Markus Hagenbuchner

Learning Structural Representations of Text Documents in Large Document Collections

Publisher: Springer Berlin Heidelberg

Date: 2013

DOI: 10.1007/978-3-642-36657-4_14

Recognition of Sequences of Graphical Patterns

Publisher: Springer Berlin Heidelberg

Date: 2010

DOI: 10.1007/978-3-642-12159-3_5

Free-living Evaluation Of Laboratory-based Machine Learning Algorithms For Activity Classification In Preschool Children

Publisher: Ovid Technologies (Wolters Kluwer Health)

Date: 06-2019

DOI: 10.1249/01.MSS.0000560991.17660.EA

A self-organizing map for adaptive processing of structured data

Publisher: Institute of Electrical and Electronics Engineers (IEEE)

Date: 05-2003

DOI: 10.1109/TNN.2003.810735

Going Deeper with Recursive Convolutional Layers

Publisher: IEEE

Date: 18-06-2023

DOI: 10.1109/IJCNN54540.2023.10191350

Efficient Clustering of Structured Documents Using Graph Self-Organizing Maps

Publisher: Springer Berlin Heidelberg

Date: 2008

DOI: 10.1007/978-3-540-85902-4_19

Sensor-enabled Activity Class Recognition in Preschoolers: Hip versus Wrist Data

Publisher: Ovid Technologies (Wolters Kluwer Health)

Date: 03-2018

DOI: 10.1249/MSS.0000000000001460

Fast and accurate dose predictions for novel radiotherapy treatments in heterogeneous phantoms using conditional 3D-UNet generative adversarial networks

Publisher: Wiley

Date: 03-03-2022

DOI: 10.1002/MP.15555

Abstract: Novel radiotherapy techniques like synchrotron X‐ray microbeam radiation therapy (MRT) require fast dose distribution predictions that are accurate at the sub‐mm level, especially close to tissue/bone/air interfaces. Monte Carlo (MC) physics simulations are recognized to be one of the most accurate tools to predict the dose delivered in a target tissue but can be very time consuming and therefore prohibitive for treatment planning. Faster dose prediction algorithms are usually developed for clinically deployed treatments only. In this work, we explore a new approach for fast and accurate dose estimations suitable for novel treatments using digital phantoms used in preclinical development and modern machine learning techniques. We develop a generative adversarial network (GAN) model, which is able to emulate the equivalent Geant4 MC simulation with adequate accuracy and use it to predict the radiation dose delivered by a broad synchrotron beam to various phantoms. The energy depositions used for the training of the GAN are obtained using full Geant4 MC simulations of a synchrotron radiation broad beam passing through the phantoms. The energy deposition is scored and predicted in voxel matrices of size 140 × 18 × 18 with a voxel edge length of 1 mm. The GAN model consists of two competing 3D convolutional neural networks, which are conditioned on the photon beam and phantom properties. The generator network has a U‐Net structure and is designed to predict the energy depositions of the photon beam inside three phantoms of variable geometry with increasing complexity. The critic network is a relatively simple convolutional network, which is trained to distinguish energy depositions predicted by the generator from the ones obtained with the full MC simulation. The energy deposition predictions inside all phantom geometries under investigation show deviations of less than 3% of the maximum deposited energy from the simulation for roughly 99% of the voxels in the field of the beam. Inside the most realistic phantom, a simple pediatric head, the model predictions deviate by less than 1% of the maximal energy deposition from the simulations in more than 96% of the in‐field voxels. For all three phantoms, the model generalizes the energy deposition predictions well to phantom geometries, which have not been used for training the model but are interpolations of the training data in multiple dimensions. The computing time for a single prediction is reduced from several hundred hours using Geant4 simulation to less than a second using the GAN model. The proposed GAN model predicts dose distributions inside unknown phantoms with only small deviations from the full MC simulation with computations times of less than a second. It demonstrates good interpolation ability to unseen but similar phantom geometries and is flexible enough to be trained on data with different radiation scenarios without the need for optimization of the model parameter. This proof‐of‐concept encourages to apply and further develop the model for the use in MRT treatment planning, which requires fast and accurate predictions with sub‐mm resolutions.

Web Spam Detection by Probability Mapping GraphSOMs and Graph Neural Networks

Publisher: Springer Berlin Heidelberg

Date: 2010

DOI: 10.1007/978-3-642-15822-3_45

High-resolution Self-Organizing Maps for advanced visualization and dimension reduction

Publisher: Elsevier BV

Date: 09-2018

DOI: 10.1016/J.NEUNET.2018.04.011

Abstract: Kohonen's Self Organizing feature Map (SOM) provides an effective way to project high dimensional input features onto a low dimensional display space while preserving the topological relationships among the input features. Recent advances in algorithms that take advantages of modern computing hardware introduced the concept of high resolution SOMs (HRSOMs). This paper investigates the capabilities and applicability of the HRSOM as a visualization tool for cluster analysis and its suitabilities to serve as a pre-processor in ensemble learning models. The evaluation is conducted on a number of established benchmarks and real-world learning problems, namely, the policeman benchmark, two web spam detection problems, a network intrusion detection problem, and a malware detection problem. It is found that the visualization resulted from an HRSOM provides new insights concerning these learning problems. It is furthermore shown empirically that broad benefits from the use of HRSOMs in both clustering and classification problems can be expected.

Sentence Extraction by Graph Neural Networks

Publisher: No publisher found

Date: 2010

DOI: 10.1007/978-3-642-15825-4\_29

Self Organizing Maps for the clustering of large sets of labeled graphs

Publisher: Springer Berlin Heidelberg

Date: 2009

DOI: 10.1007/978-3-642-03761-0_49

Application of Text Mining Methodologies to Health Insurance Schedules

Publisher: IGI Global

Date: 2006

DOI: 10.4018/978-1-59140-827-7.CH002

Abstract: This chapter describes the application of a number of text mining techniques to discover patterns in the health insurance schedule with an aim to uncover any inconsistency or ambiguity in the schedule. In particular, we will apply first a simple “bag of words” technique to study the text data, and to evaluate the hypothesis: Is there any inconsistency in the text description of the medical procedures used? It is found that the hypothesis is not valid, and hence the investigation is continued on how best to cluster the text. This work would have significance to health insurers to assist them to differentiate descriptions of the medical procedures. Secondly, it would also assist the health insurer to describe medical procedures in an unambiguous manner.

Embedding the Self-Organisation of Deep Feature Maps in the Hamburger Framework can Yield Better and Interpretable Results

Publisher: IEEE

Date: 18-06-2023

DOI: 10.1109/IJCNN54540.2023.10191477

Automated functional testing of online search services

Publisher: Wiley

Date: 24-08-2010

DOI: 10.1002/STVR.437

A supervised training algorithm for self-organizing maps for structures

Publisher: Elsevier BV

Date: 09-2005

DOI: 10.1016/J.PATREC.2005.03.009

Application of text mining methodologies to health insurance schedules

Publisher: IGI Global

Date: 2008

DOI: 10.4018/978-1-60566-050-9.CH072

Abstract: This chapter describes the application of a number of text mining techniques to discover patterns in the health insurance schedule with an aim to uncover any inconsistency or ambiguity in the schedule. In particular, we will apply first a simple “bag of words” technique to study the text data, and to evaluate the hypothesis: Is there any inconsistency in the text description of the medical procedures used? It is found that the hypothesis is not valid, and hence the investigation is continued on how best to cluster the text. This work would have significance to health insurers to assist them to differentiate descriptions of the medical procedures. Secondly, it would also assist the health insurer to describe medical procedures in an unambiguous manner.

Accurate and Fast Deep Learning Dose Prediction for a Preclinical Microbeam Radiation Therapy Study Using Low-Statistics Monte Carlo Simulations

Publisher: MDPI AG

Date: 04-04-2023

DOI: 10.3390/CANCERS15072137

Abstract: Microbeam radiation therapy (MRT) utilizes coplanar synchrotron radiation beamlets and is a proposed treatment approach for several tumor diagnoses that currently have poor clinical treatment outcomes, such as gliosarcomas. Monte Carlo (MC) simulations are one of the most used methods at the Imaging and Medical Beamline, Australian Synchrotron to calculate the dose in MRT preclinical studies. The steep dose gradients associated with the 50μm-wide coplanar beamlets present a significant challenge for precise MC simulation of the dose deposition of an MRT irradiation treatment field in a short time frame. The long computation times inhibit the ability to perform dose optimization in treatment planning or apply online image-adaptive radiotherapy techniques to MRT. Much research has been conducted on fast dose estimation methods for clinically available treatments. However, such methods, including GPU Monte Carlo implementations and machine learning (ML) models, are unavailable for novel and emerging cancer radiotherapy options such as MRT. In this work, the successful application of a fast and accurate ML dose prediction model for a preclinical MRT rodent study is presented for the first time. The ML model predicts the peak doses in the path of the microbeams and the valley doses between them, delivered to the tumor target in rat patients. A CT imaging dataset is used to generate digital phantoms for each patient. Augmented variations of the digital phantoms are used to simulate with Geant4 the energy depositions of an MRT beam inside the phantoms with 15% (high-noise) and 2% (low-noise) statistical uncertainty. The high-noise MC simulation data are used to train the ML model to predict the energy depositions in the digital phantoms. The low-noise MC simulations data are used to test the predictive power of the ML model. The predictions of the ML model show an agreement within 3% with low-noise MC simulations for at least 77.6% of all predicted voxels (at least 95.9% of voxels containing tumor) in the case of the valley dose prediction and for at least 93.9% of all predicted voxels (100.0% of voxels containing tumor) in the case of the peak dose prediction. The successful use of high-noise MC simulations for the training, which are much faster to produce, accelerates the production of the training data of the ML model and encourages transfer of the ML model to different treatment modalities for other future applications in novel radiation cancer therapies.

Prediction of activity type in preschool children using machine learning techniques

Publisher: Elsevier BV

Date: 07-2015

DOI: 10.1016/J.JSAMS.2014.06.003

Abstract: Recent research has shown that machine learning techniques can accurately predict activity classes from accelerometer data in adolescents and adults. The purpose of this study is to develop and test machine learning models for predicting activity type in preschool-aged children. Participants completed 12 standardised activity trials (TV, reading, tablet game, quiet play, art, treasure hunt, cleaning up, active game, obstacle course, bicycle riding) over two laboratory visits. Eleven children aged 3-6 years (mean age=4.8±0.87 55% girls) completed the activity trials while wearing an ActiGraph GT3X+ accelerometer on the right hip. Activities were categorised into five activity classes: sedentary activities, light activities, moderate to vigorous activities, walking, and running. A standard feed-forward Artificial Neural Network and a Deep Learning Ensemble Network were trained on features in the accelerometer data used in previous investigations (10th, 25th, 50th, 75th and 90th percentiles and the lag-one autocorrelation). Overall recognition accuracy for the standard feed forward Artificial Neural Network was 69.7%. Recognition accuracy for sedentary activities, light activities and games, moderate-to-vigorous activities, walking, and running was 82%, 79%, 64%, 36% and 46%, respectively. In comparison, overall recognition accuracy for the Deep Learning Ensemble Network was 82.6%. For sedentary activities, light activities and games, moderate-to-vigorous activities, walking, and running recognition accuracy was 84%, 91%, 79%, 73% and 73%, respectively. Ensemble machine learning approaches such as Deep Learning Ensemble Network can accurately predict activity type from accelerometer data in preschool children.

Higher Order Polynomial Transformer for Fine-Grained Freezing of Gait Detection

Publisher: Institute of Electrical and Electronics Engineers (IEEE)

Date: 2023

DOI: 10.1109/TNNLS.2023.3264647

Application of Text Mining Methodologies to Health Insurance Schedules

Publisher: IGI Global

Date: 2008

DOI: 10.4018/978-1-59904-990-8.CH045

Abstract: This chapter describes the application of a number of text mining techniques to discover patterns in the health insurance schedule with an aim to uncover any inconsistency or ambiguity in the schedule. In particular, we will apply first a simple “bag of words” technique to study the text data, and to evaluate the hypothesis: Is there any inconsistency in the text description of the medical procedures used? It is found that the hypothesis is not valid, and hence the investigation is continued on how best to cluster the text. This work would have significance to health insurers to assist them to differentiate descriptions of the medical procedures. Secondly, it would also assist the health insurer to describe medical procedures in an unambiguous manner.

Self-Organizing Maps for Structured Domains: Theory, Models, and Learning of Kernels

Publisher: Springer Berlin Heidelberg

Date: 2009

DOI: 10.1007/978-3-642-04003-0_2

Unsupervised and Supervised Learning of Graph Domains

Publisher: Springer Berlin Heidelberg

Date: 2009

DOI: 10.1007/978-3-642-04003-0_3

A Study on the effects of recursive convolutional layers in convolutional neural networks

Publisher: Elsevier BV

Date: 10-2021

DOI: 10.1016/J.NEUCOM.2021.07.021

Graph Fusion Network-Based Multimodal Learning for Freezing of Gait Detection

Publisher: Institute of Electrical and Electronics Engineers (IEEE)

Date: 03-2023

DOI: 10.1109/TNNLS.2021.3105602

Breast cancer data analysis for survivability studies and prediction

Publisher: Elsevier BV

Date: 03-2018

DOI: 10.1016/J.CMPB.2017.12.011

Abstract: Breast cancer is the most common cancer affecting females worldwide. Breast cancer survivability prediction is challenging and a complex research task. Existing approaches engage statistical methods or supervised machine learning to assess redict the survival prospects of patients. The main objectives of this paper is to develop a robust data analytical model which can assist in (i) a better understanding of breast cancer survivability in presence of missing data, (ii) providing better insights into factors associated with patient survivability, and (iii) establishing cohorts of patients that share similar properties. Unsupervised data mining methods viz. the self-organising map (SOM) and density-based spatial clustering of applications with noise (DBSCAN) is used to create patient cohort clusters. These clusters, with associated patterns, were used to train multilayer perceptron (MLP) model for improved patient survivability analysis. A large dataset available from SEER program is used in this study to identify patterns associated with the survivability of breast cancer patients. Information gain was computed for the purpose of variable selection. All of these methods are data-driven and require little (if any) input from users or experts. SOM consolidated patients into cohorts of patients with similar properties. From this, DBSCAN identified and extracted nine cohorts (clusters). It is found that patients in each of the nine clusters have different survivability time. The separation of patients into clusters improved the overall survival prediction accuracy based on MLP and revealed intricate conditions that affect the accuracy of a prediction. A new, entirely data driven approach based on unsupervised learning methods improves understanding and helps identify patterns associated with the survivability of patient. The results of the analysis can be used to segment the historical patient data into clusters or subsets, which share common variable values and survivability. The survivability prediction accuracy of a MLP is improved by using identified patient cohorts as opposed to using raw historical data. Analysis of variable values in each cohort provide better insights into survivability of a particular subgroup of breast cancer patients.

Sign Language Translation with Hierarchical Spatio-Temporal Graph Neural Network

Publisher: IEEE

Date: 2022

DOI: 10.1109/WACV51458.2022.00219

PO-1558 Fast dose predictions with generative adversarial networks for treatment planning of novel therapies

Publisher: Elsevier BV

Date: 05-2022

DOI: 10.1016/S0167-8140(22)03522-8

Sentence Extraction by Graph Neural Networks

Publisher: Springer Berlin Heidelberg

Date: 2010

DOI: 10.1007/978-3-642-15825-4_29

Data Driven Encoding of Structures and Link Predictions in Large XML Document Collections

Publisher: IGI Global

Date: 2011

DOI: 10.4018/978-1-61350-356-0

University Of Wollongong

Location: Australia

View Organisation

Linkage - International - Grant ID: LX0454446

Start Date: 01-2004

End Date: 12-2006

Amount: $20,000.00

Funder: Australian Research Council

Discovery Projects - Grant ID: DP110103376

Start Date: 2011

End Date: 12-2014

Amount: $285,000.00

Funder: Australian Research Council

Discovery Projects - Grant ID: DP0774168

Start Date: 2007

End Date: 11-2011

Amount: $311,483.00

Funder: Australian Research Council

Discovery Projects - Grant ID: DP0774617

Start Date: 09-2007

End Date: 02-2012

Amount: $405,000.00

Funder: Australian Research Council

Discovery Projects - Grant ID: DP0452862

Start Date: 01-2004

End Date: 07-2007

Amount: $282,000.00

Funder: Australian Research Council

Discovery Projects - Grant ID: DP210102674

Start Date: 2021

End Date: 12-2023

Amount: $444,416.00

Funder: Australian Research Council

Discovery Projects - Grant ID: DP0453089

Start Date: 01-2004

End Date: 07-2007

Amount: $150,000.00

Funder: Australian Research Council

Linkage Infrastructure, Equipment And Facilities - Grant ID: LE110100143

Start Date: 08-2011

End Date: 08-2012

Amount: $500,000.00

Funder: Australian Research Council

Linkage - International - Grant ID: LX0882106

Start Date: 2008

End Date: 12-2011

Amount: $23,000.00

Funder: Australian Research Council

Discovery Projects - Grant ID: DP150100116

Start Date: 06-2015

End Date: 12-2019

Amount: $286,424.00

Funder: Australian Research Council