Quality of Service (QoS) in the Internet of Things (IoT)-enabled Wireless Sensor Networks (WSNs) poses significant challenges due to the diverse constraints inherent in sensor resources and the varied requirements of applications operating within these networks. This paper introduces a novel framework called Neuro-Fuzzy Double Optimization (NFDO) approaches for enhancing QoS in IoT-enabled WSNs with a focus on enhancing QoS metrics in turn improves network lifetime and energy consumption. The main objectives of this framework are two-fold: Efficient Cluster Head Selection (first phase) and Path Optimization (second phase). Aquila optimizer in the first phase works by estimating several factors energy levels, node attributes, and distance to the sink node to select the cluster heads optimally and reliably. Levy Flight Optimization path optimization algorithm to improve further the QoS of the integrated network, the second phase introduces the LFO algorithm. The algorithm is mainly concerned with identifying the optimal packet routing paths. The reliability of each path is decided using several parameters/deciding factors including, hop count, end-to-end delay, packet loss rate, remaining energy, and connection stability. The proposed framework was subjected to simulation testing to validate its applicability. The framework’s subsequent usage and comparison with the existing integrated network-QoS-determining methods revealed the following outcomes. For QoS evaluation metrics presented in Packet delivery rate, packet loss rate, end-to-end delay, average energy consumption, network latency, reliability, and fault tolerance. The proposed framework offers a better result when compared to other methods. The packet delivery rate was increased by 17% and a 10% reduction in the packet loss rate when compared to other methods.