Establishing a Berry Sensory Evaluation Model Based on Machine Learning

被引:3
作者
Liu, Minghao [1 ]
Liu, Minhua [1 ]
Bai, Lin [2 ]
Shang, Wei [2 ]
Ren, Runhan [2 ]
Zhao, Zhiyao [1 ]
Sun, Ying [2 ,3 ]
机构
[1] Beijing Technol & Business Univ, Sch Artif Intelligence, Beijing 100048, Peoples R China
[2] Beijing Technol & Business Univ, Coll Chem & Mat Engn, Beijing 100048, Peoples R China
[3] Beijing Technol & Business Univ, Sch Light Ind, Beijing 100048, Peoples R China
基金
北京市自然科学基金;
关键词
sensory evaluation; blueberry; preservation; food shelf life; particle swarm arithmetic; support vector machines; QUALITY;
D O I
10.3390/foods12183502
中图分类号
TS2 [食品工业];
学科分类号
0832 ;
摘要
In recent years, people's quality of life has increased, and the requirements for fruits have also become higher; blueberries are particularly popular because of their rich nutrients. In the blueberry industry chain, sensory evaluation is an important link in determining the quality of blueberries. Therefore, to make a more objective scientific evaluation of blueberry quality and reduce the influence of human factors, on the basis of traditional sensory evaluation methods, machine learning is introduced to establish a support vector regression prediction model optimized by the particle swarm algorithm. Ten physical and chemical flavor indices of blueberries (such as catalase, flavonoids, and soluble solids) were used as input data, and sensory evaluation scores were used as output data. Three different predictive models were applied and compared: a particle swarm optimization support vector machine, a convolutional neural network, and a long short-term memory network model. To ensure reliability, the experiments with each of the three models were repeated 20 times, and the mean of each index was calculated. The experimental results showed that the root mean square error and mean absolute error of the particle swarm optimization support vector machine were 0.45 and 0.40, respectively; these values were lower than those of the convolutional neural network (0.96 and 0.78, respectively) and the long short-term memory network (1.22 and 0.97, respectively). Hence, these results highlighted the superiority of the proposed model when sample data are limited.
引用
收藏
页数:16
相关论文
共 50 条
  • [31] Machine-Learning-Based Lightpath QoT Estimation and Forecasting
    Allogba, Stephanie
    Aladin, Sandra
    Tremblay, Christine
    JOURNAL OF LIGHTWAVE TECHNOLOGY, 2022, 40 (10) : 3115 - 3127
  • [32] Intangible assets evaluation: The machine learning perspective
    Tsai, Chih-Fong
    Lu, Yu-Hsin
    Hung, Yu-Chung
    Yen, David C.
    NEUROCOMPUTING, 2016, 175 : 110 - 120
  • [33] Credit Risk Evaluation with Extreme Learning Machine
    Zhou, Hongming
    Lan, Yuan
    Soh, Yeng Chai
    Huang, Guang-Bin
    Zhang, Rui
    PROCEEDINGS 2012 IEEE INTERNATIONAL CONFERENCE ON SYSTEMS, MAN, AND CYBERNETICS (SMC), 2012, : 1064 - 1069
  • [34] LEAF: a process-based model of berry ripening in vineyards
    Carteni, Fabrizio
    Scognamiglio, Pasquale
    Teobaldelli, Maurizio
    Mataffo, Alessandro
    Mazzoleni, Stefano
    Garcia-Tejera, Omar
    Girona, Joan
    Queiroz, Jorge
    Cabral, Ines
    Rossi, Claudio
    Marcos, Raul
    Porras, Ignasi
    Basile, Boris
    2019 IEEE INTERNATIONAL WORKSHOP ON METROLOGY FOR AGRICULTURE AND FORESTRY (METROAGRIFOR), 2019, : 152 - 157
  • [35] Sensory evaluation based on linguistic decision analysis
    Martinez, L.
    INTERNATIONAL JOURNAL OF APPROXIMATE REASONING, 2007, 44 (02) : 148 - 164
  • [36] Production of a cheese model for sensory evaluation of flavour compounds
    Salles, C
    Dalmas, S
    Septier, C
    Issanchou, S
    Noel, Y
    Etievant, P
    LeQuere, JL
    LAIT, 1995, 75 (06): : 535 - 549
  • [37] A Review on Sensory Parameters and Evaluation Methods of Plant-Based Protein Foods
    Tireki, Suzan
    Balkaya, Melike
    Erdem, Dogan Emre
    Coskun, Gulbahar
    Gunay, Elif
    Cekirge, Mehmet
    FOOD REVIEWS INTERNATIONAL, 2024, : 3710 - 3729
  • [38] Development of prediction model for phosphate in reservoir water system based machine learning algorithms
    Latif, Sarmad Dashti
    Birima, Ahmed H.
    Ahmed, Ali Najah
    Hatem, Dahan Mohammed
    Al-Ansari, Nadhir
    Fai, Chow Ming
    El-Shafie, Ahmed
    AIN SHAMS ENGINEERING JOURNAL, 2022, 13 (01)
  • [39] Improved cooperative spectrum sensing model based on machine learning for cognitive radio networks
    Li, Zan
    Wu, Wen
    Liu, Xiangli
    Qi, Peihan
    IET COMMUNICATIONS, 2018, 12 (19) : 2485 - 2492
  • [40] Exploring green building certification credit selection: A model based on explainable machine learning
    Li, Yixin
    Li, Xiaodong
    Ma, Dingyuan
    Gong, Wei
    JOURNAL OF BUILDING ENGINEERING, 2024, 95