Search for: All records

Real-time cyber-physical systems (CPS) rely on Perception-Cognition-Actuation (PCA) pipelines to enable autonomous observation, decisionmaking, and action execution. Closed-loop PCA systems utilize feedback-driven control to iteratively adapt actions in response to real-time environmental changes whereas open-loop PCA systems execute single actions without iterative feedback. The overall performance of these systems is inherently tied to the models selected for each pipeline component. Recent advancements in neural networks, particularly for perception tasks, have substantially enhanced CPS capabilities but have introduced significant complexity into the PCA pipeline. While traditional research [1] often evaluates perception models in static, controlled settings, it fails to account for the cascading latency and accuracy trade-offs that manifest across interconnected PCA modules in dynamic, real-time applications. Additionally, the proliferation of distributed device-edge-cloud architectures [2] has expanded computational possibilities but introduced new challenges in balancing latency and accuracy with resource constraints. The holistic impact of model selection, deployment platforms, and network conditions on application performance in real-time scenarios remains under-explored. 

This paper investigates the challenges posed by delays in Closed-Loop Sense-Act Systems in the context of Adversarial Internet of Things (IoT) applications. Prior work focused on studying the impact of delays on a single resource-constrained platform. To capitalize on the capabilities of different computing platforms, this work investigates the adaptation of control placement to optimize application performance in distributed settings. An Adaptive Control Placement (ACP) strategy is introduced, which dynamically switches between a local controller with lower accuracy and a cloud controller with higher accuracy based on network dynamics, optimizing overall application performance. The effectiveness of the ACP strategy is evaluated using a simulated Vehicle Following application in the PyBullet simulator. The results demonstrate that in terms of a time-to-complete (TTC) metric, the ACP strategy consistently outperforms strategies that use a fixed combination of controller type and location (e.g., PID at Local and MPC at Cloud) across various deadline scenarios. 

Pervasive sensing has enabled continuous monitoring of user physiological state through mobile and wearable devices, allowing for large scale user studies to be conducted, such as those found in mHealth. However, current mHealth studies are limited in their ability of allowing users to express their privacy preferences on the data they share across multiple entities involved in a research study. In this work, we present mPolicy, a privacy policy language for study participants to express the context-aware and data-handling policies needed for mHealth. In addition, we provide a privacy-adaptive policy creation mechanism for byproduct data (such as motion inferences). Lastly, we create a software library called privLib for implementing parsing, enforcement, and policy creation on byproduct data for mPolicy. We evaluate the latency overhead of these operations, and discuss future improvements for scaling to realistic mHealth scenarios.