Artificial intelligence (AI) has reshaped various aspects of human lives, particularly through its capabilities to address complex sustainability challenges. Despite the rapid expansion of AI applications, their contribution to cleaner production and sustainable development remains underexplored, especially in developing nations. In Southeast Asia (SEA), where AI adoption has grown substantially across environmental, economic, and social dimensions, research that examines its role in cleaner production outcomes remains fragmented. In view of this gap, this study conducts a systematic literature review (SLR) of AI applications related to cleaner production and sustainable development by examining relevant themes, application areas, and sustainability dimensions addressed by AI, while evaluating the maturity of AI methodologies, alignment with cleaner production outcomes, and integration with circular economy and resource efficiency goals. Moreover, it investigates the barriers and challenges that constrain AI application and offers future research directions to advance AI deployment for cleaner production and sustainable development across SEA countries.

The Digital Academic Information System is an integrated platform designed to support and manage core academic functions, including research, extension, and instruction. The system streamlines research management by tracking proposals, publications, and collaborations; facilitates extension services by organizing community engagement programs and reporting outcomes; and enhances instruction through tools for course management, faculty workload tracking, and student performance monitoring. By centralizing these features, the system promotes efficiency, transparency, and improved decision-making within academic institutions. This study focuses on the evaluation of the developed digital academic system that focuses on research, instruction and extension integration which processes essentials to state universities and colleges. The researcher used the descriptive- developmental type of research. The system provides a real-time overview of the status of the performance and accomplishment of the academic institution in the mentioned areas. The evaluation of a Digital Academic Information System (DAIS) using Agile methodology and software quality model assessment provides a dynamic and structured approach to system development and analysis. Agile enables iterative development with continuous stakeholder feedback, ensuring that evolving academic requirements are met efficiently. By integrating a software quality model—such as ISO/IEC 25010—the evaluation further assesses critical attributes like functionality, usability, reliability, and maintainability The system obtained the overall weighted mean of 3.73 which interpret as Excellent in terms of Product Quality evaluated by the IT Experts. This means that the system is approved by the IT Experts and highly recommended to use.

Air quality monitoring has become increasingly critical in urban environments, particularly in densely populated megacities like Manila, Philippines. This research presents the design and conceptual framework for a comprehensive web-based air quality monitoring and mapping system that leverages fuzzy logic algorithms to provide intelligent, real-time assessment of atmospheric conditions across Metro Manila. The proposed system addresses the inherent uncertainties and complexities associated with environmental data by implementing a sophisticated fuzzy inference system specifically calibrated for Manila's unique atmospheric conditions, pollution sources, and regulatory requirements. The research encompasses a thorough analysis of Manila's current air quality challenges, including the identification of primary pollutants such as particulate matter (PM2.5 and PM10), carbon monoxide (CO), nitrogen dioxide (NO2), sulfur dioxide (SO2), and ground level ozone (O3). The proposed system architecture integrates multiple technological components including a distributed sensor network, centralized data processing infrastructure, fuzzy logic engine, web-based visualization platform, and real-time mapping capabilities. The fuzzy inference system is specifically designed to accommodate Manila's tropical climate conditions, high population density, and diverse pollution sources ranging from vehicular emissions to industrial activities. The methodology incorporates adaptive membership functions that adjust to seasonal variations and local environmental patterns, ensuring accurate and contextually relevant air quality assessments. The system design emphasizes scalability, real-time processing capabilities, and user accessibility through responsive web interfaces optimized for both desktop and mobile platforms. The technical implementation framework encompasses comprehensive hardware specifications for sensor deployment, software architecture for data processing and visualization, database design for efficient time-series data management, and API development for system integration and third-party access. Expected outcomes of this research include improved public awareness of air quality conditions, enhanced decision-making capabilities for environmental authorities, and the establishment of a robust foundation for future environmental monitoring initiatives in Manila and similar urban environments. The fuzzy logic approach provides a more nuanced and human-interpretable assessment of air quality compared to traditional crisp methodologies, enabling better communication of environmental risks to diverse stakeholder groups. This comprehensive study contributes to the growing knowledge in environmental informatics and smart city technologies, demonstrating the practical application of artificial intelligence techniques in addressing real-world environmental challenges. The research provides a detailed roadmap for implementing intelligent air quality monitoring systems in developing urban environments, with particular emphasis on cost-effectiveness, technological accessibility, and community engagement.

In an era of accelerating digital transformation, optimizing resource management through effective data governance has become vital for local governments in developing nations such as the Philippines. This study introduces a data-driven governance platform designed to enhance resource allocation and decision-making in healthcare services through integrated forecasting algorithms and data governance principles. Anchored on a comprehensive framework for local data governance, the system centralizes, analyzes, and forecasts health-related data to support evidence-based planning and resource distribution. Employing both descriptive and developmental research designs, the study developed and tested the DALAY system using forecasting techniques such as exponential smoothing to predict medical supply needs and service demand. The findings demonstrate that integrating forecasting algorithms within a structured data governance framework can significantly improve resource efficiency, transparency, and responsiveness in local government operations. The system thus provides a replicable model for strengthening data-driven governance and optimizing community resource management in the Philippines. The findings indicate that robust data governance can lead to improved operational effectiveness, enhanced accountability, and ultimately better outcomes for citizens of the Philippines. This study aligns with SDG 9 that highlights the role of ICT in modernizing governance, fostering innovation, and improving data-driven decision making.

Effective teaching forms the bedrock of education, directly influencing program accreditation and institutional performance. A competitive and supportive learning environment, fostered by strong faculty performance, is crucial for an academic institution to achieve its vision and mission. This study incorporates Sustainable Development Goals (SDGs) principles, ensuring that faculty performance evaluation contributes to long-term educational sustainability. Addressing the pressing need for robust faculty performance assessment, data mining algorithms are employed to extract insightful information regarding effective instruction, utilizing both structured and unstructured data. The developed system aims to empower institutions to identify their strengths, address areas for improvement, and cultivate continuous growth in teaching and learning processes by discerning trends within faculty data. Furthermore, sentiment analysis methods are utilized to evaluate qualitative input, with Laravel 8.0 serving as the framework for algorithm implementation. Expert evaluations of the system yielded a grand mean score of 4.38, deemed 'Very Acceptable,' thereby affirming its reliability and efficacy in supporting faculty performance reviews and advancing SDG objectives.