Pub Date : 2018-05-01DOI: 10.1109/ICOICT.2018.8528809
Anggie Nastiti, A. Rakhmatsyah, M. A. Nugroho
In Telkom University, the topology used does not have backup link for campus internal network in case of link failure because the topology is still based on interVLAN where each switch only has one path to switch core. Data packets cannot be delivered from source to destination if there is a link failure on the path. Based on the problem, it is proposed a new architecture which is Software Defined Network (SDN) that can overcome the link failure by configuring the controller in order to move to alternative links that have been provided with OpenFlow. This architecture separates the control plane and data plane, so it is centralized and programmable. To look for alternative links when a link failure occurs, the shortest path algorithm is Dijkstra and Bellman-Ford algorithms. The test parameters performed in this research are functionality to determine whether the two algorithms can determine the path or not, and convergence time to find out how long it takes to form the path from source to destination. Scenario of the test is done before and after the link failure occurs by using Ryu as controller and Mininet as emulator. Based on the results of the tests conducted, it was found that Dijkstra and Bellman-Ford algorithm can be applied well on link failure emulation in accordance with the scenario and topology used in the test. In addition to convergence time parameters obtained that Dijkstra algorithm is superior compared to Bellman-Ford algorithm. The difference gained in both scenarios has a value that is not so great the difference.
{"title":"Link Failure Emulation with Dijkstra and Bellman-Ford Algorithm in Software Defined Network Architecture (Case Study: Telkom University Topology)","authors":"Anggie Nastiti, A. Rakhmatsyah, M. A. Nugroho","doi":"10.1109/ICOICT.2018.8528809","DOIUrl":"https://doi.org/10.1109/ICOICT.2018.8528809","url":null,"abstract":"In Telkom University, the topology used does not have backup link for campus internal network in case of link failure because the topology is still based on interVLAN where each switch only has one path to switch core. Data packets cannot be delivered from source to destination if there is a link failure on the path. Based on the problem, it is proposed a new architecture which is Software Defined Network (SDN) that can overcome the link failure by configuring the controller in order to move to alternative links that have been provided with OpenFlow. This architecture separates the control plane and data plane, so it is centralized and programmable. To look for alternative links when a link failure occurs, the shortest path algorithm is Dijkstra and Bellman-Ford algorithms. The test parameters performed in this research are functionality to determine whether the two algorithms can determine the path or not, and convergence time to find out how long it takes to form the path from source to destination. Scenario of the test is done before and after the link failure occurs by using Ryu as controller and Mininet as emulator. Based on the results of the tests conducted, it was found that Dijkstra and Bellman-Ford algorithm can be applied well on link failure emulation in accordance with the scenario and topology used in the test. In addition to convergence time parameters obtained that Dijkstra algorithm is superior compared to Bellman-Ford algorithm. The difference gained in both scenarios has a value that is not so great the difference.","PeriodicalId":266335,"journal":{"name":"2018 6th International Conference on Information and Communication Technology (ICoICT)","volume":"4 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126338165","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2018-05-01DOI: 10.1109/ICOICT.2018.8528721
E. Perdana, H. Sastramihardja, I. Suwardi
Internet of Things (IoT) will change many things, open up opportunities and enabling something that was not possible before. IoT provides sensing capability so that enterprise has better global context awareness. This is the Sensing Enterprise, an enterprise that obtains multidimensional information from physical or virtual objects in a connected environment. This sensing capability is expected to increase the capacity and capability of the enterprise in responding to sustainability challenges. This paper proposes a research framework as an alternative guide for researchers to produce various artifacts or theories to realize The Sensing Enterprise for sustainability achievement. The method used in developing the framework is modification/adaptation of transdisciplinary research model and information system research model. This framework has three main area consist of scientific base, enterprise architecture research process and sustainability achievement.
{"title":"Enterprise Architecture for the Sensing Enterprise a Research Framework","authors":"E. Perdana, H. Sastramihardja, I. Suwardi","doi":"10.1109/ICOICT.2018.8528721","DOIUrl":"https://doi.org/10.1109/ICOICT.2018.8528721","url":null,"abstract":"Internet of Things (IoT) will change many things, open up opportunities and enabling something that was not possible before. IoT provides sensing capability so that enterprise has better global context awareness. This is the Sensing Enterprise, an enterprise that obtains multidimensional information from physical or virtual objects in a connected environment. This sensing capability is expected to increase the capacity and capability of the enterprise in responding to sustainability challenges. This paper proposes a research framework as an alternative guide for researchers to produce various artifacts or theories to realize The Sensing Enterprise for sustainability achievement. The method used in developing the framework is modification/adaptation of transdisciplinary research model and information system research model. This framework has three main area consist of scientific base, enterprise architecture research process and sustainability achievement.","PeriodicalId":266335,"journal":{"name":"2018 6th International Conference on Information and Communication Technology (ICoICT)","volume":"99 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115149712","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2018-05-01DOI: 10.1109/ICOICT.2018.8528779
A. Alamsyah, Made Kevin Bratawisnu, Puput Hari Sanjani
Internet and social media changes the way human act and make social interaction daily. The accumulated of human social interaction form large scale unstructured data that possibly store timely knowledge. Social Network Analysis (SNA) methodology can be used to perform knowledge extraction from those unstructured data. SNA also provide the way to model user interaction pattern in social media. The majority research regarding user interaction pattern is in the form of static model, but in real-world, the interaction dynamically evolves. Hence, we use Dynamic Network Analysis (DNA) to study network dynamic structure during the observation time. In this research, we present analysis of user interactions evolution on social media, specifically in Twitter. As case study, Indonesia e-commerce and the telecommunication businesses are used for the reason of both are having high dynamic interactions market. User interactions is modeled as networks that are annotated with the time markers. Our finding is there are difference network properties during weekday and weekend, thus provide promotion pattern opportunity. The result allows us to understand the network properties phenomenon over the time, that leads to actionable effort such as when the exact time to do product promotion for business organization.
{"title":"Finding Pattern in Dynamic Network Analysis","authors":"A. Alamsyah, Made Kevin Bratawisnu, Puput Hari Sanjani","doi":"10.1109/ICOICT.2018.8528779","DOIUrl":"https://doi.org/10.1109/ICOICT.2018.8528779","url":null,"abstract":"Internet and social media changes the way human act and make social interaction daily. The accumulated of human social interaction form large scale unstructured data that possibly store timely knowledge. Social Network Analysis (SNA) methodology can be used to perform knowledge extraction from those unstructured data. SNA also provide the way to model user interaction pattern in social media. The majority research regarding user interaction pattern is in the form of static model, but in real-world, the interaction dynamically evolves. Hence, we use Dynamic Network Analysis (DNA) to study network dynamic structure during the observation time. In this research, we present analysis of user interactions evolution on social media, specifically in Twitter. As case study, Indonesia e-commerce and the telecommunication businesses are used for the reason of both are having high dynamic interactions market. User interactions is modeled as networks that are annotated with the time markers. Our finding is there are difference network properties during weekday and weekend, thus provide promotion pattern opportunity. The result allows us to understand the network properties phenomenon over the time, that leads to actionable effort such as when the exact time to do product promotion for business organization.","PeriodicalId":266335,"journal":{"name":"2018 6th International Conference on Information and Communication Technology (ICoICT)","volume":"315 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122419371","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2018-05-01DOI: 10.1109/ICOICT.2018.8528763
Sukarno Sono, Nl. Meilani, T. Prihyugiarto, Y. Karyanti
There is a change in the technique or method of collecting and processing data on the Performance Monitoring Accountability (PMA) 2020 Survey by the National Population and Family Planning Indonesia, from a paper-based system to electronic-based which paperless system, one of the tools called Open Data Kit. This study was therefore aimed at identifying the users' perception and attitude towards the application of the new technology in this survey in Indonesia. One of the methods to determine the extent to which the users' acceptance of the application of a new technology is to use the Technology Acceptance Model. Data analysis was performed using the Structural equation Modelling with Analysis of Moment Structure software. The analysis results prove that out of six hypotheses, only one hypothesis is rejected. The results suggest that the application of a new technology system is acceptable and has no resistance from the supervisors and enumerators as the of smartphone-based surveys users. In conclusion, this technology is possible to apply in other surveys in Indonesia.
{"title":"Analysis of the Technology Acceptance Model (TAM) on Survey System Based Smartphone by the National Population and Family Planning Indonesia","authors":"Sukarno Sono, Nl. Meilani, T. Prihyugiarto, Y. Karyanti","doi":"10.1109/ICOICT.2018.8528763","DOIUrl":"https://doi.org/10.1109/ICOICT.2018.8528763","url":null,"abstract":"There is a change in the technique or method of collecting and processing data on the Performance Monitoring Accountability (PMA) 2020 Survey by the National Population and Family Planning Indonesia, from a paper-based system to electronic-based which paperless system, one of the tools called Open Data Kit. This study was therefore aimed at identifying the users' perception and attitude towards the application of the new technology in this survey in Indonesia. One of the methods to determine the extent to which the users' acceptance of the application of a new technology is to use the Technology Acceptance Model. Data analysis was performed using the Structural equation Modelling with Analysis of Moment Structure software. The analysis results prove that out of six hypotheses, only one hypothesis is rejected. The results suggest that the application of a new technology system is acceptable and has no resistance from the supervisors and enumerators as the of smartphone-based surveys users. In conclusion, this technology is possible to apply in other surveys in Indonesia.","PeriodicalId":266335,"journal":{"name":"2018 6th International Conference on Information and Communication Technology (ICoICT)","volume":"137 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123141202","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2018-05-01DOI: 10.1109/ICOICT.2018.8528812
F. Rahutomo, R. A. Asmara, Deddy Kusbianto Purwoko Aji
Indonesian vocabularies are listed in Indonesian dictionary. The dictionary is published by Language Development Council, the Ministry of Education and Culture, Republic of Indonesia. Strangely, Indonesian citizen no longer uses many of Indonesian vocabularies which are listed in the dictionary. In contrary, the citizen uses so many new vocabularies which are not listed in the dictionary. The purpose of this study is to examine this phenomenon more deeply from computer science point of view. A collection of 6 months Indonesian online news corpus consists of 153,349 articles was used. Then the corpus was compared with 51,029 lemmas in Indonesian Thesaurus Dictionary. The analysis was done per day and per online media. This study reports 26,887 lemmas which never been used with daily increase trend during the period. While with 1,000 times appearance threshold, 509 new lemmas appear with daily decreased trend.
{"title":"Computational Analysis on Rise and Fall of Indonesian Vocabulary During a Period of Time","authors":"F. Rahutomo, R. A. Asmara, Deddy Kusbianto Purwoko Aji","doi":"10.1109/ICOICT.2018.8528812","DOIUrl":"https://doi.org/10.1109/ICOICT.2018.8528812","url":null,"abstract":"Indonesian vocabularies are listed in Indonesian dictionary. The dictionary is published by Language Development Council, the Ministry of Education and Culture, Republic of Indonesia. Strangely, Indonesian citizen no longer uses many of Indonesian vocabularies which are listed in the dictionary. In contrary, the citizen uses so many new vocabularies which are not listed in the dictionary. The purpose of this study is to examine this phenomenon more deeply from computer science point of view. A collection of 6 months Indonesian online news corpus consists of 153,349 articles was used. Then the corpus was compared with 51,029 lemmas in Indonesian Thesaurus Dictionary. The analysis was done per day and per online media. This study reports 26,887 lemmas which never been used with daily increase trend during the period. While with 1,000 times appearance threshold, 509 new lemmas appear with daily decreased trend.","PeriodicalId":266335,"journal":{"name":"2018 6th International Conference on Information and Communication Technology (ICoICT)","volume":"45 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127083178","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2018-05-01DOI: 10.1109/ICOICT.2018.8528788
Jaka E. Sembodo, E. B. Setiawan, M. Bijaksana
Tweet is being informative as well as news articles, so that the automatic tweet classifier based on news category could be useful to make ease in searching tweet based on certain interesting category. We identified those are 11 categories: religion, business, entertainment, law and crime, health, motivation, sport, government, education, politics and technology. In the learning process, we use ZeroR, Naive Bayes Multinomial (NBM), Support Vector Machine (SVM), Random Forest (RF) and Sequential Minimal Optimization (SMO) algorithm based on previous work that has similar topic with this paper. In experiments, we experiment classifier using all tweet and various maximum number of tweets and terms in each category. In evaluating performance system, we used 10-fold cross validation and use accuracy (correctly classified instances) as performance paramater. In the experiments result, NBM performs the highest performance with 77,47% accuracy with maximum number of tweets and terms in every category is 500 tweets and 1000 terms. At the last, we built automatic tweet classifier with NBM due to this classifier and experiment result perform the best performances using web-based programming.
{"title":"Automatic Tweet Classification Based on News Category in Indonesian Language","authors":"Jaka E. Sembodo, E. B. Setiawan, M. Bijaksana","doi":"10.1109/ICOICT.2018.8528788","DOIUrl":"https://doi.org/10.1109/ICOICT.2018.8528788","url":null,"abstract":"Tweet is being informative as well as news articles, so that the automatic tweet classifier based on news category could be useful to make ease in searching tweet based on certain interesting category. We identified those are 11 categories: religion, business, entertainment, law and crime, health, motivation, sport, government, education, politics and technology. In the learning process, we use ZeroR, Naive Bayes Multinomial (NBM), Support Vector Machine (SVM), Random Forest (RF) and Sequential Minimal Optimization (SMO) algorithm based on previous work that has similar topic with this paper. In experiments, we experiment classifier using all tweet and various maximum number of tweets and terms in each category. In evaluating performance system, we used 10-fold cross validation and use accuracy (correctly classified instances) as performance paramater. In the experiments result, NBM performs the highest performance with 77,47% accuracy with maximum number of tweets and terms in every category is 500 tweets and 1000 terms. At the last, we built automatic tweet classifier with NBM due to this classifier and experiment result perform the best performances using web-based programming.","PeriodicalId":266335,"journal":{"name":"2018 6th International Conference on Information and Communication Technology (ICoICT)","volume":"60 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130157899","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2018-05-01DOI: 10.1109/ICOICT.2018.8528792
Gregorius Aldo Radityatama, Charles Lim, Heru Purnomo Ipung
Next Generation Firewall (NGFW) adds new capabilities of a standard firewall with an ability to inspect packets' contents, thus increasing precision. Three main usages of NGFW are to improve the Quality of Service (QoS) of a business, as an application-based filtering firewall, and to protect the network from known security threats. A complete NGFW system has three main components: Deep Packet Inspection (DPI), Intrusion Prevention System (IPS), and an extra-firewall intelligence mechanism. One example of open-source DPI implementations is called nDPI. As the number of enterprise applications (used in the commercial organizations) continues to rise, nDPI is also lagging in terms of coverage for enterprise software support. The aim of this research is to design and implement better enterprise-grade software support protocols on nDPI. Five common enterprise applications were chosen and implemented. The experiment results were then compared with the commercial implementation of NGFW in terms of overall precision and performance of nDPI. The results show that the accuracy of nDPI the new protocols implemented reaches more than 90% with a small (less than 3,5%) increase of CPU execution time and very small (less than 1%) increase of peak heap memory usage.
{"title":"Toward Full Enterprise Software Support on nDPI","authors":"Gregorius Aldo Radityatama, Charles Lim, Heru Purnomo Ipung","doi":"10.1109/ICOICT.2018.8528792","DOIUrl":"https://doi.org/10.1109/ICOICT.2018.8528792","url":null,"abstract":"Next Generation Firewall (NGFW) adds new capabilities of a standard firewall with an ability to inspect packets' contents, thus increasing precision. Three main usages of NGFW are to improve the Quality of Service (QoS) of a business, as an application-based filtering firewall, and to protect the network from known security threats. A complete NGFW system has three main components: Deep Packet Inspection (DPI), Intrusion Prevention System (IPS), and an extra-firewall intelligence mechanism. One example of open-source DPI implementations is called nDPI. As the number of enterprise applications (used in the commercial organizations) continues to rise, nDPI is also lagging in terms of coverage for enterprise software support. The aim of this research is to design and implement better enterprise-grade software support protocols on nDPI. Five common enterprise applications were chosen and implemented. The experiment results were then compared with the commercial implementation of NGFW in terms of overall precision and performance of nDPI. The results show that the accuracy of nDPI the new protocols implemented reaches more than 90% with a small (less than 3,5%) increase of CPU execution time and very small (less than 1%) increase of peak heap memory usage.","PeriodicalId":266335,"journal":{"name":"2018 6th International Conference on Information and Communication Technology (ICoICT)","volume":"81 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132742964","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2018-05-01DOI: 10.1109/ICOICT.2018.8528745
Rizka Reza Pahlevi, Aji Gautama Putrada S, M. Abdurohman
This paper proposes the enhancement of Universal Asynchronous Transmitter Receiver (UART) and Serial Peripheral Interface (SPI) protocols for improving the node performance in the Internet of Things (IoT) platform. Implementation of UART communication protocol on IoT in microcontroller ATmega328 has limitation of Serial Hardware scalability so it must do bit banging which can affect performance and lack of speed. SPI requires change of SPI Control Register (SPICR) to become Slave Select which can affect speed and also have limited of Slave Select. There are many previous methods that have been proposed to solve this problem. However, none of them are scalable and speed aware. This proposed method uses parallelism concepts by implementing hardware environment. Through some experiments, this research succeeded to implement UART on FPGA where the speed is 67,3% faster than the microcontroller ATmega328 and is able to reach four UARTs. SPI Slave on FPGA has speed up to 73.43% faster than the microcontroller ATmega328 and is able to expand to two SPI Slaves.
{"title":"Fast UART and SPI Protocol for Scalable IoT Platform","authors":"Rizka Reza Pahlevi, Aji Gautama Putrada S, M. Abdurohman","doi":"10.1109/ICOICT.2018.8528745","DOIUrl":"https://doi.org/10.1109/ICOICT.2018.8528745","url":null,"abstract":"This paper proposes the enhancement of Universal Asynchronous Transmitter Receiver (UART) and Serial Peripheral Interface (SPI) protocols for improving the node performance in the Internet of Things (IoT) platform. Implementation of UART communication protocol on IoT in microcontroller ATmega328 has limitation of Serial Hardware scalability so it must do bit banging which can affect performance and lack of speed. SPI requires change of SPI Control Register (SPICR) to become Slave Select which can affect speed and also have limited of Slave Select. There are many previous methods that have been proposed to solve this problem. However, none of them are scalable and speed aware. This proposed method uses parallelism concepts by implementing hardware environment. Through some experiments, this research succeeded to implement UART on FPGA where the speed is 67,3% faster than the microcontroller ATmega328 and is able to reach four UARTs. SPI Slave on FPGA has speed up to 73.43% faster than the microcontroller ATmega328 and is able to expand to two SPI Slaves.","PeriodicalId":266335,"journal":{"name":"2018 6th International Conference on Information and Communication Technology (ICoICT)","volume":"51 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114361678","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2018-05-01DOI: 10.1109/ICOICT.2018.8528774
A. Alamsyah, Asri Nurfathi Zahir
Stock is a high risk and high return investment. The risk-comparison scale for both losses and profits are not much different. The lure of profits temptations can be given by playing shares, sometimes make people less cautious and eventually fail to invest in stocks. To make right and profitable investment decisions, investors need to face uncertainty and fluctuating stock price movements. These phenomena cause investors to predict stock price movements for minimizing risks. The purpose of this study is to predict the Indonesian composite stock price index by using macroeconomic variables as a reflection of economic condition and as a good signal to forecast stock prices. This research is using Inflation, Interest Rates, and Exchange Rates as the macroeconomic variables. This study uses secondary data from Bank Indonesia and Indonesian Statistics Center from December 2005 to November 2017. The prediction uses Artificial Neural Network (ANN) Backpropagation method. The results gained the accuracy of 96,38% and mean-squared error of 0.0046 with the best time delay of 2 months before the predicted month. Based on the accuracy level and the error, macroeconomic variables (exchange rate, interest rate, inflation rate, and money supply M2) are the proper indicator to predict IDX Composite movement.
{"title":"Artificial Neural Network for Predicting Indonesia Stock Exchange Composite Using Macroeconomic Variables","authors":"A. Alamsyah, Asri Nurfathi Zahir","doi":"10.1109/ICOICT.2018.8528774","DOIUrl":"https://doi.org/10.1109/ICOICT.2018.8528774","url":null,"abstract":"Stock is a high risk and high return investment. The risk-comparison scale for both losses and profits are not much different. The lure of profits temptations can be given by playing shares, sometimes make people less cautious and eventually fail to invest in stocks. To make right and profitable investment decisions, investors need to face uncertainty and fluctuating stock price movements. These phenomena cause investors to predict stock price movements for minimizing risks. The purpose of this study is to predict the Indonesian composite stock price index by using macroeconomic variables as a reflection of economic condition and as a good signal to forecast stock prices. This research is using Inflation, Interest Rates, and Exchange Rates as the macroeconomic variables. This study uses secondary data from Bank Indonesia and Indonesian Statistics Center from December 2005 to November 2017. The prediction uses Artificial Neural Network (ANN) Backpropagation method. The results gained the accuracy of 96,38% and mean-squared error of 0.0046 with the best time delay of 2 months before the predicted month. Based on the accuracy level and the error, macroeconomic variables (exchange rate, interest rate, inflation rate, and money supply M2) are the proper indicator to predict IDX Composite movement.","PeriodicalId":266335,"journal":{"name":"2018 6th International Conference on Information and Communication Technology (ICoICT)","volume":"28 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115520345","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2018-05-01DOI: 10.1109/ICOICT.2018.8528797
H. Nuha, Sidik Prabowo
In this work, an analysis of Transmission Control Protocol (TCP) Congestion Window with traffic model of twitter using exponential distribution is presented. TCP is a popular reliable protocol used by many internet service. As social medias emerge and introduce new characteristic of traffic, it is interesting to evaluate the performance of TCP in the latest social media environment scenario. Twitter as top social media shows its influence by taking part of many political event in the globe. An exponential distribution traffic model of Twitter traffic is proposed and an experiment on evaluation of TCP congestion window is presented in this paper. A congestion window represents efficiency of TCP to adapt network condition since the metric shows the number of data transmitted in a single transmission. In stable condition, shared bandwidth carry out higher congestion window which makes transmission more efficient. Combination of high traffic flow and high bandwidth comes with lower congestion window variation with 0.58 where low traffic flow obtains higher variance with 1.15.
{"title":"TCP Congestion Window Analysis of Twitter with Exponential Model","authors":"H. Nuha, Sidik Prabowo","doi":"10.1109/ICOICT.2018.8528797","DOIUrl":"https://doi.org/10.1109/ICOICT.2018.8528797","url":null,"abstract":"In this work, an analysis of Transmission Control Protocol (TCP) Congestion Window with traffic model of twitter using exponential distribution is presented. TCP is a popular reliable protocol used by many internet service. As social medias emerge and introduce new characteristic of traffic, it is interesting to evaluate the performance of TCP in the latest social media environment scenario. Twitter as top social media shows its influence by taking part of many political event in the globe. An exponential distribution traffic model of Twitter traffic is proposed and an experiment on evaluation of TCP congestion window is presented in this paper. A congestion window represents efficiency of TCP to adapt network condition since the metric shows the number of data transmitted in a single transmission. In stable condition, shared bandwidth carry out higher congestion window which makes transmission more efficient. Combination of high traffic flow and high bandwidth comes with lower congestion window variation with 0.58 where low traffic flow obtains higher variance with 1.15.","PeriodicalId":266335,"journal":{"name":"2018 6th International Conference on Information and Communication Technology (ICoICT)","volume":"36 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116093886","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：