wrote chapter Isolation forest

predict_pipeline/prediction_env.yaml

@@ -193,4 +193,4 @@ dependencies:
       - pytz==2025.2
       - scikit-learn==1.6.1
       - tzdata==2025.3
-prefix: C:\Users\micha\anaconda3\envs\310
+

project_report.md

@@ -104,6 +104,14 @@ Supporting utilities in ```model_training/tools```:
 ### 4.1 CNNs
 ### 4.2 XGBoost
 ### 4.3 Isolation Forest
+To start with unsupervised learning techniques, `IsolationForest.ipynb`was created to research how well a simple ensemble classificator performs on the created dataset. 
+The notebook comes with one class grid search for hyperparameter tuning as well as a ROC curve that allows manual fine tuning. 
+Overall, our experiments have shown, that this approach is not sufficient, with the following results: 
+| Metric / Model | Isolation Forest | 
+|----------------|---------|
+| Best Balanced Accuracy |0.575|
+| Best AUC | 0.617 |
+In detail, the classificator tends to classify the majority of samples as low load. 
 ### 4.4 OCSVM
 ### 4.5 DeepSVDD
 

readme.md

@@ -11,16 +11,17 @@ Activate the conda-repository "".
 ```bash
     conda activate
 ```
-Make sure, another environment that fulfills prediction_env.yaml is available, matching with predict_pipeline/predict.service - See `predict_pipeline/predict_service_timer_documentation.md`
+**Make sure, another environment that fulfills prediction_env.yaml is available**, matching with predict_pipeline/predict.service 
-To get an overview over all available conda environments on your device, use this command in anaconda prompt terminal: 
+See `predict_pipeline/predict_service_timer_documentation.md`
+to get an overview over all available conda environments on your device, use this command in anaconda prompt terminal: 
 ```bash
     conda info --envs
 ```
-Create a new environment based on the yaml-file:
+Optionally, create a new environment based on the yaml-file:
 ```bash
     conda env create -f prediction_env.yaml
 ```
-
+Ohm-UX driving simulator jetson board only: The conda-environment `p310_FS_TF` is used for predictions. 
 
 ### 2) Camera AU + Eye Pipeline (`camera_stream_AU_and_ET_new.py`)