ARTICLE
Lithium-Ion Battery State of Health Prediction Using a Hybrid BiLSTM–Random Forest Framework
Published in Batteries, a Q1 journal indexed in both Scopus and the Web of Science Core Collection (Science Citation Index Expanded—SCIE)
<p>This study introduces a hybrid framework that combines deep learning and ensemble machine learning techniques to accurately predict the state of health of lithium-ion batteries. The proposed model demonstrated high prediction accuracy and robustness when evaluated using both the NASA and Oxford battery datasets, underscoring its potential for advanced battery health monitoring and intelligent battery management systems in electric vehicles and energy storage applications.</p>
<p>The findings contribute to the growing body of knowledge on sustainable energy technologies and support the development of more reliable and efficient energy storage solutions.</p>
<p><br>Hormuud University continues to support impactful, interdisciplinary research that advances knowledge and contributes to more equitable and sustainable livelihoods.</p>
<p>𝐏𝐥𝐞𝐚𝐬𝐞 𝐫𝐞𝐚𝐝 𝐭𝐡𝐞 𝐚𝐫𝐭𝐢𝐜𝐥𝐞 𝐚𝐭 𝐭𝐡𝐞 𝐥𝐢𝐧𝐤 𝐛𝐞𝐥𝐨𝐰: https://www.mdpi.com/2313-0105/12/6/210</p>
<p>#Lithium-IonBattery #HealthPrediction #HybridBiLSTM–RandomForestFramework #HU #Research #HURC #HormuudUni #HormuudUniversity #HUCommunity #HU2026</p>
Geopolitical Energy Shocks and the Hidden Costs for the Global South: A Critical Review
Cereal Yields In Fragile States: The Roles of Economic Growth, Inflation, Climate Variability, and Governance
Challenges and Strategic Pathways for Advancing Circular Economy in Photovoltaics
