TY - GEN
T1 - An Inconsistency-Based Hybrid Feature Selection Approach for Enhancing Medical Classification Modeling
AU - Zhao, Rong
AU - ALDharhani, Ghassan Saleh
AU - Ratnavelu, Kuru
AU - Thambiayya, Sathiyaraj
AU - Jasser, Muhammed Basheer
AU - Majeed, Anwar P.P.Abdul
AU - Luo, Yang
N1 - Publisher Copyright:
© The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.
PY - 2025
Y1 - 2025
N2 - Artificial Intelligence is an essential tool for early disease recognition and supporting patient condition monitoring in the future. Timely and exact conclusions about the type of disease are significant for treatment and life extension. A combination of classification and feature selection algorithms can effectively handle complex datasets in the medical field and improve the accuracy of disease diagnosis and treatment. In this paper, we propose a new hybrid feature selection algorithm that uses inconsistency metrics as a filter method for the first step, and then feeds the resulting dataset into a wrapper method, which ultimately results in a reduced dataset. The proposed HFSIM algorithm is tested on five datasets in the medical domain from Kaggle. The obtained feature subsets are verified on three classification algorithms, KNN, LR and RF of machine learning to validate the effectiveness of the proposed algorithm. The experimental results show that the proposed algorithm obtains feature subsets with low dimensionality on most of the datasets and also has high classification accuracy after testing on the classifiers.
AB - Artificial Intelligence is an essential tool for early disease recognition and supporting patient condition monitoring in the future. Timely and exact conclusions about the type of disease are significant for treatment and life extension. A combination of classification and feature selection algorithms can effectively handle complex datasets in the medical field and improve the accuracy of disease diagnosis and treatment. In this paper, we propose a new hybrid feature selection algorithm that uses inconsistency metrics as a filter method for the first step, and then feeds the resulting dataset into a wrapper method, which ultimately results in a reduced dataset. The proposed HFSIM algorithm is tested on five datasets in the medical domain from Kaggle. The obtained feature subsets are verified on three classification algorithms, KNN, LR and RF of machine learning to validate the effectiveness of the proposed algorithm. The experimental results show that the proposed algorithm obtains feature subsets with low dimensionality on most of the datasets and also has high classification accuracy after testing on the classifiers.
KW - Classification
KW - Hybrid Feature Selection
KW - Inconsistency Measure
KW - Machine Learning
KW - Medical Datasets
UR - http://www.scopus.com/inward/record.url?scp=105002709917&partnerID=8YFLogxK
U2 - 10.1007/978-981-96-3949-6_55
DO - 10.1007/978-981-96-3949-6_55
M3 - Conference Proceeding
AN - SCOPUS:105002709917
SN - 9789819639489
T3 - Lecture Notes in Networks and Systems
SP - 662
EP - 671
BT - Selected Proceedings from the 2nd International Conference on Intelligent Manufacturing and Robotics, ICIMR 2024 - Advances in Intelligent Manufacturing and Robotics
A2 - Chen, Wei
A2 - Ping Tan, Andrew Huey
A2 - Luo, Yang
A2 - Huang, Long
A2 - Zhu, Yuyi
A2 - PP Abdul Majeed, Anwar
A2 - Zhang, Fan
A2 - Yan, Yuyao
A2 - Liu, Chenguang
PB - Springer Science and Business Media Deutschland GmbH
T2 - 2nd International Conference on Intelligent Manufacturing and Robotics, ICIMR 2024
Y2 - 22 August 2024 through 23 August 2024
ER -