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.

Climate change is an important factor that must be considered by designers of large infrastructure projects, with its effects anticipated throughout the infrastructure’s useful life. This paper discusses how engineers can address climate change adaptation in design holistically and sustainably. It offers a framework for adaptation in engineering design, focusing on risk evaluation over the entire life cycle. This approach avoids the extremes of inaction and designing for worst-case impacts that may not occur for several decades. The research reviews case studies and best practices from different parts of the world to demonstrate effective design solutions and adjustment measures that contribute to the sustainability and performance of infrastructure. The study highlights the need for interdisciplinary cooperation, sophisticated modeling approaches, and policy interventions for developing robust infrastructure systems.

Purpose: The purpose of this paper is to explore the impact of Artificial Intelligence on the performance of Indian Banks in terms of financial metrics. The study focused specifically on the NIFTY Bank Index. The paper also advocates that a greater transparency in disclosing AI related information in a Bank’s annual report is required even if it is voluntary. Design/Methodology/Approach: The paper uses a mixed method approach where quantitative and qualitative analysis is combined. A dynamic panel data model is used to understand the impact of AI of Return on Equity (RoE) of 12 Indian Banks in the NIFTY Bank Index over a five-year period. In addition to that, Content analysis of annual reports of banks was conducted to examine AI related disclosure and transparency. Findings: The paper highlights that the integration of Artificial Intelligence (AI) significantly influences the financial performance of sample banks of India. Return on Equity the specific parameter positively influenced with adoption of AI. The profitability of banks is positively impacted by reduced errors and improved operational efficiency. The content analysis of annual reports of the banks indicates different approach for AI disclosure where some banks give detailed information and some are not transparent about AI initiatives. The findings suggest that a higher level of transparency could enhance confidence of all stakeholders. Theoretical Implications: The positive relation between adoption of AI and financial performance, specifically ROE, gives a foundation for academic research to explore the dynamics of emerging technology and financial systems. The study can be extended to explore the impact on other performance indicators in different sectors. Practical Implications: The findings of this study emphasize the importance of transparent AI related disclosures. A detailed reporting about integration of AI helps in enhanced stakeholders’ confidence in case of banking industry. The regulatory framework of banks may also consider making mandatory AI disclosure practices to ensure due accountability to maximize the benefits of AI in banking.

A significant cohort of Southeast Asian women in Taiwan, having married locals, constitutes a disadvantaged group entangled in the issues of gender, marriage migration, and social class. The lack of human capital, social discrimination and urgent personal economic demands have caused immigrant women in Taiwan to become a source of inexpensive labor in the labor market, they usually prioritize vocational training for employment. Furthermore, the rapidly growing elderly population has resulted in a severe shortage of quality care services in Taiwan. Despite Taiwanese government training for immigrant women, diverse sociocultural factors hinder them from pursuing caregiving professions. Therefore, this study aimed to investigate the effects of care service attendant (CSA) training based on culturally responsive pedagogy (CRP) and design thinking (DT) for immigrant women in Taiwan. Nine Vietnamese and Indonesian immigrant women in Taiwan attended and completed the training. The CSA training comprised core academic modules and practicum modules and was conducted in groups for 170 h over 5 weeks. This study employed a qualitative research approach, gathering data through interviews, observation, and document analysis. The results revealed that CSA training based on CRP and DT was effective in improving immigrant women’s satisfaction with training and their rate of employment as CSAs. Specifically, in addition to basic care service professionalism, the female immigrant trainees developed proactive attitudes toward problem-solving. Moreover, the integration of Taiwanese culture and frequent communication in the training facilitated the self-confidence of these trainees. In the workplace, these female immigrant CSAs’ commitment to meeting clients’ needs and innovating their service boosted the clients’ appreciation and their own cultural competency and empowerment. Overall, this study suggests that the application of CRP and DT in CSA training is a promising way of enhancing the workforce capacity of female immigrant CSAs and has value for low-skilled adult trainees. However, structuring the learning processes clearly and involving instructors with multicultural education and DT education competency are critical to implementing such vocational training.

The objective of this paper is to analyze the impact of infrastructure financing on economic growth in emerging markets through the application of both quantitative and qualitative research methodologies. In this study, the research will employ both primary and secondary data to investigate the impact of different structures of infrastructure financing on the performance of the economy through interviews with the stakeholders and policy documents alongside quantitative data from the World Bank and the IMF. The quantitative analysis employs the econometric models to establish the effect of infrastructure investment on the GDP growth of the selected countries, India, China, Brazil, and Nigeria. Additional secondary qualitative data obtained from interviews with policymakers and financial specialists from Brazil, India, and South Africa offer more practical information regarding the efficiency of the discussed financing approaches. This paper is therefore able to conclude that appropriate management of infrastructure investments, particularly those that involve the PPP, are central to the development of the economy. However, certain drawbacks such as the lack of regularity of data and the disparity in the effectiveness of financing instruments by the regions are pointed out. The research provides policy implications to policymakers and investors who wish to finance infrastructure in the emerging economy to enhance economic growth in the long run.

This study aims to develop a robust prioritization model for municipal projects in the Holy Metropolitan Municipality (Makkah) to address the challenges of aligning short-term and long-term objectives. The research explores How multi-criteria decision-making (MCDM) techniques can prioritize municipal projects effectively while ensuring alignment with strategic goals and local needs. The methodology employs the analytic hierarchy process (AHP) and exploratory factor analysis (EFA) to ensure methodological rigor and data adequacy. Data were collected from key stakeholders, including municipal planners and community representatives, to enhance transparency and reliability. The model’s validity was assessed through latent factor analysis, confirming the relevance of identified criteria and factors. Results indicate that flood prevention projects are the highest priority (0.4246), followed by road projects (0.3532), park construction (0.1026), utility projects (0.0776), and digital transformation (0.0416). The study highlights that certain factors are critical for evaluating and prioritizing municipal projects. “Capacity and Demand” emerged as the most influential factor (0.5643), followed by “Strategic Alignment” (0.2013), “Project Interdependence” (0.1088), “Increasing Investment” (0.0950), and “Risk” (0.0306). These findings are significant as they offer a structured, data-driven approach to decision-making aligned with Saudi Vision 2030. The proposed model optimizes resource allocation and project selection, representing a pioneering effort to develop the first prioritization framework specifically tailored to Makkah’s unique municipal needs. Notably, this is the first study to establish a prioritization method specifically for Makkah’s municipal projects, providing valuable contributions to the field.