Epilepsy, often associated with neurodegenerative disorders following brain strokes, manifests as abnormal electrical activity bursts in the cerebral cortex, disrupting regular brain function. Electroencephalogram (EEG) recordings capture these distinctive brain signals, offering crucial insights into seizure detection and management. This study presents a novel approach leveraging a graph neural network (GNN) model with a heterogeneous graph representation to detect epileptic seizures from EEG data. Utilizing the well-established CHB-MIT EEG dataset for training and evaluation, the proposed method includes preprocessing steps such as signal segmentation, resampling, label encoding, normalization, and exploratory data analysis. We employed a standard train-test split with stratified sampling to ensure class distribution and reduce bias. Experimental comparisons with long short-term memory (LSTM) and recurrent neural network (RNN) models highlight the GNN’s superior performance, achieving a classification accuracy of 98.0% and demonstrating incremental improvements in precision and F1-score. These findings emphasize the efficacy of GNN in capturing spatial and temporal dependencies within EEG data, surpassing conventional deep learning techniques. Furthermore, the study highlights the model’s interpretability, which is essential for clinical decision-making. By advancing EEG-based seizure prediction methods, this research offers a robust framework for enhancing patient outcomes in epilepsy management while addressing the limitations of existing approaches.

Traditional medical education encounters several challenges. The introduction of advanced facial expression recognition technology offers a new approach to address these issues. The aim of the study is to propose a medical education–assisted teaching and student evaluation method based on facial expression recognition technology. This method consists of 4 key steps. In data collection, multiangle high-definition cameras record students’ facial expressions to ensure data comprehensiveness and accuracy. Facial expression recognition uses computer vision and deep learning algorithms to identify students’ emotional states. The result analysis stage organizes and statistically analyzes the recognized emotional data to provide teachers with students’ learning status feedback. In the teaching feedback stage, teaching strategies are adjusted according to the analysis results. Although this method faces challenges such as technical accuracy, device dependency, and privacy protection, it has the potential to improve teaching effectiveness, optimize personalized learning, and promote teacher-student interaction. The application prospects of this method in medical education are broad, and it is expected to significantly enhance teaching quality and students’ learning experience.

The advancement of YOLO and similar computer vision models represents a technological era that could revolutionize numerous aspects of day-to-day life, including traffic management. This study explores the feasibility of utilizing YOLOv8 for pedestrian detection and counting to control traffic light timing sequences at isolated pedestrian crossings. By employing the Raspberry Pi 4 Model B with a camera module, real-time pedestrian video data can be captured and processed through YOLOv8. For the hardware, three LEDs and a Dot Matrix Module replicate conventional traffic light signals and timing, effectively simulating a traffic light system. The capabilities of the custom YOLOv8 model are evaluated through pedestrian detection accuracy, calculated by percentage error across twenty samples. Results reveal an average percent error of 7.33%, indicating 92.67% accuracy in pedestrian detection and counting. These findings underscore the model's competence for pedestrian-based adaptive traffic light control, highlighting its potential to enhance practicality and safety at pedestrian crossings by dynamically adjusting signal timings based on real-time pedestrian activity.

Aiming at security issues such as user password leakage, password cracking, spoofing, replay attack, man-in-the-middle attack, and server-side attack that may occur during the identity authentication process of instant messaging system users, this paper uses a hybrid algorithms of SM2 and SM3 to design a set of a dual and bidirectional certificateless authentication scheme based on SM2, SM3 and random salt value. This solution includes a two-way password authentication security model based on SM2 and SM3+random salt value, and an intelligent secret medium challenge-response two-way authentication security model based on SM2 and SM3 and random salt value. The dual bidirectional security model implemented by using the hybrid SM series algorithms can achieve the full process of ciphertext transmission, storage, and verification during the authentication process, which can effectively prevent the leakage of personal information in the authentication process, and can effectively prevent fraud, man-in-the-middle attacks, password cracking, and account theft during the authentication process.