Eero Siivola
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Research Subjects
Eero Siivola has a total of 34 co-authors. Here are the top co-authors by number of shared publications:
Aki Vehtari
Department of Computer Science Aalto University Espoo Finland
2 shared publications- Aki Vehtari
Aalto University, Espoo, Finland
2 shared publications Javier González
Microsoft Research Cambridge Microsoft Cambridge UK
2 shared publications- Juho Piironen
University of Turku Turku Finland
2 shared publications - Andrei Paleyes
Computer Science and Technology, University of Cambridge, Cambridge, United Kingdom
1 shared publication Anna-Kaisa Ronkanen
1 shared publication
Latest Publications
- Open Access
- 17 September 2026
- Published by Elsevier in Hydrology Research
A Novel Technique for Identifying Outliers in Correlated Time Series of River and Groundwater Data
- 17 September 2026
- Published by Elsevier in Hydrology Research
Open AccessA Novel Technique for Identifying Outliers in Correlated Time Series of River and Groundwater Data
- Open Access
- 3 June 2026
- Published by Elsevier in Machine Learning with Applications
- Vol. 24
On class imbalance in machine learning-based taxa identification: A comparative analysis of mitigation strategies
- 3 June 2026
- Published by Elsevier in Machine Learning with Applications
- Vol. 24
Open AccessOn class imbalance in machine learning-based taxa identification: A comparative analysis of mitigation strategies
- Open Access
- 18 July 2022
- Published by Elsevier in Environmental Modelling & Software
- Vol. 155
Data fusion system for monitoring water quality: Application to chlorophyll-a in Baltic sea coast
- 18 July 2022
- Published by Elsevier in Environmental Modelling & Software
- Vol. 155
Open AccessData fusion system for monitoring water quality: Application to chlorophyll-a in Baltic sea coast
- Open Access
- 6 May 2021
- Published by Wiley in Applied AI Letters
- Vol. 2 (2) , e24
Good practices for Bayesian optimization of high dimensional structured spaces
The increasing availability of structured but high dimensional data has opened new opportunities for optimization. One emerging and promising avenue is the exploration of unsupervised methods for projecting structured high dimensional data into low dimensional continuous representations, simplifying the optimization problem and enabling the application of traditional optimization methods. However, this line of research has been purely methodological with little connection to the needs of practitioners so far. In this article, we study the effect of different search space design choices for performing Bayesian optimization in high dimensional structured datasets. In particular, we analyses the influence of the dimensionality of the latent space, the role of the acquisition function and evaluate new methods to automatically define the optimization bounds in the latent space. Finally, based on experimental results using synthetic and real datasets, we provide recommendations for the practitioners.
- 6 May 2021
- Published by Wiley in Applied AI Letters
- Vol. 2 (2) , e24
Open AccessGood practices for Bayesian optimization of high dimensional structured spaces
The increasing availability of structured but high dimensional data has opened new opportunities for optimization. One emerging and promising avenue is the exploration of unsupervised methods for projecting structured high dimensional data into low dimensional continuous representations, simplifying the optimization problem and enabling the application of traditional optimization methods. However, this line of research has been purely methodological with little connection to the needs of practitioners so far. In this article, we study the effect of different search space design choices for performing Bayesian optimization in high dimensional structured datasets. In particular, we analyses the influence of the dimensionality of the latent space, the role of the acquisition function and evaluate new methods to automatically define the optimization bounds in the latent space. Finally, based on experimental results using synthetic and real datasets, we provide recommendations for the practitioners.
- Open Access
- 15 February 2021
- Published by Wiley in Statistics in Medicine
- Vol. 40 (10) , 2355-2372
Qualifying drug dosing regimens in pediatrics using Gaussian processes
Drug development commonly studies an adult population first and then the pediatric population. The knowledge from the adult population is taken advantage of for the design of the pediatric trials. Adjusted drug doses for these are often derived from adult pharmacokinetic (PK) models which are extrapolated to patients with smaller body size. This extrapolation is based on scaling physiologic model parameters with a body size measure accounting for organ size differences. The inherent assumption is that children are merely small adults. However, children can be subject to additional effects such as organ maturation. These effects are not present in the adult population and are possibly overlooked at the design stage of the pediatric trials. It is thus crucial to qualify the extrapolation assumptions once the pediatric trial data are available. In this work, we propose a model based on a non‐parametric regression method called Gaussian process (GP) to detect deviations from the made extrapolation assumptions. We introduce the theoretical background of this model and compare its performance to a parametric expansion of the adult model. The comparison includes simulations and a clinical study data example. The results show that the GP approach can reliably detect maturation trends from sparse pediatric data.
- 15 February 2021
- Published by Wiley in Statistics in Medicine
- Vol. 40 (10) , 2355-2372
Open AccessQualifying drug dosing regimens in pediatrics using Gaussian processes
Drug development commonly studies an adult population first and then the pediatric population. The knowledge from the adult population is taken advantage of for the design of the pediatric trials. Adjusted drug doses for these are often derived from adult pharmacokinetic (PK) models which are extrapolated to patients with smaller body size. This extrapolation is based on scaling physiologic model parameters with a body size measure accounting for organ size differences. The inherent assumption is that children are merely small adults. However, children can be subject to additional effects such as organ maturation. These effects are not present in the adult population and are possibly overlooked at the design stage of the pediatric trials. It is thus crucial to qualify the extrapolation assumptions once the pediatric trial data are available. In this work, we propose a model based on a non‐parametric regression method called Gaussian process (GP) to detect deviations from the made extrapolation assumptions. We introduce the theoretical background of this model and compare its performance to a parametric expansion of the adult model. The comparison includes simulations and a clinical study data example. The results show that the GP approach can reliably detect maturation trends from sparse pediatric data.
- Open Access
Correcting boundary over-exploration deficiencies in Bayesian optimization with virtual derivative sign observations
Bayesian optimization (BO) is a global optimization strategy designed to find the minimum of an expensive black-box function, typically defined on a compact subset of $\mathcal{R}^d$, by using a Gaussian process (GP) as a surrogate model for the objective. Although currently available acquisition functions address this goal with different degree of success, an over-exploration effect of the contour of the search space is typically observed. However, in problems like the configuration of machine learning algorithms, the function domain is conservatively large and with a high probability the global minimum does not sit on the boundary of the domain. We propose a method to incorporate this knowledge into the search process by adding virtual derivative observations in the \gp at the boundary of the search space. We use the properties of GPs to impose conditions on the partial derivatives of the objective. The method is applicable with any acquisition function, it is easy to use and consistently reduces the number of evaluations required to optimize the objective irrespective of the acquisition used. We illustrate the benefits of our approach in an extensive experimental comparison.Open AccessCorrecting boundary over-exploration deficiencies in Bayesian optimization with virtual derivative sign observations
Bayesian optimization (BO) is a global optimization strategy designed to find the minimum of an expensive black-box function, typically defined on a compact subset of $\mathcal{R}^d$, by using a Gaussian process (GP) as a surrogate model for the objective. Although currently available acquisition functions address this goal with different degree of success, an over-exploration effect of the contour of the search space is typically observed. However, in problems like the configuration of machine learning algorithms, the function domain is conservatively large and with a high probability the global minimum does not sit on the boundary of the domain. We propose a method to incorporate this knowledge into the search process by adding virtual derivative observations in the \gp at the boundary of the search space. We use the properties of GPs to impose conditions on the partial derivatives of the objective. The method is applicable with any acquisition function, it is easy to use and consistently reduces the number of evaluations required to optimize the objective irrespective of the acquisition used. We illustrate the benefits of our approach in an extensive experimental comparison. - 1 June 2018
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 341-345
Alarm Prediction in LTE Networks
Antenna line alarms are a significant indicator for failing components in LTE base stations. By predicting such alarms it is possible to prepare for system repairs or for system resets in advance, which reduces the maintenance downtime for LTE operators when a hardware failure actually occurs. In this paper we present results from an antenna line alarm prediction method in a real LTE network. The prediction model is based on the behavior of a large set of performance counters (PMs) collected in a timeseries in the LTE base stations. We create the alarm prediction model by using the random forest search method and we reach and accuracy of 67-72% From this, we pinpoint the most influential PMs for predicting different types of alarms and we discuss how to use these PMs in future research.
- 1 June 2018
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 341-345
Alarm Prediction in LTE Networks
Antenna line alarms are a significant indicator for failing components in LTE base stations. By predicting such alarms it is possible to prepare for system repairs or for system resets in advance, which reduces the maintenance downtime for LTE operators when a hardware failure actually occurs. In this paper we present results from an antenna line alarm prediction method in a real LTE network. The prediction model is based on the behavior of a large set of performance counters (PMs) collected in a timeseries in the LTE base stations. We create the alarm prediction model by using the random forest search method and we reach and accuracy of 67-72% From this, we pinpoint the most influential PMs for predicting different types of alarms and we discuss how to use these PMs in future research.
- Open Access
Requirement verification in simulation-based automation testing
The emergence of the Industrial Internet results in an increasing number of complicated temporal interdependencies between automation systems and the processes to be controlled. There is a need for verification methods that scale better than formal verification methods and which are more exact than testing. Simulation-based runtime verification is proposed as such a method, and an application of Metric temporal logic is presented as a contribution. The practical scalability of the proposed approach is validated against a production process designed by an industrial partner, resulting in the discovery of requirement violations.
Open AccessRequirement verification in simulation-based automation testing
The emergence of the Industrial Internet results in an increasing number of complicated temporal interdependencies between automation systems and the processes to be controlled. There is a need for verification methods that scale better than formal verification methods and which are more exact than testing. Simulation-based runtime verification is proposed as such a method, and an application of Metric temporal logic is presented as a contribution. The practical scalability of the proposed approach is validated against a production process designed by an industrial partner, resulting in the discovery of requirement violations.
- Open Access
Automatic monotonicity detection for Gaussian Processes
We propose a new method for automatically detecting monotonic input-output relationships from data using Gaussian Process (GP) models with virtual derivative observations. Our results on synthetic and real datasets show that the proposed method detects monotonic directions from input spaces with high accuracy. We expect the method to be useful especially for improving explainability of the models and improving the accuracy of regression and classification tasks, especially near the edges of the data or when extrapolating.
Open AccessAutomatic monotonicity detection for Gaussian Processes
We propose a new method for automatically detecting monotonic input-output relationships from data using Gaussian Process (GP) models with virtual derivative observations. Our results on synthetic and real datasets show that the proposed method detects monotonic directions from input spaces with high accuracy. We expect the method to be useful especially for improving explainability of the models and improving the accuracy of regression and classification tasks, especially near the edges of the data or when extrapolating.