Pub Date : 2018-05-03DOI: 10.1109/ICOICT.2018.8528731
Muhammad Arzaki
In this paper we study the security aspect of Megrelishvili protocol—a linear algebra-based variant of the Diffie-Hellman key agreement. We demonstrate that the conventional version of this protocol is vulnerable to the man-in-the-middle attack. Hence, to avert such attack, we propose an authenticated version of this protocol using an embedded digital signature scheme. The scheme is constructed using the hardness assumption of the Megrelishvili vector-matrix problem (MVMP)—the underlying computational problem for the security of the conventional Megrelishvili protocol. We prove the correctness of the signature scheme and argue that our proposed protocol is secure against the man-in-the-middle attack provided that the MVMP is intractable.
{"title":"Strengthening Megrelishvili Protocol Against Man-in-the-Middle Attack","authors":"Muhammad Arzaki","doi":"10.1109/ICOICT.2018.8528731","DOIUrl":"https://doi.org/10.1109/ICOICT.2018.8528731","url":null,"abstract":"In this paper we study the security aspect of Megrelishvili protocol—a linear algebra-based variant of the Diffie-Hellman key agreement. We demonstrate that the conventional version of this protocol is vulnerable to the man-in-the-middle attack. Hence, to avert such attack, we propose an authenticated version of this protocol using an embedded digital signature scheme. The scheme is constructed using the hardness assumption of the Megrelishvili vector-matrix problem (MVMP)—the underlying computational problem for the security of the conventional Megrelishvili protocol. We prove the correctness of the signature scheme and argue that our proposed protocol is secure against the man-in-the-middle attack provided that the MVMP is intractable.","PeriodicalId":266335,"journal":{"name":"2018 6th International Conference on Information and Communication Technology (ICoICT)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2018-05-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125627857","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 : 2018-05-03DOI: 10.1109/ICOICT.2018.8528764
Syifa Mutiara Hersista
In the power-limited sensor network, it is important to optimize the power allocation while maintaining connectivity for each sensor node to guarantee reliable localization. In order to prolong lifetime of sensors, optimizing the power is very crucial while maintaining a proper number of connectivity to ensure a good localizability. In this paper, we propose a connectivity control algorithm, which consider the number of connectivity while optimizing power of sensors. We investigate the information of distribution node statistically, and formulate the relaxation method of utility function in order to get quasi-concave property. Numerically, we show our proposed algorithm gives better performance compared to the recent algorithms with target connectivity $k=7$, while the other algorithm achieves zero connection with the same trade-off parameter.
{"title":"Connectivity Control Algorithm for Autonomous Wireless Agents","authors":"Syifa Mutiara Hersista","doi":"10.1109/ICOICT.2018.8528764","DOIUrl":"https://doi.org/10.1109/ICOICT.2018.8528764","url":null,"abstract":"In the power-limited sensor network, it is important to optimize the power allocation while maintaining connectivity for each sensor node to guarantee reliable localization. In order to prolong lifetime of sensors, optimizing the power is very crucial while maintaining a proper number of connectivity to ensure a good localizability. In this paper, we propose a connectivity control algorithm, which consider the number of connectivity while optimizing power of sensors. We investigate the information of distribution node statistically, and formulate the relaxation method of utility function in order to get quasi-concave property. Numerically, we show our proposed algorithm gives better performance compared to the recent algorithms with target connectivity $k=7$, while the other algorithm achieves zero connection with the same trade-off parameter.","PeriodicalId":266335,"journal":{"name":"2018 6th International Conference on Information and Communication Technology (ICoICT)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2018-05-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122123313","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 : 2018-05-03DOI: 10.1109/ICOICT.2018.8528778
Fauzan Adhi Rachman, Aji Gautama Putrada, M. Abdurohman
This paper proposes the campus distributed bike sharing system for enhancing bike service availability in Telkom University. Bike sharing has been established since 2014. But its utilization has been decreased because the flexibility of the landing system. In this paper, we propose new bike sharing system based on Internet of Thing (IoT) System using MQTT protocol. Several experiments have been evaluated. The results show performance of the system is 2.91s and 0.79 s for the response time and the average delay of the data respectively
为了提高电信大学自行车服务的可用性,本文提出了校园分布式自行车共享系统。自2014年以来,共享单车已经建立。但由于着陆系统的灵活性,降低了其利用率。本文提出了一种基于MQTT协议的物联网共享单车系统。对几个实验进行了评价。结果表明,该系统的数据响应时间为2.91s,平均时延为0.79 s
{"title":"Distributed Campus Bike Sharing System Based-on Internet of Things (IoT)","authors":"Fauzan Adhi Rachman, Aji Gautama Putrada, M. Abdurohman","doi":"10.1109/ICOICT.2018.8528778","DOIUrl":"https://doi.org/10.1109/ICOICT.2018.8528778","url":null,"abstract":"This paper proposes the campus distributed bike sharing system for enhancing bike service availability in Telkom University. Bike sharing has been established since 2014. But its utilization has been decreased because the flexibility of the landing system. In this paper, we propose new bike sharing system based on Internet of Thing (IoT) System using MQTT protocol. Several experiments have been evaluated. The results show performance of the system is 2.91s and 0.79 s for the response time and the average delay of the data respectively","PeriodicalId":266335,"journal":{"name":"2018 6th International Conference on Information and Communication Technology (ICoICT)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2018-05-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125671775","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 : 2018-05-03DOI: 10.1109/ICOICT.2018.8528743
Muhammad Fikri Suyudi Wikatama, Muhammad Arzaki, Yanti Rusmawati
We propose a formal approach to verify the safety of vaccine supply chain systems in Indonesia. The description of vaccine supply chain systems comes from PT. Bio Farma as the vaccine producer, and according to WHO regulation as well. Firstly, we describe the workflows of the system and model them using activity diagrams. Afterwards, we specify safety properties based on the WHO requirements as linear-time temporal logic formulas and translate the diagrams into temporal logic expressions in the form of NuSMV model. We verify them using NuSMV model checker to check whether the workflows conform to the requirements. In general, the result shows that the safety of the system is proven.
我们提出一种正式的方法来验证印度尼西亚疫苗供应链系统的安全性。疫苗供应链系统的描述来自疫苗生产商PT. Bio Farma,也符合世卫组织的规定。首先,我们描述了系统的工作流程,并使用活动图对其建模。然后,我们将基于WHO要求的安全属性指定为线性-时间逻辑公式,并将图转换为NuSMV模型形式的时间逻辑表达式。我们使用NuSMV模型检查器来检查工作流是否符合需求。总体而言,结果表明该系统的安全性得到了验证。
{"title":"Verifying Vaccine Supply Chain System in Indonesia Using Linear-Time Temporal Logic","authors":"Muhammad Fikri Suyudi Wikatama, Muhammad Arzaki, Yanti Rusmawati","doi":"10.1109/ICOICT.2018.8528743","DOIUrl":"https://doi.org/10.1109/ICOICT.2018.8528743","url":null,"abstract":"We propose a formal approach to verify the safety of vaccine supply chain systems in Indonesia. The description of vaccine supply chain systems comes from PT. Bio Farma as the vaccine producer, and according to WHO regulation as well. Firstly, we describe the workflows of the system and model them using activity diagrams. Afterwards, we specify safety properties based on the WHO requirements as linear-time temporal logic formulas and translate the diagrams into temporal logic expressions in the form of NuSMV model. We verify them using NuSMV model checker to check whether the workflows conform to the requirements. In general, the result shows that the safety of the system is proven.","PeriodicalId":266335,"journal":{"name":"2018 6th International Conference on Information and Communication Technology (ICoICT)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2018-05-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133796678","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 : 2018-05-03DOI: 10.1109/ICOICT.2018.8528725
Joko Azhari Suyatno, F. Nhita, A. A. Rohmawati
Bandung regency is one of Indonesian city that majority of the people are farmers. Farmers need weather information to determine the planting season. Weather forecasting become an orientation in agriculture sector to determining the beginning of planting season, and also quality and quantity of their harvest. One of the factors that affecting the harvest is rainfall. In this research, we make a classification model using C4.5 algorithm for rainfall forecasting at Bandung regency. Then, the post-pruning method is used to optimize pruning on the model. We used a weather data from BMKG (Meteorological, Climatological, and Geophysical Agency) in 2005 to 2016 period. The result of average accuracy testing without pruning is 60% and using pruning is 93.33%.
{"title":"Rainfall Forecasting in Bandung Regency Using C4.5 Algorithm","authors":"Joko Azhari Suyatno, F. Nhita, A. A. Rohmawati","doi":"10.1109/ICOICT.2018.8528725","DOIUrl":"https://doi.org/10.1109/ICOICT.2018.8528725","url":null,"abstract":"Bandung regency is one of Indonesian city that majority of the people are farmers. Farmers need weather information to determine the planting season. Weather forecasting become an orientation in agriculture sector to determining the beginning of planting season, and also quality and quantity of their harvest. One of the factors that affecting the harvest is rainfall. In this research, we make a classification model using C4.5 algorithm for rainfall forecasting at Bandung regency. Then, the post-pruning method is used to optimize pruning on the model. We used a weather data from BMKG (Meteorological, Climatological, and Geophysical Agency) in 2005 to 2016 period. The result of average accuracy testing without pruning is 60% and using pruning is 93.33%.","PeriodicalId":266335,"journal":{"name":"2018 6th International Conference on Information and Communication Technology (ICoICT)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2018-05-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125843304","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 : 2018-05-03DOI: 10.1109/ICOICT.2018.8528736
B. Erfianto, N. Suwastika, Sidik Prabowo
The lifting of sediments at the bottom of the reservoir caused by vertical currents causes rapid mass mortality of fish. The sediment, which is mostly fish excrement and feed residue, causes the dissolved oxygen (DO) content in the water surface to drop dramatically from the normal value of 3–6 mg / L to below 1 mg / L. This vertical current condition is referred to as upwelling of the reservoir. The occurrence of upwelling in freshwater waters can be predicted from factors of difference in surface temperature and under surface temperatures, DO levels and pH levels. Upwelling will occur if the temperature difference between surface temperature and underwater temperature reaches > 5°C for more than 11 hours. The system for detecting upwelling is built on Internet of Things (IoT) communications by utilizing a fuzzy logic decision system. The reading of data from temperature, DO, and pH sensors is sent to the microcontroller device and delivered to the end user via the Internet network. Fuzzy logic implanted on microcontroller device to get the decision condition is not upwelling, potentially upwelling, and upwelling occurs. Upwelling detection systems are tested in reservoirs and in test environments. From the test results the system successfully read data, process data, and send to users without any data lost or damaged.
{"title":"Decision System for Reservoir Upwelling Using Fuzzy Logic Based on Internet of Things","authors":"B. Erfianto, N. Suwastika, Sidik Prabowo","doi":"10.1109/ICOICT.2018.8528736","DOIUrl":"https://doi.org/10.1109/ICOICT.2018.8528736","url":null,"abstract":"The lifting of sediments at the bottom of the reservoir caused by vertical currents causes rapid mass mortality of fish. The sediment, which is mostly fish excrement and feed residue, causes the dissolved oxygen (DO) content in the water surface to drop dramatically from the normal value of 3–6 mg / L to below 1 mg / L. This vertical current condition is referred to as upwelling of the reservoir. The occurrence of upwelling in freshwater waters can be predicted from factors of difference in surface temperature and under surface temperatures, DO levels and pH levels. Upwelling will occur if the temperature difference between surface temperature and underwater temperature reaches > 5°C for more than 11 hours. The system for detecting upwelling is built on Internet of Things (IoT) communications by utilizing a fuzzy logic decision system. The reading of data from temperature, DO, and pH sensors is sent to the microcontroller device and delivered to the end user via the Internet network. Fuzzy logic implanted on microcontroller device to get the decision condition is not upwelling, potentially upwelling, and upwelling occurs. Upwelling detection systems are tested in reservoirs and in test environments. From the test results the system successfully read data, process data, and send to users without any data lost or damaged.","PeriodicalId":266335,"journal":{"name":"2018 6th International Conference on Information and Communication Technology (ICoICT)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2018-05-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116924996","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 : 2018-05-03DOI: 10.1109/ICOICT.2018.8528777
Reynaldi Ananda Pane, M. S. Mubarok, Nanang Saiful Huda, Adiwijaya
Al-Quran is the holy book as well as guidance for Muslims around the world. Each verse of Quran contains meaning and wisdom that can usually be classified into more than one topic of discussion. This research was conducted on the issue of classification of Quranic verses that can be classified into more than one topic as a multi-label classification problem. Multi-label classification is different from single-label classification, therefore this research provided a new model of classifier to handle multi-label classification. The system was developed using Multinomial Naïve Bayes with several stages of preprocessing data such as case folding, tokenization, and stemming. The system also used bag of words as feature extraction method. The best Hamming loss obtained from this research is 0.1247.
{"title":"A Multi-Lable Classification on Topics of Quranic Verses in English Translation Using Multinomial Naive Bayes","authors":"Reynaldi Ananda Pane, M. S. Mubarok, Nanang Saiful Huda, Adiwijaya","doi":"10.1109/ICOICT.2018.8528777","DOIUrl":"https://doi.org/10.1109/ICOICT.2018.8528777","url":null,"abstract":"Al-Quran is the holy book as well as guidance for Muslims around the world. Each verse of Quran contains meaning and wisdom that can usually be classified into more than one topic of discussion. This research was conducted on the issue of classification of Quranic verses that can be classified into more than one topic as a multi-label classification problem. Multi-label classification is different from single-label classification, therefore this research provided a new model of classifier to handle multi-label classification. The system was developed using Multinomial Naïve Bayes with several stages of preprocessing data such as case folding, tokenization, and stemming. The system also used bag of words as feature extraction method. The best Hamming loss obtained from this research is 0.1247.","PeriodicalId":266335,"journal":{"name":"2018 6th International Conference on Information and Communication Technology (ICoICT)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2018-05-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130278601","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 : 2018-05-03DOI: 10.1109/ICOICT.2018.8528749
Ridhwan Dewoprabowo, Muhammad Arzaki, Yanti Rusmawati
In this article we present a generalized version of divide and conquer approach for contributory group Diffie-Hellman key exchange (DHKE) scheme. In particular, we devise an efficient way to establish a mutual secret key for multiple participants that uses a quasilinear amount of exponentiations with respect to the number of participants. The correctness of our protocol is proven using mathematical induction. We also compute its complexity in terms of total exponentiations within the protocol, analyze several important computational characteristics, and analyze the security of the protocol against passive attack. Moreover, we provide a comprehensive comparison of our protocol with other existing contributory schemes. Finally, we present an adaptation of our protocol for Megrelishvili group key agreement as a variant of DHKE procedure.
{"title":"On Generalized Divide and Conquer Approach for Group Key Distribution: Correctness and Complexity","authors":"Ridhwan Dewoprabowo, Muhammad Arzaki, Yanti Rusmawati","doi":"10.1109/ICOICT.2018.8528749","DOIUrl":"https://doi.org/10.1109/ICOICT.2018.8528749","url":null,"abstract":"In this article we present a generalized version of divide and conquer approach for contributory group Diffie-Hellman key exchange (DHKE) scheme. In particular, we devise an efficient way to establish a mutual secret key for multiple participants that uses a quasilinear amount of exponentiations with respect to the number of participants. The correctness of our protocol is proven using mathematical induction. We also compute its complexity in terms of total exponentiations within the protocol, analyze several important computational characteristics, and analyze the security of the protocol against passive attack. Moreover, we provide a comprehensive comparison of our protocol with other existing contributory schemes. Finally, we present an adaptation of our protocol for Megrelishvili group key agreement as a variant of DHKE procedure.","PeriodicalId":266335,"journal":{"name":"2018 6th International Conference on Information and Communication Technology (ICoICT)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2018-05-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114426803","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 : 2018-05-03DOI: 10.1109/ICOICT.2018.8528810
I. Hapsari, I. Surjandari, Komarudin, Reynaldi Ananda, Pane Mohamad, Syahrul Mubarok, Nanang, Mukti Ari, H. Murfi, Satrio Adi, N. Endro, Ariyanto Andrian, Rakhmatsyah, Aji Achmad, Indra Budi, Faisal Rahutomo, Rosa Andrie, Deddy Kusbianto, Purwoko Aji, Tedjo Darmanto, Fajar Hendra, Prabowo, M. Kemas, Lhaksmana Z. K Abdurahman, Baizal
Smart tourists cannot be separated with mobile technology. With the gadget, tourist can find information about the destination, or supporting information like transportation, hotel, weather and exchange rate. They need prediction of traveling and visiting time, to arrange their journey. If traveling time has predicted accurately by Google Map using the location feature, visiting time has another issue. Until today, Google detects the user's position based on crowdsourcing data from customer visits to a specific location over the last several weeks. It cannot be denied that this method will give a valid information for the tourists. However, because it needs a lot of data, there are many destinations that have no information about visiting time. From the case study that we used, there are 626 destinations in East Java, Indonesia, and from that amount only 224 destinations or 35.78% has the visiting time. To complete the information and help tourists, this research developed the prediction model for visiting time. For the first data is tested statistically to make sure the model development was using the right method. Multiple linear regression become the common model, because there are six factors that influenced the visiting time, i.e. access, government, rating, number of reviews, number of pictures, and other information. Those factors become the independent variables to predict dependent variable or visiting time. From normality test as the linear regression requirement, the significant value was less than p that means the data cannot pass the statistic test, even though we transformed the data based on the skewness. Because of three of them are ordinal data and the others are interval data, we tried to exclude and include the ordinal by transform it to interval. We also used the Ordinal Logistic Regression by transform the interval data in dependent variable into ordinal data using Expectation Maximization, one of clustering algorithm in machine learning, but the model still did not fit even though we used 5 functions. Then we used the classification algorithm in machine learning by using 5 top algorithm which are Linear Regression, k-Nearest Neighbors, Decision Tree, Support Vector Machines, and Multi-Layer Perceptron. Based on maximum correlation coefficient and minimum root mean square error, Linear Regression with 6 independent variables has the best result with the correlation coefficient 20.41% and root mean square error 48.46%. We also compared with model using 3 independent variable, the best algorithm was still the same but with less performance. Then, the model was loaded to predict the visiting time for other 402 destinations.
{"title":"Visiting Time Prediction Using Machine Learning Regression Algorithm","authors":"I. Hapsari, I. Surjandari, Komarudin, Reynaldi Ananda, Pane Mohamad, Syahrul Mubarok, Nanang, Mukti Ari, H. Murfi, Satrio Adi, N. Endro, Ariyanto Andrian, Rakhmatsyah, Aji Achmad, Indra Budi, Faisal Rahutomo, Rosa Andrie, Deddy Kusbianto, Purwoko Aji, Tedjo Darmanto, Fajar Hendra, Prabowo, M. Kemas, Lhaksmana Z. K Abdurahman, Baizal","doi":"10.1109/ICOICT.2018.8528810","DOIUrl":"https://doi.org/10.1109/ICOICT.2018.8528810","url":null,"abstract":"Smart tourists cannot be separated with mobile technology. With the gadget, tourist can find information about the destination, or supporting information like transportation, hotel, weather and exchange rate. They need prediction of traveling and visiting time, to arrange their journey. If traveling time has predicted accurately by Google Map using the location feature, visiting time has another issue. Until today, Google detects the user's position based on crowdsourcing data from customer visits to a specific location over the last several weeks. It cannot be denied that this method will give a valid information for the tourists. However, because it needs a lot of data, there are many destinations that have no information about visiting time. From the case study that we used, there are 626 destinations in East Java, Indonesia, and from that amount only 224 destinations or 35.78% has the visiting time. To complete the information and help tourists, this research developed the prediction model for visiting time. For the first data is tested statistically to make sure the model development was using the right method. Multiple linear regression become the common model, because there are six factors that influenced the visiting time, i.e. access, government, rating, number of reviews, number of pictures, and other information. Those factors become the independent variables to predict dependent variable or visiting time. From normality test as the linear regression requirement, the significant value was less than p that means the data cannot pass the statistic test, even though we transformed the data based on the skewness. Because of three of them are ordinal data and the others are interval data, we tried to exclude and include the ordinal by transform it to interval. We also used the Ordinal Logistic Regression by transform the interval data in dependent variable into ordinal data using Expectation Maximization, one of clustering algorithm in machine learning, but the model still did not fit even though we used 5 functions. Then we used the classification algorithm in machine learning by using 5 top algorithm which are Linear Regression, k-Nearest Neighbors, Decision Tree, Support Vector Machines, and Multi-Layer Perceptron. Based on maximum correlation coefficient and minimum root mean square error, Linear Regression with 6 independent variables has the best result with the correlation coefficient 20.41% and root mean square error 48.46%. We also compared with model using 3 independent variable, the best algorithm was still the same but with less performance. Then, the model was loaded to predict the visiting time for other 402 destinations.","PeriodicalId":266335,"journal":{"name":"2018 6th International Conference on Information and Communication Technology (ICoICT)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2018-05-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133981655","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 : 2018-05-03DOI: 10.1109/ICOICT.2018.8528744
I. Indrawati, Kedar Priya Utama
Growth in mobile data consumption has the potential to transform the way in which consumers and business operate and communicate, and as such increase economic growth through productivity effect. Indonesia has a potential to increase 1.5% of GDP if success to increase the number of 4G users by 10%. Unfortunately, the 4G penetration in Indonesia has only reach less than 15%. And the factors that affecting consumers on using 4G services in Indonesia are still not clearly observed. Analyzing factors that affect the behavior intention and usage behavior of customers toward the adoption of 4G services is needed. This research intends to analyze factors that affect the behavioral intention and use behavior of customers toward the adoption of 4G services in Indonesia, based on Unified Theory of Acceptance and Use of Technology 2. The results reveals, factors that influencing the Behavioral Intention on the adoption of 4G services in Indonesia are Habit, Content, Hedonic Motivation, Performance Expectancy and Social Influence. Factors that influencing Use Behavior are Habit, Facilitating Condition and Behavioral Intention. The influence of the factors on Behavioral Intention is 62%, while the influence on Use Behavior is 48%. Based on the results, the UTAUT2 model is able to determine the Behavioral Intention and Use Behavior of consumers to use 4G services in Indonesia.
{"title":"Analyzing 4G Adoption in Indonesia Using a Modified Unified Theory of Acceptance and Use of Technology 2","authors":"I. Indrawati, Kedar Priya Utama","doi":"10.1109/ICOICT.2018.8528744","DOIUrl":"https://doi.org/10.1109/ICOICT.2018.8528744","url":null,"abstract":"Growth in mobile data consumption has the potential to transform the way in which consumers and business operate and communicate, and as such increase economic growth through productivity effect. Indonesia has a potential to increase 1.5% of GDP if success to increase the number of 4G users by 10%. Unfortunately, the 4G penetration in Indonesia has only reach less than 15%. And the factors that affecting consumers on using 4G services in Indonesia are still not clearly observed. Analyzing factors that affect the behavior intention and usage behavior of customers toward the adoption of 4G services is needed. This research intends to analyze factors that affect the behavioral intention and use behavior of customers toward the adoption of 4G services in Indonesia, based on Unified Theory of Acceptance and Use of Technology 2. The results reveals, factors that influencing the Behavioral Intention on the adoption of 4G services in Indonesia are Habit, Content, Hedonic Motivation, Performance Expectancy and Social Influence. Factors that influencing Use Behavior are Habit, Facilitating Condition and Behavioral Intention. The influence of the factors on Behavioral Intention is 62%, while the influence on Use Behavior is 48%. Based on the results, the UTAUT2 model is able to determine the Behavioral Intention and Use Behavior of consumers to use 4G services in Indonesia.","PeriodicalId":266335,"journal":{"name":"2018 6th International Conference on Information and Communication Technology (ICoICT)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2018-05-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121545537","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}