Scientechno: Journal of Science and Technology

PATTERN RECOGNITION SYSTEM FOR AUTOMATING MEDICAL DIAGNOSIS BASED ON IMAGE DATA

Evi Irianti, Nina Anis, Saifiullah Aziz — Sun, 28 Dec 2025 00:00:00 +0700

The increasing volume and complexity of medical image data have presented significant challenges for healthcare professionals in delivering timely and accurate diagnoses. Traditional diagnostic processes are often time-consuming and prone to human error, underscoring the need for automated solutions. This study aims to develop a pattern recognition system to automate medical diagnosis using image data, thereby improving diagnostic accuracy and efficiency. A hybrid methodology was employed, combining image preprocessing, feature extraction using convolutional neural networks (CNNs), and classification through deep learning algorithms. The system was trained and validated using publicly available medical image datasets across various disease types. The results demonstrate high diagnostic accuracy, with the system achieving over 92% precision in identifying disease patterns from image inputs. Furthermore, the model exhibited robustness across different imaging modalities, such as X-rays, MRIs, and CT scans. These findings suggest that the proposed pattern recognition system can serve as a reliable support tool for medical practitioners. In conclusion, the integration of image-based pattern recognition in medical diagnostics holds significant promise in enhancing clinical decision-making processes and reducing diagnostic errors.

UTILIZATION OF THE MICROBIOME TO INCREASE FOOD SECURITY THROUGHT SUSTAINABLE BIOTECHNOLOGY

Muhammad Hazmi, Seo Jiwon, Ruby Kingh — Sun, 28 Dec 2025 00:00:00 +0700

Food security remains a critical global challenge, requiring innovative and sustainable solutions to meet the growing demand for nutritious food. One promising approach is the utilization of microbiomes in sustainable biotechnology to enhance agricultural productivity, improve soil health, and increase food production efficiency. This study aims to explore the potential of microbiome-based biotechnological applications in strengthening food security through sustainable agricultural practices. A qualitative research methodology was employed, involving an extensive literature review and analysis of case studies related to microbiome utilization in agriculture. The findings indicate that microbiomes play a significant role in improving crop resilience, enhancing nutrient absorption, and reducing the need for chemical fertilizers and pesticides. Furthermore, microbiome-based biotechnology contributes to environmental sustainability by promoting soil biodiversity and reducing greenhouse gas emissions. The study concludes that integrating microbiome technology into agricultural systems can significantly enhance food security while ensuring ecological balance. Future research should focus on optimizing microbiome applications and developing scalable implementation strategies for various agricultural settings.

ADAPTIVE AND RESILIENT LEARNING TECHNOLOGIES IN FORMAL AND INFORMAL EDUCATION: A SYSTEMATIC LITERATURE REVIEW

Riska Meisyi Putri, Sarinah Sarinah, Fatimah Al-Rashid — Wed, 31 Dec 2025 00:00:00 +0700

This study reviews the use of Mobile-Assisted Language Learning (MALL) and digital storytelling in multilingual education, focusing on research trends, teaching strategies, and their impact on inclusive and effective language learning. A systematic literature review was conducted using peer-reviewed studies published between 2020 and 2025 from major academic databases. The studies were analyzed using thematic coding and comparison. The findings show that MALL and digital storytelling improve learner engagement, motivation, intercultural competence, and language proficiency in diverse linguistic and cultural contexts. These approaches also support personalized learning, collaboration, and the development of critical literacy related to social justice and educational equity. The novelty of this review is its integrated view of mobile learning and digital storytelling as connected teaching approaches in multilingual and multicultural settings. By summarizing recent research, this study shows how technology-based learning supports learner autonomy, flexible learning processes, and inclusive teaching practices. The findings offer practical guidance for educators, policymakers, and instructional designers in developing curricula and professional training suited to multilingual classrooms.

INTEGRATING DIGITAL TWINS AND SYSTEMIC AI FOR PREDICTIVE MAINTENANCE OF NATIONAL CRITICAL INFRASTRUCTURE

Lucas Wong, Sofia Lim, Rohan Kumar, Rustiyana Rustiyana — Wed, 10 Dec 2025 00:00:00 +0700

National critical infrastructure, including energy, transportation, and communication systems, plays a vital role in sustaining modern society, yet failures within these systems can trigger severe economic, environmental, and security consequences. Conventional maintenance approaches often lack the capability to anticipate failures in complex and large-scale infrastructures. Recent advancements in Digital Twin technology and Artificial Intelligence (AI) provide innovative opportunities to enhance predictive maintenance and infrastructure resilience. This study aims to integrate Digital Twins with systemic AI to optimize predictive maintenance strategies for national critical infrastructure by leveraging real-time data and intelligent prediction mechanisms. The research employs a combined framework in which sensor-generated data from infrastructure components are continuously synchronized with Digital Twin models and analyzed using machine learning algorithms to monitor system conditions, simulate operational behavior, and predict potential failures. The proposed framework was implemented in a case study of a national energy grid to evaluate its effectiveness. The results indicate that the integrated system significantly improved predictive maintenance performance, achieving a 30% reduction in unplanned downtime and a 25% decrease in maintenance costs through accurate failure prediction and timely intervention. These findings demonstrate that the integration of Digital Twins and systemic AI offers a robust, scalable, and efficient solution for enhancing reliability, resilience, and sustainability in the management of national critical infrastructure.

MODELING THE IMPACT OF SEA-LEVEL RISE ON COASTAL VULNERABILITY IN JAKARTA USING AN INTEGRATED DATA SCIENCE FRAMEWORK

Nofirman Nofirman, Dulguun Amarsaikhan, Munkhzul Ganbat, Tugsuu Jargalsaikhan — Sun, 07 Dec 2025 00:00:00 +0700

Jakarta, the capital city of Indonesia, is highly vulnerable to the impacts of sea-level rise due to its coastal location, rapid urbanization, and subsidence, making it crucial to understand how climate change-driven increases in sea levels affect the city’s coastal areas for effective adaptation planning. This study aims to model the impact of sea-level rise on the vulnerability of Jakarta’s coastal zones by using an integrated data science framework to assess potential risks such as flooding, land loss, and other environmental consequences under various sea-level rise scenarios. Employing a combination of geographic information systems (GIS), remote sensing data, and machine learning models, the analysis integrates sea-level rise projections with land elevation, population density, and infrastructure data to evaluate potential impacts, while algorithms such as Random Forest and Support Vector Machine (SVM) are utilized to predict vulnerability levels. The results indicate that Jakarta’s coastal areas face high vulnerability, with substantial portions of land projected to be inundated under higher sea-level scenarios, particularly in low-lying and densely populated regions at heightened risk of flooding and infrastructure damage. Overall, this research offers valuable insights into future coastal vulnerability in Jakarta and demonstrates how an integrated data science approach can support urban planning and climate adaptation strategies aimed at reducing the risks associated with rising sea levels.