DSpace Repository

An internet of things (IoT)-based optimum tea fermentation detection model using convolutional neural networks (CNNs) and majority voting techniques

Show simple item record

dc.contributor.author Kimutai, Gibson
dc.contributor.author Ngenzi, Alexander
dc.contributor.author Ramkat, Rose C
dc.contributor.author Förster, Anna
dc.date.accessioned 2023-07-21T11:56:11Z
dc.date.available 2023-07-21T11:56:11Z
dc.date.issued 2021
dc.identifier.uri 10.5194/jsss-10-153-2021
dc.identifier.uri http://ir.mu.ac.ke:8080/jspui/handle/123456789/7856
dc.description.abstract Tea (Camellia sinensis) is one of the most consumed drinks across the world. Based on processingtechniques, there are more than 15 000 categories of tea, but the main categories include yellow tea, Oolong tea,Illex tea, black tea, matcha tea, green tea, and sencha tea, among others. Black tea is the most popular amongthe categories worldwide. During black tea processing, the following stages occur: plucking, withering, cutting,tearing, curling, fermentation, drying, and sorting. Although all these stages affect the quality of the processedtea, fermentation is the most vital as it directly defines the quality. Fermentation is a time-bound process, andits optimum is currently manually detected by tea tasters monitoring colour change, smelling the tea, and tastingthe tea as fermentation progresses. This paper explores the use of the internet of things (IoT), deep convolutionalneural networks, and image processing with majority voting techniques in detecting the optimum fermentationof black tea. The prototype was made up of Raspberry Pi 3 models with a Pi camera to take real-time imagesof tea as fermentation progresses. We deployed the prototype in the Sisibo Tea Factory for training, validation,and evaluation. When the deep learner was evaluated on offline images, it had a perfect precision and accuracyof 1.0 each. The deep learner recorded the highest precision and accuracy of 0.9589 and 0.8646, respectively,when evaluated on real-time images. Additionally, the deep learner recorded an average precision and accuracyof 0.9737 and 0.8953, respectively, when a majority voting technique was applied in decision-making. From theresults, it is evident that the prototype can be used to monitor the fermentation of various categories of tea thatundergo fermentation, including Oolong and black tea, among others. Additionally, the prototype can also bescaled up by retraining it for use in monitoring the fermentation of other crops, including coffee and cocoa (1) (PDF) An internet of things (IoT)-based optimum tea fermentation detection model using convolutional neural networks (CNNs) and majority voting techniques. Available from: https://www.researchgate.net/publication/352903819_An_internet_of_things_IoT-based_optimum_tea_fermentation_detection_model_using_convolutional_neural_networks_CNNs_and_majority_voting_techniques [accessed Jul 21 2023]. en_US
dc.language.iso en en_US
dc.publisher Taylor & Francis en_US
dc.subject Tea (Camellia sinensis) en_US
dc.subject tea fermentation en_US
dc.subject Convolutional Neural Networks (CNNs) en_US
dc.subject Oolong and black tea en_US
dc.title An internet of things (IoT)-based optimum tea fermentation detection model using convolutional neural networks (CNNs) and majority voting techniques en_US
dc.type Article en_US


Files in this item

This item appears in the following Collection(s)

Show simple item record

Search DSpace


Advanced Search

Browse

My Account