Pub Date : 2013-10-07DOI: 10.1109/ICITEED.2013.6676243
E. Sudarmilah, R. Ferdiana, L. Nugroho, A. Susanto, Neila Ramdhani
One of difficulties in learning mathematics (counting) can be overcome by providing a relaxed and fun learning for preschoolers. Games can be used as an alternative solution. This study was conducted as a pilot project for reviewing the Kodu, Unity 3D and Construct 2 game platform for this purpose. The method used is the classification, review/evaluation, prototyping and analysis. Tech Review of these game platforms will be discussed as a result in this paper.
{"title":"Tech review: Game platform for upgrading counting ability on preschool children","authors":"E. Sudarmilah, R. Ferdiana, L. Nugroho, A. Susanto, Neila Ramdhani","doi":"10.1109/ICITEED.2013.6676243","DOIUrl":"https://doi.org/10.1109/ICITEED.2013.6676243","url":null,"abstract":"One of difficulties in learning mathematics (counting) can be overcome by providing a relaxed and fun learning for preschoolers. Games can be used as an alternative solution. This study was conducted as a pilot project for reviewing the Kodu, Unity 3D and Construct 2 game platform for this purpose. The method used is the classification, review/evaluation, prototyping and analysis. Tech Review of these game platforms will be discussed as a result in this paper.","PeriodicalId":204082,"journal":{"name":"2013 International Conference on Information Technology and Electrical Engineering (ICITEE)","volume":"159 2 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2013-10-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125934232","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 : 2013-10-01DOI: 10.1109/ICITEED.2013.6676286
I. Setiawan, A. Priyadi, M. Purnomo
Hydro power plant is a power generation system that have non-minimum phase model showing initial inverse response characteristic. For span of broad electrical load regulation, conventional non adaptive control techniques, such as PI and PID control would degrade the performance of this power generation system. To ensure the stability of Hydro power plant for severe load variations, we need a kind of controller that has adaptive capability. On the other hand, the utilization of conventional adaptive techniques such as Self Tuning Regulator and Model Reference Adaptive Controller will be diverge to control plants showing non-minimum phase mode. In this paper, the implementation of adaptive intelligence control based on B-Spline neural network along with forward controller for controlling micro hydro power plant will be presented. Based on its characteristic, this adaptive control technique could be implemented directly without any prior training phase. From the simulation studies, the proposed scheme results fast transient response to load variations compared to traditional PI control and also very stable in responding to severe disturbance.
{"title":"Controlling of non-minimum phase micro hydro power plant based on adaptive B-Spline neural network","authors":"I. Setiawan, A. Priyadi, M. Purnomo","doi":"10.1109/ICITEED.2013.6676286","DOIUrl":"https://doi.org/10.1109/ICITEED.2013.6676286","url":null,"abstract":"Hydro power plant is a power generation system that have non-minimum phase model showing initial inverse response characteristic. For span of broad electrical load regulation, conventional non adaptive control techniques, such as PI and PID control would degrade the performance of this power generation system. To ensure the stability of Hydro power plant for severe load variations, we need a kind of controller that has adaptive capability. On the other hand, the utilization of conventional adaptive techniques such as Self Tuning Regulator and Model Reference Adaptive Controller will be diverge to control plants showing non-minimum phase mode. In this paper, the implementation of adaptive intelligence control based on B-Spline neural network along with forward controller for controlling micro hydro power plant will be presented. Based on its characteristic, this adaptive control technique could be implemented directly without any prior training phase. From the simulation studies, the proposed scheme results fast transient response to load variations compared to traditional PI control and also very stable in responding to severe disturbance.","PeriodicalId":204082,"journal":{"name":"2013 International Conference on Information Technology and Electrical Engineering (ICITEE)","volume":"30 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2013-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116442414","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 : 2013-10-01DOI: 10.1109/ICITEED.2013.6676248
K. Trisna, I. Mustika, Widyawan, S. Sulistyo
In a spectrum sharing system, lower-priority users are allowed to spatially reuse the spectrum allocated to higher-priority users as long as they do not disrupt communications of the latter. Therefore, to improve spectrum utilization, an important requirement for the former users is to manage the interference and ensure that the latter users can maintain reliable communications. This paper presents a game theoretic framework to model the dynamic spectrum sharing in cognitive radio networks. First, a utility function that captures the selfish and cooperative behavior of the lower-priority users to manage the interference by selecting the best channel with minimal intra- and inter-system interference is defined. Next, based on the defined utility function, the proposed framework can be formulated as a potential game; thus, the convergence to a Nash equilibrium point is ensured as long as the best response dynamic is adopted. At the equilibrium point, power allocation algorithm is proposed such that the interference to higher-priority users can be maintained below the maximum allowable level. The simulation results show the convergence of the proposed potential game and the performance improvement of higher-priority users in terms of SINR and outage probability.
{"title":"A game-theoretic approach for dynamic spectrum sharing in cognitive radio networks","authors":"K. Trisna, I. Mustika, Widyawan, S. Sulistyo","doi":"10.1109/ICITEED.2013.6676248","DOIUrl":"https://doi.org/10.1109/ICITEED.2013.6676248","url":null,"abstract":"In a spectrum sharing system, lower-priority users are allowed to spatially reuse the spectrum allocated to higher-priority users as long as they do not disrupt communications of the latter. Therefore, to improve spectrum utilization, an important requirement for the former users is to manage the interference and ensure that the latter users can maintain reliable communications. This paper presents a game theoretic framework to model the dynamic spectrum sharing in cognitive radio networks. First, a utility function that captures the selfish and cooperative behavior of the lower-priority users to manage the interference by selecting the best channel with minimal intra- and inter-system interference is defined. Next, based on the defined utility function, the proposed framework can be formulated as a potential game; thus, the convergence to a Nash equilibrium point is ensured as long as the best response dynamic is adopted. At the equilibrium point, power allocation algorithm is proposed such that the interference to higher-priority users can be maintained below the maximum allowable level. The simulation results show the convergence of the proposed potential game and the performance improvement of higher-priority users in terms of SINR and outage probability.","PeriodicalId":204082,"journal":{"name":"2013 International Conference on Information Technology and Electrical Engineering (ICITEE)","volume":"101 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2013-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114606675","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 : 2013-10-01DOI: 10.1109/ICITEED.2013.6676250
A. Satriya, E. Setijadi
This research is focused on the effect of various incident angles of the linear polarized electromagnetic exposure from mobile phone to the value of Specific Absorption Rate (SAR) in human head which is a safety standardization for mobile phone user. Method of Moment is chosen to calculate the electric field in the human head because it is the most suitable method. The incident electromagnetic is assumed as a plane wave with a frequency at 900 MHz and power density of antenna for 4.5 W/m2. The integral used for calculation is Tensor Integral Equation (TIE). Human head is modelled as a homogeneous spheroid and is divided into cubical cells. The incident angles which are examined are 0°(horizontal polarization), 15°, 30°, 45°, 60°, 75°and 90°(vertical polarization). The results show that the incident angle does not affect the average SAR in the human head, but it affects the local and maximum SAR of the cells in human head. The difference of seven angles maximum SAR does not vary in the form of linear but in the form of damped sinusoidal. The angle which produces the least maximum SAR is 0°namely 0.1521 W/kg whereas the angle which produces the highest maximum SAR is produced by angle 15°namely 0.1748 W/kg. The highest SAR is obtained around the side of the head near the electromagnetic exposure source. None of the SAR produced by the variation of incident angle is above the limit of safety standard.
{"title":"An analysis method of effect of linear polarized electromagnetic exposure from mobile phone to human head with various incident angles","authors":"A. Satriya, E. Setijadi","doi":"10.1109/ICITEED.2013.6676250","DOIUrl":"https://doi.org/10.1109/ICITEED.2013.6676250","url":null,"abstract":"This research is focused on the effect of various incident angles of the linear polarized electromagnetic exposure from mobile phone to the value of Specific Absorption Rate (SAR) in human head which is a safety standardization for mobile phone user. Method of Moment is chosen to calculate the electric field in the human head because it is the most suitable method. The incident electromagnetic is assumed as a plane wave with a frequency at 900 MHz and power density of antenna for 4.5 W/m2. The integral used for calculation is Tensor Integral Equation (TIE). Human head is modelled as a homogeneous spheroid and is divided into cubical cells. The incident angles which are examined are 0°(horizontal polarization), 15°, 30°, 45°, 60°, 75°and 90°(vertical polarization). The results show that the incident angle does not affect the average SAR in the human head, but it affects the local and maximum SAR of the cells in human head. The difference of seven angles maximum SAR does not vary in the form of linear but in the form of damped sinusoidal. The angle which produces the least maximum SAR is 0°namely 0.1521 W/kg whereas the angle which produces the highest maximum SAR is produced by angle 15°namely 0.1748 W/kg. The highest SAR is obtained around the side of the head near the electromagnetic exposure source. None of the SAR produced by the variation of incident angle is above the limit of safety standard.","PeriodicalId":204082,"journal":{"name":"2013 International Conference on Information Technology and Electrical Engineering (ICITEE)","volume":"27 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2013-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128483030","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 : 2013-10-01DOI: 10.1109/ICITEED.2013.6676281
A. A. Mannan, H. Tamura, K. Tanno
In this paper, a continuous-time asynchronous delta-sigma (ΔΣ) modulator (ADSM) is proposed. The proposed circuit is multiple-valued output. The circuit is consists of hysteresis comparator, operational transconductance amplifier, and digital-to-analog circuits. Next, an example circuit of 5-level ADSM is discussed and simulated. An analog-to-digital converter consisted of the 5-level ADMS and multiple-valued logic decoder and digital counter is presented and simulated. All of the proposed circuits are simulated in transistors level through HSPICE with set of 2.0μm CMOS process parameters. Detailed simulation results are shown in this paper.
{"title":"Asynchronous delta-sigma modulator with multiple-valued output","authors":"A. A. Mannan, H. Tamura, K. Tanno","doi":"10.1109/ICITEED.2013.6676281","DOIUrl":"https://doi.org/10.1109/ICITEED.2013.6676281","url":null,"abstract":"In this paper, a continuous-time asynchronous delta-sigma (ΔΣ) modulator (ADSM) is proposed. The proposed circuit is multiple-valued output. The circuit is consists of hysteresis comparator, operational transconductance amplifier, and digital-to-analog circuits. Next, an example circuit of 5-level ADSM is discussed and simulated. An analog-to-digital converter consisted of the 5-level ADMS and multiple-valued logic decoder and digital counter is presented and simulated. All of the proposed circuits are simulated in transistors level through HSPICE with set of 2.0μm CMOS process parameters. Detailed simulation results are shown in this paper.","PeriodicalId":204082,"journal":{"name":"2013 International Conference on Information Technology and Electrical Engineering (ICITEE)","volume":"82 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2013-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121903227","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 : 2013-10-01DOI: 10.1109/ICITEED.2013.6676231
P. Chainapaporn, P. Netisopakul
This paper proposes two processes for merging Thai Herb information obtained from heterogeneous data sources. The objective is to combine different formats of Thai herb information into one consistent representation. The processes are implemented in a Sourcing and Merging Agent (SMA) of a Multi-Agent Thai Herb Recommendation system (MA_THR). The first process aims to find and merge the same Thai herb with different names. The second process aims to find synonyms of symptoms. Experiments give 93% accuracy of merging Thai herb information using names and 97% accuracy of finding the similarity between symptoms.
{"title":"Word similarity algorithm for merging Thai Herb information from heterogeneous data sources","authors":"P. Chainapaporn, P. Netisopakul","doi":"10.1109/ICITEED.2013.6676231","DOIUrl":"https://doi.org/10.1109/ICITEED.2013.6676231","url":null,"abstract":"This paper proposes two processes for merging Thai Herb information obtained from heterogeneous data sources. The objective is to combine different formats of Thai herb information into one consistent representation. The processes are implemented in a Sourcing and Merging Agent (SMA) of a Multi-Agent Thai Herb Recommendation system (MA_THR). The first process aims to find and merge the same Thai herb with different names. The second process aims to find synonyms of symptoms. Experiments give 93% accuracy of merging Thai herb information using names and 97% accuracy of finding the similarity between symptoms.","PeriodicalId":204082,"journal":{"name":"2013 International Conference on Information Technology and Electrical Engineering (ICITEE)","volume":"46 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2013-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133706080","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 : 2013-10-01DOI: 10.1109/ICITEED.2013.6676222
Abu Wahid Md Masud Parvez
In software outsourcing industry, to win a contract, outsourcing companies need to consider the price that they will introduce to customers. Therefore, estimation has played an important role in any type of software project and as well as for test projects. Particularly, the estimation of testing has been more critical and magnitude as companies need to present or bid their prices on the project to win the outsourcing contract. Wrong estimation can negatively affect the company sales in both ways. On the one side, the profit margin could be reduced or hurt when the bidding is less than that real effort. On the other side, the company could lose the project when the bidding is higher than that of competitors. Therefore, it is extremely necessary to apply economic and systematic estimation model or process to enhance the accuracy in estimation. The integration of highly skilled workforce and accurate test effort estimation software will provide significant benefits to companies. Up to now, there are various existing models of test effort estimation, yet use case point estimation is one of the most popular models in the agile software development industry. The present paper aims to investigate the use case point estimation model. Following the analysis, we have developed two important elements namely, efficiency and risk factor based on a new layer in the model developed by us. The benefit of the new model is to increase the performance and effectiveness of the use case point estimation model.
{"title":"Efficiency factor and risk factor based user case point test effort estimation model compatible with agile software development","authors":"Abu Wahid Md Masud Parvez","doi":"10.1109/ICITEED.2013.6676222","DOIUrl":"https://doi.org/10.1109/ICITEED.2013.6676222","url":null,"abstract":"In software outsourcing industry, to win a contract, outsourcing companies need to consider the price that they will introduce to customers. Therefore, estimation has played an important role in any type of software project and as well as for test projects. Particularly, the estimation of testing has been more critical and magnitude as companies need to present or bid their prices on the project to win the outsourcing contract. Wrong estimation can negatively affect the company sales in both ways. On the one side, the profit margin could be reduced or hurt when the bidding is less than that real effort. On the other side, the company could lose the project when the bidding is higher than that of competitors. Therefore, it is extremely necessary to apply economic and systematic estimation model or process to enhance the accuracy in estimation. The integration of highly skilled workforce and accurate test effort estimation software will provide significant benefits to companies. Up to now, there are various existing models of test effort estimation, yet use case point estimation is one of the most popular models in the agile software development industry. The present paper aims to investigate the use case point estimation model. Following the analysis, we have developed two important elements namely, efficiency and risk factor based on a new layer in the model developed by us. The benefit of the new model is to increase the performance and effectiveness of the use case point estimation model.","PeriodicalId":204082,"journal":{"name":"2013 International Conference on Information Technology and Electrical Engineering (ICITEE)","volume":"76 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2013-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114032480","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 : 2013-10-01DOI: 10.1109/ICITEED.2013.6676238
Arwin Halim, P. Mursanto
Various refactoring rules and their impact on class cohesion at high-level designs have been investigated. Early measurement and improvement of internal quality attributes such as cohesion, allows developers to avoid extensive review, frequent modification and rewriting of specifications, designs, and source codes. The impact of refactoring is obtained by comparing class cohesion of a design before and after refactoring applied. A set of class cohesion metrics that suits four properties of a good class cohesion metric was chosen based on theoretical analysis and supported by empirical evidence. We found that refactoring rules does not always improve class cohesion values.
{"title":"Refactoring rules effect of class cohesion on high-level design","authors":"Arwin Halim, P. Mursanto","doi":"10.1109/ICITEED.2013.6676238","DOIUrl":"https://doi.org/10.1109/ICITEED.2013.6676238","url":null,"abstract":"Various refactoring rules and their impact on class cohesion at high-level designs have been investigated. Early measurement and improvement of internal quality attributes such as cohesion, allows developers to avoid extensive review, frequent modification and rewriting of specifications, designs, and source codes. The impact of refactoring is obtained by comparing class cohesion of a design before and after refactoring applied. A set of class cohesion metrics that suits four properties of a good class cohesion metric was chosen based on theoretical analysis and supported by empirical evidence. We found that refactoring rules does not always improve class cohesion values.","PeriodicalId":204082,"journal":{"name":"2013 International Conference on Information Technology and Electrical Engineering (ICITEE)","volume":"30 3","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2013-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114006832","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 : 2013-10-01DOI: 10.1109/ICITEED.2013.6676253
S. Prabhavat, R. Varakulsiripunth, S. Utsumi, Yasushi Kato
Demand for large bandwidth network connections is growing continuously while network connections via multiple paths can exist because of high degree of connectivity. Utilization of the multiple paths is an economical solution for provisioning large network capacity to meet the users' requirements but it brings about key issues such as load imbalance (causing a large queue and buffer overflow at a gateway) and packet reordering problems that have significant impacts on TCP connections. In this paper, we propose a load distribution model for TCP transmission, called Load Distribution over Multipath with Extended Drop Slope Random Early Detection (LDM/ExRED). LDM/ExRED takes advantages of RED mechanism to maintain a small queue, avoid buffer overflow at a gateway, and mitigate packet reordering problem. In addition, it reduces peak buffer occupancy by using our modified RED (i.e., ExRED). Our work will be evaluated and compared to the other existing models by simulations under realistic traffic conditions.
{"title":"Load distribution using modified RED for multipath TCP communication","authors":"S. Prabhavat, R. Varakulsiripunth, S. Utsumi, Yasushi Kato","doi":"10.1109/ICITEED.2013.6676253","DOIUrl":"https://doi.org/10.1109/ICITEED.2013.6676253","url":null,"abstract":"Demand for large bandwidth network connections is growing continuously while network connections via multiple paths can exist because of high degree of connectivity. Utilization of the multiple paths is an economical solution for provisioning large network capacity to meet the users' requirements but it brings about key issues such as load imbalance (causing a large queue and buffer overflow at a gateway) and packet reordering problems that have significant impacts on TCP connections. In this paper, we propose a load distribution model for TCP transmission, called Load Distribution over Multipath with Extended Drop Slope Random Early Detection (LDM/ExRED). LDM/ExRED takes advantages of RED mechanism to maintain a small queue, avoid buffer overflow at a gateway, and mitigate packet reordering problem. In addition, it reduces peak buffer occupancy by using our modified RED (i.e., ExRED). Our work will be evaluated and compared to the other existing models by simulations under realistic traffic conditions.","PeriodicalId":204082,"journal":{"name":"2013 International Conference on Information Technology and Electrical Engineering (ICITEE)","volume":"44 2 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2013-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129193751","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 : 2013-10-01DOI: 10.1109/ICITEED.2013.6676234
Elisafina Siswanto, M. L. Khodra
The rapid growth of social media, especially Twitter in Indonesia, has produced a large amount of user generated texts in the form of tweets. Since Twitter only provides the name and location of its users, we develop a classification system that predicts latent attributes of Twitter user based on his tweets. Latent attribute is an attribute that is not stated directly. Our system predicts age and job attributes of Twitter users that use Indonesian language. Classification model is developed by employing lexical features and three learning algorithms (Naïve Bayes, SVM, and Random Forest). Based on the experimental results, it can be concluded that the SVM method produces the best accuracy for balanced data.
社交媒体的快速发展，尤其是印度尼西亚的Twitter，产生了大量以tweet形式的用户生成文本。由于Twitter只提供其用户的姓名和位置，因此我们开发了一个分类系统，该系统可以根据Twitter用户的tweet预测其潜在属性。潜在属性是没有直接声明的属性。我们的系统预测使用印尼语的Twitter用户的年龄和工作属性。利用词法特征和三种学习算法(Naïve Bayes, SVM, Random Forest)建立分类模型。实验结果表明，支持向量机方法对平衡数据的提取精度最高。
{"title":"Predicting latent attributes of Twitter user by employing lexical features","authors":"Elisafina Siswanto, M. L. Khodra","doi":"10.1109/ICITEED.2013.6676234","DOIUrl":"https://doi.org/10.1109/ICITEED.2013.6676234","url":null,"abstract":"The rapid growth of social media, especially Twitter in Indonesia, has produced a large amount of user generated texts in the form of tweets. Since Twitter only provides the name and location of its users, we develop a classification system that predicts latent attributes of Twitter user based on his tweets. Latent attribute is an attribute that is not stated directly. Our system predicts age and job attributes of Twitter users that use Indonesian language. Classification model is developed by employing lexical features and three learning algorithms (Naïve Bayes, SVM, and Random Forest). Based on the experimental results, it can be concluded that the SVM method produces the best accuracy for balanced data.","PeriodicalId":204082,"journal":{"name":"2013 International Conference on Information Technology and Electrical Engineering (ICITEE)","volume":"29 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2013-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131517693","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：