Search

In classification tasks, feature selection (FS) can reduce the data dimensionality and may also improve classification accuracy, both of which are commonly treated as the two objectives in FS problems. Many meta-heuristic algorithms have been applied to solve the FS problems and they perform satisfactorily when the problem is relatively simple. However, once the dimensionality of the datasets grows, their performance drops dramatically. This paper proposes a self-adaptive multi-objective genetic algorithm (SaMOGA) for FS, which is designed to maintain a high performance even when the dimensionality of the datasets grows. The main concept of SaMOGA lies in the dynamic selection of five different crossover operators in different evolution process by applying a self-adaptive mechanism. Meanwhile, a search stagnation detection mechanism is also proposed to prevent premature convergence. In the experiments, we compare SaMOGA with five multi-objective FS algorithms on sixteen datasets. According to the experimental results, SaMOGA yields a set of well converged and well distributed solutions on most data sets, indicating that SaMOGA can guarantee classification performance while removing many features, and the advantage over its counterparts is more obvious when the dimensionality of datasets grows. [ABSTRACT FROM AUTHOR]

Background: Depression is one of the most common neuropsychiatric symptoms of Alzheimer's disease (AD) which decreases the life quality of both patients and caregivers. There are currently no effective drugs. It is therefore important to explore the pathogenesis of depression in AD patients., Objective: The present study aimed to investigate the characteristics of the entorhinal cortex (EC) functional connectivity (FC) in the whole brain neural network of AD patients with depression (D-AD)., Methods: Twenty-four D-AD patients, 14 AD patients without depression (nD-AD), and 20 healthy controls underwent resting-state functional magnetic resonance imaging. We set the EC as the seed and used FC analysis. One-way analysis of variance was used to examine FC differences among the three groups., Results: Using the left EC as the seed point, there were FC differences among the three groups in the left EC-inferior occipital gyrus. Using the right EC as the seed point, there were FC differences among the three groups in the right EC-middle frontal gyrus, -superior parietal gyrus, -superior medial frontal gyrus, and -precentral gyrus. Compared with the nD-AD group, the D-AD group had increased FC between the right EC and right postcentral gyrus., Conclusion: Asymmetry of FC in the EC and increased FC between the EC and right postcentral gyrus may be important in the pathogenesis of depression in AD., (Copyright© Bentham Science Publishers; For any queries, please email at epub@benthamscience.net.)