Vehicles

This study investigates cross-cultural differences in public perception of mobility electrification by applying natural language processing (NLP) techniques to social media discourse in Germany and China. Using a large language model (LLM), this study conducted sentiment analysis and zero-shot text classification on over 10,000 posts to explore how citizens in each country engage with the topic of electric mobility. Results reveal that while infrastructure readiness is a dominant concern in both contexts, German discourse places greater emphasis on environmental impact, often reflecting skepticism toward sustainability claims. On the other hand, Chinese discussions highlight technological advancement and infrastructure expansion, with comparatively limited focus on environmental concerns. These findings show the importance of culturally tailored policy and communication strategies in supporting the public acceptance of electric mobility. By demonstrating how artificial intelligence-driven large-scale social media data analysis can be used to analyze public sentiment across linguistic and cultural contexts, this study contributes methodologically to the emerging field of computational social science and offers practical insights for mobility policy in diverse national settings.

Predicting the severity of traffic accidents remains challenging due to the limited ability of existing methods to extract deep semantic information from unstructured accident narratives, as traditional approaches typically depend on structured data alone. This study proposes a severity prediction approach enhanced by semantic risk reasoning derived from large language models (LLMs). A prompt-engineering template is designed to guide LLMs in extracting proxy semantic features from accident descriptions, forming an enriched feature set that incorporates causal logic. These semantic features are fused with traditional structured features through three integration strategies—direct feature concatenation, optimized feature selection, and model-level fusion. Experiments based on 4013 accident records from expressways in Yunnan Province, China, demonstrate that models using LLM-derived semantic features significantly outperform those relying solely on structured features. Notably, the LightGBM model utilizing semantic features within a balanced learning framework achieves a severe accident recall of 77.8%. While model-level fusion proves optimal for XGBoost (improving Macro-F1 to 0.6356), we identify a “feature dilution” effect in other classifiers, where high-quality semantic reasoning is compromised by low-quality structured noise. These findings indicate that the proposed approach effectively enhances the identification of high-risk accidents and offers a novel semantic-aware solution for traffic safety management. Furthermore, the obtained results provide actionable insights for traffic management agencies to optimize emergency response resource allocation and formulate targeted accident prevention strategies.

This research paper proposes a solution to reduce CO₂ emissions from a spark ignition engine’s exhaust gases by installing a filtration system on the vehicle’s exhaust pipe. The analyzed filtration system was not patented and was in the testing stage. Tests will also be carried out on the stand. The tested system can be used to reduce CO₂ levels in automotive exhaust gases and for static applications (generators, internal combustion engine test stands, fossil fuel power generation systems). The need for a system to reduce pollutant emissions emerged with the average age in Europe. In proper conditions, some vehicles can use this type of filtration system. The tested vehicle is a vehicle (produced in 2009) equipped with a 75HP Spark Ignition Engine. The CO₂ filtration system consists of a container containing a reactive aqueous solution comprising water, CaO, and MgO. Four tests were performed: the first without a filter, and the other three with the filter placed at different distances from the exhaust pipe end to the reactive solution surface. The tests consisted of evaluating the exhaust gases from the cold start of the engine and running (idle engine speed) until the engine reached the optimal operating temperature. The test procedure involved saving the data collected by the analyzer every 10 s for each of the four tests performed (the duration of a test was 1050 s). The first test (No. 1) was performed without the use of the filtering system. Tests 2, 3, and 4 were carried out using the filtering system and changing the distance between the exhaust gases’ outlet point and the surface of the aqueous substance. All tests were carried out under similar conditions. Data specific to the test of engines were collected—emissions (CO₂, CO, NO_x), ambient temperature, and exhaust temperature. The tests were analyzed and compared, and the highest CO₂ reductions without increases in CO or NO_x were observed in Tests 3 and 4. Based on the detailed analysis of the values obtained from the four tests, the system was efficient. The tests will continue on experimental engines from test stands, to develop a prototype filter for primarily static applications with internal combustion engines: test stands for engines and generators, and, after homologation, directly on vehicles. The paper aims to partially solve an important problem—reducing the level of CO₂ from the exhaust gases. The presented solution may have applicability in the automotive industry but is also feasible for static applications. Another objective is to reduce emissions from older vehicles, which are widespread in certain regions of Europe and worldwide.