Pub Date : 2017-07-01DOI: 10.1109/JCSSE.2017.8025941
Varin Chouvatut, E. Boonchieng
Typically, a sequence of the Magnetic Resonance Imaging (MRI) images is composed of a certain number of images projecting some internal organs of a human, such as brain and eyeballs of the human's head, which is the case chosen for our demonstration. Each of MRI images in the sequence presents only a thin layer of the whole head. The image processing techniques proposed in this paper aims to allow all such sequential images to be visible through a single view. In other words, the whole head of a human can be visible in just one image and thus looks as a three-dimensional view of the head. Unfortunately, there may be some deviation in positions even between contiguous images in the sequence. Centroid of the human's head appeared in each image should be measured. To ensure a centroid's position is estimated well enough so that centroids of all sequential images are not so much deviated from each other, searching for the centroid of a human's whole head is done based on an approximate convex shape rather than a circular shape as usual. From our experimental results, there is no significant deviation of centroids between contiguous frames as expected.
{"title":"Graphical representation of the whole sequentially MRI images in a single view image sequences of human's whole head","authors":"Varin Chouvatut, E. Boonchieng","doi":"10.1109/JCSSE.2017.8025941","DOIUrl":"https://doi.org/10.1109/JCSSE.2017.8025941","url":null,"abstract":"Typically, a sequence of the Magnetic Resonance Imaging (MRI) images is composed of a certain number of images projecting some internal organs of a human, such as brain and eyeballs of the human's head, which is the case chosen for our demonstration. Each of MRI images in the sequence presents only a thin layer of the whole head. The image processing techniques proposed in this paper aims to allow all such sequential images to be visible through a single view. In other words, the whole head of a human can be visible in just one image and thus looks as a three-dimensional view of the head. Unfortunately, there may be some deviation in positions even between contiguous images in the sequence. Centroid of the human's head appeared in each image should be measured. To ensure a centroid's position is estimated well enough so that centroids of all sequential images are not so much deviated from each other, searching for the centroid of a human's whole head is done based on an approximate convex shape rather than a circular shape as usual. From our experimental results, there is no significant deviation of centroids between contiguous frames as expected.","PeriodicalId":6460,"journal":{"name":"2017 14th International Joint Conference on Computer Science and Software Engineering (JCSSE)","volume":"83 1","pages":"1-6"},"PeriodicalIF":0.0,"publicationDate":"2017-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"79362870","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2017-07-01DOI: 10.1109/JCSSE.2017.8025901
Sangduan Chootong, Jirawat Thaenthong
Caching mechanism is usually used in Content-Centric Networking. Cache data is contained at provider node and all nodes along the path to the consumer node. The disadvantage of this mechanism is the data redundancy on several nodes. In the case of the cache size is limited, the cache hit of the request data is issued. In this paper proposed a Cache Replacement with Content Popularity (CRCP) mechanism that allows a node in a cluster of vehicles to make decision retaining data or performing cache replacement. The results demonstrate the performance of the proposed mechanism is better than the LFU and LRU in terms of average cache hit ratio.
{"title":"Cache replacement mechanism with Content Popularity for Vehicular Content-Centric Networks (VCCN)","authors":"Sangduan Chootong, Jirawat Thaenthong","doi":"10.1109/JCSSE.2017.8025901","DOIUrl":"https://doi.org/10.1109/JCSSE.2017.8025901","url":null,"abstract":"Caching mechanism is usually used in Content-Centric Networking. Cache data is contained at provider node and all nodes along the path to the consumer node. The disadvantage of this mechanism is the data redundancy on several nodes. In the case of the cache size is limited, the cache hit of the request data is issued. In this paper proposed a Cache Replacement with Content Popularity (CRCP) mechanism that allows a node in a cluster of vehicles to make decision retaining data or performing cache replacement. The results demonstrate the performance of the proposed mechanism is better than the LFU and LRU in terms of average cache hit ratio.","PeriodicalId":6460,"journal":{"name":"2017 14th International Joint Conference on Computer Science and Software Engineering (JCSSE)","volume":"271 1","pages":"1-6"},"PeriodicalIF":0.0,"publicationDate":"2017-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"83027308","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2017-07-01DOI: 10.1109/JCSSE.2017.8025953
Sakchai Muangsrinoon, P. Boonbrahm
The number of time that heart beats per one minute we call it as the heart rate or pulse. It is an indicator for monitoring health. In this paper, we present the Burn in Zone: Physical activity real-time heart rate monitoring, a novel model to help people who prefer to have a more physical activity to continue their intention in the long term. We were mainly interested in real-time heart rate monitoring and target heart rate zone, not its ability to change behavior. This model will help those people to monitor their heart rate while having physical activity in line with their target heart rate or training heart rate (THR). THR is the desired range of heart rate reached during physical activity. It is calculated from the percentage of the physical activity intensity (PAI) multiply with Maximum Heart Rate (MHR), the highest heart rate of each person can work efficiently and safely without severe problems through exercise stress. In this research, we developed an android wear application for getting a real-time pulse from the heart sensor in Android Smart Watch. We had collected data from undergraduate and graduate students from the School of Informatics, Walailak University, who volunteer to be part of this experiment. There are twenty-six volunteers with age ranges from nineteen to forty-two-year-olds. Among the volunteers, there are twelve males (46.15%) and fourteen females (53.85%). We separated the samples into two groups, controlled group and experimental group. The experimental criteria are cycling on a stationary bicycle with six minutes for each people. Results from the experiment showed that the percentage of heart rate of the controlled group and the experimental group were consistent with the experimental setup criteria for monitoring the heart rate data on Android wear. For future work, we plan to implement the game design elements to encourage the people to have more level of physical activity and continue their physical activity.
{"title":"Burn in Zone: Real time Heart Rate monitoring for physical activity","authors":"Sakchai Muangsrinoon, P. Boonbrahm","doi":"10.1109/JCSSE.2017.8025953","DOIUrl":"https://doi.org/10.1109/JCSSE.2017.8025953","url":null,"abstract":"The number of time that heart beats per one minute we call it as the heart rate or pulse. It is an indicator for monitoring health. In this paper, we present the Burn in Zone: Physical activity real-time heart rate monitoring, a novel model to help people who prefer to have a more physical activity to continue their intention in the long term. We were mainly interested in real-time heart rate monitoring and target heart rate zone, not its ability to change behavior. This model will help those people to monitor their heart rate while having physical activity in line with their target heart rate or training heart rate (THR). THR is the desired range of heart rate reached during physical activity. It is calculated from the percentage of the physical activity intensity (PAI) multiply with Maximum Heart Rate (MHR), the highest heart rate of each person can work efficiently and safely without severe problems through exercise stress. In this research, we developed an android wear application for getting a real-time pulse from the heart sensor in Android Smart Watch. We had collected data from undergraduate and graduate students from the School of Informatics, Walailak University, who volunteer to be part of this experiment. There are twenty-six volunteers with age ranges from nineteen to forty-two-year-olds. Among the volunteers, there are twelve males (46.15%) and fourteen females (53.85%). We separated the samples into two groups, controlled group and experimental group. The experimental criteria are cycling on a stationary bicycle with six minutes for each people. Results from the experiment showed that the percentage of heart rate of the controlled group and the experimental group were consistent with the experimental setup criteria for monitoring the heart rate data on Android wear. For future work, we plan to implement the game design elements to encourage the people to have more level of physical activity and continue their physical activity.","PeriodicalId":6460,"journal":{"name":"2017 14th International Joint Conference on Computer Science and Software Engineering (JCSSE)","volume":"126 1","pages":"1-6"},"PeriodicalIF":0.0,"publicationDate":"2017-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"87854128","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2017-07-01DOI: 10.1109/JCSSE.2017.8025913
Niramai Cherdmuangpak, Tanapat Anusas-Amornkul, B. Limthanmaphon
Internet is popular for people at all ages. A computer is used to access the Internet but a user needs to authenticate himself to the system in order to gain access. The problem of a typical authentication technique is to memorize a password. Lots of junior high school students in Pakthongchaiprachaniramit School cannot remember their own password and this work is proposed to solve the problem by using an image-based password technique instead. However, a normal image-based password can be easily hacked using a shoulder surfing attack. This work proposed the two factor image-based password technique using image and random questions. However, when the percentage of successful log-in was compared, this work outperformed the alphanumeric-based password. When the third log-in (15 days after registration) was conducted, the percentage of successful log-in of our proposed work was 95% comparing to 58.33% of alphanumeric-based password. In addition, the proposed technique was able to prevent from the shoulder surfing attack.
{"title":"Two factor image-based password authentication for junior high school students","authors":"Niramai Cherdmuangpak, Tanapat Anusas-Amornkul, B. Limthanmaphon","doi":"10.1109/JCSSE.2017.8025913","DOIUrl":"https://doi.org/10.1109/JCSSE.2017.8025913","url":null,"abstract":"Internet is popular for people at all ages. A computer is used to access the Internet but a user needs to authenticate himself to the system in order to gain access. The problem of a typical authentication technique is to memorize a password. Lots of junior high school students in Pakthongchaiprachaniramit School cannot remember their own password and this work is proposed to solve the problem by using an image-based password technique instead. However, a normal image-based password can be easily hacked using a shoulder surfing attack. This work proposed the two factor image-based password technique using image and random questions. However, when the percentage of successful log-in was compared, this work outperformed the alphanumeric-based password. When the third log-in (15 days after registration) was conducted, the percentage of successful log-in of our proposed work was 95% comparing to 58.33% of alphanumeric-based password. In addition, the proposed technique was able to prevent from the shoulder surfing attack.","PeriodicalId":6460,"journal":{"name":"2017 14th International Joint Conference on Computer Science and Software Engineering (JCSSE)","volume":"22 1","pages":"1-6"},"PeriodicalIF":0.0,"publicationDate":"2017-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"73777099","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2017-07-01DOI: 10.1109/JCSSE.2017.8025907
Raywut Ketsuwan, P. Padungweang
The linear discriminant analysis (LDA) is one of the most efficient supervised dimensionality reduction technique widely used in face recognition. This paper proposed a new weighted LDA to improve the performance of the discriminant analysis. Confusable pair of classes is considered as the primary goal in our objective function. The proposed technique not only improves the minimization of the within-class scatter, but also improves the maximization of the between classes scatter to extract better discriminant feature subset. The experimental results a real word dataset demonstrate that the proposed method achieve higher recognition rate than that traditional LDA as well as other weighted LDA.
{"title":"A linear discriminant analysis using weighted local structure information","authors":"Raywut Ketsuwan, P. Padungweang","doi":"10.1109/JCSSE.2017.8025907","DOIUrl":"https://doi.org/10.1109/JCSSE.2017.8025907","url":null,"abstract":"The linear discriminant analysis (LDA) is one of the most efficient supervised dimensionality reduction technique widely used in face recognition. This paper proposed a new weighted LDA to improve the performance of the discriminant analysis. Confusable pair of classes is considered as the primary goal in our objective function. The proposed technique not only improves the minimization of the within-class scatter, but also improves the maximization of the between classes scatter to extract better discriminant feature subset. The experimental results a real word dataset demonstrate that the proposed method achieve higher recognition rate than that traditional LDA as well as other weighted LDA.","PeriodicalId":6460,"journal":{"name":"2017 14th International Joint Conference on Computer Science and Software Engineering (JCSSE)","volume":"4 1","pages":"1-5"},"PeriodicalIF":0.0,"publicationDate":"2017-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"76063648","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2017-07-01DOI: 10.1109/JCSSE.2017.8025957
Varin Chouvatut, E. Boonchieng
Measuring area of tumor in human's brain from only single image may provide incorrect information for further diagnosis. Generally, a doctor or an expert must examine a brain tumor from several sequential MRI images to conclude its size or the severity level of patient's illness. To imitate the way a doctor diagnosing such case in a real situation, some digital image processing techniques are proposed and applied in order to provide support for a tentative or an initial analysis to the doctor. Thus, correspondence of appearances of a tumor presented in all MRI images should be linked and considered. In image processing, a closed area can be seen as an object and based on the similarity of its interior shadings, the object's centroid can be estimated. Unfortunately, although an object's centroid may be calculated even there exists slightly different shadings which are still considered as having similarity inside the closed shape of the object, only a small hole can cause deviation of computed centroid from its expected position. Since the typical thresholding techniques still leave a hole whose area has a certain amount of different shading from the major shading of the object's area. Thus, we proposed a number of image processing techniques for the purpose of tumor area approximation. Moreover, the proposed methods include a correspondence technique would also support multiple-object detection and linking centroids of the same object, which is a brain tumor in this case, presented in a pair of contiguous images.
{"title":"Brain tumor's approximate correspondence and area with interior holes filled","authors":"Varin Chouvatut, E. Boonchieng","doi":"10.1109/JCSSE.2017.8025957","DOIUrl":"https://doi.org/10.1109/JCSSE.2017.8025957","url":null,"abstract":"Measuring area of tumor in human's brain from only single image may provide incorrect information for further diagnosis. Generally, a doctor or an expert must examine a brain tumor from several sequential MRI images to conclude its size or the severity level of patient's illness. To imitate the way a doctor diagnosing such case in a real situation, some digital image processing techniques are proposed and applied in order to provide support for a tentative or an initial analysis to the doctor. Thus, correspondence of appearances of a tumor presented in all MRI images should be linked and considered. In image processing, a closed area can be seen as an object and based on the similarity of its interior shadings, the object's centroid can be estimated. Unfortunately, although an object's centroid may be calculated even there exists slightly different shadings which are still considered as having similarity inside the closed shape of the object, only a small hole can cause deviation of computed centroid from its expected position. Since the typical thresholding techniques still leave a hole whose area has a certain amount of different shading from the major shading of the object's area. Thus, we proposed a number of image processing techniques for the purpose of tumor area approximation. Moreover, the proposed methods include a correspondence technique would also support multiple-object detection and linking centroids of the same object, which is a brain tumor in this case, presented in a pair of contiguous images.","PeriodicalId":6460,"journal":{"name":"2017 14th International Joint Conference on Computer Science and Software Engineering (JCSSE)","volume":"36 1","pages":"1-5"},"PeriodicalIF":0.0,"publicationDate":"2017-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"85487914","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2017-07-01DOI: 10.1109/JCSSE.2017.8025947
Kanittha Promsakul, S. Limsiroratana
This research focuses on improving business process worked under workflow simulation. In the business process, there are several properties to be considered such as person, cost, time. The current workflow simulation cannot combine these properties to simulate the situation for business decision making. In this paper, the improving business workflow simulation is proposed by adding the business properties to the workflow simulation. Then, our simulation is able to simulate his/her work and monitor/collect status data for analysis. Both Apache Oozie and Apache Hadoop are used in this work as fundamental framework. Oozie is a workflow engine job scheduler system which is performed by the Apache Hadoop. Apache Hadoop is big data framework that provides distributed processing and storage. As a result, our workflow simulation can increase the efficiency of workflow management and scalable for solving the big business workflow process.
{"title":"Workflow simulation based on cloud platform for office automation system","authors":"Kanittha Promsakul, S. Limsiroratana","doi":"10.1109/JCSSE.2017.8025947","DOIUrl":"https://doi.org/10.1109/JCSSE.2017.8025947","url":null,"abstract":"This research focuses on improving business process worked under workflow simulation. In the business process, there are several properties to be considered such as person, cost, time. The current workflow simulation cannot combine these properties to simulate the situation for business decision making. In this paper, the improving business workflow simulation is proposed by adding the business properties to the workflow simulation. Then, our simulation is able to simulate his/her work and monitor/collect status data for analysis. Both Apache Oozie and Apache Hadoop are used in this work as fundamental framework. Oozie is a workflow engine job scheduler system which is performed by the Apache Hadoop. Apache Hadoop is big data framework that provides distributed processing and storage. As a result, our workflow simulation can increase the efficiency of workflow management and scalable for solving the big business workflow process.","PeriodicalId":6460,"journal":{"name":"2017 14th International Joint Conference on Computer Science and Software Engineering (JCSSE)","volume":"13 1","pages":"1-5"},"PeriodicalIF":0.0,"publicationDate":"2017-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"83643002","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2017-07-01DOI: 10.1109/JCSSE.2017.8025928
J. Sainui
Dependence-maximization clustering is another line of clustering framework, which clusters samples by maximizing the statistical dependence on samples in the same group. Recently, dependence-maximization clustering method based on least-squares quadratic mutual information (LSQMI), called LSQMI based clustering (LSQMIC), was proposed. A notable advantage of LSQMIC over other dependence-maximization clustering methods is that it works well even though the data containing outliers. However, the performance of this method tends to decrease in case samples are low density. To deal with this problem, in this paper, we apply Laplacian Eigenmap incorporating with local scaling similarity for representing data so that the samples in the same class will stay as close as possible. Through experiments, we demonstrate that LSQMIC performs better on Laplacian Eigenmap embedded with no losing of the high robustness against outliers.
{"title":"Improved least-squares quadratic mutual information clustering via Laplacian Eigenmap","authors":"J. Sainui","doi":"10.1109/JCSSE.2017.8025928","DOIUrl":"https://doi.org/10.1109/JCSSE.2017.8025928","url":null,"abstract":"Dependence-maximization clustering is another line of clustering framework, which clusters samples by maximizing the statistical dependence on samples in the same group. Recently, dependence-maximization clustering method based on least-squares quadratic mutual information (LSQMI), called LSQMI based clustering (LSQMIC), was proposed. A notable advantage of LSQMIC over other dependence-maximization clustering methods is that it works well even though the data containing outliers. However, the performance of this method tends to decrease in case samples are low density. To deal with this problem, in this paper, we apply Laplacian Eigenmap incorporating with local scaling similarity for representing data so that the samples in the same class will stay as close as possible. Through experiments, we demonstrate that LSQMIC performs better on Laplacian Eigenmap embedded with no losing of the high robustness against outliers.","PeriodicalId":6460,"journal":{"name":"2017 14th International Joint Conference on Computer Science and Software Engineering (JCSSE)","volume":"41 1","pages":"1-5"},"PeriodicalIF":0.0,"publicationDate":"2017-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"84056849","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2017-07-01DOI: 10.1109/JCSSE.2017.8025958
Tanin Intaramanee, Ratanak Khoeun, K. Chinnasarn
Diabetic Retinopathy is one of the most serious diseases that can lead to blindness. The small swelling blood regions or microaneurysms are the early sign of Diabetic Retinopathy. Detecting that a patient has got the Diabetic Retinopathy at the earliest stage as possible can help to prevent him/her from the vision lost. However, automatic microaneurysm detection is still a challenging topic for medical image processing researchers. This is because of the varieties of microaneurysm characteristic such as size, contrast, shape, and data distribution. In this paper, we propose an approach to automatically detect microaneurysms using Multi-level Threshold based on ISODATA. The proposed method consists of two main steps: 1) preprocessing and 2) feature extraction. In the preprocessing step, Contrast Limited Adaptive Histogram Equalization, Gaussian Filter and Median Filter are applied to enhance the image quality. Next, in the feature extraction step, Multi-level Threshold based on ISODATA and Noise Removing Techniques are adopted to remove non-microaneurysm objects. The 89 retinal fundus images from a public database DIARETDB1 are used as a dataset. By comparing with the ground truth, the proposed approach provides the reasonable results with sensitivity of 62.82%, specificity of 93.60% and accuracy of 93.43%.
{"title":"Automatic microaneurysm detection using Multi-level Threshold based on ISODATA","authors":"Tanin Intaramanee, Ratanak Khoeun, K. Chinnasarn","doi":"10.1109/JCSSE.2017.8025958","DOIUrl":"https://doi.org/10.1109/JCSSE.2017.8025958","url":null,"abstract":"Diabetic Retinopathy is one of the most serious diseases that can lead to blindness. The small swelling blood regions or microaneurysms are the early sign of Diabetic Retinopathy. Detecting that a patient has got the Diabetic Retinopathy at the earliest stage as possible can help to prevent him/her from the vision lost. However, automatic microaneurysm detection is still a challenging topic for medical image processing researchers. This is because of the varieties of microaneurysm characteristic such as size, contrast, shape, and data distribution. In this paper, we propose an approach to automatically detect microaneurysms using Multi-level Threshold based on ISODATA. The proposed method consists of two main steps: 1) preprocessing and 2) feature extraction. In the preprocessing step, Contrast Limited Adaptive Histogram Equalization, Gaussian Filter and Median Filter are applied to enhance the image quality. Next, in the feature extraction step, Multi-level Threshold based on ISODATA and Noise Removing Techniques are adopted to remove non-microaneurysm objects. The 89 retinal fundus images from a public database DIARETDB1 are used as a dataset. By comparing with the ground truth, the proposed approach provides the reasonable results with sensitivity of 62.82%, specificity of 93.60% and accuracy of 93.43%.","PeriodicalId":6460,"journal":{"name":"2017 14th International Joint Conference on Computer Science and Software Engineering (JCSSE)","volume":"144 1","pages":"1-6"},"PeriodicalIF":0.0,"publicationDate":"2017-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"77407455","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2017-07-01DOI: 10.1109/JCSSE.2017.8025918
Kittiphong Sengloiluean, N. Arch-int, S. Arch-int, Theerayut Thongkrau
Semantic Question Answering (SQA) was concerned about the natural language processing. The purpose of this study was to help facilitate the users to access the information through the natural language and to obtain the concise and needed information. As considered the current studies, it was found that this processing still encountered the problems of flexibility and accuracy, particularly those of the question processing, which was a very important processing for developing question answering system. Thus, this study proposed a semantic approach for question answering using DBpedia and WordNet. For this paper, the techniques for solving the problems were proposed consisting of (1) extracting named entities from the question and solving the problems of similarities of named entities, (2) extracting properties from the question and solving the problems of similarities of properties, and (3) evaluating the accurate capability of the answer of question. This approach evaluated the test dataset from TREC question collections, DBpedia and achieved an F-measure score of 93.43%, an average precision of 92.73%, and an average recall of 94.15% over 500 questions.
{"title":"A semantic approach for question answering using DBpedia and WordNet","authors":"Kittiphong Sengloiluean, N. Arch-int, S. Arch-int, Theerayut Thongkrau","doi":"10.1109/JCSSE.2017.8025918","DOIUrl":"https://doi.org/10.1109/JCSSE.2017.8025918","url":null,"abstract":"Semantic Question Answering (SQA) was concerned about the natural language processing. The purpose of this study was to help facilitate the users to access the information through the natural language and to obtain the concise and needed information. As considered the current studies, it was found that this processing still encountered the problems of flexibility and accuracy, particularly those of the question processing, which was a very important processing for developing question answering system. Thus, this study proposed a semantic approach for question answering using DBpedia and WordNet. For this paper, the techniques for solving the problems were proposed consisting of (1) extracting named entities from the question and solving the problems of similarities of named entities, (2) extracting properties from the question and solving the problems of similarities of properties, and (3) evaluating the accurate capability of the answer of question. This approach evaluated the test dataset from TREC question collections, DBpedia and achieved an F-measure score of 93.43%, an average precision of 92.73%, and an average recall of 94.15% over 500 questions.","PeriodicalId":6460,"journal":{"name":"2017 14th International Joint Conference on Computer Science and Software Engineering (JCSSE)","volume":"10 1","pages":"1-6"},"PeriodicalIF":0.0,"publicationDate":"2017-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"89119296","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：