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 233 Documents
Classification of Big Data Stunting Using Support Vector Regression Method at Stella Maris Medan Maternity Hospital Chen, Kelvin; Adriansyah, R. A. Fattah; Juliandy, Carles; Sinaga, Frans Mikael; Liko, Frederick; Angkasa, Aswin
Indonesian Journal of Artificial Intelligence and Data Mining Vol 7, No 2 (2024): September 2024
Publisher : Universitas Islam Negeri Sultan Syarif Kasim Riau

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.24014/ijaidm.v7i2.31112

Abstract

This study aims to classify big data related to stunting using the Support Vector Regression (SVR) method at Stella Maris Maternity Hospital, Medan. Stunting, a condition of impaired growth in children due to chronic malnutrition and repeated infections, affects physical and cognitive development. With increasing health data, big data processing methods are essential for accurate information. SVR was chosen for handling high-dimensional and non-linear data, providing precise results. The study uses medical information, nutritional history, and socio-economic factors collected from hospital patients. The research process includes data collection, pre-processing to address missing values and outliers, normalization, and SVR application. Final results use SVR with Voting Classifier combining Support Vector Classifier (SVC), Random Forest (RF), and Gradient Boosting (GB), achieving an accuracy of 91.67%. This approach effectively identifies main stunting factors, aiding clinical decision-making and intervention programs. The study showcases big data and machine learning's potential in healthcare, serving as a model for improving health services and monitoring children's health conditions.
Crowd Density Level Classification for Service Waiting Room Based on Head Detection to Enhance Visitor Experience Istiqomah, Atika; Seida, Fatih; Daradjat, Nadhira Virliany; Kesuma, Rahman Indra; Utama, Nugraha Priya
Indonesian Journal of Artificial Intelligence and Data Mining Vol 7, No 2 (2024): September 2024
Publisher : Universitas Islam Negeri Sultan Syarif Kasim Riau

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.24014/ijaidm.v7i2.29965

Abstract

The crowd within a confined space can potentially lead to air stagnation in waiting areas. Constantly running air conditioning throughout the day to balance air circulation may result in excessive energy consumption by the building. To address this issue, Heating, Ventilating, and Air-Conditioning (HVAC) systems are employed to manage and regulate indoor energy usage. However, sensor-based detection often fails to capture human variables promptly, resulting in less accurate density readings. Camera footage proves to be more reliable than sensors in accurately detecting crowds. This research utilizes You Only Look Once version 8 (YOLOv8), a robust algorithm for object detection, particularly effective in crowd detection for images, along with Convolutional Vision Transformer (CvT) for crowd density level classification into "Normal" and "Crowded" levels. CvT enhances classification accuracy by incorporating function from Convolutional Neural Network (CNN) in model training, including receptive field, shared weights, etc. By integrating YOLOv8 and CvT, this method focuses on accurately classifying crowd density levels after identifying human presence in the waiting area (indoor). Evaluation metrics include mean Average Precision (mAP) for YOLOv8, and accuracy, precision, recall, and f1-score for CvT. This approach directly influences the management of HVAC systems.
Implementation of Supervised Learning Method In Grapevine Leaf Classification Lifindra, Stevanie Aurelia; Yuadi, Imam
Indonesian Journal of Artificial Intelligence and Data Mining Vol 8, No 1 (2025): March 2025
Publisher : Universitas Islam Negeri Sultan Syarif Kasim Riau

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.24014/ijaidm.v8i1.31633

Abstract

Grapevine leaves are a type of leaf variety that is difficult to identify because it will take time if processed manually so research will be carried out using the help of machine learning. This research aims to classify 5 varieties of grapevine leaves using orange data mining and several classification methods namely k-Nearest Neighbors (kNN), logistic regression, random forest and support vector machine (SVM). The dataset used is 500 images and 5 classes where each class consists of 100 images, namely Ak (100), Buzgulu (100), Ala_Idris (100), Dimnit (100), and Nazli (100). The stages in the analysis process are to enter the image into orange data mining by passing several stages so that the image dataset can be processed and read on the test and score so that the confusion matrix can be obtained. The results of the research conducted using orange data mining show that classification using logistic regression gives the best results at a precision value of 0.848% and a recall value of 0.847%. This research shows that classification using orange data mining also provides good results, besides that this research can also help in the classification process so that it does not require a long time.
Analysis of Student Dropout Potential Using the Multinomial Naive Bayes Algorithm Afrianti, Dewi; Armansyah, Armansyah
Indonesian Journal of Artificial Intelligence and Data Mining Vol 7, No 2 (2024): September 2024
Publisher : Universitas Islam Negeri Sultan Syarif Kasim Riau

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.24014/ijaidm.v7i2.32316

Abstract

The current situation of education in Indonesia is quite concerning, especially with the high dropout rate which is one of the main problems. The variation in dropout rates in various educational institutions, including at Muhammadiyah 9 Vocational High School in Medan, reflects the diversity of challenges faced. This study aims to analyze the supporting factors that influence the potential for student dropout using the Naive Bayes Multinomial method, especially at this school. The results of the study showed that the model could understand the data with a classification performance accuracy of 83.04% at the 20% dataset testing stage. Through this test, 76 active students, 11 students with the potential to drop out, and 25 students dropped out were obtained. Meanwhile, precision, recall, and f1-score in the class with the potential to drop out cannot be displayed because the class comparison is unbalanced.
Sawit Kita WebApp Development: Artificial - Based E-Learning Intelligence and Community to Drive Actual Information Collaboration and Innovation of Palm Oil Farmers In Indonesia Patricia, Ony; Wahabbi, Alif Budiman; Syafrianto, Edy; Putra, Fajar Kurnia; Andesti, Cyntia Lasmi
Indonesian Journal of Artificial Intelligence and Data Mining Vol 7, No 2 (2024): September 2024
Publisher : Universitas Islam Negeri Sultan Syarif Kasim Riau

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.24014/ijaidm.v7i2.31366

Abstract

Web App development within the scope of the company is very in necessary in today's technological era. Development increasingly advanced technology is proof that the level of technology is high in the field of computer science. Data management is very important for a company companies, especially palm oil companies. A company needs a tool or system for managing and monitoring data company to be more efficient, simple, fast and precise. There fore the author designing a system to make it easier for companies to manage data palm oil plantations using a very easy Web App used. This research aims to develop the Sawit Kita Web App, an Artificial Intelligence based e-learning platform and community forpalm oil farmers in Indonesia. The Sawit Kita Web App consists of three main features, namely GPT 4 chat, e-learning modules and community platform. Chat GPT 4 is an Artificial Intelligence-based virtual assistant that can answer questions, provide suggestions, and produce creative content about oil palm cultivation with customization of data input by developer. The e-learning module is a feature that provides interactive and easy-to-understand learning materials about cultivation sustainable palm oil. The community platform is a feature that facilitate communication and collaboration between oil palm farmers and researchers, extension workers, and other related parties in a discussion forum. Target This research is to improve access and quality of information, literacy and skills, participation and collaboration, as well as productivity and well-being palm oil farmers in Indonesia. The research method used is method research and development with stages of analysis, design, development, implementation, and evaluation. This research is expected to provide contribution to the development of the oil palm plantation sector in Indonesia.
Implementation of Fingerprint Biometrics on Smart Door Entrance Access Integrated with Internet of Things-based PINs Handini, Wulan Tri; Endri, Jon; Salamah, Irma
Indonesian Journal of Artificial Intelligence and Data Mining Vol 8, No 1 (2025): March 2025
Publisher : Universitas Islam Negeri Sultan Syarif Kasim Riau

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.24014/ijaidm.v8i1.31738

Abstract

Security is something that must often be ignored by most people and think it is safe, but it turns out that someone can still lose their valuables. In this final project, we will design an Internet of Things (IoT)-based smart door access tool that uses a fingerprint and pin password using the Optical Scanner Sensor method. The purpose of making and designing a smart door tool based on the Internet of Things (IoT) is one of them to apply the optical method as a method used to recognize fingerprint biometric identification. By using a smartphone (android) as a controller using the NodeMCU contained in the ESP2866 WiFi module via an internet connection connected to an application made with MIT App Inventor. In the application of fingerprint sensors using the optical method, the scanning process is obtained through finger scanning based on the effect of light reflection that occurs on the optical sensor on the fingerprint.   So as to produce digital image retrieval on identified fingerprints. The communication that uses the fingerprint sensor and Arduino uno as a data processing unit uses serial data communication. When the command has run according to its function, the results of the data obtained enter in realtime at the data processing place.
A Hybrid CNN-RNN Model for Enhanced Anemia Diagnosis: A Comparative Study of Machine Learning and Deep Learning Techniques Airlangga, Gregorius
Indonesian Journal of Artificial Intelligence and Data Mining Vol 7, No 2 (2024): September 2024
Publisher : Universitas Islam Negeri Sultan Syarif Kasim Riau

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.24014/ijaidm.v7i2.29898

Abstract

This study proposes a hybrid Convolutional Neural Network-Recurrent Neural Network (CNN-RNN) model for the accurate diagnosis of anemia types, leveraging the strengths of both architectures in capturing spatial and temporal patterns in Complete Blood Count (CBC) data. The research involves the development and evaluation of various models of single-architecture deep learning (DL) models, specifically Multi-Layer Perceptron (MLP), Convolutional Neural Network (CNN), Recurrent Neural Network (RNN), and Fully Convolutional Network (FCN). The models are trained and validated using stratified k-fold cross-validation to ensure robust performance. Key metrics such as test accuracy are utilized to provide a comprehensive assessment of each model's performance. The hybrid CNN-RNN model achieved the highest test accuracy of 90.27%, surpassing the CNN (89.88%), FCN (85.60%), MLP (79.77%), and RNN (73.54%) models. The hybrid model also demonstrated superior performance in cross-validation, with an accuracy of 87.31% ± 1.77%. Comparative analysis highlights the hybrid model's advantages over single-architecture DL models, particularly in handling imbalanced data and providing reliable classifications across all anemia types. The results underscore the potential of advanced DL architectures in medical diagnostics and suggest pathways for further refinements, such as incorporating attention mechanisms or additional feature engineering, to enhance model performance. This study contributes to the growing body of knowledge on AI-driven medical diagnostics and presents a viable tool for clinical decision support in anemia diagnosis
Clothing Inventory Forecasting System at Kagas Using the Weighted Moving Average Method Sulistiani, Indah; Sembiring, Muhammad Ardiansyah; Akmal, Akmal
Indonesian Journal of Artificial Intelligence and Data Mining Vol 8, No 1 (2025): March 2025
Publisher : Universitas Islam Negeri Sultan Syarif Kasim Riau

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.24014/ijaidm.v8i1.31498

Abstract

Information systems are made in stores so that they can easily process data and produce the information needed quickly, accurately, precisely, effectively and efficiently in spending costs. Kagas is a clothing store engaged in fashion that has been established since 2020. The purpose of this study is to apply the Weighted Moving Average method to the forecasting system in determining sales of robe clothes.  The results of calculating the stock of gamis clothes manually and calculating using a forecasting system using the previous year's data from May 2023 to April 2024 are the same. Forecasting of gamis clothes for the May 2024 period is 175 with a MAD value of 8.04, an MSE value of 135.33 and a MAPE value of 4.7%. With a forecasting system using the weight moving average method, it makes it easier for Toko Kagas to forecast the stock of gamis clothes inventory in the following month.
Classification of Football Players' Abilities Using The Naïve Baiyes Method Nasution, Riski Abdul Hakim; Ikhsan, Muhammad
Indonesian Journal of Artificial Intelligence and Data Mining Vol 7, No 2 (2024): September 2024
Publisher : Universitas Islam Negeri Sultan Syarif Kasim Riau

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.24014/ijaidm.v7i2.31997

Abstract

This study aims to classify the abilities of football players in the BRI Liga 1 Indonesia season 2023/2024 using the Naïve Bayes method. The player data used includes individual stats such as the number of goals, assists, passing accuracy, tackles, and overall performance in the match. The Naïve Bayes method was chosen because of its efficient ability to process data with independent features. In this study, players were classified into several ability categories, such as excellent, good, adequate, and poor, based on their performance during the current season. The results of this classification are expected to provide useful information for coaches and club management in determining strategies and player development. The study also provides insight into the key factors that affect a player's performance in the league. Model testing shows that Naïve Bayes' method has an adequate level of accuracy for the classification of football players' abilities in BRI Liga 1. The practical implications of this study are increased efficiency in the process of evaluating players and making strategic decisions in professional football teams.
Sentiment Analysis of Ampera Bridge as a National Tourism Destination Purba, Mariana; Yadi, Yadi
Indonesian Journal of Artificial Intelligence and Data Mining Vol 7, No 2 (2024): September 2024
Publisher : Universitas Islam Negeri Sultan Syarif Kasim Riau

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.24014/ijaidm.v7i2.30132

Abstract

Ampera Bridge is one of the leading tourism icons in Palembang which attracts thousands of visitors every year. This research aims to analyze visitors' opinions about the Ampera Bridge using opinion mining techniques in Google Review reviews. Research methods include collecting review data from Google Reviews, data preprocessing, sentiment analysis, and aspect analysis. The data collected includes 307 reviews taken in the period April 2024. These reviews were analyzed using the Support Vector Machine (SVM) algorithm to classify sentiment as positive, negative, or neutral. The analysis results show that 83% of reviews have positive sentiment, 9% are negative, and 8% are neutral. The main aspects often discussed by visitors include the view and beauty of the bridge, historical and cultural value, accessibility and transportation, facilities and cleanliness, as well as tourist experiences and activities. Positive sentiments were mainly related to the beauty of the bridge's architecture and lighting, as well as its historical value. However, negative sentiment was mainly caused by cleanliness issues and traffic jams around the bridge. Based on these findings, several recommendations put forward include improving cleaning facilities, better traffic management, developing public facilities, and diversifying tourist activities. It is hoped that the implementation of these recommendations can improve the quality of the visitor experience and the attractiveness of the Ampera Bridge as a major tourist destination. This research provides valuable insights for tourism managers and local governments to improve the quality of services and facilities at the Ampera Bridge.