Arrhythmia, which is characterized by irregular heart rhythms, can lead to life-threatening conditions by disrupting the circulatory system. Thus, early arrhythmia detection is crucial for timely and appropriate patient treatment. Machine learning models have been developed to classify arrhythmia using electrocardiogram (ECG) data, which effectively capture the patterns associated with different abnormalities and achieve high classification performance. However, these models face challenges in terms of input coverage and robustness against data imbalance issues. Typically, existing methods employ a single cardiac cycle as the input, possibly overlooking the intervals between cycles, potentially resulting in the loss of critical temporal information. In addition, limited samples for rare arrhythmia types restrict the involved model’s ability to effectively learn, frequently resulting in low classification accuracy. Furthermore, the classification performance of existing methods on unseen data is not satisfactory owing to insufficient generalizability. To address these limitations, this research proposes a convolutional neural network (CNN) model for arrhythmia classification that incorporates two specialized modules. First, the proposed model utilizes images of three consecutive cardiac cycles as the input to expand the learning scope. Second, we implement a focal loss (FL) function during model training to prioritize minority classes. The experimental results demonstrate that the proposed model outperforms existing methods without requiring data preprocessing. The integration of multicycle ECG images and the FL function substantially enhances the model’s ability to capture ECG patterns, particularly for minority classes. In addition, our model exhibits satisfactory classification performance on unseen data from new patients. These findings suggest that the proposed model is a promising tool for practical application in arrhythmia classification tasks.

The ear is an effective biometric feature for personal identification. Although numerous studies have attempted personal identification using frontal-view images of the ear, only a few have attempted personal identification using multi-angle-captured ear images. To expand the extant literature and facilitate future biometric authentication technologies, we explore the feasibility of personal identification using multidirectionally captured ear images and attempted to identify the direction-independent feature points that contribute to the identification process. First, we construct a convolutional neural network model for personal identification based on multi-angle-captured ear images, after which we conduct identification experiments. We obtained high identification accuracies, exceeding 0.980 for all the evaluation metrics, confirming the feasibility of personal identification using multi-angle-captured ear images. Further, we performed Gradient-weighted Class Activation Mapping to visualize the feature points that contribute to the identification process, identifying the helix region of the ear as a key feature point. Notably, the contribution ratios for ear images in which the inner ear was visible and not visible are 97.5% and 56.0%, respectively. These findings indicate the feasibility of implementing personal identification using multi-angle-captured ear images for applications, such as surveillance and access control systems. These findings will promote the development of future biometric authentication technologies.