Journal of Graphic Era University

A Digital Twin and Bayesian Network Integrated Framework for Dynamic Resilience Assessment and Optimization of Urban Transportation Infrastructure

2025-09-04T22:39:53+00:00

Urban transportation infrastructure is a critical pillar for sustainable urban development, with its safety and resilience being vital for disaster response and functional recovery. However, traditional assessment methods rely on static data, making it difficult to address the dynamic evolution of disasters and the coupling of multiple factors, leading to lagging assessments and inefficient optimization strategies. This study proposes a dynamic resilience assessment framework that integrates Digital Twin (DT) and Bayesian Network (BN) technologies, establishing a closed-loop system of “monitoring-assessment-optimization” encompassing real-time monitoring, dynamic assessment, and intelligent optimization. By dynamically updating conditional probability tables and employing bidirectional reasoning mechanisms, the assessment error is reduced to less than 5%, achieving a 15%–20% improvement over traditional methods. A three-stage resilience indicator system of “resistance-recovery-adaptation” is established, with the innovative introduction of the “learning capability (L4)” indicator to quantify the system’s adaptive ability. The model’s effectiveness is validated using four heavy rainfall disaster cases in Zhengzhou from 2019 to 2022, and a three-tier resilience enhancement strategy of “short-term emergency response – mid-term network optimization – long-term smart upgrades” is proposed. The results indicate that redundancy design and intelligent scheduling capabilities are key factors in resilience improvement, with optimized system recovery time reduced by 12%. This framework provides a dynamic and intelligent approach for resilience assessment of transportation infrastructure and can be extended to other infrastructure sectors, offering theoretical and technical support for disaster prevention and mitigation in smart cities.

Sensitivity Analysis Considering Wiener Processes and Deep Learning for OSS Reliability Assessment

2025-09-13T16:45:11+00:00

The demand of open source software is increasing because of the low cost, high quality, and short delivery. In particular, open source software is managed by using the bug tracking system. This paper focuses on the method of reliability assessment based on the deep learning. Then, the Wiener process is applied to the output value of objective variables. Moreover, several sensitivity analyses of the parameter of Wiener process are shown as several numerical examples.

A Cross Validation of OSS Reliability Assessment Based on Deep Multimodal and Multitask Learning

2025-08-26T11:16:55+00:00

In recent years, open source software (OSS) has become ubiquitous in every field of our daily life. Hence, the OSS’s reliability is a significant challenge. The traditional models, like the software reliability growth model, can not handle a large scale of data efficiently, while the deep learning provides an effective method. This paper proposes a multi-input multi-output deep neural network to predict the fault detection time intervals and the fault modification time intervals simultaneously. Additionally, we present several numerical examples with a cross validation conducted with 3 types of data splits.