An Internet of Things based lift predictive maintenance system

January 1, 2021 by Xiaoping Ma, Lee Chengkai, Kim Hock Ng, and Hwee-Pink Tan

Image of two elevators side by side, one open, one with caution tape. — WARNING TAPE: ©SHUTTERSTOCK/VECTORPOCKET.
GOLD ELEVATOR: ©SHUTTERSTOCK/VECTORPOCKET

Lift (or elevator) breakdowns cause huge inconveniences to city dwellers and affect more than 80% of Singapore’s residents who live in high-rise apartments. Unfortunately, lift maintenance today is either preventive (e.g., follows a fixed cycle based on statistics) or reactive (the faults are fixed after they happen).

As symptoms typically manifest over some time before a breakdown happens, with the Internet of Things (IoT), massive amounts of data can be reliably collected from lifts fitted with myriad sensors. By applying artificial intelligence (AI) technologies to these data, along with operational data, such as fault records collected when a breakdown happens, predictive lift maintenance is now possible, empowering technicians to fix the lifts before they break down.

For more about this article see link below.

https://ieeexplore.ieee.org/document/9307328

Privacy implications of facial recognition technology

Facial recognition technology (FRT) has experienced enormous growth and rapid deployment across different sectors of the society in recent years, mostly motivated by safety, security, and commercial applications. However, major privacy questions arise around this technology, and regulators are still working to provide clear set of rules governing its use. This paper focuses on privacy implications of FRT usage. Specifically, we first present the definition of FRT, followed by an analysis of the vulnerability and risks that can potentially arise and how they might be concerning in such context. Finally, we discuss efforts needed to mitigate privacy concerns related to FRT, from both technical and regulatory perspectives.

Footer