product quality
-
An efficient method for chili pepper variety classification and origin tracing based on an electronic nose and deep learning
作者：Chen, Yong;Yang, Wenzheng;Yan, Jia;Wang, Xueya;Peng, Guihua;Chen, Ju;Yin, Yong;Yan, Jia;Yan, Jia
关键词：Chili pepper; Variety classification; Origin traceability; Deep learning; Electronic nose; Machine olfaction; Gas recognition
-
Aroma evaluation for chili pepper using an E-nose combined with a novel feature fusion technology based on machine learning
作者：Yan, Jia;Sun, Ruihong;Zhang, Changfu;Li, Zhe;Zhang, Aimin;Wang, Xueya;Chen, Ju;Yin, Yong;Liu, Tao
关键词：Electronic nose; Aroma evaluation; Chili pepper; Variety identification; Feature fusion
-
An Integrated Lightweight Neural Network Design and FPGA-Accelerated Edge Computing for Chili Pepper Variety and Origin Identification via an E-Nose
作者：Guo, Ziyu;Gu, Haolin;Yan, Jia;Yin, Yong;Peng, Guihua;Wang, Xueya;Chen, Ju
关键词：e-nose; FPGA-accelerated; lightweight CNN; chili pepper; variety identification; origin tracing
-
Metabolomic Profiling Reveals Dynamic Changes in Organic Acids During Zaolajiao Fermentation: Correlation with Physicochemical Properties and CAZymes
作者：Chen, Ju;Wang, Xueya;Li, Wenxin;He, Jianwen;Yin, Yong;Lu, Min;Huang, Yubing
关键词：Zaolajiao; targeted metabolomics; differential organic acids (DOAs); correlation; carbohydrate active enzymes (CAZymes); metabolic pathway
-
Revealing core functional microorganisms in the fermentation process of Qicaipaojiao ( Capsicum annuum L.) based on microbial metabolic network
作者：Chen, Ju;Wang, Xueya;He, Jianwen;Li, Wenxin;Lu, Min;Sun, Xiaojing;Yin, Yong;Huang, Yubing
关键词：Qicaipaojiao; Key taste substances; Key aroma substances; Correlation analysis; Flavor formation; Core functional microorganisms
