基于改进卷积神经网络的咖啡识别方法
作者:
作者单位:

广东工业大学 信息工程学院

中图分类号:

TS273

基金项目:

国家自然科学基金(61571140)。


Coffee recognition method based on improved convolutional neural network
Author:
Affiliation:

School of Information Engineering, Guangdong University of Technology

Fund Project:

National Natural Science Foundation of China

  • 摘要
  • | |
  • 访问统计
  • |
  • 参考文献 [26]
  • | |
  • 引证文献
  • | |
  • 文章评论
    摘要:

    咖啡风味是消费者在品鉴和选择咖啡时考虑的主要因素之一。传统且常见的咖啡香气评估方法是基于昂贵的设备或通过人工感官进行评判。这些方法耗时、成本高且需要训练有素的评估人员。因此,我们提出一种低成本、便携式的咖啡识别方法,结合改进卷积神经网络(convolutional neural network,CNN)对5种不同品种的咖啡进行识别分类。咖啡气味通过电子鼻采集,设计具有三层卷积层的改进CNN分类模型,使用Leaky-ReLU和Dropout模型优化技术,相较于常用的CNN模型性能有一定的提升。与其他多种用于机器嗅觉的模型作对比,实验结果表明,改进CNN模型对咖啡五分类问题准确率达到84.80%,该模型能够对咖啡实现有效的分类。

    Abstract:

    Coffee flavor is one of the main factors consumers consider when tasting and choosing coffee. Traditional and common methods of assessing coffee aroma are based on expensive equipment or artificial senses. These methods are time-consuming, costly, and require trained evaluators. Therefore, we propose a low-cost and portable coffee recognition method that combines an improved convolutional neural network (CNN) to recognize and classify five different varieties of coffee. The coffee smell is collected through the electronic nose, and an improved CNN classification model with three convolution layers was designed using Leaky-ReLU and Dropout model optimization techniques, which has improved performance compared to commonly used CNN models. Compared with other models used for machine olfaction, the experimental results show that the accuracy of improved CNN model for coffee five classification can reach 84.80%, and the model can effectively classify coffee.

    参考文献
    [1] Cheng B, Furtado A, Smyth H E, et al. Influence of genotype and environment on coffee quality[J]. Trends in Food Science Technology, 2016, 57: 20-30.
    [2] Giraudo A, Grassi S, Savorani F, et al. Determination of the geographical origin of green coffee beans using NIR spectroscopy and multivariate data analysis[J]. Food Control, 2019, 99: 137-145.
    [3] Flambeau K J, Lee W J, Yoon J. Discrimination and geographical origin prediction of washed specialty Bourbon coffee from different coffee growing areas in Rwanda by using electronic nose and electronic tongue[J]. Food Science and biotechnology, 2017, 26(5): 1245-1254.
    [4] Severini C, Ricci I, Marone M, et al. Changes in the aromatic profile of espresso coffee as a function of the grinding grade and extraction time: a study by the electronic nose system[J]. Journal of agricultural and food chemistry, 2015, 63(8): 2321-2327.
    [5] Bona E, Borsato D, Bassoli D G. Optimized neural network for instant coffee classification through an electronic nose[J]. International Journal of Food Engineering, 2011, 7(6).
    [6] Ongo E, Falasconi M, Sberveglieri G, et al. Chemometric discrimination of Philippine civet coffee using electronic nose and gas chromatography mass spectrometry[J]. Procedia Engineering, 2012, 47: 977-980.
    [7] Dzung N H, Dzuan L, Tu H D. The role of sensory evaluation in food quality control, food research and development: a case of coffee study[C]//Proceedings of the 8th Asean food Conference, Hanoi, Vietnam. 2003: 8-11.
    [8] Jumhawan U, Putri S P, Marwani E, et al. Selection of discriminant markers for authentication of Asian palm civet coffee (Kopi Luwak): a metabolomics approach[J]. Journal of agricultural and food chemistry, 2013, 61(33): 7994-8001.
    [9] 于菲, 董文江, 胡荣锁, 等. 烘焙速度对兴隆咖啡豆挥发性成分的影响[J]. 热带作物学报, 2021, 42(11): 3316.Yu F, Dong W J, Hu R S, et al. Effects of roasting speed on volatile Components of Xinglong Coffee bean [J]. Journal of Tropical Crops, 2021, 42(11): 3316. (in Chinese)
    [10] Nganou D N, Durand N, Tatsadjieu N L, et al. Determination of coffee origin by using 28S rDNA fingerprinting of fungal communities by PCR-DGGE: application to the Cameroonian coffee[J]. International Journal of Biosciences (IJB), 2012, 2(5): 18-30.
    [11] Bertone E, Venturello A, Giraudo A, et al. Simultaneous determination by NIR spectroscopy of the roasting degree and Arabica/Robusta ratio in roasted and ground coffee[J]. Food Control, 2016, 59: 683-689.
    [12] Dong W, Zhao J, Hu R, et al. Differentiation of Chinese robusta coffees according to species, using a combined electronic nose and tongue, with the aid of chemometrics[J]. Food chemistry, 2017, 229: 743-751.
    [13] Gutierrez-Osuna R. Pattern analysis for machine olfaction: A review[J]. IEEE Sensors journal, 2002, 2(3): 189-202.
    [14] Viejo C G, Fuentes S, Godbole A, et al. Development of a low-cost e-nose to assess aroma profiles: An artificial intelligence application to assess beer quality[J]. Sensors and Actuators B: Chemical, 2020, 308: 127688.
    [15] Fuentes S, Summerson V, Gonzalez Viejo C, et al. Assessment of smoke contamination in grapevine berries and taint in wines due to bushfires using a low-cost E-nose and an artificial intelligence approach[J]. Sensors, 2020, 20(18): 5108.
    [16] Chen Q, Zhao J, Chen Z, et al. Discrimination of green tea quality using the electronic nose technique and the human panel test, comparison of linear and nonlinear classification tools[J]. Sensors and Actuators B: Chemical, 2011, 159(1): 294-300.
    [17] Bona E, Borsato D, Bassoli D G. Optimized neural network for instant coffee classification through an electronic nose[J]. International Journal of Food Engineering, 2011, 7(6).
    [18] Thepudom T, Sricharoenchai N, Kerdcharoen T. Classification of instant coffee odors by electronic nose toward quality control of production[C]//2013 10th International Conference on Electrical Engineering/Electronics, Computer, Telecommunications and Information Technology. IEEE, 2013: 1-4.
    [19] Magfira D B, Sarno R. Classification of Arabica and Robusta coffee using electronic nose[C]//2018 International Conference on Information and Communications Technology (ICOIACT). IEEE, 2018: 645-650.
    [20] Harsono W, Sarno R, Sabilla S I. Recognition of original arabica civet coffee based on odor using electronic nose and machine learning[C]//2020 International Seminar on Application for Technology of Information and Communication (iSemantic). IEEE, 2020: 333-339.
    [21] To?a?ar M, Ergen B, C?mert Z, et al. A deep feature learning model for pneumonia detection applying a combination of mRMR feature selection and machine learning models[J]. Irbm, 2020, 41(4): 212-222.
    [22] Kattenborn T, Leitloff J, Schiefer F, et al. Review on Convolutional Neural Networks (CNN) in vegetation remote sensing[J]. ISPRS Journal of Photogrammetry and Remote Sensing, 2021, 173: 24-49.
    [23] Ioffe S, Szegedy C. Batch normalization: Accelerating deep network training by reducing internal covariate shift[C]//International conference on machine learning. PMLR, 2015: 448-456.
    [24] Lu L, Shin Y, Su Y, et al. Dying relu and initialization: Theory and numerical examples[J]. arXiv preprint arXiv:1903.06733, 2019.
    [25] Dubey A K, Jain V. Comparative study of convolution neural network’s relu and leaky-relu activation functions[M]//Applications of Computing, Automation and Wireless Systems in Electrical Engineering. Springer, Singapore, 2019: 873-880.
    [26] Srivastava N, Hinton G, Krizhevsky A, et al. Dropout: a simple way to prevent neural networks from overfitting[J]. The journal of machine learning research, 2014, 15(1): 1929-1958.
    相似文献
    引证文献
    网友评论
    网友评论
    分享到微博
    发 布
引用本文
分享
文章指标
  • 点击次数:258
  • 下载次数: 0
  • HTML阅读次数: 0
  • 引用次数: 0
历史
  • 收稿日期:2022-04-02
  • 最后修改日期:2022-05-07
  • 录用日期:2022-05-16
文章二维码