Code samples and datasets that are related to link quality estimation.
Switch branches/tags
Nothing to show
Clone or download
#1 Compare This branch is 5 commits behind sensorlab:master.
Fetching latest commit…
Cannot retrieve the latest commit at this time.
Type Name Latest commit message Commit time
Failed to load latest commit information.

Link quality estimation

Code samples and datasets that are related to link quality estimation.

Directory structure

Datasets (and their corresponding Python scripts) that are related to link quality estimation.
Feature generator is a Python script used for extraction and computation of new features from generic data. Output of this script is labelled data in Attribute-Relation File Format (ARFF), which can be further used for data modelling.
Weka classification model builder (WCMB) is a Java program based on Weka (Waikato Environment for Knowledge Analysis). WCMB is used for building custom classification models in bulk by utilizing all possible combinations of input features.
Window mean with exponentially weighted moving average (WMEWMA) link quality estimator proposed by A. Woo et al. in paper Taming the Underlying Challenges of Reliable Multihop Routing in Sensor Networks implemented as a simple Python script.

Conventional work flow

  1. Transform a dataset to a common format used by the feature generator (use dataset-specific scripts).
  2. Use featureGenerator to generate features and transform the dataset to the common format used by Weka.
  3. Build models with wekaClassificationModelBuilder.


If you are using our datasets or scripts in your research, citation of the following paper would be greatly appreciated.

Kulin, M., Fortuna, C., De Poorter, E., Deschrijver, D., & Moerman, I. (2016). Data-Driven Design of Intelligent Wireless Networks: An Overview and Tutorial. Sensors, 16(6), 790.


See files in individual sub-directories for details.


The research leading to these results has received funding from the European Horizon 2020 Programme project eWINE under grant agreement No. 688116.