Pub Date : 2015-11-23DOI: 10.1109/ICAICTA.2015.7335347
Mariko Hyodo, S. Itakura, M. Kitazaki
Behavioral economists and psychologists have investigated what factors affect trade-off between equal allocation and efficient allocation in asset allocation for others (distribution justice). In the present study we performed a behavioral experiment as a basic research of communication in cyberspace to test whether preference of equity or efficiency in asset allocation for virtual characters depends on their appearances. We found that geometrical-face characters invoked the equality preference similarly to real-face human others. Furthermore, there was a positive correlation between the love-contagion score in Emotional Contagion Scale (ECS) and the equality preference rate when there was no difference in a gross asset between equality and efficiency choices. Thus, humans have an equality preference over an efficiency preference both for human and non-human agents regardless of their visual appearances. The equity in distributive justice is affected by a human's emotional personality.
{"title":"Equity in distributive justice to virtual characters","authors":"Mariko Hyodo, S. Itakura, M. Kitazaki","doi":"10.1109/ICAICTA.2015.7335347","DOIUrl":"https://doi.org/10.1109/ICAICTA.2015.7335347","url":null,"abstract":"Behavioral economists and psychologists have investigated what factors affect trade-off between equal allocation and efficient allocation in asset allocation for others (distribution justice). In the present study we performed a behavioral experiment as a basic research of communication in cyberspace to test whether preference of equity or efficiency in asset allocation for virtual characters depends on their appearances. We found that geometrical-face characters invoked the equality preference similarly to real-face human others. Furthermore, there was a positive correlation between the love-contagion score in Emotional Contagion Scale (ECS) and the equality preference rate when there was no difference in a gross asset between equality and efficiency choices. Thus, humans have an equality preference over an efficiency preference both for human and non-human agents regardless of their visual appearances. The equity in distributive justice is affected by a human's emotional personality.","PeriodicalId":319020,"journal":{"name":"2015 2nd International Conference on Advanced Informatics: Concepts, Theory and Applications (ICAICTA)","volume":"25 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2015-11-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122317835","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 : 2015-11-23DOI: 10.1109/ICAICTA.2015.7335369
Pakawan Pugsee, Monsinee Niyomvanich
Suggestion analysis for food recipe improvement is to identify helpful suggestions from user comments to improve the recipes. Consequently, user comments about food recipes are classified into two groups that are comments with suggestions or without suggestions. The word information from modified lexicons and created rules for interpreting meaning are applied to analyze those comments or opinions. Natural language processing and text analysis are included in the proposed analysis technique. The automate comment analysis can help both users to choose the preferred food recipes and recipe authors to develop their own creative recipes. To summarize food recipe improvement, the user comments are collected and grouped into suggestion comments and other comments. The evaluation of proposed suggestion analysis shows that the accuracy and precision of comment classification are more than 70%.
{"title":"Suggestion analysis for food recipe improvement","authors":"Pakawan Pugsee, Monsinee Niyomvanich","doi":"10.1109/ICAICTA.2015.7335369","DOIUrl":"https://doi.org/10.1109/ICAICTA.2015.7335369","url":null,"abstract":"Suggestion analysis for food recipe improvement is to identify helpful suggestions from user comments to improve the recipes. Consequently, user comments about food recipes are classified into two groups that are comments with suggestions or without suggestions. The word information from modified lexicons and created rules for interpreting meaning are applied to analyze those comments or opinions. Natural language processing and text analysis are included in the proposed analysis technique. The automate comment analysis can help both users to choose the preferred food recipes and recipe authors to develop their own creative recipes. To summarize food recipe improvement, the user comments are collected and grouped into suggestion comments and other comments. The evaluation of proposed suggestion analysis shows that the accuracy and precision of comment classification are more than 70%.","PeriodicalId":319020,"journal":{"name":"2015 2nd International Conference on Advanced Informatics: Concepts, Theory and Applications (ICAICTA)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2015-11-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131164424","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 : 2015-11-23DOI: 10.1109/ICAICTA.2015.7335377
Kazuya Ito, Yuki Ota, Hiroshi Higashi, S. Nakauchi
The goal of this study is to develop a functional illuminant which assists medical institution workers who use injection equipment. In this paper, the functional illuminant for supporting people in distinguishing blood vessels from skins was developed. This functional illuminant consists of three types of LEDs. The illuminant with various LED was simulated and the three types of LEDs are selected in such a way that the resulted illuminant emphasizes the color difference between skins and blood vessels. Moreover, we developed a prototype of this functional illuminant and tested it. The test shows that the functional illuminant can support people in distinguishing blood vessels from skins. Furthermore, our experiments suggest that the functional illuminant is robust to individual difference in skin color.
{"title":"Spectral-difference enhancing illuminant for improving visual detection of blood vessels","authors":"Kazuya Ito, Yuki Ota, Hiroshi Higashi, S. Nakauchi","doi":"10.1109/ICAICTA.2015.7335377","DOIUrl":"https://doi.org/10.1109/ICAICTA.2015.7335377","url":null,"abstract":"The goal of this study is to develop a functional illuminant which assists medical institution workers who use injection equipment. In this paper, the functional illuminant for supporting people in distinguishing blood vessels from skins was developed. This functional illuminant consists of three types of LEDs. The illuminant with various LED was simulated and the three types of LEDs are selected in such a way that the resulted illuminant emphasizes the color difference between skins and blood vessels. Moreover, we developed a prototype of this functional illuminant and tested it. The test shows that the functional illuminant can support people in distinguishing blood vessels from skins. Furthermore, our experiments suggest that the functional illuminant is robust to individual difference in skin color.","PeriodicalId":319020,"journal":{"name":"2015 2nd International Conference on Advanced Informatics: Concepts, Theory and Applications (ICAICTA)","volume":"13 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2015-11-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123605374","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 : 2015-11-23DOI: 10.1109/ICAICTA.2015.7335354
I. Setiadi, A. I. Kistijantoro
The need of scalable databases has raised rapidly in these past few years. Researchers and developers have tried to develop several techniques to create replications and partitions in non-relational databases. However, high latency between distributed data centers has imposed a costly bottleneck to the system's performance. In this paper, we present a system design for nonrelational database - TippyDB - that provides better response time for users who are accessing our service. We enhance our system with the important observation that interactions between people almost always happen in a limited geographical area. We demonstrate that, in contrast with other NoSQL databases, our system offers a considerable improvement of performance in a distributed environment.
{"title":"TippyDB: Geographically-aware distributed NoSQL Key-Value store","authors":"I. Setiadi, A. I. Kistijantoro","doi":"10.1109/ICAICTA.2015.7335354","DOIUrl":"https://doi.org/10.1109/ICAICTA.2015.7335354","url":null,"abstract":"The need of scalable databases has raised rapidly in these past few years. Researchers and developers have tried to develop several techniques to create replications and partitions in non-relational databases. However, high latency between distributed data centers has imposed a costly bottleneck to the system's performance. In this paper, we present a system design for nonrelational database - TippyDB - that provides better response time for users who are accessing our service. We enhance our system with the important observation that interactions between people almost always happen in a limited geographical area. We demonstrate that, in contrast with other NoSQL databases, our system offers a considerable improvement of performance in a distributed environment.","PeriodicalId":319020,"journal":{"name":"2015 2nd International Conference on Advanced Informatics: Concepts, Theory and Applications (ICAICTA)","volume":"118 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2015-11-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115451136","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 : 2015-11-23DOI: 10.1109/ICAICTA.2015.7335368
Suvalak Vijitpornkul, Worawan Marurngsith
Crowd movement during natural disasters and major accidents can affect the success of evacuation procedure. Thus to develop an effective evacuation plan, a wide-range of scenarios causing different routes and patterns of crowd movement should be considered. Recent researches in agent-based simulation have achieved techniques to simulate crowd movement in emergency scenarios at city scale. However simulating crowd movement at a macroscopic level for disasters which might affect several cities, like large-scale flood, is still a challenge. This paper addresses this issue and makes three contributions. First, the development of an agent-based layered model to simulate large-scale flood using GIS is demonstrated. Second, the simulation of crowd agents' movement on available roads is presented. Third, the preliminary experiments running on private Cloud server is reported. The experiments cover case studies illustrated the movement of crowd agents around Thailand while several parts of the country were inundated. The 2D animation depict the movement of crowd; and the simulation results show the status of the agents and the amount of individuals which required shelters. To simulate one day events, the simulator took 4-9 hours execution time depending on the severity of floods and available facilities.
{"title":"Simulating crowd movement in agent-based model of large-scale flood","authors":"Suvalak Vijitpornkul, Worawan Marurngsith","doi":"10.1109/ICAICTA.2015.7335368","DOIUrl":"https://doi.org/10.1109/ICAICTA.2015.7335368","url":null,"abstract":"Crowd movement during natural disasters and major accidents can affect the success of evacuation procedure. Thus to develop an effective evacuation plan, a wide-range of scenarios causing different routes and patterns of crowd movement should be considered. Recent researches in agent-based simulation have achieved techniques to simulate crowd movement in emergency scenarios at city scale. However simulating crowd movement at a macroscopic level for disasters which might affect several cities, like large-scale flood, is still a challenge. This paper addresses this issue and makes three contributions. First, the development of an agent-based layered model to simulate large-scale flood using GIS is demonstrated. Second, the simulation of crowd agents' movement on available roads is presented. Third, the preliminary experiments running on private Cloud server is reported. The experiments cover case studies illustrated the movement of crowd agents around Thailand while several parts of the country were inundated. The 2D animation depict the movement of crowd; and the simulation results show the status of the agents and the amount of individuals which required shelters. To simulate one day events, the simulator took 4-9 hours execution time depending on the severity of floods and available facilities.","PeriodicalId":319020,"journal":{"name":"2015 2nd International Conference on Advanced Informatics: Concepts, Theory and Applications (ICAICTA)","volume":"35 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2015-11-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131517084","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 : 2015-11-23DOI: 10.1109/ICAICTA.2015.7335351
Tomoya Shirai, Kyoko Kanzaki, Hirofumi Yabumoto, H. Isahara
In order to realize friendly man-machine communication, machines must understand not only surface expressions of human utterance but also deep meanings of human behavior. We started compilation of “paraphrase representation list of compound verbs” as the first step of investigation and standardization of lexical items which is a part of “control language for action”. We processed the corpus and vectorized the data by using Word2Vec. Using the created vector, we performed a calculation of similarity between the compound verbs and verbs in a corpus by cosine similarity, and created a paraphrase representation list. We got paraphrase expressions for 1899 compound verbs among 3289 compound verbs (including orthographic variants) stored in the compound verb lexicon. We found by this method words which do not exist in the Japanese WordNet. We investigated the words that exist only in the result of automatic extraction, and found that there are 213 unknown words and 227 new synonymous relationship. What is worthy of special mention is that there is 14 differences between the unknown word and a new synonymous relationship, which means we could find 14 words which are stored in the Japanese WordNet, but are not considered as synonyms of a word. We can say that the proposed method is useful for the expansion of paraphrase relationship listed by human intuitions.
{"title":"Compilation and evaluation of paraphrase representation list of compound verbs: Toward development of “Control language for action”","authors":"Tomoya Shirai, Kyoko Kanzaki, Hirofumi Yabumoto, H. Isahara","doi":"10.1109/ICAICTA.2015.7335351","DOIUrl":"https://doi.org/10.1109/ICAICTA.2015.7335351","url":null,"abstract":"In order to realize friendly man-machine communication, machines must understand not only surface expressions of human utterance but also deep meanings of human behavior. We started compilation of “paraphrase representation list of compound verbs” as the first step of investigation and standardization of lexical items which is a part of “control language for action”. We processed the corpus and vectorized the data by using Word2Vec. Using the created vector, we performed a calculation of similarity between the compound verbs and verbs in a corpus by cosine similarity, and created a paraphrase representation list. We got paraphrase expressions for 1899 compound verbs among 3289 compound verbs (including orthographic variants) stored in the compound verb lexicon. We found by this method words which do not exist in the Japanese WordNet. We investigated the words that exist only in the result of automatic extraction, and found that there are 213 unknown words and 227 new synonymous relationship. What is worthy of special mention is that there is 14 differences between the unknown word and a new synonymous relationship, which means we could find 14 words which are stored in the Japanese WordNet, but are not considered as synonyms of a word. We can say that the proposed method is useful for the expansion of paraphrase relationship listed by human intuitions.","PeriodicalId":319020,"journal":{"name":"2015 2nd International Conference on Advanced Informatics: Concepts, Theory and Applications (ICAICTA)","volume":"198 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2015-11-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124103544","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 : 2015-11-23DOI: 10.1109/ICAICTA.2015.7335383
F. Muhammad, M. L. Khodra
Information extraction is a process to find structured text from unstructured or semi-structured text. This research has an objective to build an information extraction system specialized for Events in Indonesian tweets. The system consists of two main parts. First part filters relevant tweet from irrelevant tweet. This part is only using a rule based approach with additional bag of words feature and gets the best accuracy of 86%. The second part is doing the extraction process. From our experiments, we get the best combination for extractor module by using multi token tokenization method, all feature set and 1st Order Conditional Random Field. This combination result in average accuracy of 74% per token.
{"title":"Event information extraction from Indonesian tweets using conditional random field","authors":"F. Muhammad, M. L. Khodra","doi":"10.1109/ICAICTA.2015.7335383","DOIUrl":"https://doi.org/10.1109/ICAICTA.2015.7335383","url":null,"abstract":"Information extraction is a process to find structured text from unstructured or semi-structured text. This research has an objective to build an information extraction system specialized for Events in Indonesian tweets. The system consists of two main parts. First part filters relevant tweet from irrelevant tweet. This part is only using a rule based approach with additional bag of words feature and gets the best accuracy of 86%. The second part is doing the extraction process. From our experiments, we get the best combination for extractor module by using multi token tokenization method, all feature set and 1st Order Conditional Random Field. This combination result in average accuracy of 74% per token.","PeriodicalId":319020,"journal":{"name":"2015 2nd International Conference on Advanced Informatics: Concepts, Theory and Applications (ICAICTA)","volume":"7 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2015-11-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134535521","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 : 2015-11-23DOI: 10.1109/ICAICTA.2015.7335381
Y. T. Samuel, D. H. Widyantoro, A. I. Wuryandari
Fundamental indicator news have a strong influence on the movement of foreign exchange rates. There were a lot of fundamental indicator news on the internet that rapidly changes, but to read all of it and make conclusion need a lot of time and effort. Therefore a system is needed to summarize the news. In this paper we propose a framework to generate a scheme that summarize factors affecting the fundamental indicator, where these factors may adapt automatically. The approach used in this system based on 3 (three) phases: 1. News Classification. At this stage, classification process is done by looking at the factors that affect each indicator. The process of obtaining these factors is done by using information extraction approach. 2 Generating scheme based on the Influencing factors, where the scheme can adapt automatically to the factors that affect an indicator. Methods in determining the scheme is based on the extraction of information. 3. Fills the scheme. At this stage, the scheme will be filled with appropriate information so that it will produce the summary of news which related to specific indicators.
{"title":"A framework of fundamental news summarization to determine the direction of foreign exchange rate using adaptive indicator scheme","authors":"Y. T. Samuel, D. H. Widyantoro, A. I. Wuryandari","doi":"10.1109/ICAICTA.2015.7335381","DOIUrl":"https://doi.org/10.1109/ICAICTA.2015.7335381","url":null,"abstract":"Fundamental indicator news have a strong influence on the movement of foreign exchange rates. There were a lot of fundamental indicator news on the internet that rapidly changes, but to read all of it and make conclusion need a lot of time and effort. Therefore a system is needed to summarize the news. In this paper we propose a framework to generate a scheme that summarize factors affecting the fundamental indicator, where these factors may adapt automatically. The approach used in this system based on 3 (three) phases: 1. News Classification. At this stage, classification process is done by looking at the factors that affect each indicator. The process of obtaining these factors is done by using information extraction approach. 2 Generating scheme based on the Influencing factors, where the scheme can adapt automatically to the factors that affect an indicator. Methods in determining the scheme is based on the extraction of information. 3. Fills the scheme. At this stage, the scheme will be filled with appropriate information so that it will produce the summary of news which related to specific indicators.","PeriodicalId":319020,"journal":{"name":"2015 2nd International Conference on Advanced Informatics: Concepts, Theory and Applications (ICAICTA)","volume":"3 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2015-11-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128534525","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 : 2015-11-23DOI: 10.1109/ICAICTA.2015.7335376
I. Suwardi, D. Lestari, Dicky Prima Satya
Current Geographical Information System (GIS) has been applied the classical point-in-polygon algorithm such as the ray casting algorithm and winding algorithm to conduct spatial analysis. These algorithms have linear complexity with the number of points available in the map. In this paper, we introduce an efficient algorithm to handle arbitrary polygonal queries on a GIS based on the boolean overlay. The algorithm is able to find whether a point is inside, outside, or on the boundary of a given polygon by utilizing a very simple boolean overlay mechanisms in a GIS. Experimental results show that the algorithm works very accurate with 100% accuracy and works very fast.
目前的地理信息系统(geographic Information System, GIS)已经采用经典的多边形点算法，如光线投射算法和缠绕算法进行空间分析。这些算法与地图中可用点的数量呈线性关系。本文介绍了一种基于布尔叠加的高效处理GIS上任意多边形查询的算法。该算法通过利用GIS中非常简单的布尔叠加机制，能够找到一个点是在给定多边形的内部，外部还是在边界上。实验结果表明，该算法的准确率达到100%，并且速度很快。
{"title":"Handling arbitrary polygon query based on the boolean overlay on a geographical information system","authors":"I. Suwardi, D. Lestari, Dicky Prima Satya","doi":"10.1109/ICAICTA.2015.7335376","DOIUrl":"https://doi.org/10.1109/ICAICTA.2015.7335376","url":null,"abstract":"Current Geographical Information System (GIS) has been applied the classical point-in-polygon algorithm such as the ray casting algorithm and winding algorithm to conduct spatial analysis. These algorithms have linear complexity with the number of points available in the map. In this paper, we introduce an efficient algorithm to handle arbitrary polygonal queries on a GIS based on the boolean overlay. The algorithm is able to find whether a point is inside, outside, or on the boundary of a given polygon by utilizing a very simple boolean overlay mechanisms in a GIS. Experimental results show that the algorithm works very accurate with 100% accuracy and works very fast.","PeriodicalId":319020,"journal":{"name":"2015 2nd International Conference on Advanced Informatics: Concepts, Theory and Applications (ICAICTA)","volume":"55 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2015-11-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116948965","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 : 2015-11-23DOI: 10.1109/ICAICTA.2015.7335387
M. Kikuchi, Mitsuo Yoshida, Masayuki Okabe, Kyoji Umemura
Sometimes, we do not use a maximum likelihood estimator of a probability but it's a smoothed estimator in order to cope with the zero frequency problem. This is often the case when we use the Naive Bayes classifier. Laplace smoothing is a popular choice with the value of Laplace smoothing estimator being the expected value of posterior distribution of the probability where we assume that the prior is uniform distribution. In this paper, we investigate the confidence intervals of the estimator of Laplace smoothing. We show that the likelihood function for this confidence interval is the same as the likelihood of a maximum likelihood estimated value of a probability of Bernoulli trials. Although the confidence interval of the maximum likelihood estimator of the Bernoulli trial probability has been studied well, and although the approximate formulas for the confidence interval are well known, we cannot use the interval of maximum likelihood estimator since the interval contains the value 0, which is not suitable for the Naive Bayes classifier. We are also interested in the accuracy of existing approximation methods since these approximation methods are frequently used but their accuracy is not well discussed. Thus, we obtain the confidence interval by numerically integrating the likelihood function. In this paper, we report the difference between the confidence interval that we computed and the confidence interval by approximate formulas. Finally, we include a URL, where all of the intervals that we computed are available.
{"title":"Confidence interval of probability estimator of Laplace smoothing","authors":"M. Kikuchi, Mitsuo Yoshida, Masayuki Okabe, Kyoji Umemura","doi":"10.1109/ICAICTA.2015.7335387","DOIUrl":"https://doi.org/10.1109/ICAICTA.2015.7335387","url":null,"abstract":"Sometimes, we do not use a maximum likelihood estimator of a probability but it's a smoothed estimator in order to cope with the zero frequency problem. This is often the case when we use the Naive Bayes classifier. Laplace smoothing is a popular choice with the value of Laplace smoothing estimator being the expected value of posterior distribution of the probability where we assume that the prior is uniform distribution. In this paper, we investigate the confidence intervals of the estimator of Laplace smoothing. We show that the likelihood function for this confidence interval is the same as the likelihood of a maximum likelihood estimated value of a probability of Bernoulli trials. Although the confidence interval of the maximum likelihood estimator of the Bernoulli trial probability has been studied well, and although the approximate formulas for the confidence interval are well known, we cannot use the interval of maximum likelihood estimator since the interval contains the value 0, which is not suitable for the Naive Bayes classifier. We are also interested in the accuracy of existing approximation methods since these approximation methods are frequently used but their accuracy is not well discussed. Thus, we obtain the confidence interval by numerically integrating the likelihood function. In this paper, we report the difference between the confidence interval that we computed and the confidence interval by approximate formulas. Finally, we include a URL, where all of the intervals that we computed are available.","PeriodicalId":319020,"journal":{"name":"2015 2nd International Conference on Advanced Informatics: Concepts, Theory and Applications (ICAICTA)","volume":"15 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2015-11-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126758750","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：