Article Per Year (5 Year)
p-Index From 2020 - 2025
3.161
P-Index
This Author published in this journals
All Journal ComEngApp : Computer Engineering and Applications Journal Jurnal CoreIT JIEET (Journal of Information Engineering and Educational Technology) Sebatik Building of Informatics, Technology and Science Jurnal Informatika Ekonomi Bisnis JOURNAL OF INFORMATION SYSTEM RESEARCH (JOSH) Journal of Computer System and Informatics (JoSYC) Information System Journal (INFOS) Bulletin of Computer Science Research KLIK: Kajian Ilmiah Informatika dan Komputer JUSTIN (Jurnal Sistem dan Teknologi Informasi) Bulletin of Information Technology (BIT) Malcom: Indonesian Journal of Machine Learning and Computer Science Jurnal Informatika Ekonomi Bisnis
Suwanto Sanjaya
UIN Suska Riau
Computer Science & IT Decision Sciences, Operations Research & Management Economics, Econometrics & Finance Engineering Industrial & Manufacturing Engineering

Published : 24 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 24 Documents
Search

 1   2   3 
Perbandingan Performa Random Forest dan Long Short-Term Memory dalam Klasifikasi Teks Multilabel Terjemahan Hadits Bukhari: Comparison of Random Forest and Long Short-Term Memory Performance in Multilabel Text Classification of Bukhari Hadith Translation Ahmad, Rizmah Zakiah Nur; Harahap, Nazruddin Safaat; Agustian, Surya; Iskandar, Iwan; Sanjaya, Suwanto
MALCOM: Indonesian Journal of Machine Learning and Computer Science Vol. 5 No. 3 (2025): MALCOM July 2025
Publisher : Institut Riset dan Publikasi Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.57152/malcom.v5i3.2046

Abstract

Hadits merupakan fondasi utama kedua dalam Islam, yang memandu umat Islam dalam menafsirkan nilai-nilai Islam dan mengimplementasikannya secara nyata dalam berbagai aspek kehidupan. Salah satu perawi hadits yang paling dihormati adalah Imam Bukhari, yang dikenal dengan ketelitian dan ketegasannya dalam memilih hadits-hadits yang otentik. Penelitian ini menggunakan data dari terjemahan hadis dari Sahih Bukhari ke dalam bahasa Indonesia yang telah diklasifikasikan ke dalam tiga kategori utama, yaitu anjuran, larangan, dan informasi. Untuk mengidentifikasi karakteristik masing-masing kategori, klasifikasi teks dilakukan dengan menggunakan dua metode populer, yaitu Random Forest (RF) dan Long Short-Term Memory (LSTM), yang dikenal efektif dalam memproses data teks berskala besar dan kompleks. Tujuan dari penelitian ini adalah untuk menguji perbedaan kinerja antara kedua metode tersebut dalam mengelompokkan hadis yang datanya telah lengkap. Hasil evaluasi menunjukkan bahwa metode RF mencapai akurasi tertinggi sebesar 89,48%, sedikit lebih unggul dari LSTM yang memperoleh 88,52%. Kedua metode mencatat nilai Hamming Loss yang sama, yaitu 0,1048 (89,52%). Temuan ini menunjukkan bahwa kelengkapan dan kualitas data hadis Bukhari berkontribusi dalam meningkatkan akurasi klasifikasi dengan memberikan konteks dan variasi yang lebih baik untuk model.
Perbandingan Performa Metode Klasifikasi Teks Multilabel Hadis Terjemahan Bukhari Menggunakan Support Vector Machine dan Long Short Term Memory: Performance Comparison of Multilabel Text Classification Methods on Translated Hadiths of Bukhari Using Support Vector Machine and Long Short Term Memory Ramadhani, Aulia; Safaat, Nazruddin; Agustian, Surya; Iskandar, Iwan; Sanjaya, Suwanto
MALCOM: Indonesian Journal of Machine Learning and Computer Science Vol. 5 No. 3 (2025): MALCOM July 2025
Publisher : Institut Riset dan Publikasi Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.57152/malcom.v5i3.2051

Abstract

Hadis merupakan sumber hukum kedua dalam Islam, dan salah satu kitab hadis yang paling dikenal adalah Shahih al-Bukhari. Untuk mendukung pemahaman dan pengamalan yang tepat, hadis perlu diklasifikasikan secara akurat. Mengingat satu hadis dapat mengandung lebih dari satu informasi, pendekatan klasifikasi multilabel menjadi sangat relevan. Penelitian ini bertujuan untuk memberikan kontribusi dalam bidang klasifikasi teks dengan mengeksplorasi kombinasi metode dan parameter yang optimal untuk klasifikasi multilabel hadis. Hasil penelitian menunjukkan bahwa Support Vector Machine (SVM) memberikan performa terbaik pada label Larangan dengan Macro F1-score sebesar 82,57%, melalui kombinasi SVM + TF-IDF menggunakan kernel = linear, parameter C (regularization parameter) = 1 tanpa stopword removal dan tanpa balancing. Sementara itu, Long Short Term Memory (LSTM) juga unggul pada label Larangan dengan Macro F1-score 82,66% pada kombinasi parameter Epoch = 20, Dropout = 0.5, Dense = 128 dan Batch Size = 64 tanpa stopword removal dan tanpa balancing kombinasi ini juga menghasilkan nilai Hamming Loss terendah sebesar 10,452%, yang lebih baik dibandingkan dengan penelitian sebelumnya serta menunjukkan bahwa LSTM terbukti lebih efektif secara keseluruhan dengan penyetelan parameter yang tepat. Penelitian ini juga berkontribusi dalam peningkatan kualitas data dengan melengkapi matan hadis yang digunakan, sehingga menghasilkan performa klasifikasi yang lebih baik.
Penerapan Algoritma K-Means Clustering pada Kinerja Mesin Screw press Kurnia Rahman, Fikri; Jasril; Sanjaya, Suwanto; Handayani, Lestari; Insani, Fitri
Bulletin of Information Technology (BIT) Vol 6 No 2: Juni 2025
Publisher : Forum Kerjasama Pendidikan Tinggi (FKPT)

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47065/bit.v6i2.2002

Abstract

The screw press is one of the machines used in the process of separating oil from tanks containing Fresh Fruit Bunches (FFB). The machine consists of a twin-screw system that functions to extract oil from the pressing unit, with back pressure applied by a hydraulic double cone. The mixed fruit residue is compreWCSSd, causing the oil contained within the residue to be released due to the pressure exerted by the press machine. Maintenance and repair of machinery are eWCSSntial activities to support productive operations in any sector. Therefore, it is necessary to conduct analysis to identify patterns in machine conditions within the factory. One effective approach to discovering machine condition patterns is through clustering techniques. Clustering is a method of grouping data based on certain parameters to form clusters of objects that share similar characteristics. In this study, data were collected from PT. XYZ for the period of April 2024 to May 2024, with a total of 23,002 records. The analysis was conducted using the K-Means Clustering algorithm, with testing carried out on 3 to 15 clusters. Based on the evaluation using the Davies-Bouldin Index (DBI), the most optimal clustering result was obtained with 3 clusters, achieving the lowest DBI value of 0.386. Meanwhile, using the Elbow Method, the optimal number of clusters was determined to be 4, as indicated by the Elbow point on the WCSS graph, with a Sum of Square Error (WCSS) value of 270. Therefore, it can be concluded that the clustering results using the K-Means Clustering algorithm are relevant for identifying machine condition patterns and are expected to assist in monitoring and managing the condition of the screw press machine.
Turbofan Engine Remaining Useful Life Prediction Using 1-Dimentional Convolutional Neural Network Fauzan, Ahmad; Handayani, Lestari; Insani, Fitri; Jasril; Sanjaya, Suwanto
Computer Engineering and Applications Journal (ComEngApp) Vol. 13 No. 3 (2024)
Publisher : Universitas Sriwijaya

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

Abstract

Turbofan engines have been the dominant type of engine in aircraft for the last forty years. Ensuring the quality of these engines is crucial for flight safety, particularly for long-distance flights. However, their performance degrades over time, impacting flight safety. To address this issue, it is essential to predict potential engine failures by estimating the Remaining Useful Life (RUL) of the engines Deep learning, especially Convolutional Neural Networks (CNNs), has demonstrated exceptional proficiency in handling intricate, non-linear data, leading to improved RUL predictionsdue to their ability to process complex and non-linear data. In this project, a 1-D CNN is used to predict RUL using the NASA C-MAPSS FD001 dataset, which consists of 3 settings and 21 sensors, though sensors with stagnant readings are excluded. The dataset is normalized using min-max and z-score methods, and then segmented into sequences for input into the 1-D CNN model. Various training scenarios were evaluated, with the best RMSE of 3.26 achieved using 10 epochs, a learning rate of 0.0001, and z-score normalization. The results indicate that feature selection can produce a lower RMSE compared to scenarios without feature selection.
Co-Authors Agustian, Surya Ahmad Fauzan Ahmad, Rizmah Zakiah Nur Al Fiqri, M. Faiz Aqilah, M Alfandri Aulia Ramadhani Eka Pandu Cynthia, Eka Pandu Elin Haerani Elvia Budianita Ersad Alfarsy Absar, Ersad Alfarsy Fadhilah Syafria Febi Yanto, Febi Fitri Insani Fitri, Dina Deswara Gusti, Siska Kurnia Harni, Yulia Iis Afrianty Israldi, Tino Iwan Iskandar Jasril Jasril Jasril Jasril Kurnia Rahman, Fikri Kurniawan, Saifur Yusuf Lestari Handayani Masaugi, Fathan Fanrita Mazdavilaya, T Kaisyarendika Muhammad Fikry Muhammad Irsyad Nazir, Alwis Nazruddin Safaat Nazruddin Safaat H Negara, Benny Sukma Pangestu, Yoga Pizaini Pizaini, Pizaini Radili, Adi Rahmad Abdillah Saputra, Nugroho Wahyu Shahira, Fayza Sugandi, Hatami Karsa Syaputra, Muhammad Dwiky Vitriani, Yelfi Yani, Susmi Syahfrida Yusra, Yusra