Publications

@inproceedings{Pullar-Strecker2023memento,

title = {Memento: Facilitating Effortless, Efficient, and Reliable ML Experiments},

author = {Zac Pullar-Strecker and Xinglong Chang and Liam Brydon and Ioannis Ziogas and Katharina Dost and J\"{o}rg Wicker},

editor = {Gianmarco De Francisci Morales and Claudia Perlich and Natali Ruchansky and Nicolas Kourtellis and Elena Baralis and Francesco Bonchi },

url = {https://arxiv.org/abs/2304.09175

https://github.com/wickerlab/memento},

doi = {10.1007/978-3-031-43430-3_21},

isbn = {978-3-031-43430-3},

year  = {2023},

date = {2023-09-17},

urldate = {2023-09-17},

booktitle = {Machine Learning and Knowledge Discovery in Databases: Applied Data Science and Demo Track},

journal = {Lecture Notes in Computer Science},

pages = {310-314},

publisher = {Springer Nature Switzerland},

address = {Cham},

abstract = { Running complex sets of machine learning experiments is challenging and time-consuming due to the lack of a unified framework. This leaves researchers forced to spend time implementing necessary features such as parallelization, caching, and checkpointing themselves instead of focussing on their project. To simplify the process, in our paper, we introduce Memento, a Python package that is designed to aid researchers and data scientists in the efficient management and execution of computationally intensive experiments. Memento has the capacity to streamline any experimental pipeline by providing a straightforward configuration matrix and the ability to concurrently run experiments across multiple threads.



Code related to this paper is available at: https://github.com/wickerlab/memento.},

keywords = {experimental pipeline, parallel computing, reliable machine learning},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{chang2021baard,

title = {BAARD: Blocking Adversarial Examples by Testing for Applicability, Reliability and Decidability},

author = {Luke Chang and Katharina Dost and Kaiqi Zhai and Ambra Demontis and Fabio Roli and Gillian Dobbie and J\"{o}rg Wicker},

editor = {Hisashi Kashima and Tsuyoshi Ide and Wen-Chih Peng},

url = {https://arxiv.org/abs/2105.00495

https://github.com/wickerlab/baard},

doi = {10.1007/978-3-031-33374-3_1},

issn = {978-3-031-33374-3},

year  = {2023},

date = {2023-05-27},

urldate = {2023-05-27},

booktitle = {The 27th Pacific-Asia Conference on Knowledge Discovery and Data Mining (PAKDD)},

journal = {The 27th Pacific-Asia Conference on Knowledge Discovery and Data Mining (PAKDD)},

pages = {3-14},

publisher = {Springer Nature Switzerland},

address = {Cham},

abstract = {Adversarial defenses protect machine learning models from adversarial attacks, but are often tailored to one type of model or attack. The lack of information on unknown potential attacks makes detecting adversarial examples challenging. Additionally, attackers do not need to follow the rules made by the defender. To address this problem, we take inspiration from the concept of Applicability Domain in cheminformatics. Cheminformatics models struggle to make accurate predictions because only a limited number of compounds are known and available for training. Applicability Domain defines a domain based on the known compounds and rejects any unknown compound that falls outside the domain. Similarly, adversarial examples start as harmless inputs, but can be manipulated to evade reliable classification by moving outside the domain of the classifier. We are the first to identify the similarity between Applicability Domain and adversarial detection. Instead of focusing on unknown attacks, we focus on what is known, the training data. We propose a simple yet robust triple-stage data-driven framework that checks the input globally and locally, and confirms that they are coherent with the model’s output. This framework can be applied to any classification model and is not limited to specific attacks. We demonstrate these three stages work as one unit, effectively detecting various attacks, even for a white-box scenario.},

keywords = {adversarial defence, adversarial learning, applicability domain, cheminformatics, evasion attacks, machine learning},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{Chen2023targeted,

title = {Targeted Attacks on Time Series Forecasting},

author = {Zeyu Chen and Katharina Dost and Xuan Zhu and Xinglong Chang and Gillian Dobbie and J\"{o}rg Wicker},

editor = {Hisashi Kashima and Tsuyoshi Ide and Wen-Chih Peng},

url = {https://github.com/wickerlab/nvita},

doi = {10.1007/978-3-031-33383-5_25},

issn = {978-3-031-33383-5},

year  = {2023},

date = {2023-05-26},

urldate = {2023-05-25},

booktitle = {The 27th Pacific-Asia Conference on Knowledge Discovery and Data Mining (PAKDD)},

pages = {314-327},

publisher = {Springer Nature Switzerland},

address = {Cham},

abstract = {Abstract. Time Series Forecasting (TSF) is well established in domains dealing with temporal data to predict future events yielding the basis for strategic decision-making. Previous research indicated that forecasting models are vulnerable to adversarial attacks, that is, maliciously crafted perturbations of the original data with the goal of altering the model’s predictions. However, attackers targeting specific outcomes pose a substantially more severe threat as they could manipulate the model and bend it to their needs. Regardless, there is no systematic approach for targeted adversarial learning in the TSF domain yet. In this paper, we introduce targeted attacks on TSF in a systematic manner. We establish a new experimental design standard regarding attack goals and perturbation control for targeted adversarial learning on TSF. For this purpose, we present a novel indirect sparse black-box evasion attack on TSF, nVita. Additionally, we adapt the popular white-box attacks Fast Gradient Sign Method (FGSM) and Basic Iterative Method (BIM). Our experiments confirm not only that all three methods are effective but also that current state-of-the-art TSF models are indeed susceptible to attacks. These results motivate future research in this area to achieve higher reliability of forecasting models.},

keywords = {adversarial learning, forecasting, machine learning, time series},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{Kim2022closing,

title = {Closing the Loop: Graph Networks to Unify Semantic Objects and Visual Features for Multi-object Scenes},

author = {Jonathan Kim and Martin Urschler and Pat Riddle and J\"{o}rg Wicker},

url = {https://ieeexplore.ieee.org/abstract/document/9981542},

doi = {10.1109/IROS47612.2022.9981542},

isbn = {978-1-6654-7927-1},

year  = {2022},

date = {2022-10-20},

booktitle = {2022 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS 2022)},

pages = {4352-4358},

abstract = {In Simultaneous Localization and Mapping (SLAM), Loop Closure Detection (LCD) is essential to minimize drift when recognizing previously visited places. Visual Bag- of-Words (vBoW) has been an LCD algorithm of choice for many state-of-the-art SLAM systems. It uses a set of visual features to provide robust place recognition but fails to perceive the semantics or spatial relationship between feature points. Previous work has mainly focused on addressing these issues by combining vBoW with semantic and spatial information from objects in the scene. However, they are unable to exploit spatial information of local visual features and lack a structure that unifies semantic objects and visual features, therefore limiting the symbiosis between the two components. This paper proposes SymbioLCD2, which creates a unified graph structure to integrate semantic objects and visual features symbiotically. Our novel graph-based LCD system utilizes the unified graph structure by applying a Weisfeiler-Lehman graph kernel with temporal constraints to robustly predict loop closure candidates. Evaluation of the proposed system shows that having a unified graph structure incorporating semantic objects and visual features improves LCD prediction accuracy, illustrating that the proposed graph structure provides a strong symbiosis between these two complementary components. It also outperforms other Machine Learning algorithms - such as SVM, Decision Tree, Random Forest, Neural Network and GNN based Graph Matching Networks. Furthermore, it has shown good performance in detecting loop closure candidates earlier than state-of-the-art SLAM systems, demonstrating that extended semantic and spatial awareness from the unified graph structure significantly impacts LCD performance.},

keywords = {machine learning, SLAM},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{Poonawala-Lohani2022geographic,

title = {Geographic Ensembles of Observations using Randomised Ensembles of Autoregression Chains: Ensemble methods for spatio-temporal Time Series Forecasting of Influenza-like Illness},

author = {Nooriyan Poonawala-Lohani and Pat Riddle and Mehnaz Adnan and J\"{o}rg Wicker},

doi = {10.1145/3535508.3545562},

isbn = {9781450393867},

year  = {2022},

date = {2022-08-07},

pages = {1-7},

publisher = {Association for Computing Machinery},

address = {New York, NY, USA},

abstract = {Influenza is a communicable respiratory illness that can cause serious public health hazards. Flu surveillance in New Zealand tracks case counts from various District health boards (DHBs) in the country to monitor the spread of influenza in different geographic locations. Many factors contribute to the spread of the influenza across a geographic region, and it can be challenging to forecast cases in one region without taking into account case numbers in another region. This paper proposes a novel ensemble method called Geographic Ensembles of Observations using Randomised Ensembles of Autoregression Chains (GEO-Reach). GEO-Reach is an ensemble technique that uses a two layer approach to utilise interdependence of historical case counts between geographic regions in New Zealand. This work extends a previously published method by the authors called Randomized Ensembles of Auto-regression chains (Reach). State-of-the-art forecasting models look at studying the spread of the virus. They focus on accurate forecasting of cases for a location using historical case counts for the same location and other data sources based on human behaviour such as movement of people across cities/geographic regions. This new approach is evaluated using Influenza like illness (ILI) case counts in 7 major regions in New Zealand from the years 2015-2019 and compares its performance with other standard methods such as Dante, ARIMA, Autoregression and Random Forests. The results demonstrate that the proposed method performed better than baseline methods when applied to this multi-variate time series forecasting problem.},

keywords = {bioinformatics, computational sustainability, dynamic time warping, forecasting, influenza, machine learning, medicine, time series},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{graffeuille2022semi,

title = {Semi-Supervised Conditional Density Estimation with Wasserstein Laplacian Regularisation},

author = {Olivier Graffeuille and Yun Sing Koh and J\"{o}rg Wicker and Moritz Lehmann},

url = {https://ojs.aaai.org/index.php/AAAI/article/view/20630},

doi = {10.1609/aaai.v36i6.20630},

year  = {2022},

date = {2022-06-28},

urldate = {2022-02-22},

booktitle = {Proceeding of the Thirty-Sixth AAAI Conference on Artificial Intelligence},

volume = {36},

number = {6},

pages = {6746-6754},

abstract = {Conditional Density Estimation (CDE) has wide-reaching applicability to various real-world problems, such as spatial density estimation and environmental modelling. CDE estimates the probability density of a random variable rather than a single value and can thus model uncertainty and inverse problems. This task is inherently more complex than regression, and many algorithms suffer from overfitting, particularly when modelled with few labelled data points. For applications where unlabelled data is abundant but labelled data is scarce, we propose Wasserstein Laplacian Regularisation, a semi-supervised learning framework that allows CDE algorithms to leverage these unlabelled data. The framework minimises an objective function which ensures that the learned model is smooth along the manifold of the underlying data, as measured by Wasserstein distance. When applying our framework to Mixture Density Networks, the resulting semi-supervised algorithm can achieve similar performance to a supervised model with up to three times as many labelled data points on baseline datasets. We additionally apply our technique to the problem of remote sensing for chlorophyll-a estimation in inland waters.},

keywords = {classification, computational sustainability, machine learning, semi-supervised learning},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{dost2022divide,

title = {Divide and Imitate: Multi-Cluster Identification and Mitigation of Selection Bias},

author = {Katharina Dost and Hamish Duncanson and Ioannis Ziogas and Pat Riddle and J\"{o}rg Wicker},

url = {https://link.springer.com/chapter/10.1007/978-3-031-05936-0_12

https://github.com/KatDost/Mimic

https://pypi.org/project/imitatebias},

doi = {10.1007/978-3-031-05936-0_12},

isbn = {978-3-031-05935-3},

year  = {2022},

date = {2022-05-16},

urldate = {2022-05-16},

booktitle = {26th Pacific-Asia Conference on Knowledge Discovery and Data Mining (PAKDD2022)},

pages = {149-160},

publisher = {Springer-Verlag},

address = {Berlin, Heidelberg},

abstract = {Machine Learning can help overcome human biases in decision making by focusing on purely logical conclusions based on the training data. If the training data is biased, however, that bias will be transferred to the model and remains undetected as the performance is validated on a test set drawn from the same biased distribution. Existing strategies for selection bias identification and mitigation generally rely on some sort of knowledge of the bias or the ground-truth. An exception is the Imitate algorithm that assumes no knowledge but comes with a strong limitation: It can only model datasets with one normally distributed cluster per class. In this paper, we introduce a novel algorithm, Mimic, which uses Imitate as a building block but relaxes this limitation. By allowing mixtures of multivariate Gaussians, our technique is able to model multi-cluster datasets and provide solutions for a substantially wider set of problems. Experiments confirm that Mimic not only identifies potential biases in multi-cluster datasets which can be corrected early on but also improves classifier performance.},

keywords = {bias, clustering, machine learning},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{poonawala-lohani2022novel,

title = {A Novel Approach for Time Series Forecasting of Influenza-like Illness Using a Regression Chain Method},

author = {Nooriyan Poonawala-Lohani and Pat Riddle and Mehnaz Adnan and J\"{o}rg Wicker},

editor = {Russ Altman and Keith Dunker and Lawrence Hunter and Marylyn Ritchie and Tiffany Murray and Teri Klein},

url = {https://www.worldscientific.com/doi/abs/10.1142/9789811250477_0028 

http://psb.stanford.edu/psb-online/proceedings/psb22/poorawala-lohani.pdf},

doi = {10.1142/9789811250477_0028},

year  = {2022},

date = {2022-01-03},

urldate = {2022-01-03},

booktitle = {Pacific Symposium on Biocomputing},

volume = {27},

pages = {301-312},

abstract = {Influenza is a communicable respiratory illness that can cause serious public health hazards. Due to its huge threat to the community, accurate forecasting of Influenza-like-illness (ILI) can diminish the impact of an influenza season by enabling early public health interventions. Current forecasting models are limited in their performance, particularly when using a longer forecasting window. To support better forecasts over a longer forecasting window, we propose to use additional features such as weather data. Commonly used methods to fore-cast ILI, including statistical methods such as ARIMA, limit prediction performance when using additional data sources that might have complex non-linear associations with ILI incidence. This paper proposes a novel time series forecasting method, Randomized Ensembles of Auto-regression chains (Reach). Reach implements an ensemble of random chains for multi-step time series forecasting. This new approach is evaluated on ILI case counts in Auckland, New Zealand from the years 2015-2018 and compared to other standard methods. The results demonstrate that the proposed method performed better than baseline methods when applied to this multi-variate time series forecasting problem.},

keywords = {computational sustainability, forecasting, influenza, machine learning, time series},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{kim2021symbiolcd,

title = {SymbioLCD: Ensemble-Based Loop Closure Detection using CNN-Extracted Objects and Visual Bag-of-Words},

author = {Jonathan Kim and Martin Urschler and Pat Riddle and J\"{o}rg Wicker},

url = {https://ieeexplore.ieee.org/abstract/document/9636622 

http://arxiv.org/abs/2110.11491},

doi = {10.1109/IROS51168.2021.9636622},

year  = {2021},

date = {2021-09-27},

urldate = {2021-09-27},

booktitle = {2021 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)},

pages = {5425-5425},

abstract = {Loop closure detection is an essential tool of Simultaneous Localization and Mapping (SLAM) to minimize drift in its localization. Many state-of-the-art loop closure detection (LCD) algorithms use visual Bag-of-Words (vBoW), which is robust against partial occlusions in a scene but cannot perceive the semantics or spatial relationships between feature points. CNN object extraction can address those issues, by providing semantic labels and spatial relationships between objects in a scene. Previous work has mainly focused on replacing vBoW with CNN derived features. 

In this paper we propose SymbioLCD, a novel ensemble-based LCD that utilizes both CNN-extracted objects and vBoW features for LCD candidate prediction. When used in tandem, the added elements of object semantics and spatial-awareness creates a more robust and symbiotic loop closure detection system. The proposed SymbioLCD uses scale-invariant spatial and semantic matching, Hausdorff distance with temporal constraints, and a Random Forest that utilizes combined information from both CNN-extracted objects and vBoW features for predicting accurate loop closure candidates. Evaluation of the proposed method shows it outperforms other Machine Learning (ML) algorithms - such as SVM, Decision Tree and Neural Network, and demonstrates that there is a strong symbiosis between CNN-extracted object information and vBoW features which assists accurate LCD candidate prediction. Furthermore, it is able to perceive loop closure candidates earlier than state-of-the-art SLAM algorithms, utilizing added spatial and semantic information from CNN-extracted objects.},

keywords = {machine learning, SLAM},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{chester2020balancing,

title = {Balancing Utility and Fairness against Privacy in Medical Data},

author = {Andrew Chester and Yun Sing Koh and J\"{o}rg Wicker and Quan Sun and Junjae Lee},

url = {https://ieeexplore.ieee.org/abstract/document/9308226},

doi = {10.1109/SSCI47803.2020.9308226},

year  = {2020},

date = {2020-12-01},

booktitle = {IEEE Symposium Series on Computational Intelligence (SSCI)},

pages = {1226-1233},

publisher = {IEEE},

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.},

keywords = {accuracy, computational sustainability, data mining, fairness, imbalance, machine learning, medicine, privacy},

pubstate = {published},

tppubtype = {inproceedings}

}

@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},

url = {https://ieeexplore.ieee.org/document/9338355

https://github.com/KatDost/Imitate

https://pypi.org/project/imitatebias/},

doi = {10.1109/ICDM50108.2020.00115},

issn = {2374-8486},

year  = {2020},

date = {2020-11-17},

urldate = {2020-11-17},

booktitle = {2020 IEEE International Conference on Data Mining (ICDM)},

pages = {996-1001},

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 = {bias, data mining, fairness, machine learning},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{roeslin2020feature,

title = {Feature Engineering for a Seismic Loss Prediction Model using Machine Learning, Christchurch Experience},

author = {Samuel Roeslin and Quincy Ma and Pavan Chigullapally and J\"{o}rg Wicker and Liam Wotherspoon},

url = {https://www.researchgate.net/profile/Samuel_Roeslin/publication/344503593_Feature_Engineering_for_a_Seismic_Loss_Prediction_Model_using_Machine_Learning_Christchurch_Experience/links/5f7d015a92851c14bcb36ed7/Feature-Engineering-for-a-Seismic-Loss-Prediction-Model-using-Machine-Learning-Christchurch-Experience.pdf},

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 = {computational sustainability, data mining, earthquakes, machine learning},

pubstate = {published},

tppubtype = {inproceedings}

}

@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 = {Boolean matrix decomposition, data mining},

pubstate = {published},

tppubtype = {inproceedings}

}

@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  = {2019},

date = {2019-09-19},

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 = {computational sustainability, earthquakes},

pubstate = {published},

tppubtype = {inproceedings}

}

@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 = {atmospheric chemistry, breath analysis, cheminformatics, cinema data mining, data mining, emotional response analysis, machine learning, movie analysis, smell of fear, sof, time series},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{wicker2016nonlinear,

title = {A Nonlinear Label Compression and Transformation Method for Multi-Label Classification using Autoencoders},

author = {J\"{o}rg Wicker and Andrey Tyukin and Stefan Kramer},

editor = {James Bailey and Latifur Khan and Takashi Washio and Gill Dobbie and Zhexue Joshua Huang and Ruili Wang},

url = {http://dx.doi.org/10.1007/978-3-319-31753-3_27},

doi = {10.1007/978-3-319-31753-3_27},

isbn = {978-3-319-31753-3},

year  = {2016},

date = {2016-04-16},

booktitle = {The 20th Pacific Asia Conference on Knowledge Discovery and Data Mining (PAKDD)},

volume = {9651},

pages = {328-340},

publisher = {Springer International Publishing},

address = {Switzerland},

series = {Lecture Notes in Computer Science},

abstract = {Multi-label classification targets the prediction of multiple interdependent and non-exclusive binary target variables. Transformation-based algorithms transform the data set such that regular single-label algorithms can be applied to the problem. A special type of transformation-based classifiers are label compression methods, that compress the labels and then mostly use single label classifiers to predict the compressed labels. So far, there are no compression-based algorithms follow a problem transformation approach and address non-linear dependencies in the labels. In this paper, we propose a new algorithm, called Maniac (Multi-lAbel classificatioN usIng AutoenCoders), which extracts the non-linear dependencies by compressing the labels using autoencoders. We adapt the training process of autoencoders in a way to make them more suitable for a parameter optimization in the context of this algorithm. The method is evaluated on eight standard multi-label data sets. Experiments show that despite not producing a good ranking, Maniac generates a particularly good bipartition of the labels into positives and negatives. This is caused by rather strong predictions with either really high or low probability. Additionally, the algorithm seems to perform better given more labels and a higher label cardinality in the data set.},

keywords = {autoencoders, label compression, machine learning, multi-label classification},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{raza2016trading,

title = {Trading Off Accuracy for Efficiency by Randomized Greedy Warping},

author = {Atif Raza and J\"{o}rg Wicker and Stefan Kramer},

url = {https://wicker.nz/nwp-acm/authorize.php?id=N10030 

http://doi.acm.org/10.1145/2851613.2851651},

doi = {10.1145/2851613.2851651},

isbn = {978-1-4503-3739-7},

year  = {2016},

date = {2016-01-01},

booktitle = {Proceedings of the 31st Annual ACM Symposium on Applied Computing},

pages = {883-890},

publisher = {ACM},

address = {New York, NY, USA},

series = {SAC '16},

abstract = {Dynamic Time Warping (DTW) is a widely used distance measure for time series data mining. Its quadratic complexity requires the application of various techniques (e.g. warping constraints, lower-bounds) for deployment in real-time scenarios. In this paper we propose a randomized greedy warping algorithm for f i nding similarity between time series instances.We show that the proposed algorithm outperforms the simple greedy approach and also provides very good time series similarity approximation consistently, as compared to DTW. We show that the Randomized Time Warping (RTW) can be used in place of DTW as a fast similarity approximation technique by trading some classification accuracy for very fast classification.},

keywords = {data mining, dynamic time warping, time series},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{wicker2015cinema,

title = {Cinema Data Mining: The Smell of Fear},

author = {J\"{o}rg Wicker and Nicolas Krauter and Bettina Derstorff and Christof St\"{o}nner and Efstratios Bourtsoukidis and Thomas Kl\"{u}pfel and Jonathan Williams and Stefan Kramer},

url = {https://wicker.nz/nwp-acm/authorize.php?id=N10031 

http://doi.acm.org/10.1145/2783258.2783404},

doi = {10.1145/2783258.2783404},

isbn = {978-1-4503-3664-2},

year  = {2015},

date = {2015-01-01},

booktitle = {Proceedings of the 21st ACM SIGKDD International Conference on Knowledge Discovery and Data Mining},

pages = {1235-1304},

publisher = {ACM},

address = {New York, NY, USA},

organization = {ACM},

series = {KDD '15},

abstract = {While the physiological response of humans to emotional events or stimuli is well-investigated for many modalities (like EEG, skin resistance, ...), surprisingly little is known about the exhalation of so-called Volatile Organic Compounds (VOCs) at quite low concentrations in response to such stimuli. VOCs are molecules of relatively small mass that quickly evaporate or sublimate and can be detected in the air that surrounds us. The paper introduces a new field of application for data mining, where trace gas responses of people reacting on-line to films shown in cinemas (or movie theaters) are related to the semantic content of the films themselves. To do so, we measured the VOCs from a movie theatre over a whole month in intervals of thirty seconds, and annotated the screened films by a controlled vocabulary compiled from multiple sources. To gain a better understanding of the data and to reveal unknown relationships, we have built prediction models for so-called forward prediction (the prediction of future VOCs from the past), backward prediction (the prediction of past scene labels from future VOCs) and for some forms of abductive reasoning and Granger causality. Experimental results show that some VOCs and some labels can be predicted with relatively low error, and that hints for causality with low p-values can be detected in the data.},

keywords = {atmospheric chemistry, breath analysis, causality, cheminformatics, cinema data mining, data mining, emotional response analysis, movie analysis, smell of fear, sof, time series},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{tyukin2015scavenger,

title = {Scavenger - A Framework for the Efficient Evaluation of Dynamic and Modular Algorithms},

author = {Andrey Tyukin and Stefan Kramer and J\"{o}rg Wicker},

editor = {Albert Bifet and Michael May and Bianca Zadrozny and Ricard Gavalda and Dino Pedreschi and Jaime Cardoso and Myra Spiliopoulou},

url = {http://dx.doi.org/10.1007/978-3-319-23461-8_40},

doi = {10.1007/978-3-319-23461-8_40},

isbn = {978-3-319-23460-1},

year  = {2015},

date = {2015-01-01},

booktitle = {Machine Learning and Knowledge Discovery in Databases},

volume = {9286},

pages = {325-328},

publisher = {Springer International Publishing},

series = {Lecture Notes in Computer Science},

abstract = {Machine Learning methods and algorithms are often highly modular in the sense that they rely on a large number of subalgorithms that are in principle interchangeable. For example, it is often possible to use various kinds of pre- and post-processing and various base classifiers or regressors as components of the same modular approach. We propose a framework, called Scavenger, that allows evaluating whole families of conceptually similar algorithms efficiently. The algorithms are represented as compositions, couplings and products of atomic subalgorithms. This allows partial results to be cached and shared between different instances of a modular algorithm, so that potentially expensive partial results need not be recomputed multiple times. Furthermore, our framework deals with issues of the parallel execution, load balancing, and with the backup of partial results for the case of implementation or runtime errors. Scavenger is licensed under the GPLv3 and can be downloaded freely at https://github.com/jorro/scavenger.},

keywords = {autoencoders, distributed processing, framework, large-scale, Scavenger},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{tyukin2014bmad,

title = {BMaD -- A Boolean Matrix Decomposition Framework},

author = {Andrey Tyukin and Stefan Kramer and J\"{o}rg Wicker},

editor = {Toon Calders and Floriana Esposito and Eyke H\"{u}llermeier and Rosa Meo},

url = {http://dx.doi.org/10.1007/978-3-662-44845-8_40},

doi = {10.1007/978-3-662-44845-8_40},

isbn = {978-3-662-44844-1},

year  = {2014},

date = {2014-01-01},

booktitle = {Machine Learning and Knowledge Discovery in Databases},

volume = {8726},

pages = {481-484},

publisher = {Springer Berlin Heidelberg},

series = {Lecture Notes in Computer Science},

abstract = {Boolean matrix decomposition is a method to obtain a compressed 

representation of a matrix with Boolean entries. We present a modular 

framework that unifies several Boolean matrix decomposition algorithms, and 

provide methods to evaluate their performance. The main advantages of 

the framework are its modular approach and hence the flexible 

combination of the steps of a Boolean matrix decomposition and the 

capability of handling missing values. The framework is licensed under 

the GPLv3 and can be downloaded freely at 

urlhttp://projects.informatik.uni-mainz.de/bmad.},

keywords = {Boolean matrix decomposition, data mining, framework},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{wicker2012multi,

title = {Multi-label Classification Using Boolean Matrix Decomposition},

author = {J\"{o}rg Wicker and Bernhard Pfahringer and Stefan Kramer},

url = {https://wicker.nz/nwp-acm/authorize.php?id=N10032 

http://doi.acm.org/10.1145/2245276.2245311},

doi = {10.1145/2245276.2245311},

isbn = {978-1-4503-0857-1},

year  = {2012},

date = {2012-01-01},

booktitle = {Proceedings of the 27th Annual ACM Symposium on Applied Computing},

pages = {179--186},

publisher = {ACM},

series = {SAC '12},

abstract = {This paper introduces a new multi-label classifier based on Boolean matrix decomposition. Boolean matrix decomposition is used to extract, from the full label matrix, latent labels representing useful Boolean combinations of the original labels. Base level models predict latent labels, which are subsequently transformed into the actual labels by Boolean matrix multiplication with the second matrix from the decomposition. The new method is tested on six publicly available datasets with varying numbers of labels. The experimental evaluation shows that the new method works particularly well on datasets with a large number of labels and strong dependencies among them.},

keywords = {associations, Boolean matrix decomposition, machine learning, multi-label classification},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{wicker2008sindbad,

title = {SINDBAD and SiQL: An Inductive Database and Query Language in the Relational Model},

author = {J\"{o}rg Wicker and Lothar Richter and Kristina Kessler and Stefan Kramer},

editor = {Walter Daelemans and Bart Goethals and Katharina Morik},

url = {http://dx.doi.org/10.1007/978-3-540-87481-2_48},

doi = {10.1007/978-3-540-87481-2_48},

isbn = {978-3-540-87480-5},

year  = {2008},

date = {2008-01-01},

booktitle = {Machine Learning and Knowledge Discovery in Databases},

volume = {5212},

pages = {690-694},

publisher = {Springer Berlin Heidelberg},

series = {Lecture Notes in Computer Science},

abstract = {In this demonstration, we will present the concepts and an implementation of an inductive database \textendash as proposed by Imielinski and Mannila \textendash in the relational model. The goal is to support all steps of the knowledge discovery process on the basis of queries to a database system. The query language SiQL (structured inductive query language), an SQL extension, offers query primitives for feature selection, discretization, pattern mining, clustering, instance-based learning and rule induction. A prototype system processing such queries was implemented as part of the SINDBAD (structured inductive database development) project. To support the analysis of multi-relational data, we incorporated multi-relational distance measures based on set distances and recursive descent. The inclusion of rule-based classification models made it necessary to extend the data model and software architecture significantly. The prototype is applied to three different data sets: gene expression analysis, gene regulation prediction and structure-activity relationships (SARs) of small molecules.},

keywords = {data mining, inductive databases, machine learning, query languages},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{richter2008inductive,

title = {An Inductive Database and Query Language in the Relational Model},

author = {Lothar Richter and J\"{o}rg Wicker and Kristina Kessler and Stefan Kramer},

url = {https://wicker.nz/nwp-acm/authorize.php?id=N10033 

http://doi.acm.org/10.1145/1353343.1353440},

doi = {10.1145/1353343.1353440},

isbn = {978-1-59593-926-5},

year  = {2008},

date = {2008-01-01},

booktitle = {Proceedings of the 11th International Conference on Extending Database Technology: Advances in Database Technology},

pages = {740--744},

publisher = {ACM},

series = {EDBT '08},

abstract = {In the demonstration, we will present the concepts and an implementation of an inductive database -- as proposed by Imielinski and Mannila -- in the relational model. The goal is to support all steps of the knowledge discovery process, from pre-processing via data mining to post-processing, on the basis of queries to a database system. The query language SIQL (structured inductive query language), an SQL extension, offers query primitives for feature selection, discretization, pattern mining, clustering, instance-based learning and rule induction. A prototype system processing such queries was implemented as part of the SINDBAD (structured inductive database development) project. Key concepts of this system, among others, are the closure of operators and distances between objects. To support the analysis of multi-relational data, we incorporated multi-relational distance measures based on set distances and recursive descent. The inclusion of rule-based classification models made it necessary to extend the data model and the software architecture significantly. The prototype is applied to three different applications: gene expression analysis, gene regulation prediction and structure-activity relationships (SARs) of small molecules.},

keywords = {data mining, inductive databases, machine learning, query languages},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{wicker2008sindbadsails,

title = {SINDBAD SAILS: A Service Architecture for Inductive Learning Schemes},

author = {J\"{o}rg Wicker and Christoph Brosdau and Lothar Richter and Stefan Kramer},

url = {http://www.ecmlpkdd2008.org/files/pdf/workshops/sokd/2.pdf},

year  = {2008},

date = {2008-01-01},

booktitle = {Proceedings of the First Workshop on Third Generation Data Mining: Towards Service-Oriented Knowledge Discovery},

abstract = {The paper presents SINDBAD SAILS (Service Architecture for Inductive Learning Schemes), a Web Service interface to the inductive database SINDBAD. To the best of our knowledge, it is the first time a Web Service interface is provided for an inductive database. The combination of service-oriented architectures and inductive databases is particularly useful, as it enables distributed data mining without the need to install specialized data mining or machine learning software. Moreover, inductive queries can easily be used in almost any kind of programming language. The paper discusses the underlying concepts and explains a sample program making use of SINDBAD SAILS.},

keywords = {data mining, inductive databases, machine learning, query languages},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{wicker2008machine,

title = {Machine Learning and Data Mining Approaches to Biodegradation Pathway Prediction},

author = {J\"{o}rg Wicker and Kathrin Fenner and Lynda Ellis and Larry Wackett and Stefan Kramer},

editor = {Will Bridewell and Toon Calders and Ana Karla Medeiros and Stefan Kramer and Mykola Pechenizkiy and Ljupco Todorovski},

url = {http://www.ecmlpkdd2008.org/files/pdf/workshops/ipm/9.pdf},

year  = {2008},

date = {2008-01-01},

booktitle = {Proceedings of the Second International Workshop on the Induction of Process Models at ECML PKDD 2008},

keywords = {biodegradation, cheminformatics, computational sustainability, enviPath, machine learning, metabolic pathways},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{kramer2006inductive,

title = {Inductive Databases in the Relational Model: The Data as the Bridge},

author = {Stefan Kramer and Volker Aufschild and Andreas Hapfelmeier and Alexander Jarasch and Kristina Kessler and Stefan Reckow and J\"{o}rg Wicker and Lothar Richter},

editor = {Francesco Bonchi and Jean-Fran\c{c}ois Boulicaut},

url = {http://dx.doi.org/10.1007/11733492_8},

doi = {10.1007/11733492_8},

isbn = {978-3-540-33292-3},

year  = {2006},

date = {2006-01-01},

booktitle = {Knowledge Discovery in Inductive Databases},

volume = {3933},

pages = {124-138},

publisher = {Springer Berlin Heidelberg},

series = {Lecture Notes in Computer Science},

abstract = {We present a new and comprehensive approach to inductive databases in the relational model. The main contribution is a new inductive query language extending SQL, with the goal of supporting the whole knowledge discovery process, from pre-processing via data mining to post-processing. A prototype system supporting the query language was developed in the SINDBAD (structured inductive database development) project. Setting aside models and focusing on distance-based and instance-based methods, closure can easily be achieved. An example scenario from the area of gene expression data analysis demonstrates the power and simplicity of the concept. We hope that this preliminary work will help to bring the fundamental issues, such as the integration of various pattern domains and data mining techniques, to the attention of the inductive database community.},

keywords = {data mining, inductive databases, machine learning, query languages},

pubstate = {published},

tppubtype = {inproceedings}

}