Data science applications

Data science in various domains

Selected publications

Paleobiology and hominin environments

  • A survey of computational methods for fossil data analysis by Žliobaitė et al. 2017 in Evolutionary Ecology Research. PDFpreprint
  • Relative abundances and palaeoecology of four suid genera in the Turkana Basin, Kenya, during late Miocene to Pleistocene by
  • Ecosystem evolution and hominin paleobiology at East Turkana, northern Kenya between 2.0 and 1.4 Ma by Patterson et al. 2017 in Palaeogeography, Palaeoclimatology, Palaeoecology. DOI
  • Herbivore teeth predict climatic limits in Kenyan ecosystems by Žliobaitė et al. 2016 in PNAS, DOI (open access)
  • An ecometric analysis of the fossil mammal record of the Turkana Basin by Fortelius et al. 2016 in Philosophical Transactions B. DOI (open access)

Forestry and atmospheric sciences

  • Environmental control of growth variation in a boreal Scots pine stand – a data-driven approach by Kulmala et al. 2016 in Silva Fennica. DOI (open access)
  • Regression models tolerant to massively missing data: a case study in solar radiation nowcasting by Žliobaitė et al. 2014 in Atmospheric Measurement Techniques. DOI (open access)


  • Predicting respiratory motion for real-time tumour tracking in radiotherapy by Krilavičius et al. 2016 in IEEE CBMS. DOI PDF
  • Correlation of external markers and functional targets for respiration compensation in radiotherapy by Krilavičius et al. 2013 in Medical Physics in the Baltic States. slides
  • Heart Failure Hospitalization Prediction in Remote Patient Management Systems by Pechenizkiy et al. 2010 in IEEE CBMS. DOI PDF

Industrial engineering and energy

  • Online Detection of Shutdown Periods in Chemical Plants: A Case Study by Martin-Salvador et al. 2014 in Procedia Computer Science. DOI
  • From Sensor Readings to Predictions: on the Process of Developing Practical Soft Sensors by Budka et al. 2014 in IDA. DOI PDF
  • Online Mass Flow Prediction in CFB Boilers with Explicit Detection of Sudden Concept Drift in by Pechenizkiy et al. 2009 in SIGKDD Explorations. DOI PDF

Hardware design

  • A 5.3 pJ/op approximate TTA VLIW tailored for machine learning by Teittinen et al. 2017 in Microelectronics Journal DOI
  • Towards hardware-driven design of low-energy algorithms for data analysis by Žliobaitė et al. 2014 in SIGMOD Record. PDF DOI

Traffic and mobility

  • Optimal estimates for short horizon travel time prediction in urban areas by Žliobaitė and Khokhlov 2016 in Intelligent Data Analysis. DOI PDF
  • Labeling Sensing Data for Mobility Modeling by Read et al. 2016 in Information Systems. DOI PDF
  • Accessibility by public transport predicts residential real estate prices: a case study in Helsinki region by Žliobaitė et al. 2015 in MUD workshop. PDF
  • Context-aware Personal Route Recognition by Mazhelis et al. 2011 in Discovery Science. DOI PDF

Process mining

  • Dealing with Concept Drifts in Process Mining by Bose et al. 2014 in IEEE Transactions on Neural Networks and Learning Systems. DOI
  • Dealing With Concept Drifts in Process Mining: A Case Study in a Dutch Municipality by Bose, et al. 2013, Technical Report PDF

Sales prediction and customer profiling

  • Beating the baseline prediction in food sales: How intelligent an intelligent predictor is? by Žliobaitė et al. 2012 in Expert Systems with Applications. DOI PDF
  • Predicting Multi-Class Customer Profiles Based on Transactions: a Case Study in Food Sales by Apeh et al. 2012 in SGAI. DOI PDF