Electrocardiogram (ECG) signals from mobile sensors are expected to increase the availability of authentication in the emerging wearable device industry. However, mobile sensors provide a relatively lower quality signal than the conventional medical devices. This paper proposes a practical authentication procedure for ECG signals that collected via one-chip-solution mobile sensors. We designed a cascading bandpass filter for noise cancellation and suggest eight fiducial features. For classification-based authentication, we use the radial basis function kernel-based support vector machine showing the best performance among nine classifiers through experimental comparisons. In spite of noisy ECG signals in mobile sensors, we achieved 4.61% of the equal error rate (EER) on a single heartbeat, and 1.87% of EER on 15 s testing time on 175 subjects, which is a reasonable result and supports the usability of low-cost ECGs for biometric authentication.

Facial bone fractures must be diagnosed and treated as early as possible to avoid complications and sequelae. CT images need to be analyzed to detect fractures, but the analysis is time-consuming, and enough specialists are not available to analyze them. Many classification and object detection studies are being conducted to address these issues. The ability of classification-based studies to pinpoint the exact location of fractures is limited. Object detection-based research, by contrast, is problematic because the shape of a fracture is ambiguous. We propose a computer-aided facial bone fracture diagnosis (CA-FBFD) system to address the aforementioned challenges. This system adopts the object detection model YoloX-S, which is trained using only IoU Loss for box prediction, along with CT image Mixup data augmentation. For training, we used only nasal bone fracture data, whereas for testing, we used several other facial fracture data. During evaluation, the CA-FBFD system achieved an average precision of 69.8% for facial fractures, which is better than the baseline YoloX-S model by a large margin of 10.2%. In addition, the CA-FBFD system achieved a sensitivity/person of 100% for facial fractures, which is considerably better than that exhibited by the baseline YoloX-S model by a margin of 66.7%. Therefore, the CA-FBFD system can effectively minimize the labor of doctors who need to determine facial bone fractures in facial CT.

Park SW, et al. J Korean Med Sci. 2024 Jan;39:e53. https://doi.org/10.3346/jkms.2024.39.e53

Learning classifiers with imbalanced data can be strongly biased toward the majority class. To address this issue, several methods have been proposed using generative adversarial networks (GANs). Existing GAN-based methods, however, do not effectively utilize the relationship between a classifier and a generator. This article proposes a novel three-player structure consisting of a discriminator, a generator, and a classifier, along with decision boundary regularization. Our method is distinctive in which the generator is trained in cooperation with the classifier to provide minority samples that gradually expand the minority decision region, improving performance for imbalanced data classification. The proposed method outperforms the existing methods on real data sets as well as synthetic imbalanced data sets.

Recently, the field of steganography has experienced rapid developments based on deep learning (DL). DL based steganography distributes secret information over all the available bits of the cover image, thereby posing difficulties in using conventional steganalysis methods to detect, extract or remove hidden secret images. However, our proposed framework is the first to effectively disable covert communications and transactions that use DL based steganography. We propose a DL based steganalysis technique that effectively removes secret images by restoring the distribution of the original images. We formulate a problem and address it by exploiting sophisticated pixel distributions and an edge distribution of images by using a deep neural network. Based on the given information, we remove the hidden secret information at the pixel level. We evaluate our technique by comparing it with conventional steganalysis methods using three public benchmarks. As the decoding method of DL based steganography is approximate (lossy) and is different from the decoding method of conventional steganography, we also introduce a new quantitative metric called the destruction rate (DT). The experimental results demonstrate performance improvements of 10-20% in both the decoded rate and the DT.

Sleep staging is an important part of clinical neurology. However, it is still performed manually by technical experts and is labor-intensive and time-consuming. To overcome these obstacles in the manual sleep staging process, a large number of machine learning-based classifiers with hand-engineered features have been proposed. Additionally, combinations of a deep neural network (DNN) have been recently highlighted as the state-of-the-art classifiers in view of their effectiveness for automatic sleep staging. In spite of the existence of a large number of these types of classifiers, to-this-date, no prior DNN-based approach has attempted sleep-stage classification using pediatric electroencephalographic (EEG) signals. In this paper, we propose a novel end-to-end classifier based on a multi-domain hybrid neural network (HNN-multi) approach consisting of a convolutional neural network and bidirectional long short-term memory for automatic sleep staging with pediatric scalp EEG recordings. To find effective temporal, spatial, and domain-specific conditions, we investigated noticeable changes in the classification performance corresponding to: 1) the length of input signals; 2) the number of channels; and 3) the types of input signals in the time and frequency domains. Our HNN-based classifier yielded the best performance metrics using 30-s time series in combination with an instantaneous frequency using a 19-channel, three-stage classification, with overall accuracy, F1 score, and Cohen's Kappa, equal to 92.21%, 0.90, and 0.88, respectively. We suggest that an effective combination of temporal and spatial time-domain clues with time-varying frequency domain information plays a pivotal role in pediatric, automatic sleep staging. Sufficiently reasonable performance of our HNN-based approach coping with the highly complicated pediatric EEG signatures hopefully sheds light on the clinical feasibility of the DNN-based automatic sleep staging for pediatric neurology.