cover
Article Per Year (5 Year)
All
Home Page
OAI Link
Editorial Team
Contact
Reviewer
Google Scholar
Contact Name
Raymond Sutjiadi, S.T., M.Kom
Contact Email
p3m@ikado.ac.id
Phone
+62317346375
Journal Mail Official
p3m@ikado.ac.id
Editorial Address
Pattimura No. 3 Kelurahan Sonokwijenan Kecamatan Sukomanunggal Kota Surabaya 60189
Location
Kota surabaya,
Jawa timur
INDONESIA
Teknika
Published by Institut Informatika Indonesia Surabaya
ISSN : 25498037     EISSN : 25498045     DOI : https://doi.org/10.34148/teknika
Core Subject : Science, Engineering,
Computer Science & IT Electrical & Electronics Engineering Engineering
Teknika is a peer-reviewed journal dedicated to disseminate research articles in Information and Communication Technology (ICT) area. Researchers, lecturers, students, or practitioners are welcomed to submit paper which has topic below: Computer Networks Computer Security Artificial Intelligence Machine Learning Human Computer Interaction Computer Vision Virtual/Augmented Reality Digital Image Processing Data Mining Web Mining Computer Architecture Software Engineering Decision Support System Information System Audit Business Information System Datawarehouse & OLAP And any other topics relevant with Information and Communication Technology (ICT) area
Arjuna Subject : Ilmu Komputer (semua kategori) - Aplikasi Ilmu Komputer
Articles 356 Documents
 32   33   34   35   36 
Decision Support System for Teacher Performance Evaluation Using LODECI Weighting and CODAS Method Fadila Shely Amalia; Muksin Hi Abdullah; Sumanto; Setiawansyah; Junhai Wang
Teknika Vol. 15 No. 2 (2026): July 2026
Publisher : Center for Research and Community Service, Institut Informatika Indonesia (IKADO) Surabaya

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.34148/teknika.v15i2.1476

Abstract

The quality of teacher performance evaluation plays an important role in improving educational outcomes, yet conventional assessment approaches often suffer from subjectivity, inconsistency, and lack of transparent weighting mechanisms. This study proposes a Decision Support System (DSS) model by integrating the LODECI method for objective criteria weighting and the CODAS method for alternative ranking to produce more accurate and data-driven evaluation results. The LODECI method determines criterion weights based on data distribution characteristics, resulting in proportional weights where Classroom Management (0.1881), Pedagogical Competence (0.1825), and Creativity and Innovation (0.1702) are identified as the most influential criteria. Furthermore, the CODAS method evaluates teacher performance using a distance-based approach to the negative ideal solution, producing preference values that enable clear differentiation among alternatives. The ranking results show that A7 – Gina achieves Rank 1 with a value of -0.2399, followed by A3 – Citra in Rank 2 with -0.2181, and A9 – Intan in Rank 3 with -0.1374, indicating their superior performance compared to other alternatives. To ensure robustness, a sensitivity analysis was conducted using 18 threshold (φ) scenarios ranging from 0.1 to 0.95. The results demonstrate that the top-ranked alternatives (A7, A3, and A9) consistently maintain their positions across all scenarios, indicating that the proposed model is stable and not significantly affected by parameter changes. Therefore, the integration of LODECI and CODAS within a DSS framework proves to be effective in producing objective, consistent, and reliable teacher performance evaluations that can support decision-making in educational institutions.
An Integrated Decision Support System Using Respond to Criteria Weighting and Root Assessment Method for Content Creator Selection Temi Ardiansah; Iswan A. Thais; Aditia Yudhistira; Ahmad Ari Aldino; Setiawansyah
Teknika Vol. 15 No. 2 (2026): July 2026
Publisher : Center for Research and Community Service, Institut Informatika Indonesia (IKADO) Surabaya

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.34148/teknika.v15i2.1477

Abstract

This study proposes an integrated decision support system using the RECA Weighting and RAM  methods to improve the objectivity and accuracy of content creator selection in the digital marketing era. The problem addressed arises from the complexity of evaluating multiple candidates based on various criteria such as content quality, engagement, consistency, creativity, and brand alignment, which are often assessed subjectively. The RECA method is applied to determine criteria weights objectively based on data variation among alternatives, while the RAM method is used to rank candidates through normalization, weighting, and root-based transformation to ensure more stable and balanced results. The findings show that the proposed approach is capable of producing consistent and reliable rankings, where the top three alternatives are Nabila Putri as the first rank, followed by Sinta Maharani in second place, and Putri Ananda in third place, indicating their superior performance across all evaluation criteria. Furthermore, sensitivity analysis by adjusting criteria weights by ±0.05 indicates that the ranking results remain relatively stable, demonstrating the robustness of the model. Therefore, the integration of RECA and RAM provides an effective, transparent, and accountable solution for supporting decision-making in content creator selection.
Multiplatform Topic Modeling Analysis of Gender-Based Violence in Indonesia Using LDA Annisa Putri Patricia; Nina Setiyawati; Dwi Hosanna Bangkalang
Teknika Vol. 15 No. 2 (2026): July 2026
Publisher : Center for Research and Community Service, Institut Informatika Indonesia (IKADO) Surabaya

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.34148/teknika.v15i2.1478

Abstract

Gender-based violence remains a critical social issue in Indonesia, generating substantial public discourse across digital platforms. This study applies Latent Dirichlet Allocation (LDA)-based topic modeling to identify and compare the dominant themes emerging in online discussions of gender-based violence across three platforms: X (formerly Twitter), YouTube, and the news portal Detik.com. A total of 21,000 data points were collected through keyword-based web scraping covering the period January 2020 to October 2025. The two-phase modeling process yielded coherence scores of 0.38 and 0.53 for X, 0.77 and 0.73 for YouTube, and 0.8 and 0.52 for Detik.com across the first and second phases, respectively, reflecting differences in language register and content structure across platforms. A two-phase modeling approach was employed for each platform to progressively refine topic quality and eliminate irrelevant outputs. The results show that LDA successfully identified platform-specific thematic patterns: X captured emotional and psychological dimensions of gender-based violence, YouTube surfaced legislative and advocacy-oriented discourse centered on the PKS Law, and Detik.com produced case-specific topics grounded in legal proceedings and journalistic reporting. Across all three platforms, domestic violence emerged as the most consistently prominent theme. These findings demonstrate that a multi-platform approach yields a more comprehensive and nuanced picture of public discourse on gender-based violence than any single-source analysis, and that LDA is an effective tool for large-scale thematic extraction from heterogeneous online text data.
Comparative Analysis of YOLOv5, YOLOv8, and YOLOv11 for Military Aircraft Detection on Aerial Imagery Supporting Airspace Surveillance Fajar Sidik Suganda; Asep Adang Supriyadi
Teknika Vol. 15 No. 2 (2026): July 2026
Publisher : Center for Research and Community Service, Institut Informatika Indonesia (IKADO) Surabaya

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.34148/teknika.v15i2.1483

Abstract

Automated military aircraft detection from aerial imagery is a key enabler for modern Intelligence, Surveillance, and Reconnaissance (ISR) operations, particularly for nations with vast airspace such as Indonesia. While the You Only Look Once (YOLO) family has become a de facto standard for such tasks, the literature lacks a controlled, head-to-head comparison of its recent generations on a standard military aircraft benchmark, which leaves architecture selection for ISR systems largely guided by version recency rather than empirical evidence. This study addresses that gap by benchmarking three YOLO generations YOLOv5s, YOLOv8s, and YOLOv11s on the MAR20 dataset (3,842 images, 20 classes, 22,341 instances) under identical training conditions, and by analyzing the results along three axes: aggregate accuracy, per-class behavior, and accuracy–parameter trade-off. Counter to the assumption that newer is necessarily better, the oldest architecture in the comparison, YOLOv5s, achieves the highest Precision (0.985) and F1-Score (0.978) with the smallest parameter count (7.2M), while YOLOv11s, the most recent iteration, leads only on Recall (0.972) and YOLOv8s offers the most balanced profile; all three exceed mAP@0.5 of 0.988. Per-class analysis further shows that detection difficulty is driven by inter-class visual similarity rather than class imbalance, with visually similar fighter aircraft (F-22, F-16, F-15) forming a distinct hard-class cluster (mean AP 0.705–0.788) despite adequate training samples. Based on these findings we propose an operationally-mapped model-selection guide YOLOv5s as a strong candidate for edge-constrained ISR platforms, YOLOv8s for balanced ground-station workloads, and YOLOv11s for recall-critical wide-area surveillance while explicitly noting that the recommendations rest on accuracy–parameter evidence rather than on-device latency measurements, and that the single-seed, small-variant setting bounds the generality of the ranking. Validation through repeated runs with statistical testing, profiling on representative edge hardware, and evaluation on operational imagery remain important directions for future work.
Vision Transformer-Based Dog Breed Classification with a Hybrid Detection-Classification Framework Njoto Benarkah; Joko Siswantoro; Bryan Porayouw
Teknika Vol. 15 No. 2 (2026): July 2026
Publisher : Center for Research and Community Service, Institut Informatika Indonesia (IKADO) Surabaya

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.34148/teknika.v15i2.1484

Abstract

Dog breed classification remains a challenging task in computer vision due to high inter-class visual similarity, pose variations, changes in illumination, and complex background conditions. Conventional convolutional neural network (CNN) approaches often struggle to capture global contextual dependencies and subtle discriminative features. This study proposes a hybrid deep learning framework that integrates YOLOv8n for object detection with the Vision Transformer (ViT-B/16) for dog breed classification. The dataset comprises 14,181 dog images collected from the Tsinghua Dogs Dataset and supplementary real-world sources, spanning 10 dog breed categories. The proposed framework includes image preprocessing, data augmentation, transfer learning, and Bayesian hyperparameter optimization using Optuna to enhance model generalization. YOLOv8n is employed to localize dog regions, which are subsequently resized and passed to the Vision Transformer for global feature representation learning. The model is evaluated on 2,133 unseen test images. Experimental results demonstrate that the proposed framework achieves an accuracy of 97.98% with macro and weighted F1-score values of 98.76% and 97.98%, respectively. Comparative experiments against standalone ViT-B/16 and EfficientNetV2M architectures futher confirm the effectiveness of the proposed hybrid YOLOv8n–ViT-B/16 framework for dog breed classification.
Android-Based Research Title Similarity Detection Using a Combined Word2Vec and TF-IDF with Cosine Similarity Score Abyan Dzakwan Baksir; Rosihan; Muhammad Ridha Albaar
Teknika Vol. 15 No. 2 (2026): July 2026
Publisher : Center for Research and Community Service, Institut Informatika Indonesia (IKADO) Surabaya

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.34148/teknika.v15i2.1487

Abstract

Research title similarity detection is needed to support academic topic checking because manual title comparison is time-consuming and may fail to identify related topics expressed with different terms. This study develops an Android-based research title similarity detection system using a lightweight hybrid lexical-semantic approach that combines TF-IDF, Word2Vec Continuous Bag of Words (CBOW), and cosine similarity. The dataset was obtained through scraping from the GARUDA Portal and curated into 10,000 research titles related to computer science and information technology. The titles were processed through case folding, tokenization, stopword removal, and stemming using Sastrawi. TF-IDF was used to represent lexical term importance, while Word2Vec CBOW was used to capture contextual word relationships. The two similarity scores were integrated using weighted alpha configurations of 0.50, 0.60, and 0.70. The model was implemented in a Python FastAPI backend and tested through a Flutter-based Android application. Evaluation was conducted using 30 query titles with Top-5 retrieval results and manual relevance judgment based on a predefined 0–2 relevance rubric. The results show that TF-IDF only achieved the highest MAP@5 of 0.985972 and NDCG@5 of 0.939095. Among the hybrid configurations, alpha 0.70 produced the best performance with Precision@5 of 0.973333, MAP@5 of 0.981111, and NDCG@5 of 0.923408. These findings indicate that the hybrid model is competitive and more effective than Word2Vec only, while TF-IDF remains highly important for short research title matching.
A Random Forest Approach for Classifying Regional Social Stability in Banten Province Based on Socioeconomic Indicators Widyawati; Ika Ima Nissa; Bagus Setya; Lisdianto Dwi Kesumahadi; Yuda Pratama Wibawa
Teknika Vol. 15 No. 2 (2026): July 2026
Publisher : Center for Research and Community Service, Institut Informatika Indonesia (IKADO) Surabaya

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.34148/teknika.v15i2.1490

Abstract

Social stability is an important indicator in measuring regional welfare and development conditions. This study aims to classify the level of social stability in Banten Province using the Random Forest method based on several social indicators, including poverty, unemployment, Human Development Index (HDI), HDI percentage growth, Gini Ratio, population density, and average years of schooling (RLS). The dataset used in this study was obtained from the regency and city social statistical data in Banten Province from 2020 to 2025. The research process was carried out through several stages, namely data collection, data preprocessing, social stability label determination, splitting training and testing data, Random Forest modeling, model evaluation, feature importance analysis, and result visualization using the Python programming language. The Random Forest algorithm was selected because of its ability to perform classification effectively and reduce overfitting in classification models. The evaluation results showed that the Random Forest model achieved an accuracy value of 100%, with precision, recall, and F1-score values of 1.00. In addition, the feature importance analysis indicated that the unemployment variable had the strongest influence on the classification results, followed by HDI and poverty variables, while the Gini Ratio had the lowest influence. The findings of this study indicate that the Random Forest method can be effectively applied to classify regional social stability in Banten Province based on social indicators and can support data-driven regional policy analysis.
YOLOv11n-Based Oil Palm Health Classification Using Orthomosaic Drone Imagery Maudy Hellena Harlyn; Ritna Wahyuni; Andi Prayogi
Teknika Vol. 15 No. 2 (2026): July 2026
Publisher : Center for Research and Community Service, Institut Informatika Indonesia (IKADO) Surabaya

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.34148/teknika.v15i2.1494

Abstract

Monitoring oil palm plantation conditions across large-scale areas remains challenging because manual inspection is time-consuming, costly, and prone to observational errors. This study aims to develop a GIS-based monitoring system for oil palm health detection using the YOLOv11n algorithm and orthomosaic imagery acquired from UAV mapping. The study employed the Software Development Life Cycle (SDLC) Waterfall model and Unified Modeling Language (UML) for system development and design. The research stages included orthomosaic image acquisition, image tiling, dataset annotation, data augmentation, YOLOv11n model training, system implementation, and functional testing. The dataset was collected from oil palm plantation areas owned by PT Bakrie Sumatera Plantations and classified into three categories: healthy, unhealthy, and dead trees. The evaluation results demonstrated high detection performance with 0.99 precision, 0.99 recall, 0.99 mAP50, and 0.88 mAP50-95. The developed GEOPALM system was capable of generating centroid-based visualizations, plantation condition distribution graphs, and spatial outputs for plantation monitoring purposes. Overall, the proposed system can support faster, more efficient, and spatially structured oil palm plantation monitoring.
A Regression-Based Deep Learning Approach for Fish Fry Counting: Addressing Label Imbalance and Annotation Ambiguity Melly Damara Chaniago; Lukman Zaman; Yosi Kristian
Teknika Vol. 15 No. 2 (2026): July 2026
Publisher : Center for Research and Community Service, Institut Informatika Indonesia (IKADO) Surabaya

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.34148/teknika.v15i2.1495

Abstract

Manual counting of Nile tilapia fry is time-consuming and prone to human error, particularly under high-density conditions where visual overlap creates significant annotation ambiguity. Furthermore, real-world data collection often results in skewed label distributions. To address these challenges, this study proposes a regression-based fry counting system using EfficientNetV2S with transfer learning. Using a dataset collected from a real hatchery environment, targeted count-level balancing and rigorous annotation refinement were applied prior to model training to improve label consistency and data distribution. The novelty of this study lies in the integration of a count-level balancing strategy and a systematic annotation refinement process to address label imbalance and annotation ambiguity, two critical issues that are often overlooked in regression-based fish fry counting. The proposed model was evaluated using standard regression metrics, including Mean Absolute Error (MAE), Root Mean Square Error (RMSE), coefficient of determination (R²), and Mean Absolute Percentage Error (MAPE). Experimental results showed that the best-performing model achieved an optimized MAE of 13.25 fry, RMSE of 16.93 fry, R² of 0.985, and MAPE of 7.07%. Comparative experiments further demonstrated that the proposed EfficientNetV2S architecture outperformed EfficientNetB0, ResNet50, and MobileNetV2. These findings indicate that systematically addressing annotation ambiguity and balancing training data significantly contributes to robust fry count estimation performance in practical aquaculture applications.
A Systematic Literature Review of Convolutional Block Attention Module (CBAM) in Image Classification Vincentius Bernando Wijaya; Joko Siswantoro
Teknika Vol. 15 No. 2 (2026): July 2026
Publisher : Center for Research and Community Service, Institut Informatika Indonesia (IKADO) Surabaya

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.34148/teknika.v15i2.1500

Abstract

Image classification has become one of the most important tasks in computer vision and has been widely applied in medical imaging, agriculture, surveillance, and industrial systems. Recently, the Convolutional Block Attention Module (CBAM) has attracted significant attention for improving feature representation through channel and spatial attention mechanisms. However, studies on CBAM remain scattered across application domains, backbone architectures, deployment strategies, and evaluation approaches, making its implementation and effectiveness difficult to comprehensively understand. Therefore, this study conducted a Systematic Literature Review (SLR) based on the Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA) framework to analyze CBAM implementation in image classification studies published between 2018 and 2025. The literature search used Google Scholar through the Publish or Perish application. Of 855 identified articles, 47 met the eligibility criteria and were included. The review analyzed research domains, backbone architectures, CBAM effectiveness, deployment positions, evaluation metrics, and cross-analytical relationships. Medical Imaging was the dominant application domain, while ResNet was the most frequently used backbone architecture. Analysis of 156 ablation experiments showed that 82.1% reported performance improvements after CBAM integration, whereas 91.5% of the reviewed studies demonstrated positive outcomes. Cross-analysis further indicated that CBAM was particularly effective for fine-grained visual recognition tasks, most commonly integrated within backbone architectures, and generally more compatible with residual-based than lightweight architectures. Furthermore, computational efficiency remained underreported. These findings provide a comprehensive synthesis of current CBAM research and practical guidance for future image classification studies.

Page 35 of 36 | Total Record : 356

 32   33   34   35   36 

Filter by Year

2012 2026


Reset
Filter By Issues
All Issue Vol. 15 No. 2 (2026): July 2026 Vol. 15 No. 1 (2026): March 2026 Vol. 14 No. 3 (2025): November 2025 Vol. 14 No. 2 (2025): July 2025 Vol. 14 No. 1 (2025): March 2025 Vol. 13 No. 3 (2024): November 2024 Vol. 13 No. 2 (2024): Juli 2024 Vol. 13 No. 1 (2024): Maret 2024 Vol. 12 No. 3 (2023): November 2023 Vol. 12 No. 2 (2023): Juli 2023 Vol. 12 No. 1 (2023): Maret 2023 Vol. 11 No. 3 (2022): November 2022 Vol. 11 No. 2 (2022): Juli 2022 Vol. 11 No. 1 (2022): Maret 2022 Vol. 10 No. 3 (2021): November 2021 Vol. 10 No. 2 (2021): Juli 2021 Vol. 10 No. 1 (2021): Maret 2021 Vol. 9 No. 2 (2020): November 2020 Vol. 9 No. 1 (2020): Juli 2020 Vol. 8 No. 2 (2019): November 2019 Vol. 8 No. 1 (2019): Juli 2019 Vol. 7 No. 2 (2018): November 2018 Vol. 7 No. 1 (2018): Juli 2018 Vol. 6 No. 1 (2017): November 2017 Vol. 5 No. 1 (2016): November 2016 Vol. 4 No. 1 (2015): November 2015 Vol. 3 No. 1 (2014): Juli 2014 Vol. 2 No. 1 (2013): Juli 2013 Vol. 1 No. 1 (2012): Juli 2012 More Issue