ejhusom

d2m

A machine learning pipeline taking you from raw data to fully trained machine learning model - from data to model (d2m).

Erdre

Erroneous data repair for Industry 4.0. Machine learning pipeline using DVC.

DeepPower

Estimate effort during exercise using deep learning. Power estimation based on breathing patterns.

ejhusom.github.io

Projects by Erik Johannes Husom.

healthAI

Android app for applying machine learning in the health and wellness domain.

inGen

peakbase

Minimalist tool for peak baggers. Manage and visualize your collection of mountain summits privately in the browser.

RespiratoryPatterns

Recognizing respiratory rate and patterns from abdominal movement.

flow

Data collection tool for power and respiratory inductive plethysmography during exercise, using JavaScript and WebBluetooth.

Udava

Unsupervised learning for historical data validation (Udava).

bluehealthpass-ml

Machine learning pipeline used to produce models for the BlueHealthPass project.

codecarbon

Track emissions from Compute and recommend ways to reduce their impact on the environment.

ensemble-explainers

erikjohannesno

fjellregionensridehall

flower

Flower: A Friendly Federated Learning Framework

green-ai

A curated list of Green AI resources.

inGen-explain

keras-uncertainty

Utilities to perform Uncertainty Quantification on Keras Models

label-studio

Label Studio is a multi-type data labeling and annotation tool with standardized output format

mc_dropout_tensorflow

This repository reimplemented "MC Dropout" by tensorflow 2.0 Eager Extension.

MELODI

project-digitalworker

Experiments and code for the DigitalWorker project.

pydocs

Documentation for Python packages.

scaphandre-ollama

stress-detection

tscluster

Clustering time series subsequences.

udava-testing

unclutterium

Fork of Unclutter, a reader mode browser extension to remove distractions from web articles, with telemtry disabled by default.

workout-analysis

Script for visualizing workouts based on file from GPS-watch.