Wafer prediction, underwater image classification, and recycled FPGA detection.
ミア リアーズ ウル ハック
MIAN RIAZ UL HAQUE
助教
| 学部等 |
総合理工学部
知能情報デザイン学科
|
|---|---|
| researchmap 個人URL |
https://researchmap.jp/mian_riaz |
| SDGs |
|
| ホームページURL |
産業分野
- 製造業 / 電子部品・デバイス・電子回路製造業
researchmap
研究分野
- 情報通信 / 計算機システム / Multi site VLSI test
- 環境・農学 / 環境農学 / Sea grass Detection of under water water
- 自然科学一般 / 半導体、光物性、原子物理 / Detection of Recycled FPGAs
研究キーワード
Wafer-level Variation Modeling, Multi-site RF IC Testing, Hierarchical Gaussian Process, Computer Vision, Seagress, Semisupervised
研究概要
1.We propose a Gaussian process-based method for wafer-level performance prediction in multi-site testing, enhancing accuracy via hierarchical modeling of site-to-site variation.
2. HALT (Hierarchical Active Learning-based Technique) improves seagrass image classification by 1.4% through strategic data selection and transfer learning.
3. Adaptive kernel strategies for GPR improved wafer-level and FPGA delay modeling using real silicon and industry data.
2. HALT (Hierarchical Active Learning-based Technique) improves seagrass image classification by 1.4% through strategic data selection and transfer learning.
3. Adaptive kernel strategies for GPR improved wafer-level and FPGA delay modeling using real silicon and industry data.
アピールポイント
Specializing in hardware security, wafer-level modeling, and AI-based image classification for environmental monitoring and recycled FPGA detection.