English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Tools annual

Global: Zendy Free Plan

Global: Zendy Tools monthly

Global: Zendy Plus monthly

Rapid recognition of Japanese sake quality (flavor and types of sake) is an important factor affecting consumers’ preference, quality control, as well as fraud avoidance in sake labelling. This study attempted to find a prediction model that could precisely predict sake flavor grades (Q1, Q2, and Q3) and to discover a classification model that could precisely differentiate the types of sake, specifically between  Junmaishu  and  Honjozoshu . Twelve physicochemical properties of 407 sake were analyzed and sensory evaluation of 260 sake from 510 professional evaluators were further collected. The physicochemical properties, data, and sensory evaluation of 260 sake were utilized to predict sake flavor grades, while physicochemical properties data of 407 sake were used to classify the type of sake. Artificial neural network (ANN—including multilayer perceptron classifier—MLP classifier), random forest, support vector machine, and k-nearest neighbor were implemented to achieve the objective. ANN gained an accuracy of 91.14% and precision of Q1 87.5%, Q2 93.55% and Q3 77.78% for sake flavor grades prediction. As for types of sake classification, MLP classifier gained 100% accuracy as well as 100% precision of  Junmaishu  and  Honjozoshu.  In general, the physiochemical properties combined with ANN can recognize the quality of Japanese sake.

Recognition of Japanese Sake Quality Using Machine Learning Based Analysis of Physicochemical Properties