Article Per Year (5 Year)
p-Index From 2021 - 2026
6.48
P-Index
This Author published in this journals
All Journal Jurnal Teknologi Informasi dan Ilmu Komputer Jurnal Informatika dan Teknik Elektro Terapan Jurnal Ilmiah KOMPUTASI Sinkron : Jurnal dan Penelitian Teknik Informatika JOURNAL OF APPLIED INFORMATICS AND COMPUTING Jurnal Sisfokom (Sistem Informasi dan Komputer) ILKOM Jurnal Ilmiah Jurnal Infomedia MATRIK : Jurnal Manajemen, Teknik Informatika, dan Rekayasa Komputer IJISTECH (International Journal Of Information System & Technology) JOURNAL OF SCIENCE AND SOCIAL RESEARCH JOURNAL OF INFORMATICS AND COMPUTER SCIENCE Jurnal Sistem Komputer dan Informatika (JSON) Journal of Computer Science, Information Technology and Telecommunication Engineering (JCoSITTE) IJISTECH Rambideun : Jurnal Pengabdian Kepada Masyarakat International Journal of Engineering, Science and Information Technology jeti JURNAL ILMIAH GLOBAL EDUCATION JUSTIN (Jurnal Sistem dan Teknologi Informasi) Jurnal Teknik Informatika dan Elektro (JURTIE) TECHSI - Jurnal Teknik Informatika Sisfo: Jurnal Ilmiah Sistem Informasi Jurnal Teknologi Terapan and Sains 4.0 Jurnal Kemitraan Responsif untuk Aksi Inovatif dan Pengabdian Masyarakat Journal Of Artificial Intelligence And Software Engineering Journal of Advanced Computer Knowledge and Algorithms Applied Engineering, Innovation, and Technology Proceedings of International Conference on Multidisciplinary Engineering (ICOMDEN)
Munirul Ula
Universitas Malikussaleh
Agriculture, Biological Sciences & Forestry Humanities Astronomy Automotive Engineering Biochemistry, Genetics & Molecular Biology Chemical Engineering, Chemistry & Bioengineering Chemistry Civil Engineering, Building, Construction & Architecture Computer Science & IT Control & Systems Engineering Decision Sciences, Operations Research & Management Earth & Planetary Sciences Economics, Econometrics & Finance Education Electrical & Electronics Engineering Energy Engineering Environmental Science Industrial & Manufacturing Engineering Languange, Linguistic, Communication & Media Library & Information Science Materials Science & Nanotechnology Mathematics Mechanical Engineering Physics Public Health Social Sciences Transportation Other

Published : 56 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 56 Documents
Search

 2   3   4   5   6 
Comparing Long Short-Term Memory and Random Forest Accuracy for Bitcoin Price Forecasting Munirul Ula; Veri Ilhadi; Zailani Mohamed Sidek
MATRIK : Jurnal Manajemen, Teknik Informatika dan Rekayasa Komputer Vol. 23 No. 2 (2024)
Publisher : Universitas Bumigora

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30812/matrik.v23i2.3267

Abstract

Bitcoin’s daily value fluctuations are very dynamic. Understanding its rapid and intricate price movements demands advanced techniques for processing complex data. This research aims to compare the accuracy of two machine learning methods, Random Forest (RF) and Long Short-Term Memory (LSTM), in predicting Bitcoin price. This research employs RF and LSTM algorithms to forecast Bitcoin prices using a two-year Yahoo Finance dataset. The evaluation metrics used were accuracy based on Mean Absolute Percentage Error (MAPE) and computational power (CPU-Z). As a result of this research, the LSTM model demonstrates higher accuracy compared to the RF model. MAPE reveals LSTM’s precision of 99.8% and RF’s accuracy of 90.1%. Regarding computational time and resources, RF shows slightly better performance than LSTM. The visual comparison further emphasizes LSTM’s better performance in predicting Bitcoin prices, highlighting its potential for informed decision-making in cryptocurrency trading. This research contributes valuable insights into the effectiveness, strengths, and weaknesses of LSTM and RF models in predicting cryptocurrency trends.
Analisis Perbandingan Kinerja Algoritma You Only Look Once (YOLOv8) Dan Single Shot Detector (SSD) dalam Pengenalan Nominal Uang Kertas Ulfah, Julia; Ula, Munirul; Fajriana, Fajriana; Nurdin, Nurdin
Journal of Artificial Intelligence and Software Engineering Vol 5, No 4 (2025): Desember (On Progress)
Publisher : Politeknik Negeri Lhokseumawe

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30811/jaise.v5i4.7471

Abstract

The advancement of technology in the field of image recognition has significantly facilitated and improved the effectiveness of object detection in computer-based banknote recognition systems. This study aims to automatically identify banknotes based on their denominations, with the objective of minimizing human errors—such as lack of concentration, fatigue, and other factors—and enabling its application in ATMs and automated payment systems. This research compares the accuracy levels and detection success rates between the YOLO and SSD algorithms in recognizing the denominations of banknotes. The YOLO model operates by dividing the image into grids and predicting bounding boxes along with object classes in a single step, resulting in fast and consistent detection. In contrast, the SSD model employs a multi-scale approach by utilizing feature maps from multiple levels to generate predictions. The parameters used in this study include 7 classes of Indonesian banknotes: Rp1,000, Rp2,000, Rp5,000, Rp10,000, Rp20,000, Rp50,000, and Rp100,000. A total of 353 images were used in the dataset, and three images from each class were selected for testing purposes. The results of the study indicate a significant performance difference. The YOLO algorithm achieved a 100% accuracy rate under both normal and low-light conditions, while the SSD algorithm achieved an accuracy rate of 87.2% under normal lighting and 91.4% under low-light conditions.
Comparison of the Results of Double Exponential Smoothing Method with Triple Exponential Smoothing for Predicting Chili Prices Nadia Saphira; Munirul Ula; Sujacka Retno
Proceedings of International Conference on Multidisciplinary Engineering (ICOMDEN) Vol. 2 (2024): Proceedings of International Conference on Multidisciplinary Engineering (ICOMDEN)
Publisher : Faculty of Engineering, Malikussaleh University

Show Abstract | Download Original | Original Source | Check in Google Scholar

Abstract

Double Exponential Smoothing (DES) is a forecasting method that combines two components level and trend, used for data with a trend pattern that tends to increase or decrease over time. In contrast, Triple Exponential Smoothing (TES) incorporates three components: level, trend, and seasonality, making it suitable for data with trend and seasonal patterns. This study uses historical chili price data from 2020 to 2023, obtained from the Bank Indonesia website, managed by the National Strategic Food Price Information Center (PIHPS), to compare the effectiveness of DES and TES in predicting chili prices in Medan City. Prediction accuracy was evaluated using MAPE (Mean Absolute Percentage Error) and MAE (Mean Absolute Error). The study results show MAPE values for DES as follows: Large Red Chili 1.25%, Curly Red Chili 1.39%, Green Bird’s Eye Chili 1.14%, and Red Bird’s Eye Chili 1.13%. TES produced slightly lower MAPE values: Large Red Chili 1.25%, Curly Red Chili 1.38%, Green Bird’s Eye Chili 1.12%, and Red Bird’s Eye Chili 1.10%. The MAE values for DES are as follows: Large Red Chili 447.9, Curly Red Chili 494.83, Green Bird’s Eye Chili 430.92, and Red Bird’s Eye Chili 423.36. TES showed better accuracy with MAE values of Large Red Chili at 447, Curly Red Chili at 493.02, Green Bird’s Eye Chili at 416.2, and Red Bird’s Eye Chili at 409.36. The results conclude that Triple Exponential Smoothing performs better than Double Exponential Smoothing in predicting chili prices.
Identification of Environmental Security in Relation to Crime Rates in Simeulue Regency Using Density-Based Spatial Clustering of Applications with Noise (DBSCAN) Method Yopy Anfelia; Munirul Ula; Sujacka Retno
Proceedings of International Conference on Multidisciplinary Engineering (ICOMDEN) Vol. 2 (2024): Proceedings of International Conference on Multidisciplinary Engineering (ICOMDEN)
Publisher : Faculty of Engineering, Malikussaleh University

Show Abstract | Download Original | Original Source | Check in Google Scholar

Abstract

Criminal offenses are acts that violate criminal law and are punishable by the state, either through imprisonment, fines, or other sanctions. These offenses cause significant distress and harm to the general public, individuals, and the state. In Simeulue Regency, the number of criminal cases has been increasing annually, driven by social, economic, environmental, cultural, legal, technological, and psychological factors. This study aims to analyze the relationship between environmental security and the level of criminal cases in Simeulue Regency using the Density-Based Spatial Clustering of Applications with Noise (DBSCAN) algorithm. The data used includes criminal cases from 2019 to 2023 across 10 districts, along with environmental information such as population density, public facilities, and socioeconomic indicators. The research methodology involves data collection and cleaning, Euclidean distance calculation, parameter selection for DBSCAN, and the application of validation formulas to determine the vulnerability to criminal offenses in Simeulue Regency. The analysis results, using an epsilon parameter of 5 and MinPts of 3, yielded clusters 0, -1, and 1. Cluster 0 includes Salang and Teluk Dalam districts; cluster -1 includes Alafan, Simeulue Tengah, Simeulue Timur, Simeulue Barat, Teupah Barat, and Teupah Selatan districts; and cluster 1 includes Simeulue Cut and Teupah Tengah districts. The validation formula indicates that the highly vulnerable area is in Simeulue Timur district, while the at-risk areas are Teupah Tengah, Teluk Dalam, and Teupah Barat districts. The areas classified as not at risk are Alafan, Salang, Simeulue Tengah, Simeulue Cut, Simeulue Barat, and Teupah Selatan districts. This study provides insights into areas that require increased attention in efforts to address and prevent criminal offenses. Keywords: environmental security, criminal offenses, DBSCAN, clustering, Simeulue Regency
Penerapan Hybrid Data Mining Menggunakan K-Means Clutering Dan Decision Tree Untuk Klasifikasi Kasus Perceraian Kabupaten Aceh Tengah Fahruddin, Fahruddin; Ula, Munirul; Muthalib, Muchlis Abd
Jurnal Teknik Informatika dan Elektro Vol 7 No 1 (2025): Jurnal Teknik Elektro dan Informatika
Publisher : Universitas Gajah Putih

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.55542/jurtie.v7i1.1879

Abstract

Abstrak– perceraian adalah pengakhiran suatu perkawinan karena sesuatu sebab dengan keputusan hakim atas tuntutan dari salah satu pihak atau kedua belah pihak dalam perkawinan. Islam sendiri telah memberikan penjelasan dan definisi bahwa perceraian menurut ahli fikih disebut talak atau furqoh. Untuk saat ini angka kasus perceraian di Kabupaten Aceh Tengah mengalami peningkatan yang sangat signifikan pada tahun 2019 sampai dengan pertengahan tahun 2022, bahkan dari 23 Kabupaten di Provinsi Aceh yaitu Kabupaten Aceh Tengah adalah kasus perceraian tertinggi hingga mencapai 1273 kasus pada pertengahan 2022. Dari 1273 jumlah kasus tersebut perlu adanya penerapan algoritma kombinasi atau yang di sebut dengan Hybrid Data Mining menggunakan metode K-Means Clustering dan Decision Tree di mana metode ini berfungsi untuk mengolah data kasus perceraian sebagai tujuan mengklasifikasikan data kasus perceraian di kabupaten Aceh Tengah. Pengujian klaster di lakukan dengan 3 model klaster yaitu k=2,k=3 dan k4. Untuk mendapatkan data dari hasil klaster maka di lakukan pengujian kinerja davies bouldin maka menghasilkan nilai kinerja klaster dengan k=2 adalah -2,127, untuk nilai davies bouldin kinerja klaster dengan k=3 adalah -1,794, sedangkan nilai davies bouldin kinerja klaster dengan k=3 adalah -1,854. Berdasarkan simpulan diatas maka pada model 2 dengan jumlah k=3 dapat ditentukan klaster yang akan direduksi yaitu klaster dengan keanggotaan terkecil yaitu cluster 2 dengan jumlah data yang direduksi yaitu 59 data, sehingga jumlah dataset hasil reduksi yaitu 1.214 data. Dengan data hasil reduksi maka di uji menggunakan algoritma decision tree dengan komposisi split data 90:10’80:20 dan 70:10. Dengan demikian maka menghasilkan nilai akurasi data sebelum di reduksi dengan data setelah di reduksi dengan demikian nilai rata-rata akurasi untuk klasisfikasi tanpa reduksi adalah 85,96%, presisi 84,71% dan recall 79,36% dan untuk akurasi setelah direduksi adalah 87,90%, presisi 87,22%, dan recall 82,72%. Sehingga dapat disimpulkan bahwa akurasi klasifikasi dataset setelah direduksi lebih tinggi dari akurasi klasifikasi tanpa reduksi. Kata Kunci: data perceraian, hybrid, k-means clustering, Decision Tree. Abstract– Divorce is the termination of a marriage for any reason by a judge's decision based on the demands of one or both parties in the marriage. Islam itself has provided an explanation and definition that according to fiqh experts, divorce is called talak or furqoh. Currently, the number of divorce cases in Central Aceh Regency has increased very significantly from 2019 to mid-2022, In fact, of the 23 districts in Aceh Province, Central Aceh District has the highest number of divorce cases, reaching 1273 cases in mid-2022. Of the 1273 cases, it is necessary to apply a combination algorithm or what is called Hybrid Data Mining using the K-Means Clustering and Decision Tree method, where this method functions to process divorce case data for the purpose of classifying divorce case data in Central Aceh district. Cluster testing was carried out with 3 cluster models, namely k=2, k=3 and k4, To get data from the cluster results, the Davies Bouldin performance test was carried out, resulting in a cluster performance value with k=2 which was -2.127, for the Davies Bouldin value of cluster performance with k=3 is -1.794, while the Davies Bouldin value of cluster performance with k=3 is -1.854. Based on the conclusions above, in model 2 with the number k=3, the cluster that will be reduced can be determined, namely the cluster with the smallest membership, namely cluster 2 with the amount of data reduced, namely 59 data, so that the total dataset resulting from the reduction is 1,214 data. With the reduced data, it was tested using a decision tree algorithm with a data split composition of 90:10'80:20 and 70:10. In this way, the accuracy value of the data before reduction is produced with the data after reduction, so the average value of accuracy for classification without reduction is 85.96%, precision is 84.71% and recall is 79.36% and for accuracy after reduction is 87. .90%, precision 87.22%, and recall 82.72%. So it can be concluded that the classification accuracy of the dataset after reduction is higher than the classification accuracy without reduction. Keywords: divorce data, hybrid, k-means clustering, Decision Tree.
Classification of Hospital Stay Duration for Schizophrenia Patients at RSUD Muyang Kute Using a Combination of C4.5 and Particle Swarm Optimization Putri Agustina Dewi; Munirul Ula; Said Fadlan Anshari
Journal of Advanced Computer Knowledge and Algorithms Vol. 3 No. 2 (2026): Journal of Advanced Computer Knowledge and Algorithms - April 2026 (In Press)
Publisher : Department of Informatics, Universitas Malikussaleh

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.29103/jacka.v3i2.25930

Abstract

Schizophrenia is a chronic mental disorder that often requires inpatient care, so an increase in the number of patients can lead to limited bed capacity in psychiatric wards. This study aims to classify the length of hospital stay for schizophrenia patients to support room requirement planning at RSUD Muyang Kute using the C4.5 algorithm optimized with Particle Swarm Optimization (PSO). The dataset consists of 657 medical records of inpatient schizophrenia cases from February 2023 to March 2025, categorized into three length-of-stay classes: short (1–5 days), medium (6–10 days), and long (>10 days). The C4.5 algorithm is used to construct a decision tree model based on historical data, while PSO is employed as an optimization method to improve the model configuration. The evaluation uses classification accuracy and Mean Absolute Percentage Error (MAPE) for room demand estimation. The results show that both the C4.5 and C4.5–PSO models achieve similarly high accuracy on the test data, while the manual MAPE calculation for room demand estimation yields a value of 52.66%. In contrast, the MAPE calculated by the system is 0.00% in the test scenario because all classes in the test data are correctly predicted. The web-based decision support system developed using Python and Streamlit is able to automatically provide predictions of length of stay and estimates of the required number of psychiatric beds at RSUD Muyang Kute.
Co-Authors Abdullah, ⁠Dahlan Afif, Muhammad Athallah Afridah, Rita Agustriya, Manda Al-Ghiyats, Said Ananda Faridhatul Ulva Andreansyah, Sabda Arnawan Hasibuan Azzikri, Affan Syafiq Bustami Bustami Cut Agusniar Dahlan Abdullah Dhani, Saniah Dinda, Dinda Fadillah, Rizky Fahruddin Fahruddin Fajriana, F Fajriana, Fajriana Farhiyah, Dara Fasdarsyah Fasdarsyah Fidyatun Nisa Fikhri, Aditya Aziz Fitri, Anisa Amelia Fuddin, Mudhya Hasan Dalimunthe, Amir Imanda, Nanda Kamaruzzaman, Hilda Zulfira Khalid, M David Kiram, Saiful KURNIAWATI - Kurniawati Kurniawati Lidya Rosnita Lubis, Syahrul Andika Melani, Siska Amelia Muhammad Daud Muhammad Fauzan Muhammad Ikhwanus Muhammad Muhammad Mutammimul Ula Muthalib, Muchlis Abd Nadia Saphira Nasution, Wahidatunnisa Nurdin Nurdin Nurdin Nurdin Nurul Aula Putri Agustina Dewi Putri, Nazirah Allisya Rahman, Ashri Nurhajizah Ridha, Ridha Rini Meiyanti Rizal Rizal Rizal S.Si., M.IT, Rizal Rizki Suwanda Rizky Putra Fhonna Rizky Putra Phonna Rizky, Rahmat Rozzi Kesuma Dinata Rusadi, Athirah Said Fadlan Anshari Salimuddin, Salimuddin Sayed Fachrurrazi Sayuti, Muhammad Siagian, Tania Annisa Sinambela, Reza Syahputra Sitepu, Yuni SariBr Siti Aminah Sudarti, Atrida Sujacka Retno Susanti Susanti Taufiq Taufiq Ulfah, Julia Veri Ilhadi Yasin, Fijri Ahmad Yessi Apprilia Yesy Afrillia Yopy Anfelia Yulisda, Desvina Zailani Mohamed Sidek Zara Yunizar