Publicação

RIPENING ASSESSMENT CLASSIFICATION USING ARTIFICIAL INTELLIGENCE ALGORITHMS WITH ELECTROCHEMICAL IMPEDANCE SPECTROSCOPY DATA

Ver documento

Detalhes bibliográficos
Resumo:The increasingly growth of the world's population requires more efficient efforts to manage people's needs. One important problem lies on food distribution, its quality and sustainability throughout the chain, from the producer to the consumer's hands. It's more and more im-portant to achieve intelligent non-destructive methods to assess food quality, at the crop, stor-age, and shelves in the supermarket. This dissertation approaches an application of machine learning on impedance data from bananas to assess whether the fruit is edible or not. To fulfill the proposed objective, impedance data of 10 bananas was acquired during 32 days through electrochemical impedance spectroscopy (EIS) with a two ECG electrode disposition, using an Impedance Analyzer Adapter on an Analog Discovery 2 device. A database was produced with impedance, humidity and temperature values from each measurement. After data pre-pro-cessing, several machine learning classifiers were trained and tested for several different fea-ture combinations and data normalization methods. The XGB classifier achieved the best per-formance, with a F1-score of 98,36% and accuracy of 98,10%. This study can be extrapolated to other fruits and vegetables to allow a better management in the food industry, improving food quality and preventing waste.
Autores principais:Freitas, Eduardo Gonçalves
Assunto:Food waste Sustainability Fruit Banana Electrochemical Impedance Spectroscopy EIS
Ano:2023
País:Portugal
Tipo de documento:dissertação de mestrado
Tipo de acesso:acesso aberto
Instituição associada:Universidade Nova de Lisboa
Idioma:inglês
Origem:Repositório Institucional da UNL
Descrição
Resumo:The increasingly growth of the world's population requires more efficient efforts to manage people's needs. One important problem lies on food distribution, its quality and sustainability throughout the chain, from the producer to the consumer's hands. It's more and more im-portant to achieve intelligent non-destructive methods to assess food quality, at the crop, stor-age, and shelves in the supermarket. This dissertation approaches an application of machine learning on impedance data from bananas to assess whether the fruit is edible or not. To fulfill the proposed objective, impedance data of 10 bananas was acquired during 32 days through electrochemical impedance spectroscopy (EIS) with a two ECG electrode disposition, using an Impedance Analyzer Adapter on an Analog Discovery 2 device. A database was produced with impedance, humidity and temperature values from each measurement. After data pre-pro-cessing, several machine learning classifiers were trained and tested for several different fea-ture combinations and data normalization methods. The XGB classifier achieved the best per-formance, with a F1-score of 98,36% and accuracy of 98,10%. This study can be extrapolated to other fruits and vegetables to allow a better management in the food industry, improving food quality and preventing waste.