Conor Muldoon | Searcharxiv

arXiv2025

Scalable and Energy-Efficient Predictive Data Collection in Wireless Sensor Networks with Constructive Interference

A new class of Wireless Sensor Network has emerged whereby multiple nodes transmit data simultaneously, exploiting constructive interference to enable data collection frameworks with low energy usage and latency. This paper presents STAIR (Spatio-Temporal Activation for Intelligent Relaying), a scalable, resilient framework for Wireless Sensor Networks that leverages constructive interference and operates effectively under stringent resource constraints. Using constructive interference requires all nodes to transmit the same packet at the same time, thus, only one source node can send data per time slot. STAIR uses coarse-grained topology information to flood a selected subset of the network, relaying sensor readings from individual nodes during their allocated time slots. A submodular optimisation algorithm with proven quality bounds determines near-optimal sensor activation locations and times, aiming to minimise the sum of mean squared prediction errors from a multiple multivariate linear regression model, which is used to estimate values at unselected locations and times. This framework has been extensively validated on a real-world testbed deployment.

cs.NI↗

arXiv2022

Mining Explainable Predictive Features for Water Quality Management

With water quality management processes, identifying and interpreting relationships between features, such as location and weather variable tuples, and water quality variables, such as levels of bacteria, is key to gaining insights and identifying areas where interventions should be made. There is a need for a search process to identify the locations and types of phenomena that are influencing water quality and a need to explain how the quality is being affected and which factors are most relevant. This paper addresses both of these issues. A process is developed for collecting data for features that represent a variety of variables over a spatial region and which are used for training models and inference. An analysis of the performance of the features is undertaken using the models and Shapley values. Shapley values originated in cooperative game theory and can be used to aid in the interpretation of machine learning results. Evaluations are performed using several machine learning algorithms and water quality data from the Dublin Grand Canal basin.

cs.AI↗