Pub Date : 2018-07-01DOI: 10.1109/JCSSE.2018.8457330
Kanuengnij Kubola, P. Wayalun
One of the source used to diagnose the genetic disorders and abnormalities is the light microscopic images of the chromosomes. The first step to check for the abnormalities is to count the chromosome. Many researches have been done on chromosome counting from the images, but the results still need an improvement on complicated case, the cluster of mixing patterns of chromosomes including touching, overlapping, and other patterns. The main objective of this research is to focus and increase the performance of chromosome number determination especially the cluster with the complicated pattern of chromosome. The paper presents a new technique, to determine the number of complicated chromosome image (DNCC) using geometric features including endpoints, and intersection points of the skeletonized chromosome image after pre-processing. The results yield 100% for the clusters with single chromosome, 100% for the clusters with overlapping of two chromosomes, and 79.12% for the cluster of complicated patterns of chromosomes.
{"title":"Automatic Determination of The G-band Chromosomes Number based on Geometric Features","authors":"Kanuengnij Kubola, P. Wayalun","doi":"10.1109/JCSSE.2018.8457330","DOIUrl":"https://doi.org/10.1109/JCSSE.2018.8457330","url":null,"abstract":"One of the source used to diagnose the genetic disorders and abnormalities is the light microscopic images of the chromosomes. The first step to check for the abnormalities is to count the chromosome. Many researches have been done on chromosome counting from the images, but the results still need an improvement on complicated case, the cluster of mixing patterns of chromosomes including touching, overlapping, and other patterns. The main objective of this research is to focus and increase the performance of chromosome number determination especially the cluster with the complicated pattern of chromosome. The paper presents a new technique, to determine the number of complicated chromosome image (DNCC) using geometric features including endpoints, and intersection points of the skeletonized chromosome image after pre-processing. The results yield 100% for the clusters with single chromosome, 100% for the clusters with overlapping of two chromosomes, and 79.12% for the cluster of complicated patterns of chromosomes.","PeriodicalId":338973,"journal":{"name":"2018 15th International Joint Conference on Computer Science and Software Engineering (JCSSE)","volume":"7 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114887409","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 : 2018-07-01DOI: 10.1109/JCSSE.2018.8457346
T. A. Tran, Jarunee Duangsuwan, W. Wettayaprasit
Online reviews play an important role in helping companies or governments to improve product quality and services. However, these reviews are increasing day by day. It is difficult to go through the amount of these reviews and to summarize the important information manually. We proposed a novel Automatic Sentiment Summarization (ASS) system. This system has two phases. The first phase is the aspect-based representation used to represent ranked knowledge on aspect opinion calculated by using frequencies, polarity, and opinion strength. The second phase is the review summary generation used to automatically produce review summary by ranking aspect based on information of the aspect. The generated summary is more coherent by applying natural language generation technique. Furthermore, the proposed ASS system allows users to add new reviews in the same domain in order to update the generated summary. The experiments used the sentiment aspect dataset benchmarks such as customer product/service reviews for Canon, Nikon, and Laptop. The generated summaries from the proposed ASS system are well performed compared with other systems extractive summarization and abstractive summarization.
{"title":"A Novel Automatic Sentiment Summarization from Aspect-based Customer Reviews","authors":"T. A. Tran, Jarunee Duangsuwan, W. Wettayaprasit","doi":"10.1109/JCSSE.2018.8457346","DOIUrl":"https://doi.org/10.1109/JCSSE.2018.8457346","url":null,"abstract":"Online reviews play an important role in helping companies or governments to improve product quality and services. However, these reviews are increasing day by day. It is difficult to go through the amount of these reviews and to summarize the important information manually. We proposed a novel Automatic Sentiment Summarization (ASS) system. This system has two phases. The first phase is the aspect-based representation used to represent ranked knowledge on aspect opinion calculated by using frequencies, polarity, and opinion strength. The second phase is the review summary generation used to automatically produce review summary by ranking aspect based on information of the aspect. The generated summary is more coherent by applying natural language generation technique. Furthermore, the proposed ASS system allows users to add new reviews in the same domain in order to update the generated summary. The experiments used the sentiment aspect dataset benchmarks such as customer product/service reviews for Canon, Nikon, and Laptop. The generated summaries from the proposed ASS system are well performed compared with other systems extractive summarization and abstractive summarization.","PeriodicalId":338973,"journal":{"name":"2018 15th International Joint Conference on Computer Science and Software Engineering (JCSSE)","volume":"70 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114537835","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 : 2018-07-01DOI: 10.1109/JCSSE.2018.8457361
Narit Hnoohom, Sumeth Yuenyong
We present an image classification of Dhamma Esan characters by fine-tuning the Inception V3 deep neural network trained on the ImageNet dataset. Dhamma Esan is a traditional alphabet used in the north-eastern region of Thailand, primarily written on Corypha leaves for the purpose of recording Buddhist scriptures. Preservation of these historical documents calls for the ability to classify the characters of the alphabet in order to facilitate digital indexing and searching, as well as assist anyone trying to read them. Our dataset consists of over 70,000 Dhamma Esan character images, much larger than any previous work. The result of ten-fold cross-validation showed that our model had 100% accuracy for four folds, and 99.99% for the other six folds. The previous best accuracy reported was 97.77%. We also developed a Dhamma Esan character classification web service where users can upload images of characters and get immediate classification results as well as mapping to the modern Thai alphabet.
{"title":"Classification of Dhamma Esan Characters By Transfer Learning of a Deep Neural Network","authors":"Narit Hnoohom, Sumeth Yuenyong","doi":"10.1109/JCSSE.2018.8457361","DOIUrl":"https://doi.org/10.1109/JCSSE.2018.8457361","url":null,"abstract":"We present an image classification of Dhamma Esan characters by fine-tuning the Inception V3 deep neural network trained on the ImageNet dataset. Dhamma Esan is a traditional alphabet used in the north-eastern region of Thailand, primarily written on Corypha leaves for the purpose of recording Buddhist scriptures. Preservation of these historical documents calls for the ability to classify the characters of the alphabet in order to facilitate digital indexing and searching, as well as assist anyone trying to read them. Our dataset consists of over 70,000 Dhamma Esan character images, much larger than any previous work. The result of ten-fold cross-validation showed that our model had 100% accuracy for four folds, and 99.99% for the other six folds. The previous best accuracy reported was 97.77%. We also developed a Dhamma Esan character classification web service where users can upload images of characters and get immediate classification results as well as mapping to the modern Thai alphabet.","PeriodicalId":338973,"journal":{"name":"2018 15th International Joint Conference on Computer Science and Software Engineering (JCSSE)","volume":"59 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122612476","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 : 2018-07-01DOI: 10.1109/JCSSE.2018.8457331
Nattachai Tretasayuth, P. Vateekul, P. Boonkwan
Machine reading comprehension (MC) is one of the most important problems in natural language processing. Most of the previous works rely heavily on features engineering and handcrafting techniques. Since the release of SQuAD, a large-scale MC dataset, many deep learning models have been proposed. However, these models are limited by the soft attention mechanism only relied on keywords that appears in a question. Therefore, the performance is always poor in a question that needs to infer an answer from multiple sentences, which cannot depend on keywords in a question. In this paper, we propose a deep learning model that incorporates coreference information to improve the prediction performance especially on multiple sentence question. We also propose the bi-directional answering technique that can help the model avoid a local maxima of the single directional answering method in a traditional model. The results have shown that our approach outperforms the baseline in terms of F1 and Exact Match (EM).
{"title":"Enhance Machine Reading Comprehension on Multiple Sentence Questions with Gated and Dense Coreference Information","authors":"Nattachai Tretasayuth, P. Vateekul, P. Boonkwan","doi":"10.1109/JCSSE.2018.8457331","DOIUrl":"https://doi.org/10.1109/JCSSE.2018.8457331","url":null,"abstract":"Machine reading comprehension (MC) is one of the most important problems in natural language processing. Most of the previous works rely heavily on features engineering and handcrafting techniques. Since the release of SQuAD, a large-scale MC dataset, many deep learning models have been proposed. However, these models are limited by the soft attention mechanism only relied on keywords that appears in a question. Therefore, the performance is always poor in a question that needs to infer an answer from multiple sentences, which cannot depend on keywords in a question. In this paper, we propose a deep learning model that incorporates coreference information to improve the prediction performance especially on multiple sentence question. We also propose the bi-directional answering technique that can help the model avoid a local maxima of the single directional answering method in a traditional model. The results have shown that our approach outperforms the baseline in terms of F1 and Exact Match (EM).","PeriodicalId":338973,"journal":{"name":"2018 15th International Joint Conference on Computer Science and Software Engineering (JCSSE)","volume":"83 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130369339","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 : 2018-07-01DOI: 10.1109/JCSSE.2018.8457324
Chanavit Athavipach, S. Pan-Ngum, P. Israsena
This study focused on building a low-cost wearable EEG device multiple hour usage. The device suitable for long period monitoring is in-the-ear EEG, which has desirable wearable characteristics. With electrode in an earbud, it is relatively simple to install and wear. The in-the-ear prototype in this study was built from earphone rubber as an earpiece and silver-adhesive fabric as electrodes. Raw materials cost 3 dollar per piece. The impedance measurement from in-the-ear EEG is comparable to those of commercial electrodes. Signal verifications were conducted by teeth clenching, ASSR, MMN, and correlation. The signal verification results show that there is a strong correlation between in-the-ear EEG and T7/T8 signals. (γ-coefficient = 0.912)
{"title":"Development of Low-Cost in-the-Ear EEG Prototype","authors":"Chanavit Athavipach, S. Pan-Ngum, P. Israsena","doi":"10.1109/JCSSE.2018.8457324","DOIUrl":"https://doi.org/10.1109/JCSSE.2018.8457324","url":null,"abstract":"This study focused on building a low-cost wearable EEG device multiple hour usage. The device suitable for long period monitoring is in-the-ear EEG, which has desirable wearable characteristics. With electrode in an earbud, it is relatively simple to install and wear. The in-the-ear prototype in this study was built from earphone rubber as an earpiece and silver-adhesive fabric as electrodes. Raw materials cost 3 dollar per piece. The impedance measurement from in-the-ear EEG is comparable to those of commercial electrodes. Signal verifications were conducted by teeth clenching, ASSR, MMN, and correlation. The signal verification results show that there is a strong correlation between in-the-ear EEG and T7/T8 signals. (γ-coefficient = 0.912)","PeriodicalId":338973,"journal":{"name":"2018 15th International Joint Conference on Computer Science and Software Engineering (JCSSE)","volume":"101 8","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114120414","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 : 2018-07-01DOI: 10.1109/JCSSE.2018.8457364
H. Esmaeili, T. Phoka
Convolutional Neural Network (CNN) is taking a big role in image classification. B ut f ully t raining i mages by using CNN takes a plenty of time and uses a very large data set. This paper will focus on transfer learning, a technique that takes a pre-trained model e.g., Inception, Resnet or MobileNets models then retrains the model from the existing weights for a new classification p roblem. T he r etrain t echnique drastically decreases time spending in the training process and many fewer number of image data is required to yield high accuracy trained networks. This paper considers the problem of leaf image classification t hat t he e xisting a pproaches t ake m uch e ffort to choose various types of imagefeatures for classification. This also reflects p utting b iases b y c hoosing s ome f eatures a nd ignoring the other information in images. This paper will conduct the experiments in accuracy comparison between traditional leaf image classification using image processing techniques and CNN with transfer learning. The result will show that without much knowledge in image processing, the leaf image classification can be achieved with high accuracy using the transfer learning technique.
{"title":"Transfer Learning for Leaf Classification with Convolutional Neural Networks","authors":"H. Esmaeili, T. Phoka","doi":"10.1109/JCSSE.2018.8457364","DOIUrl":"https://doi.org/10.1109/JCSSE.2018.8457364","url":null,"abstract":"Convolutional Neural Network (CNN) is taking a big role in image classification. B ut f ully t raining i mages by using CNN takes a plenty of time and uses a very large data set. This paper will focus on transfer learning, a technique that takes a pre-trained model e.g., Inception, Resnet or MobileNets models then retrains the model from the existing weights for a new classification p roblem. T he r etrain t echnique drastically decreases time spending in the training process and many fewer number of image data is required to yield high accuracy trained networks. This paper considers the problem of leaf image classification t hat t he e xisting a pproaches t ake m uch e ffort to choose various types of imagefeatures for classification. This also reflects p utting b iases b y c hoosing s ome f eatures a nd ignoring the other information in images. This paper will conduct the experiments in accuracy comparison between traditional leaf image classification using image processing techniques and CNN with transfer learning. The result will show that without much knowledge in image processing, the leaf image classification can be achieved with high accuracy using the transfer learning technique.","PeriodicalId":338973,"journal":{"name":"2018 15th International Joint Conference on Computer Science and Software Engineering (JCSSE)","volume":"31 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122001487","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}
environmental awareness has been concerned as the primary factor for environmental sustainability. It can be said that people, especially young adults, should be educated to concern and aware of environmental protection. This paper addresses how to stimulate people to taking care of tree and plant by proposing a game-based learning system for plant monitoring based on Internet of Thing (IoT) technology. A novel approach of harmonization between the three main components, namely, real plant caring, game-based learning, and IoT technology, are discussed and proposed. A developed game-based learning system has been introduced and the experimental study of learners’ satisfaction of applying the proposed game in practical use has been reported.
{"title":"A Game-Based Learning System for Plant Monitoring Based on IoT Technology","authors":"Preecha Tangworakitthaworn, Vachirawit Tengchaisri, Kanokwan Rungsuptaweekoon, Tanapat Samakit","doi":"10.1109/JCSSE.2018.8457332","DOIUrl":"https://doi.org/10.1109/JCSSE.2018.8457332","url":null,"abstract":"environmental awareness has been concerned as the primary factor for environmental sustainability. It can be said that people, especially young adults, should be educated to concern and aware of environmental protection. This paper addresses how to stimulate people to taking care of tree and plant by proposing a game-based learning system for plant monitoring based on Internet of Thing (IoT) technology. A novel approach of harmonization between the three main components, namely, real plant caring, game-based learning, and IoT technology, are discussed and proposed. A developed game-based learning system has been introduced and the experimental study of learners’ satisfaction of applying the proposed game in practical use has been reported.","PeriodicalId":338973,"journal":{"name":"2018 15th International Joint Conference on Computer Science and Software Engineering (JCSSE)","volume":"27 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123781880","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 : 2018-07-01DOI: 10.1109/JCSSE.2018.8457180
Taweechai Nuntawisuttiwong, N. Dejdumrong
This paper presents a method to approximate Béziercurves by a sequence of arc splines with inscribed regular polygon. The proposed algorithm uses the arc length approximation method in subdividing a Bézier curve into subcurves which have equal arc length. Each subcurve is interpolated with a line segment which is a side of the inscribed polygon of a curve. Curve segments are then clustered into a circular arc by evaluating interior angles of inscribed polygon. This method represents a Bézier curve with the minimum number of circular arcs and acceptable errors. The experimental results are provided the similarity of original curve and approximated arc spline. The approximated arc spline which is the result of proposed algorithm is compatible for vector and raster graphic format.
{"title":"An Approach to Bézier Curve Approximation by Circular Arcs","authors":"Taweechai Nuntawisuttiwong, N. Dejdumrong","doi":"10.1109/JCSSE.2018.8457180","DOIUrl":"https://doi.org/10.1109/JCSSE.2018.8457180","url":null,"abstract":"This paper presents a method to approximate Béziercurves by a sequence of arc splines with inscribed regular polygon. The proposed algorithm uses the arc length approximation method in subdividing a Bézier curve into subcurves which have equal arc length. Each subcurve is interpolated with a line segment which is a side of the inscribed polygon of a curve. Curve segments are then clustered into a circular arc by evaluating interior angles of inscribed polygon. This method represents a Bézier curve with the minimum number of circular arcs and acceptable errors. The experimental results are provided the similarity of original curve and approximated arc spline. The approximated arc spline which is the result of proposed algorithm is compatible for vector and raster graphic format.","PeriodicalId":338973,"journal":{"name":"2018 15th International Joint Conference on Computer Science and Software Engineering (JCSSE)","volume":"60 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124184988","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 : 2018-07-01DOI: 10.1109/JCSSE.2018.8457366
Nattakarn Phaphoom, Wongduan Saelee, T. Somjaitaweeporn, Sumeth Yuenyong, Jian Qu
An enterprise resource planning (ERP) system offers vital capabilities to promote business competitiveness, operational excellence, and cost efficiency. Despite of advance in technology and research, enterprises are still struggling in the process of implementing and routinizing the use of ERP, as well as, achieving an optimal range of benefits it offers. The adoption challenges seem to be increasing in the context of developing countries where organizational cultures, attitude towards changes and ways of work are different than the context where ERP software was initiated. This study serves as a source of empirical evidences showing how ERP implementation can be carried out successfully for a SME manufacturing company in Thailand. The analysis was based on a series of in-depth interviews with the management, middle managers, and operational staffs of the company, which has integrated ERP to its enterprise processes and has enjoyed significant benefits of it for seven years. We combined qualitative analysis with a novel quantitative method called fuzzy weighting. Not only does the method offer better insight to the cases than the traditional approach, it also promotes internal validity of the analysis.
{"title":"A Combined Method for Analysing Critical Success Factors on ERP Implementation","authors":"Nattakarn Phaphoom, Wongduan Saelee, T. Somjaitaweeporn, Sumeth Yuenyong, Jian Qu","doi":"10.1109/JCSSE.2018.8457366","DOIUrl":"https://doi.org/10.1109/JCSSE.2018.8457366","url":null,"abstract":"An enterprise resource planning (ERP) system offers vital capabilities to promote business competitiveness, operational excellence, and cost efficiency. Despite of advance in technology and research, enterprises are still struggling in the process of implementing and routinizing the use of ERP, as well as, achieving an optimal range of benefits it offers. The adoption challenges seem to be increasing in the context of developing countries where organizational cultures, attitude towards changes and ways of work are different than the context where ERP software was initiated. This study serves as a source of empirical evidences showing how ERP implementation can be carried out successfully for a SME manufacturing company in Thailand. The analysis was based on a series of in-depth interviews with the management, middle managers, and operational staffs of the company, which has integrated ERP to its enterprise processes and has enjoyed significant benefits of it for seven years. We combined qualitative analysis with a novel quantitative method called fuzzy weighting. Not only does the method offer better insight to the cases than the traditional approach, it also promotes internal validity of the analysis.","PeriodicalId":338973,"journal":{"name":"2018 15th International Joint Conference on Computer Science and Software Engineering (JCSSE)","volume":"128 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128099118","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：