cover
Article Per Year (5 Year)
All
Home Page
OAI Link
Editorial Team
Contact
Reviewer
Google Scholar
Contact Name
Muhammad Rifai Katili
Contact Email
mrifaikatili@ung.ac.id
Phone
-
Journal Mail Official
syafri.tuloli@ung.ac.id
Editorial Address
-
Location
Kota gorontalo,
Gorontalo
INDONESIA
Jambura Journal of Informatics
Published by Universitas Negeri Gorontalo
ISSN : 2656467X     EISSN : 26854244     DOI : 10.37905/jji
Core Subject : Science,
Computer Science & IT
Jambura Journal of Informatics (JJi) is a peer-reviewed open access journal published by Department of Informatics Engineering, Faculty of Engineering, Universitas Negeri Gorontalo (UNG), Indonesia. The journal is an archival journal serving the scientist and engineer involved in all aspects of computer science, information technology, information systems, software engineering and education of information technology. JJI publishes original research findings and high quality scientific articles that present cutting-edge approaches including methods, techniques, tools, implementations and applications.
Arjuna Subject : -
Articles 7 Documents
 1 
Search results for , issue "VOL 8, N0 1: APRIL 2026" : 7 Documents clear
Perbandingan SVM dan CNN MobileNetV2 untuk Klasifikasi Residu Insektisida pada Citra Buah Kakao Rahmawati, Rahmawati; Arifin, Nurhikma; Firgiawan, Wawan
Jambura Journal of Informatics VOL 8, N0 1: APRIL 2026
Publisher : Universitas Negeri Gorontalo

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.37905/jji.v8i1.37972

Abstract

The decline in cocoa production in West Sulawesi due to pest attacks and the use of insecticides that leave residues on the fruit surface has reduced visual quality and highlights the need for efficient automatic classification based on digital image processing. This study aims to classify cocoa fruit images into three classes (Normal, Insecticide-Treated, and Residue) and to compare the performance of Support Vector Machine (SVM) and Convolutional Neural Network (CNN) with the MobileNetV2 architecture. The dataset consists of 672 images divided into training and testing sets with an 80:20 ratio and evaluated under two training data conditions: imbalanced and balanced through rotation-based augmentation at an image size of 224×224 pixels. For SVM, color and texture features are extracted using Hue Saturation Value (HSV) and Local Binary Pattern (LBP), while the CNN model adopts MobileNetV2 with transfer learning and an adjusted fully connected layer. The results show that SVM with combined HSV and LBP features achieves an accuracy of 86.67%, whereas CNN attains 82.22% on data without augmentation and improves to 87.41% on augmented data. The McNemar test on the same test set yields p-values of 0.6171 and 1.0000 for the imbalanced and balanced training data conditions, indicating that the performance difference between the two methods is not statistically significant and that both models provide comparable classification capability.Penurunan produksi kakao di Sulawesi Barat akibat serangan hama dan penggunaan insektisida yang meninggalkan residu pada permukaan buah menurunkan kualitas visual dan menunjukkan perlunya metode klasifikasi otomatis berbasis pengolahan citra digital yang efisien. Penelitian ini bertujuan mengklasifikasikan citra buah kakao ke dalam tiga kelas (Normal, Berinsektisida, dan Residu) serta membandingkan kinerja Support Vector Machine (SVM) dan Convolutional Neural Network (CNN) dengan arsitektur MobileNetV2. Dataset terdiri atas 672 citra yang dibagi menjadi data latih dan data uji dengan rasio 80:20 dan dievaluasi pada dua kondisi data latih, yaitu tidak seimbang dan seimbang melalui augmentasi rotasi dengan ukuran citra 224×224 piksel. Pada SVM, fitur warna dan tekstur diekstraksi menggunakan Hue Saturation Value (HSV) dan Local Binary Pattern (LBP), sedangkan CNN menggunakan MobileNetV2 dengan pendekatan transfer learning dan penyesuaian fully connected layer. Hasil pengujian menunjukkan bahwa SVM dengan kombinasi fitur HSV dan LBP mencapai akurasi 86,67%, sedangkan CNN memperoleh akurasi 82,22% pada data tanpa augmentasi dan meningkat menjadi 87,41% pada data setelah augmentasi. Uji McNemar pada data uji yang sama menghasilkan nilai p-value 0,6171 dan 1,0000 untuk kondisi data latih tidak seimbang dan seimbang, yang menunjukkan bahwa perbedaan performa kedua metode tidak signifikan secara statistik sehingga keduanya memiliki kemampuan klasifikasi yang relatif sebanding.
Identification of Factors and Models of Knowledge Management Maturity: A Systematic Literature Review Abilowo, Krisanto; Sensuse, Dana Indra
Jambura Journal of Informatics VOL 8, N0 1: APRIL 2026
Publisher : Universitas Negeri Gorontalo

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.37905/jji.v8i1.37862

Abstract

Studies related to the knowledge management maturity (KMM) model in libraries have been successfully identified. However, the model is at risk of bias because, in these studies, the KMM assessment within the organization is based on the total score across all criteria/components/factors. This poses a risk of bias if one of the criteria required at the initial maturity level is not met. Therefore, this study aims to identify KMM factors and models from various sectors to support research on developing a KMM model in the library sector. In identifying KMM factors and models, the researchers will conduct a Systematic Literature Review (SLR). The method used in this SLR is the Kitchenham method. Of the 103 KMM factors, the most widely used in previous studies were in the process category, including organizational culture. Based on the factors that make up the KMM model, it can be seen that, among the 17 KMMs, those used in previous studies had the greatest advantages in the process category, such as the army KM3. In addition, based on the objectives of the KMM model, one model that assesses the maturity level of Knowledge Management (KM) implementation and serves as a guideline for KM implementation is the General KM Maturity Model (GKMMM). Based on the issues and results of the SLR conducted, the researchers plan to develop a knowledge management maturity model for the library sector in the next study.
Integrasi Best Worst Method dan MOORA dalam Sistem Pendukung Keputusan Orientasi Karir Siswa SMK Suma, Nur Alim M.; Hadjaratie, Lillyan; Pakaya, Nikmasari; Padiku, Indhitya R.
Jambura Journal of Informatics VOL 8, N0 1: APRIL 2026
Publisher : Universitas Negeri Gorontalo

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.37905/jji.v8i1.38415

Abstract

The career orientation process in vocational high schools was frequently constrained by student confusion and teacher subjectivity due to the absence of analytical guidelines. This study developed a decision support system to provide objective career recommendations. The main contribution of this research was the provision of an early-stage analytical guideline based on mathematical computation for students. The system development utilized the Waterfall method. For computation, the Best Worst Method (BWM) was used to calculate criteria weights based on expert preferences, which was combined with Multi-Objective Optimization on the basis of Ratio Analysis (MOORA) to rank alternatives. The computation results of the BWM vector successfully achieved a consistency ratio of 0.0468. The confusion matrix testing on 30 samples indicated an accuracy rate of 86.67% and the System Usability Scale (SUS) evaluation obtained a score of 72.2 (Acceptable). However, this study is limited by the small sample size and implementation scope within a single school. These findings indicate that the integration of BWM and MOORA can be used as an initial analytical guideline to support career guidance services in vocational high schools. Proses penentuan orientasi karir di SMK sering terkendala kebingungan siswa dan subjektivitas guru akibat ketiadaan pedoman analitis. Penelitian ini mengembangkan sistem pendukung keputusan untuk memberikan rekomendasi karir secara objektif. Kontribusi utama penelitian ini adalah penyediaan pedoman analitis awal berbasis komputasi matematis bagi siswa. Pengembangan sistem menggunakan metode Waterfall. Untuk komputasi, metode Best Worst Method (BWM) digunakan untuk menghitung bobot kriteria berdasarkan preferensi pakar, yang dipadukan dengan Multi-Objective Optimization on the Basis of Ratio Analysis (MOORA) untuk merangking alternatif. Hasil komputasi vektor BWM sukses mencapai rasio konsistensi 0,0468. Pengujian confusion matrix pada 30 sampel menunjukkan tingkat akurasi 86,67% dan evaluasi System Usability Scale (SUS) memperoleh skor 72,2 (Acceptable). Meskipun demikian, penelitian ini memiliki keterbatasan pada ukuran sampel yang kecil dan cakupan implementasi yang masih terbatas di satu sekolah. Temuan ini menunjukkan bahwa integrasi BWM dan MOORA dapat digunakan sebagai pedoman analitis awal dalam mendukung layanan bimbingan karir di SMK.
Klasifikasi dan Rekomendasi Strategi Pembelajaran berbasis Gaya Belajar menggunakan Artificial Neural Network Yusuf, Mohamad Fauzi; Rohandi, Manda; Rijal, Bait Syaiful; Olii, Salahudin; Pakaja, Jemmy A.; Suwandi, Ihsanulfu'ad
Jambura Journal of Informatics VOL 8, N0 1: APRIL 2026
Publisher : Universitas Negeri Gorontalo

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.37905/jji.v8i1.35294

Abstract

Differences in student learning styles demand adaptive and personalized learning strategies. This study aims to develop a web-based learning strategy recommendation system utilizing Artificial Neural Network (ANN) to model the relationship between students' learning styles and appropriate learning strategies. Learning style identification was conducted using the Felder-Silverman questionnaire encompassing four dimensions: active–reflective, sensing–intuitive, visual–verbal, and sequential–global. The study employed a Research and Development (R&D) method with the 4D model and Personal Extreme Programming (PXP) approach. Data were collected from 25 seventh-grade students at SMP Negeri 1 Tomilito. A Multilayer Perceptron ANN model was trained using the backpropagation algorithm over 3,000 epochs, yielding a Mean Squared Error (MSE) value of 0.0541, indicating a relatively low prediction error rate. System feasibility testing obtained a score of 85.42%, categorized as "Very Feasible." The developed system is capable of identifying students' learning styles and automatically generating learning strategy recommendations, thereby potentially supporting teachers in designing more adaptive and personalized learning experiences. Perbedaan gaya belajar siswa menuntut adanya strategi pembelajaran yang adaptif dan terpersonalisasi. Penelitian ini bertujuan mengembangkan sistem rekomendasi strategi pembelajaran berbasis web yang memanfaatkan Artificial Neural Network (ANN) untuk memodelkan hubungan antara gaya belajar dan strategi pembelajaran yang sesuai. Identifikasi gaya belajar dilakukan menggunakan kuesioner Felder-Silverman yang mencakup empat dimensi: aktif–reflektif, sensori–intuitif, visual–verbal, dan sequential–global. Penelitian menggunakan metode Research and Development (R&D) dengan model 4D dan pendekatan Personal Extreme Programming (PXP). Data dikumpulkan dari 25 siswa kelas VII SMP Negeri 1 Tomilito. Model ANN Multilayer Perceptron dilatih menggunakan algoritma backpropagation dengan 3000 epoch dan menghasilkan nilai Mean Squared Error (MSE) sebesar 0,0541, yang mengindikasikan tingkat kesalahan prediksi yang relatif rendah. Hasil uji kelayakan sistem memperoleh skor 85,42% dengan kategori "Sangat Layak". Sistem yang dikembangkan mampu mengidentifikasi gaya belajar siswa dan memberikan rekomendasi strategi pembelajaran secara otomatis, sehingga berpotensi mendukung guru dalam merancang pembelajaran yang lebih adaptif dan personal.
Assessing Knowledge Management Readiness in Higher Education: An Institutional Self-Assessment from Gorontalo, Indonesia Katili, Muhammad Rifai; Lahay, Sri Nilawaty
Jambura Journal of Informatics VOL 8, N0 1: APRIL 2026
Publisher : Universitas Negeri Gorontalo

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.37905/jji.v8i1.37942

Abstract

Knowledge management (KM) has been widely recognized as a strategic enabler for organizational performance and information systems development, yet its systematic adoption in higher education institutions (HEIs) remains limited, particularly in Indonesia. This study presents an institutional KM readiness assessment at two universities in Gorontalo Province, Universitas Negeri Gorontalo (UNG, public) and Universitas Ichsan Gorontalo (UNISAN, private), as an initial descriptive baseline in this regional context. A quantitative descriptive survey was conducted using an instrument grounded in the Knowledge Management Critical Success Factors (KMCSF) framework, covering three aspects: Abstract (conceptual awareness), Soft (human and organizational factors), and Hard (technology and infrastructure). Data were collected from 226 respondents through purposive sampling. The study aims to assess KM readiness levels at both institutions and compare readiness profiles across the three aspects to identify strengths and priority areas for IS-informed governance improvement. Validity and reliability of the instrument were confirmed on this study's data prior to main data collection. Readiness levels were interpreted using a five-level readiness scale, where classifications reflect overall average scores across all dimensions. Results indicated that UNISAN obtained a score corresponding to Level 4 (Receptive) while UNG obtained Level 5 (Optimal), with both institutions showing relative strengths in technology infrastructure and organizational structure. However, knowledge hub and centers, explicit knowledge management, and organizational culture emerged as shared areas requiring priority attention. These findings establish a descriptive KM readiness baseline for HEIs in Gorontalo Province and offer evidence-based directions for knowledge management system design and IS governance improvement.
Pengembangan Media Pembelajaran Berbasis Augmented Reality pada Materi Sel Hewan dan Sel Tumbuhan di SMP Kelas VIII Mugiarto, Mugiarto; Widodo, Tri
Jambura Journal of Informatics VOL 8, N0 1: APRIL 2026
Publisher : Universitas Negeri Gorontalo

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.37905/jji.v8i1.37035

Abstract

The study of animal and plant cell materials is often challenging for students due to their microscopic and abstract nature, making them difficult to visualize through conventional media. This condition negatively impacts students' conceptual understanding and learning outcomes. This study aims to develop an Augmented Reality (AR)-based learning medium on the Android platform capable of projecting animal and plant cell structures interactively in three-dimensional format. A Research and Development (R&D) approach was employed following the ADDIE model. The trial subjects consisted of 10 eighth-grade junior high school students, one media expert, and one content expert. Data collection instruments included validation sheets, student response questionnaires, and learning achievement tests (pre-test and post-test). Media expert validation reached 96.25% and content expert validation reached 82.67%, while student responses showed 90%, all categorized as very feasible. Based on the effectiveness test, an average N-Gain score of 0.78 was obtained, classified as high. These results indicate that the developed AR-based learning medium can significantly improve students' conceptual understanding and has the potential to serve as an innovative and adaptive alternative learning medium. Materi sel hewan dan sel tumbuhan seringkali menjadi tantangan bagi siswa karena karakternya yang mikroskopis dan abstrak, sehingga sulit divisualisasikan melalui media konvensional. Kondisi ini berdampak pada rendahnya pemahaman konsep dan hasil belajar siswa. Penelitian ini bertujuan mengembangkan media pembelajaran berbasis Augmented Reality (AR) pada platform Android yang mampu memproyeksikan struktur sel hewan dan sel tumbuhan secara interaktif dalam format tiga dimensi. Pendekatan yang digunakan adalah Research and Development (R&D) dengan mengacu pada model ADDIE. Subjek uji coba terdiri dari 10 siswa kelas VIII SMP, satu ahli media, dan satu ahli materi. Instrumen pengumpulan data mencakup lembar validasi, kuesioner respons siswa, serta tes hasil belajar (pre-test dan post-test). Hasil validasi ahli media mencapai 96,25% dan ahli materi sebesar 82,67%, sedangkan respons siswa menunjukkan angka 90%, ketiganya berada pada kategori sangat layak. Berdasarkan uji efektivitas, diperoleh skor rata-rata N-Gain sebesar 0,78 yang termasuk dalam klasifikasi tinggi. Hasil ini menunjukkan bahwa media pembelajaran berbasis AR yang dikembangkan mampu meningkatkan pemahaman konsep siswa secara signifikan dan berpotensi menjadi alternatif media pembelajaran yang inovatif dan adaptif.
Digital Transformation for Rural Empowerment: A Web-Based Application Framework to Enhance BUMDesa Performance Amali, Lanto Ningrayati; Tuloli, Mohamad Syafri; Katili, Muhammad Rifai
Jambura Journal of Informatics VOL 8, N0 1: APRIL 2026
Publisher : Universitas Negeri Gorontalo

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.37905/jji.v8i1.37891

Abstract

The rapid advancement of digital technology in Indonesia presents both opportunities and challenges for rural economic actors, particularly village-owned enterprises (BUMDesa). While urban MSMEs have increasingly adopted digital platforms, many BUMDesa continue to face structural and managerial barriers to digital integration. This study addresses these issues by developing the platform, a web-based application designed to enhance BUMDesa management capacity through knowledge sharing and stakeholder collaboration. Guided by the Knowledge-Based Economy and Pentahelix collaboration model, the system integrates a digital knowledge repository, user role management, web services using XML/JSON, and modules for training, article exchange, and community QA. The prototype was developed using the Waterfall method and deployed in Gorontalo and North Sulawesi. Results indicate that SIBUDE effectively facilitates real-time communication, automatic knowledge dissemination, and multi-sector cooperation. It enables BUMDesa to learn from each other, share innovations, and access a centralized, structured repository that supports continuous improvement. The study concludes that knowledge-driven digital systems can significantly empower rural enterprises by promoting transparency, innovation, and operational efficiency. Recommendations include strengthening institutional adoption, expanding data automation features, and aligning local governance with digital transformation strategies.

Page 1 of 1 | Total Record : 7

 1 

Filter by Year

2026 2026


Reset
Filter By Issues
All Issue VOL 8, N0 1: APRIL 2026 VOL 7, N0 2: OKTOBER 2025 VOL 7, N0 1: APRIL 2025 VOL 6, N0 2: OKTOBER 2024 VOL 6, N0 1: APRIL 2024 VOL 5, NO 2: OCTOBER 2023 VOL 5, NO 1: APRIL 2023 VOL 4, NO 2: OCTOBER 2022 VOL 4, NO 1: APRIL 2022 VOL 3, NO 2: OCTOBER 2021 VOL 3, NO 1: APRIL 2021 VOL 2, NO 2: OCTOBER 2020 VOL 2, NO 1: APRIL 2020 VOL 1, NO 2: OCTOBER 2019 VOLUME 1 NOMOR 1, APRIL 2019 VOL 1, NO 1: APRIL 2019 More Issue