ORCID Profile
0000-0001-6870-5056
Current Organisations
Charles Sturt University - Bathurst Campus
,
Charles Sturt University
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.
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.
Image Processing | Artificial Intelligence and Image Processing | Signal Processing | Coding and Information Theory
Radio and Television Broadcasting | Application Software Packages (excl. Computer Games) | Film and Video Services (excl. Animation and Computer Generated Imagery) |
Publisher: IEEE
Date: 04-2015
DOI: 10.1109/DCC.2015.43
Publisher: IEEE
Date: 2010
Publisher: IEEE
Date: 23-05-2022
Publisher: Inderscience Publishers
Date: 2015
Publisher: IEEE
Date: 05-2010
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 2019
Publisher: IEEE
Date: 11-2021
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 10-2014
Publisher: IEEE
Date: 10-2008
Publisher: Springer Berlin Heidelberg
Date: 2004
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 06-2019
Publisher: IEEE
Date: 11-2015
Publisher: Inderscience Publishers
Date: 2022
Publisher: IEEE
Date: 11-2015
Publisher: IEEE
Date: 04-06-2023
Publisher: Elsevier BV
Date: 07-2017
Publisher: Elsevier BV
Date: 05-2019
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 2023
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 2022
Publisher: IEEE
Date: 11-2017
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 05-2023
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 09-2011
Publisher: Elsevier BV
Date: 11-2019
Publisher: Elsevier BV
Date: 09-2017
Publisher: IEEE
Date: 09-2010
Publisher: MDPI AG
Date: 15-10-2021
DOI: 10.3390/S21206856
Abstract: Video analytics and computer vision applications face challenges when using video sequences with low visibility. The visibility of a video sequence is degraded when the sequence is affected by atmospheric interference like rain. Many approaches have been proposed to remove rain streaks from video sequences. Some approaches are based on physical features, and some are based on data-driven (i.e., deep-learning) models. Although the physical features-based approaches have better rain interpretability, the challenges are extracting the appropriate features and fusing them for meaningful rain removal, as the rain streaks and moving objects have dynamic physical characteristics and are difficult to distinguish. Additionally, the outcome of the data-driven models mostly depends on variations relating to the training dataset. It is difficult to include datasets with all possible variations in model training. This paper addresses both issues and proposes a novel hybrid technique where we extract novel physical features and data-driven features and then combine them to create an effective rain-streak removal strategy. The performance of the proposed algorithm has been tested in comparison to several relevant and contemporary methods using benchmark datasets. The experimental result shows that the proposed method outperforms the other methods in terms of subjective, objective, and object detection comparisons for both synthetic and real rain scenarios by removing rain streaks and retaining the moving objects more effectively.
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 2022
Publisher: IEEE
Date: 09-2018
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 2021
Publisher: IEEE
Date: 07-2017
Publisher: American Dairy Science Association
Date: 07-2014
Publisher: Elsevier BV
Date: 2016
Publisher: MDPI AG
Date: 16-03-2023
DOI: 10.3390/S23063181
Abstract: Soil colour is one of the most important factors in agriculture for monitoring soil health and determining its properties. For this purpose, Munsell soil colour charts are widely used by archaeologists, scientists, and farmers. The process of determining soil colour from the chart is subjective and error-prone. In this study, we used popular smartphones to capture soil colours from images in the Munsell Soil Colour Book (MSCB) to determine the colour digitally. These captured soil colours are then compared with the true colour determined using a commonly used sensor (Nix Pro-2). We have observed that there are colour reading discrepancies between smartphone and Nix Pro-provided readings. To address this issue, we investigated different colour models and finally introduced a colour-intensity relationship between the images captured by Nix Pro and smartphones by exploring different distance functions. Thus, the aim of this study is to determine the Munsell soil colour accurately from the MSCB by adjusting the pixel intensity of the smartphone-captured images. Without any adjustment when the accuracy of in idual Munsell soil colour determination is only 9% for the top 5 predictions, the accuracy of the proposed method is 74%, which is significant.
Publisher: Springer International Publishing
Date: 2021
Publisher: IEEE
Date: 11-2016
Publisher: Science Publications
Date: 11-2019
Publisher: IEEE
Date: 11-2016
Publisher: IEEE
Date: 07-2016
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 2022
Publisher: EJournal Publishing
Date: 2015
Publisher: IEEE
Date: 11-2017
Publisher: Springer Science and Business Media LLC
Date: 31-01-2013
Publisher: IGI Global
Date: 2009
DOI: 10.4018/978-1-59904-887-1.CH026
Abstract: People’s demands are escalating with technology advances. Now, people are not happy with only text or voice messages, they like to see video as well. Video transmission through limited bandwidth, for ex le, an existing telephone line, requires an efficient video coding technique. Unfortunately, existing video coding standards have some limitations due to this demand. Recently, a pattern-based video coding technique has established its potentiality to improve the coding compared to the recent standard H.264 in the range of low bit rates. This chapter describes this technique with its background, features, recent developments, and future trends.
Publisher: Springer Science and Business Media LLC
Date: 14-03-2022
DOI: 10.1038/S41598-022-08075-6
Abstract: In recent years, the nuclear power plant has received huge attention as it generates vast amounts of power at a lower cost. However, its creation of radioactive wastes is a major environmental concern. Therefore, the nuclear power plant requires a reliable and uninterrupted monitoring system as an essential part of it. Monitoring a nuclear power plant using wireless sensor networks is a convenient and popular practice now. This paper proposes a hybrid approach for monitoring wireless sensor networks in the context of a nuclear power plant in Bangladesh. Our hybrid approach enhances the lifespan of wireless sensor networks reducing power consumption and offering better connectivity of sensors. To do so, it uses both the topology maintenance and topology construction algorithms. We found that the HGETRecRot topology maintenance algorithm enhances the network lifetime compared to other algorithms. This algorithm increases the communication and sensing coverage area but decreases the network performance. We also propose a prediction model, based on linear regression algorithm, that predicts the best combination of topology maintenance and topology construction algorithms.
Publisher: IEEE
Date: 12-2018
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 06-2005
Publisher: MDPI AG
Date: 07-10-2021
DOI: 10.3390/S21196655
Abstract: Lung cancer is the leading cause of cancer death and morbidity worldwide. Many studies have shown machine learning models to be effective in detecting lung nodules from chest X-ray images. However, these techniques have yet to be embraced by the medical community due to several practical, ethical, and regulatory constraints stemming from the “black-box” nature of deep learning models. Additionally, most lung nodules visible on chest X-rays are benign therefore, the narrow task of computer vision-based lung nodule detection cannot be equated to automated lung cancer detection. Addressing both concerns, this study introduces a novel hybrid deep learning and decision tree-based computer vision model, which presents lung cancer malignancy predictions as interpretable decision trees. The deep learning component of this process is trained using a large publicly available dataset on pathological biomarkers associated with lung cancer. These models are then used to inference biomarker scores for chest X-ray images from two independent data sets, for which malignancy metadata is available. Next, multi-variate predictive models were mined by fitting shallow decision trees to the malignancy stratified datasets and interrogating a range of metrics to determine the best model. The best decision tree model achieved sensitivity and specificity of 86.7% and 80.0%, respectively, with a positive predictive value of 92.9%. Decision trees mined using this method may be considered as a starting point for refinement into clinically useful multi-variate lung cancer malignancy models for implementation as a workflow augmentation tool to improve the efficiency of human radiologists.
Publisher: IEEE
Date: 05-2020
Publisher: Institution of Engineering and Technology (IET)
Date: 08-2015
Publisher: IEEE
Date: 07-2019
Publisher: IEEE
Date: 03-2021
Publisher: IEEE
Date: 21-09-2020
Publisher: MDPI AG
Date: 19-08-2021
DOI: 10.3390/RS13163276
Abstract: Detecting animals to estimate abundance can be difficult, particularly when the habitat is dense or the target animals are fossorial. The recent surge in the use of thermal imagers in ecology and their use in animal detections can increase the accuracy of population estimates and improve the subsequent implementation of management programs. However, the use of thermal imagers results in many hours of captured flight videos which require manual review for confirmation of species detection and identification. Therefore, the perceived cost and efficiency trade-off often restricts the use of these systems. Additionally, for many off-the-shelf systems, the exported imagery can be quite low resolution ( Hz), increasing the difficulty of using automated detections algorithms to streamline the review process. This paper presents an animal species detection system that utilises the cost-effectiveness of these lower resolution thermal imagers while harnessing the power of transfer learning and an enhanced small object detection algorithm. We have proposed a distant object detection algorithm named Distant-YOLO (D-YOLO) that utilises YOLO (You Only Look Once) and improves its training and structure for the automated detection of target objects in thermal imagery. We trained our system on thermal imaging data of rabbits, their active warrens, feral pigs, and kangaroos collected by thermal imaging researchers in New South Wales and Western Australia. This work will enhance the visual analysis of animal species while performing well on low, medium and high-resolution thermal imagery.
Publisher: Springer Science and Business Media LLC
Date: 13-03-2023
DOI: 10.1038/S41598-023-30575-2
Abstract: In recent years, quantum image computing draws a lot of attention due to storing and processing image data faster compared to classical computers. A number of approaches have been proposed to represent the quantum image inside a quantum computer. Representing and compressing medium and big-size images inside the quantum computer is still challenging. To address this issue, we have proposed a block-wise DCT-EFRQI (Direct Cosine Transform Efficient Flexible Representation of Quantum Image) approach to represent and compress the gray-scale image efficiently to save computational time and reduce the quantum bits (qubits) for the state preparation. In this work, we have demonstrated the capability of block-wise DCT and DWT transformation inside the quantum domain to investigate their relative performances. The Quirk simulation tool is used to design the corresponding quantum image circuit. In the proposed DCT-EFRQI approach, a total of 17 qubits are used to represent the coefficients, the connection between coefficients and state (i.e., auxiliary), and their position for representing and compressing grayscale images inside a quantum computer. Among those, 8 qubits are used to map the coefficient values and the rest are used to generate the corresponding coefficient XY-coordinate position including one auxiliary qubit. Theoretical analysis and experimental results show that the proposed DCT-EFRQI scheme provides better representation and compression compared to DCT-GQIR, DWT-GQIR, and DWT-EFRQI in terms of rate-distortion performance.
Publisher: American Dairy Science Association
Date: 10-2020
Publisher: The Optical Society
Date: 16-11-2017
Publisher: IEEE
Date: 09-2019
Publisher: Springer International Publishing
Date: 2016
Publisher: Elsevier BV
Date: 11-2023
Publisher: IEEE
Date: 2009
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 2019
Publisher: IEEE
Date: 12-2016
Publisher: IEEE
Date: 07-2012
Publisher: MDPI AG
Date: 21-07-2023
DOI: 10.3390/S23146585
Abstract: Screening programs for early lung cancer diagnosis are uncommon, primarily due to the challenge of reaching at-risk patients located in rural areas far from medical facilities. To overcome this obstacle, a comprehensive approach is needed that combines mobility, low cost, speed, accuracy, and privacy. One potential solution lies in combining the chest X-ray imaging mode with federated deep learning, ensuring that no single data source can bias the model adversely. This study presents a pre-processing pipeline designed to debias chest X-ray images, thereby enhancing internal classification and external generalization. The pipeline employs a pruning mechanism to train a deep learning model for nodule detection, utilizing the most informative images from a publicly available lung nodule X-ray dataset. Histogram equalization is used to remove systematic differences in image brightness and contrast. Model training is then performed using combinations of lung field segmentation, close cropping, and rib/bone suppression. The resulting deep learning models, generated through this pre-processing pipeline, demonstrate successful generalization on an independent lung nodule dataset. By eliminating confounding variables in chest X-ray images and suppressing signal noise from the bone structures, the proposed deep learning lung nodule detection algorithm achieves an external generalization accuracy of 89%. This approach paves the way for the development of a low-cost and accessible deep learning-based clinical system for lung cancer screening.
Publisher: IEEE
Date: 11-2017
Publisher: IEEE
Date: 07-2014
Publisher: IEEE
Date: 11-2017
Publisher: Oxford University Press (OUP)
Date: 05-2015
Abstract: The study investigated genetic architecture and predictive ability using genomic annotation of residual feed intake (RFI) and its component traits (daily feed intake [DFI], ADG, and back fat [BF]). A total of 1,272 Duroc pigs had both genotypic and phenotypic records, and the records were split into a training (968 pigs) and a validation dataset (304 pigs) by assigning records as before and after January 1, 2012, respectively. SNP were annotated by 14 different classes using Ensembl variant effect prediction. Predictive accuracy and prediction bias were calculated using Bayesian Power LASSO, Bayesian A, B, and Cπ, and genomic BLUP (GBLUP) methods. Predictive accuracy ranged from 0.508 to 0.531, 0.506 to 0.532, 0.276 to 0.357, and 0.308 to 0.362 for DFI, RFI, ADG, and BF, respectively. BayesCπ100.1 increased accuracy slightly compared to the GBLUP model and other methods. The contribution per SNP to total genomic variance was similar among annotated classes across different traits. Predictive performance of SNP classes did not significantly differ from randomized SNP groups. Genomic prediction has accuracy comparable to observed phenotype, and use of genomic prediction can be cost effective by replacing feed intake measurement. Genomic annotation had less impact on predictive accuracy traits considered here but may be different for other traits. It is the first study to provide useful insights into biological classes of SNP driving the whole genomic prediction for complex traits in pigs.
Publisher: IEEE
Date: 08-2015
Publisher: Elsevier BV
Date: 07-2021
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 2018
Publisher: IEEE
Date: 07-2014
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 2022
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 03-2018
Publisher: Springer Science and Business Media LLC
Date: 12-08-2012
Publisher: IEEE
Date: 07-2012
DOI: 10.1109/ICME.2012.18
Publisher: Springer Berlin Heidelberg
Date: 2007
Publisher: MDPI AG
Date: 12-02-2022
DOI: 10.3390/ANI12040455
Abstract: Current organic pig-breeding programs use pigs from conventional breeding populations. However, there are considerable differences between conventional and organic production systems. This simulation study aims to evaluate how the organic pig sector could benefit from having an independent breeding program. Two organic pig-breeding programs were simulated: one used sires from a conventional breeding population (conventional sires), and the other used sires from an organic breeding population (organic sires). For maintaining the breeding population, the conventional population used a conventional breeding goal, whereas the organic population used an organic breeding goal. Four breeding goals were simulated: one conventional breeding goal, and three organic breeding goals. When conventional sires were used, genetic gain in the organic population followed the conventional breeding goal, even when an organic breeding goal was used to select conventional sires. When organic sires were used, genetic gain followed the organic breeding goal. From an economic point of view, using conventional sires for breeding organic pigs is best, but only if there are no genotype-by-environment interactions. However, these results show that from a biological standpoint, using conventional sires biologically adapts organic pigs for a conventional production system.
Publisher: IEEE
Date: 2002
Publisher: Springer Science and Business Media LLC
Date: 08-2013
DOI: 10.1057/JMA.2013.15
Publisher: Springer Singapore
Date: 2019
Publisher: IEEE
Date: 11-2016
Publisher: MDPI AG
Date: 13-07-2022
DOI: 10.3390/ANI12141796
Abstract: Selection for the number of living pigs on day 11 (L11) aims to reduce piglet mortality and increase litter size simultaneously. This approach could be sub-optimal, especially for organic pig breeding. This study evaluated the effect of selecting for a trait by separating it into two traits. Genetic parameters for L11, the total number born (TNB), and the number of dead piglets at day 11 (D11) were estimated using data obtained from an organic pig population in Denmark. Based on these estimates, two alternative breeding schemes were simulated. Specifically, selection was made using: (1) a breeding goal with L11 only versus (2) a breeding goal with TNB and D11. Different weightings for TNB and D11 were tested. The simulations showed that selection using the first breeding scheme (L11) produced lower annual genetic gain (0.201) compared to the second (TNB and D11 0.207). A sensitivity analysis showed that the second scheme performed better because it exploited differences in heritability, and accounted for genetic correlations between the two traits. When the second breeding scheme placed more emphasis on D11, D11 declined, whereas genetic gain for L11 remained high (0.190). In conclusion, selection for L11 could be optimized by separating it into two correlated traits with different heritability, reducing piglet mortality and enhancing L11.
Publisher: IEEE
Date: 11-2016
Publisher: AOSIS
Date: 30-12-2016
Abstract: This study explores consumers’ decision-making in terms of intention to switch to foreign brands from domestic brands when purchasing cell phones and sports shoes. A survey of 584 undergraduates in Guangdong, China, shows that domestic brands retain their low quality-conscious, low fashion-and-recreational-conscious and low price-conscious customers and attract low brand-conscious and high choice-confused buyers from foreign brands. Foreign brands typically retain their consumers who are highly conscious of fashion and recreation and keep and draw customers with low choice confusion. High-price-conscious consumers and those who are highly brand-confused will assess foreign and domestic brands when searching for bargains. Regarding managerial implications, local brands should offer products of high quality at low pricesand constantly invest in R& D foreign brands may expand their customer bases and build interactive brand channels all companies can retain brand-confused customers with preferential packages and design their marketing strategies based on decision-making styles of their target consumers.
Publisher: The Optical Society
Date: 31-03-2017
Publisher: IEEE
Date: 12-2019
Publisher: IEEE
Date: 13-12-2023
Publisher: IEEE
Date: 02-2019
Publisher: IEEE
Date: 07-2016
Publisher: Springer International Publishing
Date: 2020
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 2021
Publisher: Elsevier BV
Date: 02-2017
Publisher: Springer International Publishing
Date: 2020
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 06-2022
Publisher: IEEE
Date: 09-2010
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 03-2020
Publisher: Wiley
Date: 04-10-2023
DOI: 10.1111/IJCS.12875
Abstract: This study reviews the literature on the residence after retirement via Systematic Literature Network Analysis, which consists of the systematic literature review and bibliometric network analysis. There are three research questions, including (1) what the most recent studies are on the residence after retirement, (2) Who the most significant authors, documents, and sources are in residence after retirement, and (3) whether the extant research structure could guide the future agenda for the residence after retirement. Based on the systematic literature review, this study extracts 50 publications from the Scopus database by keyword, document type, source type, publication period, language, and subject area relevant to the residence after retirement. This study analyzes data employing Nvivo, VOSviewer, and SciMAX. The clusters of authors, countries, keywords, documents, and sources linked with relevant studies on the residence after retirement are according to the co‐authorship (1) author, (2) country/territory, (3) keyword, and (4) document. Skitmore, M., Xia, B., Buys, I., Hu, X., Hu, Y., and Chen, Q. who the most influential authors are in residence after retirement. The themes of aging, continuing care retirement community, retirement village, and their associated keywords contribute to future research on the residence after retirement.
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 11-2010
Publisher: IEEE
Date: 11-2017
Publisher: IEEE
Date: 06-06-2021
Publisher: IEEE
Date: 09-2010
Publisher: Public Library of Science (PLoS)
Date: 10-03-2016
Publisher: SAGE Publications
Date: 10-2021
DOI: 10.1177/21582440211061565
Abstract: Improving consumer trust is critical for enhancing purchase intentions. This study assessed the effect of organic labeling awareness and food safety attitudes as mediating variables on the relation between green product awareness and organic food purchase intentions among consumers. The research s le comprised 404 respondents from Shantou, Shenzhen, and Guangzhou, China, collected by systematic random s ling. Structural equation modeling was used to analyze research data. First, green product awareness did not influence organic food purchase intentions. Second, organic labeling awareness and food safety attitudes mediated the relationship between green product awareness and organic food purchase intentions. The findings indicate that organic labeling awareness and food safety attitudes directly influenced consumers’ organic food purchase intentions while they were aware of green products.
Publisher: Springer International Publishing
Date: 2015
Publisher: IEEE
Date: 12-2008
Publisher: IEEE
Date: 04-2007
Publisher: Research Square Platform LLC
Date: 31-10-2023
Publisher: Oxford University Press (OUP)
Date: 09-2013
Abstract: Residual feed intake (RFI) is commonly used as a measure of feed efficiency at a given level of production. A total of 16,872 pigs with their pedigree traced back as far as possible was used to estimate genetic parameters for RFI, growth performance, food conversion ratio (FCR), body conformation, and feeding behavior traits in 3 Danish breeds [Duroc (DD), Landrace (LL), and Yorkshire (YY)]. Two measures of RFI were considered: residual feed intake 1 (RFI1) was calculated based on regression of daily feed intake (DFI) from 30 to 100 kg on initial test weight and ADG from 30 to 100 kg (ADG2). Residual feed intake 2 (RFI2) was as RFI1, except it was also regressed with respect to backfat (BF). The estimated heritabilities for RFI1 and RFI2 were 0.34 and 0.38 in DD, 0.34 and 0.36 in LL, and 0.39 and 0.40 in YY, respectively. The heritabilities ranged from 0.32 (DD) to 0.54 (LL) for ADG2, from 0.54 (DD) to 0.67 (LL) for BF, and from 0.13 (DD) to 0.19 (YY) for body conformation. Feeding behavior traits including DFI, number of visits to feeder per day (NVD), total time spent eating per day (TPD), feed intake rate (FR), feed intake per visit (FPV), and time spent eating per visit (TPV) were moderately to highly heritable. Residual feed intake 2 was genetically independent of ADG2 and BF in all breeds, except it had low genetic correlation to ADG2 in YY (0.2). Residual feed intake 1 was also genetically independent of ADG2 in DD and LL. Both RFI traits had strong genetic correlations with DFI (0.85 to 0.96) and FCR (0.76 to 0.99). They had low or no genetic correlations with feeding behavior traits. Unfavorable genetic correlations were found between ADG2 and both BF and DFI. Among feeding behavior traits, DFI had low genetic correlations to other traits in all breeds. High and negative genetic correlations were also found between TPD with FR (-0.79 in YY to -0.88 in DD), NVD, and TPD (-0.91 in DD to -0.94 in YY) and between NVD and FPV (-0.83 in DD to -0.91 in YY) in all breeds. The genetic trend for feed efficiency was favorable in all breeds regardless of the definition of feed efficiency used. In summary, RFI1 and RFI2 were heritable and selection for reduced RFI2 can be performed without adversely affecting ADG and BF and could replace FCR in the selection index for the Danish pig breeds. Selection could also be based on RFI1 for breeds with fewer concerns about a negative effect of BF or for breeds that do not have BF records.
Publisher: Institution of Engineering and Technology (IET)
Date: 12-2012
Publisher: Public Library of Science (PLoS)
Date: 03-10-2016
Publisher: IEEE
Date: 09-2017
Publisher: IEEE
Date: 16-10-2022
Publisher: IEEE
Date: 2007
Publisher: IEEE
Date: 11-2016
Publisher: IEEE
Date: 09-2008
DOI: 10.1109/AVSS.2008.12
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 06-2018
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 02-2011
Publisher: Wiley
Date: 17-10-2020
DOI: 10.1111/JBG.12448
Publisher: IEEE
Date: 21-09-2020
Publisher: IEEE
Date: 12-2012
Publisher: Springer Science and Business Media LLC
Date: 24-05-2017
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 2023
Publisher: IEEE
Date: 04-2015
Publisher: IEEE
Date: 09-2018
Publisher: Elsevier BV
Date: 12-2014
Publisher: IEEE
Date: 11-2016
Publisher: Elsevier BV
Date: 09-2021
Publisher: Springer Science and Business Media LLC
Date: 27-06-2023
Publisher: IEEE
Date: 11-2015
Publisher: IEEE
Date: 25-11-2020
Publisher: Open Engineering Inc
Date: 21-04-2020
Abstract: Detecting COVID-19 early may help in devising an appropriate treatment plan and disease containment decisions. In this study, we demonstrate how pre-trained deep learning models can be adopted to perform COVID-19 detection using X-Ray images. The aim is to provide over-stressed medical professionals a second pair of eyes through intelligent image classification models. We highlight the challenges (including dataset size and quality) in utilising current publicly available COVID-19 datasets for developing useful deep learning models. We propose a semi-automated image pre-processing model to create a trustworthy image dataset for developing and testing deep learning models. The new approach is aimed to reduce unwanted noise from X-Ray images so that deep learning models can focus on detecting diseases with specific features from them. Next, we devise a deep learning experimental framework, where we utilise the processed dataset to perform comparative testing for several popular and widely available deep learning model families such as VGG, Inception, Xception, and Resnet. The experimental results highlight the suitability of these models for current available dataset and indicates that models with simpler networks such as VGG19 performs relatively better with up to 83% precision. This will provide a solid pathway for researchers and practitioners to develop improved models in the future.
Publisher: IEEE
Date: 12-2011
Publisher: Now Publishers
Date: 2016
Publisher: Springer International Publishing
Date: 2018
Publisher: IEEE
Date: 07-2016
Publisher: IEEE
Date: 03-2012
Publisher: IEEE
Date: 07-2023
Publisher: IEEE
Date: 07-2023
Publisher: IEEE
Date: 19-09-2021
Publisher: Springer Science and Business Media LLC
Date: 09-07-2011
Publisher: IEEE
Date: 07-2017
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 02-2019
Publisher: IEEE
Date: 19-09-2021
Publisher: IEEE
Date: 11-2016
Publisher: IEEE
Date: 10-2008
Publisher: Springer Science and Business Media LLC
Date: 07-06-2017
Publisher: IEEE
Date: 25-11-2021
Publisher: MDPI AG
Date: 24-06-2174
Abstract: Light detection and ranging (LiDAR) sensors have accrued an ever-increasing presence in the agricultural sector due to their non-destructive mode of capturing data. LiDAR sensors emit pulsed light waves that return to the sensor upon bouncing off surrounding objects. The distances that the pulses travel are calculated by measuring the time for all pulses to return to the source. There are many reported applications of the data obtained from LiDAR in agricultural sectors. LiDAR sensors are widely used to measure agricultural landscaping and topography and the structural characteristics of trees such as leaf area index and canopy volume they are also used for crop biomass estimation, phenotype characterisation, crop growth, etc. A LiDAR-based system and LiDAR data can also be used to measure spray drift and detect soil properties. It has also been proposed in the literature that crop damage detection and yield prediction can also be obtained with LiDAR data. This review focuses on different LiDAR-based system applications and data obtained from LiDAR in agricultural sectors. Comparisons of aspects of LiDAR data in different agricultural applications are also provided. Furthermore, future research directions based on this emerging technology are also presented in this review.
Publisher: IEEE
Date: 13-12-2023
Publisher: Elsevier BV
Date: 03-2023
Publisher: IEEE
Date: 2008
Publisher: Wiley
Date: 19-02-2018
DOI: 10.1002/RCS.1889
Abstract: Augmented reality-based surgeries have not been successfully implemented in oral and maxillofacial areas due to limitations in geometric accuracy and image registration. This paper aims to improve the accuracy and depth perception of the augmented video. The proposed system consists of a rotational matrix and translation vector algorithm to reduce the geometric error and improve the depth perception by including 2 stereo cameras and a translucent mirror in the operating room. The results on the mandible/maxilla area show that the new algorithm improves the video accuracy by 0.30-0.40 mm (in terms of overlay error) and the processing rate to 10-13 frames/s compared to 7-10 frames/s in existing systems. The depth perception increased by 90-100 mm. The proposed system concentrates on reducing the geometric error. Thus, this study provides an acceptable range of accuracy with a shorter operating time, which provides surgeons with a smooth surgical flow.
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 2020
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 03-2020
Publisher: Open Engineering Inc
Date: 23-04-2021
Abstract: The COVID-19 pandemic has inspired unprecedented data collection and computer vision modelling efforts worldwide, focusing on diagnosis and stratification of COVID-19 from medical images. Despite this large-scale research effort, these models have found limited practical application due in part to unproven generalization of these models beyond their source study. This study investigates the generalizability of key published models using the publicly available COVID-19 Computed Tomography data through cross dataset validation. We then assess the predictive ability of these models for COVID-19 severity using an independent new dataset that is stratified for COVID-19 lung involvement. Each inter-dataset study is performed using histogram equalization, and contrast limited adaptive histogram equalization with and without a learning Gabor filter. The study shows high variability in the generalization of models trained on these datasets due to varied s le image provenances and acquisition processes amongst other factors. We show that under certain conditions, an internally consistent dataset can generalize well to an external dataset despite structural differences between these datasets with f1 scores up to 86%. Our best performing model shows high predictive accuracy for lung involvement score for an independent dataset for which expertly labelled lung involvement stratification is available. Creating an ensemble of our best model for disease positive prediction with our best model for disease negative prediction using a min-max function resulted in a superior model for lung involvement prediction with average predictive accuracy of 75% for zero lung involvement and 96% for 75-100% lung involvement with almost linear relationship between these stratifications.
Publisher: IEEE
Date: 25-11-2021
Publisher: Science Publications
Date: 09-2018
Publisher: IEEE
Date: 07-2010
Publisher: The Optical Society
Date: 05-2017
Publisher: Springer Science and Business Media LLC
Date: 22-11-2013
Publisher: Elsevier BV
Date: 2016
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 2016
Publisher: MDPI AG
Date: 04-05-2023
DOI: 10.3390/ENVIRONMENTS10050077
Abstract: Estimating various properties of soil, including moisture, carbon, and nitrogen, is crucial for studying their correlation with plant health and food production. However, conventional methods such as oven-drying and chemical analysis are laborious, expensive, and only feasible for a limited land area. With the advent of remote sensing technologies like multi/hyperspectral imaging, it is now possible to predict soil properties non-invasive and cost-effectively for a large expanse of bare land. Recent research shows the possibility of predicting those soil contents from a wide range of hyperspectral data using good prediction algorithms. However, these kinds of hyperspectral sensors are expensive and not widely available. Therefore, this paper investigates different machine and deep learning techniques to predict soil nutrient properties using only the red (R), green (G), and blue (B) bands data to propose a suitable machine/deep learning model that can be used as a rapid soil test. Another objective of this research is to observe and compare the prediction accuracy in three cases i. hyperspectral band ii. full spectrum of the visual band, and iii. three-channel of RGB band and provide a guideline to the user on which spectrum information they should use to predict those soil properties. The outcome of this research helps to develop a mobile application that is easy to use for a quick soil test. This research also explores learning-based algorithms with significant feature combinations and their performance comparisons in predicting soil properties from visual band data. For this, we also explore the impact of dimensional reduction (i.e., principal component analysis) and transformations (i.e., empirical mode decomposition) of features. The results show that the proposed model can comparably predict the soil contents from the three-channel RGB data.
Publisher: Elsevier BV
Date: 10-2016
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 10-2011
Publisher: IEEE
Date: 2007
Publisher: MDPI AG
Date: 23-08-2021
DOI: 10.3390/RS13163317
Abstract: The efficiency of a vineyard management system is directly related to the effective management of nutritional disorders, which significantly downgrades vine growth, crop yield and wine quality. To detect nutritional disorders, we successfully extracted a wide range of features using hyperspectral (HS) images to identify healthy and in idual nutrient deficiencies of grapevine leaves. Features such as mean reflectance, mean first derivative reflectance, variation index, mean spectral ratio, normalised difference vegetation index (NDVI) and standard deviation (SD) were employed at various stages in the ultraviolet (UV), visible (VIS) and near-infrared (N.I.R.) regions for our experiment. Leaves were examined visually in the laboratory and grouped as either healthy (i.e. control) or unhealthy. Then, the features of the leaves were extracted from these two groups. In a second experiment, features of in idual nutrient-deficient leaves (e.g., N, K and Mg) were also analysed and compared with those of control leaves. Furthermore, a customised support vector machine (SVM) was used to demonstrate that these features can be utilised with a high degree of effectiveness to identify unhealthy s les and not only to distinguish from control and nutrient deficient but also to identify in idual nutrient defects. Therefore, the proposed work corroborated that HS imaging has excellent potential to analyse features based on healthiness and in idual nutrient deficiencies of grapevine leaves.
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 2020
Publisher: American Institute of Mathematical Sciences (AIMS)
Date: 2021
DOI: 10.3934/MBE.2021456
Abstract: abstract The COVID-19 pandemic has inspired unprecedented data collection and computer vision modelling efforts worldwide, focused on the diagnosis of COVID-19 from medical images. However, these models have found limited, if any, clinical application due in part to unproven generalization to data sets beyond their source training corpus. This study investigates the generalizability of deep learning models using publicly available COVID-19 Computed Tomography data through cross dataset validation. The predictive ability of these models for COVID-19 severity is assessed using an independent dataset that is stratified for COVID-19 lung involvement. Each inter-dataset study is performed using histogram equalization, and contrast limited adaptive histogram equalization with and without a learning Gabor filter. We show that under certain conditions, deep learning models can generalize well to an external dataset with F1 scores up to 86%. The best performing model shows predictive accuracy of between 75% and 96% for lung involvement scoring against an external expertly stratified dataset. From these results we identify key factors promoting deep learning generalization, being primarily the uniform acquisition of training images, and secondly ersity in CT slice position. /abstract
Publisher: Springer Science and Business Media LLC
Date: 17-02-2014
Publisher: IEEE
Date: 11-2016
Publisher: Academy Publisher
Date: 10-2011
Publisher: Springer International Publishing
Date: 2019
Publisher: IEEE
Date: 07-2019
Publisher: Springer International Publishing
Date: 2019
Publisher: Public Library of Science (PLoS)
Date: 09-11-2017
Publisher: Science Publications
Date: 09-2018
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 02-2021
Publisher: ACTAPRESS
Date: 2013
Publisher: Springer International Publishing
Date: 2015
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 2018
Publisher: IEEE
Date: 09-2018
Publisher: Springer Science and Business Media LLC
Date: 28-06-2023
Publisher: Open Engineering Inc
Date: 02-02-2021
Abstract: Video coding algorithms encode and decode an entire video frame while feature coding techniques only preserve and communicate the most critical information needed for a given application. This is because video coding targets human perception, while feature coding aims for machine vision tasks. Recently, attempts are being made to bridge the gap between these two domains. In this work, we propose a video coding framework by leveraging on to the commonality that exists between human vision and machine vision applications using cuboids. This is because cuboids, estimated rectangular regions over a video frame, are computationally efficient, has a compact representation and object centric. Such properties are already shown to add value to traditional video coding systems. Herein cuboidal feature descriptors are extracted from the current frame and then employed for accomplishing a machine vision task in the form of object detection. Experimental results show that a trained classifier yields superior average precision when equipped with cuboidal features oriented representation of the current test frame. Additionally, this representation costs 7% less in bit rate if the captured frames are need be communicated to a receiver.
Publisher: AICIT
Date: 30-09-2012
Publisher: IEEE
Date: 09-2014
Publisher: Open Engineering Inc
Date: 15-04-2020
Abstract: The COVID-19 pandemic has triggered an urgent need to contribute to the fight against an immense threat to the human population. Computer Vision, as a subfield of Artificial Intelligence, has enjoyed recent success in solvingvarious complex problems in health care and has the potential to contribute to the fight of controlling COVID-19. In response to this call, computer vision researchers are putting their knowledge base at work to devise effective ways to counter COVID-19 challenge and serve the global community. New contributions are being shared with everypassing day. It motivated us to review the recent work, collect information about available research resources and an indication of future research directions. We want to make it available to computer vision researchers to save precious time. This survey paper is intended to provide a preliminary review of the available literature on the computer vision efforts against COVID-19 pandemic.
Publisher: IEEE
Date: 05-2015
Publisher: IEEE
Date: 12-2018
Publisher: IEEE
Date: 09-2011
Publisher: IEEE
Date: 12-2012
Publisher: National Taiwan University
Date: 28-05-2015
DOI: 10.4015/S1016237215500271
Abstract: Electroencephalogram (EEG) is a record of ongoing electrical signal to represent the human brain activity. It has great potential for the diagnosis to treatment of mental disorder and brain diseases such as epileptic seizure. Features extraction and classification is a crucial task to detect the stage of ictal (i.e. seizure period) and interictal (i.e. period between seizures) EEG signals for the treatment and precaution of the patient. However, existing seizure and non-seizure feature extraction techniques are not good enough for the classification of ictal and interictal EEG signals considering their non-abrupt phenomena and inconsistency in different brain locations. In this paper, we present new approaches for feature extraction using high-frequency components from discrete cosine transformation (DCT) and intrinsic mode function (IMF) extracted from empirical mode decomposition (EMD). These features are then used as an input to least square-support vector machine (LV-SVM) to classify ictal and interictal EEG signals. Experimental results show that the proposed methods outperform the existing state-of-the-art method for better classification in terms of sensitivity, specificity, and accuracy with greater consistence of ictal and interictal period of epilepsy for benchmark dataset from different brain locations.
Publisher: Research Square Platform LLC
Date: 21-04-2020
DOI: 10.21203/RS.3.RS-22341/V1
Abstract: lockchain is a relatively new technology that can be seen as a decentralised database. Blockchain systems heavily rely on cryptographic hash functions to store their data, which makes it difficult to t er with any data stored in the system. A topic that was researched along with blockchain is image authentication. Image authentication focuses on investigating and maintaining the integrity of images. As a blockchain system can be useful for maintaining data integrity, image authentication has the potential to be enhanced by blockchain. There are many techniques that can be used to authenticate images the technique investigated by this work is image hashing. Image hashing is a technique used to calculate how similar two different images are. This is done by converting the images into hashes and then comparing them using a distance formula. To investigate the topic, an experiment involving a simulated blockchain was created. The blockchain acted as a database for images. This blockchain was made up of devices which contained their own unique image hashing algorithms. The blockchain was tested by creating modified copies of the images contained in the database, and then submitting them to the blockchain to see if it will return the original image. Through this experiment it was discovered that it is plausible to create an image authentication system using blockchain and image hashing. However, the design proposed by this work requires refinement, as it appears to struggle in some situations. This work shows that blockchain can be a suitable approach for authenticating images, particularly via image hashing. Other observations include that using multiple image hash algorithms at the same time can increase performance in some cases, as well as that each type of test done to the blockchain has its own unique pattern to its data.
Publisher: IEEE
Date: 11-2016
Publisher: IEEE
Date: 12-2019
Publisher: IEEE
Date: 09-2010
Publisher: IEEE
Date: 30-11-2023
Publisher: Springer International Publishing
Date: 2019
Publisher: IEEE
Date: 30-11-2022
Publisher: Springer International Publishing
Date: 2019
Publisher: IEEE
Date: 12-2018
Publisher: IEEE
Date: 12-2015
Publisher: Springer International Publishing
Date: 2019
Publisher: ACM
Date: 02-12-2014
Publisher: IEEE
Date: 19-09-2021
Publisher: IEEE
Date: 2018
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 03-2010
Publisher: Oxford University Press (OUP)
Date: 23-03-2023
DOI: 10.1093/IWC/IWAD028
Abstract: This study examined whether participants’ adherence to an algorithmic aid was related to the degree of control they were provided at decision point and their attitudes toward new technologies and algorithms. It also tested the influence of control on participants’ subjective reports of task demands whilst using the aid. A total of 159 participants completed an online experiment centred on a simulated forecasting task, which required participants to predict the performance of school students on a standardized mathematics test. For each student, participants also received an algorithm-generated forecast of their score. Participants were randomly assigned to either the ‘full control’ (adjust forecast as much as they wish), ‘moderate control’ (adjust forecast by 30%) or ‘restricted control’ (adjust forecast by 2%) group. Participants then completed an assessment of subjective task load, a measure of their explicit attitudes toward new technologies, demographic and experience items (age, gender and computer literacy) and a novel version of the Go/No-Go Association Task, which tested their implicit attitudes toward algorithms. The results revealed that participants who were provided with more control over the final forecast tended to deviate from it more greatly and reported lower levels of frustration. Furthermore, participants showing more positive implicit attitudes toward algorithms were found to deviate less from the algorithm’s forecasts, irrespective of the degree of control they were given. The findings allude to the importance of users’ control and preexisting attitudes in their acceptance of, and frustration in using a novel algorithmic aid, which may ultimately contribute to their intention to use them in the workplace. These findings can guide system developers and support workplaces implementing expert system technology.
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 06-2009
Publisher: IEEE
Date: 2003
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 2017
Publisher: IEEE
Date: 09-2013
Publisher: IEEE
Date: 12-2015
Publisher: IGI Global
Date: 2016
DOI: 10.4018/978-1-4666-8811-7.CH015
Abstract: Epilepsy is one of the common neurological disorders characterized by a sudden and recurrent malfunction of the brain that is termed “seizure”, affecting around 65 million in iduals worldwide. Epileptic seizure may lead to many injuries such as fractures, submersion, burns, motor vehicle accidents and even death. It is highly possible to prevent these unwanted situations if we can predict/detect electrical changes in brain that occur prior to onset of actual seizure. When building a prediction model, the goal should be to make a model that accurately classifies preictal period (prior to a seizure onset) from interictal (period between seizures when non-seizure syndrome is observed) period. On the hand, for the detection we need to make a model that can classify ictal (actual seizure period) from non-ictal/interictal period. This chapter describes the seizure detection and prediction techniques with its background, features, recent developments, and future trends.
Publisher: Springer Science and Business Media LLC
Date: 20-08-2013
Publisher: IEEE
Date: 10-2008
Publisher: IEEE
Date: 04-2019
Publisher: MDPI AG
Date: 20-10-2022
DOI: 10.3390/S22207998
Abstract: Soil moisture, soil organic carbon, and nitrogen content prediction are considered significant fields of study as they are directly related to plant health and food production. Direct estimation of these soil properties with traditional methods, for ex le, the oven-drying technique and chemical analysis, is a time and resource-consuming approach and can predict only smaller areas. With the significant development of remote sensing and hyperspectral (HS) imaging technologies, soil moisture, carbon, and nitrogen can be estimated over vast areas. This paper presents a generalized approach to predicting three different essential soil contents using a comprehensive study of various machine learning (ML) models by considering the dimensional reduction in feature spaces. In this study, we have used three popular benchmark HS datasets captured in Germany and Sweden. The efficacy of different ML algorithms is evaluated to predict soil content, and significant improvement is obtained when a specific range of bands is selected. The performance of ML models is further improved by applying principal component analysis (PCA), a dimensional reduction method that works with an unsupervised learning method. The effect of soil temperature on soil moisture prediction is evaluated in this study, and the results show that when the soil temperature is considered with the HS band, the soil moisture prediction accuracy does not improve. However, the combined effect of band selection and feature transformation using PCA significantly enhances the prediction accuracy for soil moisture, carbon, and nitrogen content. This study represents a comprehensive analysis of a wide range of established ML regression models using data preprocessing, effective band selection, and data dimension reduction and attempt to understand which feature combinations provide the best accuracy. The outcomes of several ML models are verified with validation techniques and the best- and worst-case scenarios in terms of soil content are noted. The proposed approach outperforms existing estimation techniques.
Publisher: IEEE
Date: 03-2014
Publisher: Springer Science and Business Media LLC
Date: 19-02-2014
Publisher: Wageningen Academic Publishers
Date: 21-08-2015
Publisher: IEEE
Date: 07-2017
Publisher: Springer International Publishing
Date: 2016
Publisher: IEEE
Date: 07-2016
Publisher: IEEE
Date: 12-2017
Publisher: IEEE
Date: 11-2016
Publisher: IEEE
Date: 2007
Publisher: Wiley
Date: 26-09-2019
DOI: 10.1002/RCS.1958
Abstract: Augmented reality (AR) surgery has not been successfully implemented in knee replacement surgery due to the negative effect of cutting errors. This research aims to decrease the cutting error to reduce the chronic pain after knee replacement. The proposed system consists of a volume subtraction technique that considers the history of the area that has been cut and measures it against the target shape. Results minimized the cutting error by about 1 mm. Therefore, it provides a significant video accuracy improvement in alignment to 0.40 to 0.55 mm from 0.55 to 0.64 and a decrease in processing time from 12 to 13 fs/s to 9 to10 fs/s. The proposed system is focused on overlaying only the remaining areas of surgery that need to be completed. Finally, this study solves the issues of navigation with AR when cutting bones in a scheduled direction and depth.
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 12-2007
Publisher: Springer International Publishing
Date: 2023
Publisher: IEEE
Date: 12-2015
Publisher: Springer Science and Business Media LLC
Date: 11-09-2018
DOI: 10.1007/S10006-018-0719-5
Abstract: Augmented reality-based constructive jaw surgery has been facing various limitations such as noise in real-time images, the navigational error of implants and jaw, image overlay error, and occlusion handling which have limited the implementation of augmented reality (AR) in corrective jaw surgery. This research aimed to improve the navigational accuracy, through noise and occlusion removal, during positioning of an implant in relation to the jaw bone to be cut or drilled. The proposed system consists of a weighting-based de-noising filter and depth mapping-based occlusion removal for removing any occluded object such as surgical tools, the surgeon's body parts, and blood. The maxillary (upper jaw) and mandibular (lower jaw) jaw bone s le results show that the proposed method can achieve the image overlay error (video accuracy) of 0.23~0.35 mm and processing time of 8-12 frames per second compared to 0.35~0.45 mm and 6-11 frames per second by the existing best system. The proposed system concentrates on removing the noise from the real-time video frame and the occlusion. Thus, the acceptable range of accuracy and the processing time are provided by this study for surgeons for carrying out a smooth surgical flow.
Publisher: Springer International Publishing
Date: 2018
Publisher: IEEE
Date: 03-2022
Publisher: International Academy Publishing (IAP)
Date: 2018
Location: Bangladesh
Start Date: 07-2013
End Date: 07-2017
Amount: $315,000.00
Funder: Australian Research Council
View Funded ActivityStart Date: 07-2019
End Date: 06-2023
Amount: $380,000.00
Funder: Australian Research Council
View Funded Activity