Quantum Fuzzy Inference Systems: Implementation and a Case Study on Sleep Apnea Detection

Abstract

[Abstract]: Fuzzy Inference Systems (FIS) are a powerful tool for problems whose domain can be formally defined thanks to extracting knowledge from experts. These systems provide certain capabilities that current trend technologies do not, but its use has decreased in the past years due to the popularity of Machine Learning methods. In this paper, we revisit FIS through the perspective of Quantum Computing, an approach to make this model more powerful, thanks to superposition and entanglement. We present a new method for implementing FIS with quantum circuits, named Quantum Fuzzy Inference Systems, providing the definitions for the logical operators and implication. We propose a practical application in sleep medicine diagnosis, more specifically for the detection of apneic events. Our results show that we are able to replicate the behavior of the classical model using the quantum proposal, up to a similarity of 99.97%. We conclude on the contribution of this work towards the development of hybrid algorithms and uncertainty management, and pose some possible lines of future work on extending the inference process and its optimization.