With the widespread use of lithium-ion batteries in various fields, estimating the State of Health (SOH) of batteries is essential to ensure efficiency and safety during operation. Although model-based methods have been widely applied for SOH estimation, challenges in battery modeling have led to increasing interest in machine learning approaches. This paper introduces a SOH evaluation method based on time-domain data analysis. The method focuses on processing and analyzing data in the time domain to identify relationships with the usable capacity of the battery. We also compare the effectiveness of this method with various neural network models such as Feedforward Neural Networks (FNN), Convolutional Neural Networks (CNN), and Long Short-Term Memory (LSTM). The results demonstrate that the time-domain analysis method can provide high accuracy and effectively meet the needs of SOH estimation, especially when the training data is limited.

The transportation of sensitive equipment often suffers from vibrations caused by terrain, weather, and motion speed, leading to inefficiencies and potential damage. To address this challenge, this paper explores an intelligent control framework leveraging fuzzy logic, a foundational AI technique, to suppress oscillations in suspension systems. Inspired by learning-based methodologies, the proposed approach utilizes fuzzy inference and Gaussian membership functions to emulate adaptive, human-like decision-making. By minimizing the need for explicit mathematical models, the method demonstrates robustness in both linear and nonlinear systems. Experimental validation highlights the controller’s ability to adapt to varying suspension lengths, reducing oscillation amplitudes and improving stability under dynamic conditions. This research bridges the gap between traditional control systems and learning-inspired techniques, offering a scalable, data-efficient solution for modern transportation challenges.

In the era of digital transformation, the integration of Large Language Models (LLMs) into education has opened new avenues for interactive and effective learning. This paper introduces the development of a chatbot designed to support learning Vietnamese history by using advanced LLM to deliver accurate and contextually appropriate responses. The chatbot employs modern natural language processing (NLP) techniques, including the Vietnamese Bi-Encoder and Meta-LLaMA models, to convert historical textbook content into a structured and conversational format. Data was sourced from Vietnamese history textbooks for grades 6 to 12, systematically organized into a database, and processed using embedding and retrieval mechanisms to enable seamless question-answer interactions. Built on the Django framework, the system provides a user-friendly interface and a scalable back-end for diverse educational applications. Initial evaluations indicate the chatbot’s high accuracy and relevance in answering historical queries, enhancing both user engagement and accessibility. This project not only supports historical education but also promotes Vietnamese cultural heritage through the application of artificial intelligence. Future developments include expanding the dataset, incorporating multilingual capabilities, and optimizing the user experience, further establishing the chatbot as a valuable tool for learning and preserving history.