<![CDATA[The increasing adoption of electric vehicles (EVs) in urban public transportation has raised significant safety concerns, particularly regarding thermal runaway incidents that may lead to catastrophic fires. Existing battery monitoring systems often provide inadequate warning times and lack predictive capabilities to mitigate failures before they reach critical conditions. This study proposes an intelligent early warning system for EV battery safety in public transportation fleets by employing predictive analytics. The system integrates a distributed Internet of Things (IoT) sensor network that monitors temperature, voltage, current, and gas emissions, combined with machine learning algorithms—specifically, Random Forest and Support Vector Machine—to analyze battery performance patterns. The proposed architecture incorporates edge computing for real-time data processing and cloud infrastructure for centralised fleet monitoring. Field validation involving 50 electric buses operating under Jakarta's TransJakarta network over a twelve-month period achieved a prediction accuracy of 94.7% for thermal runaway events, with an average warning time of 8.3 minutes. The system successfully prevented 23 potential battery failures while maintaining a false alarm rate below 2.1%. An economic analysis further indicated a favourable cost-benefit ratio of 1:7.4. The proposed solution demonstrates significant potential in enhancing EV battery safety through predictive analytics and automated emergency response, offering a scalable model for broader industry adoption.]]>
