| Journal of Smart Sensors and Computing
Published Online: 31 December 2025.
J. Smart Sens. Comput., 2025, 1(3), 25216 | Volume 1 Issue 3 (December 2025) | DOI: https://doi.org/10.64189/ssc.25216
© The Author(s) 2025
This article is licensed under Creative Commons Attribution NonCommercial 4.0 International (CC-BY-NC 4.0)
Editorial Comments: Journal of Smart Sensors and
Computing, Volume 1 Issue 3
Thittaporn Ganokratanaa
1,2*
1 Department of Mathematics, Faculty of Science, King Mongkut's University of Technology, Bangkok, 10140, Thailand
2 Editor-in-Chief, Journal of Smart Sensors and Computing, GR Scholastic, Ahmedabad, Gujarat, 382424, India
*Email: eic.ssc@gr-journals.com (Thittaporn Ganokratanaa)
This issue of the Journal of Smart Sensors & Computing (Volume 1, Issue 3, December 2025) features a
multidisciplinary collection of research articles covering smart agriculture, neuromorphic computing, AI-based
disease detection and prediction, and machine learning applications in loan default prediction. The issue
methodological rigor, applied relevance, and interdisciplinary integration across smart sensing and
computational intelligence domains.
Salve et al.
[1]
present a comprehensive study on smart agriculture systems that integrate the Internet of Things
(IoT) and Machine Learning (ML) to enhance crop monitoring, optimize resource utilization, and support
sustainable farming practices. IoT-based wireless sensor networks (WSNs) enable continuous real-time
acquisition of environmental and soil parameters, while ML algorithms analyze the collected data to facilitate
informed decision-making. Experimental results demonstrate that the proposed ensemble-based ML model
achieves high predictive accuracy, validating the effectiveness of combining multiple learning algorithms for
smart agriculture applications. Jadhav et al.
[2]
introduce UNAL (Unified Adaptive, Hardware-Agnostic
Neuromorphic Assembly Layer), a novel compilation framework that translates high-level Spiking Neural
Network (SNN) models into portable, spike-level assembly across heterogeneous neuromorphic platforms. The
framework incorporates a unified intermediate representation (UNAL-IR), a compact instruction set, and an
optimization-driven mapping pipeline that jointly addresses latency, energy efficiency, routing congestion, and
adaptability. Quantitative evaluations on standard SNN benchmarks (DVS Gesture and CIFAR-10 SNN) mapped
to Intel Loihi 2 demonstrate 1832% latency reduction, 2138% energy savings, and 2540% lower routing
congestion compared to Loihi-native and platform-specific toolchains. A smart-city surveillance case study
-time edge deployment, establishing UNAL as a scalable and
future-ready neuromorphic compiler infrastructure. Shegar et al.
[3]
propose a multi-class skin lesion
classification framework based on transfer learning, integrating an EfficientNet-B3 backbone with a
Convolutional Block Attention Module (CBAM) to enhance discriminative feature learning. EfficientNet-B3, pre-
trained on large-scale natural image datasets, serves as a robust feature extractor, while CBAM adaptively
emphasizes informative channel and spatial features, enabling the network to focus on diagnostically relevant
lesion regions while suppressing background artifacts. The model is trained and evaluated on the DermNet-23
dataset comprising 23 clinically significant skin disease classes. Experimental results show that the proposed
EfficientNet-B3 + CBAM model achieves 87.1% accuracy, an 85.6% macro-F1 score, and a 0.94 AUC,
outperforming baseline CNN, ResNet50, MobileNetV3, and standard EfficientNet-B3 models. Gour et al.
[4]
investigated the performance of ensemble machine learning algorithms, including Random Forest, Gradient
Boosting, XGBoost, and LightGBM, for loan default prediction. Using a publicly available benchmark dataset, the
study adopts a systematic experimental workflow involving data preprocessing, feature engineering, class
imbalance handling, model training, and performance evaluation. The results, assessed using standard metrics
such as accuracy, precision, recall, F1-score, and ROC-AUC, demonstrate the effectiveness of ensemble learning
approaches in improving predictive performance for financial risk assessment.
Conflict of Interest
There is no conflict of interest.
Artificial Intelligence (AI) Use Disclosure
References
[1]
Journal of Smart Sensors and Computing 1
[2]
Journal of Smart Sensors and
Computing1
[3]
S. R. Shegar, S. S. Patil, Multi-class skin lesion classification using transfer learning with EfficientNet-B3
and convolutional block attention module, Journal of Smart Sensors and Computing, 2025, 1, 25213, doi:
10.64189/ssc.25213.
[4]
P. Soni, S. Gour, Loan default prediction using ensemble machine learning algorithms, Journal of Smart
Sensors and Computing, 2025, 1, 25215, doi: 10.64189/ssc.25215.
Publisher Note: The views, statements, and data in all publications solely belong to the authors and
contributors. GR Scholastic is not responsible for any injury resulting from the ideas, methods, or products
mentioned. GR Scholastic remains neutral regarding jurisdictional claims in published maps and institutional
affiliations.
Open Access
This article is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License, which
permits the non-commercial use, sharing, adaptation, distribution and reproduction in any medium or format,
as long as appropriate credit to the original author(s) and the source is given by providing a link to the Creative
Commons License and changes need to be indicated if there are any. The images or other third-party material
in this article are included in the article's Creative Commons License, unless indicated otherwise in a credit line
to the material. If material is not included in the article's Creative Commons License and your intended use is
not permitted by statutory regulation or exceeds the permitted use, you will need to obtain permission directly
from the copyright holder. To view a copy of this License, visit: https://creativecommons.org/licenses/by-
nc/4.0/
© The Author(s) 2025
