Optimizing Artificial Neural Networks Using Levy- Chaotic Mapping on Wolf Pack Optimization Algorithm for Detect Driving Sleepiness

Artificial Neural Networks (ANNs) are utilized to solve a variety of problems in many domains. In this type network, training and selecting parameters that define networks architecture play an important role enhancing the accuracy network's output; Therefore, Prior training, those must be optimized. Grey Wolf Optimizer (GWO) has been considered one efficient developed approaches Swarm Intelligence area is used real-world optimization problems. However, GWO still faces problem slump local optimums some places due insufficient diversity. This paper proposes novel algorithm Levy Flight- Chaotic Chen mapping on Pack Algorithm Network. It efficiently exploits search regions detect driving sleepiness balance exploration exploitation operators, which implied features any stochastic algorithm. Due lack dataset availability, 15 participants collected from scratch evaluate proposed algorithm's performance. The results show achieves 99.3%. Index Terms— Electrooculography, drowsiness, neural network (NN), grey wolf optimizer (GWO), levy flight distribution, chaotic map.