VGU RESEARCH REPOSITORY
Please use this identifier to cite or link to this item:
https://epub.vgu.edu.vn/handle/dlibvgu/1878| DC Field | Value | Language |
|---|---|---|
| dc.contributor.author | Nguyen Ngoc Vinh | en_US |
| dc.date.accessioned | 2024-11-15T07:42:54Z | - |
| dc.date.accessioned | 2024-11-15T07:42:57Z | - |
| dc.date.available | 2024-11-15T07:42:54Z | - |
| dc.date.available | 2024-11-15T07:42:57Z | - |
| dc.date.issued | 2024 | - |
| dc.identifier.uri | https://epub.vgu.edu.vn/handle/dlibvgu/1878 | - |
| dc.description.abstract | The integrated circuit (IC) is a compact electronic device comprising interconnected components such as transistors, resistors, and capacitors. These elements are etched onto a small piece of semiconductor material, typically silicon, through photolithography. ICs are essential to a vast array of electronic devices, including computers, smartphones, and televisions, where they perform critical functions like data processing and storage. However, ICs are vulnerable to external factors such as scratches, dust particles, and electrostatic discharges, which can degrade their performance or lead to complete failure with potentially severe consequences. To address this issue, I propose a machine learning anomaly detection method using the Reconstruction-Based Neural Network approach, which utilizes multiple Convolutional Neural Network Autoencoders. This approach identifies anomalies by analyzing the pattern features found in the microscopic images of the integrated circuits. It utilizes numerous CNN-Autoencoders trained to recognize and differentiate between typical and atypical patterns in the circuitry. The method involves a detailed image mapping process, where masks are used to locate specific anomaly spots on the images. By mapping these masks onto the input images, the system can determine the presence and exact location of an anomaly. Experimental evaluations using real microscopic images showed that the method achieved a high precision rate, successfully identifying and locating anomalies on the ICs with a 91% detection rate | en_US |
| dc.language.iso | en | en_US |
| dc.rights | Attribution-NonCommercial 4.0 International | * |
| dc.rights.uri | https://creativecommons.org/licenses/by-nc/4.0/ | * |
| dc.subject | Integrated circuits | en_US |
| dc.subject | Anomaly detection | en_US |
| dc.subject | Reconstruction-based neural networks | en_US |
| dc.subject | Machine learning | en_US |
| dc.subject | Deep learning | en_US |
| dc.title | Reconstruction-based neural networks for anomaly detection in microscopic integrated circuit images | en_US |
| dc.type | Thesis | en_US |
| item.fulltext | With Fulltext | - |
| item.languageiso639-1 | other | - |
| item.grantfulltext | restricted | - |
| Appears in Collections: | Computer Science (CS) Computer Science (CS) | |
Files in This Item:
| File | Description | Size | Format | Existing users please Login |
|---|---|---|---|---|
| Reconstruction-based neural networks for anomaly detection in microscopic integrated circuit images.pdf | 18.67 MB | Adobe PDF |
Page view(s)
91
checked on Aug 24, 2025
Download(s)
37
checked on Aug 24, 2025
Google ScholarTM
Check
This item is licensed under a Creative Commons License