Water quality plays an important role in sustainable agriculture. Water quality also affects the quality and quantity of fishery production. In ornamental fish cultivation, water quality influences not only production, but also the shape and color of the fish. To achieve optimal results, water quality parameters need to be maintained. Manually monitoring water quality parameters faces many challenges such as being time-consuming and not providing real-time data. This study investigated the application of Artificial Neural Networks (ANNs) in classifying water quality status. This status is based on data collected using sensors in an Internet of Things (IoT)-based monitoring system. The dataset comprised five key parameters: pH, temperature, ammonia, total dissolved solids (TDS), and total suspended solids (TSS). This data was collected from aquariums cultivating the Denison barb (Sahyadria denisonii). Data preprocessing was performed using feature standardization. This aims to improve model performance. The ANN model was constructed with two hidden layers (32 and 16 neurons). This model was trained using the Adam optimizer, with categorical cross-entropy as the loss function. The dataset was divided into 80% for training and 20% for testing. The trained ANN model achieved an accuracy of 99.95%. It has low false-positive and false-negative rates. These results demonstrate the effectiveness of ANN in predicting water quality status using sensor-based data. This suggests its potential for real-time monitoring and decision-making support in small-scale ornamental fish aquaculture.