Fusion: Practice and Applications

The classification of mushrooms as either deadly or edible stays a important challenge due to their similar appearances, which can lead to fatal poisonings. The primary difficulty lies in identifying complex patterns in mushroom appearances, such as cap shape, color, and gill structure, which complicate accurate classification. Traditional approaches and even some machine learning (ML) models fail to capture these subtle but important distinctions, leading to misclassifications. To address this issue, this paper proposed a One-Dimensional Convolutional Neural Network (1D-CNN) approach aimed at improving the accurate of mushroom classification. By effectively recognizing complex patterns in the mushroom data set, the proposed approach greatly improves classification accuracy. The model performance evaluated utilizing Precision, Accuracy, Recall, and F1-Score that achieved high scores of 100% across all metrics. These results highlight the strength of deep learning (DL) method, specifically 1D-CNNs, in recognizing with learning complex data patterns. This shows a clear advancement over traditional ML methods and ensemble techniques, establishing the 1D-CNN as a highly reliable tool for mushroom classification that can help reduce mushroom poisoning incidents.