Artificial intelligence (AI) technology makes mobile devices become intelligent objects which can learn and act automatically. Although AI will bring great opportunities for mobile applications, little work has focused on the architecture and the interaction with the cloud. In this article, we present three existing architectures of mobile intelligence in detail and introduce its broad application prospects. Furthermore, we conduct a series of experiments to evaluate the performance of the prevalent commercial applications and intelligent frameworks. Our results show that there is a big gap between Quality of Experience (QoE) requirements and the status quo. So far, we have seen only the tip of the iceberg. We pose issues and challenges to advance the area of mobile intelligence and hope to pave the way for the forthcoming. 1
BACKGROUND AND MOTIVATION 1.1 Mobile IC apps are delay limitedEmerging Immersive Computing (IC) applications, such as virtual reality (VR) and augmented reality (AR), are changing the way human beings interact with mobile smart devices. It is well-known that object recognition and rendering are the key performance bottleneck in mobile IC systems [4,6]. To speed up computation on mobile devices, the typical approach used in current IC applications is offloading computation-intensive tasks to the cloud [5,6], or leveraging local system optimizations to accelerate IC tasks [2, 3]. However, as user's QoE requirements increase over time, * Corresponding author.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.