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 
ResNet18-BLSTM-CTC-Based OCR Model for Extracting Technical Parameter Data from Digital Television Analyzer Screenshots Henrian Robby Fakhriannur; Alva Hendi Muhammad
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.v15i2.1501

Abstract

Monitoring digital television broadcasting stations requires accurate extraction of technical measurement parameters from screenshot images generated by television analyzer devices. In current practice, parameters such as frequency, signal level, bandwidth, modulation, guard interval, code rate, Fast Fourier Transform (FFT), pilot pattern, provider name, and video standard are often read and recorded manually, which may cause transcription errors when the images contain small characters, low resolution, noise, or visually similar symbols. This study proposes an Optical Character Recognition (OCR) system based on a hybrid ResNet18-Bidirectional Long Short-Term Memory-Connectionist Temporal Classification (ResNet18-BLSTM-CTC) architecture to improve technical parameter extraction from digital television analyzer screenshots. ResNet18 is used to extract visual character features, BLSTM models sequential relationships from both directions, and CTC decodes character sequences without explicit character segmentation. The implementation includes image acquisition, Region of Interest (ROI) selection, cropping, grayscale conversion, resizing into 48 x 48 pixel character images, model training, fine-tuning using hard labels, comparative evaluation, and web-based deployment using Streamlit. After fine-tuning, the proposed model achieved 96.58% accuracy, 0.0342 Character Error Rate (CER), 0.9253 macro F1-score, and reduced errors from 80 to 55. Additional comparison with Tesseract, EasyOCR, and CRNN-CTC, as well as testing on a different analyzer dataset, shows the practical relevance of the proposed OCR workflow for digital television technical monitoring.
Comparative Analysis of the SMART, TOPSIS, and MOORA Methods for Determining Village Fund Direct Cash Assistance Recipients Ida Widaningrum; Ali Nur Wakhid; Jamilah Karaman
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.v15i2.1502

Abstract

Indonesia’s poverty is still a structural problem with a rate of around 9.36 percent as of March 2023. The government gave Village Fund Direct Cash Assistance (BLT-DD) based on PMK Number 190/PMK.07/2021 Article 33. Paragraph one. So far, different Multi-Criteria Decision Making (MCDM) techniques have been used for the selection of BLT-DD recipients, but none of them has been tested for their consistency using the same dataset. This study compared three MCDM approaches on 25 potential BLT-DD recipients in Plosokerep Hamlet, Dukuh Village, Magetan Regency, using six criteria of PMK 190/PMK.07/2021 with weights determined by the Village Head. The three approaches were Simple Multi-Attribute Rating Technique (SMART), Technique for Order Preference by Similarity to Ideal Solution (TOPSIS), and Multi-Objective Optimisation on the basis of Ratio Analysis (MOORA). We used Spearman Rank Correlation, Kendall Tau and Jaccard Similarity to compare the consistency of the top 16 processes. The Spearman SMART-TOPSIS 0.92, SMART-MOORA 0.95 and TOPSIS-MOORA 0.98 values were found to be highly consistent. Thirteen of the sixteen quotas were agreed upon by all three techniques, with the top three ranks consistent. TOPSIS and MOORA obtained almost the same rankings due to the same vector normalisation, whereas SMART with linear normalisation shows a more evident differentiation at the extreme profiles. This paper presents a multi-method consensus solution to improve the dependability of BLT-DD recipient selection.
ThinkDeeper Web Coach: A Literature-Informed Design Specification for Process-Visible Reasoning in Problem-Solving-Intensive Information Technology Courses Rafli Arrasyid; Nuur Wachid Abdul Majid
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.v15i2.1504

Abstract

Information technology education increasingly requires students to demonstrate how they reason while generative tools can produce plausible code, queries, and explanations with little visible evidence of the learner's own computational thinking. This study aimed to design ThinkDeeper Web Coach, a process-visible learning artifact for problem-solving-intensive IT courses that requires structured reasoning before direct solution support is accessed. A literature-informed design and development approach was applied to academic records indexed in Semantic Scholar and OpenAlex. The evidence corpus comprised 500 records published from 2023 to 2025, 130 records retained after abstract screening, 53 full texts assessed, and 51 studies included after full-text screening and extraction. The synthesis produced the Process-Visible Learning Design Framework, eight evidence-linked design requirements, and six integrated modules: Answer Delay Gate, Coach Chat, Evidence Drawer, Depth Analytics, Learning Circle, and Resource Recommendation. The revised specification defines applicable course contexts, operational dimensions of depth of thinking, a hybrid reference architecture, server-side gate and guardrail mechanics, trace data objects, and a staged evaluation protocol. ThinkDeeper is presented as a theoretically and empirically justified design specification that still requires expert review, usability testing, trace validation, and classroom pilot evaluation before effectiveness claims can be made.
A Hybrid Transformer-Based System for Multilingual Translation with Domain-Specific Terminology Explanation Oyebamiji Micheal Tomiwa
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.v15i2.1506

Abstract

Communication across languages becomes particularly challenging when specialized terminology is involved because literal translations often fail to convey the precise meanings essential in professional contexts. Current translation systems have problems with translating technical terms from specific domains like law, medicine, or finance, such that they generate translations that lack explanations of what technical terms actually mean. This creates significant problems in professional settings where misunderstanding specialized vocabulary can have serious consequences. This research developed a hybrid transformer-based system that addresses these limitations by translating specialized terminology across legal, medical, and financial domains while providing contextual explanations in the target language. The system used two transformer models: Sentence-BERT to detect special terms and MarianMT to translate. Data collection involved extracting 7,100 specialized terms with definitions from authoritative sources, alongside 70,000 parallel sentence pairs for each of three language pairs: English-Spanish, English-French, and English-German. The CRISP-DM framework was used for development from problem definition to deployment. The English-Spanish model achieved 59.26 BLEU, English-French achieved 38.76 BLEU, and English-German achieved 25.68 BLEU. Term extraction achieved 92.8-96.5% average accuracy across domains, with perfect performance on exact matches and 79-94% accuracy on misspelled or incomplete terms.
Classification of Gram-Stained Microscopy Images of Bacteria Cultured on Multiple Media Using Frozen and Fine-Tuned ResNet-50 Transfer Learning: A Comparative Study Daniel Martomanggolo Wonohadidjojo; Lidya Handayani
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.v15i2.1507

Abstract

The accurate and rapid identification of pathogenic bacteria is critical in clinical microbiology for guiding appropriate antibiotic therapy and infection control. This study proposes an automated classification system for Gram-stained bacterial microscopy images representing four clinically significant Gram-negative pathogenic species — Enterobacter cloacae, Escherichia coli, Klebsiella pneumoniae, and Pseudomonas aeruginosa — cultivated on five different culture media: Blood Agar Plate (BAP), MacConkey agar (MAC), Mueller-Hinton agar (MHA), Mueller-Hinton broth (MHB), and Nutrient agar (NA), yielding a 20-class classification problem. A primary dataset of 166 images was collected from clinical isolates using a standardized Gram staining protocol and imaged at 1000× magnification using a Leica DM500 trinocular microscope. Two ResNet-50 transfer learning strategies were compared under stratified 5-fold cross-validation: Experiment A using a frozen ResNet-50 as a fixed feature extractor, and Experiment B using a fully fine-tuned ResNet-50. Experiment B (fine-tuned) outperformed Experiment A (frozen) overall, achieving mean accuracy of 0.5832 ± 0.1109 and macro F1-score of 0.5409 ± 0.1231 compared to 0.5601 ± 0.0603 and 0.5010 ± 0.0935 respectively. The highest per-class F1-score was 0.9333 for E. coli on MAC and MHA in both experiments. Culture medium type is identified as a key determinant of classification difficulty, with selective and differential media yielding superior results over non-selective general-purpose media. Although fine-tuning improved performance, the relatively small dataset size and moderate overall accuracy indicate that larger-scale validation is required before clinical deployment.
Optimization of Artificial Intelligence (AI) Dependency Level Classification Among Students Using Random Forest with SMOTE Oversampling Technique to Address Data Imbalance Hermanto; Riza Fahlapi; Antonius Yadi Kuntoro; Khoirul Rista Abidin
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.v15i2.1509

Abstract

The development of generative artificial intelligence (AI) has significantly transformed the way students complete academic tasks. Excessive reliance on AI has the potential to diminish students' creativity and independent thinking abilities. This study aims to classify the level of students' dependency on AI in relation to academic creativity using the Random Forest algorithm optimized with the Synthetic Minority Over-sampling Technique (SMOTE) to address class imbalance in the data. Data were collected through a structured questionnaire using a Likert scale of 1–5 consisting of 24 statement items from 74 student respondents at Politeknik 'Aisyiyah Pontianak, covering variables of AI usage intensity, dependency behavior, creativity, independent thinking, and academic motivation. Respondents were classified into three classes: Low (n=30), Moderate (n=19), and High (n=25). The results indicate that the Random Forest + SMOTE model evaluated with Cross Validation achieved an accuracy of 97.14% (±6.02%), a precision of 97.06% (micro average), and recall values of 100% for the Low class, 95.83% for the Moderate class, and 95.00% for the High class. The most dominant feature was the tendency to think of AI-generated answers when questioned by lecturers (B4, importance=0.1097), followed by AI usage intensity of more than 3 hours per day (A2, importance=0.0872). These findings contribute to the development of an early detection system for AI dependency among students in higher education institutions.

Page 36 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