Mushroom Quality Prediction using KNN and Ensemble Learning with Enhanced preprocessing.
Students & Supervisors
Student Authors
Supervisors
Abstract
It is important to correctly identify edible and poisonous mushrooms because many similar species can cause serious health problems if not correctly identified. Traditionally, identification of mushrooms is carried out in a time-consuming manner, which is not effective in most cases, leading to the adoption of computational methods, that have become indispens- able in the field of mushroom identification. This paper presents a powerful approach to mushroom classification that combines advanced preprocessing techniques with k-nearest neighbors and ensemble learning algorithms. Advanced techniques such as modal imputation, one-hot encoding, and z-score normalization are incorporated into the model to improve its efficiency. In the proposed approach, the k-nearest neighbor classifier, along with ensemble learning algorithms such as Random Forest and Extra Trees, is used to ensure accurate predictions in mushroom classification. The experimental findings show that the combination of advanced preprocessing techniques with hybrid machine learning algorithms significantly improves the efficiency of mushroom classification in terms of scalability and stability. The findings of the study show that the suggested approach is effective in ensuring the safe consumption of mushrooms while simultaneously promoting the automation of mushroom classification in an efficient, accurate, and stable manner.
Keywords
Publication Details
- DOI: https://doi.org/10.24432/c5959t
- Type of Publication:
- Conference Name: 2026 IEEE 2nd International Conference on Quantum Photonics, Artificial Intelligence & Networking
- Date of Conference: 16/04/2026 - 16/04/2026
- Venue: Chittagong University of Engineering and Technology (CUET), Chattogram, Bangladesh
- Organizer: IEEE Photonics society Bangladesh chapter.