This research aims to determine the factors driving the success of four large cities in Indonesia in implementing Transit-Oriented Development (TOD) infrastructure policies beyond the eight TOD 3.0 Principles. Only a few studies like this have been conducted. The research uses qualitative methods and is supported by in-depth interviews with stakeholders, community leaders, community groups, and service users. The research findings reveal six themes: policy dialogue, organizational structure and coordination, changes in community habits, resources, dissemination and communication, and transportation and connectivity services. The characteristics of the community in the study area that prioritize deliberation are important determinants in policy dialogue and are involved in determining policy formulation. The city government has established a comprehensive organizational and coordination structure for the village and sub-district levels. The Government controls infrastructure development activities, establishes a chain of command and coordination, and encourages people to change their private car usage habits. The city government combines all this with the principle of deliberation and conveys important information to the public. The research highlights the differences in TOD implementation in Indonesia compared to other countries. Specifically, the existence of policy dialogue and the direct involvement of community members influence the level of program policy formulation and are crucial in controlling urban infrastructure development.

Accurate drug-drug interaction (DDI) prediction is essential to prevent adverse effects, especially with the increased use of multiple medications during the COVID-19 pandemic. Traditional machine learning methods often miss the complex relationships necessary for effective DDI prediction. This study introduces a deep learning-based classification framework to assess adverse effects from interactions between Fluvoxamine and Curcumin. Our model integrates a wide range of drug-related data (e.g., molecular structures, targets, side effects) and synthesizes them into high-level features through a specialized deep neural network (DNN). This approach significantly outperforms traditional classifiers in accuracy, precision, recall, and F1-score. Additionally, our framework enables real-time DDI monitoring, which is particularly valuable in COVID-19 patient care. The model’s success in accurately predicting adverse effects demonstrates the potential of deep learning to enhance drug safety and support personalized medicine, paving the way for safer, data-driven treatment strategies.