A Comparative Study of Food Intake Detection Using Artificial Neural Network and Support Vector Machine

• Published in: 2013 12th International Conference on Machine Learning and Applications Vol. 1; p. 153
• Main Authors: Farooq, Muhammad, Fontana, Juan M., Boateng, Akua F., Mccrory, Megan A., Sazonov, Edward
• Format: Conference Proceeding
• Language: English
• Published: IEEE 01.12.2013
• Subjects: Accuracy; Artificial neural networks; chewing; eating disorder; Food intake detection; Frequency-domain analysis; Kernel; Monitoring; Neural Net; Neurons; Support vector machines; SVM; wearable sensors
• DOI: 10.1109/ICMLA.2013.33

In Machine Learning applications, the selection of the classification algorithm depends on the problem at hand. This paper provides a comparison of the performance of the Support Vector Machine (SVM) and the Artificial Neural Network (ANN) for food intake detection. A combination of time domain (TD) and frequency domain (FD) features, extracted from signals captured using a jaw motion sensor, were used to train both types of classifiers. Data were collected from 12 subjects in free-living for a period of 24-hrs under unrestricted conditions. ANN with a different number of hidden layer neurons and SVMs with different kernels were trained using a leave one out cross validation scheme. ANN achieved an average accuracy of 86.86 ± 6.5 % whereas SVM (with linear kernel) achieved an average classification accuracy of 81.93 ± 9.22 %. Data collected from an independent subject in a separate study were used to evaluate the performance of these classifiers in-terms of the number of meals detected per day resulting in an accuracy of 72.72% for ANN and 63.63% for SVM. The results suggest that ANN may perform better than SVM for this specific problem.