I am senior lecturer at the School of Computer Science of the University of Auckland and CTO of enviPath. I am member of the Machine Learning Group at UoA. My main research area is machine learning and its application to bioinformatics, cheminformatics, computational sustainability, and privacy. My approach to research is to use interesting and challenging questions in other research areas and develop new machine learning methods that address them to potentially advance not only the field of machine learning, but also the area it is applied to. In my career, I worked on diverse machine learning topics including autoencoders, Boolean matrix decomposition, inductive databases, multi-label classification, privacy-preserving data mining, adversarial learning, and time series analysis.
I am currently looking for PhD, Honours, or Masters students, if you are interested in any of my research areas, contact me by mail.
Recent Publications
Journal Articles |
||
Roeslin, Samuel; Ma, Quincy; Juárez-Garcia, Hugon; Gómez-Bernal, Alonso; Wicker, Jörg; Wotherspoon, Liam A machine learning damage prediction model for the 2017 Puebla-Morelos, Mexico, earthquake Journal Article Earthquake Spectra, 2020. Abstract | Links | BibTeX | Altmetric @article{roeslin2020machine, title = {A machine learning damage prediction model for the 2017 Puebla-Morelos, Mexico, earthquake}, author = {Samuel Roeslin and Quincy Ma and Hugon Ju\'{a}rez-Garcia and Alonso G\'{o}mez-Bernal and J\"{o}rg Wicker and Liam Wotherspoon}, doi = {https://doi.org/10.1177/8755293020936714}, year = {2020}, date = {2020-07-30}, journal = {Earthquake Spectra}, abstract = {The 2017 Puebla, Mexico, earthquake event led to significant damage in many buildings in Mexico City. In the months following the earthquake, civil engineering students conducted detailed building assessments throughout the city. They collected building damage information and structural characteristics for 340 buildings in the Mexico City urban area, with an emphasis on the Roma and Condesa neighborhoods where they assessed 237 buildings. These neighborhoods are of particular interest due to the availability of seismic records captured by nearby recording stations, and preexisting information from when the neighborhoods were affected by the 1985 Michoac\'{a}n earthquake. This article presents a case study on developing a damage prediction model using machine learning. It details a framework suitable for working with future post-earthquake observation data. Four algorithms able to perform classification tasks were trialed. Random forest, the best performing algorithm, achieves more than 65% prediction accuracy. The study of the feature importance for the random forest shows that the building location, seismic demand, and building height are the parameters that influence the model output the most.}, keywords = {}, pubstate = {published}, tppubtype = {article} } The 2017 Puebla, Mexico, earthquake event led to significant damage in many buildings in Mexico City. In the months following the earthquake, civil engineering students conducted detailed building assessments throughout the city. They collected building damage information and structural characteristics for 340 buildings in the Mexico City urban area, with an emphasis on the Roma and Condesa neighborhoods where they assessed 237 buildings. These neighborhoods are of particular interest due to the availability of seismic records captured by nearby recording stations, and preexisting information from when the neighborhoods were affected by the 1985 Michoacán earthquake. This article presents a case study on developing a damage prediction model using machine learning. It details a framework suitable for working with future post-earthquake observation data. Four algorithms able to perform classification tasks were trialed. Random forest, the best performing algorithm, achieves more than 65% prediction accuracy. The study of the feature importance for the random forest shows that the building location, seismic demand, and building height are the parameters that influence the model output the most. | ||
Jonauskaite, Domicele; Wicker, Jörg; Mohr, Chrisine; Dael, Nele; Havelka, Jelena; Papadatou-Pastou, Marietta; Zhang, Meng; Oberfeld, Daniel A machine learning approach to quantifying the specificity of color-emotion associations and their cultural differences Journal Article Royal Society Open Science, 6 (9), pp. 190741, 2019. Abstract | Links | BibTeX | Altmetric @article{Jonauskaite2019, title = {A machine learning approach to quantifying the specificity of color-emotion associations and their cultural differences}, author = {Domicele Jonauskaite and J\"{o}rg Wicker and Chrisine Mohr and Nele Dael and Jelena Havelka and Marietta Papadatou-Pastou and Meng Zhang and Daniel Oberfeld }, editor = {Andrew Dunn}, url = {https://royalsocietypublishing.org/doi/10.1098/rsos.190741 https://doi.org/10.1098/rsos.190741}, doi = {10.1098/rsos.190741}, year = {2019}, date = {2019-09-25}, journal = {Royal Society Open Science}, volume = {6}, number = {9}, pages = {190741}, abstract = {The link between colour and emotion and its possible similarity across cultures are questions that have not been fully resolved. Online, 711 participants from China, Germany, Greece and the UK associated 12 colour terms with 20 discrete emotion terms in their native languages. We propose a machine learning approach to quantify (a) the consistency and specificity of colour-emotion associations and (b) the degree to which they are country-specific, on the basis of the accuracy of a statistical classifier in (a) decoding the colour term evaluated on a given trial from the 20 ratings of colour-emotion associations and (b) predicting the country of origin from the 240 individual colour-emotion associations, respectively. The classifier accuracies were significantly above chance level, demonstrating that emotion associations are to some extent colour-specific and that colour-emotion associations are to some extent country-specific. A second measure of country-specificity, the in-group advantage of the colour-decoding accuracy, was detectable but relatively small (6.1%), indicating that colour-emotion associations are both universal and culture-specific. Our results show that machine learning is a promising tool when analysing complex datasets from emotion research.}, keywords = {}, pubstate = {published}, tppubtype = {article} } The link between colour and emotion and its possible similarity across cultures are questions that have not been fully resolved. Online, 711 participants from China, Germany, Greece and the UK associated 12 colour terms with 20 discrete emotion terms in their native languages. We propose a machine learning approach to quantify (a) the consistency and specificity of colour-emotion associations and (b) the degree to which they are country-specific, on the basis of the accuracy of a statistical classifier in (a) decoding the colour term evaluated on a given trial from the 20 ratings of colour-emotion associations and (b) predicting the country of origin from the 240 individual colour-emotion associations, respectively. The classifier accuracies were significantly above chance level, demonstrating that emotion associations are to some extent colour-specific and that colour-emotion associations are to some extent country-specific. A second measure of country-specificity, the in-group advantage of the colour-decoding accuracy, was detectable but relatively small (6.1%), indicating that colour-emotion associations are both universal and culture-specific. Our results show that machine learning is a promising tool when analysing complex datasets from emotion research. | ||
Inproceedings |
||
Chester, Andrew; Koh, Yun Sing; Sun, Quan; Wicker, Jörg; Lee, Junjae Balancing Utility and Fairness against Privacy in Medical Data Inproceedings Forthcoming IEEE Symposium Series on Computational Intelligence, IEEE, Forthcoming. @inproceedings{chester2020balancing, title = {Balancing Utility and Fairness against Privacy in Medical Data}, author = {Andrew Chester and Yun Sing Koh and Quan Sun and J\"{o}rg Wicker and Junjae Lee}, year = {2020}, date = {2020-12-01}, booktitle = {IEEE Symposium Series on Computational Intelligence}, publisher = {IEEE}, abstract = {Abstract\textemdashAbstract\textemdashThere are numerous challenges when designing algorithms that interact with sensitive data, such as, medical or financial records. One of these challenges is privacy. However, there is a tension between privacy, utility (model accuracy), and fairness. While de-identification techniques, such as generalisation and suppression, have been proposed to enable privacy protection, it comes with a cost, specifically to fairness and utility. Recent work on fairness in algorithm design defines fairness as a guarantee of similar outputs for "similar" input data. This notion is discussed in connection to de-identification. This research investigates the trade-off between privacy, fairness, and utility. In contrast, other work investigates the trade-off between privacy and utility of the data or accuracy of the model overall. In this research, we investigate the effects of two standard de-identification techniques, k-anonymity and differential privacy, on both utility and fairness. We propose two measures to calculate the trade-off between privacy-utility and privacy-fairness. Although other research has provided guarantees for privacy regarding utility, this research focuses on the trade-offs given set de-identification levels and relies on guarantees provided by the privacy preservation methods. We discuss the effects of de-identification on data of different characteristics, class imbalance and outcome imbalance. We evaluated this is on synthetic datasets and standard real-world datasets. As a case study, we analysed the Medical Expenditure Panel Survey dataset. }, keywords = {}, pubstate = {forthcoming}, tppubtype = {inproceedings} } Abstract—Abstract—There are numerous challenges when designing algorithms that interact with sensitive data, such as, medical or financial records. One of these challenges is privacy. However, there is a tension between privacy, utility (model accuracy), and fairness. While de-identification techniques, such as generalisation and suppression, have been proposed to enable privacy protection, it comes with a cost, specifically to fairness and utility. Recent work on fairness in algorithm design defines fairness as a guarantee of similar outputs for "similar" input data. This notion is discussed in connection to de-identification. This research investigates the trade-off between privacy, fairness, and utility. In contrast, other work investigates the trade-off between privacy and utility of the data or accuracy of the model overall. In this research, we investigate the effects of two standard de-identification techniques, k-anonymity and differential privacy, on both utility and fairness. We propose two measures to calculate the trade-off between privacy-utility and privacy-fairness. Although other research has provided guarantees for privacy regarding utility, this research focuses on the trade-offs given set de-identification levels and relies on guarantees provided by the privacy preservation methods. We discuss the effects of de-identification on data of different characteristics, class imbalance and outcome imbalance. We evaluated this is on synthetic datasets and standard real-world datasets. As a case study, we analysed the Medical Expenditure Panel Survey dataset. | ||
Dost, Katharina; Taskova, Katerina; Riddle, Pat; Wicker, Jörg Your Best Guess When You Know Nothing: Identification and Mitigation of Selection Bias Inproceedings Forthcoming 2020 IEEE International Conference on Data Mining (ICDM), IEEE, Forthcoming. @inproceedings{dost2020your, title = {Your Best Guess When You Know Nothing: Identification and Mitigation of Selection Bias}, author = {Katharina Dost and Katerina Taskova and Pat Riddle and J\"{o}rg Wicker}, year = {2020}, date = {2020-11-17}, booktitle = {2020 IEEE International Conference on Data Mining (ICDM)}, publisher = {IEEE}, abstract = {Machine Learning typically assumes that training and test set are independently drawn from the same distribution, but this assumption is often violated in practice which creates a bias. Many attempts to identify and mitigate this bias have been proposed, but they usually rely on ground-truth information. But what if the researcher is not even aware of the bias? In contrast to prior work, this paper introduces a new method, Imitate, to identify and mitigate Selection Bias in the case that we may not know if (and where) a bias is present, and hence no ground-truth information is available. Imitate investigates the dataset's probability density, then adds generated points in order to smooth out the density and have it resemble a Gaussian, the most common density occurring in real-world applications. If the artificial points focus on certain areas and are not widespread, this could indicate a Selection Bias where these areas are underrepresented in the sample. We demonstrate the effectiveness of the proposed method in both, synthetic and real-world datasets. We also point out limitations and future research directions.}, keywords = {}, pubstate = {forthcoming}, tppubtype = {inproceedings} } Machine Learning typically assumes that training and test set are independently drawn from the same distribution, but this assumption is often violated in practice which creates a bias. Many attempts to identify and mitigate this bias have been proposed, but they usually rely on ground-truth information. But what if the researcher is not even aware of the bias? In contrast to prior work, this paper introduces a new method, Imitate, to identify and mitigate Selection Bias in the case that we may not know if (and where) a bias is present, and hence no ground-truth information is available. Imitate investigates the dataset's probability density, then adds generated points in order to smooth out the density and have it resemble a Gaussian, the most common density occurring in real-world applications. If the artificial points focus on certain areas and are not widespread, this could indicate a Selection Bias where these areas are underrepresented in the sample. We demonstrate the effectiveness of the proposed method in both, synthetic and real-world datasets. We also point out limitations and future research directions. | ||
Roeslin, Samuel; Ma, Quincy; and Chigullapally, Pavan; Wicker, Jörg; Wotherspoon, Liam Feature Engineering for a Seismic Loss Prediction Model using Machine Learning, Christchurch Experience Inproceedings Forthcoming 17th World Conference on Earthquake Engineering, Forthcoming. @inproceedings{roeslin2020feature, title = { Feature Engineering for a Seismic Loss Prediction Model using Machine Learning, Christchurch Experience}, author = {Samuel Roeslin and Quincy Ma and and Pavan Chigullapally and J\"{o}rg Wicker and Liam Wotherspoon}, year = {2020}, date = {2020-09-17}, booktitle = {17th World Conference on Earthquake Engineering}, abstract = {The city of Christchurch, New Zealand experienced four major earthquakes (MW > 5.9) and multiple aftershocks between 4 September 2010 and 23 December 2011. This series of earthquakes, commonly known as the Canterbury Earthquake Sequence (CES), induced over NZ$40 billion in total economic losses. Liquefaction alone led to building damage in 51,000 of the 140,000 residential buildings, with around 15,000 houses left unpractical to repair. Widespread damage to residential buildings highlighted the need for improved seismic prediction tools and to better understand factors influencing damage. Fortunately, due to New Zealand unique insurance setting, up to 80% of the losses were insured. Over the entire CES, insurers received more than 650,000 claims. This research project employs multi-disciplinary empirical data gathered during and prior to the CES to develop a seismic loss prediction model for residential buildings in Christchurch using machine learning. The intent is to develop a procedure for developing insights from post-earthquake data that is subjected to continuous updating, to enable identification of critical parameters affecting losses, and to apply such a model to establish priority building stock for risk mitigation measures. The following paper describes the complex data preparation process required for the application of machine learning techniques. The paper covers the production of a merged dataset with information from the Earthquake Commission (EQC) claim database, building characteristics from RiskScape, seismic demand interpolated from GeoNet strong motion records, liquefaction occurrence from the New Zealand Geotechnical Database (NZGD) and soil conditions from Land Resource Information Systems (LRIS).}, keywords = {}, pubstate = {forthcoming}, tppubtype = {inproceedings} } The city of Christchurch, New Zealand experienced four major earthquakes (MW > 5.9) and multiple aftershocks between 4 September 2010 and 23 December 2011. This series of earthquakes, commonly known as the Canterbury Earthquake Sequence (CES), induced over NZ$40 billion in total economic losses. Liquefaction alone led to building damage in 51,000 of the 140,000 residential buildings, with around 15,000 houses left unpractical to repair. Widespread damage to residential buildings highlighted the need for improved seismic prediction tools and to better understand factors influencing damage. Fortunately, due to New Zealand unique insurance setting, up to 80% of the losses were insured. Over the entire CES, insurers received more than 650,000 claims. This research project employs multi-disciplinary empirical data gathered during and prior to the CES to develop a seismic loss prediction model for residential buildings in Christchurch using machine learning. The intent is to develop a procedure for developing insights from post-earthquake data that is subjected to continuous updating, to enable identification of critical parameters affecting losses, and to apply such a model to establish priority building stock for risk mitigation measures. The following paper describes the complex data preparation process required for the application of machine learning techniques. The paper covers the production of a merged dataset with information from the Earthquake Commission (EQC) claim database, building characteristics from RiskScape, seismic demand interpolated from GeoNet strong motion records, liquefaction occurrence from the New Zealand Geotechnical Database (NZGD) and soil conditions from Land Resource Information Systems (LRIS). | ||
Roeslin, Samuel; Ma, Quincy; Wicker, Jörg; Wotherspoon, Liam Data integration for the development of a seismic loss prediction model for residential buildings in New Zealand Inproceedings Cellier, Peggy; Driessens, Kurt (Ed.): Machine Learning and Knowledge Discovery in Databases, pp. 88-100, Springer International Publishing, Cham, 2020, ISBN: 978-3-030-43887-6. Abstract | Links | BibTeX | Altmetric @inproceedings{roeslin2019data, title = {Data integration for the development of a seismic loss prediction model for residential buildings in New Zealand}, author = {Samuel Roeslin and Quincy Ma and J\"{o}rg Wicker and Liam Wotherspoon}, editor = {Peggy Cellier and Kurt Driessens}, url = {https://link.springer.com/chapter/10.1007/978-3-030-43887-6_8}, doi = {10.1007/978-3-030-43887-6_8}, isbn = {978-3-030-43887-6}, year = {2020}, date = {2020-03-28}, booktitle = {Machine Learning and Knowledge Discovery in Databases}, pages = {88-100}, publisher = {Springer International Publishing}, address = {Cham}, abstract = {In 2010--2011, New Zealand experienced the most damaging earthquakes in its history. It led to extensive damage to Christchurch buildings, infrastructure and its surroundings; affecting commercial and residential buildings. The direct economic losses represented 20{%} of New Zealand's GDP in 2011. Owing to New Zealand's particular insurance structure, the insurance sector contributed to over 80{%} of losses for a total of more than NZ{$}31 billion. Amongst this, over NZ{$}11 billion of the losses arose from residential building claims and were covered either partially or entirely from the NZ government backed Earthquake Commission (EQC) cover insurance scheme. In the process of resolving the claims, EQC collected detailed financial loss data, post-event observations and building characteristics for each of the approximately 434,000 claims lodged following the Canterbury Earthquake sequence (CES). Added to this, the active NZ earthquake engineering community treated the event as a large scale outdoor experiment and collected extensive data on the ground shaking levels, soil conditions, and liquefaction occurrence throughout wider Christchurch. This paper discusses the necessary data preparation process preceding the development of a machine learning seismic loss model. The process draws heavily upon using Geographic Information System (GIS) techniques to aggregate relevant information from multiple databases interpolating data between categories and converting data between continuous and categorical forms. Subsequently, the database is processed, and a residential seismic loss prediction model is developed using machine learning. The aim is to develop a `grey-box' model enabling human interpretability of the decision steps.}, keywords = {}, pubstate = {published}, tppubtype = {inproceedings} } In 2010--2011, New Zealand experienced the most damaging earthquakes in its history. It led to extensive damage to Christchurch buildings, infrastructure and its surroundings; affecting commercial and residential buildings. The direct economic losses represented 20{%} of New Zealand's GDP in 2011. Owing to New Zealand's particular insurance structure, the insurance sector contributed to over 80{%} of losses for a total of more than NZ{$}31 billion. Amongst this, over NZ{$}11 billion of the losses arose from residential building claims and were covered either partially or entirely from the NZ government backed Earthquake Commission (EQC) cover insurance scheme. In the process of resolving the claims, EQC collected detailed financial loss data, post-event observations and building characteristics for each of the approximately 434,000 claims lodged following the Canterbury Earthquake sequence (CES). Added to this, the active NZ earthquake engineering community treated the event as a large scale outdoor experiment and collected extensive data on the ground shaking levels, soil conditions, and liquefaction occurrence throughout wider Christchurch. This paper discusses the necessary data preparation process preceding the development of a machine learning seismic loss model. The process draws heavily upon using Geographic Information System (GIS) techniques to aggregate relevant information from multiple databases interpolating data between categories and converting data between continuous and categorical forms. Subsequently, the database is processed, and a residential seismic loss prediction model is developed using machine learning. The aim is to develop a `grey-box' model enabling human interpretability of the decision steps. | ||
Wicker, Jörg; Hua, Yan Cathy; Rebello, Rayner; Pfahringer, Bernhard XOR-based Boolean Matrix Decomposition Inproceedings Wang, Jianyong; Shim, Kyuseok; Wu, Xindong (Ed.): 2019 IEEE International Conference on Data Mining (ICDM), pp. 638-647, IEEE, 2019, ISBN: 978-1-7281-4604-1. Abstract | Links | BibTeX | Altmetric @inproceedings{wicker2019xor, title = {XOR-based Boolean Matrix Decomposition}, author = {J\"{o}rg Wicker and Yan Cathy Hua and Rayner Rebello and Bernhard Pfahringer}, editor = {Jianyong Wang and Kyuseok Shim and Xindong Wu}, url = {https://ieeexplore.ieee.org/document/8970951}, doi = {10.1109/ICDM.2019.00074}, isbn = {978-1-7281-4604-1}, year = {2019}, date = {2019-11-08}, booktitle = {2019 IEEE International Conference on Data Mining (ICDM)}, pages = {638-647}, publisher = {IEEE}, abstract = {Boolean matrix factorization (BMF) is a data summarizing and dimension-reduction technique. Existing BMF methods build on matrix properties defined by Boolean algebra, where the addition operator is the logical inclusive OR and the multiplication operator the logical AND. As a consequence, this leads to the lack of an additive inverse in all Boolean matrix operations, which produces an indelible type of approximation error. Previous research adopted various methods to address such an issue and produced reasonably accurate approximation. However, an exact factorization is rarely found in the literature. In this paper, we introduce a new algorithm named XBMaD (Xor-based Boolean Matrix Decomposition) where the addition operator is defined as the exclusive OR (XOR). This change completely removes the error-mitigation issue of OR-based BMF methods, and allows for an exact error-free factorization. An evaluation comparing XBMaD and classic OR-based methods suggested that XBMAD performed equal or in most cases more accurately and faster. }, keywords = {}, pubstate = {published}, tppubtype = {inproceedings} } Boolean matrix factorization (BMF) is a data summarizing and dimension-reduction technique. Existing BMF methods build on matrix properties defined by Boolean algebra, where the addition operator is the logical inclusive OR and the multiplication operator the logical AND. As a consequence, this leads to the lack of an additive inverse in all Boolean matrix operations, which produces an indelible type of approximation error. Previous research adopted various methods to address such an issue and produced reasonably accurate approximation. However, an exact factorization is rarely found in the literature. In this paper, we introduce a new algorithm named XBMaD (Xor-based Boolean Matrix Decomposition) where the addition operator is defined as the exclusive OR (XOR). This change completely removes the error-mitigation issue of OR-based BMF methods, and allows for an exact error-free factorization. An evaluation comparing XBMaD and classic OR-based methods suggested that XBMAD performed equal or in most cases more accurately and faster. | ||
Williams, Jonathan; Stönner, Christof; Edtbauer, Achim; Derstorff, Bettina; Bourtsoukidis, Efstratios; Klüpfel, Thomas; Krauter, Nicolas; Wicker, Jörg; Kramer, Stefan What can we learn from the air chemistry of crowds? Inproceedings Hansel, Armin; Dunkl, Jürgen (Ed.): 8th International Conference on Proton Transfer Reaction Mass Spectrometry and its Applications, pp. 121-123, Innsbruck University Press, Innsbruck, 2019. @inproceedings{williams2019what, title = {What can we learn from the air chemistry of crowds?}, author = {Jonathan Williams and Christof St\"{o}nner and Achim Edtbauer and Bettina Derstorff and Efstratios Bourtsoukidis and Thomas Kl\"{u}pfel and Nicolas Krauter and J\"{o}rg Wicker and Stefan Kramer}, editor = {Armin Hansel and J\"{u}rgen Dunkl}, url = {https://www.ionicon.com/sites/default/files/uploads/doc/Contributions_8th-PTR-MS-Conference-2019_web.pdf#page=122}, year = {2019}, date = {2019-05-10}, booktitle = {8th International Conference on Proton Transfer Reaction Mass Spectrometry and its Applications}, pages = {121-123}, publisher = {Innsbruck University Press}, address = {Innsbruck}, abstract = {Current PTR-MS technology allows hundreds of volatile trace gases in air to be measured every second at extremely low levels (parts per trillion). These instruments are often used in atmospheric research on planes and ships and even in the Amazon rainforest. Recently, we have used this technology to examine air composition changes caused by large groups of people (10,000-30,000) under real world conditions at a football match and in a movie theater. In both cases the trace gas signatures measured in ambient air are shown to reflect crowd behavior. By applying advanced data mining techniques we have shown that groups of people reproducibly respond to certain emotional stimuli (e.g. suspense and comedy) by exhaling specific trace gases. Furthermore, we explore whether this information can be used to determine the age classification of films.}, keywords = {}, pubstate = {published}, tppubtype = {inproceedings} } Current PTR-MS technology allows hundreds of volatile trace gases in air to be measured every second at extremely low levels (parts per trillion). These instruments are often used in atmospheric research on planes and ships and even in the Amazon rainforest. Recently, we have used this technology to examine air composition changes caused by large groups of people (10,000-30,000) under real world conditions at a football match and in a movie theater. In both cases the trace gas signatures measured in ambient air are shown to reflect crowd behavior. By applying advanced data mining techniques we have shown that groups of people reproducibly respond to certain emotional stimuli (e.g. suspense and comedy) by exhaling specific trace gases. Furthermore, we explore whether this information can be used to determine the age classification of films. | ||