cover
Article Per Year (5 Year)
All
Home Page
OAI Link
Editorial Team
Contact
Reviewer
Google Scholar
Contact Name
Eko Fajar Cahyadi
Contact Email
ekofajarcahyadi@ittelkom-pwt.ac.id
Phone
+6285384848666
Journal Mail Official
infotel@ittelkom-pwt.ac.id
Editorial Address
Lembaga Penelitian dan Pengabdian Masyarakat (LPPM) Institut Teknologi Telkom Purwokerto Jl. D. I. Panjaitan, No. 128, Purwokerto 53147, Indonesia
Location
Kota bandung,
Jawa barat
INDONESIA
Jurnal INFOTEL
Published by Universitas Telkom
ISSN : 20853688     EISSN : 24600997     DOI : https://doi.org/10.20895/infotel.v15i2
Core Subject : Science, Engineering,
Computer Science & IT Electrical & Electronics Engineering
Jurnal INFOTEL is a scientific journal published by Lembaga Penelitian dan Pengabdian Masyarakat (LPPM) of Institut Teknologi Telkom Purwokerto, Indonesia. Jurnal INFOTEL covers the field of informatics, telecommunication, and electronics. First published in 2009 for a printed version and published online in 2012. The aims of Jurnal INFOTEL are to disseminate research results and to improve the productivity of scientific publications. Jurnal INFOTEL is published quarterly in February, May, August, and November. Starting in 2018, Jurnal INFOTEL uses English as the primary language.
Arjuna Subject : Teknik (semua kategori) - Teknik (Lain-Lain)
Articles 500 Documents
 46   47   48   49   50 
Strategic Planning for Rice Seed Productivity Using Integration of modified TF-IDF and SWOT-QSPM Enci Mulyani; Ridho Ananda; Famila Dwi Winati
JURNAL INFOTEL Vol 18 No 1 (2026): February
Publisher : LPPM INSTITUT TEKNOLOGI TELKOM PURWOKERTO

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.20895/infotel.v18i1.1416

Abstract

The agricultural sector of Indonesia is dependent on the availability of highquality rice seeds for its functionality. The effective management of these seeds is therefore of paramount importance to ensure the continuity of productivity and the security of food supplies. However, the aspirations of farmers, who are the primary actors, are often ineffective and only available in an unstructured narrative form. This complicates the process of strategic decision-making. The objective of this study is to enhance rice seed productivity by developing a strategy that employs an integrative informatics approach, integrating text mining, SWOT analysis, and the QSPM method. The data was collected via 100 open-endedinterviews with farmers and processed through text cleansing, modified TF-IDF weighting, and token classification into SWOT factors. The classification results were then employed to construct IFAS and EFAS matrices, which were used to determine strategic positioning. The utilization of the QSPM matrix facilitated the identification of priority strategies. The analysis indicated that the seed aspect falls into quadrant IV, suggesting a predominance of weaknesses and threats, necessitating a defensive (WT) strategy. The primary strategy identified was the provision of superior seeds that are resistant to extreme weather; this strategy achieved the highest score in the QSPM analysis. The strategy’s feasibility level, as validated by three experts, exceeded 83%, thus categorizing it as "highly feasible." The present study concludes that integrating text mining techniques with SWOT-QSPM transforms opinion data into an objective, adaptable, and applicable decision-making strategy based on local data.
Socket-based File Transfer System using AES-256 and OTP Authentication Feni Widianti; Fauza Khair; Agung Mulyo Widodo; Eko Fajar Cahyadi
JURNAL INFOTEL Vol 18 No 1 (2026): February
Publisher : LPPM INSTITUT TEKNOLOGI TELKOM PURWOKERTO

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.20895/infotel.v18i1.1429

Abstract

The increasing risk of data interception during file transmission over open networks requires the development of secure communication systems. This study proposes a secure file transfer scheme that integrates the Advanced Encryption Standard (AES) with a 256-bit key and One-Time Password (OTP)-based authentication over socket programming. The system ensures that only verified users can transmit files by requiring password log-in and OTP verification via email. Upon successful authentication, files are encrypted using AES-256 before being transmitted over a TCP/IP socket connection. The implementation is carried out in Python using Visual Studio Code, with performance evaluated based on encryption time, transfer speed, and resistance to brute-force attacks. Various file types and sizes, including text, documents, images, audio, video, and compressed files, were tested to validate the robustness and efficiency of the system. The results show that the proposed system maintains high data integrity, enforces strong access control, and effectively resists unauthorized access, making it suitable for applications requiring secure file exchange.
45-nm feasibility A Comprehensive Review of SRAM Design Using Modified Gate Diffusion Input (MGDI) Erfiana Wahyuningsih; Ganjar Febriyani Pratiwi; Tri Nur Arifin
JURNAL INFOTEL Vol 18 No 1 (2026): February
Publisher : LPPM INSTITUT TEKNOLOGI TELKOM PURWOKERTO

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.20895/infotel.v18i1.1450

Abstract

This paper presents a systematic literature review on the feasibility and practicality of implementing Modified Gate Diffusion Input (MGDI) logic for a static random access memory(SRAM) design at the 45-nm technology node. The study consolidates prior simulation-based and analytical findings to evaluate MGDI as a low-power alternative to conventional CMOS in memory circuits. Results highlight that MGDI enables significant reductions in dynamic power consumption, particularly in peripheral circuits such as decoders and drivers, where switching activity dominates. Average leakage power was also reduced by approximately 20%, with up to a 40% reduction observed in stacked configurations, owing to the intrinsic characteristics of MGDI structures. Stability analysis indicated that hold Static Noise Margin (SNM) remained comparable to CMOS cells, while read SNM improved by 5–10% due to the stacking effect and the use of swing-restoration transistors. A moderate delay penalty of about 10% was identified at the bit-cell level, but the difference was offsetby faster operation in MGDI-based peripheral circuits, resulting in improved energy-delay efficiency overall. Importantly, MGDI can be fabricated using standard CMOS processes without requiring exotic modifications, demonstrating practical compatibility. These findings suggest that MGDI is a promising candidate for ultra-low-power memory applications, particularly in Internet of Things (IoT) and energy-harvesting devices.
LLM-Based Interview Bot for Student Big Five Assessment and Career Recommendation Sang Dara Parameswari; Muharman Lubis; Sinung Suakanto; Jan M. Pawlowski
JURNAL INFOTEL Vol 18 No 1 (2026): February
Publisher : LPPM INSTITUT TEKNOLOGI TELKOM PURWOKERTO

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.20895/infotel.v18i1.1456

Abstract

The development of Artificial Intelligence (AI) and Natural Language Processing (NLP) offers new opportunities to make psychological assessments more interactive and meaningful. However, personality tests such as the International Personality Item Pool – Big Five Factor Markers (IPIP-BFM-50) still rely on static self-report questionnaires, which may limit engagement and contextual interpretation. This study proposes an InterviewBot-based Big Five Personality system (IB-B5P) that combines rule-based IPIP scoring with Large Language Model (LLM)-driven conversational assessment using GPT-3.5 Turbo. The system generates both quantitative personality scores and qualitative narrative profiles. Evaluation results show moderate to strong correlations (r = 0.31–0.71) between IB-B5P and IPIP scores, with Openness and Extraversion showing statistically significant relationships. These findings suggest that the hybrid rule–LLM approach can approximate IPIP tendencies while providing richer context-aware interpretations. The novelty of this study lies in integrating LLM-based conversational intelligence with a standardized psychometric framework, with potential applications in career guidance, educational counseling, and digital psychological assessment in higher education.
Implementation of MobileNetV2 Transfer Learning for Chicken Egg Quality Classification Using Jetson Nano Dita Novita Sari; Panji Andhika Pratomo; Yoeyong Rahsel; Akhmad Jayadi; Dwi Ely Kurniawan
JURNAL INFOTEL Vol 18 No 1 (2026): February
Publisher : LPPM INSTITUT TEKNOLOGI TELKOM PURWOKERTO

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.20895/infotel.v18i1.1499

Abstract

Eggs are an important source of animal protein and are widely consumed by the public. However, quality issues such as cracked or broken eggs are still frequently encountered during distribution and storage. Egg quality sorting has been largely done manually, making it prone to human error, time-consuming, and inconsistent. This study aims to develop a deep learning-based egg quality classification system with a transfer learning approach using the MobileNetV2 architecture that is efficient for devices with limited computing capacity. The research method involves acquiring egg image datasets (good and broken), preprocessing data with normalization and augmentation, designing a MobileNetV2 model, conducting two-stage training (feature extraction and fine-tuning), and evaluating model performance. Implementation was carried out both in the development environment and on a Jetson Nano edge computing device to test real-time application. The results showed that training with fine-tuning increased classification accuracy to 92% with an average precision, recall, and F1-score of 0.95. Confusion matrix evaluation demonstrated the model's ability to distinguish egg classes well, although there were still small errors in the classification of "good" eggs. Implementation on the Jetson Nano demonstrated relatively fast inference times (50–70 ms) with low resource consumption, demonstrating the system's applicability at both farm and small-to-medium scale distribution. This research successfully presented an accurate, lightweight, and practically implementable egg classification model as a first step towards automating the egg sorting process in the livestock industry. Implementasi pada Jetson Nano menunjukkan waktu inferensi yang relatif cepat (50–70 ms) dengan konsumsi sumber daya yang rendah, menunjukkan penerapan sistem pada pertanian dan distribusi skala kecil hingga menengah.
Student Emotion Recognition from Low-Quality Videos Using Multimodal Deep Learning ANDI MAWADDA TAIBA MAWADDA TAIBA; Rizki Yusliana Bakti; Muhammad Faisal; Muhammad Syafaat S. Kuba; Lukman Anas; Emil Agusalim H. T; Fahrim I. Rahman
JURNAL INFOTEL Vol 18 No 1 (2026): February
Publisher : LPPM INSTITUT TEKNOLOGI TELKOM PURWOKERTO

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.20895/infotel.v18i1.1523

Abstract

Emotion recognition plays a critical role in intelligent e-learning systems by enabling adaptive feedback and timely pedagogical interventions based on students’ affective states. However, most existing approaches rely heavily on visual facial cues, which are highly vulnerable to real-world conditions such as low-resolution video, partial facial occlusion, poor lighting, and unstable network connections commonly encountered in online learning environments. These limitations significantly degrade the performance of unimodal deep learning models. To address this challenge, this study proposes a multimodal deep learning framework for student emotion recognition that is robust to low-quality and occluded video input. The proposed model integrates visual and audio modalities through a hybrid architecture, combining a lightweight CNN-based visual feature extractor with a BiLSTM-based speech emotion model. An attention-based fusion mechanism is employed to adaptively weight cross-modal features, allowing the system to compensate for degraded or missing visual information using complementary acoustic cues. Experimental evaluations are conducted using publicly available datasets representative of realistic online learning scenarios, including DAiSEE and RAVDESS, with additional augmentation to simulate varying levels of occlusion and video degradation. The results demonstrate that the multimodal approach consistently outperforms unimodal baselines, particularly under high occlusion conditions, while maintaining computational efficiency suitable for near real-time deployment. These findings confirm that multimodal fusion with attention mechanisms provides a more resilient and practical solution for emotion-aware e-learning systems operating under non-ideal input conditions
Robust Facial Classification of Down Syndrome using Lightweight CNNs Yunidar Wahab; Muhammad Dika Rafi Kasha; Melinda Melinda; Nurlida Basir; Siti Rusdiana
JURNAL INFOTEL Vol 18 No 1 (2026): February
Publisher : LPPM INSTITUT TEKNOLOGI TELKOM PURWOKERTO

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.20895/infotel.v18i1.1525

Abstract

Down Syndrome (DS) is a genetic disorder caused by trisomy 21 and is characterized by distinctive facial features that can support early screening. However, access to conventional diagnostic tools remains limited, particularly in resource-constrained regions. This study presents a comparative evaluation of two lightweight convolutional neural network (CNN) architectures, EfficientNet-B1 and MobileNetV3-Large, for facial image-based DS classification. A curated dataset of 3,030 facial images underwent quality control and image enhancement processes applied exclusively to the training data, resulting in 2,620 images. The dataset was split into training, validation, and test sets at a 70:20:10 ratio. Both models were fine-tuned using ImageNet-pretrained weights and evaluated based on accuracy, precision, recall, and F1-score. Performance robustness and statistical significance between models were assessed using five-fold cross-validation and one-way ANOVA. The experimental results demonstrate that both architectures achieved high classification performance; however, EfficientNet-B1 exhibited superior stability, more balanced class predictions, and lower fold-to-fold variability. Furthermore, Grad-CAM visualization confirmed that both models focused on clinically relevant facial regions, with EfficientNet-B1 showing more consistent and interpretable attention patterns. These findings suggest that EfficientNet-B1 is a robust and interpretable model for facial-based DS screening, offering significant potential for deployment in resource-limited healthcare settings.
Classification of H2O with HCl and H2O with NaOH Solution Images Using Otsu Segmentation and CNN Mauliza Putri; Melinda Melinda; Siti Rusdiana; Aufa Rafiki; Lailatul Qadri Zakaria
JURNAL INFOTEL Vol 18 No 2 (2026): May
Publisher : LPPM INSTITUT TEKNOLOGI TELKOM PURWOKERTO

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.20895/infotel.v18i2.1541

Abstract

The classification of the image of chemical solutions is crucial in laboratory automation and chemical industry applications; however, it remains challenging when solutions such as H2O with HCl and H2O with NaOH exhibit nearly identical visual characteristics under imaging conditions, particularly when their spectral fluctuation patterns are visually subtle. This study proposes an image classification framework that integrates Otsu-based segmentation in the HSV color space with convolutional neural network (CNN) models to classify High Height Fluctuation (HHF) images generated from a Multi-Scale chemical detection system (MSCS). The dataset consists of 102 HHF images, evenly distributed between the two solution classes. Transfer learning is applied using three CNN architectures, namely EfficientNetV2S, DenseNet201, and EfficientNetB0, and performance is evaluated using accuracy, precision, recall, F1-score, and confusion matrix analysis. The experimental results show that DenseNet201 achieves the best overall performance, while EfficientNetV2S provides competitive results with computational efficiency and Efficient-NetB0 yields a lighter model with lower recall. These findings indicate that combining segmentation with modern CNN architectures can effectively improve classification robustness in chemically similar solutions. This study presents a practical framework that combines Otsu-based HSV segmentation with transfer-learning CNNs to classify chemically similar solutions, providing actionable insights for deep learning-based chemical sensing applications.
A Mathematical Model for Blockchain Adoption in High-Risk Asset Management Miftahol Arifin; Elisa Kusrini; Winda Nur Cahyo; Imam Djati Widodo
JURNAL INFOTEL Vol 18 No 2 (2026): May
Publisher : LPPM INSTITUT TEKNOLOGI TELKOM PURWOKERTO

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.20895/infotel.v18i2.1544

Abstract

This study develops and empirically validates a mathematical adoption model for blockchain-based information systems using an Extended Unified Theory of Acceptance and Use of Technology (UTAUT) framework. Previous blockchain adoption studies predominantly assessed behavioral determinants through isolated hypothesis testing, with limited efforts to integrate contextual factors into a unified structural model. To address this gap, the proposed framework incorporates blockchain-specific and organizational constructs, including trust and perceived security, operational resilience expectation, technology adaptability, and regulatory compliance, along with the core UTAUT dimensions. A quantitative, explanatory, and cross-sectional design was employed using Partial Least Squares Structural Equation Modeling (PLS-SEM) to estimate model parameters from survey data collected from 132 professionals operating in high-risk power plant asset management environments. The model explains 68.9% of the variance in behavior intention and 42.0% of actual system use. Trust and perceived security emerged as the strongest predictor of behavioral intention, followed by performance expectation and operational resilience expectation. The findings demonstrate the suitability of Extended UTAUT for mathematically representing the adoption behavior of blockchain in high-risk organizational settings and provide a transferable analytical framework for future studies of the adoption of blockchain-based information systems.
A Comparative Analysis of YOLOv5 and YOLOv8 for Watermelon Sweetness Prediction Based on Their Field-Spot Rahmad Dawood; Maya Fitria; Muhammad Hafez Al-Assad; Yudi Candra; Silvia Roza
JURNAL INFOTEL Vol 18 No 2 (2026): May
Publisher : LPPM INSTITUT TEKNOLOGI TELKOM PURWOKERTO

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.20895/infotel.v18i2.1319

Abstract

Despite its popularity and high demand in the market, determining the sweetness and ripeness of watermelon remains difficult. Traditionally, ripe and sweet watermelon is identified by visual inspection of its weight, tapping sound, and visual characteristics such as color and field spot, which indicate its maturity time on the vine. However, this inspection method is frequently viewed as subjective, time-consuming, and prone to error. The objective of this research is to use an object identification algorithm to classify the sweetness level of watermelon based on its field spot, leading to a more precise and consistent evaluation. The architectures used in this study were YOLOv5 and YOLOv8. Both models were developed using 333 watermelon image data, which were categorized into two categories: sweet and non-sweet. The evaluation is carried out by contrasting the performance of both models concerning the values of precision, recall, and mean absolute performance (mAP 50 and mAP 50-90). The findings indicated that the YOLOv5 outperformed the YOLOv8 in determining the sweetness level of the watermelon, with mAP 50 values of 85.3\% and 81.9\%, respectively. Moreover, in contrast to YOLOv5, YOLOv8 necessitated an extensive training period.

Page 50 of 50 | Total Record : 500

 46   47   48   49   50 

Filter by Year

2009 2026


Reset
Filter By Issues
All Issue Vol 18 No 2 (2026): May Vol 18 No 1 (2026): February Vol 17 No 1 (2025): February 2025 Vol 17 No 4 (2025): November Vol 17 No 3 (2025): August Vol 17 No 2 (2025): May Vol 16 No 4 (2024): November 2024 Vol 16 No 3 (2024): August 2024 Vol 16 No 2 (2024): May 2024 Vol 16 No 1 (2024): February 2024 Vol 15 No 4 (2023): November 2023 Vol 15 No 3 (2023): August 2023 Vol 15 No 2 (2023): May 2023 Vol 15 No 1 (2023): February 2023 Vol 14 No 4 (2022): November 2022 Vol 14 No 3 (2022): August 2022 Vol 14 No 2 (2022): May 2022 Vol 14 No 1 (2022): February 2022 Vol 13 No 4 (2021): November 2021 Vol 13 No 3 (2021): August 2021 Vol 13 No 2 (2021): May 2021 Vol 13 No 1 (2021): February 2021 Vol 12 No 4 (2020): November 2020 Vol 12 No 3 (2020): August 2020 Vol 12 No 2 (2020): May 2020 Vol 12 No 1 (2020): February 2020 Vol 11 No 4 (2019): November 2019 Vol 11 No 3 (2019): August 2019 Vol 11 No 2 (2019): May 2019 Vol 11 No 1 (2019): February 2019 Vol 10 No 4 (2018): November 2018 Vol 10 No 3 (2018): August 2018 Vol 10 No 2 (2018): May 2018 Vol 10 No 1 (2018): February 2018 Vol 9 No 4 (2017): November 2017 Vol 9 No 3 (2017): August 2017 Vol 9 No 2 (2017): May 2017 Vol 9 No 1 (2017): February 2017 Vol 8 No 2 (2016): November 2016 Vol 8 No 1 (2016): May 2016 Vol 7 No 2 (2015): November 2015 Vol 7 No 1 (2015): May 2015 Vol 6 No 2 (2014): November 2014 Vol 6 No 1 (2014): May 2014 Vol 5 No 2 (2013): November 2013 Vol 5 No 1 (2013): May 2013 Vol 4 No 2 (2012): November 2012 Vol 4 No 1 (2012): May 2012 Vol 3 No 2 (2011): November 2011 Vol 3 No 1 (2011): May 2011 Vol 2 No 2 (2010): November 2010 Vol 2 No 1 (2010): May 2010 Vol 1 No 2 (2009): November 2009 Vol 1 No 1 (2009): May 2009 More Issue