Reliable Extraction of Semantic Information and Rate of Innovation Estimation for Graph Signals

TL;DR

This paper introduces a robust framework for extracting semantic information from graph-structured signals and detecting innovation events, enhancing reliability in semantic signal processing for sensor networks.

Contribution

It presents a novel hierarchical graph-based framework with a time integration method, graph-edit-distance metric, and HMM for improved semantic signal extraction and innovation detection.

Findings

Enhanced fidelity of ML outputs through time integration

Effective detection of semantic innovation events

Reliable graph signal smoothing with HMM

Abstract

Semantic signal processing and communications are poised to play a central part in developing the next generation of sensor devices and networks. A crucial component of a semantic system is the extraction of semantic signals from the raw input signals, which has become increasingly tractable with the recent advances in machine learning (ML) and artificial intelligence (AI) techniques. The accurate extraction of semantic signals using the aforementioned ML and AI methods, and the detection of semantic innovation for scheduling transmission and/or storage events are critical tasks for reliable semantic signal processing and communications. In this work, we propose a reliable semantic information extraction framework based on our previous work on semantic signal representations in a hierarchical graph-based structure. The proposed framework includes a time integration method to increase fidelity of ML outputs in a class-aware manner, a graph-edit-distance based metric to detect innovation events at the graph-level and filter out sporadic errors, and a Hidden Markov Model (HMM) to produce smooth and reliable graph signals. The proposed methods within the framework are demonstrated individually and collectively through simulations and case studies based on real-world computer vision examples.