cover
Article Per Year (5 Year)
All
Home Page
OAI Link
Editorial Team
Contact
Reviewer
Google Scholar
Contact Name
Widi Aribowo
Contact Email
widiaribowo@unesa.ac.id
Phone
+62811307761
Journal Mail Official
vubeta@unesa.ac.id
Editorial Address
Jl. Prof. Moch Yamin, Ketintang, Kec. Gayungan, Surabaya, Jawa Timur 60231
Location
Kota surabaya,
Jawa timur
INDONESIA
Vokasi UNESA Bulletin of Engineering, Technology and Applied Science
Published by Universitas Negeri Surabaya
ISSN : -     EISSN : 30640768     DOI : https://doi.org/10.26740/vubeta.v1i1
Core Subject : Science, Engineering,
Computer Science & IT Engineering Mechanical Engineering Transportation
Vokasi Unesa Bulletin Of Engineering, Technology and Applied Science is a peer-reviewed, Quarterly International Journal, that publishes high-quality theoretical and experimental papers of permanent interest, that have not previously been published in a journal, in the field of engineering, technology, and applied sciences that aim to promote the theory and practice of Engineering, Technology And Applied Science.
Arjuna Subject : Teknik (semua kategori) - Teknik (Lain-Lain)
Articles 21 Documents
 1   2   3 
Search results for , issue "Vol. 2 No. 3 (2025)" : 21 Documents clear
Detecting Malaria Cells with Plasmo-D Expert System Developed on Android and Computer Vision Eganoosi Esme Atojunere; Temilola Adewunmi Onaneye
Vokasi UNESA Bulletin of Engineering, Technology and Applied Science Vol. 2 No. 3 (2025)
Publisher : Universitas Negeri Surabaya or The State University of Surabaya

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.26740/vubeta.v2i3.39626

Abstract

Malaria is a mosquito-borne disease that has been responsible for numerous deaths in humans for decades, caused by a single bite from an Anopheles mosquito. For proper treatment, the affected person needs to undergo a series of tests. Currently, separating infected and uninfected cells is done manually, which is time-consuming overall. However, this article presents a developedexpert system called Plasmodium Detector (Plasmo-D), which leverages computer vision to detect malaria-infected cells using image recognition. Plasmo-D was built as an Android application, featuring an information menu, splash screen, and classification screen, along with an image recognition system that utilized computer vision. Data sourcing of 27,528 cell images was obtained from the Data Library of the United States National Library of Medicine. Training was conducted using Microsoft Azure, and the application was deployed to Android using Java programming language and an Android XML (Extensible Markup Language) user interface, along withTensorFlow Lite. Five iterations were conducted, and the parameters studied included cell images, backgrounds, visual style, size, type, lighting, and camera angle. High accuracy (up to 99.8%) in classifying parasitized, uninfected, and irrelevant images (‘not a cell’).
Rethinking Intelligence: From Human Cognition to Artificial Futures Habib Hamam
Vokasi UNESA Bulletin of Engineering, Technology and Applied Science Vol. 2 No. 3 (2025)
Publisher : Universitas Negeri Surabaya or The State University of Surabaya

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.26740/vubeta.v2i3.44232

Abstract

The rapid advancement of AI technologies raises pressing questions about the nature and future direction of intelligence. A key challenge is to understand how human and artificial intelligences differ, not just in form but in function, and how they should be evaluated in a shared context. This paper proposes a structured framework based on 15 measurable conditions of intelligence, such as memory, adaptability, specialization, and ethical alignment. Our main contribution lies in connecting these conditions to nine key directions of AI development—such as responsible AI, human–machine collaboration, and quantum AI—to outline how intelligence can be evaluated and guided across both natural and synthetic domains. Methodologically, we cross-analyze these dimensions using a 15×9 matrix, providing both a diagnostic tool and a conceptual roadmap for future AI development. This approach blends insights from cognitive science, applied AI, ethics, and philosophy. Our findings show that intelligence must be judged not just by computational capability but by interpretability, ethical grounding, and social utility. Contextual and hybrid systems—those that adapt to environments and align with human values—emerge as the most promising. We conclude by calling for an interdisciplinary approach to build intelligence systems that are not only powerful but also trustworthy and socially meaningful.
Intelligent and Secure Package Receiver System Utilizing Internet of Things (IoT) Technology Retno Dwi Handayani; Zaidir Jamal; M. Alkahfiansyah; Lia Rosmalia; Novi H. Sudibyo; Riko Herwanto
Vokasi UNESA Bulletin of Engineering, Technology and Applied Science Vol. 2 No. 3 (2025)
Publisher : Universitas Negeri Surabaya or The State University of Surabaya

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.26740/vubeta.v2i3.38254

Abstract

The rapid expansion of e-commerce has increased the demand for secure and efficient package delivery solutions, particularly for recipients who are frequently away from home. This study presents the development of a Smart Package Receiver Box, an Internet of Things (IoT)-based system that integrates sensors and remote control functionalities to enhance package security. The system incorporates an ESP32-CAM microcontroller, an ultrasonic sensor for courier detection, a PIR sensor for package counting, and a solenoid door lock for secure access control. These components are integrated with the Telegram messaging application, enabling real-time notifications, visual monitoring, and remote control of package deliveries. Experimental testing demonstrates that the system reliably detects couriers within a 5 cm to 30 cm range, accurately counts inserted packages, and ensures a secure locking mechanism with prompt response times. The collected data confirm stable system performance, minimal delays, and effective remote accessibility for users. Despite its advantages, the system presents certain limitations that warrant further improvements. The current implementation lacks encrypted communication, posing potential security vulnerabilities that could be mitigated by integrating AES-256 encryption and secure authentication protocols. Additionally, the system's reliance on Telegram makes it susceptible to disruptions in service availability, necessitating the incorporation of alternative communication channels such as SMS notifications or cloud-based APIs. Future enhancements will focus on strengthening data security, increasing system redundancy, and conducting comprehensive field testing to improve robustness and scalability for broader adoption in modern package delivery systems.
Adaptive Resonance Theory-Based Approach for Robust and Efficient Face Recognition Hewa Zangana; Ayaz Khalid Mohammed; Marwan Omar; Firas Mahmood Mustafa; Anik Vega Vitianingsih
Vokasi UNESA Bulletin of Engineering, Technology and Applied Science Vol. 2 No. 3 (2025)
Publisher : Universitas Negeri Surabaya or The State University of Surabaya

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.26740/vubeta.v2i3.38709

Abstract

Face recognition systems play a crucial role in security, surveillance, and authentication applications. However, traditional deep learning-based models, particularly Convolutional Neural Networks (CNNs), often struggle with issues such as varying lighting conditions, occlusions, and high computational costs. This paper proposes an Adaptive Resonance Theory (ART)-based face recognition framework that enhances recognition robustness and computational efficiency. Unlike CNNs, ART enables incremental learning without requiring retraining, making it suitable for realtime applications. The study evaluated the proposed system on threebenchmark datasets: LFW, Yale, and ORL. Experimental results indicate that the ART-based model achieved an average accuracy of 96.2%, outperforming CNN-based models (93.5%) while reducing recognition time by 25%. Additionally, ART demonstrated superior adaptability, maintaining recognition accuracy above 94% even under occlusion and low-light conditions. These findings confirm the effectiveness of ART-based face recognition for security, access control, and innovative surveillance applications. Future research will focus on integrating ART with deep learning techniques for enhanced performance in large-scale datasets.
Power Quality Enhancement Using Single Phase Shunt Active Filter Based ANFIS Supplied by Photovoltaic Anis Fitriani; Amirullah Amirullah; Krischonme Bhumkittipich
Vokasi UNESA Bulletin of Engineering, Technology and Applied Science Vol. 2 No. 3 (2025)
Publisher : Universitas Negeri Surabaya or The State University of Surabaya

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.26740/vubeta.v2i3.39071

Abstract

This paper proposes a single-phase shunt active filter (ShAF) combined with photovoltaic (PV) to enhance power quality performance by reducing source current harmonics and compensating for reactive power in a single-phase 220-Volt distribution system with a frequency of 50 Hz connected to a non-linear load. The PV panel consists of several PV modules with a maximum power of 600 W each. An adaptive neuro-fuzzy inference system (ANFIS) controls the voltage in the DC link capacitor circuit in the ShAF. This method isproposed to overcome the weakness of the Fuzzy Sugeno method in neural network-based learning capabilities to determine the fuzzy rules of the input membership functions (MFs) and the weakness of the proportional-integral (PI) control in determining proportional and integral constants using trial and error method. The single-phase system is connected to a non-linear load with a combination, i.e. without ShAF, using ShAF, and using ShAF-PV, respectively, with a total of seven cases. Based on the three proposed control methods and model configurations, the ShAF-PV circuit with ANFIS control is able to result in the best performance because it is able to produce the lowest source current THD. The single-phase system using ShAF-PV with ANFIS control is also capable of injecting the largest reactive power compared to the ShAF and ShAF configurations with PI and Fuzzy-Sugeno control. The increase in reactive power in the ShAF-PV is further able to compensate for the reactive power, so it is able to suppress and reduce the source reactive power significantly.
A Deep Learning Approach to Fake News Classification Using LSTM Sitraka Herinambinina Andrianarisoa; Henri Michaël Ravelonjara; Geerish Suddul; Ravi Foogooa; Sandhya Armoogum; Doorgesh Sookarah
Vokasi UNESA Bulletin of Engineering, Technology and Applied Science Vol. 2 No. 3 (2025)
Publisher : Universitas Negeri Surabaya or The State University of Surabaya

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.26740/vubeta.v2i3.39360

Abstract

The rapid spread of misinformation on digital platforms poses a major significant challenge today. The ability to detect false information is essential to mitigate the crucial in mitigating its associated harmful consequences. This research presents a deep learning approach for detecting fake news using a Long Short-Term Memory (LSTM) model, which captures linguistic patternsand long-term dependencies in text. Our approach consists of involves optimizing the model through different various experiments based on hyperparameter tuning, using utilizing a pre-processed preprocessed dataset. The evaluation is performed using different metrics such as accuracy, precision, recall, and F1-score. Researchers evaluate the model using various metrics, including accuracy, precision, recall, and F1-score. Experimental results show that the LSTM model achieves a high accuracy of 0.9974, with an embedding dimension of 128 using, 100 LSTM units, a batch size of 64, and a dropout rate of 0.48. It is a substantial improvement over previous studies study. The application of cross-validation further confirms the model’s reliability. This research demonstrates that the application of a finetuned LSTM network, combined with robust data preprocessing, can provide a powerful tool to combat for combating online misinformation.
Estimating Residential Natural Gas Demand and Consumption: A Hybrid Ensemble Machine Learning Approach Mohammed Ajuji; Muhammad Dawaki; Ahmed Mohammed; Abuzairu Ahmad4
Vokasi UNESA Bulletin of Engineering, Technology and Applied Science Vol. 2 No. 3 (2025)
Publisher : Universitas Negeri Surabaya or The State University of Surabaya

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.26740/vubeta.v2i3.40135

Abstract

Natural gas is often used for cooking, drying clothes, heating, etc., particularly in residential settings; it has been an essential component for human beings for many decades. This study proposes a hybrid ensemble regression machine learning model for forecasting residential natural gas demand. Accurate demand prediction tends to reduce energy waste and address some of theenergy challenges; such as the need for reliable, affordable, and sustainable energy consumption, thereby, improving energy management and resource planning. The proposed approach integrates multiple regression algorithms including K-Nearest Neighbors (KNN), Support Vector Regression (SVR), Decision Tree Regression (DTR), and Linear Regression (LR) to leverage thestrengths of each model to develop a hybrid model that enhances overall predictive performance. The ensemble method operates in two phases: training individual regression models on the dataset, followed by aggregating their predictions. Model performance is evaluated using metrics such as Mean Absolute Error (MAE), Mean Squared Error (MSE), coefficient of determination (R²), and prediction accuracy, and is benchmarked against individual models. Cross-validation techniques were applied to ensure therobustness of the results. Experimental results demonstrate that the hybrid ensemble approach consistently outperforms standalone models by capturing diverse patterns and relationships within the data.
Adaptive Steganographic Technique for Digital Images Based on The Least Significant Bit Substitution Ekhlas Ghaleb Abdulkadhim; Zaman Mahdi Abbas; Muqdad Abdulraheem Hayder
Vokasi UNESA Bulletin of Engineering, Technology and Applied Science Vol. 2 No. 3 (2025)
Publisher : Universitas Negeri Surabaya or The State University of Surabaya

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.26740/vubeta.v2i3.40143

Abstract

It has become natural to retain most of the information electronically, due thanks to developments and improvements in information and communication technology. Thus, information security has become a major significant problem. Aside from cryptography, this study employs two strategies could be utilized to share information securely to ensure secure information sharing. Cryptography and steganography are two of these mechanisms. Using an encryption key known to both the receiver and the sender, the message isencrypted. Without the encryption key, no one will be able to read the message. Thus, this study proposes an efficient method based on the Least Significant Bit (LSB). Employing the LSB substitution approach ensures reliability, since as it can decrease the embedding error rate. For image-based steganography, our algorithm is formed by exploiting LSB substitution combined with a Multi-Level Encryption Algorithm (MLEA) the algorithm combines LSB substitution with a Multi-Level Encryption Algorithm (MLEA), Secret Key (SK), transposition, and flipping. According to the experimental results, the proposed method is efficient and produces effectualeffective outcomes. Several Quality Assessment Metrics (QAMs) evaluate 125 unique RGB images with varying degrees of hidden information, such as including PSNR, Contrast, and Image Histogram. Besides security analysis, the results prove that the proposed approach withstands RS analysis with great strength. Furthermore, our experimental results demonstrate that this study thoroughly tests the proposed technique with several steganographic and statistical indicators. When it compared to those of other available approaches, the analysis confirms the practicality of our method, and which is easy to implement and superior.
Control of DC Motor in Laundry Liquid Waste Treatment based on ESP32-S3 and Thingsboard Platform Benediktus Arisona Bao; Widi Aribowo; Ayusta Lukita Wardani; Aditya Chandra Hermawan
Vokasi UNESA Bulletin of Engineering, Technology and Applied Science Vol. 2 No. 3 (2025)
Publisher : Universitas Negeri Surabaya or The State University of Surabaya

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.26740/vubeta.v2i3.41371

Abstract

Untreated laundry wastewater contributes to environmental pollution, with TSS levels reaching 600 mg/L, far above the 100 mg/L limit set by East Java Governor Regulation No. 72 of 2013. This research develops an IoT-enabled automated wastewater treatment systemutilizing the ESP32-S3 microcontroller, integrated with pH, TSS, and temperature sensors, and featuring real-time monitoring via theThingsBoard platform. A DC motor serves as an actuator for chemical dosing and mixing, controlled by sensor feedback. The system serves small-scale laundry businesses with limited access to centralized treatment. Testing showed 100% effectiveness in reducing TSS and 95% in stabilizing pH. Data transmission delays averaged 4 seconds for turbidity and 5 seconds for pH. Processing effectiveness was evaluated based on regulatory compliance, with 71% classified as Feasible, 5% as Very Feasible, and 19% as Less Feasible. Whilecalibration and reliability improvements are necessary, the system demonstrates potential to assist local laundries in meetingenvironmental standards. Future work will focus on enhancing sensor accuracy and implementing fault-tolerant control.
Design of a 120V, 5A SEPIC DC-DC Converter for Unipolar 120V DC Microgrid Abdulkareem Mokif Obais; Ali Abdulkareem Mukheef
Vokasi UNESA Bulletin of Engineering, Technology and Applied Science Vol. 2 No. 3 (2025)
Publisher : Universitas Negeri Surabaya or The State University of Surabaya

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.26740/vubeta.v2i3.44140

Abstract

SEPIC is a DC-DC converter that operates in both boost and buck modes, thereby reducing voltage stress on the active power switches. It is utilized in electric vehicles, marine vessels, and aircraft to minimize dimensions, mass, maintenance, and operational expenses while enhancing efficiency, safety, and dependability. DC microgrids, characterized by their straightforward topology and economical materials, provide enhanced efficiency relative to AC microgrids. This work reviews the previous literature concerning SEPIC converters and DC-DC microgrid applications. This paper presents a SEPIC based DC-DC converter designed for direct connection to a unipolar 120V DC microgrid and capable of delivering 600W of DC power. It is outfitted with a current sensor and a protective switch to provide self-protection against microgrid disturbances, such as brief short circuits. The converter has been designed and evaluated using PSpice. The simulation results indicated that during a sudden disturbance in the DC microgrid, the current sensor detected an excessive current, prompting the control circuit to deactivate the protective switch. This action isolated the input voltage from the converter circuit, leading to an immediate reduction of the input current to zero and a subsequent decline of the output voltage toward zero. The condition endured for approximately 50 milliseconds, anticipating a possible recovery from the disruption. Therefore, the simulation results confirmed the design methods of the proposed converter and demonstrated adequate protection against highcurrent events.

Page 2 of 3 | Total Record : 21

 1   2   3 

Filter by Year

2025 2025


Reset
Filter By Issues
All Issue Vol. 3 No. 2 (2026): (In Progress) Vol. 3 No. 1 (2026) Vol. 2 No. 3 (2025) Vol. 2 No. 2 (2025) Vol. 2 No. 1 (2025) Vol. 1 No. 3 (2024) Vol. 1 No. 2 (2024) Vol. 1 No. 1 (2024)