Skip to content
Snippets Groups Projects
Select Git revision
  • 0d9f3fc2e7bb4b84c8b442f822b9edbe2faa1ac0
  • main default protected
  • 48-replace-mqtt-handling-with-ragconnect
  • dev protected
  • 40-add-mqtt-username-and-password-to-mqttreceiver-java
  • learner
  • Integration_KB_L
  • 0.1
8 results

eraser

René Schöne's avatar
Squashed commit of branch 'learner'
René Schöne authored 
- Fixed pattern to parse datetime coming from openHAB.
- add benchmark
- Create RecognitionEvents in component Plan.
- Add expression printing and fix expression tests.
- Fixing tests.
- Remove build artefacts of datasets module.
- Fixing item behavior.
- Fix bug when adding item using REST API.
  - More debug output for REST application and MQTT receiver
  - Flush cache if new MQTT Host is set
- first integration for test
- update integration activity ML
- add item room_brightness
- add ML Items in starter file
- fix import error
- update newData function
- Fix Learner bugs.
  - Let ExternalMachineLearningModel.check() return true instead of throwing an exception
  - In Learner, use temporary files to store encog model
  - In MachineLearningImpl, do not use result for now (as newData won't work at the moment)
  - Minor fixes for base (add logger, add correct input to jastadd gradle task)
- Progressing to integration of machine learning.
  - Added setKnowledgeBase to MachineLearningEncoder and -Decoder, and removed Root argument in other methods
  - Changed Learner-Impl to match new adapters
  - Updated starter to new adapters, and to use CSV files for initialization of learner
- update readercsv
- Fix imports and dependencies.
- Fix errors with changed MachineLearningEncoder interface.
- upate learner
- add ML interfaces
- implement decode encode
- learner with activity and preference
0d9f3fc2
History
René Schöne's avatar 0d9f3fc2
History
Name Last commit Last update
benchmark
cloc
commons.color
eraser-base
eraser.rest
eraser.spark
eraser.starter
feedbackloop.analyze
feedbackloop.api
feedbackloop.execute
feedbackloop.learner
feedbackloop.learner_backup
feedbackloop.main
feedbackloop.monitor
feedbackloop.plan
gradle/wrapper
influx_test
integration
integration_test
learner_test
ml_test
ml_test_boqi
openhab-mock
org.openhab.action.machinelearn
org.openlicht.action.reinforcementlearning
project-template
skywriter-hue-integration
stub.org.openhab.core.scriptengine.action
ragdoc-view @ 4bb8afb1
.gitignore
.gitlab-ci.yml
.gitmodules
README.md
build.gradle
gradlew
gradlew.bat
make-new-project.py
print-coverage.py
settings.gradle
README.md

pipeline status pipeline status

ERASER - OpenLicht Knowledge Base

Overview

There are a few subprojects in this repository:

  • Base
  • Utility
    • commons.color: Utilities for converting color spaces (XYZ, RGB, HSB)
    • project-template: Template to quickly create new subprojects used by make-new-project.py
  • Demos
    • integration and openhab-mock: Playground projects testing some features
    • skywriter-hue-integration: The first real demonstrator integrating the Skywriter gesture recogintion with a Hue using a simple rule
  • Machine Learning Integration
    • org.openhab.action.machinelearn: openHAB connector of the Machine Learning Part (implemented by Kay)
    • org.openlicht.action.reinforcementlearning: Reinforcement-Learning of preferences (implemented by Kay)
    • stub.org.openhab.core.scriptengine.action: Stub to make the other two projects build

Setup and Building

This project uses Gradle as the build tool. For detailed information, see setup guidelines

Running the demo

There is a demo project, as explained above to showcase the framework. To start it, run ./gradlew :skywriter-hue-integration:run

This demo is intended to run with a pre-configured openHAB instance and has some hard-coded settings. It will first try to connect to an MQTT broker (with a hard-coded IP) to listen on changes of item states. There is one rule implemented, namely to listen on changes of the item skywriter_xyz expecting MQTT messages of the form XVALUE,YVALUE,ZVALUE, and to change to state of another item iris1_item representing the HSB value of a Hue Iris.

Trivia

The name Eraser is a small pun on the term eRACR, which is an extension of RACR for event recognition. It was chosen to ease the search for a good repository image as it is based on a film.