Pub Date : 2019-08-01DOI: 10.1109/Ubi-Media.2019.00057
Chen Hong, Chih-Yang Lin, T. Shih
Data-driven object detection techniques are widely applied to a variety of practical areas (i.e., automatic robots, self-driving vehicles, defect detection, and face detection). Nowadays, many research projects have been proposed to improve the accuracy of computer vision applications. In this paper, we propose an automatic signboard detection method and a semi-automatic ground truth generation method to help visually impaired people walk on streets in Taiwan. We consider that when visually impaired people walk down the street, they may be interested in certain stores. Therefore, we collect images of 12 kinds of the most popular stores in people's daily lives. The collected street images number over 5 million from 6 major cities in Taiwan; however, only about 1% of images contain a signboard. We propose a hierarchical object detection module to pre-label uncertain samples. Based on this module, semi-automatic ground truth generation can be achieved.
{"title":"Automatic Signboard Detection and Semi-Automatic Ground Truth Generation","authors":"Chen Hong, Chih-Yang Lin, T. Shih","doi":"10.1109/Ubi-Media.2019.00057","DOIUrl":"https://doi.org/10.1109/Ubi-Media.2019.00057","url":null,"abstract":"Data-driven object detection techniques are widely applied to a variety of practical areas (i.e., automatic robots, self-driving vehicles, defect detection, and face detection). Nowadays, many research projects have been proposed to improve the accuracy of computer vision applications. In this paper, we propose an automatic signboard detection method and a semi-automatic ground truth generation method to help visually impaired people walk on streets in Taiwan. We consider that when visually impaired people walk down the street, they may be interested in certain stores. Therefore, we collect images of 12 kinds of the most popular stores in people's daily lives. The collected street images number over 5 million from 6 major cities in Taiwan; however, only about 1% of images contain a signboard. We propose a hierarchical object detection module to pre-label uncertain samples. Based on this module, semi-automatic ground truth generation can be achieved.","PeriodicalId":259542,"journal":{"name":"2019 Twelfth International Conference on Ubi-Media Computing (Ubi-Media)","volume":"14 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126324542","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 : 2019-08-01DOI: 10.1109/Ubi-Media.2019.00070
Suparp Kanyacome, Pitak Paksanondha, Souksan Vilavong, P. Jaikaew
This feasibility study investigated the needs of ICT training courses to be used as the primary data for developing an ICT curriculum in the service area, 4 provinces, of Champasak University, Lao PDR. Quantitative methodology was employed using a questionnaire comprising of 51 questions under 24 items. 600 questionnaires were distributed in four provinces and 530 were returned. Data were analyzed using percentage, average value, standard deviations and the One-Way ANOVA analysis. The result illustrated four main topics including the target group characteristics, ICT behavior, ICT skills, ICT course requirements and needs of ICT professionals. Additionally, it was found that 1) the most three preferable ICT courses among respondents are spreadsheet, word processing and website developing, 2) the most ten popular ICT professionals are IT supporter, network administrator, programmer, database administrator, computer aid designer, multimedia creator, website developer, system analyst, CRM / ERP operator and ICT consultant and 3) as many as 82.30% of executives from various organizations had expressed their needs to encourage their staff to increase ICT skill via attending trainings.
{"title":"ICT Curriculum Requirements in the Service Area of Champasak University, Laos","authors":"Suparp Kanyacome, Pitak Paksanondha, Souksan Vilavong, P. Jaikaew","doi":"10.1109/Ubi-Media.2019.00070","DOIUrl":"https://doi.org/10.1109/Ubi-Media.2019.00070","url":null,"abstract":"This feasibility study investigated the needs of ICT training courses to be used as the primary data for developing an ICT curriculum in the service area, 4 provinces, of Champasak University, Lao PDR. Quantitative methodology was employed using a questionnaire comprising of 51 questions under 24 items. 600 questionnaires were distributed in four provinces and 530 were returned. Data were analyzed using percentage, average value, standard deviations and the One-Way ANOVA analysis. The result illustrated four main topics including the target group characteristics, ICT behavior, ICT skills, ICT course requirements and needs of ICT professionals. Additionally, it was found that 1) the most three preferable ICT courses among respondents are spreadsheet, word processing and website developing, 2) the most ten popular ICT professionals are IT supporter, network administrator, programmer, database administrator, computer aid designer, multimedia creator, website developer, system analyst, CRM / ERP operator and ICT consultant and 3) as many as 82.30% of executives from various organizations had expressed their needs to encourage their staff to increase ICT skill via attending trainings.","PeriodicalId":259542,"journal":{"name":"2019 Twelfth International Conference on Ubi-Media Computing (Ubi-Media)","volume":"18 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131709862","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 : 2019-08-01DOI: 10.1109/Ubi-Media.2019.00068
D. Tumenbayar, A. Amarzaya, T. Navchaa
Mongolia is a country with low population density in the world. Provision of sustainable and up to date professional development for in-service teachers is one of the biggest issues in the education system of the country. Institute of Teachers Professional Development (ITPD) is a central organization of the Ministry of Education responsible for teacher's developments. ITPD started its online training system for teachers from 2014. In this paper we will study structural relationships among in-service teacher's behavioral intention, perceived usefulness and perceived ease of use, and the quality of this online system using a Technology acceptance model. Important conclusions of this study are as follows. The high quality of the online training system makes it more easy to use for teachers. In-service teachers' perceived usefulness and system quality are most important determinants of intention to use the system in the future.
{"title":"Structural Relationships Among In-Service Teacher's Behavioral Intention, Perceived Usefulness, Perceived Ease of Use and Online Professional Development System Quality","authors":"D. Tumenbayar, A. Amarzaya, T. Navchaa","doi":"10.1109/Ubi-Media.2019.00068","DOIUrl":"https://doi.org/10.1109/Ubi-Media.2019.00068","url":null,"abstract":"Mongolia is a country with low population density in the world. Provision of sustainable and up to date professional development for in-service teachers is one of the biggest issues in the education system of the country. Institute of Teachers Professional Development (ITPD) is a central organization of the Ministry of Education responsible for teacher's developments. ITPD started its online training system for teachers from 2014. In this paper we will study structural relationships among in-service teacher's behavioral intention, perceived usefulness and perceived ease of use, and the quality of this online system using a Technology acceptance model. Important conclusions of this study are as follows. The high quality of the online training system makes it more easy to use for teachers. In-service teachers' perceived usefulness and system quality are most important determinants of intention to use the system in the future.","PeriodicalId":259542,"journal":{"name":"2019 Twelfth International Conference on Ubi-Media Computing (Ubi-Media)","volume":"51 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124598378","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 : 2019-08-01DOI: 10.1109/Ubi-Media.2019.00047
Mou Wang, Xiao-Lei Zhang, S. Rahardja
Acquisition device clustering based on speech recordings is a critical problem in the field of speech forensic, especially for mobile phone clustering (MPC). Previous studies on mobile phone recognition or clustering can be categorized ainly to two approaches. One approach utilizes handcraft features such as Mel-frequency cepstral coefficients (MFCCs), while the other uses learned features from neural networks. In this paper, we propose a hybrid system for MPC. Specifically, we first extract supervectors from MFCCs by a Gaussian mixture model and obtain the deep bottleneck features by a deep auto-encoder network. Then, we feed the two features to spectral clustering respectively, which outputs two low-dimensional vectors by the Laplacian eigen-decomposition of the spectral clustering. Finally, we fuse the two vectors and conduct clustering on the fused feature by k-means. The performance of the proposed method is evaluated on a public corpus—MOBIPHONE. The results show that the proposed method is effective, and moreover, the supervectors and deep bottleneck features provide complementary information of the intrinsic characteristics of the speech recordings recorded by the mobile phones.
{"title":"A Hybrid Approach for Mobile Phone Clustering with Speech Recordings","authors":"Mou Wang, Xiao-Lei Zhang, S. Rahardja","doi":"10.1109/Ubi-Media.2019.00047","DOIUrl":"https://doi.org/10.1109/Ubi-Media.2019.00047","url":null,"abstract":"Acquisition device clustering based on speech recordings is a critical problem in the field of speech forensic, especially for mobile phone clustering (MPC). Previous studies on mobile phone recognition or clustering can be categorized ainly to two approaches. One approach utilizes handcraft features such as Mel-frequency cepstral coefficients (MFCCs), while the other uses learned features from neural networks. In this paper, we propose a hybrid system for MPC. Specifically, we first extract supervectors from MFCCs by a Gaussian mixture model and obtain the deep bottleneck features by a deep auto-encoder network. Then, we feed the two features to spectral clustering respectively, which outputs two low-dimensional vectors by the Laplacian eigen-decomposition of the spectral clustering. Finally, we fuse the two vectors and conduct clustering on the fused feature by k-means. The performance of the proposed method is evaluated on a public corpus—MOBIPHONE. The results show that the proposed method is effective, and moreover, the supervectors and deep bottleneck features provide complementary information of the intrinsic characteristics of the speech recordings recorded by the mobile phones.","PeriodicalId":259542,"journal":{"name":"2019 Twelfth International Conference on Ubi-Media Computing (Ubi-Media)","volume":"18 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"120947511","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 : 2019-08-01DOI: 10.1109/Ubi-Media.2019.00073
Qiuju Si, Baichang Zhong
This paper conducted an empirical study to investigate the effects of troubleshooting tasks with prompt information on students' transfer performance in robotics education, while taking conventional troubleshooting teaching (troubleshooting tasks without prompt information) as a reference. 84 pupils from two classes in the first grade of the junior high school participated in the experiment. Results indicated: (1) There is no significant difference in near transfer performance between the troubleshooting tasks with prompt information and the conventional troubleshooting tasks. (2) Compared with conventional troubleshooting tasks, providing prompt information to troubleshooting tasks can effectively foster students' far transfer performance. Considering that learners' knowledge level is an important factor affecting transfer of learning, the different learning phase should be taken into account when providing prompt information for learners in robotics troubleshooting teaching in the future.
{"title":"Effects of Troubleshooting Tasks with Prompt Information on Students' Transfer Performance in Robotics Education","authors":"Qiuju Si, Baichang Zhong","doi":"10.1109/Ubi-Media.2019.00073","DOIUrl":"https://doi.org/10.1109/Ubi-Media.2019.00073","url":null,"abstract":"This paper conducted an empirical study to investigate the effects of troubleshooting tasks with prompt information on students' transfer performance in robotics education, while taking conventional troubleshooting teaching (troubleshooting tasks without prompt information) as a reference. 84 pupils from two classes in the first grade of the junior high school participated in the experiment. Results indicated: (1) There is no significant difference in near transfer performance between the troubleshooting tasks with prompt information and the conventional troubleshooting tasks. (2) Compared with conventional troubleshooting tasks, providing prompt information to troubleshooting tasks can effectively foster students' far transfer performance. Considering that learners' knowledge level is an important factor affecting transfer of learning, the different learning phase should be taken into account when providing prompt information for learners in robotics troubleshooting teaching in the future.","PeriodicalId":259542,"journal":{"name":"2019 Twelfth International Conference on Ubi-Media Computing (Ubi-Media)","volume":"42 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133658775","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 : 2019-08-01DOI: 10.1109/Ubi-Media.2019.00034
Taru Kanchan, Minqiang Jiang, N. Ling
In video coding, High Efficiency Video Coding (HEVC) introduced 35 intra prediction modes. It employed a three most probable modes (MPM) based method to improve intra mode coding. This method significantly improved the performance by extracting three MPMs out of the 35 intra modes. Joint Video Exploration Team (JVET) defines 67 intra prediction modes for a possible future video coding standard. In the latest JVET development, six MPMs are chosen, and the remaining sixty-one modes are divided into 16 "selected" and 45 "non-selected" modes. These non-MPM modes are coded using fixed length coding. This paper proposes a method to select and order these non-MPM modes based on probability statistics. The modes that fall into selected category are coded using shorter codes and non-selected modes are coded using larger codes. Experimental results show performance improvement when compared to that of JEM 7.0
{"title":"Non-MPM Mode Coding for Intra Prediction in Video Coding","authors":"Taru Kanchan, Minqiang Jiang, N. Ling","doi":"10.1109/Ubi-Media.2019.00034","DOIUrl":"https://doi.org/10.1109/Ubi-Media.2019.00034","url":null,"abstract":"In video coding, High Efficiency Video Coding (HEVC) introduced 35 intra prediction modes. It employed a three most probable modes (MPM) based method to improve intra mode coding. This method significantly improved the performance by extracting three MPMs out of the 35 intra modes. Joint Video Exploration Team (JVET) defines 67 intra prediction modes for a possible future video coding standard. In the latest JVET development, six MPMs are chosen, and the remaining sixty-one modes are divided into 16 \"selected\" and 45 \"non-selected\" modes. These non-MPM modes are coded using fixed length coding. This paper proposes a method to select and order these non-MPM modes based on probability statistics. The modes that fall into selected category are coded using shorter codes and non-selected modes are coded using larger codes. Experimental results show performance improvement when compared to that of JEM 7.0","PeriodicalId":259542,"journal":{"name":"2019 Twelfth International Conference on Ubi-Media Computing (Ubi-Media)","volume":"64 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133636828","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 : 2019-08-01DOI: 10.1109/Ubi-Media.2019.00072
Chaknarin Kongcharoen
this study aims to apply instant translators for assisting English as a Foreign Language (EFL) students to understand English lecture slides in a normal classroom. Moreover, this study investigated how instant translator helped students understand in English lecture and students' perceptions toward the use of an instant translator. There are main findings of this study; most students who used instant translator perceived that it was useful for the chapter lecture. They used an instant translator to convert English slides to Thai instant transcripts for getting more understanding and summarizing chapter reports. The students of the instant translator group significantly outperformed the traditional group.
{"title":"To Investigate an Instant Translation for Assisting Students' Understandings of Lecture Slides","authors":"Chaknarin Kongcharoen","doi":"10.1109/Ubi-Media.2019.00072","DOIUrl":"https://doi.org/10.1109/Ubi-Media.2019.00072","url":null,"abstract":"this study aims to apply instant translators for assisting English as a Foreign Language (EFL) students to understand English lecture slides in a normal classroom. Moreover, this study investigated how instant translator helped students understand in English lecture and students' perceptions toward the use of an instant translator. There are main findings of this study; most students who used instant translator perceived that it was useful for the chapter lecture. They used an instant translator to convert English slides to Thai instant transcripts for getting more understanding and summarizing chapter reports. The students of the instant translator group significantly outperformed the traditional group.","PeriodicalId":259542,"journal":{"name":"2019 Twelfth International Conference on Ubi-Media Computing (Ubi-Media)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130119578","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 : 2019-08-01DOI: 10.1109/Ubi-Media.2019.00032
Li Yung-Hui, Yeh Nai-Ning, Kartika Purwandari, Latifa Nabila Harfiya
Diabetic retinopathy (DR) is the kind of diabetes complication that affects eyes and can damage the blood vessels inside the retina. To diagnose the strength of DR disease based on examination of the retina. Nowadays, the common diagnosis process asks for experienced ophthalmologists to inspect both fundus image and OCT (optical coherence tomography) images, which is time-consuming and not very convenient for remote rural inhabitants. The research purpose in this paper is to propose a new paradigm of automatic DR diagnosis by using artificial intelligence and cloud computing. Inside the DCNN, we changed max-pooling layers with factional max-pooling. We trained using support vector machine (SVM) to learn the underlying boundary of distribution of each category. Using that proposed method, we achieved the results of the recognition up to 86.17%. We also develop an iPhone APP. It called 'Deep Retina' that equipped with a handheld ophthalmoscope, a layman can take fundus images and perform the diagnosis automatically without intervention from ophthalmologists. It is a practically applicable telemedicine system which benefits the home care, remote medical care, and self-examination.
{"title":"Clinically Applicable Deep Learning for Diagnosis of Diabetic Retinopathy","authors":"Li Yung-Hui, Yeh Nai-Ning, Kartika Purwandari, Latifa Nabila Harfiya","doi":"10.1109/Ubi-Media.2019.00032","DOIUrl":"https://doi.org/10.1109/Ubi-Media.2019.00032","url":null,"abstract":"Diabetic retinopathy (DR) is the kind of diabetes complication that affects eyes and can damage the blood vessels inside the retina. To diagnose the strength of DR disease based on examination of the retina. Nowadays, the common diagnosis process asks for experienced ophthalmologists to inspect both fundus image and OCT (optical coherence tomography) images, which is time-consuming and not very convenient for remote rural inhabitants. The research purpose in this paper is to propose a new paradigm of automatic DR diagnosis by using artificial intelligence and cloud computing. Inside the DCNN, we changed max-pooling layers with factional max-pooling. We trained using support vector machine (SVM) to learn the underlying boundary of distribution of each category. Using that proposed method, we achieved the results of the recognition up to 86.17%. We also develop an iPhone APP. It called 'Deep Retina' that equipped with a handheld ophthalmoscope, a layman can take fundus images and perform the diagnosis automatically without intervention from ophthalmologists. It is a practically applicable telemedicine system which benefits the home care, remote medical care, and self-examination.","PeriodicalId":259542,"journal":{"name":"2019 Twelfth International Conference on Ubi-Media Computing (Ubi-Media)","volume":"30 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115205390","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 : 2019-08-01DOI: 10.1109/Ubi-Media.2019.00056
Chee-Hoe Loh, Sheng-Min Chiu, Yi-Chung Chen
Skyline queries are popular among researchers because of their capacity to assist decision-makers in the context of multiple criteria. However, existing studies were aimed at single objects or events. Time series, such as observing the long-term trends of stocks to select for highest profit and lowest risk, are rarely discussed. This study fills this gap. Conventional skyline queries directed at single objects or events are already time-consuming. All conventional algorithms compare data items in pairs, greatly increasing time complexity. Given the additional complexity of time series problems, we propose a method based on recurrent neural networks. To the best of our knowledge, this study is the first to propose a method for time-series skyline queries, which represents a significant contribution. Experiment results demonstrate the validity of the proposed method.
{"title":"Application of Hammerstein-Wiener Recurrent Neural Network to Accelerate Time-Series Skyline Queries","authors":"Chee-Hoe Loh, Sheng-Min Chiu, Yi-Chung Chen","doi":"10.1109/Ubi-Media.2019.00056","DOIUrl":"https://doi.org/10.1109/Ubi-Media.2019.00056","url":null,"abstract":"Skyline queries are popular among researchers because of their capacity to assist decision-makers in the context of multiple criteria. However, existing studies were aimed at single objects or events. Time series, such as observing the long-term trends of stocks to select for highest profit and lowest risk, are rarely discussed. This study fills this gap. Conventional skyline queries directed at single objects or events are already time-consuming. All conventional algorithms compare data items in pairs, greatly increasing time complexity. Given the additional complexity of time series problems, we propose a method based on recurrent neural networks. To the best of our knowledge, this study is the first to propose a method for time-series skyline queries, which represents a significant contribution. Experiment results demonstrate the validity of the proposed method.","PeriodicalId":259542,"journal":{"name":"2019 Twelfth International Conference on Ubi-Media Computing (Ubi-Media)","volume":"20 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126774000","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：