ORCID Profile
0000-0003-1507-9682
Current Organisation
Queensland University of Technology
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.
Publisher: IEEE
Date: 12-2019
Publisher: Springer Berlin Heidelberg
Date: 2003
Publisher: Hindawi Limited
Date: 13-10-2019
DOI: 10.1155/2019/3679839
Abstract: Solving diagonally dominant tridiagonal linear systems is a common problem in scientific high-performance computing (HPC). Furthermore, it is becoming more commonplace for HPC platforms to utilise a heterogeneous combination of computing devices. Whilst it is desirable to design faster implementations of parallel linear system solvers, power consumption concerns are increasing in priority. This work presents the oclspkt routine. The oclspkt routine is a heterogeneous OpenCL implementation of the truncated SPIKE algorithm that can use FPGAs, GPUs, and CPUs to concurrently accelerate the solving of diagonally dominant tridiagonal linear systems. The routine is designed to solve tridiagonal systems of any size and can dynamically allocate optimised workloads to each accelerator in a heterogeneous environment depending on the accelerator’s compute performance. The truncated SPIKE FPGA solver is developed first for optimising OpenCL device kernel performance, global memory bandwidth, and interleaved host to device memory transactions. The FPGA OpenCL kernel code is then refactored and optimised to best exploit the underlying architecture of the CPU and GPU. An optimised TDMA OpenCL kernel is also developed to act as a serial baseline performance comparison for the parallel truncated SPIKE kernel since no FPGA tridiagonal solver capable of solving large tridiagonal systems was available at the time of development. The in idual GPU, CPU, and FPGA solvers of the oclspkt routine are 110%, 150%, and 170% faster, respectively, than comparable device-optimised third-party solvers and applicable baselines. Assessing heterogeneous combinations of compute devices, the GPU + FPGA combination is found to have the best compute performance and the FPGA-only configuration is found to have the best overall estimated energy efficiency.
Publisher: IEEE
Date: 12-2019
Publisher: Springer Science and Business Media LLC
Date: 06-06-2015
DOI: 10.1007/S11136-015-1025-4
Abstract: To evaluate the reliability, agreement and smallest detectable change in a measurement instrument for pain and function in knee osteoarthritis the Dynamic weight-bearing Assessment of Pain (DAP). The s le size was set to 20 persons, recruited from the outpatient osteoarthritis clinic at Frederiksberg Hospital, Copenhagen. Two physiotherapists tested all participants during two visits at the first visit, one single DAP (including four scores) was conducted by rater one at the second visit, DAP was conducted by both raters one and two in randomized order with concealed allocation. The time interval was approximately 1.5 h. Measurement error was estimated by standard error of measurement (SEM). The intra- and inter-rater reliability was estimated by Intra-class Correlation Coefficients for agreement based on a two-way ANOVA with random effects (single measures ICC 2.1). Smallest detectable change (SDC) and limits of agreement were calculated. The pain score showed excellent reliability in terms of ICC (intra-rater 0.93, CI 0.83-0.97, inter-rater 0.91, CI 0.78-0.96), low SEM (intra-rater 0.70, inter-rater 0.86, on a scale from 0 to 10), and acceptable SDC for intra-rater test (1.95). The three knee bend scores all had ICC above 0.50, showing fair-to-good reliability. None of the knee bend scores showed acceptable SEM and SDC. The reproducibility of the DAP pain score meets the demands for use in clinical practice and research. The total knee bend could be useful for motivational purpose in clinical use. Testing of other psychometric properties of the DAP is pending.
Publisher: Elsevier BV
Date: 09-2022
Publisher: Springer Science and Business Media LLC
Date: 04-11-2021
Publisher: IEEE
Date: 11-2021
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 2021
Publisher: Australian Mathematical Publishing Association, Inc.
Date: 26-03-2014
Publisher: Springer Science and Business Media LLC
Date: 22-01-2020
DOI: 10.1186/S13638-020-1644-5
Abstract: In this paper, we present and evaluate a novel multilevel hybrid-chaotic oscillator. The proposed generalized multilevel-hybrid chaotic oscillator (GM-HCO) was created by combining a multilevel discrete function generated from user data with a continuous function having a d ing factor greater than l n (2) to achieve variable rates and adaptive carrier frequencies. Improved spectral efficiency and lower complexity of the transceiver compared with differentially coherent systems were achieved by multilevel signals at the transmitter and a matched filter at the receiver. An exact analytical solution for the generalized fixed basis function and the impulse response of the matched filter were also derived. The bit error rate (BER) expression of the GM-HCO was derived for two levels. It was found that the noise performance of the proposed system was better than a hybrid chaotic system based on forward time and differential chaos shift keying (DCSK). A comprehensive set of simulations were carried out to evaluate the performance of the proposed system with chaotic communication systems in the presence of additive white Gaussian noise (AWGN). The performance of the proposed system was comparable with that of conventional communication systems. The results demonstrate that the proposed system can offer better noise performance than existing chaotic communication systems, and it also offers variable transmitter frequencies and improved spectral efficiency. Noise-like behavior of the chaotic signals provides an additional layer of security at the physical layer compared with conventional (sinusoidal) communication systems.
Publisher: MDPI AG
Date: 15-02-2023
DOI: 10.3390/S23042195
Abstract: There exists a growing interest from the clinical practice research communities in the development of methods to automate HEp-2 stained cells classification procedure from histopathological images. Challenges faced by these methods include variations in cell densities and cell patterns, overfitting of features, large-scale data volume and stained cells. In this paper, a multi-class multilayer perceptron technique is adapted by adding a new hidden layer to calculate the variation in the mean, scale, kurtosis and skewness of higher order spectra features of the cell shape information. The adapted technique is then jointly trained and the probability of classification calculated using a Softmax activation function. This method is proposed to address overfitting, stained and large-scale data volume problems, and classify HEp-2 staining cells into six classes. An extensive experimental analysis is studied to verify the results of the proposed method. The technique has been trained and tested on the dataset from ICPR-2014 and ICPR-2016 competitions using the Task-1. The experimental results have shown that the proposed model achieved higher accuracy of 90.3% (with data augmentation) than of 87.5% (with no data augmentation). In addition, the proposed framework is compared with existing methods, as well as, the results of methods using in ICPR2014 and ICPR2016 competitions.The results demonstrate that our proposed method effectively outperforms recent methods.
Publisher: IEEE
Date: 28-05-2021
Publisher: Pensoft Publishers
Date: 28-05-2023
DOI: 10.3897/JUCS.96293
Abstract: Abstract: To identify autoimmune diseases in humans, analysis of HEp-2 staining patterns at cell level is the gold standard for clinical practice research communities. An automated procedure is a complicated task due to variations in cell densities, sizes, shapes and patterns, overfitting of features, large-scale data volume, stained cells and poor quality of images. Several machine learning methods that analyse and classify HEp-2 cell microscope images currently exist. However, accuracy is still not at the level required for medical applications and computer aided diagnosis due to those challenges. The purpose of this work to automate classification procedure of HEp-2 stained cells from microscopic images and improve the accuracy of computer aided diagnosis. This work proposes Deep Convolutional Neural Networks (DCNNs) technique to classify HEp-2 cell patterns at cell level into six classes based on employing the level-set method via edge detection technique to segment HEp-2 cell shape. The DCNNs are designed to identify cell-shape and fundamental distance features related with HEp-2 cell types. This paper is investigated the effectiveness of our proposed method over benchmarked dataset. The result shows that the proposed method is highly superior comparing with other methods in benchmarked dataset and state-of-the-art methods. The result demonstrates that the proposed method has an excellent adaptability across variations in cell densities, sizes, shapes and patterns, overfitting features, large-scale data volume, and stained cells under different lab environments. The accurate classification of HEp-2 staining pattern at cell level helps increasing the accuracy of computer aided diagnosis for diagnosis process in the future.
Publisher: MDPI AG
Date: 30-09-2023
DOI: 10.3390/APP131910874
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 2020
Publisher: MDPI AG
Date: 21-07-2023
DOI: 10.3390/S23146591
Abstract: The fingerprint is a widely adopted biometric trait in forensic and civil applications. Fingerprint biometric systems have been investigated using contact prints and latent and contactless images which range from low to high resolution. While the imaging techniques are advancing with sensor variations, the input fingerprint images also vary. A general fingerprint recognition pipeline consists of a sensor module to acquire images, followed by feature representation, matching and decision modules. In the sensor module, the image quality of the biometric traits significantly affects the biometric system’s accuracy and performance. Imaging modality, such as contact and contactless, plays a key role in poor image quality, and therefore, paying attention to imaging modality is important to obtain better performance. Further, underlying physical principles and the working of the sensor can lead to their own forms of distortions during acquisition. There are certain challenges in each module of the fingerprint recognition pipeline, particularly sensors, image acquisition and feature representation. Present reviews in fingerprint systems only analyze the imaging techniques in fingerprint sensing that have existed for a decade. However, the latest emerging trends and recent advances in fingerprint sensing, image acquisition and their challenges have been left behind. Since the present reviews are either obsolete or restricted to a particular subset of the fingerprint systems, this work comprehensively analyzes the state of the art in the field of contact-based, contactless 2D and 3D fingerprint systems and their challenges in the aspects of sensors, image acquisition and interoperability. It outlines the open issues and challenges encountered in fingerprint systems, such as fingerprint performance, environmental factors, acceptability and interoperability, and alternate directions are proposed for a better fingerprint system.
Publisher: Elsevier BV
Date: 2020
DOI: 10.1016/J.COMPBIOMED.2019.103568
Abstract: The segmentation of white blood cells and their nuclei is still difficult and challenging for many reasons, including the differences in their colour, shape, background and staining techniques, the overlapping of cells, and changing cell topologies. This paper shows how these challenges can be addressed by using level set forces via edge-based geometric active contours. In this work, three level set forces-based (curvature, normal direction, and vector field) are comprehensively studied in the context of the problem of segmenting white blood cell nuclei based on geometric flows. Cell images are first pre-processed, using contrast stretching and morphological opening and closing in order to standardise the image colour intensity, to create an initial estimate of the cell foreground and to remove the narrow links between lobes and cell bulges. Next, segmentation is conducted to prune out the white blood cell nucleus region from the cell wall and cytoplasm by combining the theory of curve evolution using curvature, normal direction, and vector field-based level set forces and edge-based geometric active contours. The overall performance of the proposed segmentation method is compared and benchmarked against existing techniques for nucleus shape detection, using the same databases. The three level set forces studied here (curvature, normal direction, and vector field) via edge-based geometric active contours achieve F-index values of 92.09%, 91.13%, and 90.76%, respectively, and the proposed segmentation method results in better performance than all other techniques for all indices, including Jaccard distance, boundary displacement error, and Rand index.
Location: Germany
No related grants have been discovered for Jasmine Banks.