A virtualization mechanism for real-time multimedia-assisted mobile food recognition application in cloud computing

The integration of multimedia-assisted healthcare systems with could-computing services and mobile technologies has led to increased accessibility for healthcare providers and patients. Utilizing cloud computing infrastructures and virtualization technologies allows for the transformation of traditional healthcare systems that demand manual care and monitoring to more salient, automatic and cost effective systems. The goal of this paper is to develop a multimedia-assisted mobile healthcare application using cloud-computing virtualization technologies. We consider calorie measurement as an example healthcare application that can benefit from cloud-computing virtualization technology. The key functionalities of our application entail image segmentation, image processing and deep learning algorithms for food classification and recognition. Client side devices (e.g. smartphones, tablets etc.) have limitations in handling time sensitive and computationally intensive algorithms pertained to our application. Image processing and deep learning algorithms, used in food recognition and calorie measurement, consume devices’ batteries quickly, which is inconvenient for the user. It is also very challenging for client side devices to scale for large number of data and images, as needed for food recognition. The entire process is time-consuming and inefficient and discomforting from users’ perspective and may deter them from using the application. In this paper, we address these challenges by proposing a virtualization mechanism in cloud computing that utilizes the Android architecture. Android allows for parting an application into activities run by the front-end user and services run by the back-end tasks. In the proposed virtualization mechanism, we use both the hosted and the hypervisor models to publish our Android-based food recognition and calorie measurement application in the cloud. By so doing, the users of our application can control their virtual smartphone operations through a dedicated client application installed on their smartphones, while the processing of the application continue to run on the virtual Android image even if the user is disconnected due to any unexpected event. We have performed several experiments to validate our mechanism. Specifically, we have run our deep learning and image processing algorithms for food recognition on different configuration platforms on both the cloud and local server connected to the mobile. The results show that the accuracy of the system with the virtualization mechanism is more than 94.33 % compared to 87.16 % when we run the application locally. Also, with our virtualization mechanism the results are processed 49 % faster than the case of running the application locally