ORCID Profile
0000-0002-9403-7140
Current Organisations
University of Wollongong
,
Organisation
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.
Communication Technology and Digital Media Studies | Communication and Media Studies | Artificial Intelligence and Image Processing | Neural, Evolutionary and Fuzzy Computation | Pattern Recognition and Data Mining | Decision Support and Group Support Systems | Software Engineering | Visual Arts and Crafts not elsewhere classified
Learner and Learning Processes | Management of Education and Training Systems | Electronic Information Storage and Retrieval Services | Expanding Knowledge in Law and Legal Studies | The Creative Arts (incl. Graphics and Craft) | Finance Services |
Publisher: Elsevier BV
Date: 08-2022
Publisher: Springer Science and Business Media LLC
Date: 2016
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 06-2022
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 07-2023
Publisher: ACM
Date: 21-10-2023
Publisher: Springer Berlin Heidelberg
Date: 2009
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 03-2022
Publisher: University of New England, Armidale
Date: 12-2021
DOI: 10.14742/ASCILITE2021.0128
Abstract: There has been a steady increase in international students pursuing postgraduate coursework education in English speaking countries. Like first-year undergraduate students, these international students need assistance transitioning into the new educational environment and preparing for self-directed, collaborative learning throughout their careers. Drawing on the social constructivist pedagogical approaches, we developed learning tasks that foster self-regulation and collaboration among postgraduate coursework IT students, aligning these tasks with the learning outcomes of the subject Information Design and Content Management. This paper presents the rationale and method for the design of the learning tasks, and how these learning tasks to not only align with the subject learning outcomes but also facilitate self-regulation. A study involving preand post-subject surveys and interviews with 133 subject students will provide us with further insights into the effectiveness of the learning task design and the areas for improvement.
Publisher: IEEE
Date: 07-2007
Publisher: Australian Journal of Information Systems
Date: 12-02-2019
Abstract: This paper presents a contemporary literature review to provide insights into the current health informatics literature. The objective of this study is to identify emerging directions of current health informatics research from the latest and existing studies in the health informatics domain. We analyse existing health informatics studies using a thematic analysis, so that justified sets of research agenda can be outlined on the basis of these findings. We selected articles that are published in the science direct online database. The selected 73 s le articles (published from 2014 to 2018 in premier health informatics journals) are considered as representative s les of health informatics studies. The analysis revealed ten topic areas and themes that would be of paramount importance for researchers and practitioners to follow. The findings provide an important foundational understanding for new health informatics studies.
Publisher: IEEE
Date: 12-2019
Publisher: IEEE
Date: 08-2017
DOI: 10.1109/CBD.2016.037
Publisher: IEEE
Date: 10-12-2020
Publisher: MDPI AG
Date: 30-12-2022
DOI: 10.3390/FI15010022
Abstract: Electricity load forecasting has seen increasing importance recently, especially with the effectiveness of deep learning methods growing. Improving the accuracy of electricity load forecasting is vital for public resources management departments. Traditional neural network methods such as long short-term memory (LSTM) and bidirectional LSTM (BiLSTM) have been widely used in electricity load forecasting. However, LSTM and its variants are not sensitive to the dynamic change of inputs and miss the internal nonperiodic rules of series, due to their discrete observation interval. In this paper, a novel neural ordinary differential equation (NODE) method, which can be seen as a continuous version of residual network (ResNet), is applied to electricity load forecasting to learn dynamics of time series. We design three groups of models based on LSTM and BiLSTM and compare the accuracy between models using NODE and without NODE. The experimental results show that NODE can improve the prediction accuracy of LSTM and BiLSTM. It indicates that NODE is an effective approach to improving the accuracy of electricity load forecasting.
Publisher: Springer Science and Business Media LLC
Date: 02-09-2015
DOI: 10.1007/S00109-015-1336-5
Abstract: Recent studies implicate TRPV4 receptors in visceral pain signaling and intestinal inflammation. Our aim was to evaluate the role of TRPV4 in the control of gastrointestinal (GI) motility and to establish the underlying mechanisms. We used immunohistochemistry and PCR to study TRPV4 expression in the GI tract. The effect of TRPV4 activation on GI motility was characterized using in vitro and in vivo motility assays. Calcium and nitric oxide (NO) imaging were performed to study the intracellular signaling pathways. Finally, TRPV4 expression was examined in the colon of healthy human subjects. We demonstrated that TRPV4 can be found on myenteric neurons of the colon and is co-localized with NO synthase (NOS-1). In vitro, the TRPV4 agonist GSK1016790A reduced colonic contractility and increased inhibitory neurotransmission. In vivo, TRPV4 activation slowed GI motility and reduced stool production in mouse models mimicking pathophysiological conditions. We also showed that TRPV4 activation inhibited GI motility by reducing NO-dependent Ca(2+) release from enteric neurons. In conclusion, TRPV4 is involved in the regulation of GI motility in health and disease. • Recent studies implicate TRPV4 in pain signaling and intestinal inflammation. • Our aim was to characterize the role of TRPV4 in the control of GI motility. • We found that TRPV4 activation reduced colonic contractility. • Our studies also showed altered TRPV4 mRNA expression in IBS-C patients. • TRPV4 may be a novel pharmacological target in functional GI diseases.
Publisher: Springer International Publishing
Date: 2020
Publisher: Elsevier BV
Date: 02-2021
Publisher: Springer Science and Business Media LLC
Date: 29-07-2022
DOI: 10.1007/S40747-022-00828-0
Abstract: This paper presents a relation-centric algorithm for solving arithmetic word problems (AWPs) by synergizing a syntax-semantics extractor for extracting explicit relations, and a neural network miner for mining implicit relations. This is the first algorithm that has a specific component to acquire implicit knowledge items for solving AWPs. This paper proposes a three-phase scheme to decompose the challenging task of designing an algorithm for solving AWPs into three smaller tasks. The first phase proposes a state-action paradigm the second phase instantiates the paradigm into a relation-centric approach and the third phase implements a relation-centric algorithm for solving AWPs. There are two main steps in the proposed algorithm: problem understanding and symbolic solver. By adopting the relation-centric approach, problem understanding becomes a task of relation acquisition. For conducting the task of relation acquisition, a relaxed syntax-semantics method first extracts a group of explicit relation candidates. In parallel, a neural network miner acquires implicit relation candidates. The miner computes the vectors encoded by BERT to determine which implicit relations should be added. Thus, problem understanding can acquire both explicit relations and implicit relations, which addresses the challenge of building a problem understanding method that can acquire all the knowledge items to find the solution. In the subsequent step of symbolic solver, a fusion procedure forms a distilled set of relations from all the candidates by discarding unnecessary relations. Experimentation on nine benchmark datasets validates the superiority of the proposed algorithm that outperforms the state-of-the-art algorithms.
Publisher: Association for Information Systems
Date: 2023
DOI: 10.17705/1CAIS.05317
Publisher: IEEE
Date: 12-2018
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 11-2020
Publisher: EDP Sciences
Date: 10-2015
Publisher: IEEE
Date: 06-2012
DOI: 10.1109/SE.2012.14
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 06-2022
Publisher: Informa UK Limited
Date: 2021
Publisher: Springer International Publishing
Date: 2020
Publisher: Springer Science and Business Media LLC
Date: 06-05-2012
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 04-2023
Publisher: Elsevier BV
Date: 03-2023
Publisher: IEEE
Date: 24-05-2023
Publisher: IEEE
Date: 09-2014
Publisher: Springer International Publishing
Date: 2015
Publisher: IEEE
Date: 07-2015
Publisher: Research Square Platform LLC
Date: 18-05-2022
DOI: 10.21203/RS.3.RS-1657073/V1
Abstract: Cloud failure is one of the critical issues since it can cost millions to the cloud service providers in addition to the loss of productivity being suffered by the industrial users using different cloud-based applications and services. As the cloud system grows larger, the process of failure prediction is still a challenge for both practitioners and academic researchers. In this study, we tackle the challenge of predicting job and task failure using the benchmarking Google Cluster Traces Dataset. We first propose a conceptual model to prepare, construct and evaluate five traditional machine learning algorithms and three variants of the latest deep learning algorithms for predicting job and task failures. We then perform a series of experiments on two datasets (1) Dataset A for the job failure prediction models and (2) Dataset B for the task failure prediction models. In the case of job failure prediction experiments, we observe that Extreme Gradient Boosting is the best performance with 94.35% accuracy with the F-Score score of 0.9310, 91.92% sensitivity, and 96.07% specificity. For Extreme Gradient Boosting, the disk space request and CPU request are the most important features in determining the outcome of the job prediction. In the case of task failure prediction, we observe that Decision Tree and Random Forest have achieved the highest 89.75% accuracy and 0.9145 for F-Score with 98% sensitivity and 78% specificity. The priority of the task is the most important feature for determining the task prediction outcome for both, the Decision Tree and Random Forest.
Publisher: Elsevier BV
Date: 06-2015
Publisher: Association for Computing Machinery (ACM)
Date: 07-12-2022
DOI: 10.1145/3530813
Abstract: Many scientific and practical areas have shown increasing interest in reaping the benefits of blockchain technology to empower software systems. However, the unique characteristics and requirements associated with Blockchain-based Software (BBS) systems raise new challenges across the development lifecycle that entail an extensive improvement of conventional software engineering. This article presents a systematic literature review of the state-of-the-art in BBS engineering research from the perspective of the software engineering discipline. We characterize BBS engineering based on the key aspects of theoretical foundations, processes, models , and roles . Based on these aspects, we present a rich repertoire of development tasks, design principles, models, roles, challenges, and resolution techniques. The focus and depth of this survey not only give software engineering practitioners and researchers a consolidated body of knowledge about current BBS development but also underpin a starting point for further research in this field.
Publisher: ACM
Date: 08-11-2010
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 2018
Publisher: Elsevier BV
Date: 07-2023
Publisher: arXiv
Date: 2021
Publisher: IEEE
Date: 10-2019
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 2020
Publisher: Springer International Publishing
Date: 2020
Publisher: Springer International Publishing
Date: 2017
Publisher: Springer International Publishing
Date: 2018
Publisher: Elsevier BV
Date: 03-2018
Publisher: SAGE Publications
Date: 18-06-2019
Abstract: Change is not a new concept in the Australian early childhood sector. However, the rate of change has significantly increased throughout the last decade, specifically with the introduction of the curriculum and quality frameworks, changes to regulations, and subsequent reviews (some particularly affecting the Victorian long day care sector). The rapid timeline of these reforms created challenges for early childhood professionals who needed to understand, interpret and translate multiple changes to their practice. This paper presents some key findings from a poststructural study involving 11 participants from the Victorian long day care sector. Foucauldian Discourse Analysis has been applied to explore how reform discourses shape and reshape the positioning and engagement of professionals within the reform process. These findings reveal how specific subject positions and discursive practices within available discourses of knowledge, teacher education and workplace can either challenge and/or support early childhood professionals in their ability to engage in reform.
Publisher: Elsevier BV
Date: 06-2013
Publisher: IGI Global
Date: 10-2017
Abstract: Micro learning becomes popular in online open learning and it is effective and helpful for learning in mobile environment. However, the delivery of open education resources (OERs) is scarcely supported by the current online systems. In this research, the authors introduce an approach to bridge the gap by providing adaptive micro open education resources for in idual learners to carry out learning activities in a short time span. They propose a framework for micro learning resource customization and a personalized learner model, which are supported by education data mining (EDM) and learning analysis (LA). A service-oriented architecture for Micro Learning as a Service (MLaaS) is designed to integrate all necessary procedures together as a complete Service for delivering micro OERs, providing a platform for resource sharing and exchanging in peer-to-peer learning environment. Working principle of a key step, namely the computational decision-making of micro OER adaptation, is also introduced.
Publisher: Elsevier BV
Date: 11-2021
Publisher: IEEE
Date: 07-2011
DOI: 10.1109/SCC.2011.29
Publisher: IEEE
Date: 12-2018
Publisher: EDP Sciences
Date: 26-04-2017
Publisher: MDPI AG
Date: 03-12-2021
DOI: 10.3390/FUTURETRANSP1030042
Abstract: In many big cities, train delays are among the most complained-about events by the public. Although various models have been proposed for train delay prediction, prior studies on both primary and secondary train delay prediction are limited in number. Recent advances in deep learning approaches and increasing availability of various data sources has created new opportunities for more efficient and accurate train delay prediction. In this study, we propose a hybrid deep learning solution by integrating long short-term memory (LSTM) and Critical Point Search (CPS). LSTM deals with long-term prediction tasks of trains’ running time and dwell time, while CPS uses predicted values with a nominal timetable to identify primary and secondary delays based on the delay causes, run-time delay, and dwell time delay. To validate the model and analyse its performance, we compare the standard LSTM with the proposed hybrid model. The results demonstrate that new variants outperform the standard LSTM, based on predicting time steps of dwell time feature. The experiment results also showed many irregularities of historical trends, which draws attention for further research.
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 2020
Publisher: Springer Singapore
Date: 2020
Publisher: Springer Science and Business Media LLC
Date: 19-11-2010
Publisher: Frontiers Media SA
Date: 28-06-2022
Abstract: A memristor is a non-linear element. The chaotic system constructed by it can improve its unpredictability and complexity. Parameter identification of a memristive chaotic system is the primary task to implement chaos control and synchronization. To identify the unknown parameters accurately and quickly, we introduce the Sine Pareto Sparrow Search Algorithm (SPSSA), a modified sparrow search algorithm (SSA). in this research. Firstly, we introduce the Pareto distribution to alter the scroungers’ location in the SSA. Secondly, we use a sine-cosine strategy to improve the producers’ position update. These measures can effectively accelerate the convergence speed and avoid local optimization. Thirdly, the SPSSA is used to identify the parameters of a memristive chaotic system. The proposed SPSSA exceeds the classic SSA, particle swarm optimization algorithm (PSO), and artificial bee colony algorithm (ABC) in simulations based on the five benchmark functions. The simulation results of parameter identification of a memristive chaotic system show that the method is feasible, and the algorithm has a fast convergence speed and high estimation accuracy.
Publisher: arXiv
Date: 2021
Publisher: American Astronomical Society
Date: 03-01-0003
Publisher: Inderscience Publishers
Date: 2018
Publisher: Emerald
Date: 10-02-2022
Abstract: Although proactive fault handling plans are widely spread, many unexpected data center outages still occurred. To rescue the jobs from faulty data centers, the authors propose a novel independent job rescheduling strategy for cloud resilience to reschedule the task from the faulty data center to other working-proper cloud data centers, by jointly considering job nature, timeline scenario and overall cloud performance. A job parsing system and a priority assignment system are developed to identify the eligible time slots for the jobs and prioritize the jobs, respectively. A dynamic job rescheduling algorithm is proposed. The simulation results show that our proposed approach has better cloud resiliency and load balancing performance than the HEFT series approaches. This paper contributes to the cloud resilience by developing a novel job prioritizing, task rescheduling and timeline allocation method when facing faults.
Publisher: Tsinghua University Press
Date: 04-2021
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 07-2012
DOI: 10.1109/TLT.2011.36
Publisher: IEEE
Date: 08-2016
DOI: 10.1109/CBD.2016.057
Publisher: EJournal Publishing
Date: 04-2018
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 06-2022
Publisher: Springer Berlin Heidelberg
Date: 2002
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 12-2022
Publisher: Elsevier BV
Date: 07-2018
DOI: 10.1016/J.CHEMOSPHERE.2018.03.080
Abstract: Agricultural and mining activities contribute to metal inputs in freshwater ecosystems around the world, which can in turn bioaccumulate in biota such as fish. Monitoring of metals loads in biota thus provides insight into the concentrations of bioavailable metals within the environment. Little research has been conducted on the potential of Australian freshwater fish for biomonitoring metals. Within the Fitzroy Basin of Central Queensland, a major agricultural and coal mining region, three commonly-encountered fish taxa were analysed for tissue metal loads. Arsenic concentrations in Nematalosa erebi and Melanotaenia splendida splendida tissue were elevated (above Food Standards Australia and New Zealand (FSANZ) guidelines), with highest concentrations in N. erebi liver tissue (up to 5.14 μg/g). Lead concentrations were above the FSANZ guidelines in all three fish taxa analysed, with highest concentrations in Hypseleotrid full-body tissue (up to 5.99 μg/g). Selenium in M. s. splendida and N. erebi tissue was positively correlated with total selenium in water (p < 0.05 r = 0.68 and 0.87 respectively). Environmental boron, selenium and nickel concentrations were positively correlated with N. erebi liver tissue metals. N. erebi hepatosomatic index was negatively correlated with dissolved arsenic, manganese, and total phosphorus (in water). The results highlight that M. s. splendida and N. erebi yield bioindicators which are responsive to environmental metals, and thus have potential for use in biomonitoring metals. The two species are also widespread along the east coast of Australia, there is thus a strong potential for applying the results to other regions within Australia.
Publisher: Springer Berlin Heidelberg
Date: 2004
Publisher: MDPI AG
Date: 28-04-2021
DOI: 10.3390/SMARTCITIES4020031
Abstract: The compliance of IoT platforms to quality is paramount to achieve users’ satisfaction. Currently, we do not have a comprehensive set of guidelines to appraise and select the most suitable IoT platform architectures that meet relevant criteria. This paper is a tentative response to this critical knowledge gap where we adopted the design science research approach to develop a novel evaluation framework. Our research, on the one hand, stimulates an unbiased competition among IoT platform providers and, on the other hand, establishes a solid foundation for IoT platform consumers to make informed decisions in this multiplicity. The application of the framework is illustrated in ex le scenarios. Moreover, lessons learned from applying design science research are shared.
Publisher: IEEE
Date: 12-2021
Publisher: Springer International Publishing
Date: 2019
Publisher: Springer Science and Business Media LLC
Date: 18-04-2020
Publisher: arXiv
Date: 2022
Publisher: EDP Sciences
Date: 21-04-2016
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 07-2017
Publisher: EJournal Publishing
Date: 2017
Publisher: IEEE
Date: 2009
Publisher: arXiv
Date: 2021
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 09-2023
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 15-11-2022
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 2022
Publisher: Oxford University Press (OUP)
Date: 27-05-2020
DOI: 10.1093/BIB/BBAA068
Abstract: In recent years, high-throughput experimental techniques have significantly enhanced the accuracy and coverage of protein–protein interaction identification, including human–pathogen protein–protein interactions (HP-PPIs). Despite this progress, experimental methods are, in general, expensive in terms of both time and labour costs, especially considering that there are enormous amounts of potential protein-interacting partners. Developing computational methods to predict interactions between human and bacteria pathogen has thus become critical and meaningful, in both facilitating the detection of interactions and mining incomplete interaction maps. In this paper, we present a systematic evaluation of machine learning-based computational methods for human–bacterium protein–protein interactions (HB-PPIs). We first reviewed a vast number of publicly available databases of HP-PPIs and then critically evaluate the availability of these databases. Benefitting from its well-structured nature, we subsequently preprocess the data and identified six bacterium pathogens that could be used to study bacterium subjects in which a human was the host. Additionally, we thoroughly reviewed the literature on ‘host–pathogen interactions’ whereby existing models were summarized that we used to jointly study the impact of different feature representation algorithms and evaluate the performance of existing machine learning computational models. Owing to the abundance of sequence information and the limited scale of other protein-related information, we adopted the primary protocol from the literature and dedicated our analysis to a comprehensive assessment of sequence information and machine learning models. A systematic evaluation of machine learning models and a wide range of feature representation algorithms based on sequence information are presented as a comparison survey towards the prediction performance evaluation of HB-PPIs.
Publisher: IEEE
Date: 06-2013
Publisher: Springer Science and Business Media LLC
Date: 20-01-2020
Publisher: IEEE
Date: 06-2017
DOI: 10.1109/SCC.2017.32
Publisher: IEEE
Date: 18-12-2022
Publisher: IEEE
Date: 05-2019
Publisher: IEEE
Date: 12-2021
Publisher: Elsevier BV
Date: 10-2012
DOI: 10.1016/J.IJMEDINF.2012.05.013
Abstract: Information and communications technology solutions have been introduced into the residential aged care system in order to improve the effectiveness and efficiency of aged care, however to date, the actual benefits have not been systematically analysed. The aim of this study was to identify the benefits of electronic health records (EHR) in residential aged care services and to examine how the benefits have been achieved. A qualitative interview study was conducted in nine residential aged care facilities (RACFs) belonging to three organisations in the Australian Capital Territory (ACT), New South Wales (NSW) and Queensland, Australia. A longitudinal investigation after the implementation of the aged care EHR systems was conducted at two data points: January 2009 to December 2009 and December 2010 to February 2011. Semi-structured interviews were conducted with 110 care staff members selected through theoretical s ling, representing all levels of care staff who worked in those facilities. Three categories of benefits were perceived by the care staff members according to who gain the benefits: the benefits to in idual care staff members, to residents and to the RACFs. The benefits to in idual care staff members include an improvement of documentation efficiency, information and knowledge growth as well as empowering the staff the benefits to residents are an improvement in the quality of in idual residents' health records, the higher quality of care and smoother communication between the residents and aged care staff the RACFs gain an increased ability to manage information and acquire funding, an increase in their ability to control the care quality and improvements in the working environment and educational benefits. Three factors leading to these benefits were examined: the nature of the aged care EHR systems in comparison with paper-based records the way the systems were used by the staff and one benefit that could lead to another. In this study, EHR systems were perceived to have substantial benefits for care staff, residents and the aged care organisations introducing the systems. The benefits were derived from the nature of the aged care EHR systems, staff members' continuous use of the systems, and one benefit led to the other.
Publisher: Springer Science and Business Media LLC
Date: 13-05-2022
DOI: 10.1007/S11265-022-01773-4
Abstract: Deep learning has been successfully applied in the recommender system. Low-dimensional dense embedding is typically used to represent the feature of users and items. To optimize the model, some models propose to dynamically search the embedding size based on the popularity of different users and items. However, these models ignore the interaction between the user and the item which will hinder the optimization of the features in embedding. In this paper, we propose Object-aware Policy Network (OPN) and introduces an object-aware method that is used for optimizing the features in embedding. We evaluate our model on the two real-world benchmark datasets. With less than 10% increased time consumption in all experiments, the results show that our proposed model is able to improve the performance of binary classification task by a margin of 0.30 and multiclass classification task by a margin of 0.35 compared to the best accuracies achieced by baselines on different datasests.
Publisher: Emerald
Date: 11-04-2008
DOI: 10.1108/14684520810879809
Abstract: This paper aims to explore the feasible mining and proper selection of QoS‐aware services for a P2P‐based business process enactment framework, and enhance the relevant workflow prototype. Design/methodology/approach – Through observing and analysing unpredictable dynamic changes that commonly exist in e‐service workflow, a set of QoS specifications and monitoring mechanisms in a P2P workflow framework is proposed. These specifications are an evolving extension of services' description with semantic web facilitators for P2P‐based e‐services. It has been demonstrated that the QoS‐OWL approach can be effectively used to describe and exploit e‐services, particularly in a decentralised environment. QoS‐OWL is also able to provide the deliberation of geographic information for e‐services, and facilitates the peers' effective cooperation and automates business processes. It is recommended that the approach be adopted in the dynamic online information system environment to increase efficiency and reduce costs in running e‐services. The QoS attributes discussed in this paper are relatively typical for benchmarking purposes, so the extension of the QoS metrics specifications and related protocols need to be discussed in future work. The authors propose an approach to dynamically selecting appropriate service‐oriented peers in a P2P network, where the composition of e‐services in a business process can be enhanced significantly. The approach is based on ontology and QoS perspectives, and the descriptions of services have rich semantic features in an attempt to make the service selection more intelligent and reliable. Therefore the proposal offers e‐service providers innovative initiatives to re‐engineer their business services.
Publisher: SAGE Publications
Date: 10-11-2022
DOI: 10.1177/07356331221115663
Abstract: Affective computing (AC) has been regarded as a relevant approach to identifying online learners’ mental states and predicting their learning performance. Previous research mainly used one single-source data set, typically learners’ facial expression, to compute learners’ affection. However, a single facial expression may represent different affections in various head poses. This study proposed a dual-source data approach to solve the problem. Facial expression and head pose are two typical data sources that can be captured from online learning videos. The current study collected a dual-source data set of facial expressions and head poses from an online learning class in a middle school. A deep learning neural network using AlexNet with an attention mechanism was developed to verify the syncretic effect on affective computing of the proposed dual-source fusion strategy. The results show that the dual-source fusion approach significantly outperforms the single-source approach based on the AC recognition accuracy between the two approaches (dual-source approach using Attention-AlexNet model 80.96% single-source approach, facial expression 76.65% and head pose 64.34%). This study contributes to the theoretical construction of the dual-source data fusion approach, and the empirical validation of the effect of the Attention-AlexNet neural network approach on affective computing in online learning contexts.
Publisher: MDPI AG
Date: 22-07-2022
DOI: 10.3390/APP12157369
Abstract: Service recommendation is key to improving users’ online experience. The development of the Internet has accelerated the creation of many services, and whether users can obtain good experiences among the massive number of services mainly depends on the quality of service recommendation. It is commonly believed that deep learning has excellent nonlinear fitting ability in capturing the complex interactions between users and items. The advantage in learning intricacy relationships enables deep learning to become an important technology for present service recommendation. Recently, it is noticed that linear models can perform almost as well as the state-of-the-art deep learning models, suggesting that capturing linear relationships between users and items is also very important for recommender systems. Therefore, numerous deep learning systems combined with linear models have been proposed. However, existing models are incapable of considering the size of the embedding. When the embedding dimension is too large, it leads to overfitting and thus influences the model’s ability to capture linear relationships. In this paper, a neural network based on two-layer matrix factorization and multi-layer perceptron—Two-layer Matrix factorization and Multi-layer perceptron Neural Network (TMMNN)—is proposed. To solve the problem of overfitting caused by an oversized embedding dimension, multi-size embedding technology has been integrated into the model. Matrix factorization and the multi-layer perceptron are placed in the upper and lower layers respectively, and they both receive embedding vectors dynamically adjusted for dimensions. In the upper layer, the matrix factorization is responsible for receiving the embedding of users and items, capturing linear relationships, and then yielding the generated new vectors as input to the multi-layer perceptron in the lower layer. Compared to other previously proposed models, the experimental results on the standard datasets MovieLens 20M and MovieLens Latest show that the TMMNN model is evidently better in terms of prediction accuracy.
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 2023
Publisher: IEEE
Date: 07-2011
DOI: 10.1109/SCC.2011.51
Publisher: SCITEPRESS - Science and Technology Publications
Date: 2018
Publisher: Springer International Publishing
Date: 2020
Publisher: American Medical Association (AMA)
Date: 20-08-2019
Publisher: IEEE
Date: 2005
DOI: 10.1109/SCC.2005.54
Publisher: Springer International Publishing
Date: 2018
Publisher: EDP Sciences
Date: 08-2015
Publisher: Elsevier BV
Date: 10-2022
Publisher: Springer International Publishing
Date: 2020
Publisher: Wiley
Date: 08-08-2017
DOI: 10.1002/CPE.4279
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 10-2022
Publisher: Elsevier BV
Date: 04-2022
Publisher: Elsevier BV
Date: 12-2022
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 12-2022
Publisher: IEEE
Date: 06-2013
Publisher: Frontiers Media SA
Date: 23-12-2022
Publisher: Wiley
Date: 28-03-2022
DOI: 10.1002/KPM.1703
Abstract: Knowledge is an intangible and vital resource that is an important source of competitive advantage however, the technologies that help create, store, and transfer knowledge are hindered by unrealistic expectations and ambiguity, and the measurement of knowledge‐sharing activities is both difficult and complex. Compounding this is the deficit of empirical studies on the factors that influence the knowledge‐sharing process. We endeavored to provide empirical evidence on these interactions using a survey developed from a prior extensive systematic literature review. The previously identified factors that were in the current study tested comprised (1) organizational culture, (2) formal processes, (3) top‐down support, (4) motivation, (5) clear strategy, and (6) quality of technology. In order, the most influential factors were organizational culture, top‐down support, motivation, and quality of technology. This study is a promising start to the exploration of the factors used in knowledge sharing and should be expanded to include new industries and contexts.
Publisher: Elsevier BV
Date: 2023
Publisher: Elsevier BV
Date: 06-2020
Publisher: Springer Berlin Heidelberg
Date: 2009
Publisher: EDP Sciences
Date: 07-2014
Publisher: Wiley
Date: 29-08-2017
DOI: 10.1111/NMO.13192
Abstract: Increases in mucosal immune cells have frequently been observed in irritable bowel syndrome (IBS) patients. However, this finding is not completely consistent between studies, possibly due to a combination of methodological variability, population differences and small s le sizes. We performed a meta-analysis of case-control studies that compared immune cell counts in colonic biopsies of IBS patients and controls. PubMed and Embase were searched in February 2017. Results were pooled using standardized mean difference (SMD) and were considered significant when zero was not within the 95% confidence interval (CI). Heterogeneity was assessed based on I Twenty-two studies on 706 IBS patients and 401 controls were included. Mast cells were increased in the rectosigmoid (SMD: 0.38 [95% CI: 0.06-0.71] P = .02) and descending colon (SMD: 1.69 [95% CI: 0.65-2.73] P = .001) of IBS patients. Increased mast cells were observed in both constipation (IBS-C) and diarrhea predominant IBS (IBS-D). CD3 Mast cells and CD3
Publisher: American Institute of Mathematical Sciences (AIMS)
Date: 2021
Publisher: Elsevier BV
Date: 05-2018
Publisher: ACM
Date: 04-02-2020
Publisher: Springer International Publishing
Date: 23-07-2021
Publisher: IEEE
Date: 07-2020
Publisher: ACM
Date: 23-05-2017
DOI: 10.1145/3129538
Publisher: IEEE
Date: 12-2022
DOI: 10.1109/ISPA-BDCLOUD-SOCIALCOM-SUSTAINCOM57177.2022.00105
Publisher: IEEE
Date: 06-2013
Publisher: MDPI AG
Date: 15-10-2020
DOI: 10.3390/SU12208522
Abstract: Collaborative problem solving (CPS) is an influential human behavior affecting working performance and well-being. Previous studies examined CPS behavior from the perspective of either social or cognitive dimensions, which leave a research gap from the interactive perspective. In addition, the traditional sequence analysis method failed to combine time sequences and sub-problem sequences together while analyzing behavioral patterns in CPS. This study proposes a developed schema for the multidimensional analysis of CPS. A combination sequential analysis approach that comprises time sequences and sub-problem sequences is also employed to explore CPS patterns. A total of 191 students were recruited and randomly grouped into 38 teams (four to six students per team) in the online collaborative discussion activity. Their discussion transcripts were coded while they conducted CPS, followed by the assessment of high- and low- performance groups according to the developed schema and sequential analysis. With the help of the new analysis method, the findings indicate that a deep exploratory discussion is generated from conflicting viewpoints, which promotes improved problem-solving outcomes and perceptions. In addition, evidence-based rationalization can motivate collaborative behavior effectively. The results demonstrated the potential power of automatic sequential analysis with multidimensional behavior and its ability to provide quantitative descriptions of group interactions in the investigated threaded discussions.
Publisher: Inderscience Publishers
Date: 2018
Publisher: Springer Science and Business Media LLC
Date: 25-07-2022
Publisher: IEEE
Date: 06-2015
Publisher: IEEE
Date: 08-10-2022
Publisher: Springer Singapore
Date: 2019
Publisher: MDPI AG
Date: 21-08-2022
DOI: 10.3390/APP12168350
Abstract: Generative Adversarial Network (GAN), deemed as a powerful deep-learning-based silver bullet for intelligent data generation, has been widely used in multi-disciplines. Furthermore, conditional GAN (CGAN) introduces artificial control information on the basis of GAN, which is more practical for many specific fields, though it is mostly used in domain transfer. Researchers have proposed numerous methods to tackle erse tasks by employing CGAN. It is now a timely and also critical point to review these achievements. We first give a brief introduction to the principle of CGAN, then focus on how to improve it to achieve better performance and how to evaluate such performance across the variants. Afterward, the main applications of CGAN in domain transfer are presented. Finally, as another major contribution, we also list the current problems and challenges of CGAN.
Publisher: MDPI AG
Date: 03-11-2021
DOI: 10.3390/MATH9212790
Abstract: At present, iris recognition has been widely used as a biometrics-based security enhancement technology. However, in some application scenarios where a long-distance camera is used, due to the limitations of equipment and environment, the collected iris images cannot achieve the ideal image quality for recognition. To solve this problem, we proposed a modified sparrow search algorithm (SSA) called chaotic pareto sparrow search algorithm (CPSSA) in this paper. First, fractional-order chaos is introduced to enhance the ersity of the population of sparrows. Second, we introduce the Pareto distribution to modify the positions of finders and scroungers in the SSA. These can not only ensure global convergence, but also effectively avoid the local optimum issue. Third, based on the traditional contrast limited adaptive histogram equalization (CLAHE) method, CPSSA is used to find the best clipping limit value to limit the contrast. The standard deviation, edge content, and entropy are introduced into the fitness function to evaluate the enhancement effect of the iris image. The clipping values vary with the pictures, which can produce a better enhancement effect. The simulation results based on the 12 benchmark functions show that the proposed CPSSA is superior to the traditional SSA, particle swarm optimization algorithm (PSO), and artificial bee colony algorithm (ABC). Finally, CPSSA is applied to enhance the long-distance iris images to demonstrate its robustness. Experiment results show that CPSSA is more efficient for practical engineering applications. It can significantly improve the image contrast, enrich the image details, and improve the accuracy of iris recognition.
Publisher: Wiley
Date: 05-2017
Publisher: Springer Science and Business Media LLC
Date: 22-02-2017
Publisher: American Association for the Advancement of Science (AAAS)
Date: 17-12-2021
Abstract: A dynamical model describes the negotiation process that led to the 2015 Paris Agreement on climate change.
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 06-2023
Publisher: Springer Science and Business Media LLC
Date: 02-01-2021
Publisher: Elsevier BV
Date: 07-2014
Publisher: IEEE
Date: 10-2017
Publisher: American Institute of Mathematical Sciences (AIMS)
Date: 2021
Abstract: style='text-indent:20px ' With the rise of the COVID-19 pandemic and its inevitable consequences in education, increased demand for robust online learning frameworks has occurred at all levels of the education system. Given the transformative power of Artificial Intelligence (AI) and machine learning algorithms, there have been determined attempts through the design and application of intelligent tools to overcome existing challenges in online learning platforms. Accordingly, educational providers and researchers are investigating and developing intelligent online learning environments which share greater commonalities with real-world classroom conditions in order to better meet learners' needs. However, short attention spans and the widespread use of smart devices and social media bring about new e-learning systems known as microlearning (ML). While there has been le research investigating ML and developing micro-content, pedagogical challenges and a general lack of alternative frameworks, theories and practices still exist. The present models have little to say about the connections between social interaction, including learner–content, learner–instructor and learner–learner communication. This has prompted us to investigate the complementary aspects of Computer-supported Collaborative Learning (CSCL) as an interactive learning model, along with an embedded ML module in the design and development of a comprehensive learning platform. The purpose of this study is to explore the pedagogical frameworks and challenges with reference to interaction and retention in online learning environments, as well as the theoretical and pedagogical foundations of ML and its applications. In addition, we delve into the theories and principles behind CSCL, the main elements in CSCL, identifying the issues and challenges to be faced in improving the efficacy of collaboration processes and outcomes. In short, we aim to synthesize how microlearning and CSCL can be applied as effective modules within a comprehensive online learning platform, thereby offering STEM educators a relevant roadmap towards progress that has yet to be offered in previous studies.
Publisher: IEEE
Date: 06-2017
Publisher: American Institute of Mathematical Sciences (AIMS)
Date: 2022
DOI: 10.3934/ACI.2022002
Abstract: abstract In obesity studies, several researchers have been applying machine learning tools to identify factors affecting human body weight. However, a proper review of strength, limitations and evaluation metrics of machine learning algorithms in obesity is lacking. This study reviews the status of application of machine learning algorithms in obesity studies and to identify strength and weaknesses of these methods. A scoping review of paper focusing on obesity was conducted. PubMed and Scopus databases were searched for the application of machine learning in obesity using different keywords. Only English papers in adult obesity between 2014 and 2019 were included. Also, only papers that focused on controllable factors (e.g., nutrition intake, dietary pattern and/or physical activity) were reviewed in depth. Papers on genetic or childhood obesity were excluded. Twenty reviewed papers used machine learning algorithms to identify the relationship between the contributing factors and obesity. Regression algorithms were widely applied. Other algorithms such as neural network, random forest and deep learning were less exploited. Limitations regarding data priori assumptions, overfitting and hyperparameter optimization were discussed. Performance metrics and validation techniques were identified. Machine learning applications are positively impacting obesity research. The nature and objective of a study and available data are key factors to consider in selecting the appropriate algorithms. The future research direction is to further explore and take advantage of the modern methods, i.e., neural network and deep learning, in obesity studies. /abstract
Publisher: Springer Science and Business Media LLC
Date: 25-09-2017
Publisher: Wiley
Date: 07-08-2018
DOI: 10.1002/CAE.22040
Publisher: Springer Science and Business Media LLC
Date: 23-10-2020
Publisher: IEEE
Date: 05-2016
Publisher: IEEE
Date: 12-2022
DOI: 10.1109/ISPA-BDCLOUD-SOCIALCOM-SUSTAINCOM57177.2022.00101
Publisher: Springer Science and Business Media LLC
Date: 2018
Publisher: Springer International Publishing
Date: 2022
Publisher: Springer International Publishing
Date: 2019
Publisher: IEEE
Date: 10-2013
DOI: 10.1109/SMC.2013.121
Publisher: Wiley
Date: 18-08-2020
DOI: 10.1002/ETT.4085
Abstract: The Internet of things (IoT), made up of a massive number of sensor devices interconnected, can be used for data exchange, intelligent identification, and management of interconnected “things.” IoT devices are proliferating and playing a crucial role in improving the living quality and living standard of the people. However, the real IoT is more vulnerable to attack by countless cyberattacks from the Internet, which may cause privacy data leakage, data t ering and also cause significant harm to society and in iduals. Network security is essential in the IoT system, and Web injection is one of the most severe security problems, especially the webshell. To develop a safe IoT system, in this article, we apply essential machine learning models to detect webshell to build secure solutions for IoT network. Future, ensemble methods including random forest (RF), extremely randomized trees (ET), and Voting are used to improve the performances of these machine learning models. We also discuss webshell detection in lightweight and heavyweight computing scenarios for different IoT environments. Extensive experiments have been conducted on these models to verify the validity of webshell intrusion. Simulation results show that RF and ET are suitable for lightweight IoT scenarios, and Voting method is effective for heavyweight IoT scenarios.
Publisher: IEEE
Date: 11-2014
DOI: 10.1109/CBD.2014.15
Publisher: Springer International Publishing
Date: 2016
Publisher: ACM
Date: 31-01-2017
Publisher: IEEE
Date: 2005
Publisher: IEEE Comput. Soc
Date: 1999
Publisher: IEEE
Date: 05-2012
Publisher: Springer Singapore
Date: 2016
Publisher: Springer Singapore
Date: 2016
Publisher: Elsevier BV
Date: 06-2022
Publisher: Emerald
Date: 07-2019
Publisher: Elsevier BV
Date: 03-2007
Publisher: Springer Science and Business Media LLC
Date: 06-2018
DOI: 10.1140/EPJC/S10052-018-5950-6
Abstract: The nuclear modification factors of $${\mathrm {J}/\psi }$$ J / ψ and $$\psi \text {(2S)}$$ ψ (2S) mesons are measured in $$\text {PbPb}$$ PbPb collisions at a centre-of-mass energy per nucleon pair of $$\sqrt{\smash [b]{s_{_{\text {NN}}}}} = 5.02\,\text {Te}\text {V} $$ s NN = 5.02 TeV . The analysis is based on $$\text {PbPb}$$ PbPb and $$\mathrm {p}\mathrm {p}$$ p p data s les collected by CMS at the LHC in 2015, corresponding to integrated luminosities of 464 $$\,\mu \mathrm {b}^{-1}$$ μ b - 1 and 28 $$\,\text {pb}^\text {-1}$$ pb -1 , respectively. The measurements are performed in the dimuon rapidity range of $$|y | 2.4$$ | y | 2.4 as a function of centrality, rapidity, and transverse momentum ( $$p_{\mathrm {T}}$$ p T ) from $$p_{\mathrm {T}} =3$$ p T = 3 $${\,\text {Ge}\text {V}/}\text {c}$$ GeV / c in the most forward region and up to 50 $${\,\text {Ge}\text {V}/}\text {c}$$ GeV / c . Both prompt and nonprompt (coming from b hadron decays) $${\mathrm {J}/\psi }$$ J / ψ mesons are observed to be increasingly suppressed with centrality, with a magnitude similar to the one observed at $$\sqrt{\smash [b]{s_{_{\text {NN}}}}} = 2.76\,\text {Te}\text {V} $$ s NN = 2.76 TeV for the two $${\mathrm {J}/\psi }$$ J / ψ meson components. No dependence on rapidity is observed for either prompt or nonprompt $${\mathrm {J}/\psi }$$ J / ψ mesons. An indication of a lower prompt $${\mathrm {J}/\psi }$$ J / ψ meson suppression at $$p_{\mathrm {T}} 25$$ p T 25 $${\,\text {Ge}\text {V}/}\text {c}$$ GeV / c is seen with respect to that observed at intermediate $$p_{\mathrm {T}}$$ p T . The prompt $$\psi \text {(2S)}$$ ψ (2S) meson yield is found to be more suppressed than that of the prompt $${\mathrm {J}/\psi }$$ J / ψ mesons in the entire $$p_{\mathrm {T}}$$ p T range.
Publisher: Elsevier BV
Date: 08-2022
Publisher: IGI Global
Date: 04-2020
Abstract: Cloud Computing (CC) is an emerging technology that can potentially revolutionise the application and delivery of IT. There has been little research, however, into the adoption of CC in Small and Medium-Sized Enterprises (SMEs). The indicators show that CC has been adopted very slowly. There is also a significant research gap in the investigation of the adoption of this innovation in SMEs. This article explores how the adoption of CC in Australia is related to technological factors, risk factors, and environmental factors. The study provides useful insights that can be utilised practically by SMEs, policymakers, and cloud vendors.
Publisher: Elsevier BV
Date: 08-2019
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 12-2022
Publisher: Springer US
Date: 2003
Publisher: ACM
Date: 21-10-2023
Publisher: IEEE
Date: 05-2015
Publisher: Springer Science and Business Media LLC
Date: 23-03-2019
Publisher: IEEE
Date: 24-05-2023
Publisher: IEEE
Date: 09-2019
Publisher: MDPI AG
Date: 31-07-2020
DOI: 10.3390/S20154291
Abstract: With smart city infrastructures growing, the Internet of Things (IoT) has been widely used in the intelligent transportation systems (ITS). The traditional adaptive traffic signal control method based on reinforcement learning (RL) has expanded from one intersection to multiple intersections. In this paper, we propose a multi-agent auto communication (MAAC) algorithm, which is an innovative adaptive global traffic light control method based on multi-agent reinforcement learning (MARL) and an auto communication protocol in edge computing architecture. The MAAC algorithm combines multi-agent auto communication protocol with MARL, allowing an agent to communicate the learned strategies with others for achieving global optimization in traffic signal control. In addition, we present a practicable edge computing architecture for industrial deployment on IoT, considering the limitations of the capabilities of network transmission bandwidth. We demonstrate that our algorithm outperforms other methods over 17% in experiments in a real traffic simulation environment.
Publisher: Springer New York
Date: 2013
Publisher: Springer Science and Business Media LLC
Date: 2018
Publisher: Elsevier BV
Date: 10-2023
Publisher: Elsevier BV
Date: 07-2013
Publisher: IEEE
Date: 11-2020
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 03-2018
Publisher: Elsevier BV
Date: 04-2007
Publisher: Elsevier BV
Date: 03-2014
Publisher: Springer International Publishing
Date: 2015
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 03-2022
Publisher: IEEE
Date: 07-2013
Publisher: IEEE
Date: 06-2017
Publisher: IEEE
Date: 11-2022
Publisher: Wiley
Date: 02-06-2020
DOI: 10.1002/CPE.5846
Publisher: University of Technology, Sydney
Date: 2018
DOI: 10.5130/ACIS2018.CT
Publisher: Wiley
Date: 16-01-2020
DOI: 10.1002/KPM.1622
Publisher: MDPI AG
Date: 21-07-2020
DOI: 10.3390/MICROORGANISMS8071085
Abstract: Microbial colonization of the gut early in life is crucial for the development of the immune and nervous systems, as well as influencing metabolism and weight gain. While early life exposure to antibiotics can cause microbial dysbiosis, prebiotics are non-digestible substrates that selectively promote the growth of beneficial gut microbiota. Our objective was to examine the effects of dietary prebiotic administration on the consequences of maternal antibiotic intake on offspring body weight, behavior, and neuroimmune responses later in life. Sprague-Dawley rat dams were given low-dose penicillin (LDP), prebiotic fiber (10% oligofructose), or both, during the third week of pregnancy and throughout lactation. Anxiety-like behavior, weight gain, body composition, cecal microbiota composition, and microglial responses to lipopolysaccharide (LPS) were assessed in offspring. Male and female prebiotic offspring had lower body weight compared to antibiotic offspring. Maternal antibiotic exposure resulted in lasting effects on select offspring microbiota including a lower relative abundance of Streptococcus, Lactococcus, and Eubacterium at 10 weeks of age. Maternal antibiotic use impaired microglial response to LPS in the hypothalamus compared to control, and this phenotype was reversed with prebiotic. Prebiotic fiber warrants further investigation as an adjunct to antibiotic use during pregnancy.
Publisher: Elsevier BV
Date: 2004
Publisher: IEEE
Date: 03-2008
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 07-2015
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 12-2022
Publisher: Springer Berlin Heidelberg
Date: 2015
Publisher: Springer Science and Business Media LLC
Date: 02-08-2020
Publisher: Springer Science and Business Media LLC
Date: 25-05-2014
Publisher: IEEE
Date: 07-2018
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 2019
Publisher: Hindawi Limited
Date: 11-10-2021
DOI: 10.1002/INT.22710
Publisher: MDPI AG
Date: 13-01-2018
DOI: 10.3390/JSAN7010004
Publisher: Wiley
Date: 19-07-2020
DOI: 10.1111/BJET.12997
Publisher: Elsevier BV
Date: 03-2023
Publisher: Wiley
Date: 31-08-2018
DOI: 10.1002/CPE.4960
Publisher: American Astronomical Society
Date: 31-08-2016
Publisher: Springer International Publishing
Date: 2021
Publisher: Elsevier BV
Date: 03-2018
Publisher: IEEE
Date: 05-2016
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 12-2022
Publisher: Springer International Publishing
Date: 2020
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 2022
Publisher: Elsevier BV
Date: 11-2023
Publisher: Springer Science and Business Media LLC
Date: 27-09-2022
DOI: 10.1038/S41575-022-00682-Y
Abstract: The management of visceral pain in patients with disorders of gut-brain interaction, notably irritable bowel syndrome, presents a considerable clinical challenge, with few available treatment options. Patients are increasingly using cannabis and cannabinoids to control abdominal pain. Cannabis acts on receptors of the endocannabinoid system, an endogenous system of lipid mediators that regulates gastrointestinal function and pain processing pathways in health and disease. The endocannabinoid system represents a logical molecular therapeutic target for the treatment of pain in irritable bowel syndrome. Here, we review the physiological and pathophysiological functions of the endocannabinoid system with a focus on the peripheral and central regulation of gastrointestinal function and visceral nociception. We address the use of cannabinoids in pain management, comparing them to other treatment modalities, including opioids and neuromodulators. Finally, we discuss emerging therapeutic candidates targeting the endocannabinoid system for the treatment of pain in irritable bowel syndrome.
Publisher: IEEE
Date: 07-2022
Publisher: Springer Berlin Heidelberg
Date: 2009
Publisher: IEEE
Date: 24-05-2023
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 2023
Publisher: University of Wollongong, SMART Infrastructure Facility
Date: 2014
Publisher: Springer Science and Business Media LLC
Date: 16-12-2022
DOI: 10.1007/S44196-022-00173-7
Abstract: Training convolutional neural networks (CNN) often require a large amount of data. However, for some biometric data, such as fingerprints and iris, it is often difficult to obtain a large amount of data due to privacy issues. Therefore, training the CNN model often suffers from specific problems, such as overfitting, low accuracy, poor generalization ability, etc. To solve them, we propose a novel image augmentation algorithm for small s le iris image in this article. It is based on a modified sparrow search algorithm (SSA) called chaotic Pareto sparrow search algorithm (CPSSA), combined with contrast limited adaptive histogram equalization (CLAHE). The CPSSA is used to search for a group of clipping limit values. Then a set of iris images that satisfies the constraint condition is produced by CLAHE. In the fitness function, cosine similarity is used to ensure that the generated images are in the same class as the original one. We select 200 categories of iris images from the CASIA-Iris-Thousand dataset and test the proposed augmentation method on four CNN models. The experimental results show that, compared with the some standard image augmentation methods such as flipping, mirroring and clipping, the accuracy and Equal Error Rate (EER)of the proposed method have been significantly improved. The accuracy and EER of the CNN models with the best recognition performance can reach 95.5 and 0.6809 respectively. This fully shows that the data augmentation method proposed in this paper is effective and quite simple to implement.
Publisher: Elsevier BV
Date: 07-2013
DOI: 10.1016/J.MARPOLBUL.2013.03.017
Abstract: We present the first evidence of ingestion of plastic by seabirds from the southern Great Barrier Reef (GBR), Australia. The occurrence of marine debris ingestion in the wedge-tailed shearwater, Ardenna pacifica, on Heron Island was the focus of this preliminary research. Our findings indicate that 21% of surveyed chicks are fed plastic fragments by their parents, having ingested 3.2 fragments on average. The most common colours of ingested plastic fragments were off/white (37.5%) and green (31.3%). Ingested fragments had a mean size of 10.17±4.55 mm and a mean weight of 0.056±0.051 g. Our results indicate that further research is critical to understanding the extent of ingestion, colour preferences, and what impacts ingestion may have on these and other seabird populations in the GBR.
Publisher: Elsevier BV
Date: 04-2018
Publisher: Elsevier BV
Date: 03-2019
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 03-2016
Publisher: IEEE
Date: 05-2021
Publisher: IEEE
Date: 09-2009
Publisher: IGI Global
Date: 10-2021
Abstract: Unexpected faults result in unscheduled cloud outage, which negatively affects the completion of workflow tasks in the cloud. This paper presents a novel PageRank-based fault handling strategy to rescue workflow tasks at the faulty data center. The proposed approach uses a holistic view and considers the task attributes, the timeline scenario, and the overall cloud performance. A priority assignment system is developed based on the modified PageRank algorithm to prioritise workflow tasks. A min-max normalization method is applied to select the target data center and match the timeline at this data center. Additionally, a dynamic PageRank-constrained task scheduling algorithm is proposed to generate the task scheduling solution. The simulation results show that the proposed approach can achieve better fault handling performance, measured by task resilience ratio, workflow resilience ratio, and workflow continuity ratio in both the traditional 3-replica and the image backup cloud environment.
Publisher: Elsevier BV
Date: 04-2016
Publisher: IEEE
Date: 11-2022
Publisher: IEEE
Date: 07-2022
Publisher: Springer Berlin Heidelberg
Date: 2006
DOI: 10.1007/11837862_38
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 2023
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 2023
Publisher: Edith Cowan University
Date: 2023
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 06-2021
Publisher: IEEE
Date: 07-2008
DOI: 10.1109/SCC.2008.15
Publisher: Springer International Publishing
Date: 2017
Publisher: IEEE
Date: 07-2018
Publisher: American Institute of Mathematical Sciences (AIMS)
Date: 2021
DOI: 10.3934/ACI.2021003
Abstract: abstract CNN models already play an important role in classification of crop and weed with high accuracy, more than 95% as reported in literature. However, to manually choose and fine-tune the deep learning models becomes laborious and indispensable in most traditional practices and research. Moreover, the classic objective functions are not thoroughly compatible with agricultural farming tasks as the corresponding models suffer from misclassifying crop to weed, often more likely than in other deep learning application domains. In this paper, we applied autonomous machine learning with a new objective function for crop and weed classification, achieving higher accuracy and lower crop killing rate (rate of identifying a crop as a weed). The experimental results show that our method outperforms state-of-the-art applications, for ex le, ResNet and VGG19. /abstract
Publisher: IEEE
Date: 2006
Publisher: IEEE
Date: 04-2017
Publisher: Informa UK Limited
Date: 10-2003
Publisher: IEEE
Date: 07-2023
Publisher: IEEE
Date: 07-2017
Publisher: Inderscience Publishers
Date: 2019
Publisher: EDP Sciences
Date: 10-2014
Publisher: MDPI AG
Date: 12-06-2020
DOI: 10.3390/S20123354
Abstract: Travel time prediction is critical for advanced traveler information systems (ATISs), which provides valuable information for enhancing the efficiency and effectiveness of the urban transportation systems. However, in the area of bus trips, existing studies have focused on directly using the structured data to predict travel time for a single bus trip. For state-of-the-art public transportation information systems, a bus journey generally has multiple bus trips. Additionally, due to the lack of study on data fusion, it is even inadequate for the development of underlying intelligent transportation systems. In this paper, we propose a novel framework for a hybrid data-driven travel time prediction model for bus journeys based on open data. We explore a convolutional long short-term memory (ConvLSTM) model with a self-attention mechanism that accurately predicts the running time of each segment of the trips and the waiting time at each station. The model is more robust to capture long-range dependence in time series data as well.
Publisher: Springer Nature Switzerland
Date: 2023
Publisher: Elsevier BV
Date: 10-2018
DOI: 10.1016/J.MARPOLBUL.2018.08.016
Abstract: Plastic ingestion by wedge-tailed shearwaters (WTS) nesting at near-shore and offshore sites along the east coast of Australia were investigated. Ingestion rates were at 20% in near-shore lavaged WTS, where the beaches were significantly more polluted, compared to 8% in birds at offshore sites. The material and colour of recovered plastics at offshore sites differed significantly between beach surveys and that ingested by seabirds in the same area. This pattern was not evident near-shore. Hence, in near-shore environments birds may feed locally and are influenced by nearby plastics, compared to birds offshore. The origins of marine debris between near-shore and offshore beaches differed with land-based sources unsurprisingly having more influence on near-shore sites. The findings of this study indicate the need for localised data to address and manage this pollutant, with nesting seabirds at greater risk in near-shore environments. A preliminary modified ecological quality objective for WTS is presented.
Publisher: Springer Berlin Heidelberg
Date: 2009
Publisher: ACM
Date: 16-01-2019
Publisher: Springer International Publishing
Date: 2018
Publisher: IEEE
Date: 10-2013
DOI: 10.1109/SKG.2013.19
Publisher: IEEE
Date: 08-2017
DOI: 10.1109/CBD.2017.24
Publisher: IEEE
Date: 2009
Publisher: Springer Science and Business Media LLC
Date: 19-09-2022
DOI: 10.1186/S13677-022-00327-0
Abstract: Cloud failure is one of the critical issues since it can cost millions of dollars to cloud service providers, in addition to the loss of productivity suffered by industrial users. Fault tolerance management is the key approach to address this issue, and failure prediction is one of the techniques to prevent the occurrence of a failure. One of the main challenges in performing failure prediction is to produce a highly accurate predictive model. Although some work on failure prediction models has been proposed, there is still a lack of a comprehensive evaluation of models based on different types of machine learning algorithms. Therefore, in this paper, we propose a comprehensive comparison and model evaluation for predictive models for job and task failure. These models are built and trained using five traditional machine learning algorithms and three variants of deep learning algorithms. We use a benchmark dataset, called Google Cloud Traces, for training and testing the models. We evaluated the performance of models using multiple metrics and determined their important features, as well as measured their scalability. Our analysis resulted in the following findings. Firstly, in the case of job failure prediction, we found that Extreme Gradient Boosting produces the best model where the disk space request and CPU request are the most important features that influence the prediction. Second, for task failure prediction, we found that Decision Tree and Random Forest produce the best models where the priority of the task is the most important feature for both models. Our scalability analysis has determined that the Logistic Regression model is the most scalable as compared to others.
Publisher: Wiley
Date: 28-09-2015
DOI: 10.1002/CAE.21696
Publisher: MDPI AG
Date: 06-08-2022
DOI: 10.3390/APP12157889
Abstract: In order to solve the education problems caused by teachers and students’ unavoidable absence in school during the COVID-19 pandemic, a series of online education activities were carried out by Nanjing University of Posts and Telecommunication in early March. To explore students and teachers’ degree of satisfaction with distance education, this paper investigates multiple dimensions such as students’ degree of satisfaction with teachers, the regional living standard, educational resources and negative factors that reduce the students’ degree of satisfaction, etc. Furthermore, the attitude of teachers toward distance education may be partially reflected by the arrangement of live classes. All of the statistics are analyzed by comparing the distribution of votes. The results show that the degree of satisfaction by students and teachers with distance education is generally high but varies in areas with different living standards. In addition, we find that students are more sensitive to the lack of a learning atmosphere.
Publisher: Springer Science and Business Media LLC
Date: 04-02-2020
Publisher: Inderscience Publishers
Date: 2013
Publisher: Elsevier BV
Date: 11-2021
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 03-2022
Publisher: Springer International Publishing
Date: 2020
Publisher: Springer Nature Switzerland
Date: 2023
Publisher: IEEE
Date: 2004
Publisher: IEEE
Date: 18-06-2023
Publisher: Springer International Publishing
Date: 2019
Publisher: The International Academic Forum(IAFOR)
Date: 02-2023
Publisher: arXiv
Date: 2020
Publisher: IEEE
Date: 12-2018
Publisher: Cold Spring Harbor Laboratory
Date: 04-04-2021
DOI: 10.1101/2021.03.28.21254501
Abstract: Tobacco smoking is one of the most dangerous risk behaviors, leading to many adverse human health consequences. The aims of this study is to estimate the prevalence of tobacco smoking and related factor among adolescents aged 13–17 years in Vietnam. The data were from two rounds of the Vietnam Global School-based Student Health Survey (GSHS) that is the nationally representative survey conducted in 2013 and 2019. The logistic regressions were carried out to identify factors associated with tobacco smoking among study participants. We found the prevalence of current smoking (water pipe and cigarettes) reduced significantly from 5.4% (95% CI: 4.0–7.2) in 2013 to 2.8% (95% CI: 2.2–3.6) in 2019. In 2019, 2.6% of students used electronic cigarette products in the last 30 days. Factors associated with higher odds of current smoking status included study year, gender, parental monitoring, loneliness, suicide attempt, sexual intercourse, truancy, alcohol drinking. Similar patterns were found in e-cigarette use. Smoking among adolescents in Vietnam reduced between 2013 and 2019. Further follow-up studies are needed to confirm the causal factors of the reduction and e-cigarettes use.
Publisher: EDP Sciences
Date: 2015
Publisher: Springer Berlin Heidelberg
Date: 2009
Publisher: IEEE
Date: 06-2014
DOI: 10.1109/SCC.2014.36
Publisher: IEEE
Date: 06-2011
Publisher: Wiley
Date: 27-07-2015
DOI: 10.1002/CPE.3589
Publisher: IEEE
Date: 05-2018
Publisher: IEEE
Date: 12-2019
Publisher: Elsevier BV
Date: 05-2017
Publisher: IEEE
Date: 10-2013
DOI: 10.1109/SMC.2013.178
Publisher: Springer Singapore
Date: 27-09-2017
Publisher: Elsevier BV
Date: 07-2012
Publisher: MDPI AG
Date: 26-05-2017
DOI: 10.3390/SU9060898
Publisher: IEEE
Date: 07-2020
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 03-2022
Publisher: Association for Information Systems
Date: 2017
DOI: 10.17705/1CAIS.04018
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 2020
Publisher: IEEE
Date: 06-2014
DOI: 10.1109/ICWS.2014.36
Publisher: Springer Science and Business Media LLC
Date: 18-02-2017
Publisher: IEEE
Date: 05-2018
Publisher: IEEE
Date: 10-2008
Publisher: IEEE
Date: 18-06-2023
Publisher: MDPI AG
Date: 16-12-2022
DOI: 10.3390/S22249913
Abstract: Iris localization in non-cooperative environments is challenging and essential for accurate iris recognition. Motivated by the traditional iris-localization algorithm and the robustness of the YOLO model, we propose a novel iris-localization algorithm. First, we design a novel iris detector with a modified you only look once v4 (YOLO v4) model. We can approximate the position of the pupil center. Then, we use a modified integro-differential operator to precisely locate the iris inner and outer boundaries. Experiment results show that iris-detection accuracy can reach 99.83% with this modified YOLO v4 model, which is higher than that of a traditional YOLO v4 model. The accuracy in locating the inner and outer boundary of the iris without glasses can reach 97.72% at a short distance and 98.32% at a long distance. The locating accuracy with glasses can obtained at 93.91% and 84%, respectively. It is much higher than the traditional Daugman’s algorithm. Extensive experiments conducted on multiple datasets demonstrate the effectiveness and robustness of our method for iris localization in non-cooperative environments.
Publisher: IEEE
Date: 2009
Publisher: IEEE
Date: 07-2011
Publisher: IEEE
Date: 10-2019
Publisher: Inderscience Publishers
Date: 2020
Publisher: IEEE
Date: 05-12-2021
Publisher: Elsevier BV
Date: 12-2022
Publisher: Maximum Academic Press
Date: 2023
Publisher: European Alliance for Innovation n.o.
Date: 09-08-2016
Publisher: Chapman and Hall/CRC
Date: 19-05-2017
Publisher: Elsevier BV
Date: 10-2014
DOI: 10.1016/J.MARPOLBUL.2014.07.060
Abstract: Many seabirds are impacted by marine debris through its presence in foraging and nesting areas. To determine the extent of this problem, marine debris use in nest material of the brown booby (Sula leucogaster) in the Great Barrier Reef, Australia, was investigated. Nine cays were examined using beach and nest surveys. On average, four marine debris items were found per nest (n=96) with 58.3% of surveyed nests containing marine debris. The source of marine debris in nests and transects were primarily oceanic. Hard plastic items dominated both nest (56.8%) and surveyed beaches (72.8%), however only two item types were significantly correlated between these surveys. Nest surveys indicated higher levels of black and green items compared to beach transects. This selectivity for colours and items suggest these nests are not good indicators of environmental loads. This is the first study to examine S. leucogaster nests for marine debris in this location.
Publisher: Elsevier BV
Date: 03-2023
Publisher: IEEE
Date: 06-2015
Publisher: ACM
Date: 04-08-2023
Publisher: Springer Nature Switzerland
Date: 2023
Publisher: IEEE
Date: 07-2014
Publisher: EDP Sciences
Date: 28-04-2017
Publisher: Springer International Publishing
Date: 2015
Publisher: Journal of Modern Power Systems and Clean Energy
Date: 2022
Publisher: IEEE
Date: 04-2007
Publisher: IEEE
Date: 06-2016
Publisher: IEEE
Date: 06-2017
Publisher: IEEE
Date: 06-2011
Publisher: Wiley
Date: 15-02-2019
DOI: 10.1002/RRA.3410
Publisher: Kluwer Academic Publishers
Date: 2003
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 08-2022
Publisher: Inderscience Publishers
Date: 2016
Publisher: Hindawi Limited
Date: 10-07-2023
DOI: 10.1155/2023/1444938
Abstract: In the realm of high-dimensional data analysis, numerous fields stand to benefit from its applications, including the biological and medical sectors that are crucial for computer-aided disease diagnosis and prediction systems. However, the presence of a significant number of redundant or irrelevant features can adversely affect system accuracy and real-time diagnosis efficiency. To mitigate this issue, this paper proposes two innovative wrapper feature selection (FS) methods that integrate the ant colony optimization (ACO) algorithm and hybrid rice optimization (HRO). HRO is a recently developed metaheuristic that mimics the breeding process of the three-line hybrid rice, which is yet to be thoroughly explored in the context of solving high-dimensional FS problems. In the first hybridization, ACO is embedded as an evolutionary operator within HRO and updated alternately with it. In the second form of hybridization, two subpopulations evolve independently, sharing the local search results to assist in idual updating. In the initial stage preceding hybridization, a problem-oriented heuristic factor assignment strategy based on the importance of the knee point feature is introduced to enhance the global search capability of ACO in identifying the smallest and most representative features. The performance of the proposed algorithms is evaluated on fourteen high-dimensional biomedical datasets and compared with other recently advanced FS methods. Experimental results suggest that the proposed methods are efficient and computationally robust, exhibiting superior performance compared to the other algorithms involved in this study.
Publisher: IEEE
Date: 12-2009
Publisher: IEEE
Date: 09-2019
Publisher: Springer Singapore
Date: 27-09-2018
Publisher: IEEE
Date: 06-2013
Publisher: IEEE
Date: 06-2013
Publisher: Elsevier BV
Date: 02-2023
Publisher: Springer Science and Business Media LLC
Date: 11-07-2020
Start Date: 2018
End Date: 2020
Funder: Australian Research Council
View Funded ActivityStart Date: 07-2023
End Date: 07-2026
Amount: $570,943.00
Funder: Australian Research Council
View Funded ActivityStart Date: 02-2018
End Date: 02-2022
Amount: $362,666.00
Funder: Australian Research Council
View Funded Activity