SAFE-OCC: A Novelty Detection Framework for Convolutional Neural Network Sensors and its Application in Process Control

02/03/2022
by   Joshua L. Pulsipher, et al.
8

We present a novelty detection framework for Convolutional Neural Network (CNN) sensors that we call Sensor-Activated Feature Extraction One-Class Classification (SAFE-OCC). We show that this framework enables the safe use of computer vision sensors in process control architectures. Emergent control applications use CNN models to map visual data to a state signal that can be interpreted by the controller. Incorporating such sensors introduces a significant system operation vulnerability because CNN sensors can exhibit high prediction errors when exposed to novel (abnormal) visual data. Unfortunately, identifying such novelties in real-time is nontrivial. To address this issue, the SAFE-OCC framework leverages the convolutional blocks of the CNN to create an effective feature space to conduct novelty detection using a desired one-class classification technique. This approach engenders a feature space that directly corresponds to that used by the CNN sensor and avoids the need to derive an independent latent space. We demonstrate the effectiveness of SAFE-OCC via simulated control environments.

READ FULL TEXT

page 6

page 8

page 9

page 12

page 17

page 22

page 29

research
01/24/2019

One-Class Convolutional Neural Network

We present a novel Convolutional Neural Network (CNN) based approach for...
research
03/30/2020

OCmst: One-class Novelty Detection using Convolutional Neural Network and Minimum Spanning Trees

We present a novel model called One Class Minimum Spanning Tree (OCmst) ...
research
01/16/2018

Learning Deep Features for One-Class Classification

We propose a deep learning-based solution for the problem of feature lea...
research
01/29/2019

MgNet: A Unified Framework of Multigrid and Convolutional Neural Network

We develop a unified model, known as MgNet, that simultaneously recovers...
research
08/23/2022

Real-Time Sonar Fusion for Layered Navigation Controller

Navigation in varied and dynamic indoor environments remains a complex t...
research
12/22/2014

Half-CNN: A General Framework for Whole-Image Regression

The Convolutional Neural Network (CNN) has achieved great success in ima...
research
03/31/2022

An image classification approach for hole detection in wireless sensor networks

Hole detection is a crucial task for monitoring the status of wireless s...

Please sign up or login with your details

Forgot password? Click here to reset