Analyzing various regularization parameter for k-space based parallel MR image reconstruction
Using variational interpolation method to remove cloud from flood satellite images
Predicting rainfall using multi-stage logistics regression and naive bayes from weather data
We propose a superpixel-based fast FCM (SFFCM) for color image segmentation. The proposed algorithm is able to achieve color image segmentation with a very low computational cost, yet achieve a high segmentation precision.
A fast and robust fuzzy c-means clustering algorithms, namely FRFCM, is proposed. The FRFCM is able to segment grayscale and color images and provides excellent segmentation results.
The purpose off this project is o investigate the potential of using passive microwave brightness temperature and emissivity data sets from satellite observationsto monitor recent land cover/land use changes and droughts. Temperature and emissivity data at differentvarious frequencies will be formulated to calculate global land surface emissivityfor the last three dacades.The estimates are then compared against the independent drought indicators which are based on percipitation and soil moisture data records.
In this paper, a novel adaptive morphological reconstruction (AMR) operation is proposed. AMR is able to obtain better seed images to improve the seeded segmentation algorithms.
We proposed an automatic fuzzy clustering framework (AFCF) for image segmentation which is published in Transactions on Fuzzy Systems, 2020.
This machine learning project learnt and predicted rainfall behavior based on 14 weather features. Applied KNN model, Clustering model and Random Forest model.
Rainfall prediction models (Linear and Logistic) trained on publicly available datasets from Austin, Texas
A system for airport weather forecasting based on circular regression trees
