{"title":"Synthetic Minority Oversampling Technique (SMOTE) for Boosting the Accuracy of C4.5 Algorithm Model","authors":"Wiwi Rahayu, Deny Jollyta, Alyauma Hajjah, Johan, Gusrianty, Gustientiedina, Yulvia Nora Marlim, Y. Desnelita","doi":"10.59934/jaiea.v3i3.469","DOIUrl":"https://doi.org/10.59934/jaiea.v3i3.469","url":null,"abstract":"The low accuracy of the classification model may be caused by dataset imbalance. In reality, low-accuracy models are unacceptable. The purpose of this research is to address data imbalances in an employee performance dataset identified using the C4.5 method. SMOTE is the approach for addressing data imbalance. SMOTE is utilized to generate a large amount of data in the majority or minority class, which has an initial classification accuracy of just 17%. The C4.5 algorithm classifies the new dataset created by SMOTE, which consists of 11 attributes divided three times between training and testing data. The research found that with a 60:40 data split, the classification model had a 69% accuracy. Model accuracy climbed to 76% at 70:30 data splitting, and 86% at the final splitting, which was 80:20. The model's output matches the evaluation findings obtained using the confusion matrix. The research findings indicate that SMOTE may improve classification model accuracy by boosting data in imbalanced classes.","PeriodicalId":320979,"journal":{"name":"Journal of Artificial Intelligence and Engineering Applications (JAIEA)","volume":"15 10","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-06-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141382681","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}
Setia Hariati1, M. H. Pardede2, Marto Sihombing3, Stmik Kaputama
{"title":"Application of the DCT Algorithm to Protect Image Files with Key Symbols","authors":"Setia Hariati1, M. H. Pardede2, Marto Sihombing3, Stmik Kaputama","doi":"10.59934/jaiea.v3i3.456","DOIUrl":"https://doi.org/10.59934/jaiea.v3i3.456","url":null,"abstract":"Image file protection is an important aspect in managing and transmitting visual data in today's digital era. One effective method for protecting images is to use the Discrete Cosine Transformation (DCT) algorithm based on the principle of randomization with key symbols. This research aims to describe the application of the DCT algorithm in the context of image protection using key symbols as a security method. This research includes the main stages, namely randomization of the original image using predetermined key symbols, transformation of the image to the DCT domain, and storage of the scrambled image. By scrambling the image using key symbols known only to authorized parties, the original image can be changed significantly so that it is difficult to reconstruct by unauthorized parties. In addition, the results of this DCT transformation can also be encrypted using a strong cryptographic algorithm, thereby increasing the security level of image protection. The research results show that this method is effective in protecting image files from unauthorized access and unwanted surveillance. The final result of implementing the DCT algorithm with this key symbol is an image that is protected with a high level of security and can be restored correctly by authorized parties using the appropriate key symbol. This research has broad potential application in a variety of contexts, including data security, confidential image storage, and secure image transmission over communications networks. Thus, this method can make a positive contribution in overcoming information security challenges in an increasingly complex digital era.","PeriodicalId":320979,"journal":{"name":"Journal of Artificial Intelligence and Engineering Applications (JAIEA)","volume":"51 7","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-06-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141382096","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":"Performance Analysis of the Support Vector Machine Algorithm in Predicting Rain Potential in DKI Jakarta","authors":"Aina Latifa, Riyana Putri","doi":"10.59934/jaiea.v3i3.490","DOIUrl":"https://doi.org/10.59934/jaiea.v3i3.490","url":null,"abstract":"Indonesia is a country with a tropical climate which is located on the equator which tends to get sunlight throughout the year. Not only gives beauty but also saves disasters that can be dangerous such as floods, which usually occur due to high rainfall. The impact is also large on facilities with damage to buildings and health problems. It is very important to prepare it so that the possibility of damage or loss can be minimized. This research will apply the Support Vector Machine (SVM) Algorithm by selecting the distribution ratio of training and test data as well as the best kernel function to predict the potential for rain using daily climate data from the Meteorology, Climatology and Geophysics Agency (BMKG) in DKI Jakarta with the help of Rstudio software. The performance evaluated using the confusion matrix method produces the highest accuracy value of 89% is the SVM model with a training data distribution ratio of 90% and the Linear kernel as the chosen model for predicting rain potential.","PeriodicalId":320979,"journal":{"name":"Journal of Artificial Intelligence and Engineering Applications (JAIEA)","volume":"47 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-06-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141384325","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}
Septian Hadi Keswara, Achmad Fauzi, Nurhayati, Stmik Kaputama
{"title":"Image Processing for Freshness Identification Tilapia Using Backpropagation Algorithm (Case Study: Binjai City Food Security and Agriculture Office)","authors":"Septian Hadi Keswara, Achmad Fauzi, Nurhayati, Stmik Kaputama","doi":"10.59934/jaiea.v3i3.478","DOIUrl":"https://doi.org/10.59934/jaiea.v3i3.478","url":null,"abstract":"Tilapia (Oreochromis niloticus) is a type of fish that comes from rivers and lakes that connect the river. Tilapia was imported to Indonesia officially by the Freshwater Fisheries Research Institute in 1969, Tilapia fish breeds in Indonesia come from Taiwan as for the dark color with vertical stripes as many as 6-8 pieces and the Philippines which is red. The problems faced today related to testing the level of freshness still use conventional methods, namely by only seeing and sorting fish by sight or sight only. This can certainly cause errors in choosing fish for ordinary people or who do not have expertise in choosing fresh fish. For this reason, a system is needed that can identify the freshness of tilapia using digital image management. Many methods are used in identifying an image, one of which is used by using the Backpropagation method. \u0000 ","PeriodicalId":320979,"journal":{"name":"Journal of Artificial Intelligence and Engineering Applications (JAIEA)","volume":"50 39","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-06-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141384144","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":"Integrating Heuristic Evaluation and Cognitive Walkthrough in Usability Evaluation of Mobile Application","authors":"Rahma Fitria","doi":"10.59934/jaiea.v3i3.488","DOIUrl":"https://doi.org/10.59934/jaiea.v3i3.488","url":null,"abstract":"This study aims to present the usability evaluation of mobile applications. The growth of mobile applications has been spread to any type of digital activities, especially for paying bills or ordering things. Unfortunately, the lack of interaction design of the application makes the application not easy to use and learn. This study proposed a combination of two usability evaluation methods which are heuristic evaluation and cognitive walkthrough. Myindihome is an application that will be studied to present this evaluation. Those selected methods is employed to evaluate based on the 10’s Nielsen heuristic principle and the Cognitive of the evaluator during the group determination. The heuristic evaluation and cognitive walkthrough are evaluated by 3 experts or evaluators. The result of the heuristic evaluation revealed 3 major issues and 6 minor issues. Whereas the cognitive walkthrough determination revealed that 1 critical main menu needs to be re-designed. Thus, the interaction design of the application in some parts is not easy to learn and not efficient. It is expected this study can be adopted by mobile developers to produce an ease-of-learn and efficient application.","PeriodicalId":320979,"journal":{"name":"Journal of Artificial Intelligence and Engineering Applications (JAIEA)","volume":"9 11","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-06-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141385152","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":"Performance Analysis of Ensemble Learning and Feature Selection Methods in Loan Approval Prediction at Banks","authors":"Iqbal Muhammad, Rizka Dahlia, Muhammad Ifan Rifani Ihsan, Lisnawanty, Rabiatus Sa’adah","doi":"10.59934/jaiea.v3i2.426","DOIUrl":"https://doi.org/10.59934/jaiea.v3i2.426","url":null,"abstract":"Applying for a loan at a bank has a series of relevant assessments based on data and credit scores in determining a borrower's eligibility to receive a loan from the bank. Machine learning is the basis for evaluating whether an individual is worthy of obtaining a loan, in order to reduce the potential risks faced by banks. This research aims to obtain the best accuracy value from the Loan Approval Prediction dataset which is sourced from the open dataset provider website, namely Kaggle. This Loan Approval Prediction dataset has 14 features with 4,269 data. The results of dataset analysis carried out on 4,269 data showed that the amount of data that could be studied was 4,173 data (2,599 data were approved and 1,574 data were rejected). The results of the feature importance evaluation on 14 features show that loan amount is the most important feature compared to other features, while bank asset value is the feature that has the lowest influence. Research on the Loan Approval Prediction dataset was also carried out by testing several Decision Tree ensemble models, including Extreme Gradient Boosting or XGBoost, Light Gradient Boosting Machine (Light GBM), Gradient Boosting, Random Forest, Adaptive Boosting (Adaboost) and Extra Trees. The comparison results show that the XGBoost (Extreme Gradient Boosting) model is the best model, with Accuracy 0.9974, AUC 0.9998, Recall 0.9963, Prec 0.9969, F1 0.9966.","PeriodicalId":320979,"journal":{"name":"Journal of Artificial Intelligence and Engineering Applications (JAIEA)","volume":"12 4","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-02-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"139774143","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":"Classification Analysis Of The Eligibility Of Recipients Of Non-Cash Food Assistance And Family Hope Programs In The City Of Sukabumi Using The Naïve Bayes Classifier Algorithm","authors":"Ariski Muhammad Nazmi, Prajoko, Agung Pambudi","doi":"10.59934/jaiea.v3i2.420","DOIUrl":"https://doi.org/10.59934/jaiea.v3i2.420","url":null,"abstract":"Providing social assistance is the government's effort to improve the welfare of the underprivileged. Non-Cash Food Assistance (BPNT) and the Family Hope Program (PKH) are two social assistance programs provided by the Indonesian government. BPNT is a food assistance program that is provided non-cash through electronic cards, while PKH is a cash social assistance program provided to poor families with certain criteria. Both programs aim to help the poor meet their food and education needs. To evaluate the effectiveness and efficiency of social assistance programs, a method is needed that can process and analyze data quickly and accurately. One method that can be used is the Naïve Bayes Classifier, which is a probabilistic classification method based on Bayes' theorem. This method can be used to classify data into certain categories based on its probability. In this study, researchers used the Naïve Bayes Classifier method to analyze social assistance data obtained from the BPNT and PKH programs. Data from the Sukabumi City Social Service was used to classify the eligibility of beneficiaries using the Naïve Bayes Classifier algorithm. Out of 5,183 data, 31.2% were classified as \"Eligible\" and 68.8% as \"Ineligible\". The algorithm showed 98.77% accuracy in eligibility classification. These results indicate the effectiveness of the Naïve Bayes Classifier algorithm in analyzing social data, providing new insights for better decision-making by relevant agencies in the development of more targeted and efficient social assistance policies","PeriodicalId":320979,"journal":{"name":"Journal of Artificial Intelligence and Engineering Applications (JAIEA)","volume":"40 36","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-02-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"139775693","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":"Performance Analysis of Ensemble Learning and Feature Selection Methods in Loan Approval Prediction at Banks","authors":"Iqbal Muhammad, Rizka Dahlia, Muhammad Ifan Rifani Ihsan, Lisnawanty, Rabiatus Sa’adah","doi":"10.59934/jaiea.v3i2.426","DOIUrl":"https://doi.org/10.59934/jaiea.v3i2.426","url":null,"abstract":"Applying for a loan at a bank has a series of relevant assessments based on data and credit scores in determining a borrower's eligibility to receive a loan from the bank. Machine learning is the basis for evaluating whether an individual is worthy of obtaining a loan, in order to reduce the potential risks faced by banks. This research aims to obtain the best accuracy value from the Loan Approval Prediction dataset which is sourced from the open dataset provider website, namely Kaggle. This Loan Approval Prediction dataset has 14 features with 4,269 data. The results of dataset analysis carried out on 4,269 data showed that the amount of data that could be studied was 4,173 data (2,599 data were approved and 1,574 data were rejected). The results of the feature importance evaluation on 14 features show that loan amount is the most important feature compared to other features, while bank asset value is the feature that has the lowest influence. Research on the Loan Approval Prediction dataset was also carried out by testing several Decision Tree ensemble models, including Extreme Gradient Boosting or XGBoost, Light Gradient Boosting Machine (Light GBM), Gradient Boosting, Random Forest, Adaptive Boosting (Adaboost) and Extra Trees. The comparison results show that the XGBoost (Extreme Gradient Boosting) model is the best model, with Accuracy 0.9974, AUC 0.9998, Recall 0.9963, Prec 0.9969, F1 0.9966.","PeriodicalId":320979,"journal":{"name":"Journal of Artificial Intelligence and Engineering Applications (JAIEA)","volume":"129 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-02-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"139833807","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 the Laplacian of Gaussian Algorithm in Edge Detection Image Processing of Zebra Cross Damage on Highways in the Langkat Regency Area","authors":"Ratih Puspadini, Melda Pita Uli Sitompul","doi":"10.59934/jaiea.v3i2.442","DOIUrl":"https://doi.org/10.59934/jaiea.v3i2.442","url":null,"abstract":"Walking is part of the traveler's movement and is the simplest means of transportation, but it is in a weak position and prone to conflict or accidents when they mix with other modes of transportation. To protect pedestrians, special facilities are needed, one of which is a crossing place (zebra crossing) that is able to serve according to pedestrian needs. Based on Law No. 22 of 2009 concerning Traffic Polytechnic Land Transportation Bali 46 Cross and Road Transportation, article 131 paragraph (2), it is stated that \"Pedestrians are entitled to priority when crossing the road at the crosswalk\". One of the important meanings for human life is the Way. Roads are used as a means of transportation that has a very useful role in efforts to develop human life. In 2018, based on statistical data, the number of motorized vehicle users in Indonesia is increasing every year to reach 146,858,759 units. The impact that occurs is that there are many Zebra Cross roads damaged with conditions that are very troubling and worrying for road users. Among the causes of zebra crossing being damaged will be traffic accidents where the vehicle does not lag obeying the path of the vehicle following the predetermined lane. So this study detects image processing with the Laplacian of Gaussian algorithm with edge detection making it easier for the government to improve traffic signs of zebra crossing images on highways that are worthy of improvement so that accidents do not occur. The results of this study illustrate the image of being able to see damaged zebra crossings with calculations of the Laplacian of Gaussian algorithm.","PeriodicalId":320979,"journal":{"name":"Journal of Artificial Intelligence and Engineering Applications (JAIEA)","volume":"898 ","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-02-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"139835131","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":"Forescating the Amount of Corn Production in North Sumatra Based on 2017 – 2021 Data Using The Single and Double Exponential Smoothing Method (Case Study of Central Bureau of Statistics of North Sumatra )","authors":"Syairul Amri Saragih, Asritanarni Munar, Wilda Rina","doi":"10.59934/jaiea.v3i2.449","DOIUrl":"https://doi.org/10.59934/jaiea.v3i2.449","url":null,"abstract":"North Sumatra Province has high potential in the management and marketing of corn (Zae Mays) crops. Cultivation of corn plants is a superior product where the largest income is obtained from the sale of commodities and their processing so that they can assist the government in improving the economy. This study aims to determine the yield of corn in North Sumatra Province in the coming year. Data collection for this study uses secondary data, namely primary data obtained from other parties which are generally made in the form of tables and diagrams. Data obtained from the Central Bureau of Statistics of North Sumatra for corn production in 2017 was 1,741,257 tons, corn production in 2018 was 1,710,784 tons, corn production in 2019 was 1,960,424 tons, corn production in 2020 was 1,965. 444 tons, corn production in 2021 is 1,724,398 tons. To find out the increase in corn production, the consideration and comparison of the forecasting methods needed to minimize forecast errors that aim to approach reality are the single and double exponential smoothing methods with one parameter from Brown.","PeriodicalId":320979,"journal":{"name":"Journal of Artificial Intelligence and Engineering Applications (JAIEA)","volume":"216 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-02-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140455597","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}