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
Small Timescaled Data for Covid-19 Prediction with RNN-LSTM in Tangerang Regency Sagita Sasmita Wijaya; Marlinda Vasty Overbeek
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.v6i1.21676

Abstract

Throughout the pandemic, many people have become familiarised with the new type of virus that has been spreading throughout the world, called the Coronavirus. On the 2nd of March, the year 2020, the Indonesian government had announced the identification of first Covid-19 case in Indonesia. With the arrival of Covid-19, and its spreading across all the provinces of Indonesia, the number of positive cases keeps growing even in the present day. Tangerang Regency is one of the areas that has opaqued citizens in the Banten Province. The purpose of this research is to discuss how to predict the sum of Covid-19 cases in the Tangerang Regency using the RNN-LSTM method. Although this method is very eloquent if used to perform a sequential task, its complexity and loss of gradient can make this model difficult to be trained, hence resulting in the use of the Long Short-Term Memory (LSTM) to reduce these weaknesses and help the RNN to look back on past data. This research uses Python as the programming language and Jupyter Notebook for the visualization of the results of the prediction. Therefore, the prediction model has been evaluated using various computational methods, such as RMSE with its error percentage of 0.05, and MSE and MAE with the same error percentage of 0.03 with the loss of their models being 9.6793e-04.
An Ensemble Voting Approach for Dropout Student Classification Using Decision Tree C4.5, K-Nearest Neighbor and Backpropagation Daffa Nur Cholis; Nurissaidah Ulinnuha
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.v6i1.23412

Abstract

Many factors cause drop out in students. This study classified active students and drop out students using 1092 student data consisting of 557 active student data and 535 drop out student data. The independent variables used are Semester, Semester Credit Units (SKS), Semester Grade Point Average (IPS), Grade Point Average (IPK), admission pathways and Single Tuition Fee (UKT). Classification is carried out using the Ensemble Voting method where the method will combine the Decision Tree C4.5, KNN and Backpropagation methods as a single method. In addition to knowing the classification of active students and drop out students, this study aims to prove whether the Ensemble Voting method is able to get better results than the single method. This classification using a comparison of training and testing data of 90:10 to build model. Classification results from a single method will be included in the Ensemble Voting method. The Decision Tree C4.5 method gets 95.45% accuracy, 98.03% precision and 92.59% recall. KNN gets 96.36% accuracy, 100% precision and 92.59% recall. Backpropagation gets 90.90% accuracy, 95.83% precision and 95.18% recall. Meanwhile, the Ensemble Voting rule used is Ensemble Soft Voting with a weight of (2,1,1). Ensemble Voting with Ensemble Soft Voting rules is able to improve the accuracy, precision and recall values with 98.18% accuracy, 100% precision and 96.29% recall.
Method of Application of Support Vector Regression In Predicting The Number of Visits of Foreign Tourists to The Province of Maluku Wahyuni Aprilya; Marlon S. N. Van Delsen; M. Y. Matdoana
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.v6i1.19803

Abstract

Maluku Province is one of the areas in Indonesia that has many tourist attractions to visit, both natural and cultural heritage. The high interest of foreign tourists who want to visit various tourist objects, makes the tourism industry able to bring benefits and profits for most of the people of Maluku. However, in the last two years, 2020-2021, all countries were faced with the Covid-19 pandemic. The Covid-19 pandemic has resulted in a decrease in the number of foreign tourist visits to Indonesia. To increase marketing activities in the midst of the Covid-19 pandemic that has hit Indonesia since 2020, foreign tourist information is increasingly needed as material for evaluation and planning for future development. One of the methods used to predict the number of foreign tourist visits to Maluku Province is Support Vector Regression (SVR). Based on forecasting using test data, the RMSE value is 1.334985 and the MAPE obtained is 1.256346%, so the prediction of the number of foreign tourist visits to Maluku Province in 2022 (January-June) states that in January the number of tourist visits was 999 hundred visits. and increased until June as many as 1121 thousand visits.
Virtual Assistant for Thesis Technical Guide Using Artificial Neural Network Mohammad Ovi Sanjaya; Saiful Bukhori; Muhammad `Ariful Furqon
Indonesian Journal of Artificial Intelligence and Data Mining Vol 6, No 2 (2023): September 2023
Publisher : Universitas Islam Negeri Sultan Syarif Kasim Riau

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.24014/ijaidm.v6i2.23473

Abstract

This study focuses on finding best practice for Artificial Neural Network (ANN) implementation in the information system for student’s thesis technical instructions. The machine learning model applied sequential model, it means ANN only use 1 input layer, a hidden/dense layer and 1 output layer. The Stochastic Gradient Decent (SGD) method was applied into data training process. The results of this study are chatbot applications, and model testing using the confusion matrix. The result of model evaluation are 99,49% accuracy and 91% in F-1 score.
Hybrid Machine Learning Techniques for Comparative Opinion Mining Bernard Omoi Ondara; Stephen Waithaka; John Kandiri; Lawrence Muchemi
Indonesian Journal of Artificial Intelligence and Data Mining Vol 6, No 2 (2023): September 2023
Publisher : Universitas Islam Negeri Sultan Syarif Kasim Riau

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.24014/ijaidm.v6i2.22644

Abstract

Comparative opinion mining has lately gained traction among individuals and businesses due to its growing range of applications in brand reputation monitoring and consumer decision making among others. Past research in sub-field of opinion mining have mostly explored single-entity opinion mining models and the mining of comparative sentences suing single classifiers. Most of these studies relied on a limited number of comparative opinion labels and datasets while applying the techniques in limited domains. Consequently, the reported performances of the techniques might not be optimal in some cases like working with big data. In this study, however, we developed four hybrid machine learning techniques, with which we performed multi-class based comparative opinion mining using three datasets from different domains.  From our results, the best-performing hybrid machine learning technique for comparative opinion mining using a multi-layer perceptron as the base estimator was the Multilayer Perceptron + Random Forest (MLP + RF). This technique had an average accuracy of 93.0% and an F1-score of 93.0%. These results show that our hybrid machine learning techniques could reliably be used for comparative opinion mining to support business needs like brand reputation monitoring.
The Use of Large Databases for Diagnosing Human Diseases at Early Stage Abdullah M. Al Al-Ansi; Vladimir Ryabtsev; Tatyana Utkina
Indonesian Journal of Artificial Intelligence and Data Mining Vol 6, No 2 (2023): September 2023
Publisher : Universitas Islam Negeri Sultan Syarif Kasim Riau

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.24014/ijaidm.v6i2.24525

Abstract

The purpose of this article is to demonstrate the ability of the Eidos intellectual system to recognize human diseases at an early stage by processing large databases containing signs of diseases. To study the signs of diseases, it is proposed to use an automated system-cognitive analysis implemented in the Eidos intellectual system. Automated system-cognitive analysis extracts information from large databases and forms knowledge from them that makes it possible to recognize human diseases. In the process of forming models, the amount of information is calculated in the value of the factor by which the modeling object will pass under its influence to a certain state corresponding to the class. This allows for comparable and correct processing of heterogeneous information about observations of the object of modeling, presented in different types of measuring scales and different units of measurement. The results of recognition of the following diseases were obtained with high reliability: chronic kidney disease, lung cancer, breast cancer, liver disease, risks of developing diabetes and stroke. The results of the study can be applied in medical institutions in many countries, since the Eidos system is freely available on the Internet.
Fuzzy Tsukamoto-Based Detection of Ping of Death Attacks: Advancing Network Security with Precise Classification Muhammad Adam Hawari; Wahyu Adi Prabowo; Rifki Adhitama
Indonesian Journal of Artificial Intelligence and Data Mining Vol 6, No 2 (2023): September 2023
Publisher : Universitas Islam Negeri Sultan Syarif Kasim Riau

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.24014/ijaidm.v6i2.23858

Abstract

Internet services have the potential to be targeted by hackers using various DDoS (Distributed Denial of Service) attack techniques, including the ping of death attack. This attack involves multiple machines launching simultaneous attacks on the database server and File Transfer Protocol (FTP), resulting in severe consequences for computer networks. To effectively classify such attacks, the Fuzzy Tsukamoto method is employed, which represents each IF-THEN rule as a Fuzzy set with a corresponding membership function. Fuzzy logic offers great flexibility, tolerance for imprecise data, and the ability to model highly complex and nonlinear functions. By implementing this classification technique, it becomes easier to differentiate and analyze network traffic captured by Wireshark, enabling the detection of ping of death attacks against the server with maximum accuracy through the Fuzzy Tsukamoto method in the classification process.
Harnessing the Power of Stacked GRU for Accurate Weather Predictions Mohammad Diqi; Ahmad Wakhid; I Wayan Ordiyasa; Nurhadi Wijaya; Marselina Endah Hiswati
Indonesian Journal of Artificial Intelligence and Data Mining Vol 6, No 2 (2023): September 2023
Publisher : Universitas Islam Negeri Sultan Syarif Kasim Riau

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.24014/ijaidm.v6i2.24769

Abstract

This research proposed a novel approach using Stacked GRU (Gated Recurrent Unit) models to address the problem of weather prediction and aimed to improve forecasting accuracy in sectors like agriculture, transportation, and disaster management. The key idea involved leveraging the temporal dependencies and memory management capabilities of Stacked GRU to model complex weather patterns effectively. Comprehensive data preprocessing ensured data quality and fine-tuning of the model architecture and hyperparameters optimized performance. The research demonstrated the Stacked GRU model's effectiveness in accurately forecasting temperature, pressure, humidity, and wind speed, validated by low RMSE and MAE scores and high R2 coefficients. However, challenges in forecasting humidity and a percentage discrepancy in wind speed predictions were observed. Overfitting and computational complexity were identified as potential limitations. Despite these constraints, the study concluded that the Stacked GRU model showed promise in weather forecasting and warranted further refinement for broader applications in time-series prediction tasks.
Trends and Advances on The K-Hyperparameter Tuning Techniques in High-Dimensional Space Clustering Rufus Kinyua Gikera; Jonathan Mwaura; Elizaphan Maina; Shadrack Mambo
Indonesian Journal of Artificial Intelligence and Data Mining Vol 6, No 2 (2023): September 2023
Publisher : Universitas Islam Negeri Sultan Syarif Kasim Riau

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.24014/ijaidm.v6i2.22718

Abstract

Clustering is one of the tasks performed during exploratory data analysis with an extensive and wealthy history in a variety of disciplines. Application of clustering in computational medicine is one such application of clustering that has proliferated in the recent past. K-means algorithms are the most popular because of their ability to adapt to new examples besides scaling up to large datasets. They are also easy to understand and implement. However, with k-means algorithms, k-hyperparameter tuning is a long standing challenge. The sparse and redundant nature of the high-dimensional datasets makes the k-hyperparameter tuning in high-dimensional space clustering a more challenging task. A proper k-hyperparameter tuning has a significant effect on the clustering results. A number of state-of-the art k-hyperparameter tuning techniques in high-dimensional space have been proposed.  However, these techniques perform differently in a variety of high-dimensional datasets and data-dimensionality reduction methods. This article uses a five-step methodology  to investigate the trends and advances on the state of the art k-hyperparameter tuning techniques in high-dimensional space clustering, data dimensionality reduction methods used with these techniques, their tuning strategies, nature of the datasets applied with them as well as the challenges associated with the cluster analysis in high-dimensional spaces. The metrics used in evaluating these techniques are also reviewed. The results of this review, elaborated in the discussion section, makes it efficient for data science researchers to undertake an empirical study among these techniques; a study that subsequently forms the basis for creating improved solutions to this k-hyperparameter tuning problem.
Artificial General Intelligence (AGI) and Its Implications For Contract Law Wahyudi Umar; Sudirman Sudirman; Rasmuddin Rasmuddin
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.v6i1.24704

Abstract

The development of artificial intelligence technology has presented AGI as an exciting future potential. In contract law, AGI can change the landscape of agreements and contract execution. The existence of AGI will raise various legal challenges and questions, such as whether AGI can be a legal party to a contract, whether AGI can execute contracts effectively, and how legal responsibility AGI is in contract execution. This study aims to analyze and identify the legal implications that may arise with the existence of AGI in the context of contract law. In this regard, the research will try to understand how AGI can influence existing principles of contract law. This study uses normative research methods by collecting and analyzing relevant legal sources, including legal literature, regulations, and court rulings related to contract law. This research also involves a comparative study of existing contract law with possible future situations with the existence of AGI. The results of this study show that the presence of AGI has the potential to change important aspects of contract law. Some of the implications identified include questions about AGI's legal status as a legal subject, AGI's legal liability in the performance of contracts, aspects of the validity and interpretation of contracts involving AGI, and legal protection for parties entering transactions with AGI. This research provides a crucial initial understanding in dealing with legal challenges that may arise due to the existence of AGI in the context of contract law

Page 9 of 21 | Total Record : 207