Machine Learning Algorithms for Classification of Gas Sensor Array Dataset
To measure the accuracy of the data being sensed predictive machine learning models have been used. These models take input in the form of datasets and predict the output based on them. By using a large dataset better and efficient predictive models can be designed because a large amount of data can be used to train the model. But having a larger dataset leads to a dimensionality problem. This problem is solved using Dimensionality Reduction Principal Component Analysis(PCA) algorithm. PCA helps to reduce the redundant data or correlated data present in the dataset by which dimensionality of the dataset is reduced. Classifier algorithms like K Nearest Neighbour(KNN), Logistic Regression(LR), Naive Bayes(NB), and Support Vector Machine(SVM) are used which gives output in the form of the confusion matrix. From this confusion matrix, the prediction accuracy of models is decided. From the accuracy measurements, it is found that the SVM model is more accurate(94%) in predicting the output whereas the NB model is the least accurate(60%).