Thuan Pham - Academia.edu (original) (raw)
Papers by Thuan Pham
Ho Chi Minh City Publishing House of Economics, 2017
Project work is a progressive teaching method which meets requirements of modern educational syst... more Project work is a progressive teaching method which meets requirements of modern educational systems. This article presents findings of a case study on how project work benefits students in an English for Specific Purposes (ESP) class in developing students’ language skills and group work skills. In the article, theoretical foundations for project work are reviewed and the implementations of a project work are applied. The study was conducted within 4 weeks in a provincial university in the North of Vietnam. The participants were 26 third-year students majoring in chemistry. Observation and interviews were applied as the instruments to collect the data. The results revealed that the use of project work is effective in teaching English for ESP classes. From theory to practice, the article suggests a pedagogic possibility for practitioners to apply project work in language learning.
Proceedings Eighteenth Annual International Computer Software and Applications Conference (COMPSAC 94)
Frameworks such as “software-buses” enable the integration of different software components into ... more Frameworks such as “software-buses” enable the integration of different software components into a coherent suite of applications. However, the communication and interoperation between these software components are limited by the boundary of the framework. We describe the software bus transceiver as a translation protocol and supporting architecture to facilitate communication and interoperation of software components from different frameworks. This paper
Journal of English Language Teaching and Applied Linguistics, 2021
Among the attributors to language learners' success, attitude and motivation are widely recog... more Among the attributors to language learners' success, attitude and motivation are widely recognized as two important attributors. This article aims to review and discuss attitude and motivation in language learning. More specially, the paper sheds light on how these two contributors are conceptualized by scholars in the literature and the configuration of the two elements in language learning. The discussions are expected to help language educators better understand the two concepts.
2022 IEEE Green Technologies Conference (GreenTech)
Power flow analysis is used to evaluate the flow of electricity in the power system network. Powe... more Power flow analysis is used to evaluate the flow of electricity in the power system network. Power flow calculation is used to determine the steady-state variables of the system, such as the voltage magnitude /phase angle of each bus and the active/reactive power flow on each branch. The DC power flow model is a popular linear power flow model that is widely used in the power industry. Although it is fast and robust, it may lead to inaccurate line flow results for some critical transmission lines. This drawback can be partially addressed by data-driven methods that take advantage of historical grid profiles. In this paper, a neural network (NN) model is trained to predict power flow results using historical power system data. Although the training process may take time, once trained, it is very fast to estimate line flows. A comprehensive performance analysis between the proposed NNbased power flow model and the traditional DC power flow model is conducted. It can be concluded that the proposed NN-based power flow model can find solutions quickly and more accurately than DC power flow model.
My thanks to these individuals, who have dedicated assistance, motivation, and encouragement to m... more My thanks to these individuals, who have dedicated assistance, motivation, and encouragement to me during my PhD research. I would not be able to achieve the current study without their support. In particular, I would like to express my thanks and sincere appreciation to: Associate Professor Xiaohui Tao, my principal supervisor, for his patience and motivation to support my PhD study. With immense knowledge, his critical analysis, quick response and guidance assisted me to build up my research foundation and to complete my research. My thesis would not have been achievable without his assistance. Associate Professor Ji Zhang, my associate supervisor, for his scientific advice and useful remarks for my PhD study. Professor Jianming Yong, my associate supervisor, to whom I am grateful for plentiful comments of my research and opportunities in teaching as well. Dr Barbara Harmes, who has assisted me in proofreading all the journal articles as well as the dissertation. My parents and friends, who have always encouraged me throughout the journey of my PhD.
2018 5th International Conference on Behavioral, Economic, and Socio-Cultural Computing (BESC), 2018
The state of relationships between actors ion the internet is constantly changing and fluctuating... more The state of relationships between actors ion the internet is constantly changing and fluctuating to a social system of constant shocks. Link prediction, community detection, recommendation systems were built from around this fundamentally unstable system. Stable relational states - which hold important and latent deterministic knowledge have often been overlooked in this regard. In this paper, we propose a novel method of quantifying and detecting stability in the relationship between a given pair of actors. Our main algorithm (MVVA) establishes relational stability from a multivariate, autoregressive link feature dynamics perspective. Under our experimental design, we provide another built-in module based on the Hamiltonian Monte Carlo technique to provide a comprehensive cross-validation on the performance and accuracy of our proposed MVVA model.
Information networks are pivotal to the operational utility of key industries like medical, finan... more Information networks are pivotal to the operational utility of key industries like medical, finance, governments, etc. However, applications in this area are not adequate in representing relationships between nodes [34]. Trending graph learning methodologies [9, 16] like Graph Convolutional Networks (GCNs) [6] lack both representational power and accuracy to perform abstract computational tasks like prediction, classification, recommendation, etc. on real-time social networks. Furthermore, most such approaches known to date rely on learning temporal adjacency matrices to describe shallow attributes [9, 16] like word co-occurance PMI [3] changes [6] and are unable to capture complex evolving entity relationships in real life for applications like event prediction, link prediction, topic tracking, etc. [34]. Importantly, such models ignore knowledge information geometry [1, 24, 32] completely, and sacrifices fidelity to speed of convergence. To address these challenges, a novel Relati...
Knowledge-Based Systems, 2022
In recent years, the means of disease diagnosis and treatment have been improved remarkably, alon... more In recent years, the means of disease diagnosis and treatment have been improved remarkably, along with the continuous development of technology and science. Researchers have spent tremendous time and effort to build models, with an aim to assist medical practitioners in decision-making support. One of the greatest challenges remains is how to identify the connection between different diseases. This study aims to discover the relationship between diseases and symptoms and predict potential diseases for patients. Considering it a multi-label classification problem, the study proposed a new multi-disease prediction model learning from NHANES, an extensive health related dataset, and MEDLINE, a corpus with medical domain knowledge. A heterogeneous information graph is firstly constructed and then populated using medical domain knowledge discovered from MEDLINE. The knowledge graph is analysed for clarification of the relevancy within nodes in positive or negative space, helping to access to the correlation amongst multiple diseases and their symptoms. A multi-label disease prediction model is then developed adopting the medical domain knowledge graph. Empirical experiments are conducted to evaluate the proposed model. The experimental results show that the performance of the proposed model surpassed state-of-the-art related works representing the mainstreams of multi-label classification. This study contributes with a novel model for multi-disease prediction to the medical community and represents a new endeavour on multi-label classification using knowledge graphs
2018 5th International Conference on Behavioral, Economic, and Socio-Cultural Computing (BESC), 2018
In the medical domain, there exists a large volume of data from multiple sources such as electron... more In the medical domain, there exists a large volume of data from multiple sources such as electronic health records, general health examination results and surveys. The data contain useful information reflecting people's health and provides great opportunities for studies to improve the quality of healthcare. However, how to mine these data effectively and efficiently still remains a critical challenge. In this paper, we propose an innovative classification model for knowledge discovery from patients' personal health repositories. By based on analytics of massive data in National Health and Nutrition Examination Survey, the study builds a classification model to classify patients' health status and reveal the specific disease potentially suffered by the patient. This paper makes significant contributions to the advancement of knowledge in data mining with an innovative classification model specifically crafted for domain-based data. Moreover, this research contributes to the healthcare community by providing a deep understanding of people's health with accessibility to the patterns in various observations.
Journal of Data Intelligence, 2021
Event prediction is a very important task in numerous applications of interest like fintech, medi... more Event prediction is a very important task in numerous applications of interest like fintech, medical, security, etc. However, event prediction is a highly complex task because it is challenging to classify, contains temporally changing themes of discussion and heavy topic drifts. In this research, we present a novel approach which leverages on the RFT framework developed in \cite{tan2020discovering}. This study addresses the challenge of accurately representing relational features in observed complex social communication behavior for the event prediction task; which recent graph learning methodologies are struggling with. The concept here, is to firstly learn the turbulent patterns of relational state transitions between actors preceeding an event and then secondly, to evolve these profiles temporally, in the event prediction process. The event prediction model which leverages on the RFT framework discovers, identifies and adaptively ranks relational turbulence as likelihood predict...
Health Information Science and Systems, 2020
Applying Pearson correlation and semantic relations in building a heterogeneous information graph... more Applying Pearson correlation and semantic relations in building a heterogeneous information graph (HIG) to develop a classification model has achieved a notable performance in improving the accuracy of predicting the status of health risks. In this study, the approach that was used, integrated knowledge of the medical domain as well as taking advantage of applying Pearson correlation and semantic relations in building a classification model for diagnosis. The research mined knowledge which was extracted from titles and abstracts of MEDLINE to discover how to assess the links between objects relating to medical concepts. A knowledge-base HIG model then was developed for the prediction of a patient's health status. The results of the experiment showed that the knowledge-base model was superior to the baseline model and has demonstrated that the knowledge-base could help improve the performance of the classification model. The contribution of this study has been to provide a framework for applying a knowledge-base in the classification model which helps these models achieve the best performance of predictions. This study has also contributed a model to medical practice to help practitioners become more confident in making final decisions in diagnosing illness. Moreover, this study affirmed that biomedical literature could assist in building a classification model. This contribution will be advantageous for future researchers in mining the knowledge-base to develop different kinds of classification models.
Computer Science Review, 2020
Information networks today play an important, fundamental role in regulating real life activities... more Information networks today play an important, fundamental role in regulating real life activities. However, many methods developed on this framework lack the capacity to adequately represent sophistication contained within the information it carries. As a result, they suffer from problems such as inaccuracies, reliability and performance. We define relational intelligence as a combination of affective (
World Wide Web, 2020
Nowadays classification models have been widely adopted in healthcare, aiming at supporting pract... more Nowadays classification models have been widely adopted in healthcare, aiming at supporting practitioners for disease diagnosis and human error reduction. The challenge is utilising effective methods to mine real-world data in the medical domain, as many different models have been proposed with varying results. A large number of researchers focus on the diversity problem of real-time data sets in classification models. Some previous works developed methods comprising of homogeneous graphs for knowledge representation and then knowledge discovery. However, such approaches are weak in discovering different relationships among elements. In this paper, we propose an innovative classification model for knowledge discovery from patients' personal health repositories. The model discovers medical domain knowledge from the massive data in the National Health and Nutrition Examination Survey (NHANES). The knowledge is conceptualised in a heterogeneous knowledge graph. On the basis of the model, an innovative method is developed to help uncover potential diseases suffered by people and, furthermore, to classify patients' health risk. The proposed model is evaluated by comparison to a baseline model also built on the NHANES data set in an empirical experiment. The performance of proposed model is promising. The paper makes significant contributions to the advancement of knowledge in data mining with an innovative classification model specifically crafted for domain-based data. In addition, by accessing the
Brain Informatics, 2019
Mining data on a knowledge level can help to achieve a higher performance of a decision support s... more Mining data on a knowledge level can help to achieve a higher performance of a decision support system. This study built a knowledge graph based on MEDLINE that has a large number of articles in the medical domain. MEDLINE uses Medical Subject Headings (MeSH) for document index. Based on MeSH, articles are extracted from the MEDLINE correspondent to medical subjects. Using the MeSH as the backbone of knowledge base, the MEDLINE articles were used to generate instances which helped to populate the knowledge base. This approach facilitated the creation of a knowledge graph that was capable of discovering the hidden knowledge among concepts of MeSH. The knowledge graph had a significant effect on improving the quality of healthcare. The contribution of the research is on a framework for building knowledge bases. Moreover, the approach provided an essential source at the knowledge level for researchers in healthcare.
Lecture Notes in Computer Science, 1994
We describe solutions to practical database problems encountered during the implementation of a p... more We describe solutions to practical database problems encountered during the implementation of a prototype Physician's Workstation (PWS) at Hewlett-Packard Laboratories:(i) the integration of legacy data repositories using an object-oriented ...
Vision Research, 2008
The effect of emotion on visual awareness is largely unknown. Pairs of natural images were presen... more The effect of emotion on visual awareness is largely unknown. Pairs of natural images were presented side by side on a screen in a binocular rivalry setup. The amount of time that each image of a pair dominated perception was computed. Our results showed: (A) A main effect of arousal: Dominance durations of the more arousing picture of iso-valence pairs were longer. (B) No effect of valence: Dominance durations of pleasant and unpleasant pictures of isoarousal pairs were similar. (C) An interaction between arousal and valence: The more pleasant picture of iso-arousal pairs of low arousal level dominated conscious perception. The less pleasant picture of iso-arousal pairs of high arousal level dominated conscious perception. Our findings suggest that the emotional content of a stimulus affects the extent to which it dominates awareness. While arousal and valence interactively affect access to awareness, only arousal exerts an independent control of such access.
Ophthalmic Epidemiology, 2009
To examine the associations among iris, skin, or hair color, and skin sun sensitivity and the 10-... more To examine the associations among iris, skin, or hair color, and skin sun sensitivity and the 10-year incidence of age-related maculopathy (ARM). The Blue Mountains Eye Study (BMES) recruited 3654 participants aged 49+ years at baseline (1992-1994, 82.4% participation rate). Re-examinations of 2335 participants (75.1% of survivors) were done after 5 years (1997-1999) and 1952 (76.5% of survivors) after 10 years (2002-2004). Retinal photographs were graded using the Wisconsin ARM Grading System and incident ARM confirmed using the side-by-side grading method. Iris, skin, and hair color, and sun-related skin damage were assessed and skin sun-sensitivity questions were asked at baseline. Ten-year ARM incidence was calculated using Kaplan Meier methods and discrete logistic models were used to assess associations after adjusting for age, sex, and smoking. After adjustment, no significant associations were found between iris or hair color and either late- or early-incident ARM. Compared to persons with fair skin, those with very fair skin had an increased risk of developing geographic atrophy (multivariate adjusted risk ratio, RR = 7.6; 95% confidence interval, CI = 3.0-19.6). In contrast, compared to persons with average skin sun sensitivity, persons who reported that their skin would usually burn and tan with difficulty had a reduced risk of neovascular ARM (RR = 0.2, 95% CI = 0.0-0.7). Sun-related skin damage was not associated with late or early ARM. In this older cohort, we did not find a consistent pattern of association between sunlight-related factors and ARM incidence, except that persons with very fair skin might have an increased risk of geographic atrophy, consistent with our 5-year incidence data. The protective association between skin sensitivity to sun damage and neovascular ARM could have be the result of confounding by sun-avoidance behavior among persons sensitive to sunburn.
Ho Chi Minh City Publishing House of Economics, 2017
Project work is a progressive teaching method which meets requirements of modern educational syst... more Project work is a progressive teaching method which meets requirements of modern educational systems. This article presents findings of a case study on how project work benefits students in an English for Specific Purposes (ESP) class in developing students’ language skills and group work skills. In the article, theoretical foundations for project work are reviewed and the implementations of a project work are applied. The study was conducted within 4 weeks in a provincial university in the North of Vietnam. The participants were 26 third-year students majoring in chemistry. Observation and interviews were applied as the instruments to collect the data. The results revealed that the use of project work is effective in teaching English for ESP classes. From theory to practice, the article suggests a pedagogic possibility for practitioners to apply project work in language learning.
Proceedings Eighteenth Annual International Computer Software and Applications Conference (COMPSAC 94)
Frameworks such as “software-buses” enable the integration of different software components into ... more Frameworks such as “software-buses” enable the integration of different software components into a coherent suite of applications. However, the communication and interoperation between these software components are limited by the boundary of the framework. We describe the software bus transceiver as a translation protocol and supporting architecture to facilitate communication and interoperation of software components from different frameworks. This paper
Journal of English Language Teaching and Applied Linguistics, 2021
Among the attributors to language learners' success, attitude and motivation are widely recog... more Among the attributors to language learners' success, attitude and motivation are widely recognized as two important attributors. This article aims to review and discuss attitude and motivation in language learning. More specially, the paper sheds light on how these two contributors are conceptualized by scholars in the literature and the configuration of the two elements in language learning. The discussions are expected to help language educators better understand the two concepts.
2022 IEEE Green Technologies Conference (GreenTech)
Power flow analysis is used to evaluate the flow of electricity in the power system network. Powe... more Power flow analysis is used to evaluate the flow of electricity in the power system network. Power flow calculation is used to determine the steady-state variables of the system, such as the voltage magnitude /phase angle of each bus and the active/reactive power flow on each branch. The DC power flow model is a popular linear power flow model that is widely used in the power industry. Although it is fast and robust, it may lead to inaccurate line flow results for some critical transmission lines. This drawback can be partially addressed by data-driven methods that take advantage of historical grid profiles. In this paper, a neural network (NN) model is trained to predict power flow results using historical power system data. Although the training process may take time, once trained, it is very fast to estimate line flows. A comprehensive performance analysis between the proposed NNbased power flow model and the traditional DC power flow model is conducted. It can be concluded that the proposed NN-based power flow model can find solutions quickly and more accurately than DC power flow model.
My thanks to these individuals, who have dedicated assistance, motivation, and encouragement to m... more My thanks to these individuals, who have dedicated assistance, motivation, and encouragement to me during my PhD research. I would not be able to achieve the current study without their support. In particular, I would like to express my thanks and sincere appreciation to: Associate Professor Xiaohui Tao, my principal supervisor, for his patience and motivation to support my PhD study. With immense knowledge, his critical analysis, quick response and guidance assisted me to build up my research foundation and to complete my research. My thesis would not have been achievable without his assistance. Associate Professor Ji Zhang, my associate supervisor, for his scientific advice and useful remarks for my PhD study. Professor Jianming Yong, my associate supervisor, to whom I am grateful for plentiful comments of my research and opportunities in teaching as well. Dr Barbara Harmes, who has assisted me in proofreading all the journal articles as well as the dissertation. My parents and friends, who have always encouraged me throughout the journey of my PhD.
2018 5th International Conference on Behavioral, Economic, and Socio-Cultural Computing (BESC), 2018
The state of relationships between actors ion the internet is constantly changing and fluctuating... more The state of relationships between actors ion the internet is constantly changing and fluctuating to a social system of constant shocks. Link prediction, community detection, recommendation systems were built from around this fundamentally unstable system. Stable relational states - which hold important and latent deterministic knowledge have often been overlooked in this regard. In this paper, we propose a novel method of quantifying and detecting stability in the relationship between a given pair of actors. Our main algorithm (MVVA) establishes relational stability from a multivariate, autoregressive link feature dynamics perspective. Under our experimental design, we provide another built-in module based on the Hamiltonian Monte Carlo technique to provide a comprehensive cross-validation on the performance and accuracy of our proposed MVVA model.
Information networks are pivotal to the operational utility of key industries like medical, finan... more Information networks are pivotal to the operational utility of key industries like medical, finance, governments, etc. However, applications in this area are not adequate in representing relationships between nodes [34]. Trending graph learning methodologies [9, 16] like Graph Convolutional Networks (GCNs) [6] lack both representational power and accuracy to perform abstract computational tasks like prediction, classification, recommendation, etc. on real-time social networks. Furthermore, most such approaches known to date rely on learning temporal adjacency matrices to describe shallow attributes [9, 16] like word co-occurance PMI [3] changes [6] and are unable to capture complex evolving entity relationships in real life for applications like event prediction, link prediction, topic tracking, etc. [34]. Importantly, such models ignore knowledge information geometry [1, 24, 32] completely, and sacrifices fidelity to speed of convergence. To address these challenges, a novel Relati...
Knowledge-Based Systems, 2022
In recent years, the means of disease diagnosis and treatment have been improved remarkably, alon... more In recent years, the means of disease diagnosis and treatment have been improved remarkably, along with the continuous development of technology and science. Researchers have spent tremendous time and effort to build models, with an aim to assist medical practitioners in decision-making support. One of the greatest challenges remains is how to identify the connection between different diseases. This study aims to discover the relationship between diseases and symptoms and predict potential diseases for patients. Considering it a multi-label classification problem, the study proposed a new multi-disease prediction model learning from NHANES, an extensive health related dataset, and MEDLINE, a corpus with medical domain knowledge. A heterogeneous information graph is firstly constructed and then populated using medical domain knowledge discovered from MEDLINE. The knowledge graph is analysed for clarification of the relevancy within nodes in positive or negative space, helping to access to the correlation amongst multiple diseases and their symptoms. A multi-label disease prediction model is then developed adopting the medical domain knowledge graph. Empirical experiments are conducted to evaluate the proposed model. The experimental results show that the performance of the proposed model surpassed state-of-the-art related works representing the mainstreams of multi-label classification. This study contributes with a novel model for multi-disease prediction to the medical community and represents a new endeavour on multi-label classification using knowledge graphs
2018 5th International Conference on Behavioral, Economic, and Socio-Cultural Computing (BESC), 2018
In the medical domain, there exists a large volume of data from multiple sources such as electron... more In the medical domain, there exists a large volume of data from multiple sources such as electronic health records, general health examination results and surveys. The data contain useful information reflecting people's health and provides great opportunities for studies to improve the quality of healthcare. However, how to mine these data effectively and efficiently still remains a critical challenge. In this paper, we propose an innovative classification model for knowledge discovery from patients' personal health repositories. By based on analytics of massive data in National Health and Nutrition Examination Survey, the study builds a classification model to classify patients' health status and reveal the specific disease potentially suffered by the patient. This paper makes significant contributions to the advancement of knowledge in data mining with an innovative classification model specifically crafted for domain-based data. Moreover, this research contributes to the healthcare community by providing a deep understanding of people's health with accessibility to the patterns in various observations.
Journal of Data Intelligence, 2021
Event prediction is a very important task in numerous applications of interest like fintech, medi... more Event prediction is a very important task in numerous applications of interest like fintech, medical, security, etc. However, event prediction is a highly complex task because it is challenging to classify, contains temporally changing themes of discussion and heavy topic drifts. In this research, we present a novel approach which leverages on the RFT framework developed in \cite{tan2020discovering}. This study addresses the challenge of accurately representing relational features in observed complex social communication behavior for the event prediction task; which recent graph learning methodologies are struggling with. The concept here, is to firstly learn the turbulent patterns of relational state transitions between actors preceeding an event and then secondly, to evolve these profiles temporally, in the event prediction process. The event prediction model which leverages on the RFT framework discovers, identifies and adaptively ranks relational turbulence as likelihood predict...
Health Information Science and Systems, 2020
Applying Pearson correlation and semantic relations in building a heterogeneous information graph... more Applying Pearson correlation and semantic relations in building a heterogeneous information graph (HIG) to develop a classification model has achieved a notable performance in improving the accuracy of predicting the status of health risks. In this study, the approach that was used, integrated knowledge of the medical domain as well as taking advantage of applying Pearson correlation and semantic relations in building a classification model for diagnosis. The research mined knowledge which was extracted from titles and abstracts of MEDLINE to discover how to assess the links between objects relating to medical concepts. A knowledge-base HIG model then was developed for the prediction of a patient's health status. The results of the experiment showed that the knowledge-base model was superior to the baseline model and has demonstrated that the knowledge-base could help improve the performance of the classification model. The contribution of this study has been to provide a framework for applying a knowledge-base in the classification model which helps these models achieve the best performance of predictions. This study has also contributed a model to medical practice to help practitioners become more confident in making final decisions in diagnosing illness. Moreover, this study affirmed that biomedical literature could assist in building a classification model. This contribution will be advantageous for future researchers in mining the knowledge-base to develop different kinds of classification models.
Computer Science Review, 2020
Information networks today play an important, fundamental role in regulating real life activities... more Information networks today play an important, fundamental role in regulating real life activities. However, many methods developed on this framework lack the capacity to adequately represent sophistication contained within the information it carries. As a result, they suffer from problems such as inaccuracies, reliability and performance. We define relational intelligence as a combination of affective (
World Wide Web, 2020
Nowadays classification models have been widely adopted in healthcare, aiming at supporting pract... more Nowadays classification models have been widely adopted in healthcare, aiming at supporting practitioners for disease diagnosis and human error reduction. The challenge is utilising effective methods to mine real-world data in the medical domain, as many different models have been proposed with varying results. A large number of researchers focus on the diversity problem of real-time data sets in classification models. Some previous works developed methods comprising of homogeneous graphs for knowledge representation and then knowledge discovery. However, such approaches are weak in discovering different relationships among elements. In this paper, we propose an innovative classification model for knowledge discovery from patients' personal health repositories. The model discovers medical domain knowledge from the massive data in the National Health and Nutrition Examination Survey (NHANES). The knowledge is conceptualised in a heterogeneous knowledge graph. On the basis of the model, an innovative method is developed to help uncover potential diseases suffered by people and, furthermore, to classify patients' health risk. The proposed model is evaluated by comparison to a baseline model also built on the NHANES data set in an empirical experiment. The performance of proposed model is promising. The paper makes significant contributions to the advancement of knowledge in data mining with an innovative classification model specifically crafted for domain-based data. In addition, by accessing the
Brain Informatics, 2019
Mining data on a knowledge level can help to achieve a higher performance of a decision support s... more Mining data on a knowledge level can help to achieve a higher performance of a decision support system. This study built a knowledge graph based on MEDLINE that has a large number of articles in the medical domain. MEDLINE uses Medical Subject Headings (MeSH) for document index. Based on MeSH, articles are extracted from the MEDLINE correspondent to medical subjects. Using the MeSH as the backbone of knowledge base, the MEDLINE articles were used to generate instances which helped to populate the knowledge base. This approach facilitated the creation of a knowledge graph that was capable of discovering the hidden knowledge among concepts of MeSH. The knowledge graph had a significant effect on improving the quality of healthcare. The contribution of the research is on a framework for building knowledge bases. Moreover, the approach provided an essential source at the knowledge level for researchers in healthcare.
Lecture Notes in Computer Science, 1994
We describe solutions to practical database problems encountered during the implementation of a p... more We describe solutions to practical database problems encountered during the implementation of a prototype Physician's Workstation (PWS) at Hewlett-Packard Laboratories:(i) the integration of legacy data repositories using an object-oriented ...
Vision Research, 2008
The effect of emotion on visual awareness is largely unknown. Pairs of natural images were presen... more The effect of emotion on visual awareness is largely unknown. Pairs of natural images were presented side by side on a screen in a binocular rivalry setup. The amount of time that each image of a pair dominated perception was computed. Our results showed: (A) A main effect of arousal: Dominance durations of the more arousing picture of iso-valence pairs were longer. (B) No effect of valence: Dominance durations of pleasant and unpleasant pictures of isoarousal pairs were similar. (C) An interaction between arousal and valence: The more pleasant picture of iso-arousal pairs of low arousal level dominated conscious perception. The less pleasant picture of iso-arousal pairs of high arousal level dominated conscious perception. Our findings suggest that the emotional content of a stimulus affects the extent to which it dominates awareness. While arousal and valence interactively affect access to awareness, only arousal exerts an independent control of such access.
Ophthalmic Epidemiology, 2009
To examine the associations among iris, skin, or hair color, and skin sun sensitivity and the 10-... more To examine the associations among iris, skin, or hair color, and skin sun sensitivity and the 10-year incidence of age-related maculopathy (ARM). The Blue Mountains Eye Study (BMES) recruited 3654 participants aged 49+ years at baseline (1992-1994, 82.4% participation rate). Re-examinations of 2335 participants (75.1% of survivors) were done after 5 years (1997-1999) and 1952 (76.5% of survivors) after 10 years (2002-2004). Retinal photographs were graded using the Wisconsin ARM Grading System and incident ARM confirmed using the side-by-side grading method. Iris, skin, and hair color, and sun-related skin damage were assessed and skin sun-sensitivity questions were asked at baseline. Ten-year ARM incidence was calculated using Kaplan Meier methods and discrete logistic models were used to assess associations after adjusting for age, sex, and smoking. After adjustment, no significant associations were found between iris or hair color and either late- or early-incident ARM. Compared to persons with fair skin, those with very fair skin had an increased risk of developing geographic atrophy (multivariate adjusted risk ratio, RR = 7.6; 95% confidence interval, CI = 3.0-19.6). In contrast, compared to persons with average skin sun sensitivity, persons who reported that their skin would usually burn and tan with difficulty had a reduced risk of neovascular ARM (RR = 0.2, 95% CI = 0.0-0.7). Sun-related skin damage was not associated with late or early ARM. In this older cohort, we did not find a consistent pattern of association between sunlight-related factors and ARM incidence, except that persons with very fair skin might have an increased risk of geographic atrophy, consistent with our 5-year incidence data. The protective association between skin sensitivity to sun damage and neovascular ARM could have be the result of confounding by sun-avoidance behavior among persons sensitive to sunburn.