• Mohamed Afsal Mohamed Rasheed
• Dr. M I Jawid Nazir

The integration of Internet of Things (IoT) technologies into smart elevator systems has revolutionized automation, operational efficiency, and user experience. However, this increased connectivity also brings heightened cybersecurity risks, exposing systems to potential threats. This case study explores the application of Artificial Intelligence (AI), particularly machine learning techniques, to detect and prevent such vulnerabilities in IoT-powered smart elevators. Using a telemetry dataset that simulates real-world elevator operations, the research implements LSTM Autoencoder model and CNN LSTM model to identify anomalous behavior. The model demonstrates strong potential in enhancing real-time threat detection and initiating automated defense responses. Through simulations and scenario analysis, the study highlights the critical role of supervised and unsupervised learning, precise threshold tuning, and sequence modeling in building resilient and secure systems. Ultimately, the findings contribute to the growing body of research advocating for AI-driven cybersecurity frameworks within increasingly connected IoT ecosystems.

IoT, Smart Elevator, AI, ML Technique, Cybersecurity, Threat Detection, LSTM, CNN, Autoencoder

"A Study on detecting and preventing threats using AI in IOT-based Smart Elevators", International Journal of Emerging Technologies and Innovative Research (www.jetir.org), ISSN:2349-5162, Vol.12, Issue 6, page no.i808-i830, June-2025, Available :http://www.jetir.org/papers/JETIR2506892.pdf

"A Study on detecting and preventing threats using AI in IOT-based Smart Elevators", International Journal of Emerging Technologies and Innovative Research (www.jetir.org | UGC and issn Approved), ISSN:2349-5162, Vol.12, Issue 6, page no. ppi808-i830, June-2025, Available at : http://www.jetir.org/papers/JETIR2506892.pdf