Pub Date : 2016-10-01DOI: 10.1109/ICSITECH.2016.7852645
Haviluddin, N. Dengen
The investigation and forecasting network traffic usage is an essential concern in the academic activities of university. This paper reports how to apply and compare SARIMA, NARX, and BPNN by using short-term time series datasets. The network traffic datasets are obtained from the ICT Universitas Mulawarman. As a result, the determination of several prediction models will continue to be an alternative for researchers to obtain more accurate prediction results. The first analysis used the SARIMA ((2,1,1)(2,1,2)12) with MSE of 0.064 indicated that it was a good model. The second analysis used the NARX models by using architecture 189∶31∶94 with performance value of MSE was 0.006717 respectively. The third one used the BPNN with two-hidden-layers (5-10-10-1) architecture with MSE value of 0.00942479. Finally, we compared the performance of methods using MSE. Based on the experiment, the artificial neural networks (ANN) i.e., NARX and BPNN models have been successfully to support the time series datasets in order to predict the future.
网络流量使用情况的调查与预测是高校学术活动的重要内容。本文报告了如何使用短期时间序列数据集应用和比较SARIMA、NARX和BPNN。网络流量数据集来自ICT Universitas Mulawarman。因此，确定几种预测模型将继续成为研究人员获得更准确预测结果的另一种选择。第一次分析使用SARIMA ((2,1,1)(2,1,2)12)， MSE为0.064，表明它是一个很好的模型。第二次分析采用结构为189∶31∶94的NARX模型，MSE的性能值分别为0.006717。第三种采用两隐层(5-10-10-1)结构的BPNN, MSE值为0.00942479。最后，我们比较了使用MSE的方法的性能。在实验的基础上，人工神经网络(ANN)即NARX和BPNN模型已成功地支持时间序列数据集，以预测未来。
{"title":"Comparison of SARIMA, NARX and BPNN models in forecasting time series data of network traffic","authors":"Haviluddin, N. Dengen","doi":"10.1109/ICSITECH.2016.7852645","DOIUrl":"https://doi.org/10.1109/ICSITECH.2016.7852645","url":null,"abstract":"The investigation and forecasting network traffic usage is an essential concern in the academic activities of university. This paper reports how to apply and compare SARIMA, NARX, and BPNN by using short-term time series datasets. The network traffic datasets are obtained from the ICT Universitas Mulawarman. As a result, the determination of several prediction models will continue to be an alternative for researchers to obtain more accurate prediction results. The first analysis used the SARIMA ((2,1,1)(2,1,2)12) with MSE of 0.064 indicated that it was a good model. The second analysis used the NARX models by using architecture 189∶31∶94 with performance value of MSE was 0.006717 respectively. The third one used the BPNN with two-hidden-layers (5-10-10-1) architecture with MSE value of 0.00942479. Finally, we compared the performance of methods using MSE. Based on the experiment, the artificial neural networks (ANN) i.e., NARX and BPNN models have been successfully to support the time series datasets in order to predict the future.","PeriodicalId":447090,"journal":{"name":"2016 2nd International Conference on Science in Information Technology (ICSITech)","volume":"25 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2016-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126343478","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 : 2016-10-01DOI: 10.1109/ICSITECH.2016.7852612
Bernardinus Harnadi
This study has a purpose to investigate the adoption of online games technologies among adolescents and their behavior in playing online games. The findings showed that half of them had experience ten months or less in playing online games with ten hours or less for each time playing per week. Nearly fifty-four percent played up to five times each week where sixty-six percent played two hours or less. Behavioral Intention has significant correlation to model variables naming Perceived Enjoyment, Flow Experience, Performance Expectancy, Effort Expectancy, Social Influence, and Facilitating Conditions; Experience; and the number and duration of game sessions. The last, Performance Expectancy and Facilitating Condition had a positive, medium, and statistically direct effect on Behavioral Intention. Four other variables Perceived Enjoyment, Flow Experience, Effort Expectancy, and Social Influence had positive or negative, medium or small, and not statistically direct effect on Behavioral Intention. Additionally, Flow Experience and Social Influence have no significant different between the mean value for male and female. Other variables have significant different regard to gender, where mean value of male was significantly greater than female except for Age. Practical implications of this study are relevant to groups who have interest to enhance or to decrease the adoption of online games technologies. Those to enhance the adoption of online games technologies must: preserve Performance Expectancy and Facilitating Conditions; enhance Flow Experience, Perceived Enjoyment, Effort Expectancy, and Social Influence; and engage the adolescent's online games behavior, specifically supporting them in longer playing games and in enhancing their experience. The opposite actions to these proposed can be considered to decrease the adoption.
{"title":"Antecedents of the adoption of online games technologies: The study of adolescent behavior in playing online games","authors":"Bernardinus Harnadi","doi":"10.1109/ICSITECH.2016.7852612","DOIUrl":"https://doi.org/10.1109/ICSITECH.2016.7852612","url":null,"abstract":"This study has a purpose to investigate the adoption of online games technologies among adolescents and their behavior in playing online games. The findings showed that half of them had experience ten months or less in playing online games with ten hours or less for each time playing per week. Nearly fifty-four percent played up to five times each week where sixty-six percent played two hours or less. Behavioral Intention has significant correlation to model variables naming Perceived Enjoyment, Flow Experience, Performance Expectancy, Effort Expectancy, Social Influence, and Facilitating Conditions; Experience; and the number and duration of game sessions. The last, Performance Expectancy and Facilitating Condition had a positive, medium, and statistically direct effect on Behavioral Intention. Four other variables Perceived Enjoyment, Flow Experience, Effort Expectancy, and Social Influence had positive or negative, medium or small, and not statistically direct effect on Behavioral Intention. Additionally, Flow Experience and Social Influence have no significant different between the mean value for male and female. Other variables have significant different regard to gender, where mean value of male was significantly greater than female except for Age. Practical implications of this study are relevant to groups who have interest to enhance or to decrease the adoption of online games technologies. Those to enhance the adoption of online games technologies must: preserve Performance Expectancy and Facilitating Conditions; enhance Flow Experience, Perceived Enjoyment, Effort Expectancy, and Social Influence; and engage the adolescent's online games behavior, specifically supporting them in longer playing games and in enhancing their experience. The opposite actions to these proposed can be considered to decrease the adoption.","PeriodicalId":447090,"journal":{"name":"2016 2nd International Conference on Science in Information Technology (ICSITech)","volume":"28 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2016-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133207130","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 : 2016-10-01DOI: 10.1109/ICSITECH.2016.7852649
Murinto, A. Harjoko
Data dimensionality reduction is an important step in the preliminary image classification. Information quantity and resolution of hyperspectral images provide a chance to solve the problem better than multispectral images. In hyperspectral image classification, higher dimensionality of data could improve the capability of class detection as well as distinguish different classes with better accuracy. The method calculation of ICA is a transforming a random vector into another space which consists of independent components. Because marginal distribution is usually unknown, the possible solution is to reduce data dimension into an optimized contrast function to measure component independency. In this research, PSO algorithm is used to solve the optimization problem. PSO is used to distinguish the signal selected by two different contrast functions. The problem existed in gradient method is solved using PSO, that is getting trapped in local optimum. The result of feature reduction done by using ICA-PSO technique is then compared with the result of feature reduction done by using ICA algorithm and PCA. Furthermore, the result gained by using ICA-PSO is used to classify hyperspectral images. In this work, Support Vector Machine is used as classifier. Classification result obtained by using ICA-PSO dimensionality reduction on AVIRIS, the value of average accuracy (AA) is 0.8535, overall accuracy (OA) is 0.8310, and K is 0.785. Whereas on HYDICE, classification result obtained by using ICA-PSO dimensionality reduction is at 0.8783 for AA, 0.8625 for OA, K is 0.850.
{"title":"Dataset feature reduction using independent component analysis with contrast function of particle swarm optimization on hyperspectral image classification","authors":"Murinto, A. Harjoko","doi":"10.1109/ICSITECH.2016.7852649","DOIUrl":"https://doi.org/10.1109/ICSITECH.2016.7852649","url":null,"abstract":"Data dimensionality reduction is an important step in the preliminary image classification. Information quantity and resolution of hyperspectral images provide a chance to solve the problem better than multispectral images. In hyperspectral image classification, higher dimensionality of data could improve the capability of class detection as well as distinguish different classes with better accuracy. The method calculation of ICA is a transforming a random vector into another space which consists of independent components. Because marginal distribution is usually unknown, the possible solution is to reduce data dimension into an optimized contrast function to measure component independency. In this research, PSO algorithm is used to solve the optimization problem. PSO is used to distinguish the signal selected by two different contrast functions. The problem existed in gradient method is solved using PSO, that is getting trapped in local optimum. The result of feature reduction done by using ICA-PSO technique is then compared with the result of feature reduction done by using ICA algorithm and PCA. Furthermore, the result gained by using ICA-PSO is used to classify hyperspectral images. In this work, Support Vector Machine is used as classifier. Classification result obtained by using ICA-PSO dimensionality reduction on AVIRIS, the value of average accuracy (AA) is 0.8535, overall accuracy (OA) is 0.8310, and K is 0.785. Whereas on HYDICE, classification result obtained by using ICA-PSO dimensionality reduction is at 0.8783 for AA, 0.8625 for OA, K is 0.850.","PeriodicalId":447090,"journal":{"name":"2016 2nd International Conference on Science in Information Technology (ICSITech)","volume":"446 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2016-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115858148","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 : 2016-10-01DOI: 10.1109/ICSITECH.2016.7852654
Arfive Gandhi, Y. G. Sucahyo, T. Sirait
Certificate Policy (CP) and Certification Practice Statement (CPS) are required documents for Certification Authority (CA) to describe its information security mechanism, business processes and regulation compliance. Ministry of Communication and Information Technology (MCIT) Indonesia need to compose CP and CPS because of its role as Root CA in Indonesia National Public Key Infrastructure (INPKI). This research proposes CP and CPS for Root CA Indonesia following the content structure in Request for Comment (RFC) 3647. The proposed CP and CPS involve elaboration among applied technology, procedures of information security, and legal aspect of information security in Indonesia. Significant contribution of this research is the development of CP and CPS as fundamental standards in establishing Indonesia National Public Key Infrastructure (INPKI) as part of national information security system. Moreover, Webtrust Perspective Criteria is used to appraise the comprehensiveness of CP and CPS. As a result, the constructed CP and CPS have 96 percent suitability (43 criteria out of 45). This performance indicates that CP and CPS are applicable and ready to be adopted by Root CA Indonesia.
{"title":"Certificate policy and Certification Practice Statement for root CA Indonesia","authors":"Arfive Gandhi, Y. G. Sucahyo, T. Sirait","doi":"10.1109/ICSITECH.2016.7852654","DOIUrl":"https://doi.org/10.1109/ICSITECH.2016.7852654","url":null,"abstract":"Certificate Policy (CP) and Certification Practice Statement (CPS) are required documents for Certification Authority (CA) to describe its information security mechanism, business processes and regulation compliance. Ministry of Communication and Information Technology (MCIT) Indonesia need to compose CP and CPS because of its role as Root CA in Indonesia National Public Key Infrastructure (INPKI). This research proposes CP and CPS for Root CA Indonesia following the content structure in Request for Comment (RFC) 3647. The proposed CP and CPS involve elaboration among applied technology, procedures of information security, and legal aspect of information security in Indonesia. Significant contribution of this research is the development of CP and CPS as fundamental standards in establishing Indonesia National Public Key Infrastructure (INPKI) as part of national information security system. Moreover, Webtrust Perspective Criteria is used to appraise the comprehensiveness of CP and CPS. As a result, the constructed CP and CPS have 96 percent suitability (43 criteria out of 45). This performance indicates that CP and CPS are applicable and ready to be adopted by Root CA Indonesia.","PeriodicalId":447090,"journal":{"name":"2016 2nd International Conference on Science in Information Technology (ICSITech)","volume":"53 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2016-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114666448","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 : 2016-10-01DOI: 10.1109/ICSITECH.2016.7852640
Reni Soelistijorini, Mike Yuliana, I. Prasetyaningrum, Lina Pratiwi
Medication error in the treatment process can be dangerous for patients that can cause adverse medicine reactions. This can occur because of allergies, medicine-medicine interactions, medicine interactions with diseases and medicine incompatibility which include duration of therapy, dose, route of administration, and amount of medicine. That is way it takes knowledge and thoroughness doctors in selecting medicines for patients. In this research, medication error prevention system in hypertension disease is made to provide recommendations to the doctor's medication. The system is integrated with Hospital Information System (HIS) which is an e-prescribing application using Fuzzy Query. The criteria used are dosage levels of medicine (low, medium, high), medicine prices (cheap, normal, expensive), availability of medicines in pharmacies (little, medium, lots) and medicines favorite (not favorite, favorite, very favorite). The test results of e-prescribing system that consist of 100 medicines for patients with stage 1 and age more than 60 show that the system has been created able to provide medicine recommendations by considering disease, patient's medical history and allergies. Form of query with some variations of criteria show that average of medicine recommendation by using AND operator is less than OR operator.
{"title":"Implementation of medical error prevention system for hypertension disease based on fuzzy","authors":"Reni Soelistijorini, Mike Yuliana, I. Prasetyaningrum, Lina Pratiwi","doi":"10.1109/ICSITECH.2016.7852640","DOIUrl":"https://doi.org/10.1109/ICSITECH.2016.7852640","url":null,"abstract":"Medication error in the treatment process can be dangerous for patients that can cause adverse medicine reactions. This can occur because of allergies, medicine-medicine interactions, medicine interactions with diseases and medicine incompatibility which include duration of therapy, dose, route of administration, and amount of medicine. That is way it takes knowledge and thoroughness doctors in selecting medicines for patients. In this research, medication error prevention system in hypertension disease is made to provide recommendations to the doctor's medication. The system is integrated with Hospital Information System (HIS) which is an e-prescribing application using Fuzzy Query. The criteria used are dosage levels of medicine (low, medium, high), medicine prices (cheap, normal, expensive), availability of medicines in pharmacies (little, medium, lots) and medicines favorite (not favorite, favorite, very favorite). The test results of e-prescribing system that consist of 100 medicines for patients with stage 1 and age more than 60 show that the system has been created able to provide medicine recommendations by considering disease, patient's medical history and allergies. Form of query with some variations of criteria show that average of medicine recommendation by using AND operator is less than OR operator.","PeriodicalId":447090,"journal":{"name":"2016 2nd International Conference on Science in Information Technology (ICSITech)","volume":"115 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2016-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123943213","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 : 2016-10-01DOI: 10.1109/ICSITECH.2016.7852662
M. Hijazi, Lyndia Libin, R. Alfred, Frans Coenen
Sentiment Analysis (SA) has gained its popularity over the years for the benefit it brings to the development of economy, sociology and politic. SA enables observation, experiment, and quantification of emotions of the public toward a particular issue. However, there is not much SA done with respect to the Malay Language, especially in the context of the Malay dialects used in social media. The research presented in this paper aims to perform SA on one of the derivatives of the Malay language, namely Sabah Language. The Sabah Language, unlike many other languages, does not have a fixed spelling and, when used in an unstructured form as in the case of social media, poses particular difficulties for SA. This paper takes a lexicon-based approach to SA of the Sabah Language as used on social media. For the investigation, the corpuses selected were Facebook posts and tweets written in the Sabah language, 443 posts and tweets in total. Each was manually annotated as positive, negative or neutral by three annotators. As Sabah Language is a derivative of Malay language, the words used in Sabah Language contains most of Malay words. That is why, in Sentiment-Lexicon (SL) construction process, opinion-bearing Malay SL is retrieved, modified and expanded to build Sabah SL. Three different methods of assigning scores to the words in SL (opinion-bearing words) were employed during SL construction: (i) Simple PSA, (ii) Simple PSA with Switch Negation (PSA-SN) and (iii) Strength-based PSA. In this paper, pre-processing phase that includes spellchecker and shortform corrector is also implemented to reduce distinct word to be analyzed for SA. In classification phase, two classification methods, simple and bias aware classifications, were used to classify the posts. Experiments are conducted to show the effect of SL modification and expansion, the effect of pre-processing as well as the effect of bias-aware classification to the SA performed. Results show the highest accuracy of 85.10% was achieved using bias-aware classification with the modified and expanded SL, scores are assigned using Simple PSA and the pre-processed text.
{"title":"Bias aware lexicon-based Sentiment Analysis of Malay dialect on social media data: A study on the Sabah Language","authors":"M. Hijazi, Lyndia Libin, R. Alfred, Frans Coenen","doi":"10.1109/ICSITECH.2016.7852662","DOIUrl":"https://doi.org/10.1109/ICSITECH.2016.7852662","url":null,"abstract":"Sentiment Analysis (SA) has gained its popularity over the years for the benefit it brings to the development of economy, sociology and politic. SA enables observation, experiment, and quantification of emotions of the public toward a particular issue. However, there is not much SA done with respect to the Malay Language, especially in the context of the Malay dialects used in social media. The research presented in this paper aims to perform SA on one of the derivatives of the Malay language, namely Sabah Language. The Sabah Language, unlike many other languages, does not have a fixed spelling and, when used in an unstructured form as in the case of social media, poses particular difficulties for SA. This paper takes a lexicon-based approach to SA of the Sabah Language as used on social media. For the investigation, the corpuses selected were Facebook posts and tweets written in the Sabah language, 443 posts and tweets in total. Each was manually annotated as positive, negative or neutral by three annotators. As Sabah Language is a derivative of Malay language, the words used in Sabah Language contains most of Malay words. That is why, in Sentiment-Lexicon (SL) construction process, opinion-bearing Malay SL is retrieved, modified and expanded to build Sabah SL. Three different methods of assigning scores to the words in SL (opinion-bearing words) were employed during SL construction: (i) Simple PSA, (ii) Simple PSA with Switch Negation (PSA-SN) and (iii) Strength-based PSA. In this paper, pre-processing phase that includes spellchecker and shortform corrector is also implemented to reduce distinct word to be analyzed for SA. In classification phase, two classification methods, simple and bias aware classifications, were used to classify the posts. Experiments are conducted to show the effect of SL modification and expansion, the effect of pre-processing as well as the effect of bias-aware classification to the SA performed. Results show the highest accuracy of 85.10% was achieved using bias-aware classification with the modified and expanded SL, scores are assigned using Simple PSA and the pre-processed text.","PeriodicalId":447090,"journal":{"name":"2016 2nd International Conference on Science in Information Technology (ICSITech)","volume":"31 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2016-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122530183","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 : 2016-10-01DOI: 10.1109/ICSITECH.2016.7852653
Noor Aida Husaini, R. Ghazali, I. R. Yanto
In this paper, we scrutinised an improvement of the Modified Cuckoo Search (MCS), called Modified Cuckoo Search-Markov chain Monte Carlo (MCS-MCMC) algorithm, for solving optimisation problems. The performance of MCS are at least on a par with the standard Cuckoo Search (CS) in terms of high rate of convergence when dealing with true global minimum, although at high number of dimensions. In conjunction with the benefits of MCS, we aim to enhance the MCS algorithm by applying Markov chain Monte Carlo (MCMC) random walk. We validated the proposed algorithm alongside several test functions and later on, we compare its performance with those of MCS-Lévy algorithm. The capability of the MCS-MCMC algorithm in yielding good results is considered as a solution to deal with the downside of those existing algorithm.
{"title":"Enhancing modified cuckoo search algorithm by using MCMC random walk","authors":"Noor Aida Husaini, R. Ghazali, I. R. Yanto","doi":"10.1109/ICSITECH.2016.7852653","DOIUrl":"https://doi.org/10.1109/ICSITECH.2016.7852653","url":null,"abstract":"In this paper, we scrutinised an improvement of the Modified Cuckoo Search (MCS), called Modified Cuckoo Search-Markov chain Monte Carlo (MCS-MCMC) algorithm, for solving optimisation problems. The performance of MCS are at least on a par with the standard Cuckoo Search (CS) in terms of high rate of convergence when dealing with true global minimum, although at high number of dimensions. In conjunction with the benefits of MCS, we aim to enhance the MCS algorithm by applying Markov chain Monte Carlo (MCMC) random walk. We validated the proposed algorithm alongside several test functions and later on, we compare its performance with those of MCS-Lévy algorithm. The capability of the MCS-MCMC algorithm in yielding good results is considered as a solution to deal with the downside of those existing algorithm.","PeriodicalId":447090,"journal":{"name":"2016 2nd International Conference on Science in Information Technology (ICSITech)","volume":"5 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2016-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115568047","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 : 2016-10-01DOI: 10.1109/ICSITECH.2016.7852637
S. Ardiansyah, M. Majid, J. Zain
Inside the sets of data, hidden knowledge can be acquired by using neural network. These knowledge are described within topology, using activation function and connection weight at hidden neurons and output neurons. Is hardly to be understanding since neural networks act as a black box. The black box problem can be solved by extracting knowledge (rule) from trained neural network. Thus, the aim of this paper is to extract valuable information from trained neural networks using decision. Further, the Levenberg Marquardt algorithm was applied to training 30 networks for each datasets, using learning parameters and basis weights differences. As the number of hidden neurons increase, mean squared error and mean absolute percentage error decrease, and more time they need to deal with the dataset, that is result of investigation from neural network architectures. Decision tree induction generally performs better in knowledge extraction result with accuracy and precision level from 84.07 to 93.17 percent. The extracted rule can be used to explaining the process of the neural network systems and also can be applied in other systems like expert systems.
{"title":"Knowledge of extraction from trained neural network by using decision tree","authors":"S. Ardiansyah, M. Majid, J. Zain","doi":"10.1109/ICSITECH.2016.7852637","DOIUrl":"https://doi.org/10.1109/ICSITECH.2016.7852637","url":null,"abstract":"Inside the sets of data, hidden knowledge can be acquired by using neural network. These knowledge are described within topology, using activation function and connection weight at hidden neurons and output neurons. Is hardly to be understanding since neural networks act as a black box. The black box problem can be solved by extracting knowledge (rule) from trained neural network. Thus, the aim of this paper is to extract valuable information from trained neural networks using decision. Further, the Levenberg Marquardt algorithm was applied to training 30 networks for each datasets, using learning parameters and basis weights differences. As the number of hidden neurons increase, mean squared error and mean absolute percentage error decrease, and more time they need to deal with the dataset, that is result of investigation from neural network architectures. Decision tree induction generally performs better in knowledge extraction result with accuracy and precision level from 84.07 to 93.17 percent. The extracted rule can be used to explaining the process of the neural network systems and also can be applied in other systems like expert systems.","PeriodicalId":447090,"journal":{"name":"2016 2nd International Conference on Science in Information Technology (ICSITech)","volume":"62 4","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2016-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"120838914","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 : 2016-10-01DOI: 10.1109/ICSITECH.2016.7852617
Hamdani, Anindita Septiarini, D. M. Khairina
Model assessment of Land suitability (MAOLS) is a valuable tool for palm land, and it is used to manage the natural resource in the land clearing of oil palm plantations. This model is applied to a decision support system (DSS) for oil palm plantation land clearing problem. This issue is intended to avoid excessive land clearing, therefore the efficient analysis in decision making is necessary. DSS model was used with Multi-Criteria Decision Making (MCDM) using Technique for Order Preference by Similarity to Ideal Solution (TOPSIS) method for 14 parameters on land's class criteria and has four alternatives of oil palm plantations was applied. The first phase of testing uses direct weighting on TOPSIS, and it obtained the fourth land as the potential for oil palm plantations clearing with the scoring values are 0,578. The second stage of the Analytical Hierarchy Process (AHP) method is used to determine the effectiveness of the proposed model. This result showed the effectiveness of the similarity ranking on alternative output in recommending an alternative to the manager to give consent to the land clearing of oil palm plantations in East Kutai, Indonesia.
{"title":"Model assessment of land suitability decision making for oil palm plantation","authors":"Hamdani, Anindita Septiarini, D. M. Khairina","doi":"10.1109/ICSITECH.2016.7852617","DOIUrl":"https://doi.org/10.1109/ICSITECH.2016.7852617","url":null,"abstract":"Model assessment of Land suitability (MAOLS) is a valuable tool for palm land, and it is used to manage the natural resource in the land clearing of oil palm plantations. This model is applied to a decision support system (DSS) for oil palm plantation land clearing problem. This issue is intended to avoid excessive land clearing, therefore the efficient analysis in decision making is necessary. DSS model was used with Multi-Criteria Decision Making (MCDM) using Technique for Order Preference by Similarity to Ideal Solution (TOPSIS) method for 14 parameters on land's class criteria and has four alternatives of oil palm plantations was applied. The first phase of testing uses direct weighting on TOPSIS, and it obtained the fourth land as the potential for oil palm plantations clearing with the scoring values are 0,578. The second stage of the Analytical Hierarchy Process (AHP) method is used to determine the effectiveness of the proposed model. This result showed the effectiveness of the similarity ranking on alternative output in recommending an alternative to the manager to give consent to the land clearing of oil palm plantations in East Kutai, Indonesia.","PeriodicalId":447090,"journal":{"name":"2016 2nd International Conference on Science in Information Technology (ICSITech)","volume":"5 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2016-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115738192","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 : 2016-10-01DOI: 10.1109/ICSITECH.2016.7852615
D. Nugraheni, Denise de Vries
Employing existing technology for a new purpose has become popular, especially in mobile phone technology. In the context of use for early warning messages, the existing technology that is commonly used is SMS (Short Messaging Services). This study focuses on understanding the profile of a typical mobile SMS user in emergency situations in an urban flood prone area. This profile was assessed based on the mobile devices' preparedness; ease of use (EOU) for using SMS, confidence in SMS skill, satisfaction and frequency of use (FOU). A survey was conducted in Semarang, Central Java, Indonesia for data collection. The respondents for this study were voluntarily respondents. Our study found that the user's level of education and FOU for SMS, influences the usage of SMS in emergency conditions.
{"title":"Profile of a typical mobile SMS user in emergency situations (empirical study in an urban flood prone area)","authors":"D. Nugraheni, Denise de Vries","doi":"10.1109/ICSITECH.2016.7852615","DOIUrl":"https://doi.org/10.1109/ICSITECH.2016.7852615","url":null,"abstract":"Employing existing technology for a new purpose has become popular, especially in mobile phone technology. In the context of use for early warning messages, the existing technology that is commonly used is SMS (Short Messaging Services). This study focuses on understanding the profile of a typical mobile SMS user in emergency situations in an urban flood prone area. This profile was assessed based on the mobile devices' preparedness; ease of use (EOU) for using SMS, confidence in SMS skill, satisfaction and frequency of use (FOU). A survey was conducted in Semarang, Central Java, Indonesia for data collection. The respondents for this study were voluntarily respondents. Our study found that the user's level of education and FOU for SMS, influences the usage of SMS in emergency conditions.","PeriodicalId":447090,"journal":{"name":"2016 2nd International Conference on Science in Information Technology (ICSITech)","volume":"22 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2016-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116035404","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：