@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},

year  = {2022},

date = {2022-02-22},

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

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 = {},

pubstate = {forthcoming},

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},

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

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 = {},

pubstate = {forthcoming},

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

year  = {2021},

date = {2021-09-27},

urldate = {2021-09-27},

booktitle = { IEEE/RSJ International Conference on Intelligent Robots and Systems},

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 = {},

pubstate = {forthcoming},

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 = {},

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},

doi = {10.1109/ICDM50108.2020.00115},

issn = {2374-8486},

year  = {2020},

date = {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 = {},

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 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 = {},

pubstate = {published},

tppubtype = {inproceedings}

}