COVID-19 vaccine is a hot topic in online platforms due to the ongoing pandemic. Most studies on sentiment analysis of COVID-19 vaccines on Indonesian social media posts only used one or two classifiers with few modifications. This research investigated sentiment analysis using seven machine learning techniques on Twitter dataset in which the one with the highest evaluation value will be used to predict on other unlabeled Twitter datasets as well as news headlines dataset. The same classifier is also used to build a visualization dashboard that reflect the result of the sentiments. The result from the sentiment classification is then used to identify the topics, by using word cloud. The experiment revealed that SVM classifier has the highest accuracy and micro average F1-measure, which is 84% and 0.76. This classifier managed to capture similar patterns of sentiments in Twitter and news headlines datasets, which is dominated by neutral sentiment. Some of the topics from each sentiment, managed to reflect the real condition when the datasets were collected.
{"title":"Sentiment Analysis of COVID-19 Vaccines from Indonesian Tweets and News Headlines using Various Machine Learning Techniques","authors":"Retnani Latifah, Ridwan Baddalwan, Popy Meilina, Ambar Dwi Saputra, Yana Adharani","doi":"10.1109/ICIMCIS53775.2021.9699187","DOIUrl":"https://doi.org/10.1109/ICIMCIS53775.2021.9699187","url":null,"abstract":"COVID-19 vaccine is a hot topic in online platforms due to the ongoing pandemic. Most studies on sentiment analysis of COVID-19 vaccines on Indonesian social media posts only used one or two classifiers with few modifications. This research investigated sentiment analysis using seven machine learning techniques on Twitter dataset in which the one with the highest evaluation value will be used to predict on other unlabeled Twitter datasets as well as news headlines dataset. The same classifier is also used to build a visualization dashboard that reflect the result of the sentiments. The result from the sentiment classification is then used to identify the topics, by using word cloud. The experiment revealed that SVM classifier has the highest accuracy and micro average F1-measure, which is 84% and 0.76. This classifier managed to capture similar patterns of sentiments in Twitter and news headlines datasets, which is dominated by neutral sentiment. Some of the topics from each sentiment, managed to reflect the real condition when the datasets were collected.","PeriodicalId":250460,"journal":{"name":"2021 International Conference on Informatics, Multimedia, Cyber and Information System (ICIMCIS","volume":"11 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-10-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114901964","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 : 2021-10-28DOI: 10.1109/ICIMCIS53775.2021.9699268
Irzan Fajari Nurahmadan, Jayanta, I. W. W. Pradnyana
Taekwondo is a martial art from South Korea that has been developing in Indonesia since 1975 in North Jakarta. Since then, Taekwondo has become increasingly popular, and it can be seen when Taekwondo entered the official sport in the XI PON arena in 1985. Due to the popularity of Taekwondo, many instructors have built Taekwondo learning clubs throughout Indonesia. Not only that, the championship for Taekwondo has also increased rapidly in Indonesia. Due to many tournaments that are held, many Taekwondo clubs carry out intensive training to train young athletes to participate in the tournament. Still, the training is considered less than optimal due to the large number of students participating in the training, which makes the instructor pay less attention. To solve the problem, the author has an idea to build an independent learning system using the Pose Estimation method, which is used so that the computer can recognize Taekwondo movements and Multilayer Perceptron with Backpropagation learning which is used to predict Taekwondo movements, By utilizing Pose Estimation and Multilayer Perceptron, machine learning models can be built that can predict Taekwondo movements in real-time which can help Taekwondo students to learn independently from home. This study uses primary data obtained from the DAS (Dynamic Able Success) club, containing two kicks and two blocks. After conducting and evaluating a series of experiments, this study got the most optimal accuracy of 100%.
跆拳道是一种来自韩国的武术，自1975年在雅加达北部发展起来。由于跆拳道的普及，许多教练在印度尼西亚各地建立了跆拳道学习俱乐部。不仅如此，跆拳道锦标赛在印度尼西亚也迅速增加。由于举办的比赛很多，很多跆拳道俱乐部都进行强化训练，培养年轻运动员参加比赛。然而，由于参与培训的学生人数较多，使得教师的注意力较少，因此培训被认为不是最优的。为了解决这一问题，作者想到利用姿态估计方法构建一个独立的学习系统，使计算机能够识别跆拳道的动作，并利用反向传播学习的多层感知器来预测跆拳道的动作。可以建立机器学习模型，实时预测跆拳道动作，帮助跆拳道学生在家独立学习。本研究使用了从DAS (Dynamic Able Success)俱乐部获得的主要数据，包含两个踢腿和两个block。经过一系列实验的进行和评估，本研究获得了100%的最优准确率。
{"title":"Utilization of Pose Estimation and Multilayer Perceptron Methods in the Development of Taekwondo Martial Arts Independent Learning","authors":"Irzan Fajari Nurahmadan, Jayanta, I. W. W. Pradnyana","doi":"10.1109/ICIMCIS53775.2021.9699268","DOIUrl":"https://doi.org/10.1109/ICIMCIS53775.2021.9699268","url":null,"abstract":"Taekwondo is a martial art from South Korea that has been developing in Indonesia since 1975 in North Jakarta. Since then, Taekwondo has become increasingly popular, and it can be seen when Taekwondo entered the official sport in the XI PON arena in 1985. Due to the popularity of Taekwondo, many instructors have built Taekwondo learning clubs throughout Indonesia. Not only that, the championship for Taekwondo has also increased rapidly in Indonesia. Due to many tournaments that are held, many Taekwondo clubs carry out intensive training to train young athletes to participate in the tournament. Still, the training is considered less than optimal due to the large number of students participating in the training, which makes the instructor pay less attention. To solve the problem, the author has an idea to build an independent learning system using the Pose Estimation method, which is used so that the computer can recognize Taekwondo movements and Multilayer Perceptron with Backpropagation learning which is used to predict Taekwondo movements, By utilizing Pose Estimation and Multilayer Perceptron, machine learning models can be built that can predict Taekwondo movements in real-time which can help Taekwondo students to learn independently from home. This study uses primary data obtained from the DAS (Dynamic Able Success) club, containing two kicks and two blocks. After conducting and evaluating a series of experiments, this study got the most optimal accuracy of 100%.","PeriodicalId":250460,"journal":{"name":"2021 International Conference on Informatics, Multimedia, Cyber and Information System (ICIMCIS","volume":"26 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-10-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123487165","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 : 2021-10-28DOI: 10.1109/ICIMCIS53775.2021.9699380
Rahmat Novrianda Dasmen, Kraugusteeliana, Rasmila
PT. Thamrin Group Palembang is one of the dealers that sells two-wheeled motor vehicles with the Yamaha brand. Currently, consumer interest in Yamaha Motorcycles is increasing so that it is not uncommon for consumers to have a pivot system to get the Yamaha Motor they want, which is because the available Yamaha Motor unit stock does not meet the buyer's demand. This happened because PT. Thamrin Group Palembang has difficulty in determining the stock needs of Yamaha Motor units for the following years, which is also influenced by sales data that changes from time to time. Therefore, in this study, the trend moment method was applied to be able to determine forecasts or predictions for the future needs of Yamaha motorcycle units. The trend moment method requires sales data from 2 years back and then forecasting calculations are carried out using the formulas from the trend moment method. In addition, as a development of previous research related to the trend moment method, researchers built an information system that can be used to simplify and shorten the time in doing forecasting or prediction calculations. In this study, samples were taken of sales data for the Yamaha Mio M3 125 R from 2019 to 2020 to predict the need for the Yamaha Mio M3 125 R motorcycle unit in January 2021. It can be seen from the results obtained in the manual calculation of the trend moment forecasting that can be displayed on the web-based system that has been built in this research, which shows the prediction results of the needs of the Yamaha Mio M3 125 R motorcycle unit in January. 2021 as many as 26 units.
PT. Thamrin Group Palembang是销售雅马哈品牌两轮汽车的经销商之一。目前，消费者对雅马哈摩托车的兴趣正在增加，因此，对于消费者来说，有一个支点系统来获得他们想要的雅马哈摩托车并不罕见，这是因为可用的雅马哈摩托车单位库存不满足买方的需求。这是因为PT. Thamrin Group Palembang难以确定雅马哈汽车未来几年的库存需求，这也受到不时变化的销售数据的影响。因此，在本研究中，采用趋势矩法来确定对雅马哈摩托车单元未来需求的预测或预测。趋势矩法需要2年前的销售数据，然后使用趋势矩法中的公式进行预测计算。此外，作为以往趋势矩法相关研究的发展，研究人员建立了一个信息系统，可以简化和缩短预测或预测计算的时间。在本研究中，采集了2019年至2020年雅马哈Mio M3 125 R的销售数据样本，以预测2021年1月雅马哈Mio M3 125 R摩托车单元的需求。从人工计算趋势矩预测得到的结果可以看出，在本研究建立的基于web的系统上可以显示趋势矩预测结果，其中显示了2021年1月雅马哈Mio M3 125 R摩托车机组需求的预测结果多达26台。
{"title":"Trend Moment Implementation in Forecasting Vehicle Sales at PT. Thamrin Group Palembang","authors":"Rahmat Novrianda Dasmen, Kraugusteeliana, Rasmila","doi":"10.1109/ICIMCIS53775.2021.9699380","DOIUrl":"https://doi.org/10.1109/ICIMCIS53775.2021.9699380","url":null,"abstract":"PT. Thamrin Group Palembang is one of the dealers that sells two-wheeled motor vehicles with the Yamaha brand. Currently, consumer interest in Yamaha Motorcycles is increasing so that it is not uncommon for consumers to have a pivot system to get the Yamaha Motor they want, which is because the available Yamaha Motor unit stock does not meet the buyer's demand. This happened because PT. Thamrin Group Palembang has difficulty in determining the stock needs of Yamaha Motor units for the following years, which is also influenced by sales data that changes from time to time. Therefore, in this study, the trend moment method was applied to be able to determine forecasts or predictions for the future needs of Yamaha motorcycle units. The trend moment method requires sales data from 2 years back and then forecasting calculations are carried out using the formulas from the trend moment method. In addition, as a development of previous research related to the trend moment method, researchers built an information system that can be used to simplify and shorten the time in doing forecasting or prediction calculations. In this study, samples were taken of sales data for the Yamaha Mio M3 125 R from 2019 to 2020 to predict the need for the Yamaha Mio M3 125 R motorcycle unit in January 2021. It can be seen from the results obtained in the manual calculation of the trend moment forecasting that can be displayed on the web-based system that has been built in this research, which shows the prediction results of the needs of the Yamaha Mio M3 125 R motorcycle unit in January. 2021 as many as 26 units.","PeriodicalId":250460,"journal":{"name":"2021 International Conference on Informatics, Multimedia, Cyber and Information System (ICIMCIS","volume":"55 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-10-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131562681","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 : 2021-10-28DOI: 10.1109/ICIMCIS53775.2021.9699136
Eric Zenas Kurniawan, Grant Denov M. Tobing, Nabil Naratama, Adilla Anggraeni
Developments in information and communication technologies disrupt the traditional media ecosystem. New media has led to the emergence of many digital platforms such as SVoD. SVoD has become very popular nowadays all over the world. Therefore, this paper aims to reveal the determinants of intention to use SVoD based on the technology acceptance model, The design of this study was a quantitative method using non-probability convenience sampling that tested 90 usable respondents that fit the sample criteria for Structural Equation Model (SEM) through smart-PLS. From the result earned from Path Coefficients, we discovered that knowledge, self-efficacy, perceived ease of use, attitude, and compatibility affect the continuance intention to keep using the SVoD. However, in this study, the perceived usefulness variable did not have any impact on the continuance intention to use SVoD.
{"title":"The Factors Influencing Millennials' Continuance Intention to Use Subscription Video-on-Demand (SVoD) in Jakarta","authors":"Eric Zenas Kurniawan, Grant Denov M. Tobing, Nabil Naratama, Adilla Anggraeni","doi":"10.1109/ICIMCIS53775.2021.9699136","DOIUrl":"https://doi.org/10.1109/ICIMCIS53775.2021.9699136","url":null,"abstract":"Developments in information and communication technologies disrupt the traditional media ecosystem. New media has led to the emergence of many digital platforms such as SVoD. SVoD has become very popular nowadays all over the world. Therefore, this paper aims to reveal the determinants of intention to use SVoD based on the technology acceptance model, The design of this study was a quantitative method using non-probability convenience sampling that tested 90 usable respondents that fit the sample criteria for Structural Equation Model (SEM) through smart-PLS. From the result earned from Path Coefficients, we discovered that knowledge, self-efficacy, perceived ease of use, attitude, and compatibility affect the continuance intention to keep using the SVoD. However, in this study, the perceived usefulness variable did not have any impact on the continuance intention to use SVoD.","PeriodicalId":250460,"journal":{"name":"2021 International Conference on Informatics, Multimedia, Cyber and Information System (ICIMCIS","volume":"29 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-10-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131900555","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 : 2021-10-28DOI: 10.1109/ICIMCIS53775.2021.9699176
Deny Haryadi, Demi Adidrana
Palm oil is one of the plantation products that becomes the export of Indonesia's leading commodity. The volume of palm oil exports tends to increase every year. This is influenced by the large demand for palm oil in palm oil importing countries in the world. The high demand for palm oil is an opportunity that must be developed so that Indonesia can compete with its competitors in the current pandemic. Indonesia as the world's largest palm oil producer must be able to group the countries that are priority as the largest importers of palm oil. For this reason, it is necessary to group the countries that are a priority as the largest importer of palm oil. The purpose of this study is to group palm oil exports based on the destination country using the K-Medoids Clustering algorithm. Based on the results of tests that have been conducted in this study using the K-Medoids Clustering algorithm, Cluster 1 is a category of countries importing low palm oil or Low, namely 7 (Netherlands, USA, Spain, Egypt, Bangladesh, Italy, Singapore) of 10 categories of countries tested, then cluster 2 is a category of countries importing medium palm oil or Medium which is 1 (Pakistan) of 10 categories of countries tested, and lastly cluster 3 is a category of high palm oil importing countries or High which is 2 (India and China) from 10 categories of countries tested.
{"title":"Implementation of K-Medoids Clustering Algorithm for Grouping Palm Oil Exports by Destination Country","authors":"Deny Haryadi, Demi Adidrana","doi":"10.1109/ICIMCIS53775.2021.9699176","DOIUrl":"https://doi.org/10.1109/ICIMCIS53775.2021.9699176","url":null,"abstract":"Palm oil is one of the plantation products that becomes the export of Indonesia's leading commodity. The volume of palm oil exports tends to increase every year. This is influenced by the large demand for palm oil in palm oil importing countries in the world. The high demand for palm oil is an opportunity that must be developed so that Indonesia can compete with its competitors in the current pandemic. Indonesia as the world's largest palm oil producer must be able to group the countries that are priority as the largest importers of palm oil. For this reason, it is necessary to group the countries that are a priority as the largest importer of palm oil. The purpose of this study is to group palm oil exports based on the destination country using the K-Medoids Clustering algorithm. Based on the results of tests that have been conducted in this study using the K-Medoids Clustering algorithm, Cluster 1 is a category of countries importing low palm oil or Low, namely 7 (Netherlands, USA, Spain, Egypt, Bangladesh, Italy, Singapore) of 10 categories of countries tested, then cluster 2 is a category of countries importing medium palm oil or Medium which is 1 (Pakistan) of 10 categories of countries tested, and lastly cluster 3 is a category of high palm oil importing countries or High which is 2 (India and China) from 10 categories of countries tested.","PeriodicalId":250460,"journal":{"name":"2021 International Conference on Informatics, Multimedia, Cyber and Information System (ICIMCIS","volume":"65 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-10-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132750648","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 : 2021-10-28DOI: 10.1109/ICIMCIS53775.2021.9699248
W. Aditya, Girinoto, R. B. Hadiprakoso, Adam Waluyo
Malware attacks and the growth of new types of malwares are things for government and industry departments to consider. More and more types of malware attacks require preventative measures using deep learning for malware analysis to minimize the impact of malware attacks. In this case, the task of the cyber-attack detection team of the National Cybersecurity and Encryption Agency Threat Detection Agency is to perform malware analysis. This research implemented malware detection and classification using a deep learning model by leveraging a sequence of API calls. The learning model is built with two different recurrent neural network architectures, LSTM and GRU for comparison. The architecture comparison shows that LSTM is better than GRU. The test results show that the accuracy rates of the learning model using the LSTM architecture in binary classification and multiple class classification are 97.3% and 56.05%, respectively. In this study, we aim to build classification platform to classify malware using the classification model that has been made and enhancing the dataset by merging and update new data. The classification model testing result shown that 146 samples were correctly predicted, with an accuracy rate of 96.8%
{"title":"Deep Learning for Malware Classification Platform using Windows API Call Sequence","authors":"W. Aditya, Girinoto, R. B. Hadiprakoso, Adam Waluyo","doi":"10.1109/ICIMCIS53775.2021.9699248","DOIUrl":"https://doi.org/10.1109/ICIMCIS53775.2021.9699248","url":null,"abstract":"Malware attacks and the growth of new types of malwares are things for government and industry departments to consider. More and more types of malware attacks require preventative measures using deep learning for malware analysis to minimize the impact of malware attacks. In this case, the task of the cyber-attack detection team of the National Cybersecurity and Encryption Agency Threat Detection Agency is to perform malware analysis. This research implemented malware detection and classification using a deep learning model by leveraging a sequence of API calls. The learning model is built with two different recurrent neural network architectures, LSTM and GRU for comparison. The architecture comparison shows that LSTM is better than GRU. The test results show that the accuracy rates of the learning model using the LSTM architecture in binary classification and multiple class classification are 97.3% and 56.05%, respectively. In this study, we aim to build classification platform to classify malware using the classification model that has been made and enhancing the dataset by merging and update new data. The classification model testing result shown that 146 samples were correctly predicted, with an accuracy rate of 96.8%","PeriodicalId":250460,"journal":{"name":"2021 International Conference on Informatics, Multimedia, Cyber and Information System (ICIMCIS","volume":"605 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-10-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123941045","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 : 2021-10-28DOI: 10.1109/ICIMCIS53775.2021.9699316
Muhamad Efendi, T. Raharjo, Agus Suhanto
Application development has progressed along with the rapid digital transformation. The stakeholders will focus more on cutting operational costs with optimal application quality and security. The DevSecOps approach provides solutions for reducing costs in the software life cycle, increasing software product quality and security. Public Company Logistic Agency (PCLA) is like other companies that must be adaptive to new technology. PCLA has an IT Division in charge of providing technology to support business. Application development by the IT Division has several problems, including application projects that mostly exceed the time, significant changes and additions during UAT, and applications that have much vulnerability. A transformation to the DevSecOps approach is needed to address these problems. In this paper, a Systematic Literature Review (SLR) was used to select journals that matched the study topic to obtain the character and transformation phases of DevSecOps in various case studies. A mixed-method approach aims to collect and analyze data companies in the software development lifecycle. For academicians, this study provides a new understanding of application development in a state-owned enterprise based on a sequential approach and their suitable solutions from the DevSecOps approach. For practitioners, the findings provide potential lessons learned and guide a state-owned enterprise to transform to the DevSecOps approach.
随着数字化转型的快速发展，应用程序开发也在不断进步。涉众将更多地关注通过优化应用程序质量和安全性来削减运营成本。DevSecOps方法提供了降低软件生命周期成本、提高软件产品质量和安全性的解决方案。上市公司物流代理(PCLA)与其他公司一样，必须适应新技术。PCLA有一个IT部门负责提供技术支持业务。IT部门的应用程序开发存在几个问题，包括应用程序项目大多超过时间，在UAT期间进行重大更改和添加，以及应用程序存在许多漏洞。要解决这些问题，需要向DevSecOps方法进行转换。本文采用系统文献综述法(Systematic Literature Review, SLR)，选择与研究主题相匹配的期刊，获得DevSecOps在不同案例中的特征和转变阶段。混合方法的目的是收集和分析软件开发生命周期中的数据公司。对于学者来说，本研究提供了对基于顺序方法的国有企业应用程序开发的新理解，以及DevSecOps方法的合适解决方案。对于从业者来说，这些发现提供了潜在的经验教训，并指导国有企业向DevSecOps方法转变。
{"title":"DevSecOps Approach in Software Development Case Study: Public Company Logistic Agency","authors":"Muhamad Efendi, T. Raharjo, Agus Suhanto","doi":"10.1109/ICIMCIS53775.2021.9699316","DOIUrl":"https://doi.org/10.1109/ICIMCIS53775.2021.9699316","url":null,"abstract":"Application development has progressed along with the rapid digital transformation. The stakeholders will focus more on cutting operational costs with optimal application quality and security. The DevSecOps approach provides solutions for reducing costs in the software life cycle, increasing software product quality and security. Public Company Logistic Agency (PCLA) is like other companies that must be adaptive to new technology. PCLA has an IT Division in charge of providing technology to support business. Application development by the IT Division has several problems, including application projects that mostly exceed the time, significant changes and additions during UAT, and applications that have much vulnerability. A transformation to the DevSecOps approach is needed to address these problems. In this paper, a Systematic Literature Review (SLR) was used to select journals that matched the study topic to obtain the character and transformation phases of DevSecOps in various case studies. A mixed-method approach aims to collect and analyze data companies in the software development lifecycle. For academicians, this study provides a new understanding of application development in a state-owned enterprise based on a sequential approach and their suitable solutions from the DevSecOps approach. For practitioners, the findings provide potential lessons learned and guide a state-owned enterprise to transform to the DevSecOps approach.","PeriodicalId":250460,"journal":{"name":"2021 International Conference on Informatics, Multimedia, Cyber and Information System (ICIMCIS","volume":"29 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-10-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121923284","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 : 2021-10-28DOI: 10.1109/ICIMCIS53775.2021.9699161
Irzan Fajari Nurahmadan, R. Arjuna, Herlambang Dwi Prasetyo, Pandu Ananto Hogantara, Ika Nurlaili Isnainiyah, Rio Wirawan
In Indonesia, waste is a very serious problem. According to research in handling and processing waste is classified into three types, namely recyclable, nonorganic, and organic waste. Organic and inorganic waste will generally be transported and stockpiled at the Final Disposal Site (TPA). So far, the only available waste bins are waste bins with manual sorting done by the community. As it is known that currently there are many people who do not understand the different types of waste to be disposed of, so that even though organic and inorganic types of waste have been provided, people still dispose of waste in inappropriate types. This of course will be very inconvenient in the effort to sort waste in the waste whereas the first place for garbage to gather. Because of the need for a tool that can help the community in distinguishing the types of waste before putting it into the waste with an accurate classification method Based on the problems in classifying the types of waste that have been described previously, we need a system that is able to classify waste according to its type, The MobileNets-V1 architecture is used in this research to classify images. The models generated by the architecture will then be deployed into mobile-based applications. The dataset used in this study consists of 3 classes, namely N (Non-Recyclable), O (Organic), R (Recyclable). Because the data is highly imbalanced, we conduct undersampling in order to balance the data. This undersampling process is done only in the training set after splitting the whole dataset into training, validation, and testing set. After the balancing process, each class has 1822 sample data, totalling of 5466 sample data in the trianing set. The pretrained MobileNets-V1 model is able to classify types of waste very well. The best model obtained is a model that uses dropout value of 0.4 which provides testing accuracy of 88.26%, training accuracy of 92.44% and validation accuracy of 89.00%.
{"title":"A Mobile Based Waste Classification Using MobileNets-V1 Architecture","authors":"Irzan Fajari Nurahmadan, R. Arjuna, Herlambang Dwi Prasetyo, Pandu Ananto Hogantara, Ika Nurlaili Isnainiyah, Rio Wirawan","doi":"10.1109/ICIMCIS53775.2021.9699161","DOIUrl":"https://doi.org/10.1109/ICIMCIS53775.2021.9699161","url":null,"abstract":"In Indonesia, waste is a very serious problem. According to research in handling and processing waste is classified into three types, namely recyclable, nonorganic, and organic waste. Organic and inorganic waste will generally be transported and stockpiled at the Final Disposal Site (TPA). So far, the only available waste bins are waste bins with manual sorting done by the community. As it is known that currently there are many people who do not understand the different types of waste to be disposed of, so that even though organic and inorganic types of waste have been provided, people still dispose of waste in inappropriate types. This of course will be very inconvenient in the effort to sort waste in the waste whereas the first place for garbage to gather. Because of the need for a tool that can help the community in distinguishing the types of waste before putting it into the waste with an accurate classification method Based on the problems in classifying the types of waste that have been described previously, we need a system that is able to classify waste according to its type, The MobileNets-V1 architecture is used in this research to classify images. The models generated by the architecture will then be deployed into mobile-based applications. The dataset used in this study consists of 3 classes, namely N (Non-Recyclable), O (Organic), R (Recyclable). Because the data is highly imbalanced, we conduct undersampling in order to balance the data. This undersampling process is done only in the training set after splitting the whole dataset into training, validation, and testing set. After the balancing process, each class has 1822 sample data, totalling of 5466 sample data in the trianing set. The pretrained MobileNets-V1 model is able to classify types of waste very well. The best model obtained is a model that uses dropout value of 0.4 which provides testing accuracy of 88.26%, training accuracy of 92.44% and validation accuracy of 89.00%.","PeriodicalId":250460,"journal":{"name":"2021 International Conference on Informatics, Multimedia, Cyber and Information System (ICIMCIS","volume":"36 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-10-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128028651","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 : 2021-10-28DOI: 10.1109/ICIMCIS53775.2021.9699129
Herlambang Permadi, D. I. Sensuse
The Knowledge Management (KM) implementation has become an important tool for the government in achieving the macro-goals of a country. KM is an important means of utilizing existing knowledge into social, business, and economic benefits also investments for the government of a country. The purpose of this study is to determine how knowledge management has been implemented by the government in various countries so that it can become a knowledge adoption for the other country's governments in managing knowledge. For this purpose, a systematic literature review was conducted to summarize the use of knowledge management in various countries in the last 6 (six) years. From the literature, we found that the level of knowledge management implementation in various countries has many diversities, even though it has experienced a significant increase since 2015. The method that was used in this research is Systematic Literature Review. The researcher also found that the attention to knowledge management is still dominated by public service institutions. Comparison results found that the government organizations do not have yet effective knowledge management systems to provide public services.
{"title":"Measuring Knowledge Management System Utilization by Government in Various Countries","authors":"Herlambang Permadi, D. I. Sensuse","doi":"10.1109/ICIMCIS53775.2021.9699129","DOIUrl":"https://doi.org/10.1109/ICIMCIS53775.2021.9699129","url":null,"abstract":"The Knowledge Management (KM) implementation has become an important tool for the government in achieving the macro-goals of a country. KM is an important means of utilizing existing knowledge into social, business, and economic benefits also investments for the government of a country. The purpose of this study is to determine how knowledge management has been implemented by the government in various countries so that it can become a knowledge adoption for the other country's governments in managing knowledge. For this purpose, a systematic literature review was conducted to summarize the use of knowledge management in various countries in the last 6 (six) years. From the literature, we found that the level of knowledge management implementation in various countries has many diversities, even though it has experienced a significant increase since 2015. The method that was used in this research is Systematic Literature Review. The researcher also found that the attention to knowledge management is still dominated by public service institutions. Comparison results found that the government organizations do not have yet effective knowledge management systems to provide public services.","PeriodicalId":250460,"journal":{"name":"2021 International Conference on Informatics, Multimedia, Cyber and Information System (ICIMCIS","volume":"54 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-10-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128969887","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 : 2021-10-28DOI: 10.1109/ICIMCIS53775.2021.9699114
Darrel Matthew, Garry R. Hellianto, Niko S. Putra, A. M. Sundjaja
This study aims to examine the determinant factors of e-commerce repurchase intention. The research design is a quantitative model. The sample size is 206 respondents, using purposive sampling. The respondents are Shopee e-commerce users in Indonesia. The data processing technique used is a linear regression model and processed using Statistical Package for the Social Sciences (SPSS) software for Windows version 25. The results of this study indicate that sales promotion and user interface influence consumer repurchase intention. The user interface is the variable with the most significant influence. Thus, to increase buyer visits and transactions on e-commerce, the user interface can be an essential input for developing e-commerce.
{"title":"The Effect of Monthly Promotion, Gamification, User Interface Usability & Attractiveness on the Marketplace Repurchase Intention","authors":"Darrel Matthew, Garry R. Hellianto, Niko S. Putra, A. M. Sundjaja","doi":"10.1109/ICIMCIS53775.2021.9699114","DOIUrl":"https://doi.org/10.1109/ICIMCIS53775.2021.9699114","url":null,"abstract":"This study aims to examine the determinant factors of e-commerce repurchase intention. The research design is a quantitative model. The sample size is 206 respondents, using purposive sampling. The respondents are Shopee e-commerce users in Indonesia. The data processing technique used is a linear regression model and processed using Statistical Package for the Social Sciences (SPSS) software for Windows version 25. The results of this study indicate that sales promotion and user interface influence consumer repurchase intention. The user interface is the variable with the most significant influence. Thus, to increase buyer visits and transactions on e-commerce, the user interface can be an essential input for developing e-commerce.","PeriodicalId":250460,"journal":{"name":"2021 International Conference on Informatics, Multimedia, Cyber and Information System (ICIMCIS","volume":"33 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-10-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129773016","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：