Dian Tjondronegoro

Griffith University

Author Statistics

Papers

Citation

H-Index

i-10 index

Research Trends

Author Order

Document Type

Co-Authors

Vinod Chandran

Vel Tech Rangarajan Dr. Sagunthala R&D Institute of Science and Technology

Ligang Zhang

Zhejiang Water Conservancy and Hydropower Survey and Design Institute

Wei Song

Shanghai Ocean University

David J. Kavanagh

University of Queensland

Leanne Hides

University of Queensland

Zachary Fitz-Walter

Queensland University of Technology

Yi‐Ping Phoebe Chen

La Trobe University

Stoyan Stoyanov

Queensland University of Technology

Binh Pham

Ho Chi Minh City University of Science

Oksana Zelenko

Volodymyr Dahl East Ukrainian National University

Cooperative Institutions

Queensland University of Technology

123

University of Queensland

Griffith University

University of Melbourne

University of Sydney

Queensland Children’s Hospital

UNSW Sydney

Children’s Health Queensland Hospital and Health Service

Chinese University of Hong Kong

Royal Brisbane and Women's Hospital

Author Statistics

Papers

Citation

H-Index

i-10 index

Research Field

Detecting gesture force peaks for intuitive interaction

Zachary Fitz-Walter Samuel A. Jones Dian Tjondronegoro

With the release of the Nintendo Wii in 2006, the use of haptic force gestures has become a very popular form of input for interactive entertainment. However, current gesture recognition techniques utilised in Nintendo Wii games fall prey to a lack of control when it comes to recognising simple gestures. This paper presents a simple gesture recognition technique called Peak Testing which gives greater control over gesture interaction. This recognition technique locates force peaks in continuous force data (provided by a gesture device such as the Wiimote) and then cancels any peaks which are not meant for input. Peak Testing is therefore technically able to identify movements in any direction. This paper applies this recognition technique to control virtual instruments and investigates how users respond to this interaction. The technique is then explored as the basis for a robust way to navigate menus with a simple flick of the wrist. We propose that this flick-form of interaction could be a very intuitive way to navigate Nintendo Wii menus instead of the current pointer techniques implemented.

Interaction technique

10.1145/1514402.1514404

Cite

Citations (38)

The Potential of High-Performance Workplaces for Boosting Worker Productivity, Health, and Creativity: A Comparison between Well and Non-Well Certified Environments

Samin Marzban Christhina Cândido Behnaz Avazpour Martin Mackey Fan Zhang

Although there is abundance of research on Indoor Environmental Quality (IEQ) in offices, aspects beyond IEQ that can affect occupants’ satisfaction and performance are not well understood. Additionally, rapid adaptation of certification schemes and scarcity of evidence in evaluating if the workplaces with these schemes outperform other workplaces necessitate research in this area. In this study, a total of 1403 Post-Occupancy Evaluation surveys from 14 open-plan offices (10 WELL-certified and 4 uncertified) in Australia, New Zealand and Hong Kong were analyzed. Key drivers of productivity, creativity, and health were investigated. Satisfaction with visual privacy and access to the outdoor environment emerged as key predictors for productivity, and layout and interior design was the main predictor for creativity. Organizational aspects were the key drivers for mental health; privacy and IEQ for physical health; and privacy and connection to the outdoor environment for overall health. The five offices that achieved the highest satisfaction in layout and interior design, IEQ, privacy and connection to the outdoor environment, and organizational aspects were all WELL certified, so a comparison was conducted between WELL and non-WELL offices. Satisfaction with the physical configuration of the space and organizational aspects were generally higher in WELL-certified offices. There were no significant differences in health between WELL and non-WELL offices, however less Sick Building Syndrome (SBS) complaints and musculoskeletal discomfort were less reported in WELL offices. More than 20% of respondents were dissatisfied with the physical environment regardless of being WELL or non-WELL certified.

Boosting

10.2139/ssrn.4456874

Cite

Citations (0)

Ensemble Methods for Classification of Physical Activities from Wrist Accelerometry

Medicine & Science in Sports & Exercise (2017)

Alok Kumar Chowdhury Dian Tjondronegoro Vinod Chandran Stewart G. Trost

To investigate whether the use of ensemble learning algorithms improve physical activity recognition accuracy compared to the single classifier algorithms, and to compare the classification accuracy achieved by three conventional ensemble machine learning methods (bagging, boosting, random forest) and a custom ensemble model comprising four algorithms commonly used for activity recognition (binary decision tree, k nearest neighbor, support vector machine, and neural network).The study used three independent data sets that included wrist-worn accelerometer data. For each data set, a four-step classification framework consisting of data preprocessing, feature extraction, normalization and feature selection, and classifier training and testing was implemented. For the custom ensemble, decisions from the single classifiers were aggregated using three decision fusion methods: weighted majority vote, naïve Bayes combination, and behavior knowledge space combination. Classifiers were cross-validated using leave-one subject out cross-validation and compared on the basis of average F1 scores.In all three data sets, ensemble learning methods consistently outperformed the individual classifiers. Among the conventional ensemble methods, random forest models provided consistently high activity recognition; however, the custom ensemble model using weighted majority voting demonstrated the highest classification accuracy in two of the three data sets.Combining multiple individual classifiers using conventional or custom ensemble learning methods can improve activity recognition accuracy from wrist-worn accelerometer data.

Ensemble Learning

Majority Rule

Boosting

Statistical classification

10.1249/mss.0000000000001291

Cite

Citations (83)

Towards robust automatic affective classification of images using facial expressions for practical applications

Multimedia Tools and Applications (2015)

Ligang Zhang Dian Tjondronegoro Vinod Chandran Jana Eggink

Semantic gap

10.1007/s11042-015-2497-5

Cite

Citations (21)

Highlights for more complete sports video summarization

IEEE Multimedia (2004)

Dian Tjondronegoro Yi‐Ping Phoebe Chen Binh Pham

Summarization is an essential requirement for achieving a more compact and interesting representation of sports video contents. We propose a framework that integrates highlights into play segments and reveal why we should still retain breaks. Experimental results show that fast detections of whistle sounds, crowd excitement, and text boxes can complement existing techniques for play-breaks and highlights localization.

Complement

Representation

10.1109/mmul.2004.28

Cite

Citations (79)

Microblog Retrieval Using Topical Features and Query Expansion.

Text REtrieval Conference (2011)

Cher Han Lau Yuefeng Li Dian Tjondronegoro

Retrieving information from Twitter is always challenging given its volume, inconsistent writing and noise. Existing systems focus on term-based approach, but important topical features such as person, proper noun and events are often neglected, leading to less satisfactory results while searching information from tweets. This paper propose a novelty feature extraction algorithm which targets the above problems, and present the experiment results using TREC11 dataset. The proposed approach considers both term-based and patternbased features and distribute weights accordingly. We experiment four different setting to evaluate different combinations and results show that our approach outperformed traditional method of using term-based or pattern only methods and signify the importance of topical features in microblog retrieval.

Microblogging

Feature (linguistics)

Source

Cite

Citations (34)

Centroid Training to achieve effective text classification

Libiao Zhang Yuefeng Li Yue Xu Dian Tjondronegoro Chao Sun

Traditional text classification technology based on machine learning and data mining techniques has made a big progress. However, it is still a big problem on how to draw an exact decision boundary between relevant and irrelevant objects in binary classification due to much uncertainty produced in the process of the traditional algorithms. The proposed model CTTC (Centroid Training for Text Classification) aims to build an uncertainty boundary to absorb as many indeterminate objects as possible so as to elevate the certainty of the relevant and irrelevant groups through the centroid clustering and training process. The clustering starts from the two training subsets labelled as relevant or irrelevant respectively to create two principal centroid vectors by which all the training samples are further separated into three groups: POS, NEG and BND, with all the indeterminate objects absorbed into the uncertain decision boundary BND. Two pairs of centroid vectors are proposed to be trained and optimized through the subsequent iterative multi-learning process, all of which are proposed to collaboratively help predict the polarities of the incoming objects thereafter. For the assessment of the proposed model, F ₁ and Accuracy have been chosen as the key evaluation measures. We stress the F ₁ measure because it can display the overall performance improvement of the final classifier better than Accuracy. A large number of experiments have been completed using the proposed model on the Reuters Corpus Volume 1 (RCV1) which is important standard dataset in the field. The experiment results show that the proposed model has significantly improved the binary text classification performance in both F ₁ and Accuracy compared with three other influential baseline models.

Centroid

10.1109/dsaa.2014.7058104

Cite

Citations (8)

Towards Generic Modelling of Viewer Interest Using Facial Expression and Heart Rate Features

IEEE Access (2018)

Prithwi Raj Chakraborty Dian Tjondronegoro Ligang Zhang Vinod Chandran

Automatic detection of viewer interest while watching video contents can enable multimedia applications, such as online video streaming, to recommend contents in real time. However, there is yet a generic model for detecting viewer interest that is independent of subject and content while using noninvasive sensors in near-natural settings. This paper is the first attempt at solving this issue by investigating the feasibility of a generic model for detecting viewer interest based on facial expression and heart rate features. The proposed model adopts deep learning features, which are trained and tested using multisubjects' data across different video stimuli domains. The experimental results show that the generic model can reach a similar accuracy to a domain-specific model.

Expression (computer science)

Region of interest

Facial expression recognition

10.1109/access.2018.2874892

Cite

Citations (4)

A Rapid Scene Depth Estimation Model Based on Underwater Light Attenuation Prior for Underwater Image Restoration

Lecture notes in computer science (2018)

Wei Song Yan Wang Dongmei Huang Dian Tjondronegoro

Depth map

10.1007/978-3-030-00776-8_62

Cite

Citations (241)

Face Recognition across Pose on Video Using Eigen Light-Fields

Moh Edi Wibowo Dian Tjondronegoro

We propose an approach to employ eigen light-fields for face recognition across pose on video. Faces of a subject are collected from video frames and combined based on the pose to obtain a set of probe light-fields. These probe data are then projected to the principal subspace of the eigen light-fields within which the classification takes place. We modify the original light-field projection and found that it is more robust in the proposed system. Evaluation on VidTIMIT dataset has demonstrated that the eigen light-fields method is able to take advantage of multiple observations contained in the video.

Light Field

Structured Light

10.1109/dicta.2011.96

Cite

Citations (3)