implementation of several data mining strategies on electronic nose data for identifying gluten in cheese

Electronic nose is an electronic device for smell detection. the data obtained from this device are stored in the form of numbers in different columns, which are related to the data of two types of cheese namely gluten-free cheese and cheese with gluten. it is  not enough to make decisions and judge the data unless discovering the relationships and patterns between the data obtained to determine the relation of new data recorded by the device to the type of cheese, for this purpose, data mining and machine learning methods have been used in this research. data mining includes various algorithms such as classification, clustering, and obtaining association rules. to get a better result from the data, a data mining process was performed on 105 different permutations of the models, and 13 models with the highest accuracy in understanding the relationships between the data were chosen. in this research, with data mining methods, cheese with gluten and gluten-free cheese data were classified into separate categories, and a model was created to predict the type of new input data in terms of the nature of cheese (gluten-free and with gluten). with analyzing 105 permutations, finally, the best suitable model to be used for data classification using the random forest algorithm and minmaxscaler for scaling was selected with a prediction accuracy of 99.8% for both test and training datasets.

implementation of several data mining strategies on electronic nose data for identifying gluten in cheese

electronic nose is an electronic device for smell detection. the data obtained from this device are stored in the form of numbers in different columns, which are related to the data of two types of cheese namely gluten-free cheese and cheese with gluten. it is  not enough to make decisions and judge the data unless discovering the relationships and patterns between the data obtained to determine the relation of new data recorded by the device to the type of cheese, for this purpose, data mining and machine learning methods have been used in this research. data mining includes various algorithms such as classification, clustering, and obtaining association rules. to get a better result from the data, a data mining process was performed on 105 different permutations of the models, and 13 models with the highest accuracy in understanding the relationships between the data were chosen. in this research, with data mining methods, cheese with gluten and gluten-free cheese data were classified into separate categories, and a model was created to predict the type of new input data in terms of the nature of cheese (gluten-free and with gluten). with analyzing 105 permutations, finally, the best suitable model to be used for data classification using the random forest algorithm and minmaxscaler for scaling was selected with a prediction accuracy of 99.8% for both test and training datasets.