ORCID Profile
0000-0001-9250-6604
Current Organisation
University of Technology Sydney
Does something not look right? The information on this page has been harvested from data sources that may not be up to date. We continue to work with information providers to improve coverage and quality. To report an issue, use the Feedback Form.
Research Topics
In Research Link Australia (RLA), "Research Topics" refer to ANZSRC FOR and SEO codes. These topics are either sourced from ANZSRC FOR and SEO codes listed in researchers' related grants or generated by a large language model (LLM) based on their publications.
Top 5 Research Topics
ANZSRC Field of Research (FoR)
Artificial Intelligence and Image Processing | Computer Vision | Computer Vision | Pattern Recognition | Detection And Prevention Of Crime; Security Services | Simulation And Modelling | Infrastructure Engineering and Asset Management | Computer Communications Networks | Library and Information Studies | Civil Engineering | Decision Support and Group Support Systems | Calculus of Variations, Systems Theory and Control Theory | Information Storage, Retrieval And Management | Simulation and Modelling | Interdisciplinary Engineering Not Elsewhere Classified | Interdisciplinary Engineering | Multimedia Programming
ANZSRC Socio-Economic Objective (SEO)
Commercial security services | Information processing services | Computer software and services not elsewhere classified | Management and productivity issues not elsewhere classified | National Security | Integrated systems | Air transport | Expanding Knowledge in the Information and Computing Sciences | Air Terminal Infrastructure and Management |
Related Links
Publications
Fusing Face and Body Display for Bi-modal Emotion Recognition: Single Frame Analysis and Multi-frame Post Integration
Publisher: No publisher found
Date: 2005
DOI: 10.1007/11573548\_14
Learning Neural Textual Representations for Citation Recommendation
Publisher: IEEE
Date: 10-01-2021
Neural network classifiers for automated video surveillance
Publisher: IEEE
Date: 2003
A Framework for Track Matching Across Disjoint Cameras using Robust Shape and Appearance Features
Publisher: IEEE
Date: 09-2007
An Embedding-Based Topic Model for Document Classification
Publisher: Association for Computing Machinery (ACM)
Date: 05-05-2021
DOI: 10.1145/3431728
Abstract: Topic modeling is an unsupervised learning task that discovers the hidden topics in a collection of documents. In turn, the discovered topics can be used for summarizing, organizing, and understanding the documents in the collection. Most of the existing techniques for topic modeling are derivatives of the Latent Dirichlet Allocation which uses a bag-of-word assumption for the documents. However, bag-of-words models completely dismiss the relationships between the words. For this reason, this article presents a two-stage algorithm for topic modelling that leverages word embeddings and word co-occurrence. In the first stage, we determine the topic-word distributions by soft-clustering a random set of embedded n -grams from the documents. In the second stage, we determine the document-topic distributions by s ling the topics of each document from the topic-word distributions. This approach leverages the distributional properties of word embeddings instead of using the bag-of-words assumption. Experimental results on various data sets from an Australian compensation organization show the remarkable comparative effectiveness of the proposed algorithm in a task of document classification.
A Discriminative Prototype Selection Approach for Graph Embedding in Human Action Recognition
Publisher: IEEE
Date: 11-2011
Tracking People in Crowds by a Part Matching Approach
Publisher: IEEE
Date: 09-2008
DOI: 10.1109/AVSS.2008.45
A bimodal face and body gesture database for automatic analysis of human nonverbal affective behavior
Publisher: IEEE
Date: 2006
DOI: 10.1109/ICPR.2006.39
V-JAUNE
Publisher: Association for Computing Machinery (ACM)
Date: 26-04-2017
DOI: 10.1145/3063532
Abstract: Video summarization and action recognition are two important areas of multimedia video analysis. While these two areas have been tackled separately to date, in this article, we present a latent structural SVM framework to recognize the action and derive the summary of a video in a joint, simultaneous fashion. Efficient inference is provided by a submodular score function that accounts for the action and summary jointly. In this article, we also define a novel measure to evaluate the quality of a predicted video summary against the annotations of multiple annotators. Quantitative and qualitative results over two challenging action datasets—the ACE and MSR DailyActivity3D datasets—show that the proposed joint approach leads to higher action recognition accuracy and equivalent or better summary quality than comparable approaches that perform these tasks separately.
Focus based Feature Extraction for Pallets Recognition
Publisher: British Machine Vision Association
Date: 2000
DOI: 10.5244/C.14.70
Well-M$^3$N: A Maximum-Margin Approach to Unsupervised Structured Prediction
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 12-2019
Eliciting visual primitives for detection of elongated shapes
Publisher: Elsevier BV
Date: 04-1999
Robust Dimensionality Reduction for Human Action Recognition
Publisher: IEEE
Date: 12-2010
Leveraging Discourse Rewards for Document-Level Neural Machine Translation
Publisher: International Committee on Computational Linguistics
Date: 2020
The Sakbot system for moving object detection and tracking
Publisher: Springer US
Date: 2001
Detecting compromised IoT devices: Existing techniques, challenges, and a way forward
Publisher: Elsevier BV
Date: 09-2023
Learning for feature selection and shape detection
Publisher: Springer Berlin Heidelberg
Date: 1997
Sequential Labeling with Structural SVM Under an Average Precision Loss
Publisher: No publisher found
Date: 2016
A hardware generator of multi-point distributed random numbers for Monte Carlo simulation (QFRC paper #156)
Publisher: Elsevier BV
Date: 02-2005
A Multi-Document Coverage Reward for RELAXed Multi-Document Summarization
Publisher: Association for Computational Linguistics
Date: 2022
Automated classification of female facial beauty by image analysis and supervised learning
Publisher: SPIE
Date: 07-01-2004
DOI: 10.1117/12.526531
Comparison of Classifier for Human Activity Recognition
Publisher: Springer Berlin Heidelberg
Date: 2007
Exploiting Symbolic Learning in Visual Inspection
Publisher: Springer Berlin Heidelberg
Date: 1997
DOI: 10.1007/BFB0052843
Automatic Human Action Recognition in Video by Graph Embedding
Publisher: Springer Berlin Heidelberg
Date: 2011
The Contextualized Regressive Topic Model
Publisher: Elsevier BV
Date: 2023
DOI: 10.2139/SSRN.4373206
BAP1, a marker for aggressive and recurrent meningioma?
Publisher: Elsevier BV
Date: 02-2019
An Infinite Adaptive Online Learning Model for Segmentation and Classification of Streaming Data
Publisher: IEEE
Date: 08-2014
HMM-MIO: An Enhanced Hidden Markov Model for Action Recognition
Publisher: IEEE
Date: 06-2011
Automatic Temporal Segment Detection and Affect Recognition From Face and Body Display
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 02-2009
Detection of Circular Objects by Wave Propagation on a Mesh-Connected Computer
Publisher: Elsevier BV
Date: 11-1995
Prototype-based budget maintenance for tracking in depth videos
Publisher: Springer Science and Business Media LLC
Date: 22-10-2017
Detection of luminosity profiles of elongated shapes
Publisher: IEEE
Date: 1996
Leveraging Discourse Rewards for Document-Level Neural Machine Translation
Publisher: arXiv
Date: 2020
Improving Data Prefetching Efficacy in Multimedia Applications
Publisher: Springer Science and Business Media LLC
Date: 2003
An Investigation of Recurrent Neural Architectures for Drug Name Recognition
Publisher: Association for Computational Linguistics
Date: 2016
DOI: 10.18653/V1/W16-6101
Human action recognition with MPEG-7 descriptors and architectures
Publisher: ACM
Date: 29-10-2010
Comparison Between Genetic Algorithms and the Baum-Welch Algorithm in Learning HMMs for Human Activity Classification
Publisher: Springer Berlin Heidelberg
Date: 2007
Comparison of Techniques for Mitigating the Effects of Illumination Variations on the Appearance of Human Target
Publisher: Springer Berlin Heidelberg
Date: 2007
BERTTune: Fine-Tuning Neural Machine Translation with BERTScore
Publisher: Association for Computational Linguistics
Date: 2021
A pair hidden Markov support vector machine for alignment of human actions
Publisher: IEEE
Date: 07-2016
Face and body gesture analysis for multimodal HCI
Publisher: Springer Berlin Heidelberg
Date: 2004
Improving Machine Translation and Summarization with the Sinkhorn Divergence
Publisher: Springer Nature Switzerland
Date: 2023
Hidden Markov Models with Kernel Density Estimation of Emission Probabilities and their Use in Activity Recognition
Publisher: IEEE
Date: 06-2007
Histogram-Based Training Initialisation of Hidden Markov Models for Human Action Recognition
Publisher: IEEE
Date: 08-2010
DOI: 10.1109/AVSS.2010.25
Disjoint Track Matching Based On A Major Color Spectrum Histogram Representation
Publisher: SPIE-Intl Soc Optical Eng
Date: 04-2007
DOI: 10.1117/1.2730482
An FPGA generator for multipoint distributed random variables
Publisher: ACM
Date: 20-02-2005
Joint action recognition and summarization by sub-modular inference
Publisher: IEEE
Date: 03-2016
A Submodular Approach for Reference Recommendation
Publisher: Springer Singapore
Date: 2020
Topic-Document Inference with the Gumbel-Softmax Distribution
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 2021
Head detection for video surveillance based on categorical hair and skin colour models
Publisher: IEEE
Date: 11-2009
Compressive Sensing of Time Series for Human Action Recognition
Publisher: IEEE
Date: 12-2010
System-Wide Tracking of Individuals
Publisher: Springer Berlin Heidelberg
Date: 2011
Track matching over disjoint camera views based on an incremental major color spectrum histogram
Publisher: IEEE
Date: 2005
Comparative beauty classification for pre-surgery planning
Publisher: IEEE
Date: 2004
Track Matching by Major Color Histograms Matching and Post-matching Integration
Publisher: No publisher found
Date: 2005
Mixtures of Normalized Linear Projections
Publisher: No publisher found
Date: 2009
Statistic and knowledge-based moving object detection in traffic scenes
Publisher: IEEE
Date: 2000
Tracking people under heavy occlusions by layered data association
Publisher: Springer Science and Business Media LLC
Date: 29-05-2015
Minimum-risk temporal alignment of videos
Publisher: Springer Science and Business Media LLC
Date: 14-08-2018
A preliminary performance evaluation of the Quadrics architecture with the DARPA image understanding benchmark
Publisher: Springer Berlin Heidelberg
Date: 1995
DOI: 10.1007/BFB0046619
Mean shift for accurate license plate localization
Publisher: IEEE
Date: 2005
Sequential Labeling With Structural SVM Under Nondecomposable Losses
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 09-2018
Detecting major segmentation errors for a tracked person using colour feature analysis
Publisher: IEEE
Date: 09-2007
Multi-Frame Moving object track matching based on an incremental major colour spectrum histogram matching algorithm
Publisher: IEEE
Date: 2006
Parallel vision subsystem for robotic inspection and manipulation
Publisher: IEEE
Date: 1994
An accurate algorithm for head detection based on XYZ and HSV hair and skin color models
Publisher: IEEE
Date: 2008
Deterministic Initialization of Hidden Markov Models for Human Action Recognition
Publisher: IEEE
Date: 2009
SMGKM: An Efficient Incremental Algorithm for Clustering Document Collections
Publisher: Springer Nature Switzerland
Date: 2023
Matching of objects moving across disjoint cameras
Publisher: IEEE
Date: 10-2006
Persian named entity recognition with structural prediction methods
Publisher: De Gruyter
Date: 08-05-2023
Comparison of Techniques for Mitigating the Effects of Illumination Variations on the Appearance of Human Targets
Publisher: No publisher found
Date: 2007
Performance Analysis of MPEG-4 Decoder and Encoder
Publisher: Croatian Soc. Electron. Marine
Date: 2002
An Efficient Bayesian Framework For On-Line Action Recognition
Publisher: IEEE
Date: 11-2009
Comparison Between Genetic Algorithms and the Baum-Welch Algorithm in Learning HMMs for Human Activity Classification
Publisher: No publisher found
Date: 2007
The GIOTTO System: a Parallel Computer for Image Processing
Publisher: Elsevier BV
Date: 10-1997
MLiT: mixtures of Gaussians under linear transformations
Publisher: Springer Science and Business Media LLC
Date: 26-03-2011
Comparative performance analysis of feature sets for abandoned object classification
Publisher: IEEE
Date: 10-2008
Multichannel mixture models for time-series analysis and classification of engagement with multiple health services: An application to psychology and physiotherapy utilization patterns after traffic a
Publisher: Elsevier BV
Date: 2021
Taxonomy-Based Feature Extraction for Document Classification, Clustering and Semantic Analysis
Publisher: Springer Nature Switzerland
Date: 2023
Detecting moving objects, ghosts, and shadows in video streams
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 10-2003
Assessing facial beauty through proportion analysis by image processing and supervised learning
Publisher: Elsevier BV
Date: 12-2006
Image analysis and rule-based reasoning for a traffic monitoring system
Publisher: IEEE
Date: 1999
Ethical thinking machines in surgery and the requirement for clinical leadership
Publisher: Elsevier BV
Date: 11-2020
Topic-Based Unsupervised and Supervised Dictionary Induction
Publisher: Association for Computing Machinery (ACM)
Date: 10-03-2023
DOI: 10.1145/3564698
Abstract: Word translation is a natural language processing task that provides translation between the words of a source and a target language. As a task, it reduces to the induction of a bilingual dictionary, which is typically performed by aligning word embeddings of the source language to word embeddings of the target language. To date, all the existing approaches have focused on performing a single, global alignment in word embedding space. However, semantic differences between the various languages, in addition to differences in the content of the corpora used for training the word embeddings, can hinder the effectiveness of such a global alignment. For this reason, in this article we propose conducting the alignment between the source and target embedding spaces by multiple mappings at topic level. The experimental results show that our approach has been able to achieve an average accuracy improvement of +3.30 percentage points over a state-of-the-art approach in unsupervised dictionary induction from languages as erse as German, French, Italian, Spanish, Finnish, Turkish, and Chinese to English, and +3.95 points average improvement in supervised dictionary induction.
A Temperature-Modified Dynamic Embedded Topic Model
Publisher: Springer Nature Singapore
Date: 2022
Fertility and survival of Swedish Red and White × Holstein crossbred cows and purebred Holstein cows
Publisher: American Dairy Science Association
Date: 04-2023
Inertial Sensor based Post Fall Analysis for False Alarming Reduction
Publisher: ACTAPRESS
Date: 2016
Track matching by major color histograms matching and post-matching integration
Publisher: Springer Berlin Heidelberg
Date: 2005
DOI: 10.1007/11553595_141
Automatic Classification of Abandoned Objects for Surveillance of Public Premises
Publisher: IEEE
Date: 2008
Block processing on multiprocessor DSPs for multimedia applications
Publisher: IEEE
Date: 1997
Efficient Video Object Classifier using Locality-Enhanced Support Vector Machines
Publisher: IEEE
Date: 2004
A real-time hardware implementation of the Hough transform
Publisher: Elsevier BV
Date: 1998
Fusing face and body gesture for machine recognition of emotions
Publisher: IEEE
Date: 2005
RewardsOfSum: Exploring Reinforcement Learning Rewards for Summarisation
Publisher: Association for Computational Linguistics
Date: 2021
A simulated annealing‐based maximum‐margin clustering algorithm
Publisher: Wiley
Date: 24-07-2019
DOI: 10.1111/COIN.12187
A multi-point distributed random variable accelerator for Monte Carlo simulation in finance
Publisher: IEEE
Date: 2005
DOI: 10.1109/ISDA.2005.11
DARPA benchmark image processing on SIMD parallel machines
Publisher: IEEE
Date: 1996
Hardware prefetching techniques for cache memories in multimedia applications
Publisher: IEEE Comput. Soc
Date: 2000
3D Object Recognition by VC-Graphs and Interactive Constraint Satisfaction
Publisher: IEEE Comput. Soc
Date: 1999
Sequential labeling with structural SVM under the F1 loss
Publisher: IEEE
Date: 10-2014
ReWE: Regressing Word Embeddings for Regularization of Neural Machine Translation Systems
Publisher: Association for Computational Linguistics
Date: 2019
DOI: 10.18653/V1/N19-1041
Big data meets multimedia analytics
Publisher: Elsevier BV
Date: 07-2016
Static Action Recognition by Efficient Greedy Inference
Publisher: IEEE
Date: 03-2016
Neural Topic Model Training with the REBAR Gradient Estimator
Publisher: Association for Computing Machinery (ACM)
Date: 30-09-2022
DOI: 10.1145/3517336
Abstract: Topic modelling is an important approach of unsupervised machine learning that allows automatically extracting the main “topics” from large collections of documents. In addition, topic modelling is able to identify the topic proportions of each in idual document, which can be helpful for organizing the collections. Many topic modelling algorithms have been proposed to date, including several that leverage advanced techniques such as variational inference and deep autoencoders. However, to date topic modelling has made limited use of reinforcement learning, a framework that has obtained vast success in many other unsupervised learning tasks. For this reason, in this article we propose training a neural topic model using a reinforcement learning objective and minimizing the objective with the recently-proposed REBAR gradient estimator. Experiments performed over two probing datasets have shown that the proposed model has achieved improvements over all the compared models in terms of both model perplexity and topic coherence, and produced topics that appear qualitatively informative and consistent.
Discriminative prototype selection methods for graph embedding
Publisher: Elsevier BV
Date: 06-2013
Learning for Feature Selection and Shape Detection
Publisher: No publisher found
Date: 1997
Exploiting image processing locality in cache pre-fetching
Publisher: IEEE Comput. Soc
Date: 1998
Detecting Objects, Shadows and Ghosts in Video Streams by Exploiting Color and Motion Information
Publisher: IEEE Comput. Soc
Date: 2001
Sequential labeling with structural SVM under an average precision loss
Publisher: Springer International Publishing
Date: 2016
A REINFORCEd Variational Autoencoder Topic Model
Publisher: Springer International Publishing
Date: 2021
The use of privacy-protected computer vision to measure the quality of healthcare worker hand hygiene
Publisher: Oxford University Press (OUP)
Date: 15-05-2019
Abstract: (i) To demonstrate the feasibility of automated, direct observation and collection of hand hygiene data, (ii) to develop computer visual methods capable of reporting compliance with moment 1 (the performance of hand hygiene before touching a patient) and (iii) to report the diagnostic accuracy of automated, direct observation of moment 1. Observation of simulated hand hygiene encounters between a healthcare worker and a patient. Computer laboratory in a university. Healthy volunteers. Sensitivity and specificity of automatic detection of the first moment of hand hygiene. We captured video and depth images using a Kinect camera and developed computer visual methods to automatically detect the use of alcohol-based hand rub (ABHR), rubbing together of hands and subsequent contact of the patient by the healthcare worker using depth imagery. We acquired images from 18 different simulated hand hygiene encounters where the healthcare worker complied with the first moment of hand hygiene, and 8 encounters where they did not. The diagnostic accuracy of determining that ABHR was dispensed and that the patient was touched was excellent (sensitivity 100%, specificity 100%). The diagnostic accuracy of determining that the hands were rubbed together after dispensing ABHR was good (sensitivity 83%, specificity 88%). We have demonstrated that it is possible to automate the direct observation of hand hygiene performance in a simulated clinical setting. We used cheap, widely available consumer technology and depth imagery which potentially increases clinical application and decreases privacy concerns.
Analysis of healthcare service utilization after transport-related injuries by a mixture of hidden Markov models
Publisher: Public Library of Science (PLoS)
Date: 08-11-2018
Automatic Human Action Recognition in Videos by Graph Embedding
Publisher: No publisher found
Date: 2011
NeuSub: A Neural Submodular Approach for Citation Recommendation
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 2021
From the Lab to the Real World: Affect Recognition Using Multiple Modalities
Publisher: I-Tech Education and Publishing
Date: 05-2008
DOI: 10.5772/6180
Background Subtraction techniques: a review
Publisher: IEEE
Date: 2004
Neighbor cache prefetching for multimedia image and video processing
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 08-2004
Local Depth Patterns for Tracking in Depth Videos
Publisher: ACM
Date: 13-10-2015
Tracking people across disjoint camera views by an illumination-tolerant appearance representation
Publisher: Springer Science and Business Media LLC
Date: 21-03-2007
Machine learning applications to clinical decision support in neurosurgery: an artificial intelligence augmented systematic review
Publisher: Springer Science and Business Media LLC
Date: 17-08-2019
DOI: 10.1007/S10143-019-01163-8
Abstract: Machine learning (ML) involves algorithms learning patterns in large, complex datasets to predict and classify. Algorithms include neural networks (NN), logistic regression (LR), and support vector machines (SVM). ML may generate substantial improvements in neurosurgery. This systematic review assessed the current state of neurosurgical ML applications and the performance of algorithms applied. Our systematic search strategy yielded 6866 results, 70 of which met inclusion criteria. Performance statistics analyzed included area under the receiver operating characteristics curve (AUC), accuracy, sensitivity, and specificity. Natural language processing (NLP) was used to model topics across the corpus and to identify keywords within surgical subspecialties. ML applications were heterogeneous. The densest cluster of studies focused on preoperative evaluation, planning, and outcome prediction in spine surgery. The main algorithms applied were NN, LR, and SVM. Input and output features varied widely and were listed to facilitate future research. The accuracy (F
Exploiting cache in multimedia
Publisher: IEEE Comput. Soc
Date: 1999
Towards simultaneous place classification and object detection based on conditional random field with multiple cues
Publisher: IEEE
Date: 11-2013
Complex event recognition by latent temporal models of concepts
Publisher: IEEE
Date: 10-2014
Traffic incident duration prediction via a deep learning framework for text description encoding
Publisher: arXiv
Date: 2022
Dissimilarity-based action recognition with the pair hidden Markov support vector machine
Publisher: IEEE
Date: 10-2017
Feature extraction techniques for abandoned object classification in video surveillance
Publisher: IEEE
Date: 2008
Correction: Analysis of healthcare service utilization after transport-related injuries by a mixture of hidden Markov models.
Publisher: Public Library of Science (PLoS)
Date: 04-2019
Minimum-Risk Structured Learning of Video Summarization
Publisher: IEEE
Date: 12-2017
DOI: 10.1109/ISM.2017.41
Local depth patterns for fine-grained activity recognition in depth videos
Publisher: IEEE
Date: 11-2016
Improving shadow suppression in moving object detection with HSV color information
Publisher: IEEE
Date: 2001
Video Surveillance at the Beginning of the Third Millennium: The Viewpoint of Research, Industry, Government Bodies, Research Funding Agencies and the Community
Publisher: IEEE
Date: 11-2006
Mean-Shift Background Image Modelling
Publisher: IEEE
Date: 2004
Regressing Word and Sentence Embeddings for Regularization of Neural Machine Translation
Publisher: arXiv
Date: 2019
Automatic visual recognition of face and body action units
Publisher: IEEE
Date: 2005
Taxonomy-augmented features for document clustering
Publisher: Springer Singapore
Date: 2019
Mixtures of Normalized Linear Projections
Publisher: Springer Berlin Heidelberg
Date: 2009
Affect Recognition from Face and Body: Early Fusion vs. Late Fusion
Publisher: IEEE
Date: 2005
BiLSTM-SSVM: Training the BiLSTM with a Structured Hinge Loss for Named-Entity Recognition
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 02-2022
Robust Density Modelling Using the Student's t-distribution for Human Action Recognition
Publisher: IEEE
Date: 09-2011
Regressing Word and Sentence Embeddings for Low-Resource Neural Machine Translation
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 06-2023
Machine learning applications to neuroimaging for glioma detection and classification: An artificial intelligence augmented systematic review.
Publisher: Elsevier BV
Date: 07-2021
Human-focused computer vision applications
Publisher: IEEE
Date: 2006
DOI: 10.1109/CGIV.2006.54
T3L: Translate-and-Test Transfer Learning for Cross-Lingual Text Classification
Publisher: MIT Press
Date: 2023
DOI: 10.1162/TACL_A_00593
Bi-modal emotion recognition from expressive face and body gestures
Publisher: Elsevier BV
Date: 11-2007
Recurrent neural networks with specialized word embeddings for health domain named-entity recognition
Publisher: Elsevier BV
Date: 12-2017
DOI: 10.1016/J.JBI.2017.11.007
Abstract: Previous state-of-the-art systems on Drug Name Recognition (DNR) and Clinical Concept Extraction (CCE) have focused on a combination of text "feature engineering" and conventional machine learning algorithms such as conditional random fields and support vector machines. However, developing good features is inherently heavily time-consuming. Conversely, more modern machine learning approaches such as recurrent neural networks (RNNs) have proved capable of automatically learning effective features from either random assignments or automated word "embeddings". (i) To create a highly accurate DNR and CCE system that avoids conventional, time-consuming feature engineering. (ii) To create richer, more specialized word embeddings by using health domain datasets such as MIMIC-III. (iii) To evaluate our systems over three contemporary datasets. Two deep learning methods, namely the Bidirectional LSTM and the Bidirectional LSTM-CRF, are evaluated. A CRF model is set as the baseline to compare the deep learning systems to a traditional machine learning approach. The same features are used for all the models. We have obtained the best results with the Bidirectional LSTM-CRF model, which has outperformed all previously proposed systems. The specialized embeddings have helped to cover unusual words in DrugBank and MedLine, but not in the i2b2/VA dataset. We present a state-of-the-art system for DNR and CCE. Automated word embeddings has allowed us to avoid costly feature engineering and achieve higher accuracy. Nevertheless, the embeddings need to be retrained over datasets that are adequate for the domain, in order to adequately cover the domain-specific vocabulary.
Maximum-likelihood dimensionality reduction in gaussian mixture models with an application to object classification
Publisher: IEEE
Date: 12-2008
Stochastic Boats Generated Acoustic Target Signal Detection in Time-Frequency Domain
Publisher: IEEE
Date: 2004
A hardware generator for multi-point distributed random variables
Publisher: IEEE
Date: 2005
From eager to lazy constrained data acquisition: A general framework
Publisher: Springer Science and Business Media LLC
Date: 12-2001
DOI: 10.1007/BF03037573
Traffic incident duration prediction via a deep learning framework for text description encoding
Publisher: IEEE
Date: 08-10-2022
Structural SVM with Partial Ranking for Activity Segmentation and Classification
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 12-2015
Data-type Dependent Cache Prefetching for MPEG Applications
Publisher: IEEE
Date: 2002
Real-Time Detection of Moving Vehicles
Publisher: IEEE Comput. Soc
Date: 1999
Human Action Recognition in Video by Fusion of Structural and Spatio-temporal Features
Publisher: No publisher found
Date: 2012
An online HDP-HMM for joint action segmentation and classification in motion capture data
Publisher: IEEE
Date: 06-2012
Fusing face and body display for bi-modal emotion recognition: single frame analysis and multi frame post integration
Publisher: Springer Berlin Heidelberg
Date: 2005
DOI: 10.1007/11573548_14
Face and Body Gesture Analysis for Multimodal HCI
Publisher: No publisher found
Date: 2004
A Multi-Document Coverage Reward for RELAXed Multi-Document Summarization
Publisher: arXiv
Date: 2022
Image analysis and rule-based reasoning for a traffic monitoring system
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 06-2000
DOI: 10.1109/6979.880969
Processing of variable size images on a cellular array: Performance analysis with the Abingdon Cross Benchmark
Publisher: IEEE Comput. Soc. Press
Date: 1993
Human Action Recognition in Video by Fusion of Structural and Spatio-temporal Features
Publisher: Springer Berlin Heidelberg
Date: 2012
Mitigating the effects of variable illumination for tracking across disjoint camera views
Publisher: IEEE
Date: 11-2006
DOI: 10.1109/AVSS.2006.76
AdOn HDP-HMM: An Adaptive Online Model for Segmentation and Classification of Sequential Data
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 09-2018
Comparison of Classifiers for Human Activity Recognition
Publisher: No publisher found
Date: 2007
Semi-supervised intelligent surveillance system for secure environments
Publisher: IEEE
Date: 07-2010
Creating and annotating affect databases from face and body display: a contemporary survey
Publisher: IEEE
Date: 10-2006
Training Initialization of Hidden Markov Models in Human Action Recognition
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 04-2014
Temporal analysis of cache prefetching strategies for multimedia applications
Publisher: IEEE
Date: 2001
A semi-supervised hidden Markov topic model based on prior knowledge
Publisher: Springer Singapore
Date: 2018
Joint Action Segmentation and Classification by an Extended Hidden Markov Model
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 12-2013
A Shared Attention Mechanism for Interpretation of Neural Automatic Post-Editing Systems
Publisher: Association for Computational Linguistics
Date: 2018
DOI: 10.18653/V1/W18-2702
Special issue on background modeling for foreground detection in real-world dynamic scenes
Publisher: Springer Science and Business Media LLC
Date: 15-11-2013
Related Organisations
Italian Ministry Of Education, Universities And Research (MIUR)
Location: Italy
Related Funding Activities
Discovery Projects - Grant ID: DP0452657
Start Date: 02-2004
End Date: 04-2008
Amount: $168,000.00
Funder: Australian Research Council
View Funded ActivityLinkage Infrastructure, Equipment And Facilities - Grant ID: LE190100080
Start Date: 2019
End Date: 12-2019
Amount: $726,921.00
Funder: Australian Research Council
View Funded ActivityDiscovery Projects - Grant ID: DP0987387
Start Date: 04-2009
End Date: 12-2011
Amount: $235,000.00
Funder: Australian Research Council
View Funded ActivityLinkage Projects - Grant ID: LP0668325
Start Date: 02-2006
End Date: 07-2009
Amount: $354,000.00
Funder: Australian Research Council
View Funded ActivityLinkage Infrastructure, Equipment And Facilities - Grant ID: LE110100023
Start Date: 2011
End Date: 12-2015
Amount: $500,000.00
Funder: Australian Research Council
View Funded ActivityLinkage Infrastructure, Equipment And Facilities - Grant ID: LE0668542
Start Date: 05-2006
End Date: 06-2009
Amount: $425,000.00
Funder: Australian Research Council
View Funded ActivityLinkage Infrastructure, Equipment And Facilities - Grant ID: LE100100235
Start Date: 2010
End Date: 12-2011
Amount: $280,000.00
Funder: Australian Research Council
View Funded ActivityLinkage Projects - Grant ID: LP0990135
Start Date: 07-2009
End Date: 12-2013
Amount: $2,400,000.00
Funder: Australian Research Council
View Funded Activity