Computing and Informatics, Bratislava: Slovak University Press, 2013
Nowadays, almost all text corpora, such as blogs, emails and RSS feeds, are a collection of text ... more Nowadays, almost all text corpora, such as blogs, emails and RSS feeds, are a collection of text streams. The traditional vector space model (VSM), or bagof-words representation, cannot capture the temporal aspect of these text streams. So far, only a few bursty features have been proposed to create text representations with temporal modeling for the text streams. We propose bursty feature representations that perform better than VSM on various text mining tasks, such as document retrieval, topic modeling and text categorization. For text clustering, we propose a novel framework to generate bursty distance measure. We evaluated it on UP-GMA, Star and K-Medoids clustering algorithms. The bursty distance measure did not only perform equally well on various text collections, but it was also able to cluster the news articles related to specific events much better than other models.
People have many activities throughout the day, ranging from meeting a client to picking up your ... more People have many activities throughout the day, ranging from meeting a client to picking up your child. The assistance application on the smartphone is used to manage time efficiently and assist in various tasks throughout the day. However, the existing assistance applications do not have social network capability. In this project, we propose the Alert Me Please (AMP) application on Android operating system. AMP designed to be an easy-to-use application with the main goal of helping users to manage their time schedule. The application consists of group-sharing event, friend subscription, location alert, voice input, social sharing, and all basic properties of reminder application. All AMP functions and intelligent agent are combined to provide the best time management assistant, which suits for everyone.
Over the past two decades, Computer Science (CS) has continued to grow as a research field. There... more Over the past two decades, Computer Science (CS) has continued to grow as a research field. There are several studies that examine trends and emerging topics in CS research or the impact of papers on the field. In contrast, in this article, we take a closer look at the entire CS research in the past two decades by analyzing the data on publications in the ACM Digital Library and IEEE Xplore, and the grants awarded by the National Science Foundation (NSF). We identify trends, bursty topics, and interesting inter-relationships between NSF awards and CS publications, finding, for example, that if an uncommonly high frequency of a specific topic is observed in publications, the funding for this topic is usually increased. We also analyze CS researchers and communities, finding that only a small fraction of authors attribute their work to the same research area for a long period of time, reflecting for instance the emphasis on novelty (use of new keywords) and typical academic research t...
Like paintings and verbal dialogues, written documents exhibit the author's distinctive style... more Like paintings and verbal dialogues, written documents exhibit the author's distinctive style and identification of the author of an anonymous document is an important and challenging task in computer security. Even more challenging is identification of a style of a group of diverse individuals acting in similar circumstances, like authors writing in certain literary period or people writing in a certain social role. The last application is important for analyzing hidden group communicating over the internet in which neither identities nor roles of the members are known. Other applications of the identification of such styles include fraud detection, author attribution and user profiling. The task of finding distinctive features of an artifact has much broader scientific implications that range from art and scriptures to network security. In this paper, we focus on capturing patterns in electronic documents. The approach involves discovering patterns at varying degrees of abstra...
With the rises of the AI technology in Healthcare, researchers have been using the technology to ... more With the rises of the AI technology in Healthcare, researchers have been using the technology to develop a computational system to aid diagnosis, commonly known as 'Clinical Decision Support Systems (CDSSs)'. The CDSS applications currently available are usually neither free, nor optimized for treating Thai patients. In this work, we propose a new CDSS platform intended as an open platform for the CDSS application in Thailand. As a prototype and proof of concept, we developed the Mahidol Snake Envenomation Support System (MSESS), as the first C DSS a pplication u sing o ur n ew p latform. MSESS was designed to help its user formulate a treatment plan for the patient with snake bite found in Thailand, particularly in rural areas, and guide the user through the treatment flow. The treatments suggested by MSESS strictly follows the Snake Envenomation guideline provided by the Ramathibodi Poison Center. The targeted user is the medical personnel such as general practitioner seek...
International Journal of Pharma Medicine and Biological Sciences
Health policy reform in major developing countries has changed how patients are treated for chron... more Health policy reform in major developing countries has changed how patients are treated for chronic diseases due to high cost and government regulations. In order to understand the overall patterns of the treatments, this study explores methods to collect Electronic Medical Records (EMRs) and analyzes patterns in prescription plan and treatment cost in health coverage programs from local data source. Focusing on admitted patients with conditions related to diabetes and hypertension, the results suggested high variations of treatment in patients with hypertension, but very limited variations among diabetes patients. The results also summarized prescription lists and treatment cost among health benefit programs.
BY APiRAK hoonLoR, BoLesLAW K. szYmAnsKi, AnD mohAmmeD J. zAKi key insights A burst of new keywor... more BY APiRAK hoonLoR, BoLesLAW K. szYmAnsKi, AnD mohAmmeD J. zAKi key insights A burst of new keywords in grants generally precedes their burst in publications; less than one-third of new keywords burst in publications first, reflecting the importance of funding for success of new Cs fields. A typical scientist's research focus changes in roughly a 10-year cycle and often includes a once-in-a-career shift, likely in response to evolving technology creating new Cs fields. Cs continues to experience continuous and fundamental transformation; for example, in the past two decades, new topics arose within the internet research cluster, while some previously popular topics (such as mathematical foundations) decayed.
Tencon 2014 2014 Ieee Region 10 Conference, Oct 1, 2014
Logs are typically used for performing post mortem for abnormal activities. Most Internet service... more Logs are typically used for performing post mortem for abnormal activities. Most Internet service providers keep the history of users' web accesses in terms of proxy logs for investigating a misuse or fraud. However, the majority of the logs represent normal behavior, and no thorough analysis of such logs is usually performed, keeping them on storage would consume very big space. This paper analyzes the characteristics of such logs and classifies them into normal, medium, high and burst rate using five main attributes: IP address, bandwidth, duration, file category, and file type. Our experimental results show different rates for each file type in five popular file categories. The results will be used in classifying web access logs and filtering out abnormal from normal logs so that only abnormal logs are kept for fast investigation.
2015 International Computer Science and Engineering Conference (ICSEC), 2015
One of the visual challenge problems that the blind faces is the consumer product identification ... more One of the visual challenge problems that the blind faces is the consumer product identification with contextual and description information problem. In order to increase their independence in food shopping and other product recognition, we implement an Android application called UCap to assist the blind in this visual challenge problem. In the visually impaired and blind persons mode, UCap is a camera-base mobile application that identifies the consumer product of a captured image using the UCap annotated image database. The UCap annotated image database is created using the crowdsourcing paradigm. In the sighted user mode, the user can use UCap to capture an image of a consumer product, add its description, and upload them to the UCap annotated image database. The sighted user can add more images of the existing products in the database. The seed database contains 3,950 annotated images. We used Infrastructure-as-a-Service (IaaS) on MS Azure cloud server for the initial system testing and evaluation. With exception of the lower-than-expected accuracy of image identification, the application received high praised from the visually impaired and blind persons. However, from the experiment and testing, the accuracy of UCap can be increased as more images are added to the database.
The burstiness values of "fuel type == diesel" and "fuel type == gas" queries on automobile data ... more The burstiness values of "fuel type == diesel" and "fuel type == gas" queries on automobile data set using horse power to arrange, on the xaxis. For y-axis, it is the burstiness, which we defined using probabilities. viii
2014 Third Ict International Student Project Conference, Mar 26, 2014
People have many activities throughout the day, ranging from meeting a client to picking up your ... more People have many activities throughout the day, ranging from meeting a client to picking up your child. The assistance application on the smartphone is used to manage time efficiently and assist in various tasks throughout the day. However, the existing assistance applications do not have social network capability. In this project, we propose the Alert Me Please (AMP) application on Android operating system. AMP designed to be an easy-to-use application with the main goal of helping users to manage their time schedule. The application consists of group-sharing event, friend subscription, location alert, voice input, social sharing, and all basic properties of reminder application. All AMP functions and intelligent agent are combined to provide the best time management assistant, which suits for everyone.
Keywords in the ACM Digital Library and IEEE Xplore digital library and in NSF grants anticipate ... more Keywords in the ACM Digital Library and IEEE Xplore digital library and in NSF grants anticipate future CS research.
Computing and Informatics, Bratislava: Slovak University Press, 2013
Nowadays, almost all text corpora, such as blogs, emails and RSS feeds, are a collection of text ... more Nowadays, almost all text corpora, such as blogs, emails and RSS feeds, are a collection of text streams. The traditional vector space model (VSM), or bagof-words representation, cannot capture the temporal aspect of these text streams. So far, only a few bursty features have been proposed to create text representations with temporal modeling for the text streams. We propose bursty feature representations that perform better than VSM on various text mining tasks, such as document retrieval, topic modeling and text categorization. For text clustering, we propose a novel framework to generate bursty distance measure. We evaluated it on UP-GMA, Star and K-Medoids clustering algorithms. The bursty distance measure did not only perform equally well on various text collections, but it was also able to cluster the news articles related to specific events much better than other models.
People have many activities throughout the day, ranging from meeting a client to picking up your ... more People have many activities throughout the day, ranging from meeting a client to picking up your child. The assistance application on the smartphone is used to manage time efficiently and assist in various tasks throughout the day. However, the existing assistance applications do not have social network capability. In this project, we propose the Alert Me Please (AMP) application on Android operating system. AMP designed to be an easy-to-use application with the main goal of helping users to manage their time schedule. The application consists of group-sharing event, friend subscription, location alert, voice input, social sharing, and all basic properties of reminder application. All AMP functions and intelligent agent are combined to provide the best time management assistant, which suits for everyone.
Over the past two decades, Computer Science (CS) has continued to grow as a research field. There... more Over the past two decades, Computer Science (CS) has continued to grow as a research field. There are several studies that examine trends and emerging topics in CS research or the impact of papers on the field. In contrast, in this article, we take a closer look at the entire CS research in the past two decades by analyzing the data on publications in the ACM Digital Library and IEEE Xplore, and the grants awarded by the National Science Foundation (NSF). We identify trends, bursty topics, and interesting inter-relationships between NSF awards and CS publications, finding, for example, that if an uncommonly high frequency of a specific topic is observed in publications, the funding for this topic is usually increased. We also analyze CS researchers and communities, finding that only a small fraction of authors attribute their work to the same research area for a long period of time, reflecting for instance the emphasis on novelty (use of new keywords) and typical academic research t...
Like paintings and verbal dialogues, written documents exhibit the author's distinctive style... more Like paintings and verbal dialogues, written documents exhibit the author's distinctive style and identification of the author of an anonymous document is an important and challenging task in computer security. Even more challenging is identification of a style of a group of diverse individuals acting in similar circumstances, like authors writing in certain literary period or people writing in a certain social role. The last application is important for analyzing hidden group communicating over the internet in which neither identities nor roles of the members are known. Other applications of the identification of such styles include fraud detection, author attribution and user profiling. The task of finding distinctive features of an artifact has much broader scientific implications that range from art and scriptures to network security. In this paper, we focus on capturing patterns in electronic documents. The approach involves discovering patterns at varying degrees of abstra...
With the rises of the AI technology in Healthcare, researchers have been using the technology to ... more With the rises of the AI technology in Healthcare, researchers have been using the technology to develop a computational system to aid diagnosis, commonly known as 'Clinical Decision Support Systems (CDSSs)'. The CDSS applications currently available are usually neither free, nor optimized for treating Thai patients. In this work, we propose a new CDSS platform intended as an open platform for the CDSS application in Thailand. As a prototype and proof of concept, we developed the Mahidol Snake Envenomation Support System (MSESS), as the first C DSS a pplication u sing o ur n ew p latform. MSESS was designed to help its user formulate a treatment plan for the patient with snake bite found in Thailand, particularly in rural areas, and guide the user through the treatment flow. The treatments suggested by MSESS strictly follows the Snake Envenomation guideline provided by the Ramathibodi Poison Center. The targeted user is the medical personnel such as general practitioner seek...
International Journal of Pharma Medicine and Biological Sciences
Health policy reform in major developing countries has changed how patients are treated for chron... more Health policy reform in major developing countries has changed how patients are treated for chronic diseases due to high cost and government regulations. In order to understand the overall patterns of the treatments, this study explores methods to collect Electronic Medical Records (EMRs) and analyzes patterns in prescription plan and treatment cost in health coverage programs from local data source. Focusing on admitted patients with conditions related to diabetes and hypertension, the results suggested high variations of treatment in patients with hypertension, but very limited variations among diabetes patients. The results also summarized prescription lists and treatment cost among health benefit programs.
BY APiRAK hoonLoR, BoLesLAW K. szYmAnsKi, AnD mohAmmeD J. zAKi key insights A burst of new keywor... more BY APiRAK hoonLoR, BoLesLAW K. szYmAnsKi, AnD mohAmmeD J. zAKi key insights A burst of new keywords in grants generally precedes their burst in publications; less than one-third of new keywords burst in publications first, reflecting the importance of funding for success of new Cs fields. A typical scientist's research focus changes in roughly a 10-year cycle and often includes a once-in-a-career shift, likely in response to evolving technology creating new Cs fields. Cs continues to experience continuous and fundamental transformation; for example, in the past two decades, new topics arose within the internet research cluster, while some previously popular topics (such as mathematical foundations) decayed.
Tencon 2014 2014 Ieee Region 10 Conference, Oct 1, 2014
Logs are typically used for performing post mortem for abnormal activities. Most Internet service... more Logs are typically used for performing post mortem for abnormal activities. Most Internet service providers keep the history of users' web accesses in terms of proxy logs for investigating a misuse or fraud. However, the majority of the logs represent normal behavior, and no thorough analysis of such logs is usually performed, keeping them on storage would consume very big space. This paper analyzes the characteristics of such logs and classifies them into normal, medium, high and burst rate using five main attributes: IP address, bandwidth, duration, file category, and file type. Our experimental results show different rates for each file type in five popular file categories. The results will be used in classifying web access logs and filtering out abnormal from normal logs so that only abnormal logs are kept for fast investigation.
2015 International Computer Science and Engineering Conference (ICSEC), 2015
One of the visual challenge problems that the blind faces is the consumer product identification ... more One of the visual challenge problems that the blind faces is the consumer product identification with contextual and description information problem. In order to increase their independence in food shopping and other product recognition, we implement an Android application called UCap to assist the blind in this visual challenge problem. In the visually impaired and blind persons mode, UCap is a camera-base mobile application that identifies the consumer product of a captured image using the UCap annotated image database. The UCap annotated image database is created using the crowdsourcing paradigm. In the sighted user mode, the user can use UCap to capture an image of a consumer product, add its description, and upload them to the UCap annotated image database. The sighted user can add more images of the existing products in the database. The seed database contains 3,950 annotated images. We used Infrastructure-as-a-Service (IaaS) on MS Azure cloud server for the initial system testing and evaluation. With exception of the lower-than-expected accuracy of image identification, the application received high praised from the visually impaired and blind persons. However, from the experiment and testing, the accuracy of UCap can be increased as more images are added to the database.
The burstiness values of "fuel type == diesel" and "fuel type == gas" queries on automobile data ... more The burstiness values of "fuel type == diesel" and "fuel type == gas" queries on automobile data set using horse power to arrange, on the xaxis. For y-axis, it is the burstiness, which we defined using probabilities. viii
2014 Third Ict International Student Project Conference, Mar 26, 2014
People have many activities throughout the day, ranging from meeting a client to picking up your ... more People have many activities throughout the day, ranging from meeting a client to picking up your child. The assistance application on the smartphone is used to manage time efficiently and assist in various tasks throughout the day. However, the existing assistance applications do not have social network capability. In this project, we propose the Alert Me Please (AMP) application on Android operating system. AMP designed to be an easy-to-use application with the main goal of helping users to manage their time schedule. The application consists of group-sharing event, friend subscription, location alert, voice input, social sharing, and all basic properties of reminder application. All AMP functions and intelligent agent are combined to provide the best time management assistant, which suits for everyone.
Keywords in the ACM Digital Library and IEEE Xplore digital library and in NSF grants anticipate ... more Keywords in the ACM Digital Library and IEEE Xplore digital library and in NSF grants anticipate future CS research.
Uploads
Papers by Apirak Hoonlor