Pub Date : 2024-05-20DOI: 10.30595/juita.v12i1.19798
A. Fadlil, Imam Riadi, Fiki Andrianto
Twitter is a social media platform that is very important in the digital world. Fast communication and interaction make Twitter a vital information center in sentiment analysis. The purpose of this research is to classify public opinion about the presence of marketplaces in Indonesia, both positive and negative sentiments, using a Non-linear SVM algorithm based on 1276 tweets. This research involves the stages of data pre-processing, labeling, feature extraction using TF-IDF, and data division into three scenarios: 80% training data and 20% test data, 50% training data and 50% test data scenario, and 20% training data and 80% test data scenario. The last process, GridSearchCV, combines cross-validation and non-linear SVM parameters for model evaluation using a confusion matrix. The best SVM model resulting from the scenario was 80% training and 20% test data, with hyperparameters Gamma = 100 and C = 0.01, achieving 89% accuracy. When tested on never-before-seen data, the accuracy increased to 90%, with an f1-score of 91%, precision of 88%, and recall of 95% on negative sentiments. In conclusion, evaluating the performance of non-linear SVM kernels with a combination of hyperparameter values can improve accuracy, especially on public response information about online marketplaces and public sentiment.
{"title":"Non-linear Kernel Optimisation of Support Vector Machine Algorithm for Online Marketplace Sentiment Analysis","authors":"A. Fadlil, Imam Riadi, Fiki Andrianto","doi":"10.30595/juita.v12i1.19798","DOIUrl":"https://doi.org/10.30595/juita.v12i1.19798","url":null,"abstract":"Twitter is a social media platform that is very important in the digital world. Fast communication and interaction make Twitter a vital information center in sentiment analysis. The purpose of this research is to classify public opinion about the presence of marketplaces in Indonesia, both positive and negative sentiments, using a Non-linear SVM algorithm based on 1276 tweets. This research involves the stages of data pre-processing, labeling, feature extraction using TF-IDF, and data division into three scenarios: 80% training data and 20% test data, 50% training data and 50% test data scenario, and 20% training data and 80% test data scenario. The last process, GridSearchCV, combines cross-validation and non-linear SVM parameters for model evaluation using a confusion matrix. The best SVM model resulting from the scenario was 80% training and 20% test data, with hyperparameters Gamma = 100 and C = 0.01, achieving 89% accuracy. When tested on never-before-seen data, the accuracy increased to 90%, with an f1-score of 91%, precision of 88%, and recall of 95% on negative sentiments. In conclusion, evaluating the performance of non-linear SVM kernels with a combination of hyperparameter values can improve accuracy, especially on public response information about online marketplaces and public sentiment.","PeriodicalId":151254,"journal":{"name":"JUITA : Jurnal Informatika","volume":"99 18","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-05-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141122651","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 : 2024-05-20DOI: 10.30595/juita.v12i1.21491
E. Rohaeti, Ani Andriyati
Analysing pre-COVID-19 unemployment in West Java is vital for comprehending and tackling Indonesia’s economic challenges. This significance arises not only due to the region’s high unemployment rate, but also from the need to understand unemployment patterns before COVID-19, which has become more relevant now during the country’s post-pandemic recovery phase. This study evaluates four machine learning models (Random Forest, Linear SVM, RBF SVM, and Polynomial SVM) to classify employment status using demographic and job-related variables. The objective is to find the most suitable model, particularly considering the imbalanced nature of the study-case data. Data from the National Labor Force Survey (SAKERNAS) in August 2019 is utilized, comprising 54,429 respondents across districts in West Java. The four models are evaluated using holdout validation with a 70:30 stratified proportion, repeated for 100 times. Results indicate that the random forest model outperforms others in balanced accuracy, F1-score, and computational time. The random forest model also underscores the importance of gender and age in classifying employment status in West Java, suggesting a need for targeted intervention, especially for female citizens and individuals in productive age groups.
{"title":"Comparative Study of Predictive Classification Models on Data with Severely Imbalanced Predictors","authors":"E. Rohaeti, Ani Andriyati","doi":"10.30595/juita.v12i1.21491","DOIUrl":"https://doi.org/10.30595/juita.v12i1.21491","url":null,"abstract":"Analysing pre-COVID-19 unemployment in West Java is vital for comprehending and tackling Indonesia’s economic challenges. This significance arises not only due to the region’s high unemployment rate, but also from the need to understand unemployment patterns before COVID-19, which has become more relevant now during the country’s post-pandemic recovery phase. This study evaluates four machine learning models (Random Forest, Linear SVM, RBF SVM, and Polynomial SVM) to classify employment status using demographic and job-related variables. The objective is to find the most suitable model, particularly considering the imbalanced nature of the study-case data. Data from the National Labor Force Survey (SAKERNAS) in August 2019 is utilized, comprising 54,429 respondents across districts in West Java. The four models are evaluated using holdout validation with a 70:30 stratified proportion, repeated for 100 times. Results indicate that the random forest model outperforms others in balanced accuracy, F1-score, and computational time. The random forest model also underscores the importance of gender and age in classifying employment status in West Java, suggesting a need for targeted intervention, especially for female citizens and individuals in productive age groups.","PeriodicalId":151254,"journal":{"name":"JUITA : Jurnal Informatika","volume":"21 8","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-05-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141120082","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 : 2024-05-20DOI: 10.30595/juita.v12i1.20608
Yulrio Brianorman, Dewi Utami
The classification of images from the Indonesian Sign Language System (SIBI) using VGG16, ResNet50, Inception, Xception, and MobileNetV2 Convolutional Neural Network (CNN) architectures is evaluated in this paper. With Google Colab Pro, a 224 × 224-pixel picture dataset was used for the study. A five-stage technique consisting of Dataset Collection, Dataset Preprocessing, Model Design, Model Training, and Model Testing was applied. Performance evaluation focused on accuracy, precision, recall, and F1-Score. The results identified VGG16 as the top-performing model with an accuracy of 99.60% and an equivalent F1-Score, followed closely by ResNet50 with nearly similar performance. Inception, XCeption, and MobileNetV2 demonstrated balanced performance but with lower accuracy. This study sheds light on the best CNN models to choose for SIBI image classification, and it makes recommendations for further research that include using sophisticated data augmentation methods, investigating novel CNN architectures, and putting the models to practical use.
本文评估了使用 VGG16、ResNet50、Inception、Xception 和 MobileNetV2 卷积神经网络（CNN）架构对印度尼西亚手语系统（SIBI）图像进行分类的情况。研究使用了 Google Colab Pro 的 224 × 224 像素图片数据集。研究采用了五阶段技术，包括数据集收集、数据集预处理、模型设计、模型训练和模型测试。性能评估的重点是准确率、精确度、召回率和 F1 分数。结果表明，VGG16 是表现最好的模型，准确率为 99.60%，F1-Score 与之相当，紧随其后的是 ResNet50，表现几乎相似。Inception、XCeption 和 MobileNetV2 表现均衡，但准确率较低。本研究揭示了用于 SIBI 图像分类的最佳 CNN 模型，并提出了进一步研究的建议，包括使用复杂的数据增强方法、研究新型 CNN 架构以及将模型投入实际使用。
{"title":"Comparative Analysis of CNN Architectures for SIBI Image Classification","authors":"Yulrio Brianorman, Dewi Utami","doi":"10.30595/juita.v12i1.20608","DOIUrl":"https://doi.org/10.30595/juita.v12i1.20608","url":null,"abstract":"The classification of images from the Indonesian Sign Language System (SIBI) using VGG16, ResNet50, Inception, Xception, and MobileNetV2 Convolutional Neural Network (CNN) architectures is evaluated in this paper. With Google Colab Pro, a 224 × 224-pixel picture dataset was used for the study. A five-stage technique consisting of Dataset Collection, Dataset Preprocessing, Model Design, Model Training, and Model Testing was applied. Performance evaluation focused on accuracy, precision, recall, and F1-Score. The results identified VGG16 as the top-performing model with an accuracy of 99.60% and an equivalent F1-Score, followed closely by ResNet50 with nearly similar performance. Inception, XCeption, and MobileNetV2 demonstrated balanced performance but with lower accuracy. This study sheds light on the best CNN models to choose for SIBI image classification, and it makes recommendations for further research that include using sophisticated data augmentation methods, investigating novel CNN architectures, and putting the models to practical use.","PeriodicalId":151254,"journal":{"name":"JUITA : Jurnal Informatika","volume":"66 2","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-05-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141121521","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 : 2024-05-20DOI: 10.30595/juita.v12i1.20688
Muhammad Rizki, Arief Hermawan, Donny Avianto
This study aims to enhance the performance of the K-Nearest Neighbors (KNN) algorithm by optimizing the hyperparameter K using the Particle Swarm Optimization (PSO) algorithm. In contrast to prior research, which typically focuses on a single dataset, this study seeks to demonstrate that PSO can effectively optimize KNN hyperparameters across diverse datasets. Three datasets from different domains are utilized: Iris, Wine, and Breast Cancer, each featuring distinct classification types and classes. Furthermore, this research endeavors to establish that PSO can operate optimally with both Manhattan and Euclidean distance metrics. Prior to optimization, experiments with default K values (3, 5, and 7) were conducted to observe KNN behavior on each dataset. Initial results reveal stable accuracy in the iris dataset, while the wine and breast cancer datasets exhibit a decrease in accuracy at K=3, attributed to attribute complexity. The hyperparameter K optimization process with PSO yields a significant increase in accuracy, particularly in the wine dataset, where accuracy improves by 6.28% with the Manhattan matrix. The enhanced accuracy in the optimized KNN algorithm demonstrates the effectiveness of PSO in overcoming KNN constraints. Although the accuracy increase for the iris dataset is not as pronounced, this research provides insight that optimizing the hyperparameter K can yield positive results, even for datasets with initially good performance. A recommendation for future research is to conduct similar experiments with different algorithms, such as Support Vector Machine or Random Forest, to further evaluate PSO's ability to optimize the iris, wine, and breast cancer datasets.
{"title":"Optimization of Hyperparameter K in K-Nearest Neighbor Using Particle Swarm Optimization","authors":"Muhammad Rizki, Arief Hermawan, Donny Avianto","doi":"10.30595/juita.v12i1.20688","DOIUrl":"https://doi.org/10.30595/juita.v12i1.20688","url":null,"abstract":"This study aims to enhance the performance of the K-Nearest Neighbors (KNN) algorithm by optimizing the hyperparameter K using the Particle Swarm Optimization (PSO) algorithm. In contrast to prior research, which typically focuses on a single dataset, this study seeks to demonstrate that PSO can effectively optimize KNN hyperparameters across diverse datasets. Three datasets from different domains are utilized: Iris, Wine, and Breast Cancer, each featuring distinct classification types and classes. Furthermore, this research endeavors to establish that PSO can operate optimally with both Manhattan and Euclidean distance metrics. Prior to optimization, experiments with default K values (3, 5, and 7) were conducted to observe KNN behavior on each dataset. Initial results reveal stable accuracy in the iris dataset, while the wine and breast cancer datasets exhibit a decrease in accuracy at K=3, attributed to attribute complexity. The hyperparameter K optimization process with PSO yields a significant increase in accuracy, particularly in the wine dataset, where accuracy improves by 6.28% with the Manhattan matrix. The enhanced accuracy in the optimized KNN algorithm demonstrates the effectiveness of PSO in overcoming KNN constraints. Although the accuracy increase for the iris dataset is not as pronounced, this research provides insight that optimizing the hyperparameter K can yield positive results, even for datasets with initially good performance. A recommendation for future research is to conduct similar experiments with different algorithms, such as Support Vector Machine or Random Forest, to further evaluate PSO's ability to optimize the iris, wine, and breast cancer datasets.","PeriodicalId":151254,"journal":{"name":"JUITA : Jurnal Informatika","volume":"71 3","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-05-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141121587","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 : 2024-05-20DOI: 10.30595/juita.v12i1.21051
Ainayah Syifa Hendri, Endah Sudarmilah
The adoption of Information Technology (IT) by Micro, Small, and Medium Enterprises (MSMEs) has become essential in the digital era. Nevertheless, challenges persist, such as enhancing IT adoption in the MSMEs sector and optimizing its benefits. This research aims to create a comprehensive model based on the Technology- Organization-Environment (TOE) framework by analyzing technological, organizational, and environmental factors influencing IT adoption among MSMEs in Pangandaran, Indonesia. Employing a quantitative approach, an online questionnaire was distributed to MSMEs, and data were analyzed using Partial Least Square-Structural Equation Modeling (PLS- SEM) through SmartPLS. The study significantly contributes to understanding IT adoption, emphasizing organizational context as the primary predictor, followed by technological and environmental contexts. Positive relationships were found between four contextual constructs: complexity, top management support, organizational readiness, and competitive pressure towards IT adoption in MSMEs. Conversely, compatibility and government support exhibited negative impacts. These findings have practical implications for Indonesian MSMEs by enhancing understanding of factors influencing IT adoption to support business operations. Furthermore, these findings hold the potential to assist MSMEs and the Indonesian government in optimizing IT adoption success. The generated data can be employed by MSMEs management authorities to devise strategies for enhancing IT adoption among MSMEs.
{"title":"Enhancing Information Technology Adoption Potential in MSMEs: a Conceptual Model Based on TOE Framework","authors":"Ainayah Syifa Hendri, Endah Sudarmilah","doi":"10.30595/juita.v12i1.21051","DOIUrl":"https://doi.org/10.30595/juita.v12i1.21051","url":null,"abstract":"The adoption of Information Technology (IT) by Micro, Small, and Medium Enterprises (MSMEs) has become essential in the digital era. Nevertheless, challenges persist, such as enhancing IT adoption in the MSMEs sector and optimizing its benefits. This research aims to create a comprehensive model based on the Technology- Organization-Environment (TOE) framework by analyzing technological, organizational, and environmental factors influencing IT adoption among MSMEs in Pangandaran, Indonesia. Employing a quantitative approach, an online questionnaire was distributed to MSMEs, and data were analyzed using Partial Least Square-Structural Equation Modeling (PLS- SEM) through SmartPLS. The study significantly contributes to understanding IT adoption, emphasizing organizational context as the primary predictor, followed by technological and environmental contexts. Positive relationships were found between four contextual constructs: complexity, top management support, organizational readiness, and competitive pressure towards IT adoption in MSMEs. Conversely, compatibility and government support exhibited negative impacts. These findings have practical implications for Indonesian MSMEs by enhancing understanding of factors influencing IT adoption to support business operations. Furthermore, these findings hold the potential to assist MSMEs and the Indonesian government in optimizing IT adoption success. The generated data can be employed by MSMEs management authorities to devise strategies for enhancing IT adoption among MSMEs.","PeriodicalId":151254,"journal":{"name":"JUITA : Jurnal Informatika","volume":"19 4","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-05-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141119641","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 : 2024-05-20DOI: 10.30595/juita.v12i1.19508
D. Mualfah, R. A. Ramadhan, Muhammad Arrafi Arrasyid
One of the solutions used for access speeds is to maximize non-volatile storage functions by a conventional Hard Disk Driver with Solid State Drive that has the TRIM architecture using the Redundant Array of Inexpensive Disks 0 configuration or the commonly known RAID 0. RAID 0 is a stripping technique that has the highest speed among other RAID configurations. However, this configuration has a disadvantage in that when there is damage to one of the storage disks all the data will be corrupted and lost. It's becoming one of the challenges in digital forensic investigation when it comes to computer crime. Furthermore, this research uses experimental practices using live forensic methods to perform analysis and examination against the merger of HDD and SSD configuration RAID 0 TRIM features. The expected is an overview of the characteristics of recovery capability to find out the authenticity integrity values of files that have been lost or permanently deleted on both TRIM SSD functions disable and enable. Furthermore, this research is expected to be a solution for the experimental and practical investigation of computer crime especially in Indonesia given the increasing development of technology that is directly compared with the rise in computer crime.
访问速度的解决方案之一，是通过具有 TRIM 架构的固态硬盘驱动器，使用 "低成本磁盘冗余阵列 0 "配置或通常所说的 RAID 0，最大限度地提高非易失性存储功能。RAID 0 是一种剥离技术，在其他 RAID 配置中速度最高。不过，这种配置也有缺点，那就是当其中一个存储磁盘损坏时，所有数据都会损坏和丢失。在涉及计算机犯罪时，这已成为数字取证调查的挑战之一。此外，本研究采用现场取证方法的实验实践，针对硬盘和固态硬盘配置 RAID 0 TRIM 功能的合并进行分析和检查。预计将概述恢复能力的特点，以找出 TRIM SSD 功能禁用和启用时丢失或永久删除的文件的真实性完整性值。此外，鉴于技术的日益发展与计算机犯罪的增加直接相关，本研究有望成为计算机犯罪实验和实际调查的解决方案，尤其是在印度尼西亚。
{"title":"Implementation of Live Forensic Method on Fusion Hard Disk Drive (HDD) and Solid State Drive (SSD) RAID 0 Configuration TRIM Features","authors":"D. Mualfah, R. A. Ramadhan, Muhammad Arrafi Arrasyid","doi":"10.30595/juita.v12i1.19508","DOIUrl":"https://doi.org/10.30595/juita.v12i1.19508","url":null,"abstract":"One of the solutions used for access speeds is to maximize non-volatile storage functions by a conventional Hard Disk Driver with Solid State Drive that has the TRIM architecture using the Redundant Array of Inexpensive Disks 0 configuration or the commonly known RAID 0. RAID 0 is a stripping technique that has the highest speed among other RAID configurations. However, this configuration has a disadvantage in that when there is damage to one of the storage disks all the data will be corrupted and lost. It's becoming one of the challenges in digital forensic investigation when it comes to computer crime. Furthermore, this research uses experimental practices using live forensic methods to perform analysis and examination against the merger of HDD and SSD configuration RAID 0 TRIM features. The expected is an overview of the characteristics of recovery capability to find out the authenticity integrity values of files that have been lost or permanently deleted on both TRIM SSD functions disable and enable. Furthermore, this research is expected to be a solution for the experimental and practical investigation of computer crime especially in Indonesia given the increasing development of technology that is directly compared with the rise in computer crime. ","PeriodicalId":151254,"journal":{"name":"JUITA : Jurnal Informatika","volume":"99 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-05-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141122665","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 : 2024-05-20DOI: 10.30595/juita.v12i1.19386
Widya Putri Nurmawati, Indahwati Indahwati, F. Afendi
The prevalence of stroke in Indonesia has increased. One survey in Indonesia that contains information about the health conditions of the Indonesian people is the Indonesian Family Life Survey (IFLS). The proportion of respondents who had a stroke and non-stroke in IFLS5 showed an imbalance with an extreme level of imbalance; hence, this research aims to overcome this problem with SMOTE, SMOTE-Tomek Link, and SMOTE-ENN; then, the balanced dataset is classified using the ensemble and cascade approaches to improve the detection of stroke risk and to identify the important variables. However, the stroke respondents were still challenging to classify after imbalance class handling, presumably because of the large amount of data before and after balancing. The solution is to balance the training data with various percentages. The results showed the best percentage is applied to 5% of the training data, balanced by the SMOTE-ENN, and the ensemble method with the cascade approach increases the sensitivity and balanced accuracy values. Random forest and logistic regression combine models that produce the best performance, with a classification tree as the final model. The important variables obtained from this combination are the addition of probability from random forest, logistic regression, history of hypertension, age, and physical activity.
{"title":"Improving Stroke Detection with Hybrid Sampling and Cascade Generalization","authors":"Widya Putri Nurmawati, Indahwati Indahwati, F. Afendi","doi":"10.30595/juita.v12i1.19386","DOIUrl":"https://doi.org/10.30595/juita.v12i1.19386","url":null,"abstract":"The prevalence of stroke in Indonesia has increased. One survey in Indonesia that contains information about the health conditions of the Indonesian people is the Indonesian Family Life Survey (IFLS). The proportion of respondents who had a stroke and non-stroke in IFLS5 showed an imbalance with an extreme level of imbalance; hence, this research aims to overcome this problem with SMOTE, SMOTE-Tomek Link, and SMOTE-ENN; then, the balanced dataset is classified using the ensemble and cascade approaches to improve the detection of stroke risk and to identify the important variables. However, the stroke respondents were still challenging to classify after imbalance class handling, presumably because of the large amount of data before and after balancing. The solution is to balance the training data with various percentages. The results showed the best percentage is applied to 5% of the training data, balanced by the SMOTE-ENN, and the ensemble method with the cascade approach increases the sensitivity and balanced accuracy values. Random forest and logistic regression combine models that produce the best performance, with a classification tree as the final model. The important variables obtained from this combination are the addition of probability from random forest, logistic regression, history of hypertension, age, and physical activity.","PeriodicalId":151254,"journal":{"name":"JUITA : Jurnal Informatika","volume":"11 11","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-05-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141119799","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 : 2024-05-20DOI: 10.30595/juita.v12i1.20452
Jan Setiawan, Silviana Simbolon, Y. Yunasfi
In the field of magnetic cooling technology, there is still much to learn about the magnetocaloric properties of magnetic cooling materials. Research into magnetocaloric manganites exhibiting a significant maximum magnetic entropy change in the vicinity of ambient temperature yields encouraging outcomes for the advancement of magnetic refrigeration apparatus. Through a combination of chemical substitutions, changes in the amount of oxygen present, and different synthesis techniques, these manganites undergo lattice distortions that result in pseudocubic, orthorhombic, and rhombohedral structures instead of perovskite cubic structures. The present investigation used backpropagation neural networks (BPNNs) to investigate the correlations among maximum magnetic entropy change (MMEC), Curie temperature (Tc), lanthanum manganite compositions, lattice properties, and dopant ionic radii. Simbrain 3.07 was used to execute the BPNN model, and the suggested model accuracy was examined using coefficient determination. As a result, the model's predicted values for the mean absolute error, root mean square, and coefficient correlation for MMEC are 0.012, 0.022, and 0.9861, respectively. The model predicts that the Curie temperature mean absolute error, root mean square, and coefficient correlation will be 0.015, 0.021, and 0.9947, respectively. Based on these results, BPNN has the potential to be applied in predicting the MMEC and Tc of manganite as preliminary decision during experiments.
{"title":"Implementation of Backpropagation Neural Network for Prediction Magnetocaloric Effect of Manganite","authors":"Jan Setiawan, Silviana Simbolon, Y. Yunasfi","doi":"10.30595/juita.v12i1.20452","DOIUrl":"https://doi.org/10.30595/juita.v12i1.20452","url":null,"abstract":"In the field of magnetic cooling technology, there is still much to learn about the magnetocaloric properties of magnetic cooling materials. Research into magnetocaloric manganites exhibiting a significant maximum magnetic entropy change in the vicinity of ambient temperature yields encouraging outcomes for the advancement of magnetic refrigeration apparatus. Through a combination of chemical substitutions, changes in the amount of oxygen present, and different synthesis techniques, these manganites undergo lattice distortions that result in pseudocubic, orthorhombic, and rhombohedral structures instead of perovskite cubic structures. The present investigation used backpropagation neural networks (BPNNs) to investigate the correlations among maximum magnetic entropy change (MMEC), Curie temperature (Tc), lanthanum manganite compositions, lattice properties, and dopant ionic radii. Simbrain 3.07 was used to execute the BPNN model, and the suggested model accuracy was examined using coefficient determination. As a result, the model's predicted values for the mean absolute error, root mean square, and coefficient correlation for MMEC are 0.012, 0.022, and 0.9861, respectively. The model predicts that the Curie temperature mean absolute error, root mean square, and coefficient correlation will be 0.015, 0.021, and 0.9947, respectively. Based on these results, BPNN has the potential to be applied in predicting the MMEC and Tc of manganite as preliminary decision during experiments.","PeriodicalId":151254,"journal":{"name":"JUITA : Jurnal Informatika","volume":"69 16","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-05-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141121401","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}
Tidiness becomes an essential aspect that everyone should maintain. Tidiness encompasses various elements, and one of the aspects closely related to it is the tidiness of a room. The tidiness of a room creates a comfortable and clean environment. The tidiness of a room is particularly crucial for individuals involved in businesses such as the hospitality industry. Therefore, a solution is needed to address this issue, and one of the approaches is to utilize Deep Learning for automatic room tidiness classification. One popular deep learning method for implementing image classification of room tidiness is the convolutional neural network (CNN), which creates a well-performing model for image classification with data augmentation. This research aims to develop an image classification model using CNN with the VGGNet architecture and data augmentation. This study is a reference for further development, with potential applications in the hospitality industry. The research results in a model that achieves an accuracy of 98.44% with a data proportion of 90% for training and validation, while the remaining 10% is used for testing purposes. The conclusion drawn from this study is that the CNN method, combined with data augmentation, can be utilized for image classification of room tidiness.
{"title":"Image Classification of Room Tidiness Using VGGNet with Data Augmentation","authors":"Leni Fitriani, Ayu Latifah, Moch. Rizky Cahyadiputra","doi":"10.30595/juita.v12i1.21204","DOIUrl":"https://doi.org/10.30595/juita.v12i1.21204","url":null,"abstract":"Tidiness becomes an essential aspect that everyone should maintain. Tidiness encompasses various elements, and one of the aspects closely related to it is the tidiness of a room. The tidiness of a room creates a comfortable and clean environment. The tidiness of a room is particularly crucial for individuals involved in businesses such as the hospitality industry. Therefore, a solution is needed to address this issue, and one of the approaches is to utilize Deep Learning for automatic room tidiness classification. One popular deep learning method for implementing image classification of room tidiness is the convolutional neural network (CNN), which creates a well-performing model for image classification with data augmentation. This research aims to develop an image classification model using CNN with the VGGNet architecture and data augmentation. This study is a reference for further development, with potential applications in the hospitality industry. The research results in a model that achieves an accuracy of 98.44% with a data proportion of 90% for training and validation, while the remaining 10% is used for testing purposes. The conclusion drawn from this study is that the CNN method, combined with data augmentation, can be utilized for image classification of room tidiness.","PeriodicalId":151254,"journal":{"name":"JUITA : Jurnal Informatika","volume":"2 13","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-05-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141120492","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 : 2024-05-20DOI: 10.30595/juita.v12i1.18731
Binti Solihah, Ahmad Zuhdi, Abdul Rochman, Edo Yulistama, Hilda Dwi Utari
Blending coal before it enters the power plant boiler unit is necessary to adjust the coal categories according to the boiler unit specifications. The power plant must also comply with the regulations regarding coal-biomass co-firing through blending. Applying a Genetic Algorithm that only considers the composition and fitness based on the blend's quality leads to accumulation issues, decreasing coal quality. This research proposes redefining chromosomes, fitness functions, mutation rules, population determination, and output as the best chromosome used in the Genetic Algorithm. Testing uses various compositions of coal inputs from the barge, coal yard, and biomass to simulate different conditions. The test results demonstrate that the developed algorithm can provide all possible alternative blends between the coal in the barge and at the coal yard. Under specific conditions, operators can choose a blend composition that involves coal stored in the coal yard for an extended period.
{"title":"Improve Coal Blending Optimization in CFPP by Cromosom and Fitness Function Redefinition of the Genetic Algorithm","authors":"Binti Solihah, Ahmad Zuhdi, Abdul Rochman, Edo Yulistama, Hilda Dwi Utari","doi":"10.30595/juita.v12i1.18731","DOIUrl":"https://doi.org/10.30595/juita.v12i1.18731","url":null,"abstract":"Blending coal before it enters the power plant boiler unit is necessary to adjust the coal categories according to the boiler unit specifications. The power plant must also comply with the regulations regarding coal-biomass co-firing through blending. Applying a Genetic Algorithm that only considers the composition and fitness based on the blend's quality leads to accumulation issues, decreasing coal quality. This research proposes redefining chromosomes, fitness functions, mutation rules, population determination, and output as the best chromosome used in the Genetic Algorithm. Testing uses various compositions of coal inputs from the barge, coal yard, and biomass to simulate different conditions. The test results demonstrate that the developed algorithm can provide all possible alternative blends between the coal in the barge and at the coal yard. Under specific conditions, operators can choose a blend composition that involves coal stored in the coal yard for an extended period.","PeriodicalId":151254,"journal":{"name":"JUITA : Jurnal Informatika","volume":"33 6","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-05-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141121864","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：