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
Leakage Warning System and Monitoring Lapindo Sidoarjo Mud Embankment Based on Internet of Things Haji, Shon; Ahfas, Akhmad; Syahrorini, Syamsudduha; Ayuni, Shazana Dhiya
Indonesian Journal of Artificial Intelligence and Data Mining Vol 7, No 1 (2024): March 2024
Publisher : Universitas Islam Negeri Sultan Syarif Kasim Riau

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.24014/ijaidm.v7i1.25269

Abstract

The emergence of the Lapindo Sidoarjo mudflow has a long history since 29 May 2006. The point of the mudflow is in Siring Village, and until now, it has shown no signs of stopping. Sidoarjo residents are still fearful of the impact and recurrence of the mudflow, especially those still living around the embankment. The real impact is often still felt, such as embankment leaks, embankment collapses, or overflowing water mixed with mud during high rainfall, making people who still live around the embankment anxious. The unavailability of monitoring information to the public and the unclear mitigation system makes it necessary to have an information system that is easily accessible to the public. Therefore, by utilizing the advances in Internet of Things technology, this research will design a prototype system to monitor the conditions around Lapindo Sidoarjo Mud using Telegram Bot as a user interface, the ESP32-Cam microcontroller board, SW-420 vibration sensor, and MPU-6050 accelerometer sensor. The result of testing this prototype tool is that the Telegram user will receive a notification if the condition of the prototype field is experiencing vibrations or changes in position. Other than that, the Telegram user can also request real-time information, such as temperature, the axis position of the prototype as an initial benchmark, and the current photo to know the condition of the Lapindo Sidoarjo mud embankment. That way, it is hoped that this prototype system will become a monitoring and mitigation solution for the local people and the general public who reach this Telegram Bot room chat.
Comparative Analysis of Support Vector Regression and Linear Regression Models to Predict Apple Inc. Share Prices Pangestu, Resza Adistya; Vitianingsih, Anik Vega; Kacung, Slamet; Maukar, Anastasia Lidya; Noertjahyana, Agustinus
Indonesian Journal of Artificial Intelligence and Data Mining Vol 7, No 1 (2024): March 2024
Publisher : Universitas Islam Negeri Sultan Syarif Kasim Riau

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.24014/ijaidm.v7i1.28594

Abstract

Stock price prediction is a complex and important challenge for stock market participants. The difficulty of predicting stock prices is a major problem that requires an approach method in obtaining stock price predictions. This research proposes using machine learning with the Support Vector Regression (SVR) model and linear regression for stock price prediction—the dataset used in the daily Apple Inc historical data from 2018 to 2023. The hyperparameter tuning technique uses the Grid Search method with a value of k = 5, which will be tested on the SVR and Linear Regression methods to get the best prediction model based on the number of cost, epsilon, kernel, and intercept fit parameters. The test results show that the linear regression model with all hyperparameters k = 5 with the average taken performs best with a True intercept fit value. The resulting model can get an excellent error value, namely the RMSE value of 0.931231 and MSE of 0.879372. This finding confirms that the linear regression model in this configuration is a good choice for predicting stock prices.
Forecasting Oil Production of Well 159-F-14H in the Volve Field Using Machine Learning Model Rhamadhani, Devy Ayu; Saputri, Eriska Eklezia Dwi; Sari, Riska Laksmita
Indonesian Journal of Artificial Intelligence and Data Mining Vol 7, No 1 (2024): March 2024
Publisher : Universitas Islam Negeri Sultan Syarif Kasim Riau

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.24014/ijaidm.v7i1.24907

Abstract

Petroleum engineers require information about the production performance of a well in order to know when the well is no longer feasible to produce. By using the approachment technique of machine learning, the research was conducted using a tree-based regression model, Random Forest Regressor, Extra Trees Regressor, and Gradient Boosting Regressor. This research was done by predicting the production of an existing well in the Volve field, namely well 159-F-14H using its field data; average downhole pressure, average downhole temperature, average wellhead temperature, average wellhead pressure, on-stream hours, average choke size percentage, gas volume from well, water volume from well. The data used is 1093 days and 70% is used for training and as much as 30% for testing. A comparative study was carried out on the predictive performance of the three models. Random Forest shows the best testing result as well as RMSE 5.134 and R2 0.974, followed by Gradient Boosting shows RMSE 5.927 and R2 0.965, and Extra Trees shows RMSE 6.524 and R2 0,958.
Implementation of Fuzzy Logic Method to Get Estimation of Fluid Depletion on Smart Infusion Permata Sari, Mira; Taqwa, Ahmad; Silvia Handayani, Ade
Indonesian Journal of Artificial Intelligence and Data Mining Vol 7, No 1 (2024): March 2024
Publisher : Universitas Islam Negeri Sultan Syarif Kasim Riau

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.24014/ijaidm.v7i1.25589

Abstract

Technology plays an important role in improving healthcare, especially in the field of medical care, particularly in infusion. Infusions are essential in hospitals, requiring constant monitoring by healthcare professionals to ensure patient safety.  The system tracks the remaining infusion fluid and displays this data on the nurse's mobile device, enabling remote control of infusion levels in each patient room. The solution incorporates a load cell sensor to measure infusion weight and an optocoupler sensor to measure infusion drip speed. In addition, the solution uses a fuzzy logic control system to make decisions based on drip speed and infusion weight, estimating when the infusion will run out.Applying this automatic infusion drip monitoring device significantly improves the accuracy and reliability of infusion management, leading to substantial improvements in patient care and safety.In this test, the results can be seen that there is a difference between the weight weighed manually and the weight on the device. with the largest weight difference of 2.49%.
The Use of Satellite Imagery Data for Poverty Clustering at the District Level Administration in Indonesia Khamila, Azzahra Dhisa; Wardani, Martha Budi; Kurniawan, Robert
Indonesian Journal of Artificial Intelligence and Data Mining Vol 7, No 1 (2024): March 2024
Publisher : Universitas Islam Negeri Sultan Syarif Kasim Riau

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.24014/ijaidm.v7i1.25278

Abstract

Poverty is a problem that will never be separated from every country, including Indonesia. One of the efforts that can be taken to reduce poverty is to carry out comprehensive monitoring of data related to poverty. The use of satellite imagery strongly supports this effort. Data taken to describe poverty in a region are CO, SO2, NO2, Night Time Light (NTL), Land Surface Temperature (LST), Normalized Difference Vegetation Index (NDVI), Normalized Difference Built-up Index (NDBI), also per capita expenditure data that can be accessed through the BPS website. Based on the theory, all of these variables negatively affect the poverty of a region except for the NDVI variable. The use of clustering with K-Means method can be implemented in this situation in order to cluster poverty in every district in Indonesia. Then it is supported by a descriptive analysis of each variable in order to describe the distribution of variables in each district in Indonesia. Based on the clustering results, it can be seen that there are 2 clusters, namely cluster 1 which shows a cluster with low poverty and cluster 2 with high poverty. There are a total of 46 districts included in cluster 1, which constitute the majority of economic centers in it's region, and 468 other districts included in cluster 2. The results of this clustering are expected to be used by stakeholders in making decisions according to the characteristics of the district.
Lepidoptera Classification Using Convolutional Neural Network EfficientNet-B0 Syamsudin, Hilmi; Khalidah, Saidatul; Unjung, Jumanto
Indonesian Journal of Artificial Intelligence and Data Mining Vol 7, No 1 (2024): March 2024
Publisher : Universitas Islam Negeri Sultan Syarif Kasim Riau

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.24014/ijaidm.v7i1.24586

Abstract

Butterflies and moths are insects that have many different species. Butterflies and moths have considerable aesthetic, ecosystem, health, economic, health, and scientific values. However, because there are so many different varieties and patterns, it is vital to divide them by type for better identification. By creating a Convolutional Neural Network (CNN) algorithm that produces accurate results, a deep learning approach can be used to classify the types of butterfly and moth species. This paper offer an Lepidoptera including butterfly and moth classification model based on convolutional neural networks.  3390 images of 25 different butterfly and moth species were acquired with various images orientations, angles, distance, and background.   Using the EfficientNet-B0 CNN architecture, different types of butterflies and moths are classified and input into the EfficientNet-B0 model. EfficientNet-B0 performs feature extraction on the image, so that it can be used to perform classification and then combined through a pooling process and connected to the final layer to produce a classification probability. The probability indicates how likely the image is to belong to a particular type or class of butterfly or moth.  In comparison to earlier studies, the test results indicate an improvement in butterfly and moth classification. Increased accuracy was seen with values of 97.91% accuracy, 97% recall,  97% precision, and 97% F1-Score. This paper novelty is the enhancement of the CNN architecture EfficientNet-B0 used in image classification, which results in improved image classification accuracy.
Web-Based Movie Recommendation System Using Content-Based Filtering and Cosine Similarity Meillano, Zico Fachreza; Richasdy, Donni; Hasmawati, Hasmawati
Indonesian Journal of Artificial Intelligence and Data Mining Vol 7, No 1 (2024): March 2024
Publisher : Universitas Islam Negeri Sultan Syarif Kasim Riau

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.24014/ijaidm.v7i1.27390

Abstract

Movie are one of the most popular entertainment media among people and are often chosen as activities during weekend holidays. As time goes by, world cinema continues to develop with various interesting and entertaining genres, stories and visuals. Because film is one of the entertainment media that can relieve stress from work assignments or lectures and now film production is also growing so that more and more films are being produced until finally people are confused about choosing the film they will watch. To resolve the obstacles faced, movie information is needed that can help people find movies that suit user preferences, so users need a system that can recommend movies. In this research, the author used the content-based filtering method to find movie recommendations. The substance utilizedis the movie genre. The Check Vectorization calculation is utilized to discover the term/word weight values in each record and after that these values are utilized as factors within the Cosine closeness to discover similitudes between archives.As a result of this last project the system can generate a kind of recommendations for the 10 most similar movies. The test results from this final project are that the system is running well and is reliable with an alpha test result of 100%, and a reliability test result of 0.7.
Sentiment Analysis and Topic Modelling on Crowdsourced Data Maria Angelika H Siallagan; Arie Wahyu Wijayanto
Indonesian Journal of Artificial Intelligence and Data Mining Vol 7, No 1 (2024): March 2024
Publisher : Universitas Islam Negeri Sultan Syarif Kasim Riau

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.24014/ijaidm.v7i1.24777

Abstract

Data analysis plays a crucial role in enhancing the decision-making process by uncovering concealed patterns within the data. One valuable form of crowdsourced data is user reviews on applications, which can effectively capture the satisfaction levels of application users. Application developers can utilize these reviews to identify and assess areas of the application that require evaluation or improvement. This study focuses on the classification of application reviews by utilizing sentiment analysis and employs various classification algorithms, including logistic regression, Support Vector Machines, and Random Forest. Additionally, to address negative sentiment labels, topic modeling is conducted using Latent Dirichlet Allocation (LDA). This study demonstrates that the best sentiment classification model is logistic regression, achieving an average accuracy of 0.925 and an average F1-score of 0.763. Furthermore, the LDA analysis successfully generates topic models for negative reviews, revealing three key topics: price-related issues, accessibility concerns, and application accuracy, all of which demand reevaluation and potential improvement
Enhancing Electric Vehicle Range Prediction through Deep Learning: An Autoencoder and Neural Network Approach Airlangga, Gregorius
Indonesian Journal of Artificial Intelligence and Data Mining Vol 7, No 1 (2024): March 2024
Publisher : Universitas Islam Negeri Sultan Syarif Kasim Riau

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.24014/ijaidm.v7i1.28803

Abstract

The burgeoning adoption of electric vehicles (EVs) signifies a pivotal shift towards sustainable transportation, necessitated by the global imperative to mitigate climate change impacts. Central to this transition is the resolution of range anxiety, a significant barrier impeding wider EV acceptance. This research introduces a novel deep learning framework combining autoencoders and deep neural networks (DNNs) to predict EV range more accurately and reliably. Leveraging a comprehensive dataset from the "Electric Vehicle Population Data," we embarked on a meticulous process of data cleaning, feature engineering, and preprocessing to prepare the dataset for analysis. The study innovatively applies an autoencoder for unsupervised feature learning, effectively reducing dimensionality and extracting salient features from high-dimensional EV data. Subsequently, a DNN model utilizes these features to predict the EV range, offering insights into the vehicle's performance across various conditions. Employing a 10-fold cross-validation approach, the model's efficacy is rigorously evaluated, ensuring robustness and generalizability of the predictions. Our methodology demonstrates a significant enhancement in prediction accuracy compared to conventional machine learning models, as evidenced by the Mean Squared Error (MSE) metric. This research not only contributes to the academic discourse on sustainable transportation and deep learning applications but also provides practical insights for manufacturers, policymakers, and consumers aiming to navigate the complexities of EV adoption and infrastructure development. By addressing the critical challenge of range prediction, this study paves the way for advancing EV analytics, ultimately supporting the transition to a more sustainable and efficient transportation ecosystem.
Tree Damage Type Classification Based on Forest Health Monitoring Using Mobile-Based Convolutional Neural Network Gandadipoera, Faishal Hariz Makaarim; Andrian, Rico; safei, rahmat
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.v7i2.29421

Abstract

One of the fundamental parts of surveying forest health conditions with Forest Health Monitoring (FHM) is to visually assess the damage experienced by trees under certain conditions. This visual assessment can be facilitated using a Convolutional Neural Network (CNN) which involves building the MobileNetV2 model architecture. The model was trained using 1600 image data with 16 classes. The image data was pre-processed by resizing it to 224x224. The data was categorized into three categories: 80% was allocated for training, 10% for validation, and testing with 10% also. Training was done by changing the values from batches with a maximum of 100 epochs. The model was then incorporated into a mobile application using TensorFlow Lite and testing the application gave satisfactory results.  The model results get the best accuracy rate of 98.75% and a loss of 0.0497. This research concludes that the classification of tree damage types based on FHM with CNN can be done. For accurate results, the image provided by the user must be clear and reflect the actual damage observed on the tree.