This paper presents an IoT-based automatic water quality monitoring system optimized using a neural network. The system aims to address the issue of water contamination and scarcity, which pose significant health risks. The proposed system integrates multiple sensors (temperature, pH, turbidity, and TDS) to measure various water parameters. These sensors are connected to an Arduino microcontroller, which processes the sensor data and transmits it to a cloud database via Wi-Fi. The cloud-based database stores and analyzes the data for further processing. The core of the system is an optimized neural network (ANN) classifier, which predicts water quality based on the collected data. The performance of the feed-forward neural network is enhanced using a hybrid Genetic Algorithm-Particle Swarm Optimization (GA-PSO) algorithm. This optimization improves the accuracy of the ANN classifier, achieving 91% accuracy compared to 70% with traditional methods. The optimized ANN also shows significant improvements in precision and recall. The system's workflow is divided into two stages: (1) real-time water quality prediction using an Arduino-based system, and (2) data storage and analysis in a cloud-based server. The proposed system ensures continuous monitoring of water quality, providing remote predictions and ensuring the safety of drinking water sources. The technology can be extended to monitor seawater quality and support water distillation centers in coastal areas. The paper includes a literature review of existing water quality monitoring systems, highlighting the importance of IoT and sensor networks in environmental applications. It also discusses the use of various sensors and microcontrollers, such as Arduino and Raspberry Pi, in water quality monitoring systems. The authors conclude that their proposed system is efficient, low-cost, and effective in predicting water quality, making it suitable for widespread implementation.This paper presents an IoT-based automatic water quality monitoring system optimized using a neural network. The system aims to address the issue of water contamination and scarcity, which pose significant health risks. The proposed system integrates multiple sensors (temperature, pH, turbidity, and TDS) to measure various water parameters. These sensors are connected to an Arduino microcontroller, which processes the sensor data and transmits it to a cloud database via Wi-Fi. The cloud-based database stores and analyzes the data for further processing. The core of the system is an optimized neural network (ANN) classifier, which predicts water quality based on the collected data. The performance of the feed-forward neural network is enhanced using a hybrid Genetic Algorithm-Particle Swarm Optimization (GA-PSO) algorithm. This optimization improves the accuracy of the ANN classifier, achieving 91% accuracy compared to 70% with traditional methods. The optimized ANN also shows significant improvements in precision and recall. The system's workflow is divided into two stages: (1) real-time water quality prediction using an Arduino-based system, and (2) data storage and analysis in a cloud-based server. The proposed system ensures continuous monitoring of water quality, providing remote predictions and ensuring the safety of drinking water sources. The technology can be extended to monitor seawater quality and support water distillation centers in coastal areas. The paper includes a literature review of existing water quality monitoring systems, highlighting the importance of IoT and sensor networks in environmental applications. It also discusses the use of various sensors and microcontrollers, such as Arduino and Raspberry Pi, in water quality monitoring systems. The authors conclude that their proposed system is efficient, low-cost, and effective in predicting water quality, making it suitable for widespread implementation.