Jove
Visualize
Contact Us
JoVE
x logofacebook logolinkedin logoyoutube logo
ABOUT JoVE
OverviewLeadershipBlogJoVE Help Center
AUTHORS
Publishing ProcessEditorial BoardScope & PoliciesPeer ReviewFAQSubmit
LIBRARIANS
TestimonialsSubscriptionsAccessResourcesLibrary Advisory BoardFAQ
RESEARCH
JoVE JournalMethods CollectionsJoVE Encyclopedia of ExperimentsArchive
EDUCATION
JoVE CoreJoVE BusinessJoVE Science EducationJoVE Lab ManualFaculty Resource CenterFaculty Site
Terms & Conditions of Use
Privacy Policy
Policies

Related Concept Videos

Effects of EDTA on End-Point Detection Methods01:18

Effects of EDTA on End-Point Detection Methods

600
Different methods, such as visual observance of metal-ion indicators, spectroscopic techniques, and potentiometric methods, can determine the endpoint of an EDTA titration.
In the visual method, metal-ion indicators (metallochromic dyes), which have distinct colors in their free and complex forms, are added to the mixture to signal the titration's end point. They form stable complexes with metal ions, but these complexes are weaker than the corresponding metal–EDTA complexes. As a...
600

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by
Same author

Non-invasive predictive model for incidental gallbladder carcinoma based on multimodal features: Integrating clinical data, MRI radiomics, and deep transfer learning features.

Translational oncology·2026
Same author

Regulatory mechanisms of ALKBH5/CIITA axis in the synergistic modulation of hepatocellular carcinoma radiotherapy and immunotherapy.

Genes and immunity·2026
Same author

Capillary-Driven Densification of Bilayer Ultrathin Carbon Fiber Composite Paper for EMI Shielding and Electrothermal Conversion.

ACS applied materials & interfaces·2025
Same author

Energy Storage, Power Management, and Applications of Triboelectric Nanogenerators for Self-Powered Systems: A Review.

Micromachines·2025
Same author

Litchi-Skin-Like NiMoP<sub>2</sub> Microspheres Supported on MOF-Derived Carbon Layer as High Performance Composite Positive Electrode of Asymmetric Supercapacitor.

Chemistry (Weinheim an der Bergstrasse, Germany)·2025
Same author

Single-cell RNA-seq analysis identifies the atlas of lymph fluid and reveals a sepsis-related T cell subset.

Cell reports·2025

Related Experiment Video

Updated: Jan 9, 2026

Amplification of Escherichia coli in a Continuous-Flow-PCR Microfluidic Chip and Its Detection with a Capillary Electrophoresis System
14:12

Amplification of Escherichia coli in a Continuous-Flow-PCR Microfluidic Chip and Its Detection with a Capillary Electrophoresis System

Published on: November 21, 2023

2.4K

Label-Efficient PCB Defect Detection with an ECA-DCN-Lite-BiFPN-CARAFE-Enhanced YOLOv5 and Single-Stage

Zhenxia Wang1,2, Nurulazlina Ramli1, Tzer Hwai Gilbert Thio1

  • 1Centre for Sustainability in Advanced Electrical and Electronics Systems (CSAEES), Faculty of Engineering, Built Environment and Information Technology, SEGi University, Petaling Jaya 47810, Malaysia.

Sensors (Basel, Switzerland)
|December 11, 2025
PubMed
Summary

This study introduces an enhanced YOLOv5 model for printed circuit board (PCB) defect detection. The improved detector achieves higher accuracy and efficiency, especially with limited data, supporting intelligent manufacturing.

Keywords:
Innovation and InfrastructurePCB defect detectionYOLOsemi-supervised object detection

More Related Videos

Laser-induced Forward Transfer for Flip-chip Packaging of Single Dies
08:21

Laser-induced Forward Transfer for Flip-chip Packaging of Single Dies

Published on: March 20, 2015

12.9K
High-precision Electromagnetic Flowmeter with Empty Pipe Detection via Complex Programmable Logic Device-based Waveform Recognition
05:11

High-precision Electromagnetic Flowmeter with Empty Pipe Detection via Complex Programmable Logic Device-based Waveform Recognition

Published on: June 27, 2025

596

Related Experiment Videos

Last Updated: Jan 9, 2026

Amplification of Escherichia coli in a Continuous-Flow-PCR Microfluidic Chip and Its Detection with a Capillary Electrophoresis System
14:12

Amplification of Escherichia coli in a Continuous-Flow-PCR Microfluidic Chip and Its Detection with a Capillary Electrophoresis System

Published on: November 21, 2023

2.4K
Laser-induced Forward Transfer for Flip-chip Packaging of Single Dies
08:21

Laser-induced Forward Transfer for Flip-chip Packaging of Single Dies

Published on: March 20, 2015

12.9K
High-precision Electromagnetic Flowmeter with Empty Pipe Detection via Complex Programmable Logic Device-based Waveform Recognition
05:11

High-precision Electromagnetic Flowmeter with Empty Pipe Detection via Complex Programmable Logic Device-based Waveform Recognition

Published on: June 27, 2025

596

Area of Science:

  • Computer Vision
  • Artificial Intelligence
  • Manufacturing Technology

Background:

  • Printed circuit board (PCB) defect detection is crucial for manufacturing quality.
  • Tiny, low-contrast defects and limited labeled data pose significant challenges for conventional detection systems.
  • Existing methods struggle with geometric adaptability and multi-scale feature fusion.

Purpose of the Study:

  • To develop an advanced object detection model for accurate and label-efficient PCB defect inspection.
  • To enhance the You Only Look Once (YOLO) version 5 (YOLOv5) architecture with specialized modules.
  • To implement a semi-supervised learning strategy to leverage unlabeled data effectively.

Main Methods:

  • Modified YOLOv5 with Efficient Channel Attention (ECA), Deformable Convolution (DCN-lite), Bi-Directional Feature Pyramid Network (BiFPN), and Content-Aware ReAssembly of FEatures (CARAFE).
  • Introduced a single-cycle semi-supervised training pipeline using high-confidence pseudo-labels for unlabeled data.
  • Evaluated the model on the PKU-PCB dataset under label-scarce conditions.

Main Results:

  • The enhanced YOLOv5 model achieved a mean Average Precision (mAP@0.5) of 0.910, an improvement from the baseline of 0.870.
  • The semi-supervised approach further boosted performance to 0.943 mAP@0.5.
  • Demonstrated faster convergence and consistent class-wise accuracy gains compared to baseline and other YOLO variants.

Conclusions:

  • The proposed ECA-DCN-lite-BiFPN-CARAFE-enhanced YOLOv5 offers accurate and label-efficient PCB defect detection.
  • The semi-supervised training pipeline effectively utilizes unlabeled data, reducing annotation dependency.
  • The system is suitable for Automated Optical Inspection (AOI) in production, supporting SDG 9 for intelligent manufacturing.