The exponential expansion in the number of smart devices in the burgeoning Internet of Things (IoT) is driving the growing demand for effective storage techniques. Cloud computing has shown to be an excellent alternative for storing and processing enormous amounts of data thus far. Cloud computing, on the other hand, is predicted to be unable to successfully handle a significant number of IoT devices in the coming years due to bandwidth constraints. Fog computing is a novel technology that is supposed to solve many of the problems associated with large-scale networks on the Internet of Things. Fog computing brings high-quality cloud services closer to mobile users. To overcome all the existing drawbacks, this study improves QoS using fog computing based on Sigmoid Neural Network Clustering (SNNC) and Entropy-Based Scheduling (EBS). The work of the IoT sensors is to collect all the data and send them to the fog computing tier. After that, fog computing performs score value calculation for each fog node based on SNNC as well as EBS. Here, the data and information collected by the edge devices are analyzed in this tier. Cloud Computing manages the various actions that are to be performed by the system. A component of the monitoring runs on the sensors which enable the sensors to collect data and send it to the fog layer also the cloud computing tier constantly supervises the system. The experimental results QoS show that our proposed strategy outperforms the traditional method.