Feature selection can efficiently improve the accuracy of classification and reduce the measurement, storage and computation demands, and thus it has been applied in biomedical research increasingly. Considering the non-deterministic polynomial-time hard characteristic of feature selection, meta-heuristics are introduced into feature selection in biomedicine on account of their excellent global search ability. However, most of biomedical problems are characterized by high dimensionality, which is a challenge for feature selection methods based on meta-heuristics due to the curse of dimensionality. Thus, six meta-heuristics, that is, a genetic algorithm, particle swarm optimization, ant colony optimization, harmony search, differential evolution, and quantum-inspired evolutionary algorithm, which are widely studied in the meta-heuristic community, are introduced into feature selection in this paper and the performance of the algorithms is analysed and compared with each other for solving feature selection in biomedicine effectively. To evaluate the search ability of the algorithms fairly and exactly, a set of feature selection benchmark problems are designed and yielded for the performance tests. The experimental results show that all the meta-heuristics are powerful enough to achieve the ideal results on low-dimensional feature selection problems, while it is essential to choose a proper algorithm for the high-dimensional ones.

Fault detection in chemical production processes is difficult because of the amount of data that needs to be analysed and the absence of fault data. This paper uses support vector machines (SVMs) to diagnose faults, as it fits the small sample problem. To eliminate system disturbances and noise from the high levels of data, it then combines SVMs with a novel quantum ant colony optimization (QACO) algorithm to select the fault features. The proposed method is then tested using the benchmark Tennessee Eastman Process and shown to be effective. In particular, it is demonstrated that QACO and SVMs can find the essential fault variables exactly, and will greatly improve the fault diagnosis performance of SVMs for a complex chemical process.