AI-Enabled Security, Safety, Smart Infrastructure and Laboratory Automation

The Journal of Smart Sensors and Computing, Volume 2, Issue 3 (September 2026) presents four scholarly contributions addressing emerging challenges in smart sensing and intelligent computing. The issue brings together research spanning Edge AI and federated learning for smart-city engineering, multimodal biometric authentication, intelligent indoor air-quality and safety management, and AI-enhanced approaches to hydrochloric acid detection. Together, these contributions demonstrate how intelligent computational techniques can be integrated with sensing, embedded systems, and data-driven analysis to develop efficient and practical solutions across different application domains.

Mariam Labib Francies presents a cross-domain review of Edge AI and federated learning in smart city engineering, examining their applications across transportation, environmental systems, and building infrastructure. The review synthesizes literature published between 2021 and early 2026 and develops a unified perspective based on computation locality and learning paradigms. It proposes a taxonomy covering cloud, fog, edge, and on-device computing alongside centralized, federated, and hybrid learning approaches. The review further presents a five-layer reference architecture and identifies important deployment challenges, including non-IID urban data, communication efficiency, model drift, privacy, fairness, and explainability. The study highlights the growing importance of distributed and privacy-conscious intelligence for next-generation smart-city systems.[1]

Ahmed Salman Ibraheem investigates multimodal biometric authentication using fingerprint and finger vein recognition through a framework based on frozen pre-trained convolutional neural network backbones and lightweight classifiers. The proposed approach combines features extracted using VGG16, ResNet50, and EfficientNet-B0 without fine-tuning the convolutional backbones. Principal Component Analysis is subsequently employed for dimensionality reduction, while Random Forest and K-Nearest Neighbour classifiers are used for biometric recognition. The multimodal framework achieves 98.88% overall accuracy with an equal error rate of 0.03%, while requiring approximately 156.2 ms per authentication request on CPU-based hardware. The work demonstrates the potential of combining complementary biometric modalities with computationally efficient feature-extraction strategies for resource-constrained authentication environments.[2]

Khan et al. introduce a hybrid Edge-AI framework for proactive indoor air quality management, integrating environmental sensing, LSTM-based prediction, vision-assisted monitoring, offline voice intelligence, and active hazard mitigation within an embedded architecture. The system employs an on-device LSTM model for air-quality forecasting and incorporates multiple sensors together with visual verification to distinguish potential fire events from non-hazardous conditions. The reported experimental evaluation achieved a MAPE of 5.8% for IAQ prediction, with an inference latency of 32 ms, while the hardware safety mechanism demonstrated an 87 ms response for relay deactivation and intervention. The study illustrates how Edge AI can combine predictive environmental monitoring with real-time safety-oriented control in smart residential systems.[3]

Shanti Vunguturi explores the application of artificial intelligence to classical analytical chemistry through an AI-enhanced approach to hydrochloric acid detection. The study integrates automated data acquisition, preprocessing, curve fitting, regression, and anomaly detection to improve the identification of equivalence points during potentiometric titration. Using standard sodium hydroxide titrants, the proposed Python-based framework is designed to reduce subjectivity in manual endpoint determination while providing visualization and real-time analytical feedback. The work demonstrates how AI and computational automation can extend the capabilities of established laboratory techniques and support more reproducible analytical workflows.[4]

In conclusion, Volume 2, Issue 3 reflects the increasingly interdisciplinary nature of smart sensing and intelligent computing research. From distributed intelligence in smart cities and multimodal biometric security to Edge-AI-enabled environmental safety and automated chemical analysis, the contributions demonstrate diverse ways in which computational intelligence can be integrated with sensing and real-world systems. Collectively, these studies emphasize the importance of developing intelligent, efficient, and application-oriented technologies capable of addressing emerging challenges across urban infrastructure, security, environmental monitoring, and scientific research.

There is no conflict of interest.

The author declares that artificial intelligence (AI)-assisted tools were used only for language refinement and grammar improvement. All technical content, experimental implementation, results, and interpretations were independently developed and verified by the author.

1. M. L. Francies, Edge AI and federated learning in smart city engineering: A cross-domain review of architectures, applications, and deployment challenges in transportation, environmental, and building systems, Journal of Smart Sensors and Computing, 2026, 2, 26213, doi: 10.64189/ssc.26213.
2. A. S. Ibraheem, Multimodal biometric authentication using fingerprint and finger vein recognition: A frozen pre-trained CNN backbone framework with lightweight classifiers, Journal of Smart Sensors and Computing, 2026, 2, 26211, doi: 10.64189/ssc.26211.
3. M. Khan, S. Khan, S. Kadam, A. Ansari, A. A. Malik, A. Sankpal, F. Shaikh, A hybrid edge-AI framework for proactive indoor air quality management: Integrating LSTM-based prediction with multi-criteria risk mitigation, Journal of Smart Sensors and Computing, 2026, 2, 26212, doi: 10.64189/ssc.26212.
4. S. Vunguturi, Leveraging python for potentiometric titrations: An AI-enhanced approach to hydrochloric acid detection, Journal of Smart Sensors and Computing, 2026, 2, 26214, doi: 10.64189/ssc.26214.

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.

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/