cover
Article Per Year (5 Year)
All
Home Page
OAI Link
Editorial Team
Contact
Reviewer
Google Scholar
Contact Name
Ellya Nurfarida
Contact Email
ellya.nurfarida@polinema.ac.id
Phone
-
Journal Mail Official
jtim@polinema.ac.id
Editorial Address
Prodi D3 Manajemen Informatika PSDKU POLINEMA KOTA KEDIRI Jalan Lingkar Maskumambang No 1 Sukorame Kecamatan Mojoroto Kota Kediri
Location
Kota malang,
Jawa timur
INDONESIA
Jurnal Informatika dan Multimedia
Published by Politeknik Negeri Malang
ISSN : 2252486X     EISSN : 25484710     DOI : https://doi.org/10.33795/jtim
Core Subject : Science,
Computer Science & IT
Game Technology, Image Processing, computer vision, Information retrieval, machine learning, biomedical engineering, computer security, Digital Forensics, Wireless Sensor, Human-Computer Interaction, dan Software Development.
Arjuna Subject : Ilmu Komputer (semua kategori) - Aplikasi Ilmu Komputer
Articles 123 Documents
 9   10   11   12   13 
Monita: Aplikasi Identifikasi Gizi Buruk Balita Berbasis Mobile Ellya Nurfarida; Fadelis Sukya; Fikha Rizky Aullia; Ratna Widyastuti
Jurnal Informatika dan Multimedia Vol. 17 No. 2 (2025): Jurnal Informatika dan Multimedia
Publisher : Politeknik Negeri Malang

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.33795/jtim.v17i2.8911

Abstract

The promotion of the one-digit stunting program is a program of the Kediri District government; this program is needed considering that cases of stunting in toddlers with malnutrition in Kediri District are still high, at around 9.8%. In contrast to cases of malnutrition in pregnant women who have had an identification and monitoring process using an android-based application from the Ministry of Health, cases of malnutrition in toddlers in the Kediri District have not been digitized and monitored correctly. Currently, the application available for the identification of under-five malnutrition is an identification application that focuses on identification only, without being able to record under-five data, so the calculation process of each measurement must always enter the under-five data first. The application for identifying and monitoring malnutrition at Puskesmas Grogol was developed mobile to facilitate cadres in recording toddler data and adding measurements, which will be called Monita. Monita is an application developed with the Flutter programming language compatible with iOS and Android-based smartphones. Monita also provides convenience to cadres because they can access it through their smartphones without using a computer. The Monita application has features for managing regions, cadres, toddler data, reports, and supplementary feeding (PMT) for toddlers with wasting cases.
Hamisfera: Sistem Rekomendasi Progresi Chord Berbasis Sentimen Lirik Melalui Studi Komparatif Arsitektur Transformer dan Mixture of Experts Fara Daud Ibra; Muhammad Fachrie
Jurnal Informatika dan Multimedia Vol. 17 No. 2 (2025): Jurnal Informatika dan Multimedia
Publisher : Politeknik Negeri Malang

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.33795/jtim.v17i2.9057

Abstract

Abstrak – Proses penciptaan lagu sering kali memerlukan penyelarasan antara nuansa emosional lirik dengan harmoni musik yang tepat. Namun, penerjemahan sentimen lirik menjadi progresi chord secara manual merupakan tantangan yang berarti. Penelitian ini bertujuan untuk mengidentifikasi arsitektur deep learning yang optimal bagi sistem Hamisfera, sebuah kerangka dua tahap yang dirancang untuk memberikan rekomendasi progresi chord yang relevan secara emosional berdasarkan lirik multibahasa. Metodologi melibatkan studi komparatif antara arsitektur Transformer dan Mixture of Experts menggunakan model pralatih XLM-R, yang dievaluasi pada dataset 73.369 entri, diperluas dari 12.000 entri data orisinal melalui augmentasi dan pembersihan. Temuan penelitian menunjukkan hasil yang berbeda per tugas, untuk klasifikasi emosi, arsitektur MoE pralatih menunjukkan keunggulan kecil dengan F1-Score sebesar 0,844. Sebaliknya, untuk generasi chord, arsitektur Transformer pralatih unggul secara keseluruhan berkat kefasihan generasi yang lebih baik, dengan BLEU-4 sebesar 0,608, serta efisiensi sumber daya yang lebih tinggi. Oleh karena itu, konfigurasi hibrida MoE untuk klasifikasi dan Transformer untuk generasi ditentukan sebagai solusi paling optimal.
Deteksi Plat Nomor Kendaraan Angkutan Bus Menggunakan YOLOv11 Benni Agung Nugroho; Toga Aldila Cinderatama; Abidatul Izzah; Ellya Nurfarida
Jurnal Informatika dan Multimedia Vol. 17 No. 2 (2025): Jurnal Informatika dan Multimedia
Publisher : Politeknik Negeri Malang

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.33795/jtim.v17i2.9204

Abstract

Penelitian ini mengatasi permasalahan pendataan plat nomor bus secara konvensional di terminal yang rentan terhadap kesalahan manusia, pelaporan yang lambat, dan kurangnya transparansi. Tujuan penelitian ini adalah merancang dan mengimplementasikan sistem deteksi dan pengenalan plat nomor angkutan bus secara otomatis menggunakan kombinasi teknologi Kecerdasan Buatan (AI), khususnya model deep learning YOLOv11, dan Internet of Things (IoT). Penelitian ini menggunakan Raspberry Pi 5 sebagai perangkat edge yang terhubung dengan webcam untuk menangkap video beresolusi 1280x720 , yang kemudian melakukan deteksi plat nomor secara real-time. Model YOLOv11 dilatih menggunakan 682 frame gambar , menunjukkan kinerja yang sangat baik pada dataset validasi dengan nilai mean Average Precision (mAP50) sebesar 0.98674. Meskipun keterbatasan Raspberry Pi 5 tanpa dedicated Neural Processing Unit (NPU) membatasi kecepatan pemrosesan real-time menjadi 10–18 FPS pada resolusi 640x480 , kecepatan ini dinilai mencukupi untuk deteksi bus di lingkungan terminal karena pergerakan kendaraan yang tidak cepat. Teks plat nomor yang berhasil dikenali dan timestamp kemudian dikirimkan ke database Firebase melalui arsitektur IoT. Sistem yang dihasilkan diharapkan dapat membantu dalam pendataan kendaraan bus di terminal dengan lebih cepat, efisien, dan akuntabel
Analisis Pengembangan Fitur pada Media Pembelajaran ILMI Menggunakan Metode UEQ: Analysis of Feature Development in ILMI Learning Media Using the UEQ Method Yohan Bakhtiar
Jurnal Informatika dan Multimedia Vol. 18 No. 1 (2026): Jurnal Informatika dan Multimedia
Publisher : Politeknik Negeri Malang

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.33795/jtim.v18i1.8745

Abstract

The Interactive Learning Media of Inventory (ILMI) is a learning platform equipped with an assistant character to support the Introduction to Accounting course. The latest development of ILMI includes additional features such as exercises and practice questions to enhance learning effectiveness. An evaluation was conducted using the User Experience Questionnaire (UEQ) method to assess the impact of these new features. The research stages consisted of literature review, instrument development, data collection, result analysis, and conclusion. The findings show that the enhanced version of ILMI achieved a score in the range of 5.6–6.1, which is higher compared to the previous version with a score of 3.8–4.2. These results indicate that the added features successfully improved both user experience and the effectiveness of the learning media.
Penerapan Algoritma Fisher-Yates Shuffle dalam Game Memory Card Sistem Periodik Unsur Kimia Berbasis Android: Implementation of the Fisher-Yates Shuffle Algorithm in an Android-Based Memory Card Game of the Periodic Table of Chemical Elements Eka Wahyu Hidayat; Firmansyah Maulana Sugiartana Nursuwars; Lita Lestari Utami; Solihin
Jurnal Informatika dan Multimedia Vol. 18 No. 1 (2026): Jurnal Informatika dan Multimedia
Publisher : Politeknik Negeri Malang

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.33795/jtim.v18i1.9064

Abstract

Educational games play an important role in supporting the learning process, including in chemistry, a subject often considered difficult by students. One of the main challenges is recognizing and remembering elements in the Periodic Table of Chemical Elements. To address this, this study developed an Android-based educational game in the form of a Memory Card game designed to help students train their memory in recognizing symbols and names of chemical elements. The development method used is the Multimedia Development Life Cycle (MDLC) which consists of six stages: concept, design, material collecting, assembly, testing, and distribution. The Fisher-Yates Shuffle algorithm is applied in the game to randomize the card positions, providing variety and a level of challenge in each game session. Testing was carried out in three stages: functionality testing using Boundary Value Analysis (BVA), visual algorithm testing through five iterations to ensure random card distribution, and usability testing using the System Usability Scale (SUS) method. The results of the functionality testing showed that all features ran according to design, the algorithm testing proved that randomization worked well without repetitive patterns, and the usability testing obtained an average score of 76.97, which is included in the good category. Based on these results, it can be concluded that the Periodic Table of Chemical Elements Memory Card game is able to be an interactive and interesting learning medium for students.
A Lightweight Drowning Person Detection Using Deep Learning Algorithm Ni Made Shavitri Mustikayani; Dayen Manoppo; Marsel Marhaen Wungow; Wahyuni Fithratul Zalmi; Muhamad Dwisnanto Putro
Jurnal Informatika dan Multimedia Vol. 18 No. 1 (2026): Jurnal Informatika dan Multimedia
Publisher : Politeknik Negeri Malang

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.33795/jtim.v18i1.9841

Abstract

Visual obstructions and fatigue often hinder human surveillance in preventing drowning incidents. Manual surveillance methods are susceptible to visual obstructions, distractions from crowds, and fatigue. To address these issues, this study proposes an automated real-time drowning detection system that utilizes state-of-the-art deep learning techniques. We use the YOLOv12-Nano architecture, selected for its balance between detection accuracy and computational efficiency. This model was trained and evaluated on the SelfMade dataset, which covers various water conditions and poses indicating swimmers in distress. In testing, YOLOv12-Nano achieved a mAP@50 of 0.984 and a mAP@50-95 of 0.732, with 2.52 million parameters and a computational requirement of 6 GFLOPs. These results demonstrate that YOLOv12-Nano-based automatic detection provides reliable, resource-efficient real-time monitoring, is suitable for implementation on real-world application, and can support human surveillance and accelerate emergency responses to reduce fatal drowning accidents.
Prediksi Keberhasilan Pengobatan dan Identifikasi Faktor Klinis Penting pada Kanker Tiroid Berdiferensiasi Menggunakan Kolmogorov-Arnold Networks dan SHAP: Prediction of Treatment Success and Identification of Important Clinical Factors in Differentiated Thyroid Cancer Using Kolmogorov-Arnold Networks and SHAP Muhammad Ainul Fikri; Ajie Kusuma Wardhana; Fauzia Anis Sekar Ningrum; Inggrid Yanuar Risca Pratiwi; Yudha Riwanto; Raditya Arief Pratama
Jurnal Informatika dan Multimedia Vol. 18 No. 1 (2026): Jurnal Informatika dan Multimedia
Publisher : Politeknik Negeri Malang

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.33795/jtim.v18i1.9909

Abstract

Kanker tiroid berdiferensiasi memerlukan evaluasi respons terapi yang akurat untuk menentukan strategi penanganan pasien tingkat lanjut. Penelitian ini bertujuan mengembangkan model prediksi keberhasilan pengobatan kanker tiroid berdiferensiasi menggunakan Kolmogorov-Arnold Networks (KAN) yang diintegrasikan dengan metode SHapley Additive exPlanations (SHAP). Integrasi ini bertujuan menghasilkan sistem prediktif yang tidak hanya akurat tetapi juga memiliki interpretabilitas intrinsik yang transparan bagi tenaga medis. Data klinis retrospektif sebanyak 383 pasien dengan 17 fitur dievaluasi menggunakan pemodelan KAN dengan optimasi pemangkasan (pruning) jaringan pembobot adaptif. Interpretasi kontribusi fitur dianalisis secara post-hoc menggunakan algoritma SHAP KernelExplainer. Hasil pengujian membuktikan bahwa model KAN mencapai performa yang sangat kompetitif dengan akurasi 97,40%, precision 97,87%, recall 97,40%, F1-score 97,47%, dan ROC-AUC 99,75%. Model ini mencatatkan tingkat sensitivitas 100% dalam memprediksi kelas keberhasilan terapi tanpa adanya kesalahan klasifikasi. Analisis SHAP mengungkap bahwa fitur Response (evaluasi respons terapi) memberikan kontribusi paling dominan terhadap hasil prediksi, diikuti oleh variabel Risk (stratifikasi risiko), Age (usia), dan M (status metastasis). Sebagai alat pendukung keputusan klinis, KAN secara efektif menyeleksi fitur otomatis melalui mekanisme sparsity pada spline-nya dan memberikan penjelasan yang komprehensif bersama metode SHAP. Sebagai saran pengembangan ke depan, penelitian selanjutnya dapat memperdalam analisis korelasi matematis antara representasi spline KAN dengan nilai distribusi SHAP, serta memperluas pengujian model menggunakan dataset multisenter dengan skala yang lebih besar.
Klasifikasi Gaya Belajar VARK Siswa Sekolah Dasar Menggunakan K-Nearest Neighbor dan Naive Bayes Berbasis Kuesioner: Classification of VARK Learning Styles of Elementary School Students Using K-Nearest Neighbor and Questionnaire-Based Naive Bayes Deden Adi Mardian Lesmana; Fathoni Mahardika; Dani Indra Junaedi
Jurnal Informatika dan Multimedia Vol. 18 No. 1 (2026): Jurnal Informatika dan Multimedia
Publisher : Politeknik Negeri Malang

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.33795/jtim.v18i1.9441

Abstract

Gaya belajar memiliki peranan penting dalam menentukan bagaimana siswa memahami informasi, khususnya pada jenjang sekolah dasar yang berada pada tahap perkembangan berpikir konkret. Penelitian ini bertujuan memetakan preferensi belajar siswa menggunakan model VARK (Visual, Aural, Read/Write, Kinesthetic) serta membangun model klasifikasi berbasis algoritma K-Nearest Neighbor (KNN). Sebanyak 40 siswa kelas IV–VI berpartisipasi dengan mengisi 16 item kuesioner VARK. Data diolah melalui proses pembersihan, normalisasi Min–Max, dan pembentukan fitur empat dimensi. Model KNN diuji menggunakan variasi nilai k melalui Stratified 5-Fold Cross Validation. Hasil penelitian menunjukkan bahwa kategori Kinesthetic dan Visual merupakan preferensi belajar yang paling dominan di SDN Cipatat. Model KNN memberikan performa terbaik pada k = 5, dengan akurasi rata-rata 82%, precision 0,81, recall 0,80, dan F1-score 0,79. Analisis confusion matrix memperlihatkan bahwa kategori Kinesthetic dan Visual lebih mudah diprediksi, sementara Aural dan Read/Write memiliki tumpang tindih fitur yang lebih besar. Temuan ini menunjukkan bahwa pendekatan berbasis data dapat memberikan gambaran objektif mengenai preferensi belajar siswa serta mendukung strategi pembelajaran yang lebih adaptif.
Optimasi Rute Pengisian Daya Kendaraan Listrik SPKLU Jakarta Pusat Menggunakan Dynamic Programming: Optimizing Electric Vehicle Charging Routes at Central Jakarta's SPKLU Using Dynamic Programming Femmy Johan; Jennifer Verty; Yohannes Yohannes
Jurnal Informatika dan Multimedia Vol. 18 No. 1 (2026): Jurnal Informatika dan Multimedia
Publisher : Politeknik Negeri Malang

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.33795/jtim.v18i1.10019

Abstract

The development of electric vehicles in Indonesia has increased the need for Public Electric Vehicle Charging Stations (SPKLU). Electric vehicle users often experience difficulties in determining the closest SPKLU location and in accordance with the current vehicle position. This study aims to create an optimization program for determining electric vehicle charging routes at SPKLU in the Central Jakarta area using the Dynamic Programming algorithm. Research data was obtained from Google Maps, including the SPKLU name, latitude, longitude, wattage, charger type, and address. Distance calculations were carried out using the Geodesic Distance method based on the coordinates of the vehicle and SPKLU locations. Next, reachable SPKLUs were evaluated using a cost function that combines travel distance and estimated charging time. The Dynamic Programming algorithm was used to determine the minimum cost value as the optimal solution, then the program generated a ranking of the best SPKLU recommendations. The study was built using the Python programming language and displayed visualizations of locations and routes to SPKLUs on a digital map using Folium. The results showed that the program was able to provide optimal SPKLU recommendations based on a combination of distance and charging time, thus helping electric vehicle users determine charging locations more effectively and efficiently.
React-Based Static Website Development for Decision Support System Using ROC and SAW: A Case Study on Hedonic Preferences of Chicken Meatballs Borneo Satria Pratama; Donor Utomo Muhammad Susilo; Sariati; Nayla Fadillah; Dodi Mahendra; Jimmy Angkasa; Elisabeth Erinawati; Penansius Delon; Fransiskus Kurnia Sandi
Jurnal Informatika dan Multimedia Vol. 18 No. 1 (2026): Jurnal Informatika dan Multimedia
Publisher : Politeknik Negeri Malang

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.33795/jtim.v18i1.9985

Abstract

This study presents the development of Qbico (Q-毘古), a React-based static website decision support system (DSS) integrating the Rank Order Centroid (ROC) method for attribute weighting and the Simple Additive Weighting (SAW) method for alternative ranking. Unlike previous web-based DSS implementations that rely on server-side architectures, Qbico operates entirely on the client-side via React CDN, making it lightweight and freely deployable via GitHub Pages without a dedicated server. The system was evaluated using a case study involving hedonic preference data from four chicken meatball formulations assessed by 18 trained panelists across three attributes: taste, texture, and saltiness level. One-Way ANOVA confirmed statistically significant differences among formulations for all three attributes (p ≤ 0.05). ROC weighting based on expert-determined priority order of taste > texture > saltiness level yielded weights of 0.611, 0.278, and 0.111, respectively. SAW computation produced a final ranking of YA > YB > XA > XB, with formulation YA identified as the best alternative, consistent with manual calculations in Microsoft Excel. Black-box testing across 17 test cases confirmed full functional correctness, and System Usability Scale (SUS) evaluation from 18 respondents yielded an average score of 90.4, corresponding to grade A+ "Best Imaginable," demonstrating excellent usability and user acceptance. Future development may extend Qbico to support additional MADM methods and incorporate data export functionality to broaden its applicability in agroindustrial decision-making.

Page 12 of 13 | Total Record : 123

 9   10   11   12   13 

Filter by Year

2010 2026


Reset
Filter By Issues
All Issue Vol. 18 No. 1 (2026): Jurnal Informatika dan Multimedia Vol. 17 No. 2 (2025): Jurnal Informatika dan Multimedia Vol. 17 No. 1 (2025): Jurnal Informatika dan Multimedia Vol. 16 No. 2 (2024): Jurnal Informatika dan Multimedia Vol. 16 No. 1 (2024): Jurnal Informatika dan Multimedia Vol. 15 No. 2 (2023): Jurnal Informatika dan Multimedia Vol. 15 No. 1 (2023): Jurnal Informatika dan Multimedia Vol. 14 No. 2 (2022): Jurnal Informatika dan Multimedia Vol. 14 No. 1 (2022): Jurnal Informatika dan Multimedia Vol. 10 No. 2 (2018): Jurnal Informatika dan Multimedia Vol. 10 No. 1 (2018): Jurnal Informatika dan Multimedia Vol. 9 No. 2 (2017): Jurnal Informatika dan Multimedia Vol. 9 No. 1 (2017): Jurnal Informatika dan Multimedia Vol. 8 No. 2 (2016): Jurnal Informatika dan Multimedia Vol. 8 No. 1 (2016): Jurnal Informatika dan Multimedia Vol. 7 No. 1 (2015): Jurnal Informatika dan Multimedia Vol. 6 No. 1 (2014): Jurnal Informatika dan Multimedia Vol. 5 No. 1 (2013): Jurnal Informatika dan Multimedia Vol. 4 No. 1 (2012): Jurnal Informatika dan Multimedia Vol. 3 No. 1 (2011): Jurnal Informatika dan Multimedia Vol. 2 No. 1 (2010): Jurnal Informatika dan Multimedia More Issue