Pub Date : 2023-11-17DOI: 10.30595/juita.v11i2.17446
Laradea Marifni, Made Sumertajaya, U. Syafitri
Biclustering is a method of grouping numerical data where rows and columns are grouped simultaneously. The Cheng and Church (CC) algorithm is one of the bi-clustering algorithms that try to find the maximum bi-cluster with a high similarity value, called MSR (Mean Square Residue). The association of rows and columns is called a bi-cluster if the MSR is lower than a predetermined threshold value (delta). Detection of people's welfare in Indonesia using Bi-Clustering is essential to get an overview of the characteristics of people's interest in each province in Indonesia. Bi-Clustering using the CC algorithm requires a threshold value (delta) determined by finding the MSR value of the actual data. The threshold value (delta) must be smaller than the MSR of the actual data. This study's threshold values are 0.1, 0.2, 0.3, 0.4, 0.5, 0.6, 0.7, and 0.8. After evaluating the optimum delta by considering the MSR value and the bi-cluster formed, the optimum delta is obtained as 0.1, with the number of bi-cluster included as 4.
{"title":"Bicluster Analysis of Cheng and Church's Algorithm to Identify Patterns of People's Welfare in Indonesia","authors":"Laradea Marifni, Made Sumertajaya, U. Syafitri","doi":"10.30595/juita.v11i2.17446","DOIUrl":"https://doi.org/10.30595/juita.v11i2.17446","url":null,"abstract":"Biclustering is a method of grouping numerical data where rows and columns are grouped simultaneously. The Cheng and Church (CC) algorithm is one of the bi-clustering algorithms that try to find the maximum bi-cluster with a high similarity value, called MSR (Mean Square Residue). The association of rows and columns is called a bi-cluster if the MSR is lower than a predetermined threshold value (delta). Detection of people's welfare in Indonesia using Bi-Clustering is essential to get an overview of the characteristics of people's interest in each province in Indonesia. Bi-Clustering using the CC algorithm requires a threshold value (delta) determined by finding the MSR value of the actual data. The threshold value (delta) must be smaller than the MSR of the actual data. This study's threshold values are 0.1, 0.2, 0.3, 0.4, 0.5, 0.6, 0.7, and 0.8. After evaluating the optimum delta by considering the MSR value and the bi-cluster formed, the optimum delta is obtained as 0.1, with the number of bi-cluster included as 4.","PeriodicalId":151254,"journal":{"name":"JUITA : Jurnal Informatika","volume":"13 5","pages":""},"PeriodicalIF":0.0,"publicationDate":"2023-11-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"139264315","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}
Sakinah Mart is a retail business that focuses on determining the layout of goods based on perceptions and implementing a discount system for specific items, but without offering bundling packages. This research aims to provide recommendations using the apriori algorithm as a decision-making tool for analyzing the layout of goods and bundling packages. The apriori algorithm is a data mining technique used to discover association rules and analyze customer purchases, specifically identifying the likelihood of customers buying item X along with item Y. The algorithm consists of two main components: support and confidence. The research applies the Cross-Industry Standard Process for Data Mining (CRISP-DM) method, utilizing the apriori algorithm to analyze sales transaction data. The dataset includes 2000 sales transactions with two attributes, resulting in the identification of 2 and 3 itemsets. The findings include 16 rules with a minimum support value of 42% and a minimum confidence of 85% for the layout of goods. For bundling packages, 5 rules with a minimum support value of 40% and a minimum confidence of 90% were generated. These results offer valuable recommendations to the company, using the apriori algorithm for analyzing the layout of goods and bundling packages.
Sakinah Mart 是一家零售企业，其业务重点是根据感知确定商品布局，并针对特定商品实施折扣制度，但不提供捆绑套餐。本研究旨在使用 apriori 算法作为决策工具，为分析商品布局和捆绑套餐提供建议。apriori 算法是一种数据挖掘技术，用于发现关联规则和分析客户购买情况，特别是识别客户在购买商品 Y 的同时购买商品 X 的可能性。研究采用跨行业数据挖掘标准流程（CRISP-DM）方法，利用 apriori 算法分析销售交易数据。数据集包括 2000 个带有两个属性的销售交易，从而识别出 2 个和 3 个项目集。研究结果包括：在商品布局方面，16 条规则的最小支持值为 42%，最小置信度为 85%。对于捆绑包装，产生了 5 条规则，最小支持值为 40%，最小置信度为 90%。这些结果为公司使用 apriori 算法分析货物布局和捆绑包装提供了有价值的建议。
{"title":"Analysis and Implementation of the Apriori Algorithm for Strategies to Increase Sales at Sakinah Mart","authors":"Karisma Dwi Fernanda, Arifin Puji Widodo, Julianto Lemantara","doi":"10.30595/juita.v11i2.17341","DOIUrl":"https://doi.org/10.30595/juita.v11i2.17341","url":null,"abstract":"Sakinah Mart is a retail business that focuses on determining the layout of goods based on perceptions and implementing a discount system for specific items, but without offering bundling packages. This research aims to provide recommendations using the apriori algorithm as a decision-making tool for analyzing the layout of goods and bundling packages. The apriori algorithm is a data mining technique used to discover association rules and analyze customer purchases, specifically identifying the likelihood of customers buying item X along with item Y. The algorithm consists of two main components: support and confidence. The research applies the Cross-Industry Standard Process for Data Mining (CRISP-DM) method, utilizing the apriori algorithm to analyze sales transaction data. The dataset includes 2000 sales transactions with two attributes, resulting in the identification of 2 and 3 itemsets. The findings include 16 rules with a minimum support value of 42% and a minimum confidence of 85% for the layout of goods. For bundling packages, 5 rules with a minimum support value of 40% and a minimum confidence of 90% were generated. These results offer valuable recommendations to the company, using the apriori algorithm for analyzing the layout of goods and bundling packages.","PeriodicalId":151254,"journal":{"name":"JUITA : Jurnal Informatika","volume":"48 4","pages":""},"PeriodicalIF":0.0,"publicationDate":"2023-11-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"139264413","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 : 2023-11-17DOI: 10.30595/juita.v11i2.17424
Siti Izati Nabila, Ami Anggraini Samudra, Irsyadunas Irsyadunas
Major is one of the important factors in the world of lectures. Along with the increasing need for knowledge and skills required in the world of work, increasing the number of majors offered by tertiary institutions. The number of considerations from prospective students regarding the selection of majors causes students to be confused in determining the best major they will choose to continue their education. The research aims to design an expert system-based website that will be used to provide major recommendations. The method to be used is the forward chaining method, where this method works by matching data based on predetermined facts, then obtaining results based on matching the data. Based on the black box testing that has been done, the results show that the designed expert system is by the expected functionality. Therefore this expert system can be said to be feasible to use.
{"title":"Sikarju: Expert System of Major Recommendation to Increase the Chances of Being Accepted by University","authors":"Siti Izati Nabila, Ami Anggraini Samudra, Irsyadunas Irsyadunas","doi":"10.30595/juita.v11i2.17424","DOIUrl":"https://doi.org/10.30595/juita.v11i2.17424","url":null,"abstract":"Major is one of the important factors in the world of lectures. Along with the increasing need for knowledge and skills required in the world of work, increasing the number of majors offered by tertiary institutions. The number of considerations from prospective students regarding the selection of majors causes students to be confused in determining the best major they will choose to continue their education. The research aims to design an expert system-based website that will be used to provide major recommendations. The method to be used is the forward chaining method, where this method works by matching data based on predetermined facts, then obtaining results based on matching the data. Based on the black box testing that has been done, the results show that the designed expert system is by the expected functionality. Therefore this expert system can be said to be feasible to use.","PeriodicalId":151254,"journal":{"name":"JUITA : Jurnal Informatika","volume":"27 5","pages":""},"PeriodicalIF":0.0,"publicationDate":"2023-11-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"139265320","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 : 2023-11-17DOI: 10.30595/juita.v11i2.17920
Helma Herlinda, Muhammad Itqan Mazdadi, M. Muliadi, D. Kartini, Irwan Budiman
Social media has exerted a significant influence on the lives of the majority of individuals in the contemporary era. It not only enables communication among people within specific environments but also facilitates user connectivity in the virtual realm. Instagram is a social media platform that plays a pivotal role in the sharing of information and fostering communication among its users through the medium of photos and videos, which can be commented on by other users. The utilization of Instagram is consistently growing each year, thereby potentially yielding both positive and negative consequences. One prevalent negative consequence that frequently arises is cyberbullying. Conducting sentiment analysis on cyberbullying data can provide insights into the effectiveness of the employed methodology. This research was conducted as an experimental research, aiming to compare the performance of Random Forest and Random Forest after applying the Particle Swarm Optimization feature selection technique on three distinct data split compositions, namely 70:30, 80:20, and 90:10. The evaluation results indicate that the highest accuracy scores were achieved in the 90:10 data split configuration. Specifically, the Random Forest model yielded an accuracy of 87.50%, while the Random Forest model, after undergoing feature selection using the Particle Swarm Optimization algorithm, achieved an accuracy of 92.19%. Therefore, the implementation of Particle Swarm Optimization as a feature selection technique demonstrates the potential to enhance the accuracy of the Random Forest method.
{"title":"Implementation of Particle Swarm Optimization on Sentiment Analysis of Cyberbullying using Random Forest","authors":"Helma Herlinda, Muhammad Itqan Mazdadi, M. Muliadi, D. Kartini, Irwan Budiman","doi":"10.30595/juita.v11i2.17920","DOIUrl":"https://doi.org/10.30595/juita.v11i2.17920","url":null,"abstract":"Social media has exerted a significant influence on the lives of the majority of individuals in the contemporary era. It not only enables communication among people within specific environments but also facilitates user connectivity in the virtual realm. Instagram is a social media platform that plays a pivotal role in the sharing of information and fostering communication among its users through the medium of photos and videos, which can be commented on by other users. The utilization of Instagram is consistently growing each year, thereby potentially yielding both positive and negative consequences. One prevalent negative consequence that frequently arises is cyberbullying. Conducting sentiment analysis on cyberbullying data can provide insights into the effectiveness of the employed methodology. This research was conducted as an experimental research, aiming to compare the performance of Random Forest and Random Forest after applying the Particle Swarm Optimization feature selection technique on three distinct data split compositions, namely 70:30, 80:20, and 90:10. The evaluation results indicate that the highest accuracy scores were achieved in the 90:10 data split configuration. Specifically, the Random Forest model yielded an accuracy of 87.50%, while the Random Forest model, after undergoing feature selection using the Particle Swarm Optimization algorithm, achieved an accuracy of 92.19%. Therefore, the implementation of Particle Swarm Optimization as a feature selection technique demonstrates the potential to enhance the accuracy of the Random Forest method.","PeriodicalId":151254,"journal":{"name":"JUITA : Jurnal Informatika","volume":"69 9","pages":""},"PeriodicalIF":0.0,"publicationDate":"2023-11-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"139266455","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 : 2023-11-17DOI: 10.30595/juita.v11i2.19298
G. Pradipta, Made Liandana, P. Ayu, Dandy Pramana Hostiadi, Putu Sumardika Eka Putra
K-Nearest Neighbor (KNN) is a widely used method for both classification and regression cases. This algorithm, known for its simplicity and effectiveness, relies primarily on the Euclidean formula for distance metrics. Therefore, this study aimed to develop a voting model where observations were made using different distance calculation formulas. The nearest neighbors algorithm was divided based on differences in distance measurements, with each resulting model contributing a vote to determine the final class. Consequently, three methods were proposed, namely k-nearest neighbors (KNN), Local Mean-based KNN, and Distance-Weighted neighbor (DWKNN), with an inclusion of a voting scheme. The robustness of these models was tested using umbilical cord data characterized by imbalance and small dataset size. The results showed that the proposed voting model for nearest neighbors consistently improved performance by an average of 1-2% across accuracy, precision, recall, and F1 score when compared to the conventional non-voting method.
K-Nearest Neighbor (KNN) 是一种广泛用于分类和回归的方法。这种算法以其简单有效而著称，主要依靠欧几里得公式进行距离度量。因此，本研究旨在开发一种投票模型，使用不同的距离计算公式进行观测。近邻算法根据距离测量的差异进行划分，每个结果模型贡献一票，以确定最终类别。因此，提出了三种方法，即 K 最近邻（KNN）、基于局部均值的 KNN 和距离加权邻（DWKNN），并加入了投票方案。利用脐带数据对这些模型的稳健性进行了测试，这些数据具有不平衡和数据集规模小的特点。结果表明，与传统的非投票方法相比，所提出的近邻投票模型在准确度、精确度、召回率和 F1 分数方面的性能平均提高了 1-2%。
{"title":"Voting Scheme Nearest Neighbors by Difference Distance Metrics Measurement","authors":"G. Pradipta, Made Liandana, P. Ayu, Dandy Pramana Hostiadi, Putu Sumardika Eka Putra","doi":"10.30595/juita.v11i2.19298","DOIUrl":"https://doi.org/10.30595/juita.v11i2.19298","url":null,"abstract":"K-Nearest Neighbor (KNN) is a widely used method for both classification and regression cases. This algorithm, known for its simplicity and effectiveness, relies primarily on the Euclidean formula for distance metrics. Therefore, this study aimed to develop a voting model where observations were made using different distance calculation formulas. The nearest neighbors algorithm was divided based on differences in distance measurements, with each resulting model contributing a vote to determine the final class. Consequently, three methods were proposed, namely k-nearest neighbors (KNN), Local Mean-based KNN, and Distance-Weighted neighbor (DWKNN), with an inclusion of a voting scheme. The robustness of these models was tested using umbilical cord data characterized by imbalance and small dataset size. The results showed that the proposed voting model for nearest neighbors consistently improved performance by an average of 1-2% across accuracy, precision, recall, and F1 score when compared to the conventional non-voting method.","PeriodicalId":151254,"journal":{"name":"JUITA : Jurnal Informatika","volume":"26 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2023-11-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"139263721","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 : 2023-11-17DOI: 10.30595/juita.v11i2.17643
Ridwan Ahmad Ma'arif, Fauziah Fauziah
In recent years User Experience (UX) has become something that must be implemented in making applications. Every application design practitioner has applied this discipline, but often they wonder how to simplify a user's journey flow by using applications and make it easier, faster, and simpler. This research aims to explain a method that can simplify the User Experience comprehensively. RESHOT is used (Refine the challenge, Remove, Shrink, Hide, Organize, Time). This method will make applications pay more attention to aspects that can increase user satisfaction. As a result, this study contributes to an explanation of simplifying the flow of uploading donor data files using the RESHOT method in the X blood donor data collection application. The results of streamlining the flow of uploading donor data files have been tested on five respondents and have a 100% user success rate in completing tasks with an average processing time of 14.5 seconds. In testing, there is a misclick rate of 10.7%. This is because the user wants to explore the designed application. And this is also a limitation of this study, namely not making the overall application design interaction.
{"title":"Implementation of RESHOT Method to Create a Good User Experience in an Application","authors":"Ridwan Ahmad Ma'arif, Fauziah Fauziah","doi":"10.30595/juita.v11i2.17643","DOIUrl":"https://doi.org/10.30595/juita.v11i2.17643","url":null,"abstract":"In recent years User Experience (UX) has become something that must be implemented in making applications. Every application design practitioner has applied this discipline, but often they wonder how to simplify a user's journey flow by using applications and make it easier, faster, and simpler. This research aims to explain a method that can simplify the User Experience comprehensively. RESHOT is used (Refine the challenge, Remove, Shrink, Hide, Organize, Time). This method will make applications pay more attention to aspects that can increase user satisfaction. As a result, this study contributes to an explanation of simplifying the flow of uploading donor data files using the RESHOT method in the X blood donor data collection application. The results of streamlining the flow of uploading donor data files have been tested on five respondents and have a 100% user success rate in completing tasks with an average processing time of 14.5 seconds. In testing, there is a misclick rate of 10.7%. This is because the user wants to explore the designed application. And this is also a limitation of this study, namely not making the overall application design interaction.","PeriodicalId":151254,"journal":{"name":"JUITA : Jurnal Informatika","volume":"48 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2023-11-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"139262534","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 : 2023-11-17DOI: 10.30595/juita.v11i2.17568
Yesi Novaria Kunang, Widya Putri Mentari
Twitter users use social media to express emotions about something, whether it is criticism or praise. Analyzing the opinions or sentiments in the tweets that Twitter users send can identify their emotions for a particular topic. This study aims to determine the impact of vectorization methods on public sentiment analysis regarding the readiness for offline learning in Indonesia during the Covid-19 pandemic. The authors labeled sentiment using two different approaches: manually and automatically using the NLP TextBlob library. We compared the vectorization method used by employing count vectorization, TF-IDF, and a combination of both. The feature vectors were then classified using three classification methods: naïve Bayes, logistic regression, and k-nearest neighbor, for both manual and automatic labeling. To assess the performance of sentiment analysis models, we used accuracy, precision, recall, and F1-score for performance metrics. The best results showed that the Logistic regression classifier with the feature extraction technique that combines count vectorization and TF-IDF provided the best performance for both data with manual and automatic labeling.
{"title":"Analysis of the Impact of Vectorization Methods on Machine Learning-Based Sentiment Analysis of Tweets Regarding Readiness for Offline Learning","authors":"Yesi Novaria Kunang, Widya Putri Mentari","doi":"10.30595/juita.v11i2.17568","DOIUrl":"https://doi.org/10.30595/juita.v11i2.17568","url":null,"abstract":"Twitter users use social media to express emotions about something, whether it is criticism or praise. Analyzing the opinions or sentiments in the tweets that Twitter users send can identify their emotions for a particular topic. This study aims to determine the impact of vectorization methods on public sentiment analysis regarding the readiness for offline learning in Indonesia during the Covid-19 pandemic. The authors labeled sentiment using two different approaches: manually and automatically using the NLP TextBlob library. We compared the vectorization method used by employing count vectorization, TF-IDF, and a combination of both. The feature vectors were then classified using three classification methods: naïve Bayes, logistic regression, and k-nearest neighbor, for both manual and automatic labeling. To assess the performance of sentiment analysis models, we used accuracy, precision, recall, and F1-score for performance metrics. The best results showed that the Logistic regression classifier with the feature extraction technique that combines count vectorization and TF-IDF provided the best performance for both data with manual and automatic labeling.","PeriodicalId":151254,"journal":{"name":"JUITA : Jurnal Informatika","volume":"38 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2023-11-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"139262866","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 : 2023-11-17DOI: 10.30595/juita.v11i2.18435
Putu Desiana, Wulaning Ayu, G. Pradipta, Roy Rudolf Huizen, Kadek Eka, Sapta, G. Artana
Amniotic fluid a crucial role in ensuring the well-being of the fetus during pregnancy and is contained within the amnion cavity, which is surrounded by a membrane. Several studies have shown that volume of amniotic fluid can vary throughout pregnancy and is closely linked to the health and safety of the fetus. This indicates that it is essential to perform accurate measurement and identification of its volume. Obstetric specialist often use a manual method to identify amniotic fluid by visually determining the longest straight vertical line between the upper and lower boundaries. Therefore, this study aims to develop detection model, known as modified Single Deepest Vertical Detection (SDVD) algorithm to automatically measure the longest vertical line by following medical rules and regulations. SDVD algorithm was designed to measure the depth of amniotic fluid vertically by searching the column of pixels that comprised the image sample, excluding any intersection with the fetal body. Performance testing was carried out using 130 images by comparing the manual measurement results obtained by obstetric specialists and the proposed model. Based on the experimental results using modified SDVD, the average accuracy, precision, and recall achieved for amniotic fluid classification were 92.63%, 85.23%, and 95.6%, respectively.
{"title":"Modified of Single Deepest Vertical Detection (SDVD) Algorithm for Amniotic Fluid Volume Classification","authors":"Putu Desiana, Wulaning Ayu, G. Pradipta, Roy Rudolf Huizen, Kadek Eka, Sapta, G. Artana","doi":"10.30595/juita.v11i2.18435","DOIUrl":"https://doi.org/10.30595/juita.v11i2.18435","url":null,"abstract":"Amniotic fluid a crucial role in ensuring the well-being of the fetus during pregnancy and is contained within the amnion cavity, which is surrounded by a membrane. Several studies have shown that volume of amniotic fluid can vary throughout pregnancy and is closely linked to the health and safety of the fetus. This indicates that it is essential to perform accurate measurement and identification of its volume. Obstetric specialist often use a manual method to identify amniotic fluid by visually determining the longest straight vertical line between the upper and lower boundaries. Therefore, this study aims to develop detection model, known as modified Single Deepest Vertical Detection (SDVD) algorithm to automatically measure the longest vertical line by following medical rules and regulations. SDVD algorithm was designed to measure the depth of amniotic fluid vertically by searching the column of pixels that comprised the image sample, excluding any intersection with the fetal body. Performance testing was carried out using 130 images by comparing the manual measurement results obtained by obstetric specialists and the proposed model. Based on the experimental results using modified SDVD, the average accuracy, precision, and recall achieved for amniotic fluid classification were 92.63%, 85.23%, and 95.6%, respectively.","PeriodicalId":151254,"journal":{"name":"JUITA : Jurnal Informatika","volume":"17 5","pages":""},"PeriodicalIF":0.0,"publicationDate":"2023-11-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"139265990","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 : 2023-11-17DOI: 10.30595/juita.v11i2.17880
Ahmad Fitra Hamdani, Daniel Swanjaya, Risa Helilintar
Accuracy is the primary focus in prediction research. Optimization is conducted to improve the performance of prediction models, thereby enhancing prediction accuracy. This study aims to optimize the Facebook Prophet model by performing hyperparameter tuning using Bayesian Optimization to improve the accuracy of USD Index Value prediction. Evaluation is conducted through multiple prediction experiments using different ranges of historical data. The results of the study demonstrate that performing hyperparameter tuning on the Facebook Prophet model yields better prediction results. Prior to parameter tuning, the MAPE indicator metric is 1.38% for the historical data range of 2014-2023, and it decreases to 1.33% after parameter tuning. Further evaluation shows improved prediction performance using different ranges of historical data. For the historical data range of 2015-2023, the MAPE value decreases from 1.39% to 1.20%. Similarly, for the data range of 2016-2023, the MAPE decreases from 1.12% to 0.80%. Furthermore, for the data range of 2017-2023, there is a decrease from 0.80% to 0.76%. This is followed by the data range of 2018-2023, with a decrease from 0.75% to 0.70%. Lastly, for the data range of 2019-2023, there is a decrease from 0.63% to 0.55%. These results demonstrate that performing Hyperparameter Optimization using Bayesian Optimization consistently improves prediction accuracy in the Facebook Prophet model.
{"title":"Facebook Prophet Model with Bayesian Optimization for USD Index Prediction","authors":"Ahmad Fitra Hamdani, Daniel Swanjaya, Risa Helilintar","doi":"10.30595/juita.v11i2.17880","DOIUrl":"https://doi.org/10.30595/juita.v11i2.17880","url":null,"abstract":"Accuracy is the primary focus in prediction research. Optimization is conducted to improve the performance of prediction models, thereby enhancing prediction accuracy. This study aims to optimize the Facebook Prophet model by performing hyperparameter tuning using Bayesian Optimization to improve the accuracy of USD Index Value prediction. Evaluation is conducted through multiple prediction experiments using different ranges of historical data. The results of the study demonstrate that performing hyperparameter tuning on the Facebook Prophet model yields better prediction results. Prior to parameter tuning, the MAPE indicator metric is 1.38% for the historical data range of 2014-2023, and it decreases to 1.33% after parameter tuning. Further evaluation shows improved prediction performance using different ranges of historical data. For the historical data range of 2015-2023, the MAPE value decreases from 1.39% to 1.20%. Similarly, for the data range of 2016-2023, the MAPE decreases from 1.12% to 0.80%. Furthermore, for the data range of 2017-2023, there is a decrease from 0.80% to 0.76%. This is followed by the data range of 2018-2023, with a decrease from 0.75% to 0.70%. Lastly, for the data range of 2019-2023, there is a decrease from 0.63% to 0.55%. These results demonstrate that performing Hyperparameter Optimization using Bayesian Optimization consistently improves prediction accuracy in the Facebook Prophet model.","PeriodicalId":151254,"journal":{"name":"JUITA : Jurnal Informatika","volume":"39 2","pages":""},"PeriodicalIF":0.0,"publicationDate":"2023-11-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"139264659","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 : 2023-11-17DOI: 10.30595/juita.v11i2.17372
Christian Sri Kusuma Aditya, Vinna Rahmayanti Setyaning Nastiti, Qori Raditya Damayanti, Gian Bagus Sadewa
The fashion industry has changed a lot over the years, which makes it hard for people to compare different kinds of fashion. To make it easier, different styles of clothing are tried out to find the exact and precise look desired. So, we opted to employ the Convolutional Neural Network (CNN) method for fashion classification. This approach represents one of the methodologies employed to utilize computers for the purpose of recognizing and categorizing items. The goal of this research is to see how well the Convolutional Neural Network method classifies the Fashion-MNIST dataset compared to other methods, models, and classification processes used in previous research. The information in this dataset is about different types of clothes and accessories. These items are divided into 10 categories, which include ankle boots, bags, coats, dresses, pullovers, sandals, shirts, sneakers, t-shirts, and trousers. The new classification method worked better than before on the test dataset. It had an accuracy value of 95. 92%, which is higher than in previous research. This research also uses a method called image data generator to make the Fashion MNIST image better. This method helps prevent too much focus on certain details and makes the results more accurate.
{"title":"Implementation of Convolutional Neural Network Method in Identifying Fashion Image","authors":"Christian Sri Kusuma Aditya, Vinna Rahmayanti Setyaning Nastiti, Qori Raditya Damayanti, Gian Bagus Sadewa","doi":"10.30595/juita.v11i2.17372","DOIUrl":"https://doi.org/10.30595/juita.v11i2.17372","url":null,"abstract":"The fashion industry has changed a lot over the years, which makes it hard for people to compare different kinds of fashion. To make it easier, different styles of clothing are tried out to find the exact and precise look desired. So, we opted to employ the Convolutional Neural Network (CNN) method for fashion classification. This approach represents one of the methodologies employed to utilize computers for the purpose of recognizing and categorizing items. The goal of this research is to see how well the Convolutional Neural Network method classifies the Fashion-MNIST dataset compared to other methods, models, and classification processes used in previous research. The information in this dataset is about different types of clothes and accessories. These items are divided into 10 categories, which include ankle boots, bags, coats, dresses, pullovers, sandals, shirts, sneakers, t-shirts, and trousers. The new classification method worked better than before on the test dataset. It had an accuracy value of 95. 92%, which is higher than in previous research. This research also uses a method called image data generator to make the Fashion MNIST image better. This method helps prevent too much focus on certain details and makes the results more accurate.","PeriodicalId":151254,"journal":{"name":"JUITA : Jurnal Informatika","volume":"44 8","pages":""},"PeriodicalIF":0.0,"publicationDate":"2023-11-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"139264268","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：