The Special Interest Group on Spatio-Temporal Data Mining (SIG-STDM) was founded by Dr Mitra Baratchi, in 2019 to provide a platform for the exchange of knowledge on topics related to spatial, temporal, and spatio-temporal data mining. SIG-STDM brings together and connects the researchers of Leiden Institute for Advanced Computer Science (LIACS) and Leiden Center of Data Science (LCDS) who focus on the design of machine learning algorithms suited for modelling geospatial, time-series, and spatio-temporal data as well as their application in a variety of scientific, industrial, urban, and environmental domains.
Our members come from a diverse range of backgrounds and interests, unified by their shared interest in spatial, temporal and spatio-temporal data.
Mitra is an assistant professor at LIACS. She is also affiliated with LCDS, and Leiden-Delft-Erasmus (LDE) center for BOLD Cities. Her research interest lies in spatio-temporal, time-series, spatio-temporal, and mobility data modeling. More specifically, she aims at designing algorithms that extract patterns from such data in a fully automated manner. Such research is targeting applications in a broad range of urban, environmental, and industrial domains for which she has collaborations notably with the European Space Agency, Honda Research Institute, various municipalities, and researchers in other scientific disciplines.
Before joining LIACS, Mitra was a postdoctoral researcher in the Design and Analysis of Communication Systems Research (DACS) Group at the University of Twente. Prior to that, she was a researcher in the Ambient Intelligence Research Group at Saxion University of Applied Sciences. In June 2015, she received her PhD. degree in Computer Science from University of Twente.
Matthijs van Leeuwen
Matthijs is associate professor and group leader of the Explanatory Data Analysis group at the Leiden Institute of Advanced Computer Science (LIACS), Leiden University. He likes data, patterns, algorithms, and information theory. He strives for data mining and machine learning methods and results that are principled, interpretable, and incorporate domain knowledge.
Matthijs was previously a senior researcher (2015-2016) and tenure track assistant professor (2016-2020) at LIACS. Before that, he was a postdoctoral researcher at Universiteit Utrecht for almost two years (2009-2011) and in the Machine Learning group of KU Leuven for four years (2011-2015). He defended his Ph.D. thesis titled Patterns that Matter in February 2010, which he wrote under supervision of prof.dr. Arno Siebes in the Algorithmic Data Analysis group of Universiteit Utrecht.
Iris is a postdoc at LIACS involved in the D-ActWheels project with Prof.dr. Kraaij. Within this project, accelerometer data from wearables and indirect calorimetry data is used for human activity recognition and energy expenditure estimation models aimed at promoting a healthy lifestyle for wheelchair users. Her research interests involve the integration of multimodal data, the use and analyses of wearable data, psychometrics and applied statistics.
Iris has obtained her master’s degree in Brain and Cognition Psychology at the Erasmus University Rotterdam and in Methodology and Statistics in Psychology at Leiden University. In September 2019, she obtained her PhD in psychometrics from the Erasmus University Rotterdam, titled ‘Testing in higher education: decisions on student’s performance’.
Daniela is a PhD researcher at LIACS working on methods to integrate multimodal data and extract information from such data. Her research is part of the project Dementia Back in the Heart of the Community where the use of a public park by patients with dementia, their families and people from the neighbourhood is assessed. Her work is supervised by Dr Matthijs van Leeuwen, her promotor is Prof.dr. Aske Plaat.
Stelios is a PhD candidate at Leiden University Medical Center (LUMC) with a background in Computer Science and Mathematics. His research interest is on machine learning tools and methodologies for human activity recognition and energy expenditure estimation using wearable sensor data (time series data). His work focuses on healthy ageing and how physical activity of older individuals is linked to parameters of metabolic health. He is supervised by Dr M.Beekman (LUMC) and Dr A.Knobbe (LIACS), his promotor is Prof. E.Slagboom (LUMC).
Nuno César de Sá
Nuno is a PhD researcher within LCDS at the Institute of Environmental Science (CML) of Leiden University on the topic of Earth observation for Ecosystem processes. His research explores the use of big data and cloud computing opportunities in the field of Earth observation to monitor biodiversity variables with a focus on Rewilding and nature-driven solutions. He is supervised by Dr Mitra Baratchi (LIACS) and Prof.dr.ir. P.M. van Bodegom (CML).
Wouter Verschoof-van der Vaart
Wouter is a PhD researcher within LCDS at the Faculty of Archaeology. His research focuses on combining Deep Learning and Geographic Information Systems for the automated detection of archaeology in remotely sensed data. He is supervised by Dr Karsten Lambers and Dr Wojtek Kowalczyk.
Duc Nguyen joined LIACS in October 2017 to work on the “Cross-Industry Platform for Predictive Maintenance Optimization (CIMPLO)” project. This project is a collaboration between LIACS, KLM and Honda. The project aims at developing a cross-industry predictive maintenance optimization platform, which addresses the real-world requirements for dynamic, scalable multiple-criteria maintenance scheduling. Although the system's capabilities will be demonstrated on the application of aircraft engines (KLM) and passenger cars (Honda), it will be developed as a cross-industry platform for generic applications in predictive, multi-objective, dynamic maintenance scheduling. His main interest is predictive maintenance where he uses time-series data from sensors to predict upcoming failures and remaining useful lifetime of systems, sub-system, and/or components in complex engineered systems.
Marios Kefalas joined LIACS in September 2015 as a master's student in Computer Science and since April 2018 has a PhD. position in the Natural Computing group under the supervision of Prof.dr. Thomas Baeck and Dr. Mitra Baratchi in the CIMPLO project. He has a background in pure and applied Mathematics and Bioinformatics. His interests are in time series analysis, predictive modelling, forecasting, optimization and applications.
Zhou joined the ADA research group at LIACS in September 2019 as a visiting PhD student under the supervision of Prof.dr. Holger Hoos and Dr Mitra Baratchi. In his research, he focuses on time-series data mining techniques, including pre-processing, representation, classification and prediction. He is now working on online time-series segmentation with the purpose of dimension reduction, especially on how to apply Automated Machine Learning methods for this task.
Can joined the ADA research group at LIACS in January 2018 as a PhD. candidate under the supervision of prof.dr. Holger H. Hoos, prof.dr.Thomas Bäck, and Dr Mitra Baratchi. Before joining LIACS, she was a researcher under the supervision of Beng Chin Ooi at School of Computing, National University of Singapore. Can received her master degrees from Ecole Centrale Paris (France) and Université libre de Bruxelles (Belgium) by majoring in computer science in 2017.
Can's research interests include automated machine learning, dynamic data analytics, data mining and general machine learning. Currently, she is working at project 'Dynamic Data Analytics through automatically Constructed Machine Learning Pipelines'. This research aims at developing a platform for dynamic data analytics that is based on techniques for automatically constructing machine learning pipelines for the task at hand.
Marieke is a PhD student working on the 'Data Science for State-of-the-Art Blood Banking' (BloodStart) project. This project is a collaboration between Sanquin and Leiden University, and aims to significantly improve the prediction of donor medical test outcomes and donor behaviour. Data of the past 20 years is available, on around 12 million donations. The BloodStart project will deliver enhanced data-driven models and evidence-based donor management strategies that will maximise the effectiveness of resources and minimise donor loss. The main supervisors of the project will be Mart Janssen from Sanquin and Matthijs van Leeuwen and Aske Plaat from Leiden University.
Marieke completed the Master Statistical Science with a specialisation in Data Science in 2018 at Leiden University. Her Bachelor's degree is in Biology, and she enjoys combining knowledge from both scientific areas in her research.
Maedeh Nasri is a PhD candidate at the Department of Developmental and Educational Psychology (Institute of Psychology) at Leiden University. Her PhD project is embedded in a larger research project called “Data‐driven, urban policymaking for social inclusion of young, vulnerable people” within the Centre for BOLD Cities, as part of the NWO-funded 'Breaking the cycle' project.
Within this larger project, Maedeh will focus on designing algorithms that extract patterns representing individual and social behaviours of pupils; and their use of space; thus exploring the complex interaction patterns over time and in space of prosocial behaviour and its links with structural and functional developmental changes.
Maedeh's PhD project is supervised by Prof.dr. Carolien Rieffe, Dr Mitra Baratchi (LIACS), Dr Sarah Giest (Leiden University) and Dr Alexander Koutamanis (Delft University of Technology).
Laurens is a PhD student at LIACS under the supervision of Mitra Baratchi, Holger Hoos and Peter van Bodegom. Prior to this, he joined SIG-STDM as a MSc student, and he obtained his Master's degree at Leiden University in 2020.
Laurens' research is funded by an NWO ENW-KLEIN grant awarded to Mitra Baratchi for her project named "Physics-aware Spatio-temporal Machine Learning for Earth Observation Data", which involves a collaboration with the European Space Agency. The goal of the project is to create hybrid models of mutually interacting environmental processes on Earth, combining theory-driven physical models and data-diven machine learning models using Earth observation data.
Gilles is a Master’s student in Computer Science at LIACS. Previously, he finished his Bachelor studies in Computer Science and Economics at LIACS and the Erasmus School of Economics and parallel to that he completed his Bachelor’s degree in Psychology at Leiden University. His interests span the fields of AI, Machine Learning, Optimization and High Performance Computing, and their applications to real-world problems.
He is working on his Master's thesis where he is developing a system for the automated selection and configuration of early time series classification algorithms, under the supervision of Can Wang, Dr Mitra Baratchi, and Prof.dr. Holger Hoos.
Frederick van der Meulen
Frederick is a Master’s student in Computer Science: Advanced Data Analytics student at LIACS. His interests lie in the field of Machine Learning, Neural Networks, Artificial Intelligence and Lossless data compression techniques. He is currently working on his master’s thesis.
Nelly Rosaura Palacios Salinas
Nelly is a Master’s student in the Computer Science: Advanced Data Analytics program at LIACS. She holds a Bachelor's degree in Applied Mathematics and Computer Science from the National Autonomous University of Mexico. She completed a research program on Information Analysis of Web Contents in Social Media at the Kanazawa Institute of Technology supported by the Japan International Cooperation Agency. Her fields of interest are Urban Computing, Distributed Data Mining, and Automated Machine Learning.
She's currently doing her Master’s Project under the supervision of Dr Mitra Baratchi and Dr Jan van Rijn. Nelly wants to analyze the outcomes of employing Automated Machine Learning methods for Satellite imagery analysis, as well as the hyperparameter importance of deep learning models for this task. To achieve this, she collaborates with researchers from the European Space Agency (ESA-ESRIN).
Jaco is a Master’s student in Computer Science & Advanced Data Analytics within the Artificial Intelligence track. He is working on his master thesis project on COVID-19 spread prediction. The aim of his project is to enhance existing epidemiology models using new mobility data sets. He works under the supervision of Dr Mitra Baratchi and Prof.dr. Holger Hoos.
Fan Yang works as a PhD student at LIACS. His research interests include automated machine learning, data mining, time series data analysis and blockchain technology. The aim of his research is to use time series data mining methods for classification, regression, and the automated optimization of parameter settings in data mining algorithms. In addition, recent projects aim to use automated machine learning methods for earthquake time to failure prediction, and to propose an automated machine learning model using EEG data to achieve the task of depression level forecasting.
Students who graduated and other valued former members of our group.
|02 September 2021|| Ahnjili Zhuparris ||TBA|
|08 July 2021|| Stelios Paraschiakos ||Quantifying physical activity in older people to study healthy ageing, the GOTO study|
|10 June 2021|| Jaco Tetteroo ||Automated COVID-19 Forecasting|
|12 May 2021|| Annelinde Lettink ||Movement Sequence Mapping: Cut-Points Based vs. Data-Driven Method|
|15 April 2021|| Saskia Koldijk ||Detecting Physiological Arousal in Children Using a Wearable|
|18 March 2021|| Maedeh Nasri ||Siamese Hybrid Architectures for Learning Trajectory Similarity|
|21 January 2021|| Daniela Gawehns ||Finding Questions in Temporal Data|
|26 November 2020|| Iris Yocarini ||Classification Wheelchair Activities|
|29 October 2020|| Wouter Verschoof ||CarcassonNet: A Novel Approach to Detect and Trace Medieval Hollow Roads in LiDAR Data|
|3 September 2020|| Dafne van Kuppevelt and Vincent van Hees ||(Automated) Machine Learning for Time Series Classification|
|30 July 2020|| Laurens Arp||A Markov Reward Process-inspired method for spatial interpolation enhanced by spatial features|
|2 July 2020||Gilles Ottervanger|| AutoML for Early Time Series Classification|
|11 June 2020||Duc Nguyen|| Predictive Maintenance: Case study Error Classification of Electrical Motor|
|14 May 2020||Marieke Vinkenoog||Time Series Analysis for Blood Donors|
|16 April 2020||Nuno César de Sá||Challenges of Estimating Biophysical Rraits of Vegetation in RS|
|19 March 2020||Stylianos Paraschiakos|| Activity Recognition and Energy Expenditure Estimation towards a Healthy Ageing|
|27 February 2020||Marios Kefalas|| Time-series Analysis for Remaining Useful Life Estimation|