Petri Myllymäki
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
Petri Myllymäki has a total of 72 co-authors. Here are the top co-authors by number of shared publications:
- Teemu Roos
Department of Computer Science, University of Helsinki, Helsinki, Finland
11 shared publications Samuel Kaski
Aalto University, Finland
5 shared publications- Giulio Jacucci
University of Helsinki
4 shared publications - Jaakko Peltonen
Tampere University, Tampere, Finland
4 shared publications Petri Kontkanen
Complex Systems Computation Group, Helsinki Institute for Information Technology HIIT, University of Helsinki & Helsinki University of Technology, P.O.Box 68 (Department of Computer Science), FIN-00014 University of Helsinki, Finland
4 shared publications- Tuukka Ruotsalo
University of Copenhagen
4 shared publications
Latest Publications
- Open Access
- 3 October 2018
- Published by Association for Computing Machinery (ACM) in ACM Transactions on Information Systems
- Vol. 36 (4) , 1-46
Interactive Intent Modeling for Exploratory Search
Exploratory search requires the system to assist the user in comprehending the information space and expressing evolving search intents for iterative exploration and retrieval of information. We introduce interactive intent modeling, a technique that models a user’s evolving search intents and visualizes them as keywords for interaction. The user can provide feedback on the keywords, from which the system learns and visualizes an improved intent estimate and retrieves information. We report experiments comparing variants of a system implementing interactive intent modeling to a control system. Data comprising search logs, interaction logs, essay answers, and questionnaires indicate significant improvements in task performance, information retrieval performance over the session, information comprehension performance, and user experience. The improvements in retrieval effectiveness can be attributed to the intent modeling and the effect on users’ task performance, breadth of information comprehension, and user experience are shown to be dependent on a richer visualization. Our results demonstrate the utility of combining interactive modeling of search intentions with interactive visualization of the models that can benefit both directing the exploratory search process and making sense of the information space. Our findings can help design personalized systems that support exploratory information seeking and discovery of novel information.
- 3 October 2018
- Published by Association for Computing Machinery (ACM) in ACM Transactions on Information Systems
- Vol. 36 (4) , 1-46
Open AccessInteractive Intent Modeling for Exploratory Search
Exploratory search requires the system to assist the user in comprehending the information space and expressing evolving search intents for iterative exploration and retrieval of information. We introduce interactive intent modeling, a technique that models a user’s evolving search intents and visualizes them as keywords for interaction. The user can provide feedback on the keywords, from which the system learns and visualizes an improved intent estimate and retrieves information. We report experiments comparing variants of a system implementing interactive intent modeling to a control system. Data comprising search logs, interaction logs, essay answers, and questionnaires indicate significant improvements in task performance, information retrieval performance over the session, information comprehension performance, and user experience. The improvements in retrieval effectiveness can be attributed to the intent modeling and the effect on users’ task performance, breadth of information comprehension, and user experience are shown to be dependent on a richer visualization. Our results demonstrate the utility of combining interactive modeling of search intentions with interactive visualization of the models that can benefit both directing the exploratory search process and making sense of the information space. Our findings can help design personalized systems that support exploratory information seeking and discovery of novel information.
- 1 September 2018
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 1-6
DETECTING INDUSTRIAL FOULING BY MONOTONICITY DURING ULTRASONIC CLEANING
High power ultrasound permits non-invasive cleaning of industrial equipment, but to make such cleaning systems energy efficient, one needs to recognize when the structure has been sufficiently cleaned without using invasive diagnostic tools. This can be done using ultrasound reflections generated inside the structure. This inverse modeling problem cannot be solved by forward modeling for irregular and complex structures, and it is difficult to tackle also with machine learning since human-annotated labels are hard get. We provide a deep learning solution that relies on the physical properties of the cleaning process. We rely on the fact that the amount of fouling is reduced as we clean more. Using this monotonicity property as indirect supervision we develop a semi-supervised model for detecting when the equipment has been cleaned.
- 1 September 2018
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 1-6
DETECTING INDUSTRIAL FOULING BY MONOTONICITY DURING ULTRASONIC CLEANING
High power ultrasound permits non-invasive cleaning of industrial equipment, but to make such cleaning systems energy efficient, one needs to recognize when the structure has been sufficiently cleaned without using invasive diagnostic tools. This can be done using ultrasound reflections generated inside the structure. This inverse modeling problem cannot be solved by forward modeling for irregular and complex structures, and it is difficult to tackle also with machine learning since human-annotated labels are hard get. We provide a deep learning solution that relies on the physical properties of the cleaning process. We rely on the fact that the amount of fouling is reduced as we clean more. Using this monotonicity property as indirect supervision we develop a semi-supervised model for detecting when the equipment has been cleaned.
- Open Access
- 20 December 2017
- Published by Springer Nature in Machine Learning
- Vol. 107 (1) , 247-283
Empirical hardness of finding optimal Bayesian network structures: algorithm selection and runtime prediction
- 20 December 2017
- Published by Springer Nature in Machine Learning
- Vol. 107 (1) , 247-283
Open AccessEmpirical hardness of finding optimal Bayesian network structures: algorithm selection and runtime prediction
- 21 December 2016
- Published by Springer Nature in New Generation Computing
- Vol. 35 (1) , 47-67
Duplicate Detection for Bayesian Network Structure Learning
- 21 December 2016
- Published by Springer Nature in New Generation Computing
- Vol. 35 (1) , 47-67
Duplicate Detection for Bayesian Network Structure Learning
- Open Access
- 9 November 2015
- Published by Springer Nature in BMC Bioinformatics
- Vol. 16 (1) , 1-15
Inferring intra-motif dependencies of DNA binding sites from ChIP-seq data
Statistical modeling of transcription factor binding sites is one of the classical fields in bioinformatics. The position weight matrix (PWM) model, which assumes statistical independence among all nucleotides in a binding site, used to be the standard model for this task for more than three decades but its simple assumptions are increasingly put into question. Recent high-throughput sequencing methods have provided data sets of sufficient size and quality for studying the benefits of more complex models. However, learning more complex models typically entails the danger of overfitting, and while model classes that dynamically adapt the model complexity to data have been developed, effective model selection is to date only possible for fully observable data, but not, e.g., within de novo motif discovery. To address this issue, we propose a stochastic algorithm for performing robust model selection in a latent variable setting. This algorithm yields a solution without relying on hyperparameter-tuning via massive cross-validation or other computationally expensive resampling techniques. Using this algorithm for learning inhomogeneous parsimonious Markov models, we study the degree of putative higher-order intra-motif dependencies for transcription factor binding sites inferred via de novo motif discovery from ChIP-seq data. We find that intra-motif dependencies are prevalent and not limited to first-order dependencies among directly adjacent nucleotides, but that second-order models appear to be the significantly better choice. The traditional PWM model appears to be indeed insufficient to infer realistic sequence motifs, as it is on average outperformed by more complex models that take into account intra-motif dependencies. Moreover, using such models together with an appropriate model selection procedure does not lead to a significant performance loss in comparison with the PWM model for any of the studied transcription factors. Hence, we find it worthwhile to recommend that any modern motif discovery algorithm should attempt to take into account intra-motif dependencies.
- 9 November 2015
- Published by Springer Nature in BMC Bioinformatics
- Vol. 16 (1) , 1-15
Open AccessInferring intra-motif dependencies of DNA binding sites from ChIP-seq data
Statistical modeling of transcription factor binding sites is one of the classical fields in bioinformatics. The position weight matrix (PWM) model, which assumes statistical independence among all nucleotides in a binding site, used to be the standard model for this task for more than three decades but its simple assumptions are increasingly put into question. Recent high-throughput sequencing methods have provided data sets of sufficient size and quality for studying the benefits of more complex models. However, learning more complex models typically entails the danger of overfitting, and while model classes that dynamically adapt the model complexity to data have been developed, effective model selection is to date only possible for fully observable data, but not, e.g., within de novo motif discovery. To address this issue, we propose a stochastic algorithm for performing robust model selection in a latent variable setting. This algorithm yields a solution without relying on hyperparameter-tuning via massive cross-validation or other computationally expensive resampling techniques. Using this algorithm for learning inhomogeneous parsimonious Markov models, we study the degree of putative higher-order intra-motif dependencies for transcription factor binding sites inferred via de novo motif discovery from ChIP-seq data. We find that intra-motif dependencies are prevalent and not limited to first-order dependencies among directly adjacent nucleotides, but that second-order models appear to be the significantly better choice. The traditional PWM model appears to be indeed insufficient to infer realistic sequence motifs, as it is on average outperformed by more complex models that take into account intra-motif dependencies. Moreover, using such models together with an appropriate model selection procedure does not lead to a significant performance loss in comparison with the PWM model for any of the studied transcription factors. Hence, we find it worthwhile to recommend that any modern motif discovery algorithm should attempt to take into account intra-motif dependencies.
- Open Access
- 9 August 2015
- Published by Association for Computing Machinery (ACM)
- p. 1043-1044
SciNet
Current search engines offer limited assistance for exploration and information discovery in complex search tasks. Instead, users are distracted by the need to focus their cognitive efforts on finding navigation cues, rather than selecting relevant information. Interactive intent modeling enhances the human information exploration capacity through computational modeling, visualized for interaction. Interactive intent modeling has been shown to increase task-level information seeking performance by up to 100%. In this demonstration, we showcase SciNet, a system implementing interactive intent modeling on top of a scientific article database of over 60 million documents.
- 9 August 2015
- Published by Association for Computing Machinery (ACM)
- p. 1043-1044
Open AccessSciNet
Current search engines offer limited assistance for exploration and information discovery in complex search tasks. Instead, users are distracted by the need to focus their cognitive efforts on finding navigation cues, rather than selecting relevant information. Interactive intent modeling enhances the human information exploration capacity through computational modeling, visualized for interaction. Interactive intent modeling has been shown to increase task-level information seeking performance by up to 100%. In this demonstration, we showcase SciNet, a system implementing interactive intent modeling on top of a scientific article database of over 60 million documents.
- Open Access
- 1 January 2015
- Published by Springer Nature
- p. 46-60
Hashing-Based Hybrid Duplicate Detection for Bayesian Network Structure Learning
- 1 January 2015
- Published by Springer Nature
- p. 46-60
Open AccessHashing-Based Hybrid Duplicate Detection for Bayesian Network Structure Learning
- Open Access
- 23 December 2014
- Published by Association for Computing Machinery (ACM) in Communications of the ACM
- Vol. 58 (1) , 86-92
Interactive intent modeling
The system should let users incrementally direct their search toward relevant, though not initially obvious, information.
- 23 December 2014
- Published by Association for Computing Machinery (ACM) in Communications of the ACM
- Vol. 58 (1) , 86-92
Open AccessInteractive intent modeling
The system should let users incrementally direct their search toward relevant, though not initially obvious, information.
- 1 July 2014
- Published by IGI Global Scientific Publishing in International Journal of Robotics Applications and Technologies
- Vol. 2 (2) , 20-36
Passive Localization of a Robot Using Multiple-View Geometry
Finding the location of a robot, equipped with an imaging sensor, by taking photos from its surrounding environment is a multifaceted task consisting several obligatory phases. It starts from the calibration of a sensor, and ends in propagation of errors, to consequently express our uncertainty about the unknowns. This article uses a mathematical language to elaborate a model based on recent trends to show how the structure and motion can be estimated by image-processing methods on digital images taken from a regular non-metric camera. The direct and inverse Brown's model for calibration, as well as the basic definition of an image pyramid is discussed first. The concepts of Epipolar geometry, collinearity and co-planarity, and registrations of models, are described next. Generating a reference map, the bundle-adjustment and localization are presented finally. In the last sections, some recent trends about parallel computing are reviewed, and recommendations for building a real-time system are discussed.
- 1 July 2014
- Published by IGI Global Scientific Publishing in International Journal of Robotics Applications and Technologies
- Vol. 2 (2) , 20-36
Passive Localization of a Robot Using Multiple-View Geometry
Finding the location of a robot, equipped with an imaging sensor, by taking photos from its surrounding environment is a multifaceted task consisting several obligatory phases. It starts from the calibration of a sensor, and ends in propagation of errors, to consequently express our uncertainty about the unknowns. This article uses a mathematical language to elaborate a model based on recent trends to show how the structure and motion can be estimated by image-processing methods on digital images taken from a regular non-metric camera. The direct and inverse Brown's model for calibration, as well as the basic definition of an image pyramid is discussed first. The concepts of Epipolar geometry, collinearity and co-planarity, and registrations of models, are described next. Generating a reference map, the bundle-adjustment and localization are presented finally. In the last sections, some recent trends about parallel computing are reviewed, and recommendations for building a real-time system are discussed.
- Open Access
- 26 April 2014
- Published by Association for Computing Machinery (ACM)
- p. 455-458
Intentradar
- 26 April 2014
- Published by Association for Computing Machinery (ACM)
- p. 455-458
Open AccessIntentradar