liu.seSearch for publications in DiVA
Change search
Refine search result
123 1 - 50 of 119
CiteExportLink to result list
Permanent link
Cite
Citation style
  • apa
  • harvard1
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • oxford
  • Other style
More styles
Language
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Other locale
More languages
Output format
  • html
  • text
  • asciidoc
  • rtf
Rows per page
  • 5
  • 10
  • 20
  • 50
  • 100
  • 250
Sort
  • Standard (Relevance)
  • Author A-Ö
  • Author Ö-A
  • Title A-Ö
  • Title Ö-A
  • Publication type A-Ö
  • Publication type Ö-A
  • Issued (Oldest first)
  • Issued (Newest first)
  • Created (Oldest first)
  • Created (Newest first)
  • Last updated (Oldest first)
  • Last updated (Newest first)
  • Disputation date (earliest first)
  • Disputation date (latest first)
  • Standard (Relevance)
  • Author A-Ö
  • Author Ö-A
  • Title A-Ö
  • Title Ö-A
  • Publication type A-Ö
  • Publication type Ö-A
  • Issued (Oldest first)
  • Issued (Newest first)
  • Created (Oldest first)
  • Created (Newest first)
  • Last updated (Oldest first)
  • Last updated (Newest first)
  • Disputation date (earliest first)
  • Disputation date (latest first)
Select
The maximal number of hits you can export is 250. When you want to export more records please use the Create feeds function.
  • 1.
    Arganda-Carreras, Ignacio
    et al.
    Institute Jean Pierre Bourgin, France.
    Turaga, Srinivas C.
    Howard Hughes Medical Institute, VA USA.
    Berger, Daniel P.
    Harvard University, MA 02138 USA.
    Ciresan, Dan
    Scuola University of Profess Svizzera Italiana, Switzerland.
    Giusti, Alessandro
    Scuola University of Profess Svizzera Italiana, Switzerland.
    Gambardella, Luca M.
    Scuola University of Profess Svizzera Italiana, Switzerland.
    Schmidhuber, Juergen
    Scuola University of Profess Svizzera Italiana, Switzerland.
    Laptev, Dmitry
    ETH, Switzerland.
    Dwivedi, Sarvesh
    ETH, Switzerland.
    Buhmann, Joachim M.
    ETH, Switzerland.
    Liu, Ting
    University of Utah, UT USA.
    Seyedhosseini, Mojtaba
    University of Utah, UT USA.
    Tasdizen, Tolga
    University of Utah, UT USA.
    Kamentsky, Lee
    Broad Institute, MA USA.
    Burget, Radim
    Brno University of Technology, Czech Republic.
    Uher, Vaclav
    Brno University of Technology, Czech Republic.
    Tan, Xiao
    University of New S Wales, Australia.
    Sun, Changming
    CSIRO, Australia.
    Pham, Tuan
    Linköping University, Department of Biomedical Engineering. Linköping University, Faculty of Science & Engineering.
    Bas, Erhan
    Howard Hughes Medical Institute, VA USA.
    Uzunbas, Mustafa G.
    Rutgers State University, NJ 08903 USA.
    Cardona, Albert
    Howard Hughes Medical Institute, VA USA.
    Schindelin, Johannes
    University of Wisconsin, WI USA.
    Sebastian Seung, H.
    Princeton University, NJ 08544 USA; Princeton University, NJ 08544 USA.
    Crowdsourcing the creation of image segmentation algorithms for connectomics2015In: Frontiers in Neuroanatomy, ISSN 1662-5129, E-ISSN 1662-5129, Vol. 9, no 142Article in journal (Refereed)
    Abstract [en]

    To stimulate progress in automating the reconstruction of neural circuits, we organized the first international challenge on 2D segmentation of electron microscopic (EM) images of the brain. Participants submitted boundary maps predicted for a test set of images, and were scored based on their agreement with a consensus of human expert annotations. The winning team had no prior experience with EM images, and employed a convolutional network. This "deep learning" approach has since become accepted as a standard for segmentation of FM images. The challenge has continued to accept submissions, and the best so far has resulted from cooperation between two teams. The challenge has probably saturated, as algorithms cannot progress beyond limits set by ambiguities inherent in 2D scoring and the size of the test dataset. Retrospective evaluation of the challenge scoring system reveals that it was not sufficiently robust to variations in the widths of neurite borders. We propose a solution to this problem, which should be useful for a future 3D segmentation challenge.

  • 2.
    Beck, Dominik
    et al.
    Bioengineering and Bioinformatics Program, The Methodist Hospital Research Institute, Weill Cornell Medical College, USA//The University of New South Wales, Canberra, ACT, 2600, Australia..
    Ayers, Steve
    Department of Pathology, The Methodist Hospital and The Methodist.
    Wen, Jianguo
    The Methodist Hospital and The Methodist Hospital Research Institute, Weill Cornell Medical College, Houston, TX, USA.
    Brandl, Miriam B
    Bioengineering and Bioinformatics Program, The Methodist Hospital Research Institute, Weill Cornell Medical College, USA//The University of New South Wales, Canberra, ACT, 2600, Australia..
    Pham, Tuan D
    Bioengineering and Bioinformatics Program, The Methodist Hospital Research Institute, Weill Cornell Medical College.
    Webb, Paul
    The Methodist Hospital Research Institute and Department of Radiology, Weill Cornell Medical College, Houston, TX, 77030, USA..
    Chang, Chung-Che
    The Methodist Hospital and The Methodist Hospital Research Institute, Weill Cornell Medical College, Houston, TX, USA.
    Zhou, Xiaobo
    Bioengineering and Bioinformatics Program, The Methodist Hospital Research Institute, Weill Cornell Medical College, USA.
    Integrative analysis of next generation sequencing for small non-coding RNAs and transcriptional regulation in Myelodysplastic Syndromes2011In: BMC Medical Genomics, ISSN 1755-8794, E-ISSN 1755-8794, Vol. 4, no 19, p. 1-16Article in journal (Refereed)
    Abstract [en]

    Background

    Myelodysplastic Syndromes (MDSS) are pre-leukemic disorders with increasing incident rates worldwide, but very limited treatment options. Little is known about small regulatory RNAs and how they contribute to pathogenesis, progression and transcriptome changes in MDS.

    Methods

    Patients' primary marrow cells were screened for short RNAs (RNA-seq) using next generation sequencing. Exon arrays from the same cells were used to profile gene expression and additional measures on 98 patients obtained. Integrative bioinformatics algorithms were proposed, and pathway and ontology analysis performed.

    Results

    In low-grade MDS, observations implied extensive post-transcriptional regulation via microRNAs (miRNA) and the recently discovered Piwi interacting RNAs (piRNA). Large expression differences were found for MDS-associated and novel miRNAs, including 48 sequences matching to miRNA star (miRNA*) motifs. The detected species were predicted to regulate disease stage specific molecular functions and pathways, including apoptosis and response to DNA damage. In high-grade MDS, results suggested extensive post-translation editing via transfer RNAs (tRNAs), providing a potential link for reduced apoptosis, a hallmark for this disease stage. Bioinformatics analysis confirmed important regulatory roles for MDS linked miRNAs and TFs, and strengthened the biological significance of miRNA*. The "RNA polymerase II promoters" were identified as the tightest controlled biological function. We suggest their control by a miRNA dominated feedback loop, which might be linked to the dramatically different miRNA amounts seen between low and high-grade MDS.

    Discussion

    The presented results provide novel findings that build a basis of further investigations of diagnostic biomarkers, targeted therapies and studies on MDS pathogenesis.

  • 3.
    Brandl, Miriam B
    et al.
    School of Engineering and Information Technology, The University of New South Wales, Canberra, Australia .
    Beck, Dominik
    School of Engineering and Information Technology, The University of New South Wales, Canberra, Australia .
    Pham, Tuan D
    School of Engineering and Information Technology, The University of New South Wales, Canberra, Australia .
    Application of Fuzzy c-Means and Joint-Feature-Clustering to Detect Redundancies of Image-Features in Drug Combinations Studies of Breast Cancer2011Conference paper (Refereed)
    Abstract [en]

    The high dimensionality of image‐based dataset can be a drawback for classification accuracy. In this study, we propose the application of fuzzy c‐means clustering, cluster validity indices and the notation of a joint‐feature‐clustering matrix to find redundancies of image‐features. The introduced matrix indicates how frequently features are grouped in a mutual cluster. The resulting information can be used to find data‐derived feature prototypes with a common biological meaning, reduce data storage as well as computation times and improve the classification accuracy

  • 4.
    Cirillo, Marco Domenico
    et al.
    Linköping University, Department of Biomedical Engineering, Division of Biomedical Engineering. Linköping University, Faculty of Science & Engineering.
    Mirdell, Robin
    Linköping University, Department of Clinical and Experimental Medicine, Division of Surgery, Orthopedics and Oncology. Linköping University, Faculty of Medicine and Health Sciences. Region Östergötland, Anaesthetics, Operations and Specialty Surgery Center, Department of Hand and Plastic Surgery.
    Sjöberg, Folke
    Linköping University, Department of Clinical and Experimental Medicine, Division of Surgery, Orthopedics and Oncology. Linköping University, Faculty of Medicine and Health Sciences. Region Östergötland, Anaesthetics, Operations and Specialty Surgery Center, Department of Hand and Plastic Surgery.
    Pham, Tuan
    Linköping University, Department of Biomedical Engineering, Division of Biomedical Engineering. Linköping University, Faculty of Science & Engineering.
    Time-Independent Prediction of Burn Depth using Deep Convolutional Neural Networks2019In: Journal of Burn Care & Research, ISSN 1559-047X, E-ISSN 1559-0488Article in journal (Refereed)
    Abstract [en]

    We present in this paper the application of deep convolutional neural networks, which are a state-of-the-art artificial intelligence (AI) approach in machine learning, for automated time-independent prediction of burn depth. Colour images of four types of burn depth injured in first few days, including normal skin and background, acquired by a TiVi camera were trained and tested with four pre-trained deep convolutional neural networks: VGG-16, GoogleNet, ResNet-50, and ResNet-101. In the end, the best 10-fold cross-validation results obtained from ResNet- 101 with an average, minimum, and maximum accuracy are 81.66%, 72.06% and 88.06%, respectively; and the average accuracy, sensitivity and specificity for the four different types of burn depth are 90.54%, 74.35% and 94.25%, respectively. The accuracy was compared to the clinical diagnosis obtained after the wound had healed. Hence, application of AI is very promising for prediction of burn depth and therefore can be a useful tool to help in guiding clinical decision and initial treatment of burn wounds.

  • 5.
    Cirillo, Marco Domenico
    et al.
    Linköping University, Department of Biomedical Engineering, Division of Biomedical Engineering. Linköping University, Faculty of Science & Engineering.
    Mirdell, Robin
    Linköping University, Department of Clinical and Experimental Medicine, Division of Surgery, Orthopedics and Oncology. Linköping University, Faculty of Medicine and Health Sciences. Brännskadeavdelningen, Linköpings Universitetssjukhus.
    Sjöberg, Folke
    Linköping University, Department of Clinical and Experimental Medicine, Division of Surgery, Orthopedics and Oncology. Linköping University, Faculty of Medicine and Health Sciences. Region Östergötland, Anaesthetics, Operations and Specialty Surgery Center, Department of Hand and Plastic Surgery. Brännskadeavdelningen, Linköpings Universitetssjukhus.
    Pham, Tuan
    Linköping University, Department of Biomedical Engineering, Division of Biomedical Engineering. Linköping University, Faculty of Science & Engineering.
    Time-Independent Prediction of Burn Depth using Deep Convolutional Neural NetworksIn: Journal of Burn Care & Research, ISSN 1559-047X, E-ISSN 1559-0488Article in journal (Refereed)
    Abstract [en]

    We present in this paper the application of deep convolutional neural networks, which are a state-of-the-art artificial intelligence (AI) approach in machine learning, for automated time-independent prediction of burn depth. Colour images of four types of burn depth injured in first few days, including normal skin and background, acquired by a TiVi camera were trained and tested with four pre-trained deep convolutional neural networks: VGG-16, GoogleNet, ResNet-50, and ResNet-101. In the end, the best 10-fold cross-validation results obtained from ResNet- 101 with an average, minimum, and maximum accuracy are 81.66%, 72.06% and 88.06%, respectively; and the average accuracy, sensitivity and specificity for the four different types of burn depth are 90.54%, 74.35% and 94.25%, respectively. The accuracy was compared to the clinical diagnosis obtained after the wound had healed. Hence, application of AI is very promising for prediction of burn depth and therefore can be a useful tool to help in guiding clinical decision and initial treatment of burn wounds.

  • 6.
    Jin, Qiangguo
    et al.
    School of Computer Software, College of Intelligence and Computing, Tianjin University, Tianjin, China.
    Meng, Zhaopeng
    School of Computer Software, College of Intelligence and Computing, Tianjin University, Tianjin, China; Tianjin University of Traditional Chinese Medicine, Tianjin, China.
    Pham, Tuan
    Linköping University, Department of Biomedical Engineering, Division of Biomedical Engineering. Linköping University, Faculty of Science & Engineering.
    Chen, Qi
    School of Computer Software, College of Intelligence and Computing, Tianjin University, Tianjin, China.
    Wei, Leyi
    School of Computer Science and Technology, College of Intelligence and Computing, Tianjin University, Tianjin, China.
    Su, Ran
    School of Computer Software, College of Intelligence and Computing, Tianjin University, Tianjin, China.
    DUNet: A deformable network for retinal vessel segmentation2019In: Knowledge-Based Systems, ISSN 0950-7051, E-ISSN 1872-7409, Vol. 178, p. 149-162Article in journal (Refereed)
    Abstract [en]

    Automatic segmentation of retinal vessels in fundus images plays an important role in the diagnosis of some diseases such as diabetes and hypertension. In this paper, we propose Deformable U-Net (DUNet), which exploits the retinal vessels’ local features with a U-shape architecture, in an end to end manner for retinal vessel segmentation. Inspired by the recently introduced deformable convolutional networks, we integrate the deformable convolution into the proposed network. The DUNet, with upsampling operators to increase the output resolution, is designed to extract context information and enable precise localization by combining low-level features with high-level ones. Furthermore, DUNet captures the retinal vessels at various shapes and scales by adaptively adjusting the receptive fields according to vessels’ scales and shapes. Public datasets: DRIVE, STARE, CHASE_DB1 and HRF are used to test our models. Detailed comparisons between the proposed network and the deformable neural network, U-Net are provided in our study. Results show that more detailed vessels can be extracted by DUNet and it exhibits state-of-the-art performance for retinal vessel segmentation with a global accuracy of 0.9566/0.9641/0.9610/0.9651 and AUC of 0.9802/0.9832/0.9804/0.9831 on DRIVE, STARE, CHASE_DB1 and HRF respectively. Moreover, to show the generalization ability of the DUNet, we use another two retinal vessel data sets, i.e., WIDE and SYNTHE, to qualitatively and quantitatively analyze and compare with other methods. Extensive cross-training evaluations are used to further assess the extendibility of DUNet. The proposed method has the potential to be applied to the early diagnosis of diseases.

  • 7.
    Liu, Jin
    et al.
    School of Computer Science and Technology, China University of Mining and Technology, Xuzhou, Jiangshu, China; School of Engineering and Information Technology, The University of New South Wales, Canberra, Australia.
    Pham, Tuan D
    School of Engineering and Information Technology, The University of New South Wales, Canberra, Australia.
    A spatially constrained fuzzy hyper-prototype clustering algorithm2012In: Pattern Recognition, ISSN 0031-3203, E-ISSN 1873-5142, Vol. 45, no 4, p. 1759-1771Article in journal (Refereed)
    Abstract [en]

    We present in this paper a fuzzy clustering algorithm which can handle spatially constraint problems often encountered in pattern recognition. The proposed method is based on the notions of hyperplanes, the fuzzy c-means, and spatial constraints. By adding a spatial regularizer into the fuzzy hyperplane-based objective function, the proposed method can take into account additionally important information of inherently spatial data. Experimental results have demonstrated that the proposed algorithm achieves superior results to some other popular fuzzy clustering models, and has potential for cluster analysis in spatial domain.

  • 8.
    Liu, Jin
    et al.
    School of Engineering and Information Technology, University of New South Wales, Canberra, ACT, Australia.
    Pham, Tuan D
    School of Engineering and Information Technology, University of New South Wales, Canberra, ACT, Australia.
    FHC: The fuzzy hyper-prototype clustering algorithm2012In: Journal of Knowledge-based & Intelligent Engineering Systems, ISSN 1327-2314, E-ISSN 1875-8827, Vol. 16, no 1, p. 35-47Article in journal (Refereed)
    Abstract [en]

    We propose a fuzzy hyper-prototype clustering algorithm in this paper. This approach uses hyperplanes to represent the cluster centers in the fuzzy clustering. We present the formulation of fuzzy objective function and derive an iterative numerical algorithm for minimizing the objective function. Validations and comparisons are made between the proposed fuzzy clustering algorithm and existing fuzzy clustering methods on artificially generated data as well as on real world dataset include UCI dataset and gene expression dataset, the results show that the proposed method can give better performance in the above cases.

  • 9.
    Liu, Jin
    et al.
    School of Engineering and Information Technology, University of New South Wales, Canberra, Australia .
    Pham, Tuan D
    School of Engineering and Information Technology, University of New South Wales, Canberra, Australia.
    Fuzzy hyper-prototype clustering2010In: Knowledge-Based and Intelligent Information and Engineering Systems: 14th International Conference, KES 2010, Cardiff, UK, September 8-10, 2010, Proceedings, Part I / [ed] Rossitza Setchi; Ivan Jordanov; Robert J. Howlett; Lakhmi C. Jain, Springer Berlin/Heidelberg, 2010, p. 379-389Conference paper (Other academic)
    Abstract [en]

    We propose a fuzzy hyper-prototype algorithm in this paper. This approach uses hyperplanes to represent the cluster centers in the fuzzy c-means algorithm. We present the formulation of a hyperplane-based fuzzy objective function and then derive an iterative numerical procedure for minimizing the clustering criterion. We tested the method with data degraded with random noise. The experimental results show that the proposed method is robust to clustering noisy linear structure.

  • 10.
    Liu, Jin
    et al.
    School of Engineering and Information Technology, University of New South Wales, Canberra, ACT, 2600, Australia .
    Pham, Tuan D
    School of Engineering and Information Technology University of New South Wales Canberra, ACT 2600, Australia.
    Fuzzy hyper-prototype clustering2010In: Knowledge-Based and Intelligent Information and Engineering Systems: 14th International Conference, KES 2010, Cardiff, UK, September 8-10, 2010, Proceedings, Part I / [ed] Rossitza Setchi, Ivan Jordanov, Robert J. Howlett, Lakhmi C. Jain, Springer Berlin/Heidelberg, 2010, 6276, p. 379-389Chapter in book (Other academic)
    Abstract [en]

    We propose a fuzzy hyper-prototype algorithm in this paper. This approach uses hyperplanes to represent the cluster centers in the fuzzy c-means algorithm. We present the formulation of a hyperplanebased fuzzy objective function and then derive an iterative numerical procedure for minimizing the clustering criterion. We tested the method with data degraded with random noise. The experimental results show that the proposed method is robust to clustering noisy linear structure.

  • 11.
    Liu, Jin
    et al.
    School of Computer Science, China University of Mining and Technology, Xuzhou, Jiangsu, China.
    Pham, Tuan
    Linköping University, Department of Biomedical Engineering, Division of Biomedical Engineering. Linköping University, Faculty of Science & Engineering.
    Yan, Hong
    Department of Electronic Engineering, City University of Hong Kong, Kowloon, Hong Kong.
    Liang, Zhizhen
    School of Computer Science, China University of Mining and Technology, Xuzhou, Jiangsu, China.
    Fuzzy mixed-prototype clustering algorithm for microarray data analysis2018In: Neurocomputing, ISSN 0925-2312, E-ISSN 1872-8286, Vol. 276, p. 42-54Article in journal (Refereed)
    Abstract [en]

    Being motivated by combining the advantages of hyperplane-based pattern analysis and fuzzy clustering techniques, we present in this paper a fuzzy mix-prototype (FMP) clustering for microarray data analysis. By integrating spherical and hyper-planar cluster prototypes, the FMP is capable of capturing latent data models with both spherical and non-spherical geometric structures. Our contributions of the paper can be summarized into three folds: first, the objective function of the FMP is formulated. Second, an iterative solution which minimizes the objective function under given constraints is derived. Third, the effectiveness of the proposed FMP is demonstrated through experiments on yeast and leukemia data sets.

    The full text will be freely available from 2019-09-20 16:11
  • 12.
    Ng, Theam Foo
    et al.
    The University of New South Wales, Canberra, ACT 2600, Australia.
    Pham, Tuan D
    The University of New South Wales, Canberra, ACT 2600, Australia.
    Jia, Xiuping
    The University of New South Wales, Canberra, ACT 2600, Australia.
    Feature interaction in subspace clustering using the Choquet integral2012In: Pattern Recognition, ISSN 0031-3203, E-ISSN 1873-5142, Vol. 45, no 7, p. 2645-2660Article in journal (Refereed)
    Abstract [en]

    Subspace clustering has recently emerged as a popular approach to removing irrelevant and redundant features during the clustering process. However, most subspace clustering methods do not consider the interaction between the features. This unawareness limits the analysis performance in many pattern recognition problems. In this paper, we propose a novel subspace clustering technique by introducing the feature interaction using the concepts of fuzzy measures and the Choquet integral. This new framework of subspace clustering can provide optimal subsets of interacted features chosen for each cluster, and hence can improve clustering-based pattern recognition tasks. Various experimental results illustrate the effective performance of the proposed method.

  • 13.
    Ng, Theam Foo
    et al.
    School of Engineering and Information Technology, The University of New South Wales, Canberra, Australia; School of Electrical and Electronic Engineering, Universiti Sains Malaysia, Engineering Campus, Nibong Tebal, Penang, Malaysia.
    Pham, Tuan D
    Aizu Research Cluster for Medical Engineering and Informatics, Research Center for Advanced Information Science and Technology, The University of Aizu, Aizu-Wakamatsu, Fukushima, Japan.
    Jia, Xiuping
    School of Engineering and Information Technology, The University of New South Wales, Canberra, Australia.
    Fraser, Donald
    School of Engineering and Information Technology, The University of New South Wales, Canberra, Australia.
    Fuzzy Knowledge-Based Subspace Clustering for Life Science Data Analysis2013In: Knowledge-Based Systems in Biomedicine and Computational Life Science / [ed] Tuan D. Pham and Lakhmi C. Jain, Springer Berlin/Heidelberg, 2013, p. 177-213Chapter in book (Other academic)
    Abstract [en]

    Features or attributes play an important role when handling multi-dimensional datasets. Generally, not all the features are needed to find several groups of similar objects in traditional clustering methods because some of the features may not be relevant and also redundant. Hence, the concept of identifying subsets of the features that are relevant to clusters is introduced, instead of using the full set of features. This chapter discusses the use of the prior knowledge of the importance of features and their interaction in constructing both fuzzy measures and signed fuzzy measures for subspace clustering. The Choquet integral, which is known as a useful aggregation operator with respect to fuzzy measure, is used to aggregate the importance and interaction of the features. The concept of fuzzy knowledge-based subspace clustering is applied especially to the analysis of life science data in this chapter.

  • 14.
    Ng, Theam Foo
    et al.
    The University of New South Wales, ADFA, Canberra, Australia.
    Pham, Tuan D
    The University of New South Wales, ADFA, Canberra, Australia.
    Sun, Changming
    CSIRO Mathematics, Informatics and Statistics, Locked Bag 17, N. Ryde, Australia.
    Automated feature weighting in fuzzy declustering-based vector quantization2010Conference paper (Refereed)
    Abstract [en]

    Feature weighting plays an important role in improving the performance of clustering technique. We propose an automated feature weighting in fuzzy declustering-based vector quantization (FDVQ), namely AFDVQ algorithm, for enhancing effectiveness and efficiency in classification. The proposed AFDVQ imposes weights on the modified fuzzy c-means (FCM) so that it can automatically calculate feature weights based on their degrees of importance rather than treating them equally. Moreover, the extension of FDVQ and AFDVQ algorithms based on generalized improved fuzzy partitions (GIFP), known as GIFP-FDVQ and GIFP-AFDVQ respectively, are proposed. The experimental results on real data (original and noisy data) and modified data (biased and noisy-biased data) have demonstrated that the proposed algorithms outperformed standard algorithms in classifying clusters especially for biased data.

  • 15.
    Ng, Theam Foo
    et al.
    School of Engineering and Information Technology, The University of New South Wales, ADFA, Canberra, ACT 2600, Australia .
    Pham, Tuan D
    School of Engineering and Information Technology, The University of New South Wales, ADFA, Canberra, ACT 2600, Australia.
    Zhou, Xiaobo
    Center for Biotechnology and Informatics, The Methodist Hospital Research Institute, Weill Cornell Medical College, Houston, TX 77030, USA .
    Justification of Fuzzy Declustering Vector Quantization Modeling in Classification of Genotype-Image Phenotypes2010Conference paper (Refereed)
    Abstract [en]

    With the fast development of multi‐dimensional data compression and pattern classification techniques, vector quantization (VQ) has become a system that allows large reduction of data storage and computational effort. One of the most recent VQ techniques that handle the poor estimation of vector centroids due to biased data from undersampling is to use fuzzy declustering‐based vector quantization (FDVQ) technique. Therefore, in this paper, we are motivated to propose a justification of FDVQ based hidden Markov model (HMM) for investigating its effectiveness and efficiency in classification of genotype‐image phenotypes. The performance evaluation and comparison of the recognition accuracy between a proposed FDVQ based HMM (FDVQ‐HMM) and a well‐known LBG (Linde, Buzo, Gray) vector quantization based HMM (LBG‐HMM) will be carried out. The experimental results show that the performances of both FDVQ‐HMM and LBG‐HMM are almost similar. Finally, we have justified the competitiveness of FDVQ‐HMM in classification of cellular phenotype image database by using hypotheses t‐test. As a result, we have validated that the FDVQ algorithm is a robust and an efficient classification technique in the application of RNAi genome‐wide screening image data.

  • 16.
    Pham, Tuan
    Linköping University, Department of Biomedical Engineering, Division of Biomedical Engineering. Linköping University, Faculty of Science & Engineering.
    Complementary features for radiomic analysis of malignant and benign mediastinal lymph nodes2017Conference paper (Refereed)
  • 17.
    Pham, Tuan
    Linköping University, Department of Biomedical Engineering, Division of Biomedical Engineering. Linköping University, Faculty of Science & Engineering. Linköping University, Center for Medical Image Science and Visualization (CMIV).
    Deep learning of p73 biomarker expression in rectal cancer patients2019Conference paper (Refereed)
  • 18.
    Pham, Tuan
    Linköping University, Department of Biomedical Engineering, Medical Informatics. Linköping University, Faculty of Science & Engineering.
    Enhancing texture characteristics with synthesis and noise for image retrieval2016In: IEEE 8th International Conference on Intelligent Systems (IS), 2016, IEEE, 2016, p. 433-437Conference paper (Refereed)
    Abstract [en]

    Texture images of limited size can be insufficient for statistical learning to perform the task of image retrieval. This paper proposes a hypothesis that the utilization of synthesized texture and noise addition can improve texture analysis with spatial statistics. Rationales for this hypothesis are that texture synthesis allows the enlargement of an image size for better description of its spatial statistics, and noise added to texture pixels at some levels enhances discriminative power of texture randomness. The improvements using synthesized images of coarse-aperiodic and fine-periodic texture categories with added noise for feature extraction with the semi-variogram and feature-vector matching using the log-likelihood ratio suggest the validation of the proposed hypothesis that is promising for handling classification of texture of small sample sizes.

  • 19.
    Pham, Tuan
    Linköping University, Department of Biomedical Engineering, Medical Informatics. Linköping University, Faculty of Science & Engineering.
    Fuzzy recurrence plots2016In: Europhysics letters, ISSN 0295-5075, E-ISSN 1286-4854, Vol. 116, p. p1-p5, article id 50008Article in journal (Other academic)
    Abstract [en]

    Recurrence plots display binary texture of time series from dynamical systems with single dots and line structures. Using fuzzy recurrence plots, recurrences of the phase-space states can be visualized as grayscale texture, which is more informative for pattern analysis. The proposed method replaces the crucial similarity threshold required by symmetrical recurrence plots with the number of cluster centers, where the estimate of the latter parameter is less critical than the estimate of the former.

  • 20.
    Pham, Tuan
    Linköping University, Department of Biomedical Engineering, Division of Biomedical Engineering. Linköping University, Faculty of Science & Engineering.
    Fuzzy Weighted Recurrence Networks of Time Series2018In: Physica A: Statistical Mechanics and its Applications, ISSN 0378-4371Article in journal (Refereed)
  • 21.
    Pham, Tuan
    Linköping University, Center for Medical Image Science and Visualization (CMIV). Linköping University, Department of Biomedical Engineering, Division of Biomedical Engineering. Linköping University, Faculty of Science & Engineering.
    Geostatistical Simulation of Medical Images for Data Augmentation in Deep Learning2019In: IEEE Access, E-ISSN 2169-3536, Vol. 7, p. 68752-68763Article in journal (Refereed)
    Abstract [en]

    Data augmentation, which is the process for creating alternative copies of each sample in a small training data set, is important for extracting deep-learning features for medical image classification problems. However, data augmentation has not been well explored and existing methods are heuristic. In this paper, a geostatistical simulation of images is introduced as a data augmentation approach for extracting deep-learning features from medical images that are characterized with texture. The stochastic simulation procedure is to generate realizations of an image by modeling its spatial variability through the generation of multiple equiprobable stochastic realizations. The approach employed for the geostatistical simulation is based on the concepts of regionalized variables and kriging formulation to create multiple textural variations of medical images. Experimental results on classifying two medical-image data sets show that the use of geostatistical simulation for extracting deep-learning features with several popular pre-trained deep-learning models (AlexNet, ResNet-50, and GoogLeNet/Inception) provided better accuracy rates and more balanced results in terms of sensitivity and specificity than either with or without the implementation of conventional data augmentation. The proposed approach can be applied to other pre-trained networks as well as those without data pre-training for effective deep-feature extraction from medical images. The proposed application of the theory of geostatistics for medical image data augmentation in deep learning is original. The novelty of this approach can also be applied to many other types of data that are inherently textural. Geostatistical simulation opens a new door to the development of state-of-the-art artificial intelligence in feature extraction of medical images.

  • 22.
    Pham, Tuan
    Linköping University, Department of Biomedical Engineering, Division of Biomedical Engineering. Linköping University, Faculty of Science & Engineering.
    Nonlinear dynamics analysis of short-time photoplethysmogram in Parkinson's disease2018Conference paper (Refereed)
  • 23.
    Pham, Tuan
    Linköping University, Department of Biomedical Engineering, Division of Biomedical Engineering. Linköping University, Faculty of Science & Engineering.
    Pattern analysis and classification of blood oxygen saturation signals with nonlinear dynamics features2018Conference paper (Refereed)
    Abstract [en]

    Pattern analysis of blood oxygen saturation is important for gaining insights into the cardiorespiratory control system, real-time monitoring during operations, identifying potential predictors for the diagnosis of disease severity, and improving the hospitalization of patients with critical chronic diseases. This paper investigates the use of nonlinear dynamics features for machine learning and classification of blood oxygen saturation signals in healthy young and healthy old subjects. The validation of the feature reliability for the signal variability analysis has a clinical implication for differentiating blood oxygen saturation in patients with respect to the particular influence of aging, when patient's data become available.

  • 24.
    Pham, Tuan
    Linköping University, Department of Biomedical Engineering, Division of Biomedical Engineering. Linköping University, Faculty of Science & Engineering.
    Pattern analysis of computer keystroke time series in healthy control and early-stage Parkinson's disease subjects using fuzzy recurrence and scalable recurrence network features2018In: Journal of Neuroscience Methods, ISSN 0165-0270, E-ISSN 1872-678X, Vol. 307, p. 128-130Article in journal (Refereed)
    Abstract [en]

    A noncommutative algebra corresponding to the classical catenoid is introduced together with a differential calculus of derivations. We prove that there exists a unique metric and torsion-free connection that is compatible with the complex structure, and the curvature is explicitly calculated. A noncommutative analogue of the fact that the catenoid is a minimal surface is studied by constructing a Laplace operator from the connection and showing that the embedding coordinates are harmonic. Furthermore, an integral is defined and the total curvature is computed. Finally, classes of left and right modules are introduced together with constant curvature connections, and bimodule compatibility conditions are discussed in detail.

    The full text will be freely available from 2019-11-30 14:48
  • 25.
    Pham, Tuan
    Linköping University, Department of Biomedical Engineering, Division of Biomedical Engineering. Linköping University, Faculty of Science & Engineering.
    Quantification of white matter lesions on brain MRI with 2D fuzzy weighted recurrence networks2019Conference paper (Refereed)
    Abstract [en]

    White matter lesions detected on magnetic resonance imaging scans of the brain have been hypothesized to have associations with the causes of several diseases. Accurate quantification of white matter lesions is important for the hypothesis validation. However, the clinical quantification is highly variable due to subjective opinions of different raters and is likely to compromise the reliability of the assessment. This paper introduces a new method of two-dimensional fuzzy weighted recurrence networks that can numerically express the quantity of white matter lesions. The results illustrate the promising application of the proposed method that offers as a useful computational tool in brain research.

  • 26.
    Pham, Tuan
    Linköping University, Department of Biomedical Engineering. Linköping University, Faculty of Science & Engineering.
    Quantifying visual perception of texture with fuzzy metric entropy2016In: Journal of Intelligent & Fuzzy Systems, ISSN 1064-1246, E-ISSN 1875-8967, Vol. 31, no 2, p. 1089-1097Article in journal (Refereed)
    Abstract [en]

    The quantitative categorization of textures according to their visual appearances is an important area of research in computer vision and image understanding, because texture analysis and its applications are found useful in many areas of health, medicine, sciences, and engineering. For the first time, the theory of chaos and fuzzy sets are applied in this paper to measure the spatial dynamics of the texture spectrum. Experiments carried out on the well-known Brodatz texture database suggest the promising application of the method proposed for texture quantification.

  • 27.
    Pham, Tuan
    Linköping University, Department of Biomedical Engineering, Division of Biomedical Engineering. Linköping University, Faculty of Science & Engineering. Linkoping University.
    Scaling of texture in training autoencoders for classification of histological images of colorectal cancer2017In: Advances in Neural Networks: 14th International Symposium on Neural Networks (ISNN 2017 / [ed] F. Cong et al., Springer, 2017, p. 524-532Chapter in book (Refereed)
  • 28.
    Pham, Tuan
    Linköping University, Department of Biomedical Engineering, Division of Biomedical Engineering. Linköping University, Faculty of Science & Engineering.
    Tensor decomposition of non-EEG physiological signals for visualization and recognition of human stress2019Conference paper (Refereed)
  • 29.
    Pham, Tuan
    Linköping University, Department of Biomedical Engineering. Linköping University, Faculty of Science & Engineering.
    The Kolmogorov-Sinai entropy in the setting of fuzzy sets for image texture analysis and classification2016In: Pattern Recognition, ISSN 0031-3203, E-ISSN 1873-5142, Vol. 53, p. 229-237Article in journal (Refereed)
    Abstract [en]

    The Kolmogorov–Sinai (K–S) entropy is used to quantify the average amount of uncertainty of a dynamical system through a sequence of observations. Sequence probabilities therefore play a central role for the computation of the entropy rate to determine if the dynamical system under study is deterministically non-chaotic, deterministically chaotic, or random. This paper extends the notion of the K–S entropy to measure the entropy rate of imprecise systems using sequence membership grades, in which the underlying deterministic paradigm is replaced with the degree of fuzziness. While constructing sequential probabilities for the calculation of the K–S entropy is difficult in practice, the estimate of the K–S entropy in the setting of fuzzy sets in an image is feasible and can be useful for modeling uncertainty of pixel distributions in images. The fuzzy K–S entropy is illustrated as an effective feature for image analysis and texture classification.

  • 30.
    Pham, Tuan
    Linköping University, Department of Biomedical Engineering, Division of Biomedical Engineering. Linköping University, Faculty of Science & Engineering. Linkoping University.
    Time-shift multiscale entropy analysis of physiological signals2017In: Entropy, ISSN 1099-4300, E-ISSN 1099-4300, Vol. 19, no 6, article id 257Article in journal (Refereed)
    Abstract [en]

    Measures of predictability in physiological signals using entropy measures have been widely applied in many areas of research. Multiscale entropy expresses different levels of either approximate entropy or sample entropy by means of multiple factors for generating multiple time series, enabling the capture of more useful information than using a scalar value produced by the two entropy methods. This paper presents the use of different time shifts on various intervals of time series to discover different entropy patterns of the time series. Examples and experimental results using white noise, 1/ f noise, photoplethysmography, and electromyography signals suggest the validity and better performance of the proposed time-shift multiscale entropy analysis of physiological signals than the multiscale entropy.

  • 31.
    Pham, Tuan
    et al.
    Linköping University, Department of Biomedical Engineering. Linköping University, Faculty of Science & Engineering.
    Abe, Taishi
    University of Aizu, Japan.
    Oka, Ryuichi
    University of Aizu, Japan.
    Chen, Yung-Fu
    Central Taiwan University of Science and Technology, Taiwan; China Medical University, Taiwan.
    Measures of Morphological Complexity of Gray Matter on Magnetic Resonance Imaging for Control Age Grouping2015In: Entropy, ISSN 1099-4300, E-ISSN 1099-4300, Vol. 17, no 12, p. 8130-8151Article in journal (Refereed)
    Abstract [en]

    Current brain-age prediction methods using magnetic resonance imaging (MRI) attempt to estimate the physiological brain age via some kind of machine learning of chronological brain age data to perform the classification task. Such a predictive approach imposes greater risk of either over-estimate or under-estimate, mainly due to limited training data. A new conceptual framework for more reliable MRI-based brain-age prediction is by systematic brain-age grouping via the implementation of the phylogenetic tree reconstruction and measures of information complexity. Experimental results carried out on a public MRI database suggest the feasibility of the proposed concept.

  • 32.
    Pham, Tuan D
    School of Engineering and Information Technology, University of New South Wales, Canberra, Australia.
    Brain lesion detection in MRI with fuzzy and geostatistical models2010Conference paper (Refereed)
    Abstract [en]

    Automated image detection of white matter changes of the brain is essentially helpful in providing a quantitative measure for studying the association of white matter lesions with other types of biomedical data. Such study allows the possibility of several medical hypothesis validations which lead to therapeutic treatment and prevention. This paper presents a new clustering-based segmentation approach for detecting white matter changes in magnetic resonance imaging with particular reference to cognitive decline in the elderly. The proposed method is formulated using the principles of fuzzy c-means algorithm and geostatistics.

  • 33.
    Pham, Tuan D
    Bioinformatics Applications Research Centre; and the School of Mathematics, Physics and Information Technology, James Cook University, Australia.
    Cancer classification by minimizing fuzzy scattering effect2008Conference paper (Refereed)
    Abstract [en]

    Proteomic technology has been found promising for classifying complex diseases that leads to early prediction. However, for effective classification, the extraction of good features that can represent the identities of different classes plays the frontal critical factor for any classification problems. In addition, another major problem associated with pattern recognition is how to effectively handle a large feature space. This paper addresses these two frontal issues for mass spectrometry (MS) classification. We apply the theory of linear predictive coding to extract features and fuzzy vector quantization to reduce the large feature space of MS data. The minimization of the fuzzy scattering matrix in the setting of the fuzzy c-means algorithm provides better grouping for feature classification. The proposed methodology was tested using two MS-based cancer datasets and the results are promising.

  • 34.
    Pham, Tuan D
    Aizu Research Cluster for Medical Engineering and Informatics Center for Advanced Information Science and Technology, The University of Aizu, Aizu-Wakamatsu 965-8580, Fukushima, Japan.
    ’Current Informatics and Technology in Biology and Medicine’2015In: Computers in Biology and Medicine, ISSN 0010-4825, E-ISSN 1879-0534, Vol. 68, p. 28-Article in journal (Other academic)
  • 35.
    Pham, Tuan D
    Aizu Research Cluster for Medical Engineering and Informatics Center for Advanced Information Science and Technology The University of Aizu, Aizuwakamatsu, Fukushima 965-8580, Japan.
    Detecting mitochondria in intracellular images with nonstationary indicator kriging2014Conference paper (Refereed)
    Abstract [en]

    The mitochondrion is a membrane-bound organelle found in most eukaryotic cells. Mitochondria are considered as the powerhouse of the cell because they function as the platform for generating the production of chemical energy. The visual information of mitochondria revealed by the recent advanced technology in nanoimaging opens doors to life-science researchers to gain insights into its spatial structure and its spatial distribution within the cell. In order to simulate and model mitochondria using a large amount of images, the first task in image processing is the automated detection of this organelle. This paper introduces a nonstationary indicator kriging model, which can model the spatial uncertainty in an image, for feature extraction. This feature can be effectively applied for the detection of mitochondria.

  • 36.
    Pham, Tuan D
    Aizu Research Cluster for Medical Engineering and Informatics, Research Center for Advanced Information Science and Technology, The University of Aizu, Aizuwakamatsu, Japan.
    Dynamic-Time-Warping Analysis of Feature-Vector Reliability for Cognitive Stimulation Therapy Assessment2015In: Information Science and Applications / [ed] Kuinam J. Kim, Springer Berlin/Heidelberg, 2015, p. 235-241Chapter in book (Other academic)
    Abstract [en]

    Cognitive stimulation therapy (CST) can help people with mental illness improve their health condition. In particular, CST provides an alternative treatment for people with mild to moderate dementia. Signal processing and pattern recognition methods are promising tools for automated assessment of the effectiveness of CST in treating individuals with dementia. This paper applies the dynamic time-warping for investigating the reliability of photoplethysmography-derived features extracted by the largest Lyapunov exponents and spectral distortion for CST evaluation.

  • 37.
    Pham, Tuan D
    Aizu Research Cluster for Medical Engineering and Informatics, Center for Advanced Information Science and Technology, The University of Aizu, Aizuwakamatsu, Japan.
    Estimating Parameters of Optimal Average and Adaptive Wiener Filters for Image Restoration with Sequential Gaussian Simulation2015In: IEEE Signal Processing Letters, ISSN 1070-9908, E-ISSN 1558-2361, Vol. 22, no 11, p. 1950-1954Article in journal (Refereed)
    Abstract [en]

    Filtering additive white Gaussian noise in images using the best linear unbiased estimator (BLUE) is technically sound in a sense that it is an optimal average filter derived from the statistical estimation theory. The BLUE filter mask has the theoretical advantage in that its shape and its size are formulated in terms of the image signals and associated noise components. However, like many other noise filtering problems, prior knowledge about the additive noise needs to be available, which is often obtained using training data. This paper presents the sequential Gaussian simulation in geostatistics for measuring signal and noise variances in images without the need of training data for the BLUE filter implementation. The simulated signal variance and the BLUE average can be further used as parameters of the adaptive Wiener filter for image restoration.

  • 38.
    Pham, Tuan D
    James Cook University, Bioinformatics Applications Research Centre, Information Technology Discipline, School of Mathematics, Physics, and Information Technology, Townsville, Australia.
    Fractal characteristics of mass spectrometry based cancer data2007In: WSEAS Transactions on Mathematics, ISSN 1109-2769, E-ISSN 2224-2880, p. 30-35Article in journal (Refereed)
    Abstract [en]

    This paper addresses the fractal analysis of mass spectrometry data for the prediction of complex diseases. We studied ovarian and prostate cancers as examples of the analysis. Experimental results show that the fractal dimensions of cancer states distinctively tend to have higher values than those of the control states. High values of the Hurst exponent of the mass spectrometry data under study suggest the persistent behavior of the datasets and the reliability of the fractal dimensions.

  • 39.
    Pham, Tuan D
    School of Engineering and Information Technology, University of New South Wales, Canberra, Australia.
    Fuzzy posterior-probabilistic fusion2011In: Pattern Recognition, ISSN 0031-3203, E-ISSN 1873-5142, Vol. 44, no 5, p. 1023-1030Article in journal (Refereed)
    Abstract [en]

    The paradigm of the permanence of updating ratios, which is a well-proven concept in experimental engineering approximation, has recently been utilized to construct a probabilistic fusion approach for combining knowledge from multiple sources. This ratio-based probabilistic fusion, however, assumes the equal contribution of attributes of diverse evidences. This paper introduces a new framework of a fuzzy probabilistic data fusion using the principles of the permanence of ratios paradigm, and the theories of fuzzy measures and fuzzy integrals. The fuzzy sub-fusion of the proposed approach allows an effective model for incorporating evidence importance and interaction.

  • 40.
    Pham, Tuan D
    School of Engineering and Information Technology, The University of New South Wales, Canberra, ACT 2600, Australia.
    GeoEntropy: A measure of complexity and similarity2010In: Pattern Recognition, ISSN 0031-3203, E-ISSN 1873-5142, Vol. 43, no 3, p. 887-896Article in journal (Refereed)
    Abstract [en]

    Measuring the complexity of a pattern expressed either in time or space has been introduced to quantify the information content of the pattern, which can then be applied for classification. Such information measures are particularly useful for the understanding of systems complexity in many fields of sciences, business and engineering. The novel concept of geostatistical entropy (GeoEntropy) as a measure of pattern complexity and similarity is addressed in this paper. It has been experimentally shown that GeoEntropy is an effective algorithm for studying signal predictability and has superior capability of classifying complex bio-patterns.

  • 41.
    Pham, Tuan D
    Department of Electrical Engineering, University of Sydney, Sydney NSW 2006, Australia;.
    Grade Estimation Using Fuzzy-Set Algorithms1997In: MATHEMATICAL GEOLOGY, ISSN 1874-8961, Vol. 29, no 2, p. 291-305Article in journal (Refereed)
    Abstract [en]

    This paper presents a new approach for estimating unknown ore grades within a mining deposit in a fuzzy environment using fuzzy c-means clustering and a fuzzy inference system. Based on a collection of cluster centers obtained from fuzzy c-means, a fuzzy rule base and fuzzy search domains are established to compute grades at these cluster centers. These cluter center-grade pairs act as control information in the fuzzy space-grade system in order to infer unknown grades on the basis of fuzzy interpolation, fuzzy extrapolation, and a defuzzification process of fuzzy control.

  • 42.
    Pham, Tuan D
    Aizu Research Cluster for Medical Engineering and Informatics Research Center for Advanced Information Science and Technology.
    Image texture analysis using geostatistical information entropy2012In: Intelligent Systems (IS), 2012 6th IEEE International Conference, 2012, p. 353-356Conference paper (Refereed)
    Abstract [en]

    Extraction of effective features of objects is an important area of research in the intelligent processing of image data. A well-known feature in images is texture which can be used for image description, segmentation and classification. This paper presents a novel texture extraction method using the principles of geostatistics and the concept of entropy in information theory. Experimental results on medical image data have shown the superior performance of the proposed approach over some popular texture extraction methods.

  • 43.
    Pham, Tuan D
    Aizu Research Cluster for Medical Engineering and Informatics, Research Center for Advanced Information Science and Technology, The University of Aizu Aizu-Wakamatsu, Fukushima, Japan.
    Image texture analysis using geostatistical information entropy2012In: Intelligent Systems (IS), 2012 6th IEEE International Conference, IEEE , 2012, p. 353-356Conference paper (Refereed)
    Abstract [en]

    Extraction of effective features of objects is an important area of research in the intelligent processing of image data. A well-known feature in images is texture which can be used for image description, segmentation and classification. This paper presents a novel texture extraction method using the principles of geostatistics and the concept of entropy in information theory. Experimental results on medical image data have shown the superior performance of the proposed approach over some popular texture extraction methods.

  • 44.
    Pham, Tuan D
    Bioinformatics Applications Research Center, James Cook University School of Information Technology Townsville, QLD 4811, Australia.
    Integration of fuzzy and geostatistical models for estimating missing multivariate observations.2005In: WSEAS Transactions on Systems, ISSN 1991-8763, Vol. 4, no 4, p. 233-237Article in journal (Refereed)
    Abstract [en]

    The estimation of missing observations is an important research field which has practical applications in many science and engineering disciplines. In analyzing the variability of a particular data set which can be spatially related, classical statistical methods make no use of this type of information; whereas geostatistics accomodates the spatial information of the data set in its regression analysis for estimating missing observations or unknown data. This paper incorporates the modeling of fuzzy protoptyes in the cokriging system of geostatistics in order to improve the accuracy of the estimates and alleviate the computational complexity of cokriging.

  • 45.
    Pham, Tuan D
    Bioinfonnatics Applications Research Centre/School of Mathematics, Physics, and Infonnation Technology James Cook University Townsville, AUSTRALIA.
    Matching and fusing signal-estimation errors for similarity-based pattern classification2007In: WSEAS Transactions on Systems, ISSN 1109-2777, Vol. 6, no 1, p. 125-132Article in journal (Refereed)
    Abstract [en]

    Error estimation using different optimal models for signal processing has been an active research field in data analysis such as speech recognition, image analysis, geophysics, and earth science. A popular direction of research in pattern classification is to develop computational models for comparing objects being either abstract or physical based on some measure of similarity or dissimilarity. This paper explores some linear-prediction models for deriving signal estimation errors and their fusion for similarity-based pattern classification.

  • 46.
    Pham, Tuan D
    School of Engineering and Information Technology, University of New South Wales, Canberra, ACT, Australia.
    Medical image restoration using multiple-point geostatistics2010In: 2010 3rd International Conference on Biomedical Engineering and Informatics (BMEI 2010): Volume 1, IEEE , 2010, p. 371-374Conference paper (Other academic)
    Abstract [en]

    Noise inherently exists in medical and biological images as any imaging device, by a finite exposure time, is subject to stochastic noise from the random arrival events of photons. The purpose of image restoration is to bring back as much as possible the original image from its degraded state. This paper presents a spatial multiple-point statistical approach for restoration of medical image degradation.

  • 47.
    Pham, Tuan D
    Aizu Research Cluster for Medical Engineering and Informatics Center for Advanced Information Science and Technology The University of Aizu Aizu-Wakamatsu, Fukushima 965-8580, Japan.
    Modeling spatial uncertainty of imprecise information in images.2014Conference paper (Refereed)
    Abstract [en]

    The description of information content in images is imprecise in nature. Quantification of uncertainty in images for pattern analysis has been addressed with the theories of probability and fuzzy sets. In this paper, an approach for modeling the spatial uncertainty of images is proposed in the setting of geostatistics and probability measure of fuzzy events. The proposed approach can be utilized to extract an effective feature for image classification.

  • 48.
    Pham, Tuan D
    James Cook Univ., Townsville .
    Predictive Modeling in Proteomics-based Disease Detection2007Conference paper (Refereed)
    Abstract [en]

    Recent advent of mass-spectrometry data generated by proteomic technology provides a new type of biological information which is very promising in the search for diagnostic and therapeutic approaches that enables the early detection of fatal diseases and the development of personalized medicine. Successful analysis of such high-throughput proteomic data relies much on signal-processing and pattern-recognition techniques. This paper addresses the application of prediction models for cancer detection using mass spectral data.

  • 49.
    Pham, Tuan D
    School of Computer Science and Engineering, Research Center for Advanced Information Science and Technology, The University of Aizu, Tsuruga, Ikki-machi, Aizu-Wakamatsu City, Japan.
    Regularity dimension of sequences and its application to phylogenetic tree reconstruction2012In: Chaos, Solitons & Fractals, ISSN 0960-0779, E-ISSN 1873-2887, Vol. 45, no 6, p. 879-887Article in journal (Refereed)
    Abstract [en]

    The concept of dimension is a central development of chaos theory for studying nonlinear dynamical systems. Different types of dimensions have been derived to interpret different geometrical or physical observations. Approximate entropy and its modified methods have been introduced for studying regularity and complexity of time-series data in physiology and biology. Here, the concept of power laws and entropy measure are adopted to develop the regularity dimension of sequences to model a mathematical relationship between the frequency with which information about signal regularity changes in various scales. The proposed regularity dimension is applied to reconstruct phylogenetic trees using mitochondrial DNA (mtDNA) sequences for the family Hominidae, which can be validated according to the hypothesized evolutionary relationships between organisms.

  • 50.
    Pham, Tuan D
    Bioinformatics Applications Research Centre / School of Information Technology, James Cook University, Townsville, Australia.
    Similarity searching in DNA sequences by spectral distortion measures2006In: Advances in Data Mining. Applications in Medicine, Web Mining, Marketing, Image and Signal Mining: 6th Industrial Conference on Data Mining, ICDM 2006, Leipzig, Germany, July 14-15, 2006. Proceedings / [ed] Petra Perner, Springer Berlin/Heidelberg, 2006, p. 24-37Chapter in book (Refereed)
    Abstract [en]

    Searching for similarity among biological sequences is an important research area of bioinformatics because it can provide insight into the evolutionary and genetic relationships between species that open doors to new scientific discoveries such as drug design and treament. In this paper, we introduce a novel measure of similarity between two biological sequences without the need of alignment. The method is based on the concept of spectral distortion measures developed for signal processing. The proposed method was tested using a set of six DNA sequences taken from Escherichia coli K-12 and Shigella flexneri, and one random sequence. It was further tested with a complex dataset of 40 DNA sequences taken from the GenBank sequence database. The results obtained from the proposed method are found superior to some existing methods for similarity measure of DNA sequences.

123 1 - 50 of 119
CiteExportLink to result list
Permanent link
Cite
Citation style
  • apa
  • harvard1
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • oxford
  • Other style
More styles
Language
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Other locale
More languages
Output format
  • html
  • text
  • asciidoc
  • rtf