The Last Word with Anthony D. Parfitt: How Ci Global is shifting UAE fire safety to prevention

by Featured NewsFire DetectionSafety

Anthony D. Parfitt, Chairman & Founder of Ci Global, discusses how Ci Safe’s AI-driven system embeds electrical fire prevention into the UAE’s smart buildings

Now that Ci Global has established a presence in the UAE, how do you plan to integrate Ci Safe with existing building and safety infrastructures?

The UAE already operates within a sophisticated safety environment, with Civil Defence regulation, fire-detection systems and advanced building-management platforms in place.

Our integration plan is to embed prevention into that existing model.

Ci Safe is embedded within the building’s electrical infrastructure, where it continuously monitors thermal behaviour and can isolate power automatically if dangerous heat build-up is detected.

At building level, the system communicates through a secure gateway, allowing relevant safety data to interface with building-management systems and national fire-safety platforms, while also incorporating selected third-party sensors where required.

It is designed to operate alongside detection, suppression and smoke-control systems – adding a prevention layer beneath them so detection becomes the safety net, rather than the first line of defence.

What long-term goals does the company have for its UAE presence?

The UAE has prioritised smart city development, resilient urban growth and modern fire-safety standards.

That makes it a serious market for prevention-first fire protection.

Our long-term objective is to see electrical fire prevention embedded as standard across residential towers, villas and major developments – not as an upgrade or feature, but as baseline infrastructure.

We see the UAE as a strategic launch point for the GCC – a market where prevention can be demonstrated at scale and adopted across fast-growing urban environments.

Ci Safe is designed to prevent electrical fires at the source. Can you explain how its AI-driven and autonomous features work in practice, especially in environments where connectivity may be limited?

Ci Safe uses AI in two places – within the device and in the cloud.

At device level, AI continuously monitors electrical load and thermal behaviour in real time and identifies dangerous heat escalation before ignition.

If risk is detected, intelligent autonomy isolates power immediately at source.

That decision is made locally, so protection continues even without internet connectivity or cloud access.

In parallel, cloud-based AI analyses safety data across buildings, identifying recurring fault patterns and strengthening prediction over time.

Ci Safe monitors other safety risks. How do you see this system evolving to address a wider spectrum of building-safety challenges in the UAE and the region?

Electrical fire prevention is the foundation.

From there, the system expands into monitoring gas and water leaks with automatic shut-off, and environmental conditions that can lead to mould.

It can also recognise unsafe sounds, such as glass breaking, which may indicate a break-in or wider risk.

The longer-term evolution is about distributed intelligence across the building.

In high-rise environments, this can extend to real-time digital building mapping and drone visual support, giving emergency responders clearer visibility of emerging risk within complex structures.

That level of situational awareness can materially improve decision-making during an incident.

Buildings should not be passive structures that simply trigger alarms.

They should actively help protect the people inside them.

That is the direction this technology is moving.

This was originally published in the March 2026 Edition of International Fire & Safety Journal. To read your FREE copy, click here.

Fire and smoke detection results raise questions for smart cities

by AI & Deep LearningFeatured NewsFire DetectionResearch

Detection system combines two AI models

Researchers at Jouf University in Saudi Arabia have developed an artificial intelligence framework for early smoke and fire detection in smart city environments.

A study by Amr Abozeid and Rayan Alanazi describes a hybrid system that combines a Vision Transformer with the YOLOv8 object detection architecture.

The framework is designed to identify early-stage smoke and fire patterns in complex visual scenes and support faster response through smart city monitoring systems.

The study says conventional heat and smoke detectors often raise alerts only after smoke reaches the device.

It adds that existing video-based systems can also produce false alarms when visual conditions include dust, clouds or changes in lighting.

The Vision Transformer analyses global visual patterns in an image so the system can detect subtle smoke characteristics and spatial relationships across a scene.

The YOLOv8 module then performs real-time object detection to localise smoke and fire regions at speed.

Detection results and next steps

According to the study in Scientific Reports, the researchers trained and tested the model on more than 7,000 images from urban and rural datasets.

These images included smoke and fire scenes captured under different lighting conditions and in different environments.

The system achieved 99.2% accuracy, with precision of 98.5% and recall of 97.8%.

Its F1 score reached 98.1% and inference latency was about 45 milliseconds, which the study says enabled real-time detection at about 22 frames per second.

The researchers reported an accuracy increase of about 4.3% compared with conventional convolutional neural network approaches and other single-model detection systems.

The study also says the framework performed better than several existing detection models across precision, recall and localisation accuracy.

It states that the hybrid architecture can distinguish real smoke or fire from visually similar features such as printed flames or static images by analysing contextual and spatial characteristics rather than relying only on colour.

The authors say further validation in real-world settings is still needed, with future work set to examine thermal imaging and environmental sensor inputs for low-visibility conditions.