cover
Article Per Year (5 Year)
All
Home Page
OAI Link
Editorial Team
Contact
Reviewer
Google Scholar
Contact Name
Arie Vatresia
Contact Email
arie.vatresia@unib.ac.id
Phone
+6282179370950
Journal Mail Official
arie.vatresia@unib.ac.id
Editorial Address
Jalan W.R. Supratman gang Cipta Baru no. 12 RT/RW 19/01 Talang Kering
Location
Kota bengkulu,
Bengkulu
INDONESIA
Jurnal Pseudocode
Published by Universitas Bengkulu
ISSN : 23555920     EISSN : 26551845     DOI : https://doi.org/10.33369
Core Subject : Science, Engineering,
Computer Science & IT Control & Systems Engineering Decision Sciences, Operations Research & Management Electrical & Electronics Engineering
Pseudocodeis a scientific journal in the information science family that contains the results of informatics research, scientific literature on informatics, and reviews of the development of theories, methods, and application of informatics engineering science. Pseudocode is published by the Informatics Study Program, Faculty of Engineering, University of Bengkulu. Editors invite researchers, practitioners, and students to submit article manuscripts in the field of informatics engineering. Pseudocode is published 2 (two) times a year in February and September with p-ISSN 2355-5920 e-ISSN 2655-1845. Jurnal Pseudocode is Accredited by the Ministry for Research, Technology and Higher Education (RISTEKDIKTI) in SINTA 4 No. 36/E/KPT/2019 since 13 December 2019.
Arjuna Subject : Ilmu Komputer (semua kategori) - Ilmu Komputer (Lain-Lain)
Articles 220 Documents
 18   19   20   21   22 
Komparasi Model Deep Learning untuk Klasifikasi Jenis Eyelash Extension Menggunakan Citra Digital Anggitha Sindy Kurnia Aprillia; Abd. Hadi
Jurnal Pseudocode Vol 13 No 2 (2026): Volume 13 Nomor 2 September 2026
Publisher : UNIB Press

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.33369/pseudocode.13.2.108-116

Abstract

High interest in eyelash extension services at Le'Goub Beauty is accompanied by challenges in visual perception between clients and therapists, which affect the consistency of final results. This study compares three deep learning models: a basic CNN, MobileNetV2, and EfficientNet-B0. The comparison is used to classify three types of eyelash extensions (anime, natural, and volume) from 662 internal salon images, using a stratified k-fold cross-validation scheme (K=5) along with a two-phase training approach (freezing and fine-tuning) and the Adam optimizer. The basic CNN, without transfer learning, produces low and unstable performance (36.02% accuracy, SD 11.98%), with a tendency toward bias for the anime class. Applying transfer learning improves performance considerably: MobileNetV2 achieves a higher average accuracy of 82.59% (SD 2.65%), slightly above EfficientNet-B0's 80.95%, though EfficientNet-B0 shows greater stability (SD 1.76%). Both models perform consistently in the anime class but continue to have difficulty distinguishing between the natural and volume classes due to their visual similarity. MobileNetV2 is recommended as the primary model for Le'Goub Beauty, with EfficientNet-B0 as an alternative in scenarios where consistency is a priority. Keywords: Deep learning; EfficientNet-B0; MobileNetV2; image classification; eyelash extension.
Motіon graрhісs Motіon graрhісs рada medіa рembelajaran self resсue berbasіs androіd untuk anak tunagrahіta rіngan hingga sedang рada materі mengamankan dіrі darі benda-benda berbahaуa (Studi Kasus: SLB Negeri 1 Kota Bengkulu): (Studi Kasus: SLB Negeri 1 Kota Bengkulu) Ejiman Saputra; Desi Andreswari; Widhia KZ Oktoeberza
Jurnal Pseudocode Vol 13 No 2 (2026): Volume 13 Nomor 2 September 2026
Publisher : UNIB Press

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.33369/pseudocode.13.2.124-130

Abstract

Children with mild to moderate intellectual disabilities experience cognitive constraints that limit their ability to identify, assess, and avoid hazardous objects in their surrounding environment, thereby increasing their vulnerability to accidents both in school settings and everyday activities. This condition highlights the urgent need for learning media that are not only safe and developmentally appropriate but also engaging and visually supportive to strengthen self-rescue competencies. This study aims to develop and evaluate the effectiveness of an Android-based self-rescue learning medium incorporating motion graphics animation focused on self-protection from dangerous objects. The research adopted a Research and Development (R&D) approach using the Multimedia Development Life Cycle (MDLC) model. The participants consisted of 28 phase D students with mild to moderate intellectual disabilities at SLB Negeri 1 Bengkulu City. Application effectiveness was measured through pre-test and post-test scores analyzed using the Wilcoxon signed-rank test. The findings revealed a statistically significant improvement in students’ understanding after the intervention, with a significance value of 0.01 (<0.05). These results confirm that the developed media effectively enhances students’ ability to recognize and protect themselves from sharp, pointed, slippery, and hot objects. Keywords: Android; Dangerous Objects; Mild Intellectual Disability; Motion Graphics; Self-Rescue.
Implementasi Metode Adaptif Neuro-Fuzzy Inference System (ANFIS) Dalam Sistem Pakar Prediksi Risiko Diabetes Mellitus Tipe II Ratna Yanti Simbolon; Desi Andreswari; Julia Purnama Sari; Ester Morina Silalahi
Jurnal Pseudocode Vol 13 No 2 (2026): Volume 13 Nomor 2 September 2026
Publisher : UNIB Press

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.33369/pseudocode.13.2.131-141

Abstract

Type 2 Diabetes Mellitus (T2DM) is frequently undetected at an early stage because its symptoms develop gradually. Therefore, an accessible risk-screening method is needed to support early awareness and further medical examination. This study developed an Adaptive Neuro-Fuzzy Inference System with a Takagi-Sugeno-Kang structure for three-class T2DM risk prediction using eight non-laboratory health indicators from the Behavioral Risk Factor Surveillance System dataset. After conflict removal, 65,369 records were divided into stratified training, validation, and testing sets. SMOTENC was applied only to the training set to reduce class imbalance. To provide a fair evaluation, ANFIS was compared with Logistic Regression, Decision Tree, Random Forest, XGBoost, Linear Support Vector Machine, Multilayer Perceptron, and a majority-class predictor under the same experimental protocol. Macro-F1 was used as the primary evaluation metric because of the severe class imbalance. A sensitivity analysis of Top-K values of 128, 256, and 512 were also conducted, and permutation importance was used to examine the contribution of each input variable. The final ANFIS model using Top-K = 128 achieved an accuracy of 84.18%, a Macro-F1 of 48.59%, a weighted F1-score of 88.06%, and a balanced accuracy of 62.85%. Random Forest achieved the highest Macro-F1 of 50.98%, indicating that ANFIS did not outperform the strongest baseline in overall class-balanced performance. However, ANFIS achieved the highest balanced accuracy and the highest prediabetes recall among the evaluated models. BMI, GenHlth, and Age were the most influential variables according to permutation importance. The selected model was implemented in a Django-based web expert system as a preliminary risk-screening prototype rather than a medical diagnostic tool. Keywords: ANFIS, Type 2 Diabetes Mellitus, Expert System, Risk Prediction
Web-Based OBE Learning Assessment System with Rule-Based Student Profile Mapping Intan Budiarty; Endina Putri Purwandari; Andang Wijanarko
Jurnal Pseudocode Vol 13 No 2 (2026): Volume 13 Nomor 2 September 2026
Publisher : UNIB Press

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.33369/pseudocode.13.2.142-149

Abstract

This study is motivated by the implementation of the Outcome-Based Education (OBE) curriculum in the Information Systems Study Program at the University of Bengkulu, which still faces operational challenges due to managing Graduate Learning Outcomes (PLO) and Course Learning Outcomes (CLO) through manual spreadsheet-based tracking. This localized workflow is prone to entry errors, lacks collaborative environments, and fails to systematically trace high-level structural insights from raw continuous academic marks. This research aims to design and develop a web-based automated evaluation ecosystem called Acapela that provides centralized tracking of PLO-CLO matrices, incorporates interactive diagram visualization components, and deploys a predictive analytics feature using a rule-based inference mechanism. The development uses a modified Research and Development (R&D) strategy incorporating qualitative methods via deep institutional observation and stakeholder interviews alongside quantitative validation using systematic User Acceptance Testing (UAT) evaluated via five-point Likert scales. The empirical testing demonstrates that the Acapela platform effectively manages centralized configurations, executes automated curriculum-linked score aggregations, maps multidimensional outputs via radar charts, and successfully resolves multi-criteria decision steps to yield student profile predictions classified into five granular performance bands. Software correctness was fully verified through automated black-box scenarios, while field utility metrics achieved an overall viability rate of 87.05% from operational user groups, denoting high feasibility for strategic deployment. Keywords: Academic analytics; Automated evaluation; Information systems curriculum; Outcome-Based Education; Web-based application.
Design and Usability Evaluation of the SkinPal Facial Skin Type Detection Application Prototype Using Figma and Modified SUS Ika Jihan Pratiwi; Dewi Purnamasari
Jurnal Pseudocode Vol 13 No 2 (2026): Volume 13 Nomor 2 September 2026
Publisher : UNIB Press

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.33369/pseudocode.13.2.117-123

Abstract

The development of digital applications in the beauty and healthcare fields requires a user interface that is not only visually attractive but also easy to use and comfortable for users. This study aims to design and evaluate the user interface of the SkinPal facial skin type detection application using Figma. The research stages consisted of literature review, requirement analysis, interface design using Figma, prototype development, usability testing, data analysis, and conclusion. The interface was designed based on user needs to support facial skin type detection and assist users in selecting appropriate skincare digitally. The data analysis results showed that the mean score for the indicator display is easy to understand and informative was 3.85, icons are easy to understand was 4.05, display consistency was 4.10, and overall user experience was 3.90. These results indicate that respondents gave positive assessments of the SkinPal interface. Usability testing was conducted involving 20 respondents using a Likert-scale questionnaire. Since all questionnaire items were positive statements, the data were analyzed using the Modified System Usability Scale (SUS) method. The results showed that the SkinPal prototype obtained an average SUS score of 73.25, with a minimum score of 30.00, a maximum score of 100.00, and a standard deviation of 18.16. The average score indicates that the SkinPal user interface is categorized as Acceptable and classified as Good. These findings show that the proposed interface is feasible to use, easy to understand, and suitable for supporting facial skin type detection. However, improvements are still needed in navigation clarity, instruction readability, button visibility, and visual consistency. Future research is recommended to develop the prototype into a functional mobile application integrated with automatic facial skin type detection.Bottom of Form Keywords: user interface, Figma, usability testing, System Usability Scale, facial skin type detection, SkinPal.
Optimalisasi Layanan Administrasi Publik Melalui E-Government (Government To Citizen): Studi Perancangan dan Evaluasi Kinerja pada Kelurahan Padang Jati, Kota Bengkulu Thesa Febriani; Yusran Panca Putra; Willi Novrian
Jurnal Pseudocode Vol 13 No 2 (2026): Volume 13 Nomor 2 September 2026
Publisher : UNIB Press

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.33369/pseudocode.13.2.177-184

Abstract

The transformation of e-government-based public services at the smallest government unit is a main pillar in realizing efficient and transparent governance. However, Kelurahan Padang Jati still faces challenges in the form of manual bureaucracy that triggers risks of data redundancy, time inefficiency, and limited validity of physical documents. This study aims to develop a web-based administrative service information system (Government-to-Citizen) using the Design Science Research Methodology (DSRM) framework and empirically evaluate its performance quality through the E-GovQual model. The design phase was modeled using Use Case and Activity Diagrams, followed by program code development and functionality testing using the black-box testing method. The pre-implementation performance evaluation was conducted by distributing questionnaires to 100 respondents, determined through Slovin's formula calculation and selected using the purposive sampling technique, which were then analyzed using multiple linear regression. The functional testing results showed a 100% technical success rate after passing the debugging phase on the document validation aspect. The inferential statistical analysis results proved that the dimensions of efficiency, trust, reliability, and citizen support simultaneously have a significant effect on community satisfaction  with a model contribution of 59.8%. Partially, the Trust dimension became the most dominant predictor in shaping user satisfaction  These findings indicate that the integration of digital security features plays a crucial role in building trust and driving community acceptance of public administration technology at the kelurahan level.   Keywords: Design Science Research Methodology; Electronic Signature; E-GovQual; Government-to-Citizen; Kelurahan Administration.
Human-in-the-Loop Request-Response Access Control for Mobile Smart School Information Systems: A TAM Evaluation Muhamad Irfan; Herbert Siregar; Ani Anisyah
Jurnal Pseudocode Vol 13 No 2 (2026): Volume 13 Nomor 2 September 2026
Publisher : UNIB Press

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.33369/pseudocode.13.2.150-163

Abstract

Digital transformation in Islamic boarding schools (pesantren) presents a distinctive information-governance challenge because parental demands for access to students' academic information must coexist with institutional policies, teacher verification processes, and restricted student use of personal mobile devices. Existing educational information systems generally provide either role-based access without approval workflows or fragmented monitoring services, while structured authorization mechanisms incorporating professional human judgment remain insufficiently explored in this context. This study proposes a mobile-based Smart School Information System that introduces a Human-in-the-Loop Request–Response access control mechanism to regulate parental access to sensitive academic information while preserving institutional governance. The system was developed using a Research and Development (R&D) approach integrated with a prototyping methodology, employing Flutter as the cross-platform mobile framework and Laravel as the REST API backend with Laravel Sanctum token-based authentication. Functional performance was evaluated through Black Box Testing comprising 45 role-based scenarios, with seven critical scenarios reported in detail, while user acceptance was assessed using the Technology Acceptance Model (TAM) involving 59 respondents representing parents, teachers, homeroom teachers, ustadz, and school administrators. The 45 role-based functional test scenarios achieved a 100% success rate, indicating that the implemented functions operated according to their specified requirements. TAM analysis revealed that Perceived Usefulness (β = 0.390, p < 0.001), Perceived Ease of Use (β = 0.324, p < 0.001), and Attitude Toward Using (β = 0.308, p = 0.002) significantly influenced Behavioral Intention to Use, with a coefficient of determination (R²) of 0.734. These findings demonstrate positive user acceptance of the implemented system and confirm that the Request–Response authorization workflow operated according to its specified functional rules. The results provide functional and user-acceptance evidence for the implementation of the proposed mechanism in the studied pesantren context, rather than establishing the broader effectiveness of the mechanism in balancing information privacy and institutional governance. This study contributes a Human-in-the-Loop Request–Response authorization framework that extends conventional Role-Based Access Control (RBAC) by incorporating structured human decision-making into educational information systems. Keywords: Flutter; Human-in-the-Loop; Request–Response Access Control; Smart School; Technology Acceptance Model
Rancang Bangun Platform WebGIS Direktori dan Promosi UMKM Kuliner Menggunakan Metode R&D dan Content-Based Filtering Adrian Mulianto; Herbert Siregar; Ani Anisyah
Jurnal Pseudocode Vol 13 No 2 (2026): Volume 13 Nomor 2 September 2026
Publisher : UNIB Press

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.33369/pseudocode.13.2.164-176

Abstract

Culinary Micro, Small, and Medium Enterprises (MSMEs) around Universitas Pendidikan Indonesia (UPI) face challenges in digital promotional visibility, while the academic community experiences information overload. This study aims to design and implement a WebGIS platform for culinary directories and promotion using the Research and Development (R&D) method with the ADDIE model. The platform integrates a Content-Based Filtering (CBF) algorithm that processes users’ explicit and implicit preference data via Weighted Category Scoring, a 50% Spillover Effect, and a 4-3-3 proportional allocation pattern. The resulting WebGIS platform features interactive Leaflet.js mapping, OSRM Live Tracking route navigation, and crowdsourcing, achieving a 100% pass rate in Black Box testing across 17 modules. Computational evaluation of the CBF algorithm using scenario-based state-transition testing and sensitivity analysis covered 10 sessions, three sequential checkpoints, and nine configurations, resulting in 270 evaluation runs. The evaluation produced Precision@10 values of 97.00%, 2.56%, and 90.78% at Checkpoints A, B, and C, respectively, while accumulated interactions at Checkpoint C achieved a new-category adoption rate of 90.37%. Usability evaluation involving 30 primary end-users via the USE Questionnaire resulted in a TCR of 90.62% (Very Good). Furthermore, the User Experience Questionnaire (UEQ) administered to 27 valid respondents revealed that all six scales (Attractiveness: 1.98, Perspicuity: 2.15, Efficiency: 1.98, Dependability: 1.77, Stimulation: 1.66, Novelty: 1.66) achieved an Excellent benchmark rating. Keywords: Content-Based Filtering; Culinary MSMEs; Research and Development; User Experience Questionnaire; WebGIS.
Klasifikasi Video Berisi Bahasa Kasar Berbasis Deep Learning Muhammad Asep Suhanda; Ryan Ari Setyawan; Yumarlin MZ
Jurnal Pseudocode Vol 13 No 2 (2026): Volume 13 Nomor 2 September 2026
Publisher : UNIB Press

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.33369/pseudocode.13.2.185-195

Abstract

The growing popularity of social media has made it simpler for videos with strong or offensive language to spread quickly, which has led to a need for automatic tools to find and group this type of content. This study uses deep learning to identify videos with harsh language by looking at their visual, audio, and text parts using a detailed method that covers all these aspects. The model uses EfficientNetB0 to get visual features, a CNN to handle audio features from spectrogram images, and an Embedding layer along with a BiGRU to deal with text information. These three types of features are combined using an Adaptive Multimodal Fusion technique and then sorted into categories with the help of a Deep Neural Network (DNN). The final dataset includes 1,473 videos, with 738 videos marked as Harsh and 735 videos marked as Safe. The model is trained using the Adam optimizer and Binary Crossentropy loss function, and it also uses label smoothing. For evaluation purposes, 295 videos were used, which included 148 Harsh videos and 147 Safe videos. The model's accuracy was 83%, and it had average precision, recall, and F1-score values of 0.83 each. The model also achieved an ROC-AUC score of 0.8686, showing it can effectively tell the difference between the two types of videos. These results show that the new deep learning method that uses multiple types of data can work well in identifying harsh language in videos by combining visual, audio, and text information, and it can help with automatically checking and managing video content. Keywords: Deep Learning, Video Classification, EfficientNetB0, Adaptive multimodal fusion, Harsh Language
Pengaruh Usability Berdasarkan ISO 9241-11 Terhadap Kepuasan Pengguna pada Sistem Informasi Manajemen Arsip Administrasi dan Keuangan Meisy Dianita; Andang Wijanarko; Endina Putri Purwandari
Jurnal Pseudocode Vol 13 No 2 (2026): Volume 13 Nomor 2 September 2026
Publisher : UNIB Press

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.33369/pseudocode.13.2.196-206

Abstract

The development of information technology encourages organizations to develop information systems capable of providing user satisfaction. The Information Systems Student Association (ISSA) at the University of Bengkulu still manages administration and finance using Google Drive and basic Google Sheets, resulting in unintegrated archive management, inefficient document search processes, and manual financial recording that is not yet capable of generating automated financial reports. This condition indicates the need for a web-based management information system capable of integrating the management of administrative and financial archives in a structured manner. This study aims to design, develop, evaluate the system's usability, and analyze the effect of usefulness, ease of use, and ease of learning on satisfaction. The usability evaluation involved 148 respondents referring to ISO 9241-11 using the USE Questionnaire to measure users' satisfaction levels. Then, Generalized Structured Component Analysis (GSCA) was used as the method for analyzing relationships between variables. The study results showed a usability level of 86.84%, categorized as excellent. Hypothesis testing indicated that the variables of usefulness and ease of use had a positive and significant effect on satisfaction, whereas the variable of ease of learning does not have a significant effect. The research model also met the goodness of fit criteria with a FIT value of 61%, an AFIT 60.4%, a GFI 99.3%, and a SRMR 0.047. Keywords: Management Information System; ISO 9241-11; USE Questionnaire; Usability; Generalized Structured Component Analysis (GSCA)

Page 22 of 22 | Total Record : 220

 18   19   20   21   22 

Filter by Year

2014 2026


Reset
Filter By Issues
All Issue Vol 13 No 2 (2026): Volume 13 Nomor 2 September 2026 Vol 13 No 1 (2026): Volume 13 Nomor 1 Februari 2026 Vol 12 No 2 (2025): Volume 12 Nomor 2 September 2025 Vol 12 No 1 (2025): Volume 12 Nomor 1 Februari 2025 Vol 11 No 2 (2024): Volume 11 Nomor 2 September 2024 Vol 11 No 1 (2024): Volume 11 Nomor 1 Februari 2024 Vol 10 No 2 (2023): Volume 10 Nomor 2 September 2023 Vol 10 No 1 (2023): Volume 10 Nomor 1 Februari 2023 Vol 9 No 2 (2022): Volume 9 Nomor 2 September 2022 Vol 9, No 1 (2022): Volume 9 Nomor 1 Februari 2022 Vol 9 No 1 (2022): Volume 9 Nomor 1 Februari 2022 Vol 8, No 2 (2021): Volume 8 Nomor 2 September 2021 Vol 8, No 1 (2021): Volume 8 Nomor 1 Februari 2021 Vol 7, No 2 (2020): Volume 7 Nomor 2 September 2020 Vol 7, No 1 (2020): Volume 7 Nomor 1 Februari 2020 Vol 7 No 1 (2020): Volume 7 Nomor 1 Februari 2020 Vol 6, No 2 (2019): Volume 6 Nomor 2 September 2019 Vol 6 No 1 (2019): Volume 6 Nomor 1 Februari 2019 Vol 6, No 1 (2019): Volume 6 Nomor 1 Februari 2019 Vol 5, No 2 (2018): Volume 5 Nomor 2 September 2018 Vol 5, No 1 (2018): Volume 5 Nomor 1 Februari 2018 Vol 4, No 2 (2017): Volume 4 Nomor 2 September 2017 Vol 4, No 1 (2017): Volume 4 Nomor 1 Februari 2017 Vol 3, No 2 (2016): Volume 3 Nomor 2 September 2016 Vol 3, No 1 (2016): Volume 3 Nomor 1 Februari 2016 Vol 2, No 2 (2015) Vol 2, No 1 (2015) Vol 1, No 2 (2014) Vol 1, No 1 (2014) Vol 1, No 1 (2014): Jurnal Pseudocode More Issue