TY - GEN
T1 - A food recognition and tracking system for diabetics in the middle east
AU - Usman, Muhammad
AU - Ahmad, Kashif
AU - Qaraqe, Marwa
N1 - Publisher Copyright:
© 2019 IEEE.
PY - 2019/10
Y1 - 2019/10
N2 - The concerns for a healthier diet are increasing day by day, especially in diabetics wherein the aim of healthier diet can only be achieved by keeping a track of daily food intake and glucose-level. As a consequence, there is an ever-increasing need of automatic tools able to help diabetics to manage their diet and also help physicians to better analyze the effects of various types of food on the glucose-level of diabetics. In this paper, we propose an intelligent food recognition and tracking system for diabetics, which is potentially an essential part of a mobile application that we propose to couple food intake with the blood glucose-level using glucose measuring sensors. Being an essential component of the application, for food recognition we rely on several feature extraction and classification techniques individually and jointly utilized using an early and two different late fusion techniques, namely (i) Particle Swarm Optimization (PSO) based fusion and (iii) simple averaging. Moreover, we also evaluate the performance of several deep features. In addition, we collect a large-scale dataset containing images from several types of local Middle-Eastern food, which is intended to become a powerful support tool for future research in the domain.
AB - The concerns for a healthier diet are increasing day by day, especially in diabetics wherein the aim of healthier diet can only be achieved by keeping a track of daily food intake and glucose-level. As a consequence, there is an ever-increasing need of automatic tools able to help diabetics to manage their diet and also help physicians to better analyze the effects of various types of food on the glucose-level of diabetics. In this paper, we propose an intelligent food recognition and tracking system for diabetics, which is potentially an essential part of a mobile application that we propose to couple food intake with the blood glucose-level using glucose measuring sensors. Being an essential component of the application, for food recognition we rely on several feature extraction and classification techniques individually and jointly utilized using an early and two different late fusion techniques, namely (i) Particle Swarm Optimization (PSO) based fusion and (iii) simple averaging. Moreover, we also evaluate the performance of several deep features. In addition, we collect a large-scale dataset containing images from several types of local Middle-Eastern food, which is intended to become a powerful support tool for future research in the domain.
KW - CNNs
KW - Continuous Glucose Monitoring
KW - Deep Features
KW - Diabetes
KW - Food Recognition
KW - Particle Swarm Optimization
UR - http://www.scopus.com/inward/record.url?scp=85084665705&partnerID=8YFLogxK
U2 - 10.1109/ISC246665.2019.9071759
DO - 10.1109/ISC246665.2019.9071759
M3 - Conference contribution
AN - SCOPUS:85084665705
T3 - 5th IEEE International Smart Cities Conference, ISC2 2019
SP - 218
EP - 222
BT - 5th IEEE International Smart Cities Conference, ISC2 2019
PB - Institute of Electrical and Electronics Engineers Inc.
T2 - 5th IEEE International Smart Cities Conference, ISC2 2019
Y2 - 14 October 2019 through 17 October 2019
ER -