Yeonhee Kim

The National Pension Service (NPS) will continue to expand its real estate portfolio in North America, Europe and India, targeting residential, logistics and d

Real estate credit continues to appeal to South Korea’s major asset owners, even amid declining interest rates, as they prioritize stable yields and rema

Asset-backed finance (ABF) is evolving from a defensive niche into a central pillar of private credit’s expansion, offering investors yield, security and

The commercial real estate market in the US and Europe is showing early signs of a rebound, supported by limited supply after a construction slowdown during CO

Asia’s private markets, particularly the secondaries segment, are primed for strong growth as constrained supply, attractive pricing and improving liquid

Heightened geopolitical uncertainty and the energy transition are fueling defense and infrastructure spending in Europe, positioning its private credit market

South Korean President Lee Jae Myung said on Friday that the US has agreed to support Seoul’s long-held pursuit of nuclear-powered submarines and expande

South Korea and the United Arab Emirates (UAE) have agreed to jointly pursue nuclear energy exports to third countries, while Seoul is also poised to take part

I Squared Capital sees the global infrastructure industry entering a supercycle, powered by

Printed Circuit Board (PCB) defect detection is critical for quality control in electronics manufacturing. Traditional manual inspection and classical Automated Optical Inspection (AOI) methods face challenges in speed, consistency, and flexibility. This paper proposes a CNN-based approach for automatic PCB defect detection using the YOLOv5 model. The method leverages a Convolutional Neural Network to identify various PCB defect types (e.g., open circuits, short circuits, and missing holes) from board images. In this study, a model was trained on a PCB image dataset with detailed annotations. Data augmentation techniques, such as sharpening and noise filtering, were applied to improve robustness. The experimental results showed that the proposed approach could locate and classify multiple defect types on PCBs, with overall detection precision and recall above 90% and 91%, respectively, enabling reliable automated inspection. A brief comparison with the latest YOLOv8 model is also presented, showing that the proposed CNN-based detector offers competitive performance. This study shows that deep learning-based defect detection can improve the PCB inspection efficiency and accuracy significantly, paving the way for intelligent manufacturing and quality assurance in PCB production. From a sensing perspective, we frame the system around an industrial RGB camera and controlled illumination, emphasizing how imaging-sensor choices and settings shape defect visibility and model robustness, and sketching future sensor-fusion directions.