Original Article A lightweight neural network for lung nodule detection based on improved ghost module Liuyang Yang, Hongyu Cai, Xinyu Luo, Jianping Wu, Rui Tang, Yu Chen, Wei Li

Selecting the right set of features from data of high dimensionality for inducing an accurate classification model is a tough computational challenge. It is almost a NP-hard problem as the combinations of features escalate exponentially as the number of features increases. Unfortunately in data mining, as well as other engineering applications and bioinformatics, some data are described by a long array of features. Many feature subset selection algorithms have been proposed in the past, but not all of them are effective. Since it takes seemingly forever to use brute force in exhaustively trying every possible combination of features, stochastic optimization may be a solution. In this paper, we propose a new feature selection scheme called Swarm Search to find an optimal feature set by using metaheuristics. The advantage of Swarm Search is its flexibility in integrating any classifier into its fitness function and plugging in any metaheuristic algorithm to facilitate heuristic search. Simulation experiments are carried out by testing the Swarm Search over some high-dimensional datasets, with different classification algorithms and various metaheuristic algorithms. The comparative experiment results show that Swarm Search is able to attain relatively low error rates in classification without shrinking the size of the feature subset to its minimum.

Arrhythmias are prevalent symptoms of cardiovascular disease, necessitating accurate and timely detection to mitigate associated risks. Detecting arrhythmias from ECGs quickly and accurately holds great significance in preventing heart disease and reducing mortality. This research endeavors to outperform previous studies by developing a scientific neural network model capable of training and predicting ECG signals for 11 categories of arrhythmias, accounting for up to 5 co-existing labels. In this study, we initially address the issue of imbalanced datasets by employing Borderline SMOTE and Cluster Centroids techniques during preprocessing. Subsequently, we propose a novel SAR model that combines attention and resnet mechanisms. The dataset is subjected to a 10-fold validation process to train and evaluate the model. Finally, several metrics such as HammingLoss, RankingLoss, F1-score, AUC and Coverage are used to evaluate the model. By evaluating the results of the tests, the average Hamming Loss is 1.12 %, the average Ranking Loss is 1.17 %, the average Micro F1-score is 98.46 %, the average Micro AUC is 98.76 %, and the average Coverage is 3.2762. The results show that the SAR model outperforms previous related studies on the task of classifying arrhythmia signals with multiple categories and labels. The SAR model demonstrated excellent performance in accurately classifying multi-category and multi-label arrhythmia signals, affirming its scientific validity. Compared with previous studies, the model achieves a certain improvement in performance, which can help cardiologists to achieve scientific and accurate diagnosis of arrhythmia diseases.