Article Per Year (5 Year)
p-Index From 2021 - 2026
0.408
P-Index
This Author published in this journals
All Journal Jurnal RESTI (Rekayasa Sistem dan Teknologi Informasi) Journal of Computing and Smart Ecosystems
Fayza Nayla Riyana Putri
Universitas Muhammadiyah Semarang
Computer Science & IT Electrical & Electronics Engineering Engineering

Published : 2 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 2 Documents
Search

 1 
Convergence and Empirical Performance of Tanh-Based Adaptive Particle Swarm Optimization Joko Riyono; Aina Latifa Riyana Putri; Sofia Debi Puspa; Supriyadi Supriyadi; Christina Eni Pujiastuti; Fayza Nayla Riyana Putri
Jurnal RESTI (Rekayasa Sistem dan Teknologi Informasi) Vol 10 No 3 (2026): June 2026
Publisher : Ikatan Ahli Informatika Indonesia (IAII)

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.29207/resti.v10i3.7247

Abstract

Particle Swarm Optimization (PSO) is a widely used population-based optimization method but faces challenges in premature convergence, leading to suboptimal solutions. To address this issue, this study proposes a Tanh-Based Acceleration Coefficient PSO (TB-PSO), where the acceleration coefficients are modified using the hyperbolic tangent (tanh) function. The smooth and continuous behavior of tanh enables gradual coefficient updates, limits excessive particle velocities, and maintains swarm diversity, thereby improving convergence stability and balancing exploration and exploitation. The convergence theorem analysis confirms that TB-PSO meets stability criteria before being evaluated on unimodal and multimodal benchmark functions in 10 and 30 dimensions. Its performance is compared against several PSO variants, including TVAC-PSO, SCAC-PSO, NDAC-PSO, and SAC-PSO. In the 10-dimensional experiments, TB-PSO achieves the best overall final ranking based on the average and standard deviation of best solution, ranking first for functions f₃ and f₅, second for f₂ with only a marginal difference from the best-performing method, and remaining competitive for f₁ and f₄. These results indicate superior solution quality and stable convergence. For the 30-dimensional benchmark functions, TB-PSO ranks first for f₂, second for f₅, and third for f₁, f₃, and f₄ based on the same evaluation criteria. Although its ranking decreases compared to the 10-dimensional case, TB-PSO remains competitive, reflecting the increased complexity of high-dimensional optimization problems. Overall, the results demonstrate that the tanh-based acceleration coefficient modification effectively enhances PSO performance, particularly in lower-dimensional search spaces, while maintaining robustness in higher-dimensional scenarios.
Accuracy-Efficiency Benchmarking of Lightweight Machine Learning Models for Building Heating and Cooling Load Prediction Nuki Pujiani Yosephine; Fayza Nayla Riyana Putri; Zamrud Mahfur Abdillah; Marita Prasetyani
Journal of Computing and Smart Ecosystems Vol. 2 No. 1 (2026): J-CaSE
Publisher : S1 Teknologi Informasi, Universitas Muhammadiyah Semarang

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

Abstract

Early-stage estimation of heating and cooling loads supports energy-efficient building design, but complex predictive models may impose unnecessary computational costs for small tabular datasets. This study benchmarks four lightweight regression models, such as Linear Regression, Ridge Regression, Random Forest, and Gradient Boosting, using the UCI Energy Efficiency dataset containing 768 simulated building configurations, eight design variables, and two continuous targets. Model accuracy was evaluated with shuffled 10-fold cross-validation using mean absolute error (MAE), root mean squared error (RMSE), and the coefficient of determination (R²). Computational efficiency was assessed through training time, prediction latency, and serialized model size, while permutation importance was used for interpretation. Random Forest achieved the lowest heating-load RMSE (0.4624) and an R² of 0.9978; however, its difference from Gradient Boosting was not statistically significant. Gradient Boosting was approximately 96 times smaller and 20 times faster at inference. For cooling load, Gradient Boosting achieved the lowest RMSE (1.4903) and an R² of 0.9751, significantly outperforming Random Forest in fold-level RMSE. Relative compactness was the most influential heating-load feature, whereas overall height dominated cooling-load prediction. The results indicate that Gradient Boosting offers the strongest overall accuracy-efficiency trade-off for lightweight smart-building prediction systems.
Co-Authors Aina Latifa Riyana Putri Christina Eni Pujiastuti Joko Riyono Marita Prasetyani Nuki Pujiani Yosephine Sofia Debi Puspa Supriyadi Supriyadi Zamrud Mahfur Abdillah