p-Index From 2021 - 2026
7.599
P-Index
This Author published in this journals
All Journal TELKOMNIKA (Telecommunication Computing Electronics and Control) JAIS (Journal of Applied Intelligent System) SISFOTENIKA Journal of Electrical Technology Jurnal Teknologi Informasi MURA Voice Of Informatics Zero : Jurnal Sains, Matematika, dan Terapan JOURNAL OF SCIENCE AND SOCIAL RESEARCH JURNAL TEKNOLOGI DAN ILMU KOMPUTER PRIMA (JUTIKOMP) CSRID (Computer Science Research and Its Development Journal) Jurnal Informatika Kaputama (JIK) Jurnal Mantik IT (INFORMATIC TECHNIQUE) JOURNAL ICIT (Innovative Creative and Information Technology) Journal REMIK : Riset dan E-Jurnal Manajemen Informatika Komputer Journal of Computer Science, Information Technology and Telecommunication Engineering (JCoSITTE) Journal of Computer Networks, Architecture and High Performance Computing Jurnal Generic JUDIMAS (Jurnal Inovasi Pengabdian Kepada Masyarakat) Journal of Applied Computer Science and Technology (JACOST) DEVICE Syntax: Journal of Software Engineering, Computer Science and Information Technology Majalah Ilmiah UPI YPTK Jurnal SAINTIKOM (Jurnal Sains Manajemen Informatika dan Komputer) INFOSYS (INFORMATION SYSTEM) JOURNAL Jurnal IPTEK Bagi Masyarakat Jurnal Ipteks Terapan : research of applied science and education International Journal of Research in Vocational Studies (IJRVOCAS) Jurnal Minfo Polgan (JMP) Jurnal Komputer Teknologi Informasi Sistem Komputer (JUKTISI) JURNAL ILMIAH INFOKOM Majalah Ilmiah METHODA TAMIKA: Jurnal Tugas Akhir Manajemen Informatika & Komputerisasi Akuntansi Jurnal Teknologi Informasi Mura Jurnal Abdimastek (Pengabdian Masyarakat Berbasis Teknologi) CSRID
Claim Missing Document
Check
Articles

Penerapan Metode POQ dalam Penentuan Persediaan Material Proyek pada PT. Swakarya Putra Berbasis Android Daniel Ginting; Rika Rosnelly
TAMIKA: Jurnal Tugas Akhir Manajemen Informatika & Komputerisasi Akuntansi Vol 5 No 2 (2025): TAMIKA: Jurnal Tugas Akhir Manajemen Informatika & Komputerisasi Akuntansi
Publisher : Universitas Methodist Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.46880/tamika.Vol5No2.pp302-310

Abstract

Material inventory is a crucial factor in the smooth running of construction projects. PT. Swakarya Putra has been facing challenges in managing its inventory, such as delays in stock information, recording errors, and unplanned purchases. The purpose of implementing the POQ method is to control material inventory to minimize inventory costs and ensure timely material availability. The POQ method contributes to determining the optimal order quantity and timing by considering ordering, storage costs, and project material requirements. The system is built on an Android platform so that it can be accessed in real time by relevant parties in the field. The implementation results show that the system is able to calculate material ordering schedules accurately, simplify stock monitoring, and reduce the risk of shortages or excess inventory. Thus, the implementation of the Android-based POQ method can improve the efficiency of controlling project material inventory at PT. Swakarya Putra. This method helps minimize the risk of stockouts and excess stock, as well as improve operational efficiency by ordering quantities at specific time intervals.
OPTIMASI PIPELINE KLASIFIKASI PENYAKIT PADI MENGGUNAKAN STRATEGI AUGMENTASI CITRA INTENSIF DAN TRANSFER LEARNING EFFICIENTNET-B0 Dwi Robiul R; Diyo Mollana F; Nanda S; Johan; Rahmad S; Satriyo W; Rika Rosnelly
INFOKOM (Informatika & Komputer) Vol. 13 No. 2 (2025): JURNAL INFOKOM DESEMBER 2025
Publisher : POLITEKNIK PIKSI GANESHA

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.56689/infokom.v13i2.2355

Abstract

Rice plant diseases represent a significant challenge to global food productivity. This study aims to optimize a rice disease classification pipeline using the EfficientNet-B0 architecture combined with intensive image augmentation strategies and transfer learning. The dataset comprises 10,407 rice leaf images categorized into 10 classes, including healthy conditions and nine types of diseases. Augmentation strategies such as random rotation, color jittering, and random resized cropping were implemented to enhance model robustness against diverse field conditions. Evaluation results demonstrate that the model achieved outstanding performance, with a Top-1 Accuracy of 96.25% and a Top-5 Accuracy of 99.90%. Grad-CAM++ analysis validated that the model accurately focuses feature extraction on pathological leaf areas. t-SNE visualization revealed clear feature cluster separation between classes, further supported by ROC curve AUC values reaching 1.00 for the majority of categories. This research confirms that the proposed pipeline is highly reliable for early rice disease detection and holds significant potential for mobile device implementation to assist farmers.
Practice-Based Digital Marketing and Coding Training to Strengthen Students’ Entrepreneurial Competencies at Bina Satria School Linda Wahyuni; Rika Rosnelly; Soeheri Soeheri; Chairul Rizal; Hardianto Hardianto; Andika Wiratama; Afandi Maulana
Jurnal IPTEK Bagi Masyarakat Vol 6 No 1 (2026)
Publisher : Ali Institute of Research and Publication

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.55537/j-ibm.v6i1.1738

Abstract

This community service program implemented practice-based digital marketing and coding training to strengthen students’ digital entrepreneurship competencies at Bina Satria School. The program integrated experiential learning and project-based learning through website development using HTML, PHP, and MySQL, product catalog management, and digital promotion activities. Thirty students participated in six groups. Data were collected through observation, interviews, documentation, identical pre-test and post-test questionnaires, and project assessment. The 12-item questionnaire was reviewed by three experts. Internal consistency testing yielded Cronbach’s α = 0.683 and standardized Cronbach’s α = 0.715. Before the training, 83.3% of participants reported no or limited understanding; after the training, 73.3% reported understanding or high understanding. All six groups completed functional website projects with scores ranging from 88 to 91. The findings indicate an aggregate shift toward higher understanding and support the practical feasibility of integrating coding and digital marketing in contextual entrepreneurship training. Because the evaluation used categorical descriptive data without a comparison group or paired inferential analysis, the findings do not establish the program’s causal effectiveness.
Optimasi Algoritma Genetika pada Perbandingan ANN dan KNN untuk Klasifikasi Penyakit Jantung Andreas Zai; Lima Hartima Rambe; Reza Ananda Putra; Rika Rosnelly; Tamado Simon Sagala; Indra Kelana Jaya
Majalah Ilmiah METHODA Vol. 15 No. 1 (2025): Majalah Ilmiah METHODA
Publisher : Universitas Methodist Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.46880/methoda.Vol15No1.pp10-23

Abstract

A comparative analysis of genetic algorithm optimization methods on the performance of Artificial Neural Network (ANN) and K-Nearest Neighbor (KNN) in heart disease classification shows significant results. The research used a heart disease dataset consisting of 303 samples with 14 attributes. Genetic algorithm optimization produced substantial performance improvements in both models. The optimized ANN model achieved 94.85% accuracy, 93.00% precision, 97.00% recall, and 97.00% ROC AUC, demonstrating excellence in positive case identification. Meanwhile, the optimized KNN model achieved 93.30% accuracy, 92.00% precision, 95.00% recall, and 96.77% ROC AUC, yielding more balanced performance. The genetic algorithm optimization method proves its effectiveness in improving heart disease classification accuracy, where ANN is optimal for applications requiring high sensitivity and KNN is more stable for small datasets.
EVALUASI DENSENET-201 UNTUK IDENTIFIKASI BIJI KOPI MENGGUNAKAN HYPERPARAMETER GRIDSEARCH Yuke Manza; Lima Hartimar Rambe; Kiki Putri Ani Siregar; Rika Rosnelly; Adil Setiawan
JOURNAL OF SCIENCE AND SOCIAL RESEARCH Vol. 8 No. 3 (2025): August 2025
Publisher : Smart Education

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.54314/jssr.v8i3.3898

Abstract

Abstract: Coffee is one of the most important commodities in the global agricultural sector. However, the manual sorting process of coffee beans, which is still widely applied in the Small and Medium Industry (IKM) sector, tends to be time-consuming and often results in inconsistent quality assessments. This study aims to classify coffee bean quality using the DenseNet-201 deep learning architecture, optimized with the GridSearch method to obtain the best combination of hyperparameters. The dataset used consists of 450 images of coffee beans divided into two classes: good-quality and defective beans. The model was trained for 20 epochs using a transfer learning approach and evaluated using performance metrics such as accuracy, precision, recall, and F1-score. The test results show that the model before optimization achieved an accuracy of only 78.67%, while the model optimized with GridSearch reached a high accuracy of 99.47% with a low loss value. These findings indicate that the application of DenseNet-201 with hyperparameter tuning is capable of producing accurate and stable classification results, and can be relied upon as an automated solution for sorting coffee beans based on their quality. Keywords: Deep Learning, DenseNet201, Hyperparameter, GridSearch, Coffee Bean Classification Abstrak: Kopi merupakan salah satu komoditas penting dalam sektor pertanian global. Namun, proses pemilahan biji kopi secara manual yang masih banyak diterapkan pada sektor Industri Kecil dan Menengah (IKM) cenderung memakan waktu dan menghasilkan penilaian kualitas yang tidak konsisten. Penelitian ini bertujuan untuk mengklasifikasikan kualitas biji kopi menggunakan arsitektur Deep Learning DenseNet-201 yang dioptimalkan dengan metode GridSearch untuk memperoleh kombinasi hyperparameter terbaik. Dataset yang digunakan terdiri dari 450 gambar biji kopi dengan dua kelas: biji kopi bagus dan biji kopi rusak. Model dilatih selama 20 epoch dengan pendekatan transfer learning dan dilakukan evaluasi terhadap performa model menggunakan metrik akurasi, precision, recall, dan f1-score. Hasil pengujian menunjukkan bahwa model sebelum optimasi hanya mencapai akurasi sebesar 78,67%, sedangkan model dengan optimasi GridSearch mampu mencapai akurasi tinggi sebesar 99,47% dan nilai loss yang rendah. Hal ini menunjukkan bahwa penerapan DenseNet-201 dengan tuning hyperparameter mampu menghasilkan klasifikasi yang akurat dan stabil, serta dapat diandalkan sebagai solusi otomatis dalam proses sortasi biji kopi berdasarkan kualitasnya. Kata kunci: Deep Learning, DenseNet201, Hyperparameter, GridSearch, Klasifikasi Biji Kopi
Perbandingan LSTM dan 1D CNN dalam Prediksi Harga Saham BCA Andra Alfitra; Rika Rosnelly; Wanayumini
Jurnal Minfo Polgan Vol. 15 No. 3 (2026): Artikel Penelitian
Publisher : Politeknik Ganesha Medan

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.33395/jmp.v15i3.16221

Abstract

Investasi merupakan salah satu aktivitas yang banyak diminati masyarakat, baik dalam bentuk real asset maupun financial asset, salah satunya adalah saham. Saham menjadi instrumen investasi yang memiliki potensi keuntungan tinggi, namun harga saham di pasar modal bersifat fluktuatif sehingga sulit diprediksi. Penelitian ini bertujuan untuk menganalisis dan membandingkan metode Long Short Term Memory (LSTM) dan One Dimensional Convolutional Neural Network (1D CNN) dalam prediksi harga saham PT Bank Central Asia Tbk (BBCA). Saham BBCA dipilih karena PT Bank Central Asia merupakan salah satu bank dengan jumlah pelanggan terbesar di Indonesia pada tahun 2024. Metode LSTM dipilih karena mampu menangani permasalahan vanishing gradient pada data sekuensial jangka panjang, sedangkan metode 1D CNN digunakan untuk mengekstraksi pola data time series secara efektif. Penelitian dilakukan melalui beberapa tahap pengujian parameter, meliputi time series, jumlah hidden neuron, max epoch, dan batch size untuk memperoleh model prediksi yang optimal. Hasil pengujian menunjukkan bahwa parameter terbaik diperoleh pada time series sebesar 5, hidden neuron sebesar 5, max epoch sebesar 50, dan batch size sebesar 4. Model yang dihasilkan memperoleh nilai Root Mean Square Error (RMSE) sebesar 117,266 dan Mean Absolute Percentage Error (MAPE) sebesar 2,980%. Nilai MAPE yang kurang dari 10% menunjukkan bahwa metode LSTM dan 1D CNN memiliki tingkat akurasi yang baik dalam melakukan prediksi harga saham BBCA. Penelitian selanjutnya disarankan menggunakan data yang lebih besar dan menambahkan indikator teknikal untuk meningkatkan performa prediksi.
Optimasi Feature Selection Dalam Sistem Pengenalan Emosi Wajah Menggunakan CNN dan GNN Sahbansyah Harahap; Rika Rosnelly; Bob Subhan Riza
Jurnal Minfo Polgan Vol. 15 No. 2 (2026): Artikel Penelitian
Publisher : Politeknik Ganesha Medan

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.33395/jmp.v15i2.16432

Abstract

Facial Emotion Recognition (FER) is a field of computer vision that aims to identify human emotions based on facial expressions. Convolutional Neural Networks (CNNs) are widely used for automatic visual feature extraction; however, they have limitations in modeling spatial relationships among facial components. Therefore, this study implements a Graph Neural Network (GNN) based on the Graph Attention Network (GAT) architecture and applies Principal Component Analysis (PCA) as a feature selection method to improve feature representation quality and computational efficiency. The study utilizes the FER-2013 dataset, which consists of seven emotion classes: angry, disgust, fear, happy, sad, surprise, and neutral. The research stages include data preprocessing, feature extraction using MobileNetV2, dimensionality reduction using PCA, graph construction, model training, and performance evaluation using accuracy, precision, recall, and F1-score metrics. Four experimental scenarios were evaluated: CNN, CNN+PCA, GNN, and GNN+PCA. The results show that the CNN model achieved an accuracy of 62%, CNN+PCA achieved 61.95%, GNN achieved 70.71%, and GNN+PCA achieved 74.32%. Furthermore, the GNN+PCA model obtained a precision of 75.57%, recall of 74.32%, and F1-score of 74.64%, representing the best performance among all evaluated models. The findings indicate that PCA does not significantly improve CNN performance but substantially enhances GNN performance by reducing feature redundancy and optimizing graph-based feature representation. In conclusion, the combination of GNN and PCA proved to be more effective than CNN and CNN+PCA in recognizing facial emotions on the FER-2013 dataset. Therefore, this approach has strong potential as a more accurate deep learning-based facial emotion recognition system.
Analisis Sentimen Opini Publik Terhadap Penundaan Pengangkatan CPNS 2025 Menggunakan Machine Learning Andreas Rezeki Zai; Rika Rosnelly; Wanayumini Wanayumini
Jurnal Minfo Polgan Vol. 15 No. 2 (2026): Artikel Penelitian
Publisher : Politeknik Ganesha Medan

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.33395/jmp.v15i2.16474

Abstract

Penjadwalan ulang penunjukan Calon Pegawai Negeri Sipil pada tahun 2025 telah memicu berbagai pandangan publik dan menjadi isu yang banyak diperdebatkan di media sosial X.  Penelitian ini berusaha untuk menyelidiki sentimen publik mengenai penjadwalan ulang penunjukan Calon Pegawai Negeri Sipil pada tahun 2025 dengan menggunakan metodologi Machine Learning dan menganalisis dampak optimasi Algoritma Genetik terhadap akurasi klasifikasi.  Komentar sebanyak 16.075 dikumpulkan dari media sosial X dalam rentang waktu 11 Maret 2025 hingga 1 Juni 2025.  Tahapan pra-pemrosesan mencakup pembersihan data, pengubahan huruf besar-kecil, normalisasi kata, tokenisasi, penghapusan kata-kata umum, stemming, penanganan negasi, dan penghapusan catatan duplikat.  Klasifikasi sentimen otomatis dicapai melalui strategi InSet Lexicon, yang menghasilkan tiga jenis sentimen: negatif, netral, dan positif.  Frekuensi Istilah Inverse Frekuensi Dokumen digunakan untuk ekstraksi fitur, yang kemudian diikuti dengan klasifikasi menggunakan Naive Bayes dan Support Vector Machine.  Algoritma Genetika diterapkan untuk pemilihan fitur dan penyetelan hiperparameter guna meningkatkan efektivitas model.  Analisis dilakukan melalui penggunaan akurasi, presisi, recall, F1-score, matriks kebingungan, cross-validation, Area Under Curve, dan Uji Wilcoxon Signed Rank.  Penelitian menunjukkan bahwa model Naive Bayes memperoleh akurasi sebesar 87,11 persen, sementara model yang ditingkatkan mencapai akurasi sebesar 87,61 persen.  Model Support Vector Machine mencapai akurasi sebesar 95,18 persen, sementara model yang telah disempurnakan memberikan kinerja tertinggi dengan akurasi 96,02 persen, F1-score 96,01 persen, dan Area Under Curve 99,14 persen.  Hasil dari pemeriksaan signifikansi statistik menunjukkan bahwa peningkatan kinerja setelah optimasi adalah signifikan.  Oleh karena itu, Algoritma Genetik telah membuktikan potensinya untuk meningkatkan hasil kategorisasi sentimen, dengan model Support Vector Machine yang dioptimalkan diakui sebagai model unggulan dalam analisis kami.
Performance Evaluation of K-Nearest Neighbors and Random Forest on Monkeypox Dataset Using Particle Swarm Optimization (PSO) Limar Hartimar Rambe; Rika Rosnelly; Wanayumini
Jurnal Minfo Polgan Vol. 15 No. 3 (2026): Artikel Penelitian
Publisher : Politeknik Ganesha Medan

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.33395/jmp.v15i3.16603

Abstract

This study aims to evaluate and compare the performance of the K-Nearest Neighbors (KNN) and Random Forest (RF) algorithms in classifying Monkeypox disease by applying the Particle Swarm Optimization (PSO) technique. PSO is used to obtain optimal parameters for each algorithm in order to improve the accuracy and efficiency of the classification models. The data used consist of 10,000 patient records with 11 clinical symptom features representing health conditions related to Monkeypox infection and are numerical in nature. Model performance evaluation was conducted before and after optimization using accuracy, precision, recall, F1-score, and sensitivity metrics. The results show that the application of PSO improves the performance of both algorithms compared to the non-optimized models, particularly in enhancing accuracy and balancing precision and recall. Overall, the combination of classification algorithms with the PSO optimization technique produces more optimal performance in detecting Monkeypox disease. This study is expected to contribute to the development of more accurate machine learning based classification systems and to support effective early diagnosis of Monkeypox.
Introduction to Image-Based Computer Vision Applications in Modern Medical Practice Rika Rosnelly; Bob Subhan Riza; Edy Victor Haryanto; Wahyu Saptha Negoro; Iwan Fitrianto Rahmad; Vidi Agung Fragastia; Annisa Ashari
Majalah Ilmiah UPI YPTK Vol. 33 (2026) No. 1
Publisher : Universitas Putra Indonesia YPTK Padang

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.35134/jmi.v33i1.224

Abstract

The development of Artificial Intelligence (AI)—specifically image-based computer vision—has significantly contributed to modern medical practice by enabling more accurate and efficient medical image analysis. However, understanding and practical skills regarding the implementation of computer vision within community and educational settings remain relatively limited. This community service initiative aimed to enhance participants' conceptual understanding and foundational skills in applying image-based computer vision to medical contexts through a hands-on learning approach. The program was conducted via an integrated workshop that combined theoretical instruction with practical exercises using the cloud-based platform Google Colab. Evaluation was carried out using pre- and post-tests alongside practical assessments. Results showed an increase in participants' understanding, with the average score rising from 54.2 to 82.6 (a 52.4% improvement). Notably, 85% of participants were able to execute image processing modules independently, and 88% successfully completed the practical case study. Participant satisfaction reached a score of 4.6 out of 5. This initiative contributes to improving technological literacy and bridging the gap between conceptual understanding and practical competence in the application of AI within the healthcare sector.
Co-Authors Abwabul Jinan Adil Setiawan Aditia Rangga Afandi Maulana Agung RM Alam Agus F Nduru Agus F.S. Ndruru Agus Fahmi Agus Fs Ndruru Akbar Idaman Alan Prayogi Alesia Lorenza Sinaga Alvinur Naswar Alvinur Naswar Ameliana Sihotang Andika Wiratama Andra Alfitra Andreas Jorghy Parapat Andreas Rezeki Zai Andreas Zai Andri Armaginda Siregar Annisa Ashari Anton Purnama Arselan Ashraf B. Herawan Hayadi Bambang Suhardi Batubara, Muhammad Akbarri Bill Raj Bob Subhan Riza Bob Subhan Riza Chairul Rizal Cindy Paramitha Cindy Paramitha Damri Mulia Hutabalian Daniel Ginting Dedi Irawan Dedi Irawan Della Syahrani Desi Irfan Dian Maya Sari Diky Wahyudi Diyo Mollana F Dwi Robiul R Edy Victor Haryanto Edy Victor Haryanto, Edy Victor Eko Setyo Budi Putra Aji Elly Veronika Sihite Elsa Aditya Eri Triwanda Esmawaty Sinaga Fadil Habib Fadil Habib Farhan Sardy Abdillah Finis Hermanto Laia Fragastia, Vidi Agung Gilang Harahap Gusti Firanda Hardianto Hardianto Hardianto Hardianto Hartono Hartono Hetty Zahrani Indra Kelana Jaya Iqbal Giffari Ritonga Iswanto Iwan Fitrianto Rahmad Jaka Kusuma Jaka Tirta Samudra Jalaluddin Nasution Jazmi Hadi Matondang Johan Junaidi Junaidi Karuniaman Buulolo Kiki Putri Ani Siregar Kristine Wau Lima Hartima Rambe Lima Hartimar Rambe Limar Hartimar Rambe Linda Wahyuni Linda Wahyuni Linda Wahyuni Lubis, Cindy Paramitha M Suhada WD M. Agung Oki Prayugo Maradona Jonas Simanullang MARIA BINTANG Masri Wahyuni Mega Christin Lase Mega Christin Morys Lase Mega Marisani Ziraluo Mhd Agung Irnanda Mhd Prasetyo Mimi Chintya Adelina Mira Kartiwi Mubarak - Muhammad Al Adib Muhammad Fachrurrozi Nasution Muhammad Sadikin Muhammad Suhada WD Muhammad Zulkarnain Lubis Mutiara S. Simanjuntak Nanda S Naufal Dhiya Putra Dalimunthe Negoro, Wahyu Saptha Pebruarianto Hutabarat Pius Deski Manalu Progresif Bulolo Progresif Bulolo5 Puji Sari Ramadhan Rabiatul Adawiyah Hasibuan Rahmad S Rahmat Humala Putra Hasibuan Rahmatika Hizria Rais Affaruq Zunnurain Ramadhani Ritonga Reza Ananda Putra Ricky Irnanda Ridha Maya Faza Lubis Rofiqoh Dewi Rohima, Rohima Romi Antoni Rony, Zahara Tussoleha Roslina, Roslina Rubianto Rubianto Rubianto Sahbansyah Harahap Sartika Mandasari Sarwadi Sarwadi Sarwadi, Sarwadi Satriyo W Setiawan, Adil Soeheri Soeheri Surya Tri Nowo Susiana Khosasih Syawaluddin Kadafi Parinduri Tamado Simon Sagala Teddy Gunawan Teddy Surya Gunawan Teddy Surya Gunawan Teresa Tamba Tri Andre Anu Triandi, Budi Ubaidullah Hasibuan Wahyuni, Linda Wanayumini Wanayumini Wulandari, Wulandari Yiska Dayanti Zagoto Yuke Manza Yuni Franciska Zakarias Situmorang Zuriati Janin