Article Per Year (5 Year)
p-Index From 2021 - 2026
6.722
P-Index
This Author published in this journals
All Journal Communications in Science and Technology Jurnal Informatika Universitas Pamulang INTECOMS: Journal of Information Technology and Computer Science JSiI (Jurnal Sistem Informasi) Indonesian Physical Review Building of Informatics, Technology and Science Infotekmesin Piston: Journal of Technical Engineering Journal of Innovation and Future Technology (IFTECH) Jurnal Sistem Komputer & Kecerdasan Buatan Buletin LOUPE (Laporan Umum Penelitian) Journal of Applied Sciences and Advanced Technology Jurnal Pengendalian Pencemaran Lingkungan (JPPL) Jurnal Teknologi Informatika dan Komputer Akrab Juara : Jurnal Ilmu-ilmu Sosial Jurnal Mesin Nusantara Jurnal Pengabdian kepada Masyarakat Jurnal Abdimas Indonesia : Jurnal Abdimas Indonesia International Journal of Engagement and Empowerment (IJE2) JURNAL ILMIAH GLOBAL EDUCATION Journal Of Sustainable Research In Management Of Agroindustry (SURIMI) ACROPORA: Jurnal Ilmu Kelautan dan Perikanan Papua JAMAIKA: Jurnal Abdi Masyarakat Abdi Jurnal Publikasi Jurnal Teknologi Pangan dan Industri Perkebunan OKTAL : Jurnal Ilmu Komputer dan Sains Hikmayo: Jurnal Pengabdian Masyarakat Jurnal Ilmiah Multidisiplin Indonesia MULTIPLE: Journal of Global and Multidisciplinary Acta Solum Food and Agro-industry (FAGI) Journal Jurnal Ilmu Komputer
Murni Handayani
Universitas Pamulang, Banten, Indonesia
Religion Aerospace Engineering 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 Law, Crime, Criminology & Criminal Justice Library & Information Science Materials Science & Nanotechnology Mathematics Mechanical Engineering Medicine & Pharmacology Physics Public Health Social Sciences Transportation Other

Published : 43 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 43 Documents
Search

 1   2   3   4   5 
Pengembangan Material Maju Superkonduktor Mg-B dengan Penambahan Graphene Oxide melalui Proses Powder in Sealed Tube Mahendra, Brillian Ardy; Herbirowo, Satrio; Saefuloh, Iman; Handayani, Murni
Jurnal Mesin Nusantara Vol 5 No 1 (2022): Jurnal Mesin Nusantara
Publisher : Universitas Nusantara PGRI Kediri

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.29407/jmn.v5i1.17894

Abstract

MgB2 is a high possible superconducting material that can be applied quite practically with the functionalization of Mg-B materials. Material development is carried out by adding carbon, namely Graphene Oxide (GO), which is a single atom layered material. The Powder in Sealed Tube (PIST) method is practically used to reduce oxidation. This study aims to analyze the effect of GO material doped with the PIST method made from MgB2 with a sintering temperature of 800℃ for 2 hours on its superconductivity, compound formation, and microstructure. The manufacturing process is carried out in a 1:2 ratio where 98% purity Mg is mixed with Boron, which is then added with 0, 0.3 and 3% wt GO doping, all ingredients are mixed stoichiometrically. The material that has been put in a tube and compacted sufficiently into SS316L which has been closed on one side to enter the powder, is then compacted with high pressure up to 1000 MPa. The material is sintered at a temperature of 800℃ for 2 hours which is then carried out by cooling in the furnace and taking bulk samples. The XRD results showed the formation of the dominant MgB2 phase and the formation of an impurity phase in the form of MgO and obtained a decent crystal size of 295 which was owned by the 3%wt GO PIST MgB2 sample. The SEM test shows the forms of formation (agglomeration) in each sample, with the presence of several axes. Cryogenic testing shows that with doping there is a movement of critical temperature to a lower direction where MgB2 0%wt GO has a TcOnset value of 39.4 K and a TcZero of 38.7 K, while MgB2 3%wt GO has a TcOnset value of 39.6 K and TcZero of 38 K.
A Comparative Study of DenseNet-201 and Swin Transformer for Malignant and Benign Skin Lesion Classification Hidayat, Dahlan; Musyafa, Ahmad; Handayani, Murni
Jurnal Teknologi Informatika dan Komputer Vol. 12 No. 1 (2026): Jurnal Teknologi Informatika dan Komputer
Publisher : Universitas Mohammad Husni Thamrin

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.37012/jtik.v12i1.3265

Abstract

Skin cancer has a high global prevalence, underscoring the need for accurate and efficient early detection systems to support screening. This study presents a comparative analysis of DenseNet-201 and Swin Transformer for binary classification of malignant and benign skin lesions using the BCN20000 dataset, which contains 12,413 dermoscopic images. The proposed workflow includes image preprocessing and augmentation, transfer learning-based model training, and evaluation under a 5-fold stratified cross-validation protocol. Performance is assessed using Accuracy, Precision, Sensitivity (Recall), F1-score, and the area under the receiver operating characteristic curve (AUC-ROC). In addition, computational efficiency is examined in terms of parameter count, model size, and training time. Across five folds, DenseNet-201 achieved 88.05% Accuracy, 88.90% Precision, 89.48% Sensitivity, 89.17% F1-score, and 94.73% AUC, whereas Swin Transformer achieved 87.42% Accuracy, 89.77% Precision, 87.06% Sensitivity, 88.39% F1-score, and 94.33% AUC. A paired t-test at α = 0.05 indicated no statistically significant performance difference between the two models. Model interpretability was investigated using Grad-CAM for DenseNet-201 and EigenCAM for Swin Transformer to verify that predictions were driven by lesion-relevant regions. Overall, the results suggest that both architectures are suitable candidates for dermoscopic image-based skin lesion screening support systems, including teledermatology applications.
Utilization of Coconut Shells as a Source of Graphene Nanosheets Fe/N-GNS for Environmentally Friendly Primary Battery Electrodes Giyanto; Affi, Jon; Gunawarman; Handayani, Murni; Yetri, Yuli
Piston: Journal of Technical Engineering Vol. 9 No. 2 (2026)
Publisher : Program Studi Teknik Mesin Universitas Pamulang

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.32493/pjte.v9i2.57488

Abstract

The research on the performance of carbon (C)/d-orbital metals (graphite/graphene, graphene/N-graphene, graphite/Fe-graphene, graphite/Fe-N-graphene, and graphene/Fe-N-graphene) in primary battery electrode systems was carried out using a simple technology by mixing coconut shell powder with N and Fe. The purpose of this study was to determine the preparation method of Fe/GNS and Fe/N-GNS electrodes and to evaluate the performance of the electrolyte on electron distribution in Fe/GNS and Fe/N-GNS electrodes as primary battery anodes based on electrical conductivity values. This research was conducted as a laboratory experimental study. GNS and N-GNS were synthesized using a modified Hummers method, while Fe/GNS and Fe/N-GNS electrodes were synthesized using the impregnation method. GNS, N-GNS, Fe/GNS, and Fe/N-GNS after electrolyte combination were characterized using SEM–EDX and a multimeter, respectively. The SEM–EDX results at 170 °C and 500–600 °C showed a folded and wrinkled graphene structure with dispersed Fe (5.3 wt% by EDX), dominated by C and O. The addition of Fe–NH₃ acted as a catalyst to form more regularly structured graphite. The DHL test showed the highest electrical conductivity (~51,400 at 40 V) for Fe-N-GNS samples synthesized at 170 °C and 600 °C, which were identified as the most optimal synthesis conditions.
Synthesis of Graphene-Like Carbon from Coconut Shell and Electrical Conductivity Properties Rohmat, Nur; Affi, Jon; Gunawarman; Handayani, Murni; Yetri, Yuli
Piston: Journal of Technical Engineering Vol. 9 No. 2 (2026)
Publisher : Program Studi Teknik Mesin Universitas Pamulang

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.32493/pjte.v9i2.57489

Abstract

Demand for batteries continues to increase in line with the growth of electric vehicles, while the availability of lithium in nature is limited. One alternative is the use of renewable natural materials, such as coconut shells, to produce functional carbon materials. This study aims to synthesize graphene-like carbon (GLC) from coconut shells using pyrolysis and sonication methods. The process was carried out through drying at 150–200 °C and pyrolysis at 700 °C. XRD characterization showed main peaks at 2θ ≈ 23.11° and 43.75° (150 °C/700 °C), and 23.15° and 43.38° (200 °C/700 °C), with an interlayer spacing of 0.35 nm and a shift in the C (002) peak from pure graphite, indicating the formation of nanosized graphene layers. FTIR analysis confirmed the presence of O–H, aromatic C=C, C=O, and C–O groups, indicating a hexagonal carbon framework with oxygen functionality on the surface. The Raman spectrum showed ID/IG ratios of 0.84 and 0.83, indicating structural disorder while still consistent with graphene-like characteristics. Conductivity tests showed relatively stable electrical conductivity with gradual electron energy loss at small current increases, allowing better control of electron mobility.
Optimization of RNN and Tree-Based Models with Imbalance Handling for Fraud Detection in Digital Banking Transactions Darmawan, Rizki Ahmad; Musyafa, Ahmad; Handayani, Murni
Jurnal Ilmiah Multidisiplin Indonesia (JIM-ID) Vol. 5 No. 02 (2026): Jurnal Ilmiah Multidisplin Indonesia (JIM-ID), February 2026
Publisher : Sean Institute

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

Abstract

This study focuses on addressing the growing challenge of fraud detection in digital banking transactions, which has intensified alongside the rapid expansion of digital financial services. Fraud detection is particularly complex due to the highly imbalanced nature of transaction data, large data volumes, and intricate transaction patterns that make fraudulent activities difficult to identify accurately. Although previous research has applied a wide range of methods, from conventional machine learning techniques to advanced deep learning models, many approaches still face limitations in balancing high detection accuracy with computational efficiency. The main objective of this research is to compare the performance of Recurrent Neural Network (RNN)–based models, including Long Short-Term Memory (LSTM), Gated Recurrent Unit (GRU), and Bidirectional LSTM (BiLSTM), with tree-based ensemble models such as XGBoost and LightGBM in detecting fraudulent banking transactions. To enhance model effectiveness, the study implements a comprehensive data preprocessing framework that includes data cleaning, feature engineering, and techniques for handling class imbalance, particularly the use of Synthetic Minority Over-sampling Technique (SMOTE). Furthermore, model performance is optimized through systematic hyperparameter tuning using Optuna, Hyperopt, and Keras Tuner. Evaluation is conducted using metrics suitable for imbalanced datasets, such as precision, recall, F1-score, and AUC-ROC. The expected outcome is the identification of a robust and efficient fraud detection model that improves detection accuracy and sensitivity, while offering valuable insights for both academic research and practical banking applications.
Analysis and Evaluation of Qur’an Translation Topics Using Classical, Neural, and Transformer-Based Topic Modelling Kurnia, Akhmad Rinaldy; Anggai, Sajarwo; Handayani, Murni
Jurnal Ilmiah Multidisiplin Indonesia (JIM-ID) Vol. 5 No. 02 (2026): Jurnal Ilmiah Multidisplin Indonesia (JIM-ID), February 2026
Publisher : Sean Institute

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

Abstract

Topic modelling is an important approach for extracting latent thematic structures from text corpora, including religious texts that are characterized by dense semantics and short documents. This study aims to compare the performance of several topic modelling methods Latent Dirichlet Allocation (LDA), Biterm Topic Model (BTM), Combined Topic Model (CombinedTM), and BERTopic in extracting topics from the Indonesian translation of the Qur’an. The dataset consists of 6,236 verses, with each verse treated as a single document. Topic quality is evaluated using two main metrics: coherence score (C_v) and topic diversity. The experimental results show that CombinedTM achieves the highest coherence score, with a maximum value of approximately 0.52 at K = 10 topics, followed by BTM, which demonstrates relatively high and stable coherence scores (around 0.50) across certain topic number variations. LDA yields the highest topic diversity, exceeding 0.90, but with lower coherence scores compared to the other models, indicating its limitations in preserving semantic coherence in short texts. Meanwhile, BERTopic exhibits consistently high topic diversity (0.85–0.88) across different numbers of topics, although its bag-of-words–based coherence scores do not always increase significantly. These findings highlight that the choice of topic modelling method should be aligned with the characteristics of the corpus and the objectives of thematic analysis, particularly in the context of short-form religious texts.
Nickel Electroplating on 3D Printed Polylactic Acid (PLA) for Hardness Enhancement Ragaventrand, Ramses Maur; Saptaji, Kushendarsyah; Setiawan, Iwan; Handayani, Murni; Fernandez, Nikolas Krisma Hadi
Journal of Applied Sciences and Advanced Technology Vol. 8 No. 2 (2025): Journal of Applied Science and Advanced Technology
Publisher : Faculty of Engineering Universitas Muhammadiyah Jakarta

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.24853/jasat.8.2.27-34

Abstract

Electroplating is a process that uses electric current to deposit a layer of metal onto the surface of a conductive material, enhancing its properties such as corrosion resistance, electrical conductivity, and mechanical strength. This study investigates the process of nickel electroplating on 3D-printed polylactic acid (PLA) substrates, focusing on the efficiency and quality of the nickel coatings achieved through electroplating techniques. The methodology encompasses several stages, starting with the design and 3D printing of PLA specimens. Following this, the preparation of the electroplating setup is meticulously carried out, ensuring optimal conditions for the electroplating process. The quality of the nickel coating is then evaluated through a series of tests to assess its mechanical and electrical properties. The key findings from this research indicate that the electroplating process effectively deposits nickel onto the PLA substrates. This deposition significantly enhances the mechanical strength and electrical conductivity of the PLA specimens. The study's results suggest that nickel electroplating on PLA can be a viable method for improving the material properties of 3D-printed parts. This advancement not only contributes to the development of cost-effective and sustainable metal coating techniques for polymer-based materials but also has the potential to broaden the application scope of 3D-printed parts in various fields of engineering and technology. Such improvements could be particularly beneficial in industries requiring enhanced material performance, such as electronics, automotive, and aerospace sectors.
ANALISIS SISTEM DETEKSI DINI FRAUD PADA TRANSAKSI PERBANKAN MENGGUNAKAN LONG SHORT-TERM MEMORY (LSTM) DAN TRANSFORMER Abdullah, Arken; Waskita, Arya Adhyaksa; Handayani, Murni
INTECOMS: Journal of Information Technology and Computer Science Vol. 9 No. 1 (2026): INTECOMS: Journal of Information Technology and Computer Science
Publisher : Institut Penelitian Matematika, Komputer, Keperawatan, Pendidikan dan Ekonomi (IPM2KPE)

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.31539/83yrz474

Abstract

The development of digital banking services in electronic payment channels has led to a significant increase in transaction volumes, accompanied by higher fraud risk. Fraud patterns are dynamic and temporal, making detection based solely on individual transactions ineffective. This study aims to develop an early fraud detection system using a cluster-aware sequential deep learning approach. Transaction data are processed through data cleansing, behavioral feature extraction, and customer clustering based on transaction characteristics. Long Short-Term Memory (LSTM) is employed to learn temporal transaction patterns, while Transformer is used to capture global context and nominal transaction deviations. Both models are integrated through a dynamic ensemble approach with adaptive thresholds for each cluster. Model evaluation is conducted in a supervised manner using PR-AUC as the primary metric, supported by ROC-AUC, Precision, Recall, and F1-Score. The results demonstrate that the cluster-based ensemble approach improves detection stability, reduces false positives, and adapts effectively to differences in customer behavior. Experimental results show that models trained without oversampling provide more stable precision–recall performance on datasets where fraud manifests as extreme behavioral outliers, while SMOTE is used as a comparative scenario.  Keywords: Fraud Detection, Deep Learning, LSTM, Transformer, Bank
ANALISIS PREDIKTIF UNTUK MENINGKATKAN RETENSI MAHASISWA MENGGUNAKAN METODE RECURRENT NEURAL NETWORK DAN SUPPORT VECTOR MACHINE Siti Cici Carliah; Tukiyat Tukiyat; Murni Handayani
Journal of Innovation And Future Technology Vol. 8 No. 1 (2026): Vol 8 No 1 (Februari 2026): Journal of Innovation and Future Technology (IFTECH
Publisher : LPPM Unbaja

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47080/iftech.v8i1.4382

Abstract

Student retention is a critical indicator in evaluating the quality of higher education institutions. High dropout rates pose significant challenges, including at Al-Khairiyah University in Cilegon, Banten. This study develops a predictive model for student retention using two machine learning approaches: Recurrent Neural Network (RNN) and Support Vector Machine (SVM), while identifying the most influential factors. The dataset comprises 3371 records from 2021-2024, including academic variables (GPA, semester grades 1-8, attendance) and non-academic variables (organizational activity, competition achievements, parental income, admission pathway, and study system). Data was split into 80% training and 20% testing sets. Results show that the RNN model demonstrates superior performance with 93.5% accuracy, 99.7% precision, 89.3% recall, 94.2% F1-score, and 0.967 AUC, while SVM achieved 85.5% accuracy, 89.8% precision, 85.3% recall, 87.5% F1-score, and 0.912 AUC. Feature importance analysis reveals that Total GPA and first-semester grades (IPS.1) are the dominant factors influencing student retention, while non-academic factors have relatively small contributions. This research provides practical contributions through an Early Warning System framework that can be implemented by universities to detect at-risk students early, enabling proactive academic interventions.
Chatbot dengan RAG untuk Sistem FAQ Pondok Pesantren menggunakan Model Retriever dan Generator: Chatbot dengan RAG untuk Sistem FAQ Pondok Pesantren menggunakan Model Retriever dan Generator Surya, Surya Ariwibowo; Heryandi Suradiradja, Kahfi; Handayani, Murni
Jurnal SISKOM-KB (Sistem Komputer dan Kecerdasan Buatan) Vol. 9 No. 2 (2026): Volume IX - Nomor 2 - Februari 2026
Publisher : Teknik Informatika, Sistem Informasi dan Teknik Elektro

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47970/siskom-kb.v9i2.890

Abstract

Pesatnya perkembangan teknologi informasi mendorong lembaga pendidikan, termasuk pondok pesantren, untuk menyediakan akses informasi yang lebih efisien. Saat ini, penyampaian informasi di pondok pesantren masih dilakukan secara manual, sehingga memakan waktu dan tenaga karena harus menjawab pertanyaan yang berulang dari wali santri. Penelitian ini mengembangkan chatbot FAQ berbahasa Indonesia menggunakan pendekatan Retrieval-Augmented Generation (RAG) yang menggabungkan model retriever dan generator untuk menghasilkan jawaban yang relevan dan alami. Model retriever yang digunakan meliputi SBERT, DPR, dan E5, sedangkan model generator terdiri dari IndoBART, IDT5, dan IndoGPT. Data dikumpulkan melalui observasi, wawancara, dan studi literatur. Sistem dirancang menggunakan pencocokan semantik berbasis vektor dan decoding autoregresif untuk menghasilkan jawaban. Evaluasi performa dilakukan dengan metrik Hit@1, BLEU, dan BERTScore. Berdasarkan Hasil penelitian menunjukkan bahwa kombinasi SBERT + IndoBART mencapai akurasi tertinggi sebesar 96%, diikuti SBERT + IdT5 sebesar 95%. Model E5 mencatat skor CSAT tertinggi sebesar 70% dan respon tercepat 0.066 detik, sementara RoBERTa memperoleh skor CSAT terendah 39%, sehingga kombinasi SBERT + IndoBART cocok diterapkan dalam chatbot FAQ PPS. Imam Syafi’i.
Co-Authors Abdullah, Arken Abu Khalid Rivai Agus Santoso Ahmad Gunawan Wibisono Al Habib, Irsyad Allam Ramzy Allam Ramzy Anggai, Sajarwo Annisa Yuliana Angeline Any Kurniawati, Any Ari Kristiningsih Arrozi , Ubed Sonai Fahruddin Arsita Nur Rizkia Putri Astuti, Wijayanti Dwi Aza Fauziana, Noer Choirunnisa Firdaus Ivana Da, Oh Wen Darmawan, Rizki Ahmad Dawam Agung Pribadi Destiny, Keysi Devain Dewanto, Hizkia Alpha Dwi, Sadina Sahitya Dwityaningsih, Rosita Evila Purwanti Sri Rahayu, Theresia Fadillah Fajar Hidayanto, Fajar Feni Aryanti Fernandez, Nikolas Krisma Hadi Fitri Khoerunnisa Giyanto Gunawarman Hartanto Heryandi Suradiradja, Kahfi Hesti Rahayuningsih Hidayat, Dahlan Hizam, Fadli Iasya, Yurin Karunia Apsha Albaina Ilma Fadlilah Ipung Saputra Irnanda, Istifhamy Iwan Setiawan Jatmoko Awali Joko Setia Pribadi Jon Affi, Jon Kanim Kristiningsih, Ari Kurnia, Akhmad Rinaldy Kushendarsyah Saptaji Latifatul Khusna Lutfi Syafirullah Mahendra, Brillian Ardy Makhsun Makhsun Makhsun Mardiyana Mardiyana Mardiyana Mardiyana Maulana, Romdon Mila Prametha, Novika Moh. Triyana Abbas Mohammad Nurhilal Mohammad Rayhan Afdillah Muhamad Sibli Muji Mulyani Mustofa, Rizki musyafa, ahmad Nabila, Najwa Natasya Arifah Natasya Arifah Nur Indah Wardani Nur Rohmat Nuraini Sitepu Nuraini Sitepu Nurhayati, Mita Nurlinda Ayu Triwuri Oto Prasadi putri, raekhanrahmah Putri, Restiani Alia Raekhan Rahmah Putri Rafli Rafli Rafli Rafli Ragaventrand, Ramses Maur Reno Saeprani Retno Tri Purnamasari Rifqi Fakhri Yogi Syafruddin Rizki Agustian Rosita Dwityaningsih Rosita, Rosita Dwityaningsih Saefuloh, Iman Salma Maulikhatun Zulfa Santika, Ariel Sari Widya Utami Sari Widya Utami Satrio Herbirowo, Satrio Siti Cici Carliah Siti Khoirunnisa Slamet Raharjo Slamet Raharjo Sudarno Sudarno Sumardiono, Arif Surya, Surya Ariwibowo Syadilla Ega Maharani Taswanda Taryo Taswanda Taryo Tukiyat Tukiyat Tukiyat Tukiyat Tukiyat, Tukiyat Ulikaryani Uliyatunisa Uliyatunisa, Uliyatunisa Waskita, Arya Adhyaksa Widuri Indana Saleha Widuri Indana Saleha Witriansyah, Khoeruddin Wittriansyah, Khoeruddin Yessi Permana Yuli Yetri Yunita Triana, Yunita Yunus Yunus Zain, Rafi Mahmud Zeni Ulma