This paper proposes a feature selection method that is effective in distinguishing colorectal cancer patients from normal individuals using K-means clustering and the modified harmony search algorithm. As the genetic cause of colorectal cancer originates from mutations in genes, it is important to classify the presence or absence of colorectal cancer through gene information. The proposed methodology consists of four steps. First, the original data are Z-normalized by data preprocessing. Candidate genes are then selected using the Fisher score. Next, one representative gene is selected from each cluster after candidate genes are clustered using K-means clustering. Finally, feature selection is carried out using the modified harmony search algorithm. The gene combination created by feature selection is then applied to the classification model and verified using 5-fold cross-validation. The proposed model obtained a classification accuracy of up to 94.36%. Furthermore, on comparing the proposed method with other methods, we prove that the proposed method performs well in classifying colorectal cancer. Moreover, we believe that the proposed model can be applied not only to colorectal cancer but also to other gene-related diseases.

In this study, we propose a method to automatically find features from a dataset that are effective for classification or prediction, using a new method called multi-agent reinforcement learning and a guide agent. Each feature of the dataset has one of the main and guide agents, and these agents decide whether to select a feature. Main agents select the optimal features, and guide agents present the criteria for judging the main agents’ actions. After obtaining the main and guide rewards for the features selected by the agents, the main agent that behaves differently from the guide agent updates their Q-values by calculating the learning reward delivered to the main agents. The behavior comparison helps the main agent decide whether its own behavior is correct, without using other algorithms. After performing this process for each episode, the features are finally selected. The feature selection method proposed in this study uses multiple agents, reducing the number of actions each agent can perform and finding optimal features effectively and quickly. Finally, comparative experimental results on multiple datasets show that the proposed method can select effective features for classification and increase classification accuracy.

In this study, we propose a model for classifying normal and abnormal sounds by extracting characteristics from abnormal heart sounds in which normal and symbolic murmurs appear. Heart sound data obtained through an electronic stethoscope are converted into mel-spectrogram images. The pre-trained Inception V3 model that carries out fine-tuning uses the mel-spectrogram image as input. Convolutional layers of fine-tuning completed Inception V3 models were used as feature extractors. A point-binary correlation analysis technique was used to select effective features for classification from the features extracted through the feature extractor. A crystal coefficient value, which is the square of the correlation coefficient value, is used for an accurate comparison between the features. We used an artificial neural network as a classifier in this experiment. Fine-tuned Inception V3 has an average accuracy of 87.7%. When 5-fold class validation is advanced by selecting the top 30 characteristics with high crystal coefficient values, the accuracy is 97.5%. These results can greatly assist physicians trying to detect a systolic murmur.