cover
Article Per Year (5 Year)
All
Home Page
OAI Link
Editorial Team
Contact
Reviewer
Google Scholar
Contact Name
Fido Rizki
Contact Email
fidorizki@gmail.com
Phone
+6282179654408
Journal Mail Official
-
Editorial Address
Jalan Jendral Besar H.M Soeharto Kelurahan Lubuk Kupang Kecamatan Lubuklinggau Barat I Kota Lubuklinggau Provinsi Sumatera Selatan
Location
Kota lubuk linggau,
Sumatera selatan
INDONESIA
JUTIM (Jurnal Teknik Informatika Musirawas)
Published by Universitas Bina Insan Lubuklinggau
ISSN : 25411888     EISSN : 26145782     DOI : https://doi.org/10.32767/jutim
Core Subject : Science, Education, Engineering,
Computer Science & IT Control & Systems Engineering Engineering Other
Jurnal Teknik Informatika Musirawas merupakan Jurnal ilmiah yang meliputi kompetensi Human Computer Interaction, IT Governance, Networking Technology, New Media Technology, Information Search Engine, Multimedia, Information Retrieval, Intelligent System, Distributed Computing System, Mobile Processing, Computer Network Security, Natural Language Processing, Software Engineering, Programming Methodology and Paradigm, Data Engineering, Information Management, Knowledge Based Management System, Game Technology Jurnal Teknik Informatika Musirawas terbit sebanyak dua kali dalam satu tahun, pada bulan Juni dan Desember.
Arjuna Subject : Ilmu Komputer (semua kategori) - Ilmu Komputer (Lain-Lain)
Articles 264 Documents
 23   24   25   26   27 
ANALISIS FAKTOR YANG MEMPENGARUHI PREDIKSI HARGA BITCOIN DAN ETHEREUM MENGGUNAKAN EXPLAINABLE AI (SHAP) DAN ALGORITMA MACHINE LEARNING Kevin Grado Agusto; Raymond Maulany
JUTIM (Jurnal Teknik Informatika Musirawas) Vol. 11 No. 1 (2026): JUTIM (Jurnal Teknik Informatika Musirawas) Maret
Publisher : LPPM UNIVERSITAS BINA INSAN

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.32767/jutim.v11i1.2955

Abstract

The high volatility of cryptocurrency assets such as Bitcoin and Ethereum poses significant challenges for producing accurate and transparent price predictions. This instability is driven by factors including trading volume, market sentiment, and global economic conditions, requiring predictive models that not only forecast price movements but also explain the contribution of each variable. This study analyzes the factors influencing Bitcoin and Ethereum price prediction using a Long Short-Term Memory (LSTM) model integrated with Explainable Artificial Intelligence (XAI) through SHAP (SHapley Additive exPlanations). The dataset was obtained from Yahoo Finance covering January 2022–December 2024. Model evaluation using MAE, MSE, RMSE, and the coefficient of determination (R²) indicates that the model captures the main price movement trends, although it shows limitations in representing extreme short-term fluctuations due to the high volatility of cryptocurrency markets. Autocorrelation Function (ACF) analysis of residuals suggests that the primary temporal patterns have been effectively learned by the model. SHAP analysis identifies Low, High, and short-term Moving Average (MA7) as the most influential features. Overall, the integration of LSTM and XAI enables interpretable cryptocurrency price prediction, supporting a more transparent and data-driven understanding of market dynamics and investment decision-making.
IMPLEMENTASI GOOGLE APPS UNTUK PENGELOLAAN LABORATORIUM PERIKANAN Jemi Ferizal; Wahyu Adi; iski zaliman; Siti Aisyah
JUTIM (Jurnal Teknik Informatika Musirawas) Vol. 11 No. 2 (2026): JUTIM (Jurnal Teknik Informatika Musirawas) Juni
Publisher : LPPM UNIVERSITAS BINA INSAN

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.32767/jutim.v11i2.2828

Abstract

Manual laboratory management practices commonly found in many educational institutions often create various challenges, such as data duplication, delays in information delivery, recording errors, and ineffective coordination across service units. These issues not only hinder operational efficiency but also reduce service quality, decision-making accuracy, and the laboratory’s ability to respond promptly and appropriately to academic demands. This study designed and implemented a management system for the Marine Fisheries and Hatchery Laboratory based on Google Workspace Tools, including Google Forms, Google Spreadsheets, AppSheet, and Google Sites. The integration of these tools aims to improve work efficiency, information accuracy, and the speed of administrative and laboratory service processes. The study employed the Rapid Application Development (RAD) method, consisting of requirement analysis, system design using UML, prototype development, implementation, and user evaluation. Data were collected through interviews, direct observations, document reviews, and Likert-scale questionnaires. The analysis shows that all evaluation indicators fall within the range of 85–90%, with average scores of 4.26 for effectiveness, 4.23 for efficiency, and 4.36 for user satisfaction, all categorized as very high. The system proved capable of enhancing information accuracy, accelerating service workflows, increasing process transparency, and improving internal coordination. The Rapid Application Development (RAD) method used in this study was found to be more effective than conventional approaches such as Waterfall and Agile, as it enables rapid, iterative, and user-oriented system development. This model is highly suitable for replication as a cloud-based laboratory management solution that is efficient, adaptive, and user-centric.
PENGEMBANGAN SISTEM Q&A CERDAS BERBASIS RETRIEVAL-AUGMENTED GENERATION (RAG) DAN LARGE LANGUAGE MODEL (LLM) UNTUK PELAYANAN PUBLIK PADA BPS KABUPATEN EMPAT LAWANG Prabu Jaya Wijaya; M Nur Alamsyah; Antoni Zulius
JUTIM (Jurnal Teknik Informatika Musirawas) Vol. 11 No. 1 (2026): JUTIM (Jurnal Teknik Informatika Musirawas) Maret
Publisher : LPPM UNIVERSITAS BINA INSAN

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.32767/jutim.v11i1.2932

Abstract

This study proposes the development of an intelligent Question and Answering (Q&A) system based on Retrieval-Augmented Generation (RAG) and Large Language Models (LLM) to support public statistical services at the Central Bureau of Statistics (BPS) of Empat Lawang Regency. Conventional public information services still rely heavily on manual interactions, which often result in delayed responses, high workload for officers, and inconsistent information delivery. Large Language Models have demonstrated strong natural language understanding capabilities; however, they suffer from hallucination issues when not grounded in authoritative data sources. To address this limitation, the RAG approach is employed by integrating document retrieval mechanisms with generative language models, ensuring that responses are generated based on official statistical documents. This research adopts the CRISP-DM framework as the system development methodology, with evaluation conducted using confusion matrix metrics, including accuracy, precision, recall, and F1-score. The results show that the proposed system is able to deliver accurate, relevant, and context-aware answers to public statistical queries, thereby improving efficiency, accessibility, and reliability of digital public services.  
KLASIFIKASI JENIS JAMUR BERDASARKAN CITRA DIGITAL MENGGUNAKAN METODE HYBRID FUSION DEEP LEARNING Dilla Monalisa; Rudi Kurniawan; Budi Santoso
JUTIM (Jurnal Teknik Informatika Musirawas) Vol. 11 No. 2 (2026): JUTIM (Jurnal Teknik Informatika Musirawas) Juni
Publisher : LPPM UNIVERSITAS BINA INSAN

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.32767/jutim.v11i2.2954

Abstract

Mushroom species identification based on digital images remains challenging due to high visual similarity among species and the limitations of manual identification. This study proposes a Hybrid Fusion Deep Learning classification system that integrates two Convolutional Neural Network (CNN) architectures, DenseNet201 and MobileNetV3Large, as feature extractors through feature-level fusion. The novelty of this research lies in the complementary integration of two CNN architectures not previously combined for mushroom classification, further coupled with Random Forest as the final classifier to improve stability and generalization. The dataset comprises 2,573 images of five mushroom classes from Kaggle, split at 70:15:15 (training: 1,801; validation: 386; testing: 386 images). Preprocessing includes resizing to 224×224 pixels, pixel normalization, and data augmentation. Evaluation was conducted using stratified 5-fold cross-validation, with accuracy, precision, recall, F1-score, and AUC metrics. The proposed model achieves a validation accuracy of 95.53%, with micro-average AUC = 0.9961 and macro-average AUC = 0.9951. Compared to single-model baselines (DenseNet201: 91.45%; MobileNetV3Large: 89.73%), the proposed method demonstrates significant improvement. These findings confirm that the hybrid fusion approach effectively enhances mushroom image classification and has strong potential for computer vision-based biological identification in food safety and biodiversity conservation.
PENGEMBANGAN CHATBOT INFORMASI HUKUM BERBASIS RETRIEVAL AUGMENTED GENERATION: STUDI KASUS KUHP 2023 Yuda Putra Pratama; Rudi Kurniawan; Budi Santoso
JUTIM (Jurnal Teknik Informatika Musirawas) Vol. 11 No. 1 (2026): JUTIM (Jurnal Teknik Informatika Musirawas) Maret
Publisher : LPPM UNIVERSITAS BINA INSAN

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.32767/jutim.v11i1.2959

Abstract

Pemberlakuan KUHP 2023 sebagai sistem hukum pidana baru di Indonesia memerlukan mekanisme penyaluran informasi hukum yang cepat dan akurat. Namun kompleksitas regulasi dan keterbatasan akses informasi menjadi kendala utama bagi masyarakat di dalam memahami sistem hukum baru yang berlaku. Penelitian ini mengembangkan chatbot berbasis RetrievalAugmented Generation (RAG) untuk mengoptimalkan Large Language Model dengan menyediakan konteks informasi hukum pidana dari KUHP 2023. Sistem RAG dibangun melalui tahapan parsing dokumen, chunking per-pasal, indexing, embedding menggunakan Qwen3Embedding, penyimpanan vektor ke ChromaDB, dan retrieval konteks relevan. Model LLM Qwen2.5 melalui Ollama menghasilkan respons akurat berdasarkan konteks yang diperoleh. Chatbot diintegrasikan ke Telegram untuk kemudahan akses. Evaluasi menggunakan RAGAs menunjukkan nilai faithfulness 0.825 dan context precision 0.947, mengindikasikan kemampuan sistem memberikan respons akurat dan relevan. Pengujian Black Box Testing memvalidasi seluruh fungsi chatbot berjalan optimal. Secara keseluruhan sistem terbukti dapat diandalkan untuk menyalurkan informasi hukum pidana KUHP 2023.
KLASIFIKASI CITRA MAKANAN INDONESIA DAN ESTIMASI KALORI MENGGUNAKAN MOBILENETV2 DENGAN INTEGRASI KE PLATFORM WEB Yudi Putra Pratama; Sri Tita Faulina; Fido Rizki
JUTIM (Jurnal Teknik Informatika Musirawas) Vol. 11 No. 1 (2026): JUTIM (Jurnal Teknik Informatika Musirawas) Maret
Publisher : LPPM UNIVERSITAS BINA INSAN

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.32767/jutim.v11i1.2972

Abstract

Pengelolaan asupan kalori harian masih menjadi tantangan bagi masyarakat karena keterbatasan pengetahuan nutrisi serta kompleksitas visual makanan Indonesia yang beragam, sehingga estimasi kalori sering dilakukan secara subjektif dan kurang akurat. Penelitian ini bertujuan untuk mengembangkan sistem otomatis yang mampu mengklasifikasikan citra makanan Indonesia dan mengestimasi nilai kalorinya secara akurat dengan memanfaatkan pendekatan deep learning berbasis arsitektur MobileNetV2. Metode yang digunakan meliputi transfer learning dari model pra-latih ImageNet dan fine-tuning terkontrol pada lapisan atas jaringan untuk meningkatkan performa dan stabilitas model. Dataset yang digunakan terdiri dari 18 kelas makanan Indonesia dengan total 25.536 citra untuk data latih dan validasi, serta 450 citra data uji. Evaluasi model dilakukan menggunakan metrik akurasi, presisi, recall, F1-score, dan confusion matrix. Hasil eksperimen menunjukkan bahwa konfigurasi fine-tuning terkontrol pada MobileNetV2 mampu mencapai akurasi pengujian tertinggi sebesar 93,33%, dengan performa yang stabil dan kemampuan generalisasi yang baik pada seluruh kelas makanan. Model selanjutnya diintegrasikan ke dalam aplikasi web berbasis Streamlit, di mana hasil klasifikasi makanan dipetakan ke basis data nutrisi FatSecret untuk menghasilkan estimasi kalori per 100 gram. Implementasi ini menunjukkan bahwa MobileNetV2 merupakan model ringan yang efektif untuk klasifikasi citra makanan dan estimasi kalori berbasis web yang mudah diakses.
PENERAPAN K-MEANS CLUSTERING UNTUK IDENTIFIKASI LOKASI STRATEGIS BISNIS FOOD AND BEVERAGE DI KOTA LUBUKLINGGAU M. Rizky Pratama Putra; Novi Lestari; Davit Irawan
JUTIM (Jurnal Teknik Informatika Musirawas) Vol. 11 No. 2 (2026): JUTIM (Jurnal Teknik Informatika Musirawas) Juni
Publisher : LPPM UNIVERSITAS BINA INSAN

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

Abstract

Perkembangan usaha bisnis food and beverage (F&B) di Kota Lubuklinggau menuntut penentuan lokasi usaha yang strategis dan berbasis data. Penelitian ini bertujuan untuk mengidentifikasi pola persebaran lokasi usaha F&B menggunakan pendekatan analisis spasial berbasis algoritma K-Means Clustering. Data diperoleh dari Google Maps melalui teknik web scraping menggunakan framework Playwright berbasis Node.js dengan jumlah awal 4.350 data lokasi usaha. Data kemudian diproses menggunakan tahapan Knowledge Discovery in Databases (KDD) yang meliputi Exploratory Data Analysis (EDA), preprocessing, transformasi data, dan pemodelan clustering hingga diperoleh 1.602 data bersih. Penentuan jumlah klaster optimal dilakukan menggunakan Elbow Method dan dievaluasi menggunakan Silhouette Score. Hasil penelitian menunjukkan bahwa jumlah klaster optimal adalah dua klaster dengan nilai Silhouette Score sebesar 0,5653 yang mengindikasikan kualitas klaster cukup baik. Klaster pertama memiliki kepadatan usaha tinggi dan berada dekat pusat Kota Lubuklinggau sehingga diinterpretasikan sebagai kawasan paling strategis, sedangkan klaster kedua memiliki kepadatan lebih rendah dan berpotensi dikembangkan dengan tingkat persaingan yang lebih kecil.
KLASIFIKASI SUARA BURUNG LOKAL INDONESIA MENGGUNAKAN PEMBELAJARAN MESIN Prety Sugiharta Suwita; Tri Hasanah Bimastari Aviani; Harma Oktafia Lingga Wijaya
JUTIM (Jurnal Teknik Informatika Musirawas) Vol. 11 No. 1 (2026): JUTIM (Jurnal Teknik Informatika Musirawas) Maret
Publisher : LPPM UNIVERSITAS BINA INSAN

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

Abstract

Identifikasi spesies burung lewat sinyal bioakustik sangat penting untuk pemantauan biodiversitas, tetapi sering terkendala oleh subjektivitas pengamatan manual dan kesamaan pola kicauan antarspesies. Penelitian ini bertujuan untuk mengembangkan model klasifikasi otomatis dengan memanfaatkan algoritma Support Vector Machine (SVM). Metode diterapkan melalui tahap pra-pemrosesan sinyal berupa normalisasi amplitudo dan penghapusan hening, serta augmentasi data yang intensif. Ekstraksi fitur Mel-Frequency Cepstral Coefficients (MFCC) digunakan untuk menggambarkan karakteristik spektral suara dalam bentuk data numerik. Evaluasi terakhir pada data uji menunjukkan akurasi keseluruhan mencapai 80,95%, dengan presisi sempurna 100% tercatat pada kelas Nuri Tanau. Kekuatan implementasi didukung oleh pengujian inferensi tunggal yang menghasilkan identifikasi akurat dengan tingkat kepercayaan (confidence score) 87,98%. Penemuan ini menegaskan bahwa walaupun ada tantangan pada spesies yang berkerabat dekat, sistem dapat mengklasifikasikan sinyal bioakustik secara efisien sebagai suatu solusi teknologi untuk konservasi.
HYBRID ARTIFICIAL NEURAL NETWORK DAN RULE-BASED UNTUK EARLY WARNING SYSTEM STATUS GIZI BALITA BERBASIS DATA ANTROPOMETRI Muhammad Firza Fernanda; Wahyuni Wahyuni; Pitrasacha Adytia
JUTIM (Jurnal Teknik Informatika Musirawas) Vol. 11 No. 2 (2026): JUTIM (Jurnal Teknik Informatika Musirawas) Juni
Publisher : LPPM UNIVERSITAS BINA INSAN

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.32767/jutim.v11i2.3017

Abstract

Nutritional status of toddlers is a critical indicator of early childhood growth and health; however, manual identification methods remain prone to inconsistency and delayed decision-making, particularly when applied to large-scale data. The absence of a Hybrid system integrating Machine Learning and Rule-based approaches for an Early Warning System (EWS) of toddler nutritional status represents a research gap that needs to be addressed. This study implements an Artificial Neural Network (ANN) using the Multilayer Perceptron (MLPClassifier) algorithm on a synthetic dataset generated from the WHO child growth Z-score formula, with class distributions of Normal (54.57%), Tall (17.69%), Severely Stunted (16.54%), and Stunted (11.20%). Stepwise experiments were conducted on hidden layer configurations, activation functions, and solvers to determine the optimal model. The best configuration was achieved using hidden layers (64,32), ReLU activation, and LBFGS solver, yielding an accuracy of 0.9954 and a Macro F1-Score of 0.9935. Validation through 5-fold cross-validation produced a mean accuracy of 0.9955 with a standard deviation of 0.0005, confirming model stability and absence of overfitting. The model was integrated into a Rule-based EWS to provide early risk-level classification of toddler growth status. This Hybrid ANN and Rule-based combination proves effective as a decision support system in child healthcare.
SISTEM PENYIRAMAN TANAMAN MENGGUNAKAN ALGORITMA FUZZY LOGIC BERBASIS INTERNET OF THINGS DENGAN ENERGI SURYA Mohammad Fajar Maulidi; Tanhella Zein Vitadiar
JUTIM (Jurnal Teknik Informatika Musirawas) Vol. 11 No. 1 (2026): JUTIM (Jurnal Teknik Informatika Musirawas) Maret
Publisher : LPPM UNIVERSITAS BINA INSAN

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.32767/jutim.v11i1.3030

Abstract

Irregular watering of plants often leads to water waste and reduced plant growth quality. This study developed an IoT-based automatic watering system using a Fuzzy Logic algorithm powered by solar energy and equipped with a buzzer as a warning for critical conditions. A soil moisture sensor is used to read soil moisture, while a DHT11 sensor monitors environmental temperature. Sensor data is processed by an ESP32 microcontroller to determine automatic watering decisions, and the results are displayed through the Blynk application so users can monitor the system in real-time. Tests on corn plants showed that the system is able to turn on the water pump only when needed and save water usage compared to manual watering. The addition of a buzzer effectively provides notification when humidity is very dry. This system is proven to be efficient, energy independent, and supports the concept of smart and sustainable agriculture.

Page 25 of 27 | Total Record : 264

 23   24   25   26   27 

Filter by Year

2016 2026


Reset
Filter By Issues
All Issue Vol. 11 No. 2 (2026): JUTIM (Jurnal Teknik Informatika Musirawas) Juni Vol. 11 No. 1 (2026): JUTIM (Jurnal Teknik Informatika Musirawas) Maret Vol. 10 No. 2 (2025): JUTIM (JURNAL TEKNIK INFORMATIKA MUSIRAWAS) DESEMBER Vol 10 No 1 (2025): JUTIM (Jurnal Teknik Informatika Musirawas) JUNI Vol 9 No 2 (2024): JUTIM (Jurnal Teknik Informatika Musirawas) DESEMBER Vol 9 No 1 (2024): JUTIM (Jurnal Teknik Informatika Musirawas) JUNI Vol 8 No 2 (2023): JUTIM (Jurnal Teknik Informatika Musirawas) DESEMBER Vol 8 No 1 (2023): JUTIM (Jurnal Teknik Informatika Musirawas) JUNI Vol 7 No 2 (2022): JUTIM (Jurnal Teknik Informatika Musirawas) DESEMBER Vol 7 No 1 (2022): JUTIM (Jurnal Teknik Informatika Musirawas) JUNI Vol 6 No 2 (2021): JUTIM (Jurnal Teknik Informatika Musirawas) DESEMBER Vol 6 No 1 (2021): JUTIM (Jurnal Teknik Informatika Musirawas) JUNI Vol 5 No 2 (2020): JUTIM (Jurnal Teknik Informatika Musirawas) DESEMBER Vol 5 No 1 (2020): JUTIM (Jurnal Teknik Informatika Musirawas) JUNI Vol 4 No 2 (2019): JUTIM (Jurnal Teknik Informatika Musirawas) DESEMBER Vol 4 No 1 (2019): JUTIM (Jurnal Teknik Informatika Musirawas) JUNI Vol 4 No 1 (2019): JUTIM (JURNAL TEKNIK INFORMATIKA MUSIRAWAS) JUNI Vol 3 No 2 (2018): JUTIM (Jurnal Teknik Informatika Musirawas) DESEMBER Vol 3 No 2 (2018): JUTIM (JURNAL TEKNIK INFORMATIKA MUSIRAWAS) DESEMBER Vol 3 No 1 (2018): JUTIM (Jurnal Teknik Informatika Musirawas) JUNI Vol 3 No 1 (2018): JUTIM (JURNAL TEKNIK INFORMATIKA MUSIRAWAS) JUNI Vol 3, No 1 (2018): JURNAL TEKNIK INFORMATIKA MUSIRAWAS (JUTIM) JUNI Vol 2 No 2 (2017): JUTIM (Jurnal Teknik Informatika Musirawas) DESEMBER Vol 2, No 2 (2017): JURNAL TEKNIK INFORMATIKA MUSIRAWAS (JUTIM) DESEMBER Vol 2 No 2 (2017): JUTIM (JURNAL TEKNIK INFORMATIKA MUSIRAWAS) DESEMBER Vol 2 No 1 (2017): JUTIM (JURNAL TEKNIK INFORMATIKA MUSIRAWAS) JUNI Vol 2 No 1 (2017): JUTIM (JURNAL TEKNIK INFORMATIKA MUSIRAWAS) JUNI Vol 2, No 1 (2017): Jurnal Teknik Informatika MUSIRAWAS (JUTIM) Juni Vol 1, No 1 (2016): Jurnal Teknik Informatika MUSIRAWAS (JUTIM) Desember Vol 1 No 1 (2016): JUTIM (JURNAL TEKNIK INFORMATIKA MUSIRAWAS) DESEMBER Vol 1 No 1 (2016): JUTIM (JURNAL TEKNIK INFORMATIKA MUSIRAWAS) DESEMBER More Issue