Loading article...
Loading article...
Stream/Area:
-
Subject:
-
Paper ID:
IJSREM61932
Volume:
10 |
4 |
April 2026
Pages:
1-5
Publication Frequency:
Monthly (12 issues per year)
License:International Journal of Scientific Research in Engineering and Management follows the Creative Commons Attribution 4.0 (CC BY 4.0) License, allowing free use and distribution with proper attribution.
Department of Computer Science & IT
JAIN (Deemed to be University), Bengaluru, Karnataka
Department of Computer Science & IT
JAIN (Deemed to be University), Bengaluru, Karnataka
Department of Computer Science & IT
JAIN (Deemed to be University), Bengaluru, Karnataka
Contemporary residential living is undergoing a fundamental technological transformation, driven by converging advances in Artificial Intelligence (AI) and the Internet of Things (IoT). This paper introduces the Smart Home Transformation System (SHTS)—a comprehensive five-tier AI-IoT framework engineered to unify adaptive device automation, real-time energy conservation, and data-driven security surveillance within a single deployable architecture. The sensing tier deploys eight distinct IoT modalities spanning thermal, luminous, kinetic, chemical, and electrical domains, whose outputs are aggregated at a Raspberry Pi 4B gateway and relayed via MQTT to a cloud-resident intelligence engine. The AI tier comprises three specialized sub-systems: a Random Forest occupancy classifier achieving 94.7% accuracy, a two-layer LSTM network for anticipatory behavioral modeling with 87.3% prediction accuracy, and an Isolation Forest anomaly detector delivering F1-score of 0.909 for residential security. A 5,200-record composite dataset assembled from testbed instrumentation and two established open-access repositories underpins model training and evaluation. The SHTS realizes a 31.2% aggregate reduction in household energy consumption and maintains mean command-to-actuation latency of 1.4 seconds. Benchmarked against threshold-driven controllers and prior AI-IoT implementations, the SHTS demonstrates statistically significant improvements across all assessed dimensions, establishing a robust foundation for next-generation intelligent residential environments.
KEYWORDS
This paper has introduced the Smart Home Transformation System (SHTS), a five-tier artificial intelligence (AI) and Internet of Things (IoT) framework-based intelligent residential automation, occupancy-responsive energy saving and anomaly-driven security surveillance unifying. Experimental evaluation had shown: Occupancy prediction accuracy: 94.7; aggregate household energy consumption reduction: 31.2%; anomaly detections F1-score: 0.909; mean command-to-actuation latency: 1.4 seconds. Eight quantitative figures show visual evidence in energy saving, classifier performance, training dynamics of LSTMs, latency distributions and system benchmarking. Comparative analysis shows statistically significant improvements in both threshold-based automation and previous AI-IoT implementations. The two-folds advantage of hybrid edge-cloud is bandwidth relief by lowering upstream bandwidth usage and operational resilience in the event of cloud connectivity outages. As the cost of IoT hardware continues to fall and the cost of compute in the cloud becomes more affordable, this is creating a situation where the main obstacles to widespread adoption of SHTS in the residential sector are behavioral and regulatory rather than technical. The trajectory of improvement that is shown here - especially in energy conservation and emergency security response - makes a strong case for continued research investment in smart residential environments.
[1] Harper, R. (Ed.). (2003). Inside the Smart Home. Springer-Verlag, London. [2] IEA. (2023). Electricity - Analysis and Important Findings. Paris: International Energy Agency. [3] Grand View Research. (2024). Smart Home Market Size, Share & Trends Analysis Report, 2024 to 2030. [4] Soliman, M., et al. (2013). Smart home: Combining IoT and Web services, Cloud Computing. Proc. IEEE CloudCom, pp. 317-320. [5] Alaa, M., et al. (2017). A review of smart home applications, based on IoT. Journal of Network and Computer Applications, 97(48-65), 48-65. [6] Stanford-Clark, A. & Truong, H. L. (2013). MQTT Working Group Sensor Networks protocol specification, v1.2. IBM and Eurotech. [7] Batra, N., et al. (2014). NILMTK: Non-intrusive load monitoring tool kit. Proc. ACM e-Energy, pp. 265-276. [8] Mocanu, E., et al. (2016). Deep learning in estimating energy consumption in buildings. Sustainable Energy, Grids and Networks, 6, 91 - 99. [9] Nagarathinam, S., et al. (2017). Energy optimization for multi zone HVAC systems. Proc. ICCPS, pp. 235-244. [10] Beaudin, M. & Zareipour, H. (2015). Home energy management systems: An overview. Renewable and Sustainable energy reviews, 45:318-335.
Publication Date
5/1/2026
Peer Review Type
Double-Blind Peer Review
Review Rounds: 2
Documents
Article Views
0
Total views since publication
PDF Downloads
3
Total downloads since publication
Geographic Reach
5
Digital Preservation: This article is permanently archived on Zenodo and complies with all data preservation standards across major indexing platforms.
Plagiarism Screening
This manuscript has been checked for plagiarism using TurnitinPlagiarismChecker software.
Conflict of Interest
The authors declare no conflict of interest related to this research work.
Funding Information
No funding information available for this research.
Related research in the same subject area
Loading similar articles...