ahmadmobeen.github.io

---

Project maintained by ahmadmobeen Hosted on GitHub Pages — Theme by mattgraham

Ahmad Mobeen

Welcome to my page.

Career Interests

• Image-to-Image translation, Image Super-Resolution, Denoising
• Neural Architecture Search, AtuoML
• Object Detection, Video Analysis, Small-object detection

Projects

Neural Architecture Search (NAS) usinng Binary Crow Search Algorithm

Binary Crow Search Algorithm (BCSA) is inspired by the original Crow Search Algorithm (CSA). However, CSA is not compatible to be used for NAS. CSA deals with continuous numbers for calculation of distance between the targets and the agents whereas in NAS we cannot differentiate between several neural network architectures using a continuous number. Therefore, a Binary Encoding Scheme is integrated with CSA, hence named Binary CSA. The binary encoding scheme is as follows:

Stepwise Transfer Learning

Synthetic Disguise Face Generation

Small-Object Detection

Video Quality Enchancement

Satellite Image Denoising

Patents

• CycleGAN 및 IoU 손실을 활용한 이미지 생성 방법 및 장치 (Image Generation Method and Apparatus Using CycleGAN and IoU loss)- (pending)
• 단계적 전이 학습 기반 합성곱 신경망을 활용한 분류 방법 및 장치 (Classification Method and Apparatus Using CNN with Stepwise Transfer Learning) – (pending)
• 까마귀 탐색 알고리즘에 기반한 인공 신경망 구조의 자동 설계 방법 및 장치 (출원 예정) {METHOD AND APPARATUS FOR AUTOMATIC DESIGN OF ARTIFICIAL NEURAL NETWORK STRUCTURE BASED ON CROW SEARCH ALGORITHM} - 10-2020-0135247

Selected Publications

• M. Ahmad, U. Cheema, M. Abdullah, S. Moon, and D. Han, “Generating Synthetic Disguise Face Database using Cycle-Consistency Loss and Automatic Filtering Algorithm”, in Mathematics. 2022, 10, 4. https://doi.org/10.3390/math10010004.
• M. Ahmad, M. Abdullah, H. Moon, and D. Han, “Plant Disease Detection in Imbalanced Datasets Using Efficient Convolutional Neural Networks with Stepwise Transfer Learning,” in IEEE Access, vol. 9, pp. 140565-140580, 2021, doi: https://doi.org/10.1109/ACCESS.2021.3119655.
• M. Ahmad, M. Abdullah, H. Moon, S. J. Yoo, and D. Han, “Image Classification Based on Automatic Neural Architecture Search using Binary Crow Search Algorithm,” in IEEE Access, doi: https://doi.org/10.1109/ACCESS.2020.3031599.
• U. Cheema, M. Ahmad, Dongil Han, Seungbin Moon, “Heterogeneous Visible-Thermal and VisibleInfrared Face Recognition Using Cross-Modality Discriminator Network and Unit-Class Loss”, Computational Intelligence and Neuroscience, vol. 2022, Article ID 4623368, 15 pages, 2022. https://doi.org/10.1155/2022/4623368.
• M. Ahmad, M. Abdullah, and D. Han, “Video Quality Enhancement using Generative Adversarial Networks-based Super-Resolution and Noise Removal”, in 2021 36th International Technical Conference on Circuits/Systems, Computers and Communications (ITC-CSCC), Jeju, Korea, 2021 https://doi.org/10.1109/ITC-CSCC52171.2021.9568313.
• M. Abdullah, M. Ahmad, and D. Han, “Hierarchical Attention Approach in Multimodal Emotion Recognition for Human Robot Interaction” in 2021 36th International Technical Conference on Circuits/Systems, Computers and Communications (ITC-CSCC), Jeju, Korea, 2021. https://doi.org/10.1109/ITC-CSCC52171.2021.9501446.
• M. Ahmad, M. Abdullah, and D. Han, “Small Object Detection in Aerial Imagery using RetinaNet with Anchor Optimization,” 2020 International Conference on Electronics, Information, and Communication (ICEIC), Barcelona, Spain, 2020, pp. 1-3, doi: https://doi.org/10.1109/ICEIC49074.2020.9051269.
• M. Ahmad, J. Joe, and D. Han, “CortexNet: Convolutional Neural Network with Visual Cortex in human brain,” 2018 IEEE International Conference on Consumer Electronics - Asia (ICCE-Asia), Jeju, 2018, pp. 206-212, doi: https://doi.org/10.1109/ICCE-ASIA.2018.8552151.

Resume

The resume can be downloaded from here.

Contact

ahmadmobeen24@gmail.com