Pub Date : 2018-08-01DOI: 10.1109/ICAICTA.2018.8541319
Anocha Yaemjaem, N. Sutthisangiam, Amnat Sompan, Nattakit Sa-ngiam, Pongsak Jindasee
This paper is the develop of a high-definition 3D mapping system for use in topographic surveys and management of water resources by using MMS technology (Mobile mapping System) as a tool survey information on the topography, such as canal width, water level, bank level, road height and water regulating building structure. This information is the important in analyzing water situation and finding solutions for water resources management. This research uses 4 part type of devices: GPS, IMU, camera and 3D laser scanner. All devices are designed to be mounted on vehicles. The results of the test run of land vehicles in the area frequently flooded are Chai Nat and Nakhon Sawan Thailand and provide high-definition 3D maps from system. The system can generate high-definition 3D maps, measuring 9 centimeters in horizontal accuracy and 20 centimeters in vertical accuracy.
{"title":"Development of High-Definition 3D Mapping System for Water Resources Management","authors":"Anocha Yaemjaem, N. Sutthisangiam, Amnat Sompan, Nattakit Sa-ngiam, Pongsak Jindasee","doi":"10.1109/ICAICTA.2018.8541319","DOIUrl":"https://doi.org/10.1109/ICAICTA.2018.8541319","url":null,"abstract":"This paper is the develop of a high-definition 3D mapping system for use in topographic surveys and management of water resources by using MMS technology (Mobile mapping System) as a tool survey information on the topography, such as canal width, water level, bank level, road height and water regulating building structure. This information is the important in analyzing water situation and finding solutions for water resources management. This research uses 4 part type of devices: GPS, IMU, camera and 3D laser scanner. All devices are designed to be mounted on vehicles. The results of the test run of land vehicles in the area frequently flooded are Chai Nat and Nakhon Sawan Thailand and provide high-definition 3D maps from system. The system can generate high-definition 3D maps, measuring 9 centimeters in horizontal accuracy and 20 centimeters in vertical accuracy.","PeriodicalId":184882,"journal":{"name":"2018 5th International Conference on Advanced Informatics: Concept Theory and Applications (ICAICTA)","volume":"33 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":"122649229","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.2018.8541274
Sasiporn Tongman, N. Wattanakitrungroj
The contents in website and social networks are rapidly generated. The opinions and reviews can be analyzed and classified into two classes, positive or negative opinions, by machine learning methods. However, the main issue is how to representing each text as a proper set of variables, a p-feature vector, so that the successful classifiers can be obtained by one of the supervised learning approaches with its suitable parameter setting. In this study, a two-feature vector representing positive and negative moods in each text was prepared by using lists of positive and negative words, and then combined with term frequency - inverse document frequency (TF-IDF) features. kNN and SVM classifiers were comparatively built by this set and also other baseline set to predict each test vector and measure their effectiveness. Data of text Reviews from Yelp, Amazon and IMDB, were experimented with 10-fold cross validation in parameter variation and feature set reduction using PCA. The best Accuracy results across these three datasets, ~0.81-0.87, were yielded by SVM classifiers with each size of the reduced feature sets that is very smaller than the original size.
{"title":"Classifying Positive or Negative Text Using Features Based on Opinion Words and Term Frequency - Inverse Document Frequency","authors":"Sasiporn Tongman, N. Wattanakitrungroj","doi":"10.1109/ICAICTA.2018.8541274","DOIUrl":"https://doi.org/10.1109/ICAICTA.2018.8541274","url":null,"abstract":"The contents in website and social networks are rapidly generated. The opinions and reviews can be analyzed and classified into two classes, positive or negative opinions, by machine learning methods. However, the main issue is how to representing each text as a proper set of variables, a p-feature vector, so that the successful classifiers can be obtained by one of the supervised learning approaches with its suitable parameter setting. In this study, a two-feature vector representing positive and negative moods in each text was prepared by using lists of positive and negative words, and then combined with term frequency - inverse document frequency (TF-IDF) features. kNN and SVM classifiers were comparatively built by this set and also other baseline set to predict each test vector and measure their effectiveness. Data of text Reviews from Yelp, Amazon and IMDB, were experimented with 10-fold cross validation in parameter variation and feature set reduction using PCA. The best Accuracy results across these three datasets, ~0.81-0.87, were yielded by SVM classifiers with each size of the reduced feature sets that is very smaller than the original size.","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":"130395162","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.2018.8541318
Kyoji Umemura, Yuto Kohara, Nudtawon Yusuk, Ayaka Takamoto, Mitsuo Yoshida
There are two counting methods of "aa" in "aaa". The first method is overlapping count and this method count two "aa" in "aaa". The overlapping count uses the middle "a" twice. The other method is non-overlapping count which can count only one "aa" in "aaa". Non-overlapping counting uses each character once; therefore, there is only one "aa" in "aaa". In this paper, we provide the formulas to compute non-overlapping count of a string from the overlapping count of the related strings. Because a suffix array is known to be an efficient data structure, to obtain overlapping count of any string we can use suffix array to obtain the non-overlapping count of the given string by the formula which is presented in this paper.
{"title":"Non-overlapping Counting of String Using Suffix Array","authors":"Kyoji Umemura, Yuto Kohara, Nudtawon Yusuk, Ayaka Takamoto, Mitsuo Yoshida","doi":"10.1109/ICAICTA.2018.8541318","DOIUrl":"https://doi.org/10.1109/ICAICTA.2018.8541318","url":null,"abstract":"There are two counting methods of \"aa\" in \"aaa\". The first method is overlapping count and this method count two \"aa\" in \"aaa\". The overlapping count uses the middle \"a\" twice. The other method is non-overlapping count which can count only one \"aa\" in \"aaa\". Non-overlapping counting uses each character once; therefore, there is only one \"aa\" in \"aaa\". In this paper, we provide the formulas to compute non-overlapping count of a string from the overlapping count of the related strings. Because a suffix array is known to be an efficient data structure, to obtain overlapping count of any string we can use suffix array to obtain the non-overlapping count of the given string by the formula which is presented in this paper.","PeriodicalId":184882,"journal":{"name":"2018 5th International Conference on Advanced Informatics: Concept Theory and Applications (ICAICTA)","volume":"44 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":"121335028","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}
The flipped classroom has become famous as an effective educational method that flips the purpose of classroom study and homework. In this paper, we propose a video learning system for flipped classrooms, called Response Collector, which enables students to record their responses to preparation videos. Our system provides response visualization for teachers and students to understand what they have acquired and questioned. We performed a practical user study of our system in a flipped classroom setup. The results show that students preferred to use the proposed method as the inputting method, rather than naive methods. Moreover, sharing responses among students was helpful for resolving individual students' questions, and students were satisfied with the use of our system.
{"title":"Response Collector: A Video Learning System for Flipped Classrooms","authors":"Hayato Okumoto, Mitsuo Yoshida, Kyoji Umemura, Yuko Ichikawa","doi":"10.1109/ICAICTA.2018.8541338","DOIUrl":"https://doi.org/10.1109/ICAICTA.2018.8541338","url":null,"abstract":"The flipped classroom has become famous as an effective educational method that flips the purpose of classroom study and homework. In this paper, we propose a video learning system for flipped classrooms, called Response Collector, which enables students to record their responses to preparation videos. Our system provides response visualization for teachers and students to understand what they have acquired and questioned. We performed a practical user study of our system in a flipped classroom setup. The results show that students preferred to use the proposed method as the inputting method, rather than naive methods. Moreover, sharing responses among students was helpful for resolving individual students' questions, and students were satisfied with the use of our system.","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":"130669487","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.2018.8541322
U. P. Ishanka, Takashi Yukawa
At present, many recommendation systems focus on adapting psychological parameters, such as user emotion and personality, in recommendation algorithms in order to enhance the accuracy of recommendation lists according to user needs. Since users with different personalities tend to prefer items with different features, the personality of a user provides valuable information in exploiting personalized recommendations. Among personality models, the five-factor model appears to be suitable for applying recommendation systems, as it can be quantitatively measured. Moreover, emotion has also been widely adapted to a wide variety of recommendation domains, although few studies have examined tourist destination recommendation. In the present study, we use Plutchick’s emotion classification for emotion acquisition in the recommendation process. In addition, personality traits can be directly related to user emotions in decision making and exploring the relationship between emotion and personality in recommending items is also important. In order to incorporate user emotion in the recommendation process together with user personality, we propose a travel recommendation system that incorporated user personality and emotion. Thus, we compare and clarify the effectiveness of using emotion and personality in the recommendation process together with collaborative filtering techniques.
{"title":"User Emotion and Personality in Context-aware Travel Destination Recommendation","authors":"U. P. Ishanka, Takashi Yukawa","doi":"10.1109/ICAICTA.2018.8541322","DOIUrl":"https://doi.org/10.1109/ICAICTA.2018.8541322","url":null,"abstract":"At present, many recommendation systems focus on adapting psychological parameters, such as user emotion and personality, in recommendation algorithms in order to enhance the accuracy of recommendation lists according to user needs. Since users with different personalities tend to prefer items with different features, the personality of a user provides valuable information in exploiting personalized recommendations. Among personality models, the five-factor model appears to be suitable for applying recommendation systems, as it can be quantitatively measured. Moreover, emotion has also been widely adapted to a wide variety of recommendation domains, although few studies have examined tourist destination recommendation. In the present study, we use Plutchick’s emotion classification for emotion acquisition in the recommendation process. In addition, personality traits can be directly related to user emotions in decision making and exploring the relationship between emotion and personality in recommending items is also important. In order to incorporate user emotion in the recommendation process together with user personality, we propose a travel recommendation system that incorporated user personality and emotion. Thus, we compare and clarify the effectiveness of using emotion and personality in the recommendation process together with collaborative filtering techniques.","PeriodicalId":184882,"journal":{"name":"2018 5th International Conference on Advanced Informatics: Concept Theory and Applications (ICAICTA)","volume":"33 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":"132541607","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.2018.8541340
S. Masruroh, Syifa Fauzia, Nashrul Hakiem
Software measurement has been used to analyse software quality in order to provide information for improving software processes and products. The objective of this research is to measure e-commerce Content Management System (CMS) based open source: Magento, OsCommerce, Prestashop, Zencart, and Opencart. The measurement uses two parameters, Object Oriented Metrics (OO Metrics) esspecially in CK Metrics Suite and Quality Factor with the Analytical Hierarchy Process method as the completion step of the parameters used. By using OO Metrics and Quality Factor as a benchmark this will give a ranking in form of CMS e-commerce recommendations which have the best software quality criteria. The CK Metrics Suite that is implemented consists of Weighted Method per Class (WMC), Depth of Inheritance Tree (DIT), Number of Children (NOC), and Coupling Between Objects (CBO). The Quality Factor parameter consists of Maintainability, Efficiency, Understandability, and Reusability. The system development uses is the Rapid Application Development (RAD) method by building JAVA applications. The result found that Magento is the best CMS based on Object Oriented Metrics and Quality Factor parameters.
{"title":"Software Measurement for E-Commerce CMS by Using OO Metrics and Quality Factor Parameters Based on JAVA","authors":"S. Masruroh, Syifa Fauzia, Nashrul Hakiem","doi":"10.1109/ICAICTA.2018.8541340","DOIUrl":"https://doi.org/10.1109/ICAICTA.2018.8541340","url":null,"abstract":"Software measurement has been used to analyse software quality in order to provide information for improving software processes and products. The objective of this research is to measure e-commerce Content Management System (CMS) based open source: Magento, OsCommerce, Prestashop, Zencart, and Opencart. The measurement uses two parameters, Object Oriented Metrics (OO Metrics) esspecially in CK Metrics Suite and Quality Factor with the Analytical Hierarchy Process method as the completion step of the parameters used. By using OO Metrics and Quality Factor as a benchmark this will give a ranking in form of CMS e-commerce recommendations which have the best software quality criteria. The CK Metrics Suite that is implemented consists of Weighted Method per Class (WMC), Depth of Inheritance Tree (DIT), Number of Children (NOC), and Coupling Between Objects (CBO). The Quality Factor parameter consists of Maintainability, Efficiency, Understandability, and Reusability. The system development uses is the Rapid Application Development (RAD) method by building JAVA applications. The result found that Magento is the best CMS based on Object Oriented Metrics and Quality Factor parameters.","PeriodicalId":184882,"journal":{"name":"2018 5th International Conference on Advanced Informatics: Concept Theory and Applications (ICAICTA)","volume":"29 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":"134116978","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.2018.8541337
Steffi Indrayani, M. L. Khodra
In order to fulfill the needs of journalistic automation, we develop automatic news generator that accepts structured data and user query and generates Indonesian news article. This paper employs template-based natural language generation in generating Indonesian municipal elections. Based on evaluation using Indonesian news characteristics as the evaluation metric by 15 linguistic experts and 25 active news readers, the average score of the generated news was 3.292 out of 4.
{"title":"Data-Driven News Generation for Indonesian Municipal Election","authors":"Steffi Indrayani, M. L. Khodra","doi":"10.1109/ICAICTA.2018.8541337","DOIUrl":"https://doi.org/10.1109/ICAICTA.2018.8541337","url":null,"abstract":"In order to fulfill the needs of journalistic automation, we develop automatic news generator that accepts structured data and user query and generates Indonesian news article. This paper employs template-based natural language generation in generating Indonesian municipal elections. Based on evaluation using Indonesian news characteristics as the evaluation metric by 15 linguistic experts and 25 active news readers, the average score of the generated news was 3.292 out of 4.","PeriodicalId":184882,"journal":{"name":"2018 5th International Conference on Advanced Informatics: Concept Theory and Applications (ICAICTA)","volume":"53 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":"127960610","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.2018.8541320
Catherine Pricilla, D. Lestari, Dody Dharma
Chatbot-based conversational commerce which allows buyers to do online shopping by conversing with chatbot through messaging application has been growing in the e-commerce industry. However, based on studies conducted in this paper, findings show that interaction design of the existing conversational commerce are still lacking in various areas. Therefore, an interaction and interface design for chatbot-based conversational commerce are developed in this study using user-centered design. The outcome of this study is a prototype that fulfills the usability goal and the user experience goal defined for chatbot-based conversational commerce on mobile platform especially for Indonesian users. We conduct usability testing to evaluate the prototype. The results show that the prototype fulfills the defined usability goals and user experience goals as 100% users agree that the prototype is effective to use, efficient to use, easy to learn, enjoyable and helpful, although only 83.3% users agree that the prototype is safe to use.
{"title":"Designing Interaction for Chatbot-Based Conversational Commerce with User-Centered Design","authors":"Catherine Pricilla, D. Lestari, Dody Dharma","doi":"10.1109/ICAICTA.2018.8541320","DOIUrl":"https://doi.org/10.1109/ICAICTA.2018.8541320","url":null,"abstract":"Chatbot-based conversational commerce which allows buyers to do online shopping by conversing with chatbot through messaging application has been growing in the e-commerce industry. However, based on studies conducted in this paper, findings show that interaction design of the existing conversational commerce are still lacking in various areas. Therefore, an interaction and interface design for chatbot-based conversational commerce are developed in this study using user-centered design. The outcome of this study is a prototype that fulfills the usability goal and the user experience goal defined for chatbot-based conversational commerce on mobile platform especially for Indonesian users. We conduct usability testing to evaluate the prototype. The results show that the prototype fulfills the defined usability goals and user experience goals as 100% users agree that the prototype is effective to use, efficient to use, easy to learn, enjoyable and helpful, although only 83.3% users agree that the prototype is safe to use.","PeriodicalId":184882,"journal":{"name":"2018 5th International Conference on Advanced Informatics: Concept Theory and Applications (ICAICTA)","volume":"214 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":"117349698","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.2018.8541301
P. Bamrungthai, Prasatporn Wongkamchang
The development of an image fusion system is described in this paper. The system consists of thermal and visible (color) cameras. Image alignment between two camera views is performed by using homography. The homography was estimated from four pairs of corresponding points on a planar object in the captured images that was manually selected by the user. Then, the user-defined region of interest (ROI) is used to adjust scale and position of the two images. Finally, the image fusion algorithm is applied to create the fused image. By thresholding the thermal image at a specified intensity level, the pixel values in the color image will be replaced with a predefined color if the corresponding pixels in the thermal image exceed the threshold value. This technique can provide thermal information of possible targets to be fused with original color image. This makes the system suitable for situation awareness. The experimental results show that the system can operate in real-time with satisfactory results.
{"title":"Development of a Thermal/Visible Image Fusion System for Situation Awareness","authors":"P. Bamrungthai, Prasatporn Wongkamchang","doi":"10.1109/ICAICTA.2018.8541301","DOIUrl":"https://doi.org/10.1109/ICAICTA.2018.8541301","url":null,"abstract":"The development of an image fusion system is described in this paper. The system consists of thermal and visible (color) cameras. Image alignment between two camera views is performed by using homography. The homography was estimated from four pairs of corresponding points on a planar object in the captured images that was manually selected by the user. Then, the user-defined region of interest (ROI) is used to adjust scale and position of the two images. Finally, the image fusion algorithm is applied to create the fused image. By thresholding the thermal image at a specified intensity level, the pixel values in the color image will be replaced with a predefined color if the corresponding pixels in the thermal image exceed the threshold value. This technique can provide thermal information of possible targets to be fused with original color image. This makes the system suitable for situation awareness. The experimental results show that the system can operate in real-time with satisfactory results.","PeriodicalId":184882,"journal":{"name":"2018 5th International Conference on Advanced Informatics: Concept Theory and Applications (ICAICTA)","volume":"21 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":"125913231","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.2018.8541335
Supaporn Erjongmanee, Navatasn Kongsamutr
Air passenger estimation is essential since air-travel demand continuously grows. This work proposes to derive an air-passenger estimation model using three forms of gravity model and two machine learning approaches, regression and neural network. Data used in this work are Thailand’s domestic air-passengers and affecting factors on air-travel demand collected from publicly available sources. The results show that both regression and neural network with one hidden layer provide low error. Gross domestic product and number of tourists change in the same direction with air-passenger demand. The outcomes of this work give more understandings in employing machine learning to estimate air passengers in Thailand and can be developed for more complex forecast models in the future.
{"title":"Air Passenger Estimation Using Gravity Model and Learning Approaches: Case Study of Thailand","authors":"Supaporn Erjongmanee, Navatasn Kongsamutr","doi":"10.1109/ICAICTA.2018.8541335","DOIUrl":"https://doi.org/10.1109/ICAICTA.2018.8541335","url":null,"abstract":"Air passenger estimation is essential since air-travel demand continuously grows. This work proposes to derive an air-passenger estimation model using three forms of gravity model and two machine learning approaches, regression and neural network. Data used in this work are Thailand’s domestic air-passengers and affecting factors on air-travel demand collected from publicly available sources. The results show that both regression and neural network with one hidden layer provide low error. Gross domestic product and number of tourists change in the same direction with air-passenger demand. The outcomes of this work give more understandings in employing machine learning to estimate air passengers in Thailand and can be developed for more complex forecast models in the future.","PeriodicalId":184882,"journal":{"name":"2018 5th International Conference on Advanced Informatics: Concept Theory and Applications (ICAICTA)","volume":"174 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":"124261971","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：