Chronic wound segmentation is an essential task for evaluating wound and its recovery progress. A physician usually measures a wound area to choose proper treatment according to wound conditions. However, precise measurement needs accurate image-region segmentation. With the advent of deep learning for semantic image segmentation, accuracy of region segmentation is dramatically higher than traditional methods. Unfortunately, semantic segmentation in prior work did not produce satisfactory outputs in wound image segmentation, even with a large training dataset. This work, therefore, rethinks about the challenge and aims at not only improving segmentation accuracy, but also studying the impact of wound tissue types and color on accuracy. Since an end-to-end approach of semantic segmentation in prior work performed relatively poorly, the proposed method employs both image processing and deep learning techniques. The experiments indicated that slough was the most challenging tissue to be segmented. Also, properly increasing color variety of wound images significantly improved segmentation performance. The accuracy of the proposed method was 72%, 40%, and 53% in terms of intersection over union for granulation, necrosis, and slough wound tissue types, respectively. The proposed method outperformed a prior end-to-end approach, even though this method employed particularly simpler neural network models and much smaller number of training images.
{"title":"Study of Chronic Wound Image Segmentation: Impact of Tissue Type and Color Data Augmentation","authors":"Nanthipath Pholberdee, Chanok Pathompatai, Pinyo Taeprasartsit","doi":"10.1109/JCSSE.2018.8457392","DOIUrl":"https://doi.org/10.1109/JCSSE.2018.8457392","url":null,"abstract":"Chronic wound segmentation is an essential task for evaluating wound and its recovery progress. A physician usually measures a wound area to choose proper treatment according to wound conditions. However, precise measurement needs accurate image-region segmentation. With the advent of deep learning for semantic image segmentation, accuracy of region segmentation is dramatically higher than traditional methods. Unfortunately, semantic segmentation in prior work did not produce satisfactory outputs in wound image segmentation, even with a large training dataset. This work, therefore, rethinks about the challenge and aims at not only improving segmentation accuracy, but also studying the impact of wound tissue types and color on accuracy. Since an end-to-end approach of semantic segmentation in prior work performed relatively poorly, the proposed method employs both image processing and deep learning techniques. The experiments indicated that slough was the most challenging tissue to be segmented. Also, properly increasing color variety of wound images significantly improved segmentation performance. The accuracy of the proposed method was 72%, 40%, and 53% in terms of intersection over union for granulation, necrosis, and slough wound tissue types, respectively. The proposed method outperformed a prior end-to-end approach, even though this method employed particularly simpler neural network models and much smaller number of training images.","PeriodicalId":338973,"journal":{"name":"2018 15th International Joint Conference on Computer Science and Software Engineering (JCSSE)","volume":"46 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":"132103365","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.2018.8457365
Narong Boonsirisumpun, Wichai Puarungroj
The Thai traditional woven fabrics are handicraft products indicate the flourish of Thai national culture and creativity of the nation. Many provinces have a long history of their own patterns on hand-woven fabric weaving style. One of the well-known provinces is Loei. Several villages produce their own unique styles in the woven pattern: Tai Loei, Tai Dam, or Tai Lue. Local people are able to recognize and distinguish the difference between these fabric groups but it is not easy for people from other areas, especially tourists to discriminate them. Moreover, the most complicated one is to train a machine to tell the difference between these fabric patterns. The issues about machine to classify the identity of something used to be the difficult problem in the area of pattern recognition and image classification. But the advancement in the popular algorithms of Deep Neural Network on image recognition opens the new opportunity to accomplish these problems with the greatly improved result. In this paper, we proposed to apply the Deep Neural Network techniques to solve Thai Loei woven fabric pattern recognition problem. For helping the machine to recognize the local weaving style and for the tourist to understand the exclusive on each local tradition.
{"title":"Loei Fabric Weaving Pattern Recognition Using Deep Neural Network","authors":"Narong Boonsirisumpun, Wichai Puarungroj","doi":"10.1109/JCSSE.2018.8457365","DOIUrl":"https://doi.org/10.1109/JCSSE.2018.8457365","url":null,"abstract":"The Thai traditional woven fabrics are handicraft products indicate the flourish of Thai national culture and creativity of the nation. Many provinces have a long history of their own patterns on hand-woven fabric weaving style. One of the well-known provinces is Loei. Several villages produce their own unique styles in the woven pattern: Tai Loei, Tai Dam, or Tai Lue. Local people are able to recognize and distinguish the difference between these fabric groups but it is not easy for people from other areas, especially tourists to discriminate them. Moreover, the most complicated one is to train a machine to tell the difference between these fabric patterns. The issues about machine to classify the identity of something used to be the difficult problem in the area of pattern recognition and image classification. But the advancement in the popular algorithms of Deep Neural Network on image recognition opens the new opportunity to accomplish these problems with the greatly improved result. In this paper, we proposed to apply the Deep Neural Network techniques to solve Thai Loei woven fabric pattern recognition problem. For helping the machine to recognize the local weaving style and for the tourist to understand the exclusive on each local tradition.","PeriodicalId":338973,"journal":{"name":"2018 15th International Joint Conference on Computer Science and Software Engineering (JCSSE)","volume":"67 2 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":"126966001","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.2018.8457369
Tanut Kongkhaensarn, M. Piantanakulchai
This research focuses on comparing probabilistic neural network with multilayer perceptron and support vector machine for detecting traffic incident on expressway based on simulation data. The data used in this experiment contains speed, density, occupancy, traffic flow, and time headway at specific location on expressway, as well as both upstream and downstream detectors. These data are generated by using the traffic modelling software, AIMSUN. Four indicators are used in evaluating the model’s performance which are detection rate, false alarm rate, mean time to detect, and classification rate. The result of these three models is not much different. These three models can mostly detect traffic incident and greatly classify between non-incident and incident situation. These model’s accuracy are more than 95 percent in training data and more than 75 percent in validating data.
{"title":"Comparison of probabilistic neural network with multilayer perceptron and support vector machine for detecting traffic incident on expressway based on simulation data","authors":"Tanut Kongkhaensarn, M. Piantanakulchai","doi":"10.1109/JCSSE.2018.8457369","DOIUrl":"https://doi.org/10.1109/JCSSE.2018.8457369","url":null,"abstract":"This research focuses on comparing probabilistic neural network with multilayer perceptron and support vector machine for detecting traffic incident on expressway based on simulation data. The data used in this experiment contains speed, density, occupancy, traffic flow, and time headway at specific location on expressway, as well as both upstream and downstream detectors. These data are generated by using the traffic modelling software, AIMSUN. Four indicators are used in evaluating the model’s performance which are detection rate, false alarm rate, mean time to detect, and classification rate. The result of these three models is not much different. These three models can mostly detect traffic incident and greatly classify between non-incident and incident situation. These model’s accuracy are more than 95 percent in training data and more than 75 percent in validating data.","PeriodicalId":338973,"journal":{"name":"2018 15th International Joint Conference on Computer Science and Software Engineering (JCSSE)","volume":"3 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":"115178927","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}
Kantinee Katchapakirin, K. Wongpatikaseree, P. Yomaboot, Y. Kaewpitakkun
Depression is one of the leading mental health problems. It is a cause of psychological disability and economic burden to a country. Around 1.5 Thai people suffer from depression and its prevalence has been growing up fast. Although it is a serious psychological problem, less than a half of those who have this emotional problem gained access to mental health service. This could be a result of many factors including having lack awareness about the disease. One of the solutions would be providing a tool that depression could be easily and early detected. This would help people to be aware of their emotional states and seek help from professional services. Given Facebook is the most popular social network platform in Thailand, it could be a largescale resource to develop a depression detection tool. This research employs Natural Language Processing (NLP) techniques to develop a depression detection algorithm for the Thai language on Facebook where people use it as a tool for sharing opinions, feelings, and life events. Results from 35 Facebook users indicated that Facebook behaviours could predict depression level.
{"title":"Facebook Social Media for Depression Detection in the Thai Community","authors":"Kantinee Katchapakirin, K. Wongpatikaseree, P. Yomaboot, Y. Kaewpitakkun","doi":"10.29007/TSCC","DOIUrl":"https://doi.org/10.29007/TSCC","url":null,"abstract":"Depression is one of the leading mental health problems. It is a cause of psychological disability and economic burden to a country. Around 1.5 Thai people suffer from depression and its prevalence has been growing up fast. Although it is a serious psychological problem, less than a half of those who have this emotional problem gained access to mental health service. This could be a result of many factors including having lack awareness about the disease. One of the solutions would be providing a tool that depression could be easily and early detected. This would help people to be aware of their emotional states and seek help from professional services. Given Facebook is the most popular social network platform in Thailand, it could be a largescale resource to develop a depression detection tool. This research employs Natural Language Processing (NLP) techniques to develop a depression detection algorithm for the Thai language on Facebook where people use it as a tool for sharing opinions, feelings, and life events. Results from 35 Facebook users indicated that Facebook behaviours could predict depression level.","PeriodicalId":338973,"journal":{"name":"2018 15th International Joint Conference on Computer Science and Software Engineering (JCSSE)","volume":"57 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-06-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128918886","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 : 2014-09-09DOI: 10.1109/JCSSE.2018.8457173
Sunsern Cheamanunkul, Y. Freund
Handwriting is a natural and versatile method for human-computer interaction, especially on small mobile devices such as smart phones. However, as handwriting varies significantly from person to person, it is difficult to design handwriting recognizers that perform well for all users. A natural solution is to use machine learning to adapt the recognizer to the user. One complicating factor is that, as the computer adapts to the user, the user also adapts to the computer and probably changes their handwriting. This paper investigates the dynamics of coadaptation, a process in which both the computer and the user are adapting their behaviors in order to improve the speed and accuracy of the communication through handwriting. We devised an information-theoretic framework for quantifying the efficiency of a handwriting system where the system includes both the user and the computer. Using this framework, we analyzed data collected from an adaptive handwriting recognition system and characterized the impact of machine adaptation and of human adaptation. We found that both machine adaptation and human adaptation have significant impact on the input rate and must be considered together in order to improve the efficiency of the system as a whole.
{"title":"Co-adaptation in a Handwriting Recognition System","authors":"Sunsern Cheamanunkul, Y. Freund","doi":"10.1109/JCSSE.2018.8457173","DOIUrl":"https://doi.org/10.1109/JCSSE.2018.8457173","url":null,"abstract":"Handwriting is a natural and versatile method for human-computer interaction, especially on small mobile devices such as smart phones. However, as handwriting varies significantly from person to person, it is difficult to design handwriting recognizers that perform well for all users. A natural solution is to use machine learning to adapt the recognizer to the user. One complicating factor is that, as the computer adapts to the user, the user also adapts to the computer and probably changes their handwriting. This paper investigates the dynamics of coadaptation, a process in which both the computer and the user are adapting their behaviors in order to improve the speed and accuracy of the communication through handwriting. We devised an information-theoretic framework for quantifying the efficiency of a handwriting system where the system includes both the user and the computer. Using this framework, we analyzed data collected from an adaptive handwriting recognition system and characterized the impact of machine adaptation and of human adaptation. We found that both machine adaptation and human adaptation have significant impact on the input rate and must be considered together in order to improve the efficiency of the system as a whole.","PeriodicalId":338973,"journal":{"name":"2018 15th International Joint Conference on Computer Science and Software Engineering (JCSSE)","volume":"63 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2014-09-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114223113","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：