Oman-based Onsor Technologies has integrated AI from Australian firm BrainChip into smart glasses so they can predict epileptic seizures.

BrainChip produces low-power, digital, event-based, neuromorphic AI. It is collaborating with Onsor on an innovative approach using neuromorphic computing on BrainChip’s Akida platform in a wearable design.

“At Onsor, we believe technology should empower people, not just assist them,” said Maadh Al Hinaai, CEO of Onsor Technologies (onsor.om). “That’s why we set out to create something truly life changing – a device that predicts seizures before they happen using AI. By integrating BrainChip’s Akida technology, we’re giving people real-time alerts, the power to take control, and the freedom to live with confidence. Great partnerships create breakthroughs. By integrating BrainChip’s Akida technology, we’re pushing the boundaries of what’s possible in AI and IoT. This collaboration isn’t just about technology, it’s about creating real-world options, like our neuromorphic seizure prediction glasses, that make a meaningful impact.”

The Onsor offering consists of a pair of wearable glasses incorporating EEG sensors and neuromorphic processing capabilities, paired with a user-friendly alert system on a mobile device. The key innovation is a seizure prediction neural network running on BrainChip’s Akida architecture, trained using Onsor data sets to achieve more than 95% accuracy out of the box with incremental learning and personalisation algorithms to increase accuracy continuously for the user.

“Wearable devices such as these are only possible due to the innovation of Akida’s neuromorphic approach to produce ultra-low-power processing and its ability to optimise the development and deployment of AI applications for the edge,” said Sean Hehir, BrainChip CEO. “We look forward to continuing to collaborate with Onsor to advance the capabilities of this revolutionary product throughout its development and introduction into the market.”

BrainChip (www.brainchip.com) specialises in edge AI on-chip processing and learning. The company’s Akida digital event-based AI processor uses neuromorphic principles to mimic the human brain, analysing only essential sensor inputs at the point of acquisition. Akida enables edge learning on the chip, independent of the cloud, reducing latency while improving privacy and data security.

Akida’s neural processor IP (brainchip.com/akida-foundations), when integrated into SoCs on any process technology, has shown benefits on workloads and networks, and offers a platform for developers to create, tune and run their models using standard AI workflows. In enabling effective edge compute to be universally deployable across real world applications such as connected cars, consumer electronics and industrial IoT, BrainChip says it is showing that on-chip AI, close to the sensor, is the future.