{"title":"Data Augmentations to Improve BERT-based Detection of Covid-19 Fake News on Twitter","authors":"Feby Dahlan, S. Suyanto","doi":"10.1109/ICCoSITE57641.2023.10127796","DOIUrl":"https://doi.org/10.1109/ICCoSITE57641.2023.10127796","url":null,"abstract":"Since Covid-19 has attacked the entire world, news about Covid-19 has been shared to reduce the impact of this outbreak. Social media, particularly Twitter, is a reliable source of information exchange. However, Covid-19 fake news is also being spread by irresponsible people to the public. This fact is so harmful to all parties. Hence, a fake news detector is required to tackle the problem. In this research, a Transformer-based fake news detection system is created. First, an architecture is designed using the Bidirectional Encoder Representations from Transformers (BERT). Three augmentation methods namely spell-checking-based, acronym-based, and typography-based augmentations are then developed to improve the BERT model. A comprehensive examination is performed based on 5-fold cross-validation using eleven thousand Twitter posts with four metrics: Accuracy, Precision, Recall, and F1-Score. Experimental results indicate that those three proposed augmentation methods can increase the BERT's performance detecting fake news related to Covid-19. The acronym-based augmentation gives a low improvement. Next, the spell-checking-based one provides a medium enhancement. Finally, the typography-based one offers the most significant improvement.","PeriodicalId":256184,"journal":{"name":"2023 International Conference on Computer Science, Information Technology and Engineering (ICCoSITE)","volume":"28 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-02-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"117147337","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}
{"title":"Control of Direct Current (DC) Output Voltage for Two Level DC/DC Boost Converter by Sliding Mode Controller in Application of Fuel Cell","authors":"Muhammad Izaaz Rozan, Moch. Rusli, M. A. Muslim","doi":"10.1109/ICCoSITE57641.2023.10127669","DOIUrl":"https://doi.org/10.1109/ICCoSITE57641.2023.10127669","url":null,"abstract":"This paper presents a Sliding Mode Controller (SMC) applied in Two Level DC/DC Boost Converter (TLBC) for Fuel Cell (FC) application. The purpose of this paper is to control the output voltage generated by TLBC with the input voltage supplied from FC. In its implementation, the SMC method is used because it is adaptive and nonlinear so it can produce a constant voltage output even though there is a varying voltage from FC. In general, the variation of output voltage from FC caused by V-I characteristics is that the output voltage value will decrease if the output current value increases. Besides that, SMC can also overcome the nonlinear nature of TLBC where the TLBC system works based on switching, so it has different equations with different conditions (on and off). The FC output voltage specification used as the TLBC input voltage is 250V, while the TLBC output voltage is 600V. Research conducted in this paper uses a simulation system with MATLAB/Simulink software in designing the entire system and displays research results in graphic form.","PeriodicalId":256184,"journal":{"name":"2023 International Conference on Computer Science, Information Technology and Engineering (ICCoSITE)","volume":"48 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-02-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123429478","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}
{"title":"Comparison of Human Emotion Classification on Single-Channel and Multi-Channel EEG using Gate Recurrent Unit Algorithm","authors":"Yuri Pamungkas, Ulfi Widya Astuti","doi":"10.1109/ICCoSITE57641.2023.10127686","DOIUrl":"https://doi.org/10.1109/ICCoSITE57641.2023.10127686","url":null,"abstract":"The use of EEG to recognize human emotions has become a notable trend and breakthrough today. EEG-based emotion recognition is a form of research that uses biomedical signals to distinguish a person's psychological condition (without directly paying attention to changes in facial gestures and attitudes). However, there are many studies related to emotion recognition whose classification accuracy is still low and needs to be improved. Therefore, we propose an EEG-based recognition of positive and negative emotions in this study using the Gate Recurrent Unit (GRU) algorithm. EEG data were taken from 38 participants with four recording channels (FP1, FP2, F7, and F8). In EEG recording, a video was played to stimulate the participants' emotions (positive and negative). Then, the EEG data is processed by filtering, artefact removal, frequency band decomposition, feature extraction, and emotion classification based on signal features. Several classification scenarios (such as by varying the activation function of the classifier and the number of EEG channels) are carried out to obtain an optimal level of accuracy. Based on the emotion classification results (using the Softmax activation function) on multi-channel EEG, the accuracy values reached 98.85% (for training) and 91.45% (for testing).","PeriodicalId":256184,"journal":{"name":"2023 International Conference on Computer Science, Information Technology and Engineering (ICCoSITE)","volume":"22 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-02-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125345683","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}
{"title":"Predicting Priority Time Patrol using Triple Exponential Smoothing and AHP","authors":"N. Nurhaeni, Azhari Sn, Agus Byna","doi":"10.1109/ICCoSITE57641.2023.10127709","DOIUrl":"https://doi.org/10.1109/ICCoSITE57641.2023.10127709","url":null,"abstract":"Prediction is a systematic process of determining what will happen in the future based on current historical data, which reduces inaccuracies. The purpose of this study is to predict the number of crimes in the future so that it can be used as a basis for decision support to determine time priorities for the police to carry out patrol duties. Researchers use Analytical Hierarchy Process (AHP) as one of the methods used to make decision support and Triple Exponential Smoothing as a method used to predict the number of crimes. The study's results used the Triple Exponential Smoothing method with a vulnerable time when the crime occurred at dawn, afternoon, evening, and night with an average accuracy of 63.60%. In the AHP method, the pairwise comparison assessment for each hierarchy consistently gives a CR value of less than 0.1. Thus, the priority of patrol time generated by the two methods is acceptable.","PeriodicalId":256184,"journal":{"name":"2023 International Conference on Computer Science, Information Technology and Engineering (ICCoSITE)","volume":"13 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-02-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126779995","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}
Muhammad Ichwandar Akrianto, Adhistya Erna Permanasari, Indriana Hidayah, M. Sholihin
{"title":"Analysis of Google Play Store's Sentiment Review on Waqf Digital Platform Using Fasttext Embedding","authors":"Muhammad Ichwandar Akrianto, Adhistya Erna Permanasari, Indriana Hidayah, M. Sholihin","doi":"10.1109/ICCoSITE57641.2023.10127810","DOIUrl":"https://doi.org/10.1109/ICCoSITE57641.2023.10127810","url":null,"abstract":"Waqf has an important role in the development and increase in welfare. In addition to reducing dependence on funds from the Indonesian government, waqf has also had a significant impact on reviving the economy, especially since the outbreak of the COVID-19 virus. The rapid advancement of technology has also transformed waqf, one of which is that people can donate waqf money online through several digital applications. But so far, several advantages and disadvantages are felt by application users. To make it easier to get information based on user experience, we propose to develop a model that can classify sentiments into positive, negative, and neutral automatically. Text classification using word embedding is the basis for getting the best performance results. Bag of Word (BOW) is a word embedding model that is often used, but this model is considered not optimal because it has disadvantages such as dependence on certain languages. Therefore, we suggest the fastText model minimizes dependency on pre-processing words and use 2 classification methods, namely SVM and KNN. This study aims to compare the performance results using the fastText model with conventional models that are often used, namely Bag of Word (BOW) and Term Frequency – Inverse Document Frequency (TF-IDF) to find the best accuracy value produced. Based on this research, it can be interpreted that in general, the fastText model can produce better performance than BOW and TF-IDF.","PeriodicalId":256184,"journal":{"name":"2023 International Conference on Computer Science, Information Technology and Engineering (ICCoSITE)","volume":"215 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-02-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114901158","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}
Y. Sari, Fajar Aina Rizky, I. Ranggadara, Nia Rahma Kurnianda, Ifan Prihandi, Suhendra
{"title":"Comparison of Feature Extraction to Test Dryness and Moisture Levels in Burned Restoration Areas Using Linear Discriminant Analysis","authors":"Y. Sari, Fajar Aina Rizky, I. Ranggadara, Nia Rahma Kurnianda, Ifan Prihandi, Suhendra","doi":"10.1109/ICCoSITE57641.2023.10127793","DOIUrl":"https://doi.org/10.1109/ICCoSITE57641.2023.10127793","url":null,"abstract":"The growth process after forest fires takes a long time because much land is often burned again, and some soils are less fertile. This research was conducted in Katingan, Central Kalimantan, as an area of interest. In this case, many human resources do not realize that they are trying to re-utilize the land that was burned by fires in that location. Land that has been burned should be rechecked a few months after the fire to see vegetation density. Using Landsat 8 OLI imagery to detect changes after the fire occurred, this research needs to compare feature extraction to test the level of dryness and humidity in the burnt restoration area. The feature extraction used is Normalized Difference Drought Index for drought detection and the Normalized Difference Moisture Index for detecting post-fire humidity. Furthermore, it will be tested using the Linear Discriminant Analysis algorithm to assess the classification of results from 1 June 2020 - 31 December 2020 in the area of interest carried out. The results of this research obtained for feature extraction NDDI has a lightness level with a range of 0.01 - 0.15 to 0.15 - 0.25, which indicates moderate to a severe drought that occurred in Katingan, Central Kalimantan, with a precision value of 98.33%, Recall 98.33% and Accuracy 98%. While NDMI has humidity in the range of 0.2 to - 0.4 to 0.4 to 0.6, which shows no growth to low growth with a precision value of 68.57%, Recall 68.57% and Accuracy 68% obtained.","PeriodicalId":256184,"journal":{"name":"2023 International Conference on Computer Science, Information Technology and Engineering (ICCoSITE)","volume":"16 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-02-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116234938","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}
{"title":"Project Management Performance Evaluation of Medical Oxygen Generator","authors":"M. Dachyar, Yudi Fernando Silalelo","doi":"10.1109/ICCoSITE57641.2023.10127737","DOIUrl":"https://doi.org/10.1109/ICCoSITE57641.2023.10127737","url":null,"abstract":"The need for easier and more affordable access to oxygen is still an obstacle in some parts of Indonesia, especially in the eastern part of Indonesia. A medical oxygen generator device can answer the problems related to the difficulty of accessing oxygen. There are frequent delays in the completion of the medical oxygen generator project, causing cost overruns and delays in providing first aid. The purpose of this study is to measure the performance of companies project management and provide suggestions for improvement strategies so that companies can improve their project performance. In this study, data collection was carried out by recapitulating some of the estimated project cost data, followed by compiling standard budgets for each project. Based on these two data, the company's project management performance is evaluated using Earned Value method with the CR as the indicator. The goal is to find the best strategies to improve the company’s project management performance based on our results. The proposed measurements provide the stages that have poor performance and then provide solutions for the company for each stage that have poor performance.","PeriodicalId":256184,"journal":{"name":"2023 International Conference on Computer Science, Information Technology and Engineering (ICCoSITE)","volume":"102 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-02-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"117294898","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}
Refa Septiansyah Mulyana, Asep Id Hadiana, Edvin Ramadhan
{"title":"Recommendation System Of Product Sales Ideas For MSMEs Using Content-based Filtering and Collaborative Filtering Methods","authors":"Refa Septiansyah Mulyana, Asep Id Hadiana, Edvin Ramadhan","doi":"10.1109/ICCoSITE57641.2023.10127844","DOIUrl":"https://doi.org/10.1109/ICCoSITE57641.2023.10127844","url":null,"abstract":"Looking for an idea to differentiate a product from other sellers is not easy. Sometimes sellers of MSME products need sales recommendations on what is trending among the public. A product recommendation can help users recommend a product that is interesting and needed by that user. Recommendation systems can help users come up with previously unknown or unthinkable information, which can directly aid user knowledge in their search results. In this research, a recommendation system will be built to search for product ideas. This study uses content-based filtering and collaborative filtering methods as well as the TF-IDF algorithm to assist users in recommending the products they are looking for to assist users in finding product-selling ideas they expect. Previous research has examined the recommendation system for Modern Musical Instrument Sales using the Simple Additive Weighing method but has the drawback that the weighting calculation must use fuzzy numbers. Therefore, the content-based and collaborative filtering methods are assisted by the TF-IDF algorithm used in this study to answer these problems. After implementation, we test accuracy by dividing the test data and training data differently. System testing is done by using a confusion matrix. The results that have been tested get an accuracy of 78%. Subsequent research suggests adding MSME product data in recommending product sales ideas to MSMEs so that recommendations are more optimal.","PeriodicalId":256184,"journal":{"name":"2023 International Conference on Computer Science, Information Technology and Engineering (ICCoSITE)","volume":"4 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-02-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128473521","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}
{"title":"Implementation of wild horse optimization (WHO) method for optimal hybrid renewable energy designs","authors":"Marliani, A. Arief, I. Gunadin","doi":"10.1109/ICCoSITE57641.2023.10127755","DOIUrl":"https://doi.org/10.1109/ICCoSITE57641.2023.10127755","url":null,"abstract":"The use of renewable energy has been widely applied worldwide to reduce fossil energy use. A hybrid electric power system based on renewable energy is one of the solutions to produce maximum energy. In this paper, the hybrid systems discussed include photovoltaic (PV), wind turbine (WT), and battery storage (BS). This hybrid design system is very dependent on the load profile, potential energy sources, and geographical location of the research location. This research shows the technical design and capital cost of a hybrid electric power system that will be implemented as an alternative energy source for practical work on the Soroako Technical Academy or Akademi Teknik Soroako (ATS) vocational campus. Irradiance, temperature, average wind speed, and component sizing are the main parameters for the design. The technical analysis and capital cost design use MATLAB software with the wild horse optimization (WHO) algorithm. The results of the WHO analysis will be compared with the HOMER application. The results showed that the WHO algorithm method is better than the HOMER application, with a capital cost of $ 198,363.05 with a total of 772 PV units, 1 unit of WT, and 54 battery units.","PeriodicalId":256184,"journal":{"name":"2023 International Conference on Computer Science, Information Technology and Engineering (ICCoSITE)","volume":"99 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-02-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124681457","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}
N. Kurniawan, Jacques, Muammar Azhim Tohepaly, A. Gui, M. S. Shaharudin, Y. Ganesan
{"title":"Information Security and the Quality of Online Loan Applications: A Societal Analysis","authors":"N. Kurniawan, Jacques, Muammar Azhim Tohepaly, A. Gui, M. S. Shaharudin, Y. Ganesan","doi":"10.1109/ICCoSITE57641.2023.10127698","DOIUrl":"https://doi.org/10.1109/ICCoSITE57641.2023.10127698","url":null,"abstract":"Online loan is viewed as an alternative to banking but easier and provide direct connection between public and loan offerer. However, online security threats and scam are undermining the quality of online loan. This study aims to determine how the public views their privacy while using online loan applications, perceived risk, perceived security, and qualities on intention to apply online loan. In order to examine the intention, a quantitative survey method was adopted and survey questionnaire was sent to the public who had experienced and apply for online loan applications. 153 responses were received and analysed using IBM SPSS version 28 for demographic analysis and SmartPLS 4 for model and structural measurements. Results show that perceived security, service quality and system quality were not critical to the respondents when choosing online loan applications while perceived risk, information sharing, and privacy concern were critical. This study shows that general public believed that security and quality are part of the package when organization offered a product or service. Interestingly, while privacy, risk, and information are important, public felt that it is the duty of organization to take care of their interests. Future research should look into behavioural aspects of public risk, information sharing, and privacy concern to understand in-depth.","PeriodicalId":256184,"journal":{"name":"2023 International Conference on Computer Science, Information Technology and Engineering (ICCoSITE)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-02-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129732505","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}