cover
Contact Name
Suwanto Sanjaya
Contact Email
suwantosanjaya@uin-suska.ac.id
Phone
-
Journal Mail Official
coreit@uin-suska.ac.id
Editorial Address
-
Location
Kab. kampar,
Riau
INDONESIA
Jurnal CoreIT
ISSN : 2460738X     EISSN : 25993321     DOI : -
Core Subject : Science,
Jurnal CoreIT: Jurnal Hasil Penelitian Ilmu Komputer dan Teknologi Informasi published by Informatics Engineering Department – Universitas Islam Negeri Sultan Syarif Kasim Riau with Registration Number: Print ISSN 2460-738X | Online ISSN 2599-3321. This journal is published 2 (two) times a year (June and December) containing the results of research on Computer Science and Information Technology.
Arjuna Subject : -
Articles 162 Documents
Optimizing Scalability in Spice Identification through Transfer Learning with Convolutional Neural Networks Switrayana, I Nyoman; Azwar, Muhamad
Jurnal CoreIT: Jurnal Hasil Penelitian Ilmu Komputer dan Teknologi Informasi Vol 11, No 1 (2025): June 2025
Publisher : Fakultas Sains dan Teknologi, Universitas Islam Negeri Sultan Syarif Kasim Riau

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.24014/coreit.v11i1.35453

Abstract

Indonesia is renowned for its rich diversity of spices, which hold significant cultural and economic value. However, public knowledge of these spices remains limited, making their identification challenging. Addressing this issue, this study aims to develop a scalable spice identification system using Convolutional Neural Networks (CNN) with a Transfer Learning approach. The system is designed to recognize 30 types of spices while maintaining high accuracy, utilizing the Cross-Industry Standard Process for Data Mining (CRISP-DM) framework for systematic development. The dataset was collected through open sources and web scraping from Google Images. Four CNN models (ResNet50, EfficientNetB0, Xception, and MobileNet) were evaluated under three data splits: 90:10, 80:20, and 70:30. Performance metrics including accuracy, precision, recall, and F1-score were used for evaluation. Among these models, Xception achieved the best performance in the 90:10 split, with an accuracy of 84.51%, followed by EfficientNetB0 at 83.57%. The results demonstrate that transfer learning effectively enhances model accuracy and scalability, enabling reliable spice identification across diverse categories. This system has practical implications for promoting public awareness, supporting culinary industries, and preserving Indonesia’s rich spice heritage. The proposed approach highlights the potential of CNN-based systems for addressing classification challenges in resource-constrained settings, offering a foundation for future research and real-world applications.
Reviewing Factors of Audience Engagement in Live Streaming Subiyakto, Aang; Yudhanta, Satya; Nurmiati, Evy; Utami, Meinarini Catur; Fetrina, Elvy; Sugiarti, Yuni; Hakiem, Nashrul; Huda, Muhammad Qomarul; Sangsawang, Thosporn
Jurnal CoreIT: Jurnal Hasil Penelitian Ilmu Komputer dan Teknologi Informasi Vol 11, No 1 (2025): June 2025
Publisher : Fakultas Sains dan Teknologi, Universitas Islam Negeri Sultan Syarif Kasim Riau

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.24014/coreit.v11i1.36039

Abstract

Live streaming has become one of the most prominent digital phenomena in recent years, changing the way individuals interact, consume content and shop online. This study aims to identify and analyze the factors that influence audience engagement in live streaming, including audience motivation, the role of social interaction, technological features, platform distribution, and popular genres. Through a systematic literature review approach, 27 articles from relevant ScienceDirect and DOAJ databases were selected for analysis. The study results show that audience engagement is mainly influenced by parasocial interaction (PSI), entertainment-based motivation (hedonic value), and practical benefits (utilitarian value). Technologies such as live chat, gifting, and data-driven recommendation systems strengthen viewing duration and audience loyalty. In addition, platforms such as Twitch dominate the gaming and esports genres, while TikTok Live thrives in the e-commerce space. New genres such as VTubers and travel offer opportunities to attract a wider audience with avatar-based interaction approaches and virtual experiences. The research also identified gaps in the literature, including a lack of studies on local platforms, new genres, and the impact of innovative technologies such as AR/VR. This study makes an academic contribution by summarizing key findings and providing strategic guidance for platform developers, streamers and businesses in creating more engaging and effective live streaming experiences.
Stunting Detection System and Nutritional Status of Toddlers using Anthropometric Index and Body Mass Index Karsana, I Wayan Widi; Andhika Kurniawijaya, Putu; Resty Wasita, Rai Riska
Jurnal CoreIT: Jurnal Hasil Penelitian Ilmu Komputer dan Teknologi Informasi Vol 11, No 1 (2025): June 2025
Publisher : Fakultas Sains dan Teknologi, Universitas Islam Negeri Sultan Syarif Kasim Riau

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.24014/coreit.v11i1.33882

Abstract

The stunting problem in Indonesia is a problem that has become a national concern. The target of reducing stunting in 2024 is 14%, while in 2022 it is still at 24%. Various efforts to deal with stunting have been carried out by the Indonesian government at both the central and local government levels but have not been able to reduce stunting significantly. To conduct early detection of stunting in toddlers, one can use anthropometric index data as a reference and body mass index for nutritional status in toddlers. Parameters in the anthropometric index use height by age or body length by age, while the body mass index uses body weight and height as indicators. This study aims to develop a stunting detection system and nutritional status of toddlers using anthropometric indices and body mass index and validate the comparison of system output results with the results of manual calculations with standard formulas from the Ministry of Health of the Republic of Indonesia. The research found that there is a match between the results of manual calculations and calculations from the developed system, or, in other words, it can be concluded that there is a valid influence of nutritional status on the potential for stunting in toddlers.
Red Curly Chili Forecast in Southeast Sulawesi Using Auto Regressive Integrated Moving Average (ARIMA) Al Qadri, Muhammad Vannes; Saputra, Rizal Adi; Pramono, Bambang
Jurnal CoreIT: Jurnal Hasil Penelitian Ilmu Komputer dan Teknologi Informasi Vol 11, No 1 (2025): June 2025
Publisher : Fakultas Sains dan Teknologi, Universitas Islam Negeri Sultan Syarif Kasim Riau

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.24014/coreit.v11i1.33986

Abstract

Abstract. Price is a crucial aspect in the world of trade. Red curly chili peppers have become one of the plants favored by many consumers. This research aims to develop a forecasting model that can provide a more accurate insight into the future prices of red chili peppers, particularly in Southeast Sulawesi. Because price forecasting plays a crucial role in predicting future price trends, the Auto Regressive Integrated Moving Average (ARIMA) method becomes one of the models that can be used for time series analysis. The data for this research is sourced from the National Food Body Price Panel Website. The data period starts from August 8, 2022, to December 15, 2023, with the last 500 days' prices used as both test and training data. In this study, the ARIMA (1,1,1) model emerged as the best among the three ARIMA models analyzed. The ARIMA (1,1,1) model yielded a MAPE percentage of 17.97%, indicating that this model is suitable or reliable for time series forecasting. Furthermore, the results of this experiment show that the forecasted prices for the next 10 days do not experience significant decreases or increases, referring to several recent data points used as training data samples.
Big Data Processing with Neural Networks on RESTful API for Product Recommendation Using Python hartanto, budi; Fahurian, Fatimah; Dwi Yunita, Hilda; Winarko, Triyugo
Jurnal CoreIT: Jurnal Hasil Penelitian Ilmu Komputer dan Teknologi Informasi Vol 11, No 1 (2025): June 2025
Publisher : Fakultas Sains dan Teknologi, Universitas Islam Negeri Sultan Syarif Kasim Riau

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.24014/coreit.v11i1.34704

Abstract

The exponential growth of e-commerce data has created an urgent need for efficient and scalable systems that provide personalized product recommendations. This study addresses that challenge by integrating big data processing with neural networks and delivering recommendations via RESTful APIs. The primary objective is to develop a system capable of handling large datasets and providing real-time recommendations to enhance user engagement. The methodology involves using Apache Spark for distributed big data processing and feature engineering, followed by the implementation of neural networks in Python using TensorFlow to generate recommendations. The system integrates the model with a RESTful API to support seamless interaction with external applications. Extensive testing was conducted on a dataset containing over a million user-item interactions to evaluate performance and scalability. The results show that the proposed system achieves better recommendation accuracy compared to traditional machine learning approaches. It processes high-dimensional data efficiently and maintains latency below 200 milliseconds per API request, making it suitable for real-time applications. The novelty of this research lies in the end-to-end design that combines a big data framework with neural networks and RESTful APIs for practical implementation. This research provides a scalable and adaptive solution for e-commerce platforms and serves as a foundation for the advancement of real-time recommendation systems in the future.
Optimizing Student Depression Prediction Using Particle Swarm Optimization and Random Forest Effendi, Mukhammad Khoirul; -, Sriyanto; Irianto, Suhendro Yusuf; Fauzi, Chairani; Vitriani, Yelfi
Jurnal CoreIT: Jurnal Hasil Penelitian Ilmu Komputer dan Teknologi Informasi Vol 11, No 1 (2025): June 2025
Publisher : Fakultas Sains dan Teknologi, Universitas Islam Negeri Sultan Syarif Kasim Riau

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.24014/coreit.v11i1.35954

Abstract

Student mental health is a growing concern due to increasing academic pressure, social demands, and economic factors affecting their well-being. Depression, a common issue among students, significantly impacts academic performance and overall quality of life. Therefore, early detection and accurate prediction of student mental health conditions are essential to provide timely interventions. This study aims to improve the accuracy of depression prediction among university students by integrating Particle Swarm Optimization (PSO) for feature selection with Random Forest (RF) as the classification model. The dataset used is the Student Depression Dataset from Kaggle, consisting of 27,900 respondents with 18 features related to demographic, academic, and psychological factors. Data preprocessing includes handling missing values, normalization, categorical encoding, and feature selection using PSO. The model is trained and evaluated using 10-Fold Cross-Validation. Experimental results show that PSO-optimized Random Forest outperforms the standard Random Forest model. The optimized model achieves an accuracy of 84.08%, precision of 82.79%, recall of 77.79%, and an AUC-ROC score of 0.912, improving classification performance. These findings demonstrate that PSO effectively enhances feature selection, leading to better classification accuracy. This study contributes to the development of a more accurate and efficient machine learning model for detecting student depression. By optimizing feature selection, this approach reduces computational complexity while maintaining high predictive performance. Future research can explore hybrid optimization techniques such as Genetic Algorithm (GA) or Differential Evolution (DE) to further enhance model generalization across different datasets.
APPLICATION OF K-NEAREST NEIGHBOR REGRESSION METHOD FOR RICE YIELD PREDICTION Handayani, Lestari; Alfarabi.B, Alif; Aprilia, Tasya; Wulandari, Indah; Jasril, Jasril; Ramadhani, Siti; Budianita, Elvia
Jurnal CoreIT: Jurnal Hasil Penelitian Ilmu Komputer dan Teknologi Informasi Vol 11, No 1 (2025): June 2025
Publisher : Fakultas Sains dan Teknologi, Universitas Islam Negeri Sultan Syarif Kasim Riau

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.24014/coreit.v11i1.30907

Abstract

Rice plants with the Latin name Oryza Sativa are food plants that are widely used as the main food crop in various countries, one of which is Indonesia. Indonesia is ranked 4th as the largest rice consuming country in the world. This requires the availability of rice to be maintained. Unstable rice production can be a problem. One of the districts that has experienced a decline in rice production in recent years is the district of Lima puluh kota located in West Sumatra province. This requires prediction of rice production so that it can be used as a benchmark for the future. This study uses data on rice production in fifty cities from 2013 to 2023. The method used to predict is k-nearest neighbor regression (KNN Regression). The data division uses rasio 90 : 10. In testing the data used is divided into 2, namely normal data and data that has been normalized. The test results produce the smallest mean absolute percentage error (MAPE) value of 6.98% on normal data, the value of k is 6 with data division using k-fold 5. Based on the resulting MAPE value, it can be said that KNN Regression can predict rice production results very accurately.
Classification of Apple Tree Leaf Diseases Using Pretrained EfficientNetB0 and XGBoost Qohar, Bagus Al; Dullah, Ahmad Ubai; Darmawan, Aditya Yoga; Unjung, Jumanto
Jurnal CoreIT: Jurnal Hasil Penelitian Ilmu Komputer dan Teknologi Informasi Vol 11, No 2 (2025): December 2025
Publisher : Fakultas Sains dan Teknologi, Universitas Islam Negeri Sultan Syarif Kasim Riau

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.24014/coreit.v11i2.33174

Abstract

The diseases that affect apple tree leaves seriously compromise agricultural production; therefore, early and accurate diagnosis is quite important for good disease control. Machine learning's recent developments have opened fascinating possibilities for automating the detection process and enhancing methods of precision agriculture. This study aims to create a strong classification model that can accurately and efficiently identify various diseases that affect apple tree leaves. The approach combines the pre-trained EfficientNetB0 architecture for feature extraction with the XGBoost model for classification, utilizing the advantages of both deep learning and gradient-boosting methods. With high performance measures including a macro-average precision of 95.86%, recall of 95.44%, and F1 score of 95.64%, the model achieved a classification accuracy of 95.74%. Furthermore, the average ROC-AUC score of 0.9964 emphasizes how well the model differentiates the five disease categories. This work stands out due to its hybrid approach, which integrates a robust pre-trained convolutional neural network (EfficientNetB0) with the XGBoost model. This significantly improves the accuracy of disease classification. This approach presents a novel pathway for precision agriculture, providing a reliable and effective instrument for the automatic identification of diseases in apple orchards.
Health Monitoring Application for Covid-19 Self-Isolation Patients Setiawan (Scopus ID: 56829262300), Eko Budi
Jurnal CoreIT: Jurnal Hasil Penelitian Ilmu Komputer dan Teknologi Informasi Vol 10, No 1 (2024): June 2024
Publisher : Fakultas Sains dan Teknologi, Universitas Islam Negeri Sultan Syarif Kasim Riau

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.24014/coreit.v9i2.25488

Abstract

The self-isolation procedure must be carried out under the supervision of a local health facility which is part of the Covid-19 handling post so that the health condition of the patient can continue to be monitored while undergoing self-isolation. However, in practice, supervision of this self-isolation patient is often neglected, resulting in many patients experiencing deteriorating health conditions and being given treatment late which leads to death. The purpose of this research is to create an android-based application that can be used to monitor the health condition of patients who are undergoing self-isolation. This application was developed using the Java and Kotlin programming languages, the Firebase Realtime Database, and several technologies, namely Smartband, Bluetooth Low Energy, Google Maps API, Google Places API, Firebase Cloud Messaging, Covid-19 Indonesia API, RS Bed Covid-19 Indonesia API and Indonesia News API. The software development method used is the waterfall method. Based on the results of alpha testing using the black-box method, it can be concluded that the application built meets the requirements and works according to its functional requirements. Meanwhile, based on the results of beta testing using the questionnaire method given to 6 respondents with a Likert scale calculation, the percentages for each question were 100%, 93.33%, and 93.33%, so it can be concluded that the application built has achieved the desired goals.
Science Interest Detection Using Computerized Adaptive Testing Based on Fuzzy Item Response Theory Wulandari, Fitri
Jurnal CoreIT: Jurnal Hasil Penelitian Ilmu Komputer dan Teknologi Informasi Vol 9, No 2 (2023): December 2023
Publisher : Fakultas Sains dan Teknologi, Universitas Islam Negeri Sultan Syarif Kasim Riau

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.24014/coreit.v9i2.27258

Abstract

Choosing a major or interest at the beginning of High School is a very important process for the future development of students.  A test  may be performed to determine the learner's ability in a particular field In this research, an interest test was developed to determine the students' ability in science. Students will be measured for their cognitive ability in Mathematics and Science subjects for junior high school level. The research was developed using an adaptive test system called Computerized Adaptive Testing (CAT). CAT is an adaptive media based model,  test participants will receive the test according to their ability. The test item selection procedure uses the fuzzy algorithm using item difficulty parameters, item strengths and participants' response data as input data. While the rule or procedure for terminating the test is done with the maximum likelihood estimation method, MLE. Based on the test results, each student received different test items according to their ability level and the difficulty indexs that received by the students according to the characteristics of the item information. Therefore, the CAT program with the fuzzy item response theory can be used as a support for measuring the students' ability and interest in a major.