Actively Semi-Supervised Deep Rule-based Classifier Applied to Adverse Driving Scenarios

By Eduardo Almeida Soares, Plamen Parvanov Angelov, Bruno Costa, Marcos Castro. 2019

16 citations recorded by the source corpus.

This paper presents an actively semi-supervised multi-layer neuro-fuzzy modeling method, ASSDRB, to classify different lighting conditions for driving scenes. ASSDRB is composed of a massively parallel ensemble of AnYa type 0-order fuzzy rules. It uses a recursive learning algorithm to update its structure when new data items are provided and, therefore, is able to cope with nonstationarities. Different lighting conditions for driving situations are considered in the analysis, which is used by self-driving cars as a safety mechanism. Differently from mainstream Deep Neural Networks approaches, the ASSDRB is able to learn from unseen data. Experiments on different lighting conditions for driving scenes, demonstrated that the deep neuro-fuzzy modeling is an efficient framework for these challenging classification tasks. Classification accuracy is higher than those produced by alternative machine learning methods. The number of algebraic calculations for the present method are significantly smaller and, therefore, the method is significantly faster than common Deep Neural Networks approaches. Moreover, DRB produced transparent AnYa fuzzy rules, which are human interpretable.

Subfields: Artificial Intelligence, Automotive Engineering, Computer Vision and Pattern Recognition

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

In Automotive Engineering

In Computer Vision and Pattern Recognition

Citations in the corpus

Towards Explainable Deep Neural Networks (xDNN) (2019, neutral): “For comparison, our earlier version of deep rule-based models, called DRB [17] also produced a high accuracy and was trained a bit faster, but ended up with 521 prototypes (on average 75 prototypes per class) [26].”
Explainable artificial intelligence: an analytical review (2021, background): “Recently, examples of prototype-based approaches were published in which XAI was used for understanding the visual scene (Soares et al., 2019) and the situation awareness of a self-driving car on a highway/motorway/autobahn through the so-called vector of affordance indicators (relative velocities a”
Novelty Detection and Learning from Extremely Weak Supervision (2019, methodology): “Then the m-σ rule is applied, for detailed explanation about the m-σ please refer to [20].”
Continual Learning for Real-World Autonomous Systems: Algorithms, Challenges and Frameworks (2021, background): “15 Human understandable fuzzy rule (Example) [29] Fig.”