Claim Missing Document
Check
Articles

Found 6 Documents
Search

The preliminary study of carbon x-change rakyat using blockchain application Putro, Wahyu Sasongko; Rahmi, Nitia; Asditama, Raditya Yoga; Akbar, Nur Arifin
International Journal of Electrical and Computer Engineering (IJECE) Vol 14, No 1: February 2024
Publisher : Institute of Advanced Engineering and Science

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.11591/ijece.v14i1.pp672-680

Abstract

Today’s air pollution is detrimental to the environment, particularly in Indonesia. Carbon dioxide (CO2) and nitrogen oxide (NOx) are present in the atmosphere due to air pollution. Many individuals employ reforestation to lessen the influence of CO2 and NOx gases on the atmosphere. However, in the digitalized era, lowering carbon emissions may also be accomplished through a carbon credit exchange. Thus, in this study we investigate the performance of the carbon x-change rakyat (CXR) based on blockchain platform utilizing the stress test approach. We provided four scenarios with 10,000 to 100,000 transactions evaluated on the CXR blockchain system i.e., transfer, insert, remove, and update. The outcome demonstrates CXR’s effectiveness with 100% success and 0% failure rate based on testing and statistical computations calculation. The mean absolute error (MAE), variance accounted for (VAF), and percent error (PE) are obtained with values ranging from 0.38% to 4.67%. In this study, the transaction per-second (TPS) is used to calculate include error request (IER) and exclude error request (EER) values around 312 to 746 milliseconds (ms). In addition, the TPS of CXR based on blockchain platform is a capability to create and trace database carbon certificate ownership (nonfinancial activity). It means CXR based on the blockchain platform has a fast response to process carbon certificate ownership for transactions across local and international countries in the world.
AI-Based Business Model Analysis of Education-Focused Beauty Salon Entrepreneurship Putro, Wahyu Sasongko; Dwijuliani, Rina; Rosita, Rosita
JURNAL HURRIAH: Jurnal Evaluasi Pendidikan dan Penelitian Vol. 6 No. 2 (2025): Jurnal Hurriah: Journal of Educational Evaluation and Research
Publisher : Yayasan Pendidikan dan Kemanusiaan Hurriah Aceh

Show Abstract | Download Original | Original Source | Check in Google Scholar

Abstract

This study aimed to analyse business models using AI to enhance education in beauty salon entrepreneurship over Surabaya, East Java, Indonesia. Here, the data observation is taken from a famous beauty salon group at Surabaya with three service products such as Make Up, Hair Treatment, and Facial. The daily basis data from customers who use three products was analysed to obtain an estimation value of each service product. In this study, the Artificial Neural Network (ANN) method is performed to find an estimation value with Multi-Layer Perceptron (MLP) architecture with two to three variation hidden layers. The Levenberg-Marquardt backpropagation algorithm is also used to obtain RMSE over training value. The result shows the three products Make Up, Hair Treatment, and Facial were compared by customer basis over famous beauty salon group, Surabaya. Here, The ANN model with four hidden layers MLP architecture with 1000 iterations in the training process. The statistical calculation such as MSE of 172, RMSE of 0.812, MAE of 1.234, and MAPE of 3.123% indicate that the model performs exceptionally well, with minimal errors in predictions, respectively. ANN model is proposed to develop a business intelligence system in the near future in beauty salon entrepreneurship
Mediator of Technology Competence and Solar Panel Module on Satisfaction, Motivation, and Self-Regulated Learning Baskoro, Farid; Agung, Achmad Imam; Achmad, Fendi; Firmansyah, Rifqi; Nurdiansyah, Aristyawan Putra; Putro, Wahyu Sasongko
Jurnal Pemberdayaan Masyarakat Vol 4, No 4 (2025)
Publisher : Yayasan Keluarga Guru Mandiri

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.46843/jpm.v4i4.579

Abstract

The development of digital technology requires higher vocational education, particularly in engineering, to emphasize practical competency and independent learning. This study aims to analyze active engagement as a mediator in the relationship between technological competency and practical modules on learning satisfaction, motivation, and self-regulated learning. The study used a quantitative-correlation approach with the Structural Equation Modeling–Partial Least Squares (SEM-PLS) analysis technique on 80 electrical engineering students, Surabaya State University (Unesa) who were selected using purposive sampling. The results showed that technological competence had a significant effect on active involvement (? = 0.291; p 0.01) and motivation (? = 0.276; p 0.05). The practical module has a significant effect on learning satisfaction, active engagement is the most potent factor influencing learning satisfaction, motivation, and self-regulated learning. Active engagement as a crucial mediating mechanism within the technology-enhanced learning framework is related to engagement-driven learning through collaborative projects, problem-based learning, and digital simulations. These findings are relevant to contributing to the digital transformation of vocational education and the needs of the renewable energy industry.
A Longitudinal Evaluation of Student Knowledges and Skills Development Using Artificial Intelligence Putro, Wahyu Sasongko; Rosita, Rosita; Dwijuliani, Rina
JURNAL HURRIAH: Jurnal Evaluasi Pendidikan dan Penelitian Vol. 6 No. 4 (2025): Jurnal Hurriah: Journal of Educational Evaluation and Research
Publisher : Yayasan Pendidikan dan Kemanusiaan Hurriah Aceh

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.56806/jh.v6i4.388

Abstract

This study seeks to examine the progression of students' knowledge (P) and skills (K) scores in an Indonesian Vocational High School (SMK), focused on Multimedia, through an artificial intelligence (AI)–driven longitudinal analysis methodology. The research data comprises academic scores from 32 students gathered over five semesters and examined via data preprocessing, descriptive statistical analysis, and machine learning modelling employing the Random Forest algorithm. The results show that both knowledge and skills scores have been going up steadily over the semesters. The predictive model based on Random Forest works very well, with a high level of accuracy and a low level of prediction error. Additionally, Pearson correlation analysis and simple linear regression demonstrate that knowledge significantly and positively influences students' skills (p < 0.05), suggesting that proficiency in cognitive dimensions directly facilitates the enhancement of practical skills in vocational education. These results validate that the amalgamation of longitudinal analysis and artificial intelligence can enhance data-driven learning assessment and promote more precise academic decision-making in vocational education
Energy Density Prediction of Metal-Organic Frameworks (MOFs) From Synthesis Conditions Using Deep Neural Network (DNN): Hydrogen Storage Application Putro, Wahyu Sasongko; Gumilang, Yandhika Surya Akbar; Baskoro, Farid
JURNAL HURRIAH: Jurnal Evaluasi Pendidikan dan Penelitian Vol. 7 No. 1 (2026): Jurnal Hurriah: Journal of Educational Evaluation and Research (In Progres)
Publisher : Yayasan Pendidikan dan Kemanusiaan Hurriah Aceh

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.56806/jh.v7i1.414

Abstract

The global transition toward sustainable energy systems necessitates efficient and scalable hydrogen storage technologies. Metal–organic frameworks (MOFs) have emerged as promising candidates for hydrogen storage due to their high surface area, tunable pore structures, and favorable surface chemistry that enhance adsorption performance. However, real-time experimental measurement of hydrogen uptake using physical sensing systems is costly, computationally intensive, and operationally complex. To address these limitations, this study proposes a data-driven soft-sensor framework based on machine learning to predict energy density for hydrogen storage applications from synthesis parameters. High-fidelity secondary data sourced from an open-access Kaggle dataset were utilized, focusing on synthesis descriptors including metal type, oxidation state, temperature, and reaction time. Recognizing the intrinsic influence of transition metals on structural stability and adsorption behavior, a per-metal modeling strategy was implemented to capture material-specific relationships. A Deep Neural Network (DNN) employing a Multi-Layer Perceptron (MLP) architecture trained via backpropagation was developed to model nonlinear interactions between structural variables and energy density. To enhance interpretability, complementary linear regression models were also constructed, yielding explicit predictive equations. Model performance was rigorously evaluated using statistical error metrics, achieving a Mean Squared Error (MSE) of 0.0821 and a Root Mean Squared Error (RMSE) of 0.2852, demonstrating strong predictive capability and generalization across different metallic linkers. The low error values confirm that artificial neural network–based soft sensors provide a reliable, low-latency alternative to physical sensing systems for monitoring hydrogen storage performance. This approach significantly reduces experimental burden, accelerates materials screening, and supports intelligent optimization of hydrogen-based fuel cell technologies, contributing to the advancement of scalable clean energy infrastructure
From Line to Logic: STEM Learning Based on Line Follower Robot Program for Vocational Students' Logical Thinking Development Gumilang, Yandhika Surya Akbar; Subairi, Subairi; Rabi', Abdur; Bello, Saeed Abioye; Putro, Wahyu Sasongko; Afifah, Binti
Smart Society Vol. 6 No. 1 (2026): Smart Society
Publisher : FOUNDAE (Foundation of Advanced Education)

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.58524/smartsociety.v6i1.1036

Abstract

In the current digital era, logical thinking skills and technological understanding are increasingly essential for vocational high school (SMK) students preparing to enter a technology-driven workforce. This community service program aimed to strengthen students’ logical thinking skills through STEM-based learning activities focused on the configuration and programming of line follower robots. The program was conducted over one month and comprised three stages: focus group discussion with school partners, development of instructional materials, and training sessions. The training involved 17 students. Participants were introduced to fundamental concepts of line follower robots, including basic logic, sensors, and programming principles, and then applied this knowledge through practical tasks. Evaluation results showed that 76% of students expressed increased interest in further learning robotics, while all participants (100%) successfully completed the assigned task of programming the robot to navigate from the starting point to the finish line. These findings indicate that robotics-based learning effectively supports the program’s objective of enhancing logical thinking while simultaneously increasing students’ engagement with STEM concepts. By integrating theoretical explanations with direct practice, the line follower robot served as an accessible and meaningful medium for translating abstract logical reasoning into concrete technological applications. The main contribution of this community service activity lies in offering an applied STEM learning model for vocational high schools, particularly in contexts with limited prior exposure to robotics. This program provides a practical reference for integrating educational robotics into SMK learning environments to strengthen logical reasoning, technical competence, and students’ motivation to pursue STEM-related fields.