Sep. 2021 - Present
1. Developed a model to detect ship tracks in satellite images with U-net that saves 80% time.
2. Cooperated with multiple domain experts, including Atmospheric Science and Environmental Science, to explore machine learning techniques.
3. Developed a model to classify typhoon tracks with 96.5% accuracy rate.
4. Configured and managed a GPU-enforced workstation for the lab members to execute High Performance Computing (HPC) tasks.
五月 2019 - 八月 2021
1. Developed the end-to-end pipeline to detect Breast Cancer in 3D Breast MRI images, including data storage, data pre-processing, and detection model building. The project passed the pre-submission of FDA.
2. Deployed the Deep-learning Breast Cancer Detection model integrated into the hospital PACS system.
3. Developed the model to segment 3D breast MR images and deployed it to imageJ to speed up annotation to shorten the labeling time three times.
4. Cleaned and labeled the raw Dicom data of breast MRI images manually.
5. Managed the project timeline, updated work records every week and ensured the project direction is correct.
Python, Matlab, Fortran
Machine Learning :
Tree based (i.e. Random Forest, XGBoost)
Clustering (i.e. K-means, DBSCAN)
Dimensionality Reduction (i.e. PCA, t-SNE)
Deep Learning :
Object Detection (i.e. Fast/Faster/Mask R-CNN,)
Image Segmentation (i.e. U-Net)
Generative Adversarial Network (i.e., DCGAN, Cycle GAN)
Explainable AI (i.e. Saliency Map, CAM, LRP)
CNNs, RNNs, transformer
Satellite Image Processing, Medical Image Processing, Abnormal Detection
BlockChain, Quantitative Research
Lightning Prediction with Deep Learning and explain the model with physical methods.
Learning to generate the Manhattan building with Deep Convolutional GAN from OpenStreeMap building model.
Predicting short-term stock market price trends with Machine Learning.
Build an Investment Portfolio machine with a Rebalancing Strategy from scratch.