Pub Date : 2018-08-01DOI: 10.1109/icaicta.2018.8541288
Yukino Sato
Provides an abstract of the tutorial presentation and may include a brief professional biography of the presenter. The complete presentation was not made available for publication as part of the conference proceedings.
提供教程演示的摘要，可能包括演示者的简短专业简介。完整的报告没有作为会议记录的一部分提供出版。
{"title":"ICAICTA 2018 Tutorial","authors":"Yukino Sato","doi":"10.1109/icaicta.2018.8541288","DOIUrl":"https://doi.org/10.1109/icaicta.2018.8541288","url":null,"abstract":"Provides an abstract of the tutorial presentation and may include a brief professional biography of the presenter. The complete presentation was not made available for publication as part of the conference proceedings.","PeriodicalId":184882,"journal":{"name":"2018 5th International Conference on Advanced Informatics: Concept Theory and Applications (ICAICTA)","volume":"11 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127474139","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 : 2018-08-01DOI: 10.1109/ICAICTA.2018.8541309
A. I. Kistijantoro, Aufar Gilbran
The ARINC 653 specifies multiple operating system components to provide isolation between partitions. This means failure on one partition does not affect any other partition. While each partition cannot affect the other partitions, the failure still happens and possibly leads to failure to the whole system. In this paper, we extend the partition scheduler on ARINC 653 compliant hypervisor called ARLX to use primary-backup scheme. The resulting scheduler will be able to provide the needed service on failed partitions through their backup partitions.
{"title":"Improving ARINC 653 System Reliability by Using Fault-Tolerant Partition Scheduling","authors":"A. I. Kistijantoro, Aufar Gilbran","doi":"10.1109/ICAICTA.2018.8541309","DOIUrl":"https://doi.org/10.1109/ICAICTA.2018.8541309","url":null,"abstract":"The ARINC 653 specifies multiple operating system components to provide isolation between partitions. This means failure on one partition does not affect any other partition. While each partition cannot affect the other partitions, the failure still happens and possibly leads to failure to the whole system. In this paper, we extend the partition scheduler on ARINC 653 compliant hypervisor called ARLX to use primary-backup scheme. The resulting scheduler will be able to provide the needed service on failed partitions through their backup partitions.","PeriodicalId":184882,"journal":{"name":"2018 5th International Conference on Advanced Informatics: Concept Theory and Applications (ICAICTA)","volume":"167 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126300953","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 : 2018-08-01DOI: 10.1109/ICAICTA.2018.8541275
Watcharaphong Yookwan, K. Chinnasarn, Benchaporn Jantarakongkul
Dual-Energy X-ray Absorptiometry Scanner plays an important role in medical diagnosis and clinical routine. Typically, this kind of machine produces two radiography images of human spine consisted of Anteroposterior and Lateral side. However, these two images provided different viewpoints. This paper proposed a method to automatically estimate human vertebrae pose in lateral-side image by using Multi-theta Orientation Gabor Filter combined with Principle Component Analysis and Geometric Ellipse Shape Analysis. The proposed method offered an automated estimation of human lumbar vertebrae pose that can reduce work load of radiologist, computational time and complexity in various bone-clinical applications. The result of the proposed method can help support many applications such as lumbar vertebrae pose segmentation, bone mineral density analysis and vertebral pose deformation. The proposed method can estimate the vertebrae pose with 86.4% for accuracy, 80.5% of recall, precision for 89.11% and 13.6% of false negative rate.
{"title":"Automated Vertebrae Pose Estimation in Low-Radiation Image using Modified Gabor Filter and Ellipse Analysis","authors":"Watcharaphong Yookwan, K. Chinnasarn, Benchaporn Jantarakongkul","doi":"10.1109/ICAICTA.2018.8541275","DOIUrl":"https://doi.org/10.1109/ICAICTA.2018.8541275","url":null,"abstract":"Dual-Energy X-ray Absorptiometry Scanner plays an important role in medical diagnosis and clinical routine. Typically, this kind of machine produces two radiography images of human spine consisted of Anteroposterior and Lateral side. However, these two images provided different viewpoints. This paper proposed a method to automatically estimate human vertebrae pose in lateral-side image by using Multi-theta Orientation Gabor Filter combined with Principle Component Analysis and Geometric Ellipse Shape Analysis. The proposed method offered an automated estimation of human lumbar vertebrae pose that can reduce work load of radiologist, computational time and complexity in various bone-clinical applications. The result of the proposed method can help support many applications such as lumbar vertebrae pose segmentation, bone mineral density analysis and vertebral pose deformation. The proposed method can estimate the vertebrae pose with 86.4% for accuracy, 80.5% of recall, precision for 89.11% and 13.6% of false negative rate.","PeriodicalId":184882,"journal":{"name":"2018 5th International Conference on Advanced Informatics: Concept Theory and Applications (ICAICTA)","volume":"26 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126354578","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 : 2018-08-01DOI: 10.1109/ICAICTA.2018.8541294
Tidarat Luangrungruang, Urachart KoKaew
This study focused on the implementation of display technology used for providing information to hearing impaired students wishing to studying Information Technology (IT) at a higher education level. In this work, virtual reality scenes superimposed on the real world were created, using a smartphone application with specialized equipment to provide the projection. The Augmented Reality (AR) of smartphone applications was designed with Universal Design for Learning (UDL) in order to help with learning of hearing impaired high school students. The objective of the mobile AR application was to provide students with a tool to understand the content without the help of teachers. Because video content has been translated into the Thai sign language, smartphones could be used to read markers serving to provide education guidance for higher education. In AR technology, virtual objects are placed real-time on the real environment. To provide education guidance, the study used an AR application called Aurasma. A heuristic technique and the UDL were applied to the development of the education guidance on Aurasma. A total of 30 students of Sakon Nakhon Rajabhat University took part in this study. The heuristic evaluation results of this study were rated as good and the application has a potential to help hearing impaired students to become more interested in higher education, resulting in more education opportunities in higher education for them.
{"title":"Applying Universal Design for Learning in Augmented Reality Education Guidance for Hearing Impaired Student","authors":"Tidarat Luangrungruang, Urachart KoKaew","doi":"10.1109/ICAICTA.2018.8541294","DOIUrl":"https://doi.org/10.1109/ICAICTA.2018.8541294","url":null,"abstract":"This study focused on the implementation of display technology used for providing information to hearing impaired students wishing to studying Information Technology (IT) at a higher education level. In this work, virtual reality scenes superimposed on the real world were created, using a smartphone application with specialized equipment to provide the projection. The Augmented Reality (AR) of smartphone applications was designed with Universal Design for Learning (UDL) in order to help with learning of hearing impaired high school students. The objective of the mobile AR application was to provide students with a tool to understand the content without the help of teachers. Because video content has been translated into the Thai sign language, smartphones could be used to read markers serving to provide education guidance for higher education. In AR technology, virtual objects are placed real-time on the real environment. To provide education guidance, the study used an AR application called Aurasma. A heuristic technique and the UDL were applied to the development of the education guidance on Aurasma. A total of 30 students of Sakon Nakhon Rajabhat University took part in this study. The heuristic evaluation results of this study were rated as good and the application has a potential to help hearing impaired students to become more interested in higher education, resulting in more education opportunities in higher education for them.","PeriodicalId":184882,"journal":{"name":"2018 5th International Conference on Advanced Informatics: Concept Theory and Applications (ICAICTA)","volume":"48 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132595889","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 : 2018-08-01DOI: 10.1109/ICAICTA.2018.8541287
P. Silapachote, A. Srisuphab, Warot Banchongthanakit
Crucial for successful farrowing in swine production is the monitoring of health and welfare of pigs from insemination to farrowing and lactation. Although most are naturally farrowed, a significant number of piglets are lost due to fetal hypoxia. Common causes are ruptured umbilical cords, getting stuck in the birth canal, and exhaustion of sow. Prompt assistance offered by farmers can save lives of many piglets. Time is critical. Minutes of delay could mean another loss. Around-the-clock monitoring, at the same time, is not only labor-intensive but also a financial burden for farm management. One of the keys toward better assessment of the right timing for farmworkers to attend to a farrow with minimal wait-around time - first and foremost - is to collect and analyze the detailed timing of the farrowing process. Bringing digital technology of embedded systems to farming, we developed a monitoring device capable of continuously recording a video of a sow. Farrowing videos were collected for seven weeks. Graphical visualization and statistical analysis of the data were evaluated. Employing computer vision and machine intelligence, we proposed a methodology for extracting features and training a classifier to automatically detect the firstborn piglet. Preliminary image processing results are presented.
{"title":"An Embedded System Device to Monitor Farrowing","authors":"P. Silapachote, A. Srisuphab, Warot Banchongthanakit","doi":"10.1109/ICAICTA.2018.8541287","DOIUrl":"https://doi.org/10.1109/ICAICTA.2018.8541287","url":null,"abstract":"Crucial for successful farrowing in swine production is the monitoring of health and welfare of pigs from insemination to farrowing and lactation. Although most are naturally farrowed, a significant number of piglets are lost due to fetal hypoxia. Common causes are ruptured umbilical cords, getting stuck in the birth canal, and exhaustion of sow. Prompt assistance offered by farmers can save lives of many piglets. Time is critical. Minutes of delay could mean another loss. Around-the-clock monitoring, at the same time, is not only labor-intensive but also a financial burden for farm management. One of the keys toward better assessment of the right timing for farmworkers to attend to a farrow with minimal wait-around time - first and foremost - is to collect and analyze the detailed timing of the farrowing process. Bringing digital technology of embedded systems to farming, we developed a monitoring device capable of continuously recording a video of a sow. Farrowing videos were collected for seven weeks. Graphical visualization and statistical analysis of the data were evaluated. Employing computer vision and machine intelligence, we proposed a methodology for extracting features and training a classifier to automatically detect the firstborn piglet. Preliminary image processing results are presented.","PeriodicalId":184882,"journal":{"name":"2018 5th International Conference on Advanced Informatics: Concept Theory and Applications (ICAICTA)","volume":"116 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124800634","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 : 2018-08-01DOI: 10.1109/ICAICTA.2018.8541285
Geraldi Dzakwan, A. Purwarianti
On language generation system such as chatbot and machine translation, there is a recent approach called sequence to sequence learning. This approach takes advantages of two recurrent neural networks (encoder and decoder) as an end-to-end mapping tool to generatively build the output from a certain input. In this paper, we try to find a combination of topology and feature which produces the highest result according to automatic evaluation metrics BLEU for non-task-oriented chatbot as the case study. The topologies used in the experiment are RNN, GRU, and LSTM along with their modifications, which are bidirectional encoder and attention-based decoder. The features used in the experiment are word-based feature and character-based feature. The experiment is conducted using Papaya English dialogue dataset. From the dataset, ten thousand pairs of conversation are picked for training data and a thousand pairs of conversation are picked for testing data. The result shows that bidirectional LSTM encoder with attention-based decoder and word based feature produced the highest cumulative BLEU-4 score amongst other topologies, which is 0.31.
{"title":"Comparative Study of Topology and Feature Variants for Non-Task-Oriented Chatbot using Sequence to Sequence Learning","authors":"Geraldi Dzakwan, A. Purwarianti","doi":"10.1109/ICAICTA.2018.8541285","DOIUrl":"https://doi.org/10.1109/ICAICTA.2018.8541285","url":null,"abstract":"On language generation system such as chatbot and machine translation, there is a recent approach called sequence to sequence learning. This approach takes advantages of two recurrent neural networks (encoder and decoder) as an end-to-end mapping tool to generatively build the output from a certain input. In this paper, we try to find a combination of topology and feature which produces the highest result according to automatic evaluation metrics BLEU for non-task-oriented chatbot as the case study. The topologies used in the experiment are RNN, GRU, and LSTM along with their modifications, which are bidirectional encoder and attention-based decoder. The features used in the experiment are word-based feature and character-based feature. The experiment is conducted using Papaya English dialogue dataset. From the dataset, ten thousand pairs of conversation are picked for training data and a thousand pairs of conversation are picked for testing data. The result shows that bidirectional LSTM encoder with attention-based decoder and word based feature produced the highest cumulative BLEU-4 score amongst other topologies, which is 0.31.","PeriodicalId":184882,"journal":{"name":"2018 5th International Conference on Advanced Informatics: Concept Theory and Applications (ICAICTA)","volume":"56 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129439586","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 : 2018-08-01DOI: 10.1109/ICAICTA.2018.8541293
A. Romadhony, A. Purwarianti, D. H. Widyantoro
Open Information Extraction (Open IE) is a paradigm that tries to extract as much information as possible, with less restriction on the information type to be extracted. It extracts relation tuples, in which a relation tuple consists of a relation tuple trigger and several relation arguments. Previous studies on developing Open IE systems have mainly been for English. Recently, several works have also been carried out in other languages, but there is no study on Open IE for Indonesian. In this paper, we investigate several rule-based methods for building an Open IE system for Indonesian. We use lexical and syntactic features that were obtained from an Indonesian language processing tool and compare the extraction results against the standard English Open IE systems. The experimental results for English-Indonesian parallel sentences show that the POSTag+Noun Phrase-based rules have better performance. At the same time, the dependency relation-based performance depends on the dependency parser performance, which still needs improvement since we use a small size dataset on training the parser. However, both approaches show good performance in identifying the relation tuple trigger, with the recall score being 0.96 for the POSTag+Noun Phrase-based rules and 0.6 for the POSTag+Dependency relation based-rules.
开放信息提取(Open Information Extraction, Open IE)是一种范式，它试图提取尽可能多的信息，对要提取的信息类型限制较少。它提取关系元组，其中关系元组由一个关系元组触发器和几个关系参数组成。以前关于开发Open IE系统的研究主要是针对英语的。最近也开展了几项其他语言的工作，但没有针对印尼语的Open IE的研究。在本文中，我们研究了几种基于规则的方法来构建一个开放的印尼IE系统。我们使用从印度尼西亚语言处理工具获得的词汇和句法特征，并将提取结果与标准英语Open IE系统进行比较。英汉-印尼语并列句的实验结果表明，基于POSTag+名词短语的规则具有更好的性能。同时，基于依赖关系的性能取决于依赖解析器的性能，由于我们使用的是小数据集来训练解析器，因此仍然需要改进。然而，这两种方法在识别关系元组触发器方面表现良好，基于POSTag+名词短语的规则的召回分数为0.96，基于POSTag+依赖关系的规则的召回分数为0.6。
{"title":"Rule-based Indonesian Open Information Extraction","authors":"A. Romadhony, A. Purwarianti, D. H. Widyantoro","doi":"10.1109/ICAICTA.2018.8541293","DOIUrl":"https://doi.org/10.1109/ICAICTA.2018.8541293","url":null,"abstract":"Open Information Extraction (Open IE) is a paradigm that tries to extract as much information as possible, with less restriction on the information type to be extracted. It extracts relation tuples, in which a relation tuple consists of a relation tuple trigger and several relation arguments. Previous studies on developing Open IE systems have mainly been for English. Recently, several works have also been carried out in other languages, but there is no study on Open IE for Indonesian. In this paper, we investigate several rule-based methods for building an Open IE system for Indonesian. We use lexical and syntactic features that were obtained from an Indonesian language processing tool and compare the extraction results against the standard English Open IE systems. The experimental results for English-Indonesian parallel sentences show that the POSTag+Noun Phrase-based rules have better performance. At the same time, the dependency relation-based performance depends on the dependency parser performance, which still needs improvement since we use a small size dataset on training the parser. However, both approaches show good performance in identifying the relation tuple trigger, with the recall score being 0.96 for the POSTag+Noun Phrase-based rules and 0.6 for the POSTag+Dependency relation based-rules.","PeriodicalId":184882,"journal":{"name":"2018 5th International Conference on Advanced Informatics: Concept Theory and Applications (ICAICTA)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128331254","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}
On-line selling website is currently famous and popular. There are several websites selling products and/or services including on-line book-selling websites. At present, the current book-selling websites usually apply recommender systems to recommend a book or a set of books to customers. However, the recommender systems mostly focus on recommending books that users usually view or buy together and also on books having high review rates. This may cause failure to recommend books that cover most required contents, for example, books related to a course description of a course students have registered. To address on this issue, we here introduce an alternative recommender system called Supplementary Books Suggestion system (SBS system) to create a list of supplementary books related/relevance to a course description of a course in computer science domain by regarding relevance between a book and a course description. This can help students easily find supplementary books to read and also may help to encourage the students doing self-learning. Experiments on real course descriptions were conducted to investigate the effectiveness of the SBS system in the terms of precision, recall, F-measure and average (also total) coverage/uncoverage of contents between a list of supplementary books and a course description.
{"title":"Supplementary Book Suggestion for Computer Science Courses","authors":"Benchamawan Chaisoongnoen, Komate Amphawan, Aekapop Bunpeng","doi":"10.1109/ICAICTA.2018.8541347","DOIUrl":"https://doi.org/10.1109/ICAICTA.2018.8541347","url":null,"abstract":"On-line selling website is currently famous and popular. There are several websites selling products and/or services including on-line book-selling websites. At present, the current book-selling websites usually apply recommender systems to recommend a book or a set of books to customers. However, the recommender systems mostly focus on recommending books that users usually view or buy together and also on books having high review rates. This may cause failure to recommend books that cover most required contents, for example, books related to a course description of a course students have registered. To address on this issue, we here introduce an alternative recommender system called Supplementary Books Suggestion system (SBS system) to create a list of supplementary books related/relevance to a course description of a course in computer science domain by regarding relevance between a book and a course description. This can help students easily find supplementary books to read and also may help to encourage the students doing self-learning. Experiments on real course descriptions were conducted to investigate the effectiveness of the SBS system in the terms of precision, recall, F-measure and average (also total) coverage/uncoverage of contents between a list of supplementary books and a course description.","PeriodicalId":184882,"journal":{"name":"2018 5th International Conference on Advanced Informatics: Concept Theory and Applications (ICAICTA)","volume":"62 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114707509","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 : 2018-08-01DOI: 10.1109/ICAICTA.2018.8541332
J. Sarasook, C. Thongchaisuratkrul
This research presents experimental set of distribution light. Light illuminance is displayed by LabView application. The set was tested by four types of lamp including complex fluorescent (CFL), incandescent, E27 LED (Light Emitting Diode), T8 tubular fluorescent (FL). The 3 types of luminaire are used for testing. They consisted of down light, high bay and fluorescent reflector. The black close room was 1.5x1.5x1.5 m in size. It was constructed by steel and plywood. The center floor of the room is installed by LDR (Light Dependent Resistor). It was used for measuring the illuminance. LabView application was applied to display value on computer screen. The stepping motor was installed to rotate the lamp. It was controlled by LabView through DAQ 6008 interface card. It was rotated from -90o to 90o. The control set consisted of interface card, motor drive and power supply. They were contained in the insulation box outside of the test room. From the experimental result, the LDR illuminance meter can measure illuminance with 4.52% average error. The light distribution curve from experiment set is correspondent with theory.
本研究提出一套配电灯实验装置。光源照度由LabView应用程序显示。采用复合荧光灯(CFL)、白炽灯、E27 LED (Light Emitting Diode)、T8管状荧光灯(FL)四种灯进行测试。测试使用3种类型的灯具。它们由筒灯、高舱和荧光反射器组成。黑色的密室尺寸为1.5x1.5x1.5 m。它是由钢和胶合板建造的。房间的中央楼层安装了LDR(光依赖电阻)。它被用来测量照度。应用LabView程序在计算机屏幕上显示数值。安装步进电机使灯转动。LabView通过DAQ 6008接口卡对其进行控制。它从-90度旋转到90度。控制装置由接口卡、电机驱动和电源组成。它们被装在测试室外的绝缘盒里。实验结果表明，LDR照度计测量照度的平均误差为4.52%。实验所得的配光曲线与理论相符。
{"title":"The Experimental Set of Light Distribution Analysis by LabView Application","authors":"J. Sarasook, C. Thongchaisuratkrul","doi":"10.1109/ICAICTA.2018.8541332","DOIUrl":"https://doi.org/10.1109/ICAICTA.2018.8541332","url":null,"abstract":"This research presents experimental set of distribution light. Light illuminance is displayed by LabView application. The set was tested by four types of lamp including complex fluorescent (CFL), incandescent, E27 LED (Light Emitting Diode), T8 tubular fluorescent (FL). The 3 types of luminaire are used for testing. They consisted of down light, high bay and fluorescent reflector. The black close room was 1.5x1.5x1.5 m in size. It was constructed by steel and plywood. The center floor of the room is installed by LDR (Light Dependent Resistor). It was used for measuring the illuminance. LabView application was applied to display value on computer screen. The stepping motor was installed to rotate the lamp. It was controlled by LabView through DAQ 6008 interface card. It was rotated from -90o to 90o. The control set consisted of interface card, motor drive and power supply. They were contained in the insulation box outside of the test room. From the experimental result, the LDR illuminance meter can measure illuminance with 4.52% average error. The light distribution curve from experiment set is correspondent with theory.","PeriodicalId":184882,"journal":{"name":"2018 5th International Conference on Advanced Informatics: Concept Theory and Applications (ICAICTA)","volume":"8 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114762468","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 : 2018-08-01DOI: 10.1109/ICAICTA.2018.8541284
Vosco Pereira, S. Tamura, S. Hayamizu, Hidekazu Fukai
Image processing techniques have been actively used for research on road condition inspection and achieving high detection accuracies. Many studies focus on the detection of cracks and potholes of the road. However, in some least developed countries, there are some distances of roads are still unpaved and it escaped the attention of the researchers. Inspired by penetration and success in applying deep learning technic to computer vision and to any other fields and by the existence of the various type of smartphone devices, we proposed a low - cost method for paved and unpaved road images classification using convolutional neural network (CNN). Our model is trained with 13.186 images and validate with 3.186 images which collected using smartphone device in various conditions of roads such as wet, muddy, dry, dusty and shady conditions and with different types of road surface such as ground, rocks and sands. The experiment using 500 new testing images showed that our model can achieve high Precision (98.0%), Recall (98.4%) and F1 -Score (98.2%) simultaneously.
{"title":"Classification of Paved and Unpaved Road Image Using Convolutional Neural Network for Road Condition Inspection System","authors":"Vosco Pereira, S. Tamura, S. Hayamizu, Hidekazu Fukai","doi":"10.1109/ICAICTA.2018.8541284","DOIUrl":"https://doi.org/10.1109/ICAICTA.2018.8541284","url":null,"abstract":"Image processing techniques have been actively used for research on road condition inspection and achieving high detection accuracies. Many studies focus on the detection of cracks and potholes of the road. However, in some least developed countries, there are some distances of roads are still unpaved and it escaped the attention of the researchers. Inspired by penetration and success in applying deep learning technic to computer vision and to any other fields and by the existence of the various type of smartphone devices, we proposed a low - cost method for paved and unpaved road images classification using convolutional neural network (CNN). Our model is trained with 13.186 images and validate with 3.186 images which collected using smartphone device in various conditions of roads such as wet, muddy, dry, dusty and shady conditions and with different types of road surface such as ground, rocks and sands. The experiment using 500 new testing images showed that our model can achieve high Precision (98.0%), Recall (98.4%) and F1 -Score (98.2%) simultaneously.","PeriodicalId":184882,"journal":{"name":"2018 5th International Conference on Advanced Informatics: Concept Theory and Applications (ICAICTA)","volume":"27 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121582081","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：