Pub Date : 2017-10-01DOI: 10.1109/BESC.2017.8256398
H. Mohammed, I. Hameed, R. Seidu
Variety of modeling techniques have been widely applied for predicting levels of fecal indicator organisms in raw water. However, deficiencies in the performances of some methods make it difficult for implementation in full-scale water supply systems. This study examines the efficiency of random forest (RF) which is made up of a number of decision trees in the prediction of fecal indicator organisms in raw water based on records of conductivity, pH, color, turbidity taken from a drinking water source in Bergen, Norway, as well as seasons. Results of the study indicate that the method is capable of estimating important variations in levels of the microorganisms in the raw water with acceptable accuracy. Color of water and the effect of autumn season were the most important in explaining the variations in the levels of the coliform bacteria, intestinal enterococci and E. coli in raw water in both the full and the reduced models. Considerable reduction in the model out-of-bag sample error was achieved in the reduced models, where only two most important variables were used as predictors. With further research aimed at improving the estimation error, the random forest method can be a reliable tool for real time prediction of potential levels of microorganisms in raw water.
{"title":"Random forest tree for predicting fecal indicator organisms in drinking water supply","authors":"H. Mohammed, I. Hameed, R. Seidu","doi":"10.1109/BESC.2017.8256398","DOIUrl":"https://doi.org/10.1109/BESC.2017.8256398","url":null,"abstract":"Variety of modeling techniques have been widely applied for predicting levels of fecal indicator organisms in raw water. However, deficiencies in the performances of some methods make it difficult for implementation in full-scale water supply systems. This study examines the efficiency of random forest (RF) which is made up of a number of decision trees in the prediction of fecal indicator organisms in raw water based on records of conductivity, pH, color, turbidity taken from a drinking water source in Bergen, Norway, as well as seasons. Results of the study indicate that the method is capable of estimating important variations in levels of the microorganisms in the raw water with acceptable accuracy. Color of water and the effect of autumn season were the most important in explaining the variations in the levels of the coliform bacteria, intestinal enterococci and E. coli in raw water in both the full and the reduced models. Considerable reduction in the model out-of-bag sample error was achieved in the reduced models, where only two most important variables were used as predictors. With further research aimed at improving the estimation error, the random forest method can be a reliable tool for real time prediction of potential levels of microorganisms in raw water.","PeriodicalId":142098,"journal":{"name":"2017 International Conference on Behavioral, Economic, Socio-cultural Computing (BESC)","volume":"7 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116858230","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}
Predicting the popularity of online content is an important issue. The mainstream method is to model the cumulative growth of the popularity as a temporal point process and to make predictions based on the observed initial period of information cascade. The peeking window, which will be taken into consideration in making predictions, is vitally important for the accuracy of predictions. However, the existing studies only generated hypotheses about the initial burst and maintained a consistent size of the peeking window for all content. The limited accuracy of previous approaches raises a fundamental question, i.e., How can we obtain the most effective part of the history to make an accurate prediction? In this paper, we identified the existence of a strong correlation between the peeking window and the temporal dynamic of the instantaneous relative attractiveness for a given online content. An investigation was conducted to explore the adaptive peeking window, which was used in a selfexciting point process model to predict eventual future popularity. Empirical studies on a Twitter dataset demonstrated that the proposed method significantly outperformed existing approaches.
{"title":"Leveraging adaptive peeking window to improve self-exciting point process model for popularity prediction","authors":"Zemin Bao, Yun Liu, Hui Liu, Zhenjiang Zhang, Bo Shen, Junjun Cheng","doi":"10.1109/BESC.2017.8256373","DOIUrl":"https://doi.org/10.1109/BESC.2017.8256373","url":null,"abstract":"Predicting the popularity of online content is an important issue. The mainstream method is to model the cumulative growth of the popularity as a temporal point process and to make predictions based on the observed initial period of information cascade. The peeking window, which will be taken into consideration in making predictions, is vitally important for the accuracy of predictions. However, the existing studies only generated hypotheses about the initial burst and maintained a consistent size of the peeking window for all content. The limited accuracy of previous approaches raises a fundamental question, i.e., How can we obtain the most effective part of the history to make an accurate prediction? In this paper, we identified the existence of a strong correlation between the peeking window and the temporal dynamic of the instantaneous relative attractiveness for a given online content. An investigation was conducted to explore the adaptive peeking window, which was used in a selfexciting point process model to predict eventual future popularity. Empirical studies on a Twitter dataset demonstrated that the proposed method significantly outperformed existing approaches.","PeriodicalId":142098,"journal":{"name":"2017 International Conference on Behavioral, Economic, Socio-cultural Computing (BESC)","volume":"40 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124401278","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 : 2017-10-01DOI: 10.1109/BESC.2017.8256368
Menglan Ma, Peng Fang, Jianbo Gao, Changqing Song
Tone of a news report is intimately related to the topic of the article, and therefore can reflect the attitude of journalists or media. It is often thought that tone of news report, especially the international news, is affected by ideology. To test whether this is the case, we use GDELT (Global Database of Events, Language, and Tone) to compare the tone of international news reports among nine countries, the United States, Britain, Australia, Germany, China, Nigeria, Argentina, Zimbabwe and United Arab Emirates. We find that albeit international news reported by different countries differ significantly in event types, they nevertheless converge in tone. The former reflects the different preferences in content selection by each country, and thus reflect culture. The convergence in tone reflects the fact that reporters are not overly influenced by their respective ideology; rather they share to a large degree some universal values when covering international news.
{"title":"Does ideology affect the tone of international news coverage?","authors":"Menglan Ma, Peng Fang, Jianbo Gao, Changqing Song","doi":"10.1109/BESC.2017.8256368","DOIUrl":"https://doi.org/10.1109/BESC.2017.8256368","url":null,"abstract":"Tone of a news report is intimately related to the topic of the article, and therefore can reflect the attitude of journalists or media. It is often thought that tone of news report, especially the international news, is affected by ideology. To test whether this is the case, we use GDELT (Global Database of Events, Language, and Tone) to compare the tone of international news reports among nine countries, the United States, Britain, Australia, Germany, China, Nigeria, Argentina, Zimbabwe and United Arab Emirates. We find that albeit international news reported by different countries differ significantly in event types, they nevertheless converge in tone. The former reflects the different preferences in content selection by each country, and thus reflect culture. The convergence in tone reflects the fact that reporters are not overly influenced by their respective ideology; rather they share to a large degree some universal values when covering international news.","PeriodicalId":142098,"journal":{"name":"2017 International Conference on Behavioral, Economic, Socio-cultural Computing (BESC)","volume":"11 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128294326","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 : 2017-10-01DOI: 10.1109/BESC.2017.8256410
Krzysztof Rudek, J. Kozlak
Social media users create communities or groups that focus on a particular topic or place. In addition, logins ascribed to users allow us to link created content with its authors, by which means direct relationships between them are being created. In this article we analyze relations between users of Polish blogosphere, where direct interactions between them constitute a basis for assessment of the relation strength and its durability in time. We also analyze how amount of created content, influences the strength of the relationship between their author and the bloggers writing comments.
{"title":"The influence of relationships strength on their duration in blogosphere","authors":"Krzysztof Rudek, J. Kozlak","doi":"10.1109/BESC.2017.8256410","DOIUrl":"https://doi.org/10.1109/BESC.2017.8256410","url":null,"abstract":"Social media users create communities or groups that focus on a particular topic or place. In addition, logins ascribed to users allow us to link created content with its authors, by which means direct relationships between them are being created. In this article we analyze relations between users of Polish blogosphere, where direct interactions between them constitute a basis for assessment of the relation strength and its durability in time. We also analyze how amount of created content, influences the strength of the relationship between their author and the bloggers writing comments.","PeriodicalId":142098,"journal":{"name":"2017 International Conference on Behavioral, Economic, Socio-cultural Computing (BESC)","volume":"18 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134538300","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 : 2017-10-01DOI: 10.1109/BESC.2017.8256392
Yiming Wei, Guiying Zhang, Wenyong Weng
From the old Chinese saying “While his parents are alive, the son may not go abroad to a distance.” to the new buzzwords “There is such a lot of world to see.”. Different attitudes towards tourism bear the marks of times and technology. Since the 21st century, with the continuous improvement of China's economic and per capita disposable income, the tourism industry has undergone enormous changes in the wave of Internet tourism. On september 16, 2015, China National Tourism Administration issued Notification on the Implementation Plan of “Travel + Internet” Action. This notification points out that in the new round of science and technology revolution, the combination of Internet and tourism has brought a subversive change to the traditional tourism industry, and the deep integration of the two has become an irreversible trend of the times. To grasp the new vision of tourism integrated into Internet, we should sort out two key factors [1] of tourism and Internet. One is the force of the core factors of Internet and the other is the key components of tourism system. Thus can ultimately stimulate The strategic global evolution of the tourism industry.
{"title":"The influence of “Internet Plus” on China's tourism: Evolution and breakthrough","authors":"Yiming Wei, Guiying Zhang, Wenyong Weng","doi":"10.1109/BESC.2017.8256392","DOIUrl":"https://doi.org/10.1109/BESC.2017.8256392","url":null,"abstract":"From the old Chinese saying “While his parents are alive, the son may not go abroad to a distance.” to the new buzzwords “There is such a lot of world to see.”. Different attitudes towards tourism bear the marks of times and technology. Since the 21st century, with the continuous improvement of China's economic and per capita disposable income, the tourism industry has undergone enormous changes in the wave of Internet tourism. On september 16, 2015, China National Tourism Administration issued Notification on the Implementation Plan of “Travel + Internet” Action. This notification points out that in the new round of science and technology revolution, the combination of Internet and tourism has brought a subversive change to the traditional tourism industry, and the deep integration of the two has become an irreversible trend of the times. To grasp the new vision of tourism integrated into Internet, we should sort out two key factors [1] of tourism and Internet. One is the force of the core factors of Internet and the other is the key components of tourism system. Thus can ultimately stimulate The strategic global evolution of the tourism industry.","PeriodicalId":142098,"journal":{"name":"2017 International Conference on Behavioral, Economic, Socio-cultural Computing (BESC)","volume":"12 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127717335","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 : 2017-10-01DOI: 10.1109/BESC.2017.8256396
Muhammad Irfan, I. Hameed
This paper presents a deep learning based mechanism to analyze the healthcare data to detect the possible anomalies and classify the data into different so that we can know the nature of health problem. An implementation of deep convolutional neural network (DCNN) to classify the image patterns data extracted from electrocardiograph (ECG) is discussed in detail. A dedicated convolutional neural network will be trained using different data samples taken from various patients termed as training data. On later stage, the algorithm is tested using test data samples and it is observed that the proposed algorithm does perform efficient, stable and superior classification performance for the detection of normal beats (N-Type), ventricular ectopic beats (V-Type) and super ventricular ectopic beats (SV-Type). The experimental analysis shows the recognition accuracy and loss value. Subsequently, sensitivity and specificity of the algorithm is measured to show the effectiveness of the proposed solution.
{"title":"Deep learning based classification for healthcare data analysis system","authors":"Muhammad Irfan, I. Hameed","doi":"10.1109/BESC.2017.8256396","DOIUrl":"https://doi.org/10.1109/BESC.2017.8256396","url":null,"abstract":"This paper presents a deep learning based mechanism to analyze the healthcare data to detect the possible anomalies and classify the data into different so that we can know the nature of health problem. An implementation of deep convolutional neural network (DCNN) to classify the image patterns data extracted from electrocardiograph (ECG) is discussed in detail. A dedicated convolutional neural network will be trained using different data samples taken from various patients termed as training data. On later stage, the algorithm is tested using test data samples and it is observed that the proposed algorithm does perform efficient, stable and superior classification performance for the detection of normal beats (N-Type), ventricular ectopic beats (V-Type) and super ventricular ectopic beats (SV-Type). The experimental analysis shows the recognition accuracy and loss value. Subsequently, sensitivity and specificity of the algorithm is measured to show the effectiveness of the proposed solution.","PeriodicalId":142098,"journal":{"name":"2017 International Conference on Behavioral, Economic, Socio-cultural Computing (BESC)","volume":"118 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127983747","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 : 2017-10-01DOI: 10.1109/BESC.2017.8256361
J. Kozlak, Malgorzata Zabinska
One of major problems that the societies and economies of developed countries face are traffic congestion and travel speed limits caused by them. Therefore, there is need to work on more efficient traffic control models than these commonly used. The aim of this paper is to propose such a way of managing the road network in order to adapt the allocation and costs of particular sections of roads to financial resources offered by the drivers of vehicles using them. A model of traffic management in a city based on the market model and application of the agent-based approach is presented. Numerous experiments have been conducted evaluating the approach for different types of road network graphs, route booking algorithms, and various cost functions of drivers.
{"title":"Agent-based simulation of road traffic using market approach","authors":"J. Kozlak, Malgorzata Zabinska","doi":"10.1109/BESC.2017.8256361","DOIUrl":"https://doi.org/10.1109/BESC.2017.8256361","url":null,"abstract":"One of major problems that the societies and economies of developed countries face are traffic congestion and travel speed limits caused by them. Therefore, there is need to work on more efficient traffic control models than these commonly used. The aim of this paper is to propose such a way of managing the road network in order to adapt the allocation and costs of particular sections of roads to financial resources offered by the drivers of vehicles using them. A model of traffic management in a city based on the market model and application of the agent-based approach is presented. Numerous experiments have been conducted evaluating the approach for different types of road network graphs, route booking algorithms, and various cost functions of drivers.","PeriodicalId":142098,"journal":{"name":"2017 International Conference on Behavioral, Economic, Socio-cultural Computing (BESC)","volume":"45 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134119933","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 : 2017-10-01DOI: 10.1109/BESC.2017.8256358
Svitlana Galeshchuk, Y. Demazeau
This paper investigates the advantages of deep learning methods, in particular convolutional neural networks, to predict the exchange rate for non-reserve currencies of developed economies. Our findings prove better performance of deep learning methods comparing to the other available techniques.
{"title":"Forecasting hungarian forint exchange rate with convolutional neural networks","authors":"Svitlana Galeshchuk, Y. Demazeau","doi":"10.1109/BESC.2017.8256358","DOIUrl":"https://doi.org/10.1109/BESC.2017.8256358","url":null,"abstract":"This paper investigates the advantages of deep learning methods, in particular convolutional neural networks, to predict the exchange rate for non-reserve currencies of developed economies. Our findings prove better performance of deep learning methods comparing to the other available techniques.","PeriodicalId":142098,"journal":{"name":"2017 International Conference on Behavioral, Economic, Socio-cultural Computing (BESC)","volume":"21 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134306468","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 : 2017-10-01DOI: 10.1109/BESC.2017.8256363
Hung-Wen Lin, Jing-Bo Huang, Kun-Ben Lin
We studied the relationships among momentum, transparency, and media by causality detections in Chinese stock markets. Our results suggest that momentum strongly and individually attracts media coverage in China, as this effect exists both in the Granger test and the transfer entropy test. Media coverage causes momentum only in Granger test, which is consistent with Hillert et al. (2014). In other words, momentum and media coverage are tightly related to each other in China. In the Granger test, transparency causes momentum with the assistance of media coverage, and it receives media coverage with the assistance of momentum. These results suggest that transparency has to release its information because of the pushing power from momentum or media. In the transfer entropy test, transparency can individually cause momentum or media coverage, which implies that transparency indirectly releases information when there is no influence of momentum or media.
本文通过对中国股票市场的因果关系检验，研究了动量、透明度和媒介三者之间的关系。我们的研究结果表明，动量在中国对媒体报道具有很强的吸引力，这种效应在格兰杰检验和传递熵检验中都存在。媒体报道仅在格兰杰检验中产生动量，这与Hillert et al.(2014)的结论一致。换句话说，在中国，势头和媒体报道是紧密相关的。在格兰杰检验中，透明度在媒体报道的帮助下产生动量，在动量的帮助下获得媒体报道。这些结果表明，由于动量或媒体的推动，透明度必须发布其信息。在传递熵检验中，透明度可以单独引起动量或媒体报道，这意味着在没有动量或媒体影响的情况下，透明度是间接释放信息的。
{"title":"Causalities among momentum, transparency and media in China","authors":"Hung-Wen Lin, Jing-Bo Huang, Kun-Ben Lin","doi":"10.1109/BESC.2017.8256363","DOIUrl":"https://doi.org/10.1109/BESC.2017.8256363","url":null,"abstract":"We studied the relationships among momentum, transparency, and media by causality detections in Chinese stock markets. Our results suggest that momentum strongly and individually attracts media coverage in China, as this effect exists both in the Granger test and the transfer entropy test. Media coverage causes momentum only in Granger test, which is consistent with Hillert et al. (2014). In other words, momentum and media coverage are tightly related to each other in China. In the Granger test, transparency causes momentum with the assistance of media coverage, and it receives media coverage with the assistance of momentum. These results suggest that transparency has to release its information because of the pushing power from momentum or media. In the transfer entropy test, transparency can individually cause momentum or media coverage, which implies that transparency indirectly releases information when there is no influence of momentum or media.","PeriodicalId":142098,"journal":{"name":"2017 International Conference on Behavioral, Economic, Socio-cultural Computing (BESC)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114147765","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 : 2017-10-01DOI: 10.1109/BESC.2017.8256375
Yang Liu, Lin Li, Zhongwei Xie, Ge Zhu, Guiming Xu
Recently, in the world natural and man-made disasters have occurred frequently. In this case, disaster prevention work is necessary. In order to improve the quality of shelter site selection, this paper proposes social chocie based integrated evaluation models which combine the statistics and social science theory to construct a new evaluation model. By comparing the results calculated from all the models with expert solutions, it shows that the proposed social choice based integrated evaluation models get better results than the other integrated models and all the traditional models.
{"title":"Urban emergency shelter site selection","authors":"Yang Liu, Lin Li, Zhongwei Xie, Ge Zhu, Guiming Xu","doi":"10.1109/BESC.2017.8256375","DOIUrl":"https://doi.org/10.1109/BESC.2017.8256375","url":null,"abstract":"Recently, in the world natural and man-made disasters have occurred frequently. In this case, disaster prevention work is necessary. In order to improve the quality of shelter site selection, this paper proposes social chocie based integrated evaluation models which combine the statistics and social science theory to construct a new evaluation model. By comparing the results calculated from all the models with expert solutions, it shows that the proposed social choice based integrated evaluation models get better results than the other integrated models and all the traditional models.","PeriodicalId":142098,"journal":{"name":"2017 International Conference on Behavioral, Economic, Socio-cultural Computing (BESC)","volume":"203 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131461272","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：