@article{Pfisterer_Amelard_Wong_2018, title={Intuitive Data-Driven Visualization of Food Relatedness via t-Distributed Stochastic Neighbor Embedding}, volume={4}, url={https://openjournals.uwaterloo.ca/index.php/vsl/article/view/330}, abstractNote={<p>The relationship between diet and health is important, yet difficult<br>to study in practice. Dietary pattern analysis is one method for<br>investigating this link; having more variety in diet tends to be bene-<br>ficial and a score can be generated based on a heuristic approach<br>to food intake habits. We aim to enhance the intuition behind<br>these food scores by creating an intuitive data-driven visualization<br>of food relatedness by leveraging t-distributed stochastic neighbor<br>embedding (t-SNE). More specifically, by performing t-SNE anal-<br>ysis in a controlled manner to project the high-dimensional nutri-<br>tional information of food items into a lower dimensional food sim-<br>ilarity space, the natural clustering of foods based on the underly-<br>ing nutritional composition becomes visually observable. The effi-<br>cacy of this data-driven approach for visualizing food relatedness<br>was investigated on a total of 8549 food item entries in the USDA<br>food composition database, with the results showing considerable<br>promise as a tool for gaining important nutritional insights. This is<br>the first step toward providing a novel method to enhance dietary<br>pattern analysis with additional context and insight into food intake<br>habits based on the inherent nutritional content of the foods con-<br>sumed.</p>}, number={1}, journal={Journal of Computational Vision and Imaging Systems}, author={Pfisterer, Kaylen J. and Amelard, Robert and Wong, Alexander}, year={2018}, month={Dec.}, pages={3} }