A Reliable, Self-Adaptive Face Identification Framework via Lyapunov Optimization
This addresses reliability issues in face identification for mobile or embedded systems, but it appears incremental as it applies Lyapunov optimization to a specific domain problem.
The paper tackles the problem of real-time face identification on resource-constrained devices by proposing a queue-aware framework that adapts the sampling rate to maximize performance while avoiding queue overflow, with preliminary simulation confirming its effectiveness.
Realtime face identification (FID) from a video feed is highly computation-intensive, and may exhaust computation resources if performed on a device with a limited amount of resources (e.g., a mobile device). In general, FID performs better when images are sampled at a higher rate, minimizing false negatives. However, performing it at an overwhelmingly high rate exposes the system to the risk of a queue overflow that hampers the system's reliability. This paper proposes a novel, queue-aware FID framework that adapts the sampling rate to maximize the FID performance while avoiding a queue overflow by implementing the Lyapunov optimization. A preliminary evaluation via a trace-based simulation confirms the effectiveness of the framework.