Martin Geissmann's repositories
fall-detection
Lightweight fall detection based on human pose estimation
economics-related
Some analysis of economics and world trade in R
map-related
map related animation and application
mintos-spark
first steps with Apache Spark in R with sparklyr on a P2P loan dataset from mintos.com
telsearchR
R function for tel.search.ch API
wealthplanning
Retirement wealth planning and simulation in R
investable_indices
exploring the stock market with R
swiss-hospitals-classification
A simple R Shiny app to classify Swiss hospitals according to their DRG positions using clustering and wordclouds
treasuryTR
R package to generate treasury total returns from yield data
alpha-generation
Reviews of popular trading strategies
election-votes
getting data from srgssr polis-api and doing analysis
engagement-ring
R Shiny app that demonstrates clickable images, feather file format, and csv saving user inputs
fmpcloudr
R package for accessing the FMP Cloud API
forextrades
R package to analyze forex trade data
impressive
http://impressive.sourceforge.net/
Leveraged-ETF-premium
2018 review of my 2012 Master's thesis on leveraged ETFs
marketboard
Market information dashboard based on data from fmpcloud.io
Mask_RCNN
Mask R-CNN for object detection and instance segmentation on Keras and TensorFlow
Pneumonia-Diagnosis-using-XRays-96-percent-Recall
BEST SCORE ON KAGGLE SO FAR , EVEN BETTER THAN THE KAGGLE TEAM MEMBER WHO DID BEST SO FAR. The project is about diagnosing pneumonia from XRay images of lungs of a person using self laid convolutional neural network and tranfer learning via inceptionV3. The images were of size greater than 1000 pixels per dimension and the total dataset was tagged large and had a space of 1GB+ . My work includes self laid neural network which was repeatedly tuned for one of the best hyperparameters and used variety of utility function of keras like callbacks for learning rate and checkpointing. Could have augmented the image data for even better modelling but was short of RAM on kaggle kernel. Other metrics like precision , recall and f1 score using confusion matrix were taken off special care. The other part included a brief introduction of transfer learning via InceptionV3 and was tuned entirely rather than partially after loading the inceptionv3 weights for the maximum achieved accuracy on kaggle till date. This achieved even a higher precision than before.
pytorch-generative-adversarial-networks
A very simple generative adversarial network (GAN) in PyTorch
sdcar
end-to-end self-driving car
shiny-lm
Shiny app for feature selection in a linear model
themes-list-hugo
Theme list from https://themes.gohugo.io/