The demand for integrated circuit (IC) chips has risen markedly across various industries in conjunction with advancements in global technology. Prior to packaging, IC elements undergo several processes, including wafer dicing, wire bonding, and encapsulation. Scanning Acoustic Tomography (SAT) effectively analyzes the internal structures of integrated circuit products, thereby preventing the supply of defective components, including chip fractures, delamination, voids, and adhesion issues. The study aims to reduce operator eye strain, enhance productivity, and minimize employee turnover rates by proposing the use of convolutional neural networks (CNN) to develop a predictive model for automating defect detection in integrated circuit (IC) products within SAT images, replacing traditional visual inspections. To enhance the accuracy of the CNN model, we implement the flood-fill algorithm as the primary augmentation strategy and create an image augmentation model in Python. This method produces a training set that accurately reflects the true characteristics of defects, thereby mitigating the problem of limited defect data and ensuring the model is trained on reliable information. The incorporation of various rates and scaling factors into SAT defect images, along with the manipulation of the original defect, contributes to the development of a robust dataset suitable for real-world testing. The CNN model is trained using various batch sizes, resulting in customized training datasets and predictive models to improve accuracy. Key findings indicate that employing 40× augmentation alongside a batch size of 32 enhances the model’s performance, yielding a missed detection rate below 0.4% and a false alarm rate of 0.1%. This model offers an improved solution to the issue of manual inspections on assemblies, thereby alleviating operator stress and establishing a robust framework for automated integrated circuit quality management.

Indonesian coffee MSMEs face increasing pressure to meet certification standards and adopt digital technologies to remain competitive in export markets. Despite strong agro-ecological advantages and rising global demand, upgrading efforts remain fragmented and lack clear prioritization. This study develops and empirically evaluates a decision-focused upgrading framework by integrating Porter’s Diamond, Global Value Chain (GVC) upgrading, and Analytic Hierarchy Process (AHP). Using Dampit coffee MSMEs as a case study, the results identify competitiveness gaps linked to functional upgrading needs. AHP prioritization highlights Operational Excellence as the most critical strategy, emphasizing process improvement and reliability. The framework offers practical guidance for MSMEs and policymakers to support structured and sustainable upgrading toward global market integration.