A topological data analysis based classification method for multiple measurements

Henri Riihimäki, Wojciech Chachólski, Jakob Theorell, Jan Hillert, Ryan Ramanujam* (Corresponding Author)

*Corresponding author for this work

Research output: Contribution to journalArticlepeer-review

13 Citations (Scopus)
5 Downloads (Pure)


Background: Machine learning models for repeated measurements are limited. Using topological data analysis (TDA), we present a classifier for repeated measurements which samples from the data space and builds a network graph based on the data topology. A machine learning model with cross-validation is then applied for classification. When test this on three case studies, accuracy exceeds an alternative support vector machine (SVM) voting model in most situations tested, with additional benefits such as reporting data subsets with high purity along with feature values. Results: For 100 examples of 3 different tree species, the model reached 80% classification accuracy after 30 datapoints, which was improved to 90% after increased sampling to 400 datapoints. The alternative SVM classifier achieved a maximum accuracy of 68.7%. Using data from 100 examples from each class of 6 different random point processes, the classifier achieved 96.8% accuracy, vastly outperforming the SVM. Using two outcomes in neuron spiking data, the TDA classifier was similarly accurate to the SVM in one case (both converged to 97.8% accuracy), but was outperformed in the other (relative accuracies 79.8% and 92.2%, respectively). Conclusions: This algorithm and software can be beneficial for repeated measurement data common in biological sciences, as both an accurate classifier and a feature selection tool.

Original languageEnglish
Article number336
Number of pages18
JournalBMC Bioinformatics
Publication statusPublished - 29 Jul 2020

Bibliographical note

HR was partly supported by a collaboration agreement between the University of Aberdeen and EPFL. WC was partially supported by VR 2014-04770 and Wallenberg AI, Autonomous System and Software Program (WASP) funded by Knut and Alice Wallenberg Foundation, Göran Gustafsson Stiftelse. JT is fully funded by the Wenner-Gren Foundation. JH is partially supported by VR K825930053. RR is partially supported by MultipleMS. The collaboration agreement between EPFL and University of Aberdeen played a role in the design of the neuron spiking analysis and in providing the data required, i.e. the neuronal network and the spiking activity. Open access funding provided by Karolinska Institute.


  • Topological data analysis
  • machine learning
  • multiple measurement analysis
  • Machine learning
  • Multiple measurement analysis
  • Trees/anatomy & histology
  • Humans
  • Rats
  • Support Vector Machine
  • Machine Learning
  • Algorithms
  • Animals
  • Lasers
  • Computer Simulation
  • Data Analysis


Dive into the research topics of 'A topological data analysis based classification method for multiple measurements'. Together they form a unique fingerprint.

Cite this