Deplomo Bhai Nhuraisha I, Villaverde Jocelyn F, Paglinawan Arnold C
School of Graduate Studies, Mapua University, Manila 1002, Philippines.
College of Computing and Information Sciences (CCIS), University of Makati, Makati 1215, Philippines.
Sensors (Basel). 2024 Jun 24;24(13):4095. doi: 10.3390/s24134095.
This research introduces the NeuRaiSya (Neural Railway System Application), an innovative railway signaling system integrating deep learning for passenger analysis. The objectives of this research are to simulate the NeuRaiSya and evaluate its effectiveness using the GreatSPN tool (graphical editor for Petri nets). GreatSPN facilitates evaluations of system behavior, ensuring safety and efficiency. Five models were designed and simulated using the Petri nets model, including the Dynamics of Train Departure model, Train Operations with Passenger Counting model, Timestamp Data Collection model, Train Speed and Location model, and Train Related-Issues model. Through simulations and modeling using Petri nets, the study demonstrates the feasibility of the proposed NeuRaiSya system. The results highlight its potential in enhancing railway operations, ensuring passenger safety, and maintaining service quality amidst the evolving railway landscape in the Philippines.
本研究介绍了NeuRaiSya（神经铁路系统应用），这是一种集成深度学习用于乘客分析的创新型铁路信号系统。本研究的目的是模拟NeuRaiSya，并使用GreatSPN工具（Petri网图形编辑器）评估其有效性。GreatSPN有助于评估系统行为，确保安全和效率。使用Petri网模型设计并模拟了五个模型，包括列车出发动态模型、带乘客计数的列车运行模型、时间戳数据收集模型、列车速度和位置模型以及列车相关问题模型。通过使用Petri网进行模拟和建模，该研究证明了所提出的NeuRaiSya系统的可行性。结果突出了其在菲律宾不断发展的铁路格局中增强铁路运营、确保乘客安全和维持服务质量方面的潜力。
