cover
Contact Name
Mustakim
Contact Email
Mustakim
Phone
-
Journal Mail Official
ijaidm@uin-suska.ac.id
Editorial Address
-
Location
Kab. kampar,
Riau
INDONESIA
Indonesian Journal of Artificial Intelligence and Data Mining
ISSN : 26143372     EISSN : 26146150     DOI : -
Core Subject : Science,
Indonesian Journal of Artificial Intelligence and Data Mining (IJAIDM) is an electronic periodical publication published by Puzzle Research Data Technology (Predatech) Faculty of Science and Technology UIN Sultan Syarif Kasim Riau, Indonesia. IJAIDM provides online media to publish scientific articles from research in the field of Artificial Intelligence and Data Mining. IJAIDM will be published 2 (two) times a year, in March and September, each edition contains 7 (seven) articles. Articles may be written in English or Indonesia.
Arjuna Subject : -
Articles 207 Documents
Algorithm Decission Tree C4.5 and Backpropagation Neural Network for Smarthpone Price Classification Muhammad Ridho Al Fathan; M Fadhil Arfa; Habibah Br. Lumbantobing; Rahmaddeni Rahmaddeni
Indonesian Journal of Artificial Intelligence and Data Mining Vol 5, No 2 (2022): September 2022
Publisher : Universitas Islam Negeri Sultan Syarif Kasim Riau

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.24014/ijaidm.v5i2.19064

Abstract

Smartphones are a necessity in this technological age. In fact, everyone has at least one smartphone, this is because of its role that can help daily activities. There are data smartphone prices from major companies from Kaggle. The data is divided into 2000 training data and 1000 test data, the price range of smartphones based on the features provided. The analysis needed is the relationship between the features of smartphone and the selling price. To get this information, data mining techniques can be used. This study uses the Decission Tree C4.5 algorithms and the Backpropagaition Neural Network algorithm for classification problems. The technique used will be compared to a better algorithm in carrying out the classification process. The classification method consists of predictor variables and one target variable. The software used to process the data is Rapid Miner software. The results of the study get the accuracy of the Backpropagation Neural Network algorithm 96.65% and the same data is also applied to the C4.5 algorithms with an accuracy of 83.75%. From the research results, it can be concluded that the backpropagation neural network algorithm is the best algorithm for smartphone price classification with accuracy 96.65%.
Early Detection of COVID-19 Disease Based on Behavioral Parameters and Symptoms Using Algorithm-C5.0 Joko Riyono; Aina Latifa Riyana Putri; Christina Eni Pujiastuti
Indonesian Journal of Artificial Intelligence and Data Mining Vol 6, No 1 (2023): Maret 2023
Publisher : Universitas Islam Negeri Sultan Syarif Kasim Riau

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.24014/ijaidm.v6i1.22074

Abstract

The spread of COVID-19 disease has continued since it was first discovered at the end of 2019 until now. Transmission of COVID-19 is very fast, including through close contact through droplets and through the air. Therefore, early detection of COVID-19 is very important for patients and also those around them to be able to fight the COVID-19 pandemic because if patients get proper and fast treatment, then other people around them will be protected. In this study, an analysis of the classification of decision making for COVID-19 detection was carried out based on behavioral parameters and symptoms that could trigger exposure to COVID-19 using the C5.0 algorithm, followed by measuring the performance of the model using the Confusion Matrix. The C5.0 algorithm is a decision tree-based data mining method. The results of the C5.0 algorithm use a comparison of training data and test data of 70:30. After going through the Confusion Matrix test, an accuracy value of 98% is obtained which indicates that the resulting classification is very good, so that the resulting model can be used for early detection of COVID-19 patients.
Glaucoma Identification on Retinal Fundus Image Using Random Forest Method Iga Novinda Rantaya
Indonesian Journal of Artificial Intelligence and Data Mining Vol 6, No 1 (2023): Maret 2023
Publisher : Universitas Islam Negeri Sultan Syarif Kasim Riau

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.24014/ijaidm.v6i1.18765

Abstract

Glaucoma is a disease caused by a buildup of fluid in the eye that can increase intraocular pressure and cause vision loss. This disease cannot be cured, therefore early detection is very important to prevent total vision loss in sufferers. To reduce the errors of observation and diagnosis from doctors, applied computer vision to detect glaucoma in retinal fundus images. The retinal fundus image is first cropped to remove unnecessary parts, then the color image captured by the fundus camera is converted into a grayscale image. The gray scale image will be extracted using the Gray Level Co-occurrence Matrix (GLCM) method. The extracted features will be processed to create a classification model using the Random Forest method which will determine whether the image identified is normal or glaucoma. A series of experiments were conducted on the comparison of training data and testing data, as well as the number of decision trees. Experiments were also conducted on the size of the image cropping and changes in the value of the distance variable in the GCLM feature extraction process. The results of the experiment on an image size of 720x720 pixels and a distance value of 2, obtained a model with an accuracy of 81%, precision 79% and recall 88% in a data comparison of 80:20, and the number of trees as much as 50. The results show that the more number of decision trees does not increase the number of decision trees. accuracy value significantly.
Prediction of Indonesia School Enrollment Rate by Using Adaptive Neuro Fuzzy Inference System Bibit Waluyo Aji; Neza Zhevira Septiani; Wyne Mumtaazah Putri; Bambang Irawanto; Bayu Surarso; Farikhin Farikhin; Yosza Dasril
Indonesian Journal of Artificial Intelligence and Data Mining Vol 6, No 1 (2023): Maret 2023
Publisher : Universitas Islam Negeri Sultan Syarif Kasim Riau

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.24014/ijaidm.v6i1.21839

Abstract

The study aimed to predict the school enrollment rate in Indonesia using the Adaptive Neuro Fuzzy Inference System (ANFIS). ANFIS is a combination of fuzzy inference system and artificial neural networks. The study used the Gaussian and Gbell membership functions to make the predictions. The results were evaluated using the R square score (coefficient of determination) and Mean Square Error methods. The results showed that the model performed well in predicting the school enrollment rate, particularly in the age categories of 7-12 years and 13-15 years. The R square score for these categories was 0.981551771 and 0.989081085, respectively, while the Mean Square Error was 0.023947290 and 0.3675162695238, respectively. The performance of the model in the age categories of 16-18 years and 19-24 years was also good, but with a slightly lower R square score and Mean Square Error compared to the younger age categories. When using the Gaussian membership function, the model performed even better, particularly in the age categories of 13-15 years and 19-24 years. The R square score for these categories was 0.99020792 and 0.9883091, respectively, while the Mean Square Error was 0.32958834 and 0.31523466571, respectively. Overall, the study demonstrated that ANFIS is a suitable method for predicting school enrollment rate in Indonesia. The results from this study can provide useful information for decision makers in the education sector, who can use the model to make informed decisions about future educational policies and programs.
Comparison of Naïve Bayes Algorithm, Support Vector Machine and Decision Tree in Analyzing Public Opinion on COVID-19 Vaccination in Indonesia Rahmaddeni Rahmaddeni; Firman Akbar
Indonesian Journal of Artificial Intelligence and Data Mining Vol 6, No 1 (2023): Maret 2023
Publisher : Universitas Islam Negeri Sultan Syarif Kasim Riau

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.24014/ijaidm.v6i1.19966

Abstract

The spread of COVID-19 in Indonesia has caused many negative impacts. Therefore, the government is taking vaccination measures to suppress the spread of COVID-19. Public response to vaccinations on Twitter has been mixed, with some supporting it and some not. The data for this study comes from the Twitter feed of the drone portal Emprit Academy (dea). Classification is performed using SVM, decision tree and Naive Bayes algorithm. The purpose of this study is to inform the public about whether vaccination against COVID-19 is inclined toward positive, neutral, or negative opinions. Moreover, this study compares the accuracy of the three algorithms used, namely Naive Bayes (NB), Support Vector Machine (SVM) and Decision Tree, and the validation performed using the K-Fold Cross-Validation method, AdaBoost feature selection, and the TF-IDF Transformer feature extraction test. The result obtained from this study is that the accuracy of the 90:10 data keeps improving, dividing by 82.86% on the SVM algorithm, 81.43% on the Naive Bayes and 78.57% on the decision tree.
Performance Comparison of Data Mining Classification Algorithms on Student Academic Achievement Prediction Munarsih Munarsih; Besse Arnawisuda Ningsi
Indonesian Journal of Artificial Intelligence and Data Mining Vol 6, No 1 (2023): Maret 2023
Publisher : Universitas Islam Negeri Sultan Syarif Kasim Riau

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.24014/ijaidm.v6i1.21874

Abstract

Academic achievement is one of the benchmarks of student success in carrying out the learning process. Grade Point Average (GPA) is a reference for universities in determining student academic achievement. For universities, academic achievement can be an indicator of determining the success of the learning system and can improve the image of the university. This study aims to determine the prediction of academic achievement results of Pamulang University students with Naive Bayes, C4.5 and KNN, and to determine the comparison results of Naive Bayes, C4.5 and KNN algorithms in predicting the academic achievement of Pamulang University students. The algorithms compared in this study are Naive Bayes, C4.5 and K-Nearest Neighbor (KNN) algorithms, using the factors of gender, age, faculty, regional origin, work status, organisation participation, type of school origin, distance of residence, and parents' profession as artibut. The results of this study show that the KNN algorithm is the algorithm with the greatest accuracy rate of 56.25%, followed by the Naive Bayes algorithm and the C4.5 algorithm with an accuracy rate of 50.00%.
Clustering of Tuberculosis and Normal Lungs Based on Image Segmentation Results of Chan-Vese and Canny with K-Means Fayza Nayla Riyana Putri; Nur Cahyo Hendro Wibowo; Hery Mustofa
Indonesian Journal of Artificial Intelligence and Data Mining Vol 6, No 1 (2023): Maret 2023
Publisher : Universitas Islam Negeri Sultan Syarif Kasim Riau

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.24014/ijaidm.v6i1.21835

Abstract

The lungs are a vital organ in the human body. If there is interference with lung function, the health of the human body as a whole can be affected. Examination by medical workers needs to be done when there is interference with lung function. This examination can usually be done in various ways, one of which is through a chest X-ray radiographic examination procedure. The application of Artificial Intelligence is growing rapidly in the medical field, especially in diagnostics and treatment management. Artificial intelligence in the medical world can also be applied in processing image data in radiology to analyze X-ray results as supporting diagnostic information. Operators Chan-Vese and Canny are two edge detection operators in digital image processing in an effort to obtain the necessary information based on the shape and size of the object. This study was conducted for clustering of normal and tuberculosis lung conditions based on the results of chest X-ray image segmentation from Chan-Vese and Canny using K-Means Clustering. The results of clustering using K-Means obtained an accuracy value of 77.1%, a precision value of 88%, and a specificity value of 97.2%
Image Classification of Beef and Pork Using Convolutional Neural Network Architecture EfficienNet-B1 Isnan Mellian Ramadhan; Jasril - Jasril; Suwanto Sanjaya; Febi Yanto; Fadhilah Syafria
Indonesian Journal of Artificial Intelligence and Data Mining Vol 6, No 1 (2023): Maret 2023
Publisher : Universitas Islam Negeri Sultan Syarif Kasim Riau

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.24014/ijaidm.v6i1.21843

Abstract

The increasing demand for beef has made many meat traders mix beef with pork to get more profit. Mixing beef and pork is harmful, especially for Muslims. In this study, the EfficientNet-B1 Convolutional Neural Network (CNN) approach was used to classify beef and pork. Experiments were conducted to compare accuracy using original data (without data augmentation) and with data augmentation. The data augmentation techniques used are rotation and horizontal flip. The total dataset after the data augmentation process is 3000 images. Many different settings were tested, including learning rates (0.00001, 0.0001, 0.001, 0.01, 0.1), batch size (32, 64), and optimizer (Adam, Adamax). After testing the Confusion Matrix, the highest accuracy results were obtained using data augmentation with a batch size of 32 of 98%. Meanwhile, those without data augmentation were 96%
Forecasting The Value of Indonesian Oil-Non-Oil and Gas Imported Using The Gated Recurrent Unit (GRU) Dian Kurniasari; Sulistian Oskavina; Wamiliana Wamiliana; Warsono Warsono
Indonesian Journal of Artificial Intelligence and Data Mining Vol 6, No 1 (2023): Maret 2023
Publisher : Universitas Islam Negeri Sultan Syarif Kasim Riau

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.24014/ijaidm.v6i1.20651

Abstract

In Indonesia, various factors play a role in economic development. Oil-non-oil and gas imports are one of the main factors. However, the value of oil-non-oil and gas imports in Indonesia fluctuates monthly. Therefore, an appropriate method is required to monitor changes in the value of oil-non-oil and gas imports in Indonesia so that the government can make the right choices. This study uses the GRU method to estimate the amount of oil-non-oil and gas imports in Indonesia. The best model for forecasting over the next two years has an optimum structure of 32 GRU units, 16 batch sizes, and 100 epochs, with a dropout of 0.2 and uses 80% training data and 20% test data. The MAPE value obtained is 0.999955%, with an accuracy of 99.000044%. Forecast results suggest an improvement from June 2022 to July 2024.
Watermarking Study on The Vector Map Hartanto Tantriawan; Rinaldi Munir
Indonesian Journal of Artificial Intelligence and Data Mining Vol 6, No 1 (2023): Maret 2023
Publisher : Universitas Islam Negeri Sultan Syarif Kasim Riau

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.24014/ijaidm.v6i1.22211

Abstract

In addition to being employed in a variety of military and security applications, GIS vector maps are frequently used in social, environmental, and economic applications like navigation, business planning, infrastructure & utility allocation, and disaster management. Given the high value of this map, copyright protection is implemented in the watermarking as a required safeguard against unauthorized modification and exchange of GIS vector maps. Watermarking is inserting information (watermark) stating ownership of multimedia data. This paper discusses several approaches that can be used to watermark vector maps, including using the space-domain algorithm and transform-domain algorithm. Second The watermarking algorithm was developed with the following quality metrics: fidelity, robustness, capacity, complexity, and security. The challenge in this study is that the higher the capacity, the lower the fidelity value. Low fidelity causes map properties to be lost, making the map unusable. These two things need to be balanced.

Page 8 of 21 | Total Record : 207