Garuda - Garba Rujukan Digital

Simulation Study of EfficientNetB0 Performance for Cocoa Pod Disease Classification Using Literature Based Synthetic Data Okta Veza; Sherly Agustini; Nofri Yudi Arifin; Albertus Laurensius Setyabudhi
Engineering and Technology International Journal Vol 7 No 03 (2025): Engineering and Technology International Journal (EATIJ)
Publisher : YCMM

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.55642/eatij.v7i03.1335

Automated detection of cocoa (Theobroma cacao) pod diseases such as black pod, pod borer infestation, and frosty pod rot is critical for safeguarding yield, yet the development of deep-learning classifiers is frequently constrained by the scarcity of curated, well-balanced image datasets. This study presents a controlled simulation that evaluates the expected performance envelope of an EfficientNetB0 classifier under idealized, literature-grounded conditions before field data collection is undertaken. Rather than asserting empirical field results, a synthetic dataset is constructed whose per-class feature distributions (color, texture, and lesion morphology) are parameterized from values reported across six core references. A balanced corpus of 3,000 synthetic images spanning four classes (healthy, black pod, pod borer, frosty pod) was generated and partitioned using a stratified 70/15/15 split. EfficientNetB0, initialized with ImageNet weights and fine-tuned with standard augmentation, achieved a simulated test accuracy of 93.8%, a macro-averaged F1-score of 0.926, and balanced per-class precision and recall in the 0.90-0.95 range. The confusion matrix indicates that the principal source of error is morphological overlap between pod borer and frosty pod presentations. The results delineate a plausible upper-bound performance band to guide sample-size planning, augmentation strategy, and architecture selection for a subsequent field study. All reported figures are framed explicitly as simulation outputs.

Deep Learning Approaches for Cocoa Pod Disease Classification A Literature Review Okta Veza; Nofri Yudi Arifin; Albertus Laurensius Setyabudhi
Engineering and Technology International Journal Vol 6 No 03 (2024): Engineering and Technology International Journal (EATIJ)
Publisher : YCMM

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.55642/eatij.v6i03.1337

Cocoa (Theobroma cacao) is a cornerstone of many tropical economies, yet its yield is persistently threatened by pod diseases such as black pod rot, frosty pod rot, and cocoa pod borer infestation. Over the past decade, deep learning, and convolutional neural networks (CNNs) in particular, has emerged as a powerful tool for automated plant disease diagnosis from images. This paper presents a structured literature review of deep-learning approaches applied, directly or by close analogy, to cocoa pod disease classification. Following a PRISMA style protocol, 41 studies published between 2016 and 2025 were selected from major databases and synthesized along five dimensions: data sources and dataset construction, preprocessing and augmentation, network architectures, training and transfer-learning strategies, and evaluation methodology. The review finds that transfer learning with compact architectures, notably ResNet, MobileNet, and EfficientNet variants, dominates recent work and consistently achieves reported accuracies above 90% on related tasks. Three persistent gaps are identified: the scarcity of large, balanced, and openly available cocoa specific image datasets; limited validation under realistic field conditions; and inconsistent reporting of evaluation metrics. The review concludes by outlining research directions, including domain adaptation, lightweight on device inference, explainability, and standardized benchmarking, to move cocoa pod disease classification from controlled experiments toward deployable tools for smallholder agriculture.

Comparative Analysis of Classification Methods for Cyberattack Detection on Computer Networks Sherly Agustini; Mustakim Mustakim; Okta Veza
Jurnal Responsive Teknik Informatika Vol 10 No 01 (2026): JR : Jurnal Responsive Teknik Informatika
Publisher : LPPM Universitas Ibnu Sina Batam

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.36352/jr.v10i01.1516

The rapid growth of computer networks has increased the complexity and intensity of cyber threats, making machine learning based intrusion detection one of the most widely studied defense mechanisms. This study compares the performance of five classification methods Decision Tree, Random Forest, Support Vector Machine (SVM), K-Nearest Neighbors (KNN), and Naive Bayes in detecting five categories of network activity: Normal, Denial of Service (DoS), Probing, Remote to Local (R2L), and User to Root (U2R). Due to limited access to sensitive real-world network traffic data, this study uses a small-scale simulated dataset of 500 samples generated programmatically using controlled statistical distributions to represent the characteristics of each category, including the class imbalance condition commonly found in real network traffic. The data was split into 70% training and 30% testing using a stratified scheme and evaluated using accuracy, precision, recall, F1-score, and computation time metrics. Results show that Decision Tree achieved the highest macro F1-score (85.96%) with 94.00% accuracy, slightly ahead of Naive Bayes (84.52% macro F1-score, 95.33% accuracy). Random Forest recorded the highest overall accuracy (96.67%), but its macro F1-score (84.06%) lagged due to low recall on the U2R class, which has very few samples. Feature-importance analysis indicates that srv_count, dst_host_count, and count are the main determinants for distinguishing attack categories. Naive Bayes and KNN recorded the fastest computation times, while Random Forest required the longest training time. The small dataset size causes performance estimates on minority classes (R2L and U2R) to be prone to fluctuation, so these findings should be regarded as a preliminary proof-of-concept study requiring further validation using a larger dataset or real world network traffic data.

Comparative Analysis of Classification Methods for Cyberattack Detection on Computer Networks Sherly Agustini; Mustakim Mustakim; Okta Veza
Jurnal Responsive Teknik Informatika Vol 10 No 01 (2026): JR : Jurnal Responsive Teknik Informatika
Publisher : LPPM Universitas Ibnu Sina Batam

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.36352/jr.v10i01.1516

The rapid growth of computer networks has increased the complexity and intensity of cyber threats, making machine learning based intrusion detection one of the most widely studied defense mechanisms. This study compares the performance of five classification methods Decision Tree, Random Forest, Support Vector Machine (SVM), K-Nearest Neighbors (KNN), and Naive Bayes in detecting five categories of network activity: Normal, Denial of Service (DoS), Probing, Remote to Local (R2L), and User to Root (U2R). Due to limited access to sensitive real-world network traffic data, this study uses a small-scale simulated dataset of 500 samples generated programmatically using controlled statistical distributions to represent the characteristics of each category, including the class imbalance condition commonly found in real network traffic. The data was split into 70% training and 30% testing using a stratified scheme and evaluated using accuracy, precision, recall, F1-score, and computation time metrics. Results show that Decision Tree achieved the highest macro F1-score (85.96%) with 94.00% accuracy, slightly ahead of Naive Bayes (84.52% macro F1-score, 95.33% accuracy). Random Forest recorded the highest overall accuracy (96.67%), but its macro F1-score (84.06%) lagged due to low recall on the U2R class, which has very few samples. Feature-importance analysis indicates that srv_count, dst_host_count, and count are the main determinants for distinguishing attack categories. Naive Bayes and KNN recorded the fastest computation times, while Random Forest required the longest training time. The small dataset size causes performance estimates on minority classes (R2L and U2R) to be prone to fluctuation, so these findings should be regarded as a preliminary proof-of-concept study requiring further validation using a larger dataset or real world network traffic data.

TINJAUAN LITERATUR SISTEMATIS TERHADAP METODE HISTOGRAM OF ORIENTED GRADIENTS (HOG) PADA PENGOLAHAN CITRA Okta Veza; Nofri Yudi Arifin
Jurnal Sains Informatika Terapan Vol. 4 No. 3 (2025): Jurnal Sains Informatika Terapan (Oktober, 2025)
Publisher : Riset Sinergi Indonesia (RISINDO)

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

Histogram of Oriented Gradients (HOG) merupakan metode ekstraksi fitur berbasis gradien yang banyak digunakan dalam visi komputer karena efisiensi dan kemampuannya merepresentasikan struktur tepi objek. Dalam bidang inspeksi nondestruktif pengelasan berbasis citra, HOG telah diterapkan untuk mendeteksi dan mengklasifikasikan cacat pengelasan. Namun, sebagian besar penelitian masih menggunakan konfigurasi HOG konvensional yang kurang adaptif terhadap variasi intensitas, noise, dan kompleksitas pola cacat pengelasan. Penelitian ini menyajikan tinjauan literatur sistematis terhadap penerapan metode HOG pada inspeksi cacat pengelasan berdasarkan artikel-artikel ilmiah yang terindeks Scopus. Literatur diklasifikasikan berdasarkan kesamaan metode dan objek penelitian untuk mengidentifikasi tren, keunggulan, serta keterbatasan metode yang ada. Hasil kajian menunjukkan bahwa penerapan HOG secara spesifik pada objek pengelasan masih terbatas, sehingga membuka peluang pengembangan metode HOG yang lebih adaptif dan robust. Temuan ini diharapkan menjadi dasar pengembangan metode ekstraksi fitur yang lebih akurat dan aplikatif dalam mendukung inspeksi pengelasan di lingkungan industri.

Towards Integrated Smart Tourism Systems in Urban Destinations: A Systematic Literature Review on End-to-End Journey and SME Digital Integration Okta Veza; Nofri Yudi Arifin; Sherly Agustini
Engineering and Technology International Journal Vol 8 No 01 (2026): Engineering and Technology International Journal (EATIJ)
Publisher : YCMM

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.55642/eatij.v8i01.1238

The rapid development of digital technologies has significantly transformed the tourism sector, particularly in urban destinations characterized by complex ecosystems and diverse stakeholders. Smart tourism systems have emerged as a key approach to enhancing service efficiency, improving tourist experiences, and enabling data-driven decision-making. However, existing studies are still fragmented and largely focus on partial implementations, lacking comprehensive end-to-end integration. This study aims to conduct a systematic literature review on smart tourism systems in urban destinations, with a focus on system integration, end-to-end tourist journey, and Small and Medium Enterprises (SMEs) digital integration. The review was conducted using selected articles from reputable international journals published between 2023 and 2025. The analysis categorizes the studies into three groups: same system and same scope, same system and similar scope, and same system and different scope. The results indicate that only a limited number of studies have developed fully integrated smart tourism systems, while most studies focus on specific components or are applied in different domains. In addition, stakeholder integration and SME digital inclusion remain key challenges in developing comprehensive smart tourism ecosystems. This study contributes by identifying research gaps and proposing future research directions focused on developing integrated, scalable, and inclusive smart tourism systems. The findings are expected to support the advancement of smart tourism system design in urban destinations.

Data Driven Smart Tourism Management: A Literature Review on System Integration, Digital Tourist Journey, and UMKM Connectivity in Smart Cities Sherly Agustini; Okta Veza; Nofri Yudi Arifin; Albertus Laurensius Setyabudhi
Engineering and Technology International Journal Vol 8 No 01 (2026): Engineering and Technology International Journal (EATIJ)
Publisher : YCMM

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.55642/eatij.v8i01.1239

The rapid development of smart city initiatives has significantly transformed the tourism sector through the adoption of digital technologies and data-driven systems. This study aims to analyze the development of data-driven smart tourism management by focusing on system integration, digital tourist journey, and UMKM connectivity within smart city environments. A Systematic Literature Review (SLR) method was employed to examine 30 relevant articles published between 2020 and 2025. The findings indicate that most studies utilize similar methodological approaches but are applied to different research objects, resulting in fragmented research outcomes. Furthermore, the lack of integration among systems and limited involvement of UMKM in digital platforms remain major challenges in developing effective smart tourism ecosystems. This study highlights the need for integrated, interoperable, and scalable smart tourism systems supported by advanced technologies such as artificial intelligence, big data analytics, and Internet of Things (IoT). The results of this study provide a conceptual foundation and research directions for developing more comprehensive and sustainable smart tourism systems in smart city contexts.

Pelatihan Welding Procedure Specification (WPS) untuk Meningkatkan Kompetensi Mahasiswa Menghadapi Kebutuhan Dunia Kerja Albertus Laurensius Setyabudhi; Yuni Hardi; Amelia Rachmi Nasution; Lucky Agustin; Agustin Dwi Sumiwi; Ramdhani Yusli Arbain Sugoro; Okta Veza; Nofri Yudi Arifin
JURNAL PENGABDIAN MASYARAKAT AKADEMISI Vol. 4 No. 2 (2026): April : JURNAL PENGABDIAN MASYARAKAT AKADEMISI
Publisher : CV. ALIM'SPUBLISHING

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.59024/jpma.v4i2.2404

The competency gap between university graduates and industrial requirements remains a significant challenge in preparing job-ready human resources, particularly in the welding sector. One of the essential competencies required by industry is the ability to understand and interpret the Welding Procedure Specification (WPS) as the primary document governing welding operations in accordance with international standards. This community service program aimed to enhance students' competencies in understanding the concepts, structure, and implementation of WPS to improve their readiness for the industrial workforce. The program was organized by the Department of Logistics Engineering and the Department of Naval Architecture Engineering, Faculty of Science and Technology, Universitas Ibnu Sina, in collaboration with the Alumni Association of Institut Teknologi Sepuluh Nopember (IKA ITS), using a Participatory Training and Practice-Based Learning approach. The activities included competency needs assessment, lectures on WPS, Procedure Qualification Record (PQR), Welder Performance Qualification (WPQ), ASME Section IX and AWS D1.1 standards, industrial case studies, practical interpretation of WPS documents, interactive discussions, and program evaluation. The results demonstrated that participants significantly improved their understanding of WPS functions, the relationship between WPS and PQR, welding parameters, and the application of international standards in fabrication processes. The program also enhanced participants' awareness of industrial competency requirements while strengthening collaboration between higher education institutions and industry practitioners. The WPS training proved to be an effective approach for improving students' technical competencies, reducing the gap between academic learning and industrial practice, and supporting graduate readiness for careers in manufacturing, construction, oil and gas, and shipbuilding industries.

Penguatan Jiwa Teknopreneur Berdampak melalui Sosialisasi Pemberdayaan Masyarakat pada Siswa SMA Negeri 3 Batam Okta Veza; Albertus Laurensius Setyabudhi; Nofri Yudi Arifin; Nabila Husnul Khotimah; Said Nurdian Syah; Timor Alex Chandra Ian Qurnia; Rofi Zakirahmad; M. Riski; Kamiruddin Kamiruddin
JURNAL PENGABDIAN MASYARAKAT AKADEMISI Vol. 4 No. 2 (2026): April : JURNAL PENGABDIAN MASYARAKAT AKADEMISI
Publisher : CV. ALIM'SPUBLISHING

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.59024/jpma.v4i2.2330

Impact-driven technopreneurship is a technology-based entrepreneurial orientation that creates not only economic value but also social and environmental value in support of the Sustainable Development Goals (SDGs). This community service activity aims to foster and strengthen the spirit of impact-driven technopreneurship among senior high school students, whose understanding of entrepreneurship is generally still limited to conventional buying and selling. The activity was conducted at the Wan Sri Beni Hall of SMA Negeri 3 Batam and attended by 102 tenth- and eleventh-grade students. The method was participatory, comprising preparation, classical delivery of material built on three pillars (empathy, technology utilization, and sustainability), interactive case-based discussion, and observational evaluation of participation and comprehension. The results show that participants were highly engaged, able to identify real problems in their surroundings, and able to formulate simple technology-based solution ideas relevant to community needs. The activity strengthened students' awareness of innovation, creativity, and social responsibility, and reinforced university-school collaboration as a sustainable entrepreneurship-learning ecosystem. Continued mentoring and idea incubation are recommended so that the ideas generated can be developed into applicable and sustainable solutions.

Title

Found 39 Documents
Search

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Title Search

Found 39 Documents Search

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Title

Found 39 Documents
Search