Pub Date : 2019-10-01DOI: 10.1109/ICICoS48119.2019.8982490
Maulana Ihsan, A. H. Saputro, W. Handayani
Hyperspectral imaging system is an alternative in measuring biological content, especially in plants. Carotenoid content in leaves is one of the ingredients that can be measured using Vis-NIR hyperspectral camera because carotenoids are pigments that are in that range. The combination of spatial and spectral information produces many advantages; one of them is fast measurement time. Spatial and spectral information is extensive data that must be processed in making prediction systems. Spectral information is the wavelength that becomes features in machine learning. A large number of features results in increased computational costs and general rules of machine learning if too many features are used that will result in overfitting. Therefore, this study aims to increase computational costs and reduce overfitting by reducing features not related to the target. The use of supervised learning in selecting features can maintain wavelength information on carotenoid content which the unsupervised method cannot do. The system predicts carotenoid content with MAE and RMSE values obtained at 21.42 and 39.21 using the random forest model with decision tree feature selection.
{"title":"Hyperspectral Imaging Feature Selection Using Regression Tree Algorithm: Prediction of Carotenoid Content Velvet Apple Leaf","authors":"Maulana Ihsan, A. H. Saputro, W. Handayani","doi":"10.1109/ICICoS48119.2019.8982490","DOIUrl":"https://doi.org/10.1109/ICICoS48119.2019.8982490","url":null,"abstract":"Hyperspectral imaging system is an alternative in measuring biological content, especially in plants. Carotenoid content in leaves is one of the ingredients that can be measured using Vis-NIR hyperspectral camera because carotenoids are pigments that are in that range. The combination of spatial and spectral information produces many advantages; one of them is fast measurement time. Spatial and spectral information is extensive data that must be processed in making prediction systems. Spectral information is the wavelength that becomes features in machine learning. A large number of features results in increased computational costs and general rules of machine learning if too many features are used that will result in overfitting. Therefore, this study aims to increase computational costs and reduce overfitting by reducing features not related to the target. The use of supervised learning in selecting features can maintain wavelength information on carotenoid content which the unsupervised method cannot do. The system predicts carotenoid content with MAE and RMSE values obtained at 21.42 and 39.21 using the random forest model with decision tree feature selection.","PeriodicalId":105407,"journal":{"name":"2019 3rd International Conference on Informatics and Computational Sciences (ICICoS)","volume":"5 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127133090","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 : 2019-10-01DOI: 10.1109/ICICoS48119.2019.8982423
Nurzaman, T. Siswantining, S. Soemartojo, Devvi Sarwinda
Missing values means the absence of data items for an observation that can result in the loss of certain information. During surveys, there are often missing values or missing data because there are likely respondents who cannot answer the question or do not want to answer the question. One way to handle missing values can be done by imputation, which is the process of filling or replacing missing values in the dataset with possible values based on information obtained in the dataset. This paper will apply the sequential regression multivariate imputation (SRMI) method for imputation of missing values in normal multivariate data. SRMI is a multiple imputation method whose imputation values are obtained from the sequence of regression model, where each variable containing missing values is regressed against all other variables that do not contain missing values as predictor variables. The way to get the value of imputation is to use an iteration approach to draw values from the predictive posterior distribution of the missing values under each successive regression model. the results of the evaluation of imputation quality on simulation data using Root Mean Square Error (RMSE).
{"title":"Application of Sequential Regression Multivariate Imputation Method on Multivariate Normal Missing Data","authors":"Nurzaman, T. Siswantining, S. Soemartojo, Devvi Sarwinda","doi":"10.1109/ICICoS48119.2019.8982423","DOIUrl":"https://doi.org/10.1109/ICICoS48119.2019.8982423","url":null,"abstract":"Missing values means the absence of data items for an observation that can result in the loss of certain information. During surveys, there are often missing values or missing data because there are likely respondents who cannot answer the question or do not want to answer the question. One way to handle missing values can be done by imputation, which is the process of filling or replacing missing values in the dataset with possible values based on information obtained in the dataset. This paper will apply the sequential regression multivariate imputation (SRMI) method for imputation of missing values in normal multivariate data. SRMI is a multiple imputation method whose imputation values are obtained from the sequence of regression model, where each variable containing missing values is regressed against all other variables that do not contain missing values as predictor variables. The way to get the value of imputation is to use an iteration approach to draw values from the predictive posterior distribution of the missing values under each successive regression model. the results of the evaluation of imputation quality on simulation data using Root Mean Square Error (RMSE).","PeriodicalId":105407,"journal":{"name":"2019 3rd International Conference on Informatics and Computational Sciences (ICICoS)","volume":"63 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125083806","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 : 2019-10-01DOI: 10.1109/ICICoS48119.2019.8982482
A. Wicaksono, Siti Mariyah
The regular availability of up to date data for evaluating the government's policy is still lack. One of them is data for evaluating development in the health sector. Data are crucial for decision making and policy evaluation. Public perspective or sentiment to each program initiated by the government is a form of evaluation from the citizen. Therefore, we need a technique that can regularly supply data used for decision-maker to measure the success of development programs. Utilization of news can help overcome the cost and time in carrying out updates on development initiated and performed by the government. In this study, we developed an application which can collect health development-related online news, process and analyze them to reflect the public's perspective to the health development programs. Successfully collected 1,204 news articles where 117 articles from detik.com, 661 articles from kompas.com and 426 articles from tempo. co. A total of 500 from 1,204 news articles are used as training data for making Named Entity Recognition models. Sentiment analysis of research results shows that the sentiments of the public to the issue of equitable quality of health services, financial protection, and distribution of drugs and medical personnel are positive. The results of the study indicate that news can be used as an analytical material for evaluating development, the results of which are quite relevant to the results achieved.
{"title":"Social Network Analysis of Health Development in Indonesia","authors":"A. Wicaksono, Siti Mariyah","doi":"10.1109/ICICoS48119.2019.8982482","DOIUrl":"https://doi.org/10.1109/ICICoS48119.2019.8982482","url":null,"abstract":"The regular availability of up to date data for evaluating the government's policy is still lack. One of them is data for evaluating development in the health sector. Data are crucial for decision making and policy evaluation. Public perspective or sentiment to each program initiated by the government is a form of evaluation from the citizen. Therefore, we need a technique that can regularly supply data used for decision-maker to measure the success of development programs. Utilization of news can help overcome the cost and time in carrying out updates on development initiated and performed by the government. In this study, we developed an application which can collect health development-related online news, process and analyze them to reflect the public's perspective to the health development programs. Successfully collected 1,204 news articles where 117 articles from detik.com, 661 articles from kompas.com and 426 articles from tempo. co. A total of 500 from 1,204 news articles are used as training data for making Named Entity Recognition models. Sentiment analysis of research results shows that the sentiments of the public to the issue of equitable quality of health services, financial protection, and distribution of drugs and medical personnel are positive. The results of the study indicate that news can be used as an analytical material for evaluating development, the results of which are quite relevant to the results achieved.","PeriodicalId":105407,"journal":{"name":"2019 3rd International Conference on Informatics and Computational Sciences (ICICoS)","volume":"53 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125951630","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 : 2019-10-01DOI: 10.1109/ICICoS48119.2019.8982443
Serenada Salma Shafira, Nadya Ulfa, H. A. Wibawa, Rismiyati
Facial expression recognition is one of the technological capabilities in identifying a face image to follow up on research conducted by psychologists. The recognition of facial expressions is very important to know the emotions of someone who is experiencing it. In this study two datasets were used, namely the FER2013 and CK + datasets. The FER2013 dataset and CK+ are datasets designed to identify facial expressions. At the feature extraction stage, it uses the Histogram of Oriented Gradient (HOG) feature dan Local Binary Pattern (LBP) feature. Whereas in the classification stage, the Extreme Learning Machine (ELM) classifier is used. The greatest accuracy by using HOG feature is 63.86% for the FER2013 dataset and 99.79% for the CK + dataset with sigmoid as an activation function. And the greatest accuracy by using LBP feature is 55.11 % for the FER2013 dataset and 98.72% for the CK + dataset with RBF as an activation function.
{"title":"Facial Expression Recognition Using Extreme Learning Machine","authors":"Serenada Salma Shafira, Nadya Ulfa, H. A. Wibawa, Rismiyati","doi":"10.1109/ICICoS48119.2019.8982443","DOIUrl":"https://doi.org/10.1109/ICICoS48119.2019.8982443","url":null,"abstract":"Facial expression recognition is one of the technological capabilities in identifying a face image to follow up on research conducted by psychologists. The recognition of facial expressions is very important to know the emotions of someone who is experiencing it. In this study two datasets were used, namely the FER2013 and CK + datasets. The FER2013 dataset and CK+ are datasets designed to identify facial expressions. At the feature extraction stage, it uses the Histogram of Oriented Gradient (HOG) feature dan Local Binary Pattern (LBP) feature. Whereas in the classification stage, the Extreme Learning Machine (ELM) classifier is used. The greatest accuracy by using HOG feature is 63.86% for the FER2013 dataset and 99.79% for the CK + dataset with sigmoid as an activation function. And the greatest accuracy by using LBP feature is 55.11 % for the FER2013 dataset and 98.72% for the CK + dataset with RBF as an activation function.","PeriodicalId":105407,"journal":{"name":"2019 3rd International Conference on Informatics and Computational Sciences (ICICoS)","volume":"34 12 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123463282","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 : 2019-10-01DOI: 10.1109/ICICoS48119.2019.8982531
Surjandy, Erick Fernando, Meyliana, Ferrianto Surya Wijaya, T. Swasti, K. Oktriono
Social Media is vigorously personalized for many purposes, ranging from social information to commercial information such as marketing campaign. However, the message in social media is effortless to fabricate and may cause potential loss of the image of a person, product image, or company reputation. In this line, there are three forms of the social media message, i.e. text message form, audiovisual/video message form, and the visual/picture message form. On this background, this study aims to explore the reliance influence factor on the message that disseminates through social media. The result of this preliminary study contributes to future marketing research. However, the contemporary university student is the most active user of social media in Indonesia. The causal/explanatory research in this study functionates to explain the relationship between university student background and communication device used by the student to trust factor of message form in social media. This study involved 388 respondents and revealed 15 essential relationships and a strong influence of trust factor to message form eventually.
{"title":"Analysis of Reliance Factors in The Text, Images and Videos on Social Media","authors":"Surjandy, Erick Fernando, Meyliana, Ferrianto Surya Wijaya, T. Swasti, K. Oktriono","doi":"10.1109/ICICoS48119.2019.8982531","DOIUrl":"https://doi.org/10.1109/ICICoS48119.2019.8982531","url":null,"abstract":"Social Media is vigorously personalized for many purposes, ranging from social information to commercial information such as marketing campaign. However, the message in social media is effortless to fabricate and may cause potential loss of the image of a person, product image, or company reputation. In this line, there are three forms of the social media message, i.e. text message form, audiovisual/video message form, and the visual/picture message form. On this background, this study aims to explore the reliance influence factor on the message that disseminates through social media. The result of this preliminary study contributes to future marketing research. However, the contemporary university student is the most active user of social media in Indonesia. The causal/explanatory research in this study functionates to explain the relationship between university student background and communication device used by the student to trust factor of message form in social media. This study involved 388 respondents and revealed 15 essential relationships and a strong influence of trust factor to message form eventually.","PeriodicalId":105407,"journal":{"name":"2019 3rd International Conference on Informatics and Computational Sciences (ICICoS)","volume":"23 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125418444","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 : 2019-10-01DOI: 10.1109/ICICoS48119.2019.8982390
Laatansa, R. Saputra, B. Noranita
Password data in a system usually stored in hash. Various human-caused negligence and system vulnerability can make those data fall in the hand of those who isn't entitled to or even those who have malicious purpose. Attacks which could be done on the hashed password data using GPGPU-based machine are for example: brute-force, dictionary, mask-attack, and word-list. This research explains about effectivity of brute-force and dictionary attack which done on SHA-l hashed password using GPGPU-based machine. Result is showing that brute-force effectively crack more password which has lower set of character, with over 11% of 7 or less characters passwords vs mere 3 % in the dictionary attack counterpart. Whereas dictionary attack is more effective on cracking password which has unsecure character pattern with 5,053 passwords vs 491 on best brute-force attack scenario. Usage of combined attack method (brute-force + dictionary) gives more balanced approach in terms of cracking whether the password is long or secure patterned string.
{"title":"Analysis of GPGPU-Based Brute-Force and Dictionary Attack on SHA-1 Password Hash","authors":"Laatansa, R. Saputra, B. Noranita","doi":"10.1109/ICICoS48119.2019.8982390","DOIUrl":"https://doi.org/10.1109/ICICoS48119.2019.8982390","url":null,"abstract":"Password data in a system usually stored in hash. Various human-caused negligence and system vulnerability can make those data fall in the hand of those who isn't entitled to or even those who have malicious purpose. Attacks which could be done on the hashed password data using GPGPU-based machine are for example: brute-force, dictionary, mask-attack, and word-list. This research explains about effectivity of brute-force and dictionary attack which done on SHA-l hashed password using GPGPU-based machine. Result is showing that brute-force effectively crack more password which has lower set of character, with over 11% of 7 or less characters passwords vs mere 3 % in the dictionary attack counterpart. Whereas dictionary attack is more effective on cracking password which has unsecure character pattern with 5,053 passwords vs 491 on best brute-force attack scenario. Usage of combined attack method (brute-force + dictionary) gives more balanced approach in terms of cracking whether the password is long or secure patterned string.","PeriodicalId":105407,"journal":{"name":"2019 3rd International Conference on Informatics and Computational Sciences (ICICoS)","volume":"12 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114255249","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 : 2019-10-01DOI: 10.1109/ICICoS48119.2019.8982424
Mutia Fadhila Putri, A. Hidayanto, E. S. Negara, N. Budi, P. Utari, Z. Abidin
The trend of mobile payment in Indonesia is rapidly growing since BI as Indonesia's central bank has initiated a movement called “Gerakan Nasional Non Tunai” (national cashless movement). this movement drove the emergence of several mobile payment systems, with GO-PAY from GO-JEK dominates the market. this paper aims to explore the motives of GO-PAY users in using gamification, as one of the loyalty programs, by using uses and gratification(U&G) perspectives. U&G perspectives was successfully implemented to identify the factors that effect on continuous intention to use a variety of media, but its application in mobile payment context is still limited. our results revealed three types of gratification that have significant impacts on user motivation to continue to use GO-PAY: hedonic gratification (perceived enjoyment and passing the time), utilitarian gratification (ease of use, self-presentation, information quality, and economic rewards), and social gratification (social value).
自BI以来，印尼的移动支付趋势迅速发展，因为印尼央行发起了一项名为“Gerakan Nasional Non Tunai”(全国无现金运动)的运动。这一运动推动了几个移动支付系统的出现，其中GO-JEK的GO-PAY主导了市场。本文旨在通过使用和满足(U&G)的视角，探讨GO-PAY用户使用游戏化这一忠诚计划的动机。U&G的观点被成功地用于识别影响持续使用各种媒体的因素，但其在移动支付环境中的应用仍然有限。我们的研究结果揭示了三种类型的满足对用户继续使用GO-PAY的动机有显著影响:享乐满足(感知到的享受和打发时间)、功利满足(易用性、自我呈现、信息质量和经济奖励)和社会满足(社会价值)。
{"title":"Gratification Sought in Gamification on Mobile Payment","authors":"Mutia Fadhila Putri, A. Hidayanto, E. S. Negara, N. Budi, P. Utari, Z. Abidin","doi":"10.1109/ICICoS48119.2019.8982424","DOIUrl":"https://doi.org/10.1109/ICICoS48119.2019.8982424","url":null,"abstract":"The trend of mobile payment in Indonesia is rapidly growing since BI as Indonesia's central bank has initiated a movement called “Gerakan Nasional Non Tunai” (national cashless movement). this movement drove the emergence of several mobile payment systems, with GO-PAY from GO-JEK dominates the market. this paper aims to explore the motives of GO-PAY users in using gamification, as one of the loyalty programs, by using uses and gratification(U&G) perspectives. U&G perspectives was successfully implemented to identify the factors that effect on continuous intention to use a variety of media, but its application in mobile payment context is still limited. our results revealed three types of gratification that have significant impacts on user motivation to continue to use GO-PAY: hedonic gratification (perceived enjoyment and passing the time), utilitarian gratification (ease of use, self-presentation, information quality, and economic rewards), and social gratification (social value).","PeriodicalId":105407,"journal":{"name":"2019 3rd International Conference on Informatics and Computational Sciences (ICICoS)","volume":"8 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130351360","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 : 2019-10-01DOI: 10.1109/ICICoS48119.2019.8982510
Emha Fathul Akmam, T. Siswantining, S. Soemartojo, Devvi Sarwinda
Missing data are condition when there are some missing values or empty entries on several observations on data. It could inhibit statistical analysis process and might give a bias conclusion from the analysis if couldn't be handled properly. This problem can be found on some linear regression analysis. One way to handle this problem is using multiple imputation (MI) method named Predictive Mean Matching (PMM). PMM will matching the predictive mean distance of incomplete observations with the complete observations. To get the multiple imputation concept, the predictive mean of incomplete observations were estimated by Bayesian approach while the complete observations were estimated with ordinary least square. Thus, the complete observation that has the closest distance will be a donor value for the incomplete one. Simulation data with two variable (x and y), univariate missing data pattern (on y), and MAR mechanism is used to analyzed the effectiveness of PMM based on relative efficiency estimation result of missing covariate data. Regression analysis used x as independent variable and y as dependent variable. The result showed that PMM give a significant coefficient regression parameter at 5% level of significance and only loss 1 % of relative efficiency.
{"title":"Multiple Imputation with Predictive Mean Matching Method for Numerical Missing Data","authors":"Emha Fathul Akmam, T. Siswantining, S. Soemartojo, Devvi Sarwinda","doi":"10.1109/ICICoS48119.2019.8982510","DOIUrl":"https://doi.org/10.1109/ICICoS48119.2019.8982510","url":null,"abstract":"Missing data are condition when there are some missing values or empty entries on several observations on data. It could inhibit statistical analysis process and might give a bias conclusion from the analysis if couldn't be handled properly. This problem can be found on some linear regression analysis. One way to handle this problem is using multiple imputation (MI) method named Predictive Mean Matching (PMM). PMM will matching the predictive mean distance of incomplete observations with the complete observations. To get the multiple imputation concept, the predictive mean of incomplete observations were estimated by Bayesian approach while the complete observations were estimated with ordinary least square. Thus, the complete observation that has the closest distance will be a donor value for the incomplete one. Simulation data with two variable (x and y), univariate missing data pattern (on y), and MAR mechanism is used to analyzed the effectiveness of PMM based on relative efficiency estimation result of missing covariate data. Regression analysis used x as independent variable and y as dependent variable. The result showed that PMM give a significant coefficient regression parameter at 5% level of significance and only loss 1 % of relative efficiency.","PeriodicalId":105407,"journal":{"name":"2019 3rd International Conference on Informatics and Computational Sciences (ICICoS)","volume":"14 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130019604","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 : 2019-10-01DOI: 10.1109/ICICoS48119.2019.8982442
Sonia Helena Ladasi, M. R. Shihab, A. Hidayanto, N. Budi
At present, manufacturing industry has the challenge of being able to manage the production chain to be responsive and quickly. In doing so, industry has tried to meet this need by adopting the latest technology of Internet of Things (IoT). This study aims to prioritize the determinants that influence the decision to adopt the Internet of Things technology in one of the agribusiness industries in Indonesia, namely PT. XYZ. This research model was built by combining two theories of information technology adoption, namely technology-organization-environment (TOE) and human-organization-technology (HOT -fit). The research model consists of four main criteria, namely human, technological, organizational, and environmental criteria with 20 factors spread across each criterion. Data collection was done using a questionnaire given to 12 decision makers of PT. XYZ. The data was processed by using Decision-Making Trial and Evaluation and Laboratory (DEMATEL) technique. The conclusion obtained from this study is that human factor becomes the most important criteria when compared to other main criteria. According to human factor, the innovation attitude of the leaders and technical skills of IT staff are the most important factors when compared to other factors. From the technological perspective, the IS / IT infrastructure as well as data security and privacy factors are the most important factors when compared to other factors. On the other side, top management support and perceived technology adoption costs are the most important factors from the perspective of organizational criteria. Finally, the perceived mimetic pressure factor and perceived coercive pressure are the most important factors in environmental perspective.
{"title":"Prioritizing Determinants of Internet of Things (IoT) Technology Adoption: Case Study of Agribusiness PT. XYZ","authors":"Sonia Helena Ladasi, M. R. Shihab, A. Hidayanto, N. Budi","doi":"10.1109/ICICoS48119.2019.8982442","DOIUrl":"https://doi.org/10.1109/ICICoS48119.2019.8982442","url":null,"abstract":"At present, manufacturing industry has the challenge of being able to manage the production chain to be responsive and quickly. In doing so, industry has tried to meet this need by adopting the latest technology of Internet of Things (IoT). This study aims to prioritize the determinants that influence the decision to adopt the Internet of Things technology in one of the agribusiness industries in Indonesia, namely PT. XYZ. This research model was built by combining two theories of information technology adoption, namely technology-organization-environment (TOE) and human-organization-technology (HOT -fit). The research model consists of four main criteria, namely human, technological, organizational, and environmental criteria with 20 factors spread across each criterion. Data collection was done using a questionnaire given to 12 decision makers of PT. XYZ. The data was processed by using Decision-Making Trial and Evaluation and Laboratory (DEMATEL) technique. The conclusion obtained from this study is that human factor becomes the most important criteria when compared to other main criteria. According to human factor, the innovation attitude of the leaders and technical skills of IT staff are the most important factors when compared to other factors. From the technological perspective, the IS / IT infrastructure as well as data security and privacy factors are the most important factors when compared to other factors. On the other side, top management support and perceived technology adoption costs are the most important factors from the perspective of organizational criteria. Finally, the perceived mimetic pressure factor and perceived coercive pressure are the most important factors in environmental perspective.","PeriodicalId":105407,"journal":{"name":"2019 3rd International Conference on Informatics and Computational Sciences (ICICoS)","volume":"197 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131747431","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 : 2019-10-01DOI: 10.1109/ICICoS48119.2019.8982432
Nahda Rosa Ramadhanti, Siti Mariyah
Most researches on text duplication in Bahasa uses the TF-IDF method. In this method, each word will have a different weight. The more frequencies the word appears, the greater the weight. This study aims to detect the similarity of documents by calculating cosine similarity from word vectors. The corpus was built from a collection of Indonesian Wikipedia articles. This study proposes two techniques to calculate the similarity which is simultaneous and partial comparison. Simultaneous comparison is direct comparison without dividing documents into several chapters, while partial comparison divides documents into several chapters before calculating the similarity. Similarity result from partial comparison is more accurate than simultaneous comparison. This study uses Unicheck application TF-IDF method as a benchmark. Similarity result from Unicheck and this study are different, due to the different method applied. Similarity result using TF -IDF method is smaller than using Word2vec, this is because TF-IDF can't detect paraphrase. The limitation in this study is that the Unicheck application used as a benchmark does not use the same method as the method used in this study other than that the determination of expected value is still subjective.
{"title":"Document Similarity Detection Using Indonesian Language Word2vec Model","authors":"Nahda Rosa Ramadhanti, Siti Mariyah","doi":"10.1109/ICICoS48119.2019.8982432","DOIUrl":"https://doi.org/10.1109/ICICoS48119.2019.8982432","url":null,"abstract":"Most researches on text duplication in Bahasa uses the TF-IDF method. In this method, each word will have a different weight. The more frequencies the word appears, the greater the weight. This study aims to detect the similarity of documents by calculating cosine similarity from word vectors. The corpus was built from a collection of Indonesian Wikipedia articles. This study proposes two techniques to calculate the similarity which is simultaneous and partial comparison. Simultaneous comparison is direct comparison without dividing documents into several chapters, while partial comparison divides documents into several chapters before calculating the similarity. Similarity result from partial comparison is more accurate than simultaneous comparison. This study uses Unicheck application TF-IDF method as a benchmark. Similarity result from Unicheck and this study are different, due to the different method applied. Similarity result using TF -IDF method is smaller than using Word2vec, this is because TF-IDF can't detect paraphrase. The limitation in this study is that the Unicheck application used as a benchmark does not use the same method as the method used in this study other than that the determination of expected value is still subjective.","PeriodicalId":105407,"journal":{"name":"2019 3rd International Conference on Informatics and Computational Sciences (ICICoS)","volume":"165 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131772869","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：