Wireless Sensor Networks are a growing technology used in many applications, such as Environmental monitoring, Healthcare Systems, Military Applications, etc. Service disruption attacks are a potential risk in Wireless Sensor Networks. Typically, the sensor nodes in the Wireless Sensor Network function with a limited battery capacity, which makes it easy for the attacker to destroy the network. The major DoS attacks in WSN include the blackhole, grayhole, flooding, and scheduling attacks. This paper presents a Machine Learning-based Intrusion Detection System (IDS) for Denial of Service (DoS) attacks detection in Wireless Sensor Networks, which introduces a novel feature selection method that integrates the Grey Wolf Optimizer (GWO) and Whale Optimization Algorithm (WOA). The Grey Wolf Optimizer (GWO) mimics the hunting behaviour of grey wolves, and its leadership hierarchy excels at exploration. The Whale Optimization Algorithm (WOA), designed following the circular hunting mechanism of humpback whales, is highly effective in exploitation and local search. This hybrid metaheuristic algorithm effectively selects an optimum set of features, and a Random Forest classifier, which achieves an accuracy of 99.52%, Precision of 99.52%, recall of 99.52% and an F1-Score of 99.51%. From the observed evaluation, it can be stated that the proposed hybrid model gives an optimized results.