Specialized AI-based vision system for detecting surface and structural defects on printed circuit boards (PCBs) during manufacturing inspection.

A lightweight face recognition solution leveraging Edge Impulse’s FOMO model, designed for fast, accurate deployment on edge devices in industrial environments.

A training pipeline for customizing YAMNet to recognize new environmental or industrial sounds.

Robust speaker ID/verification using ECAPA-TDNN embeddings for secure, personalized HMI and analytics.

Advanced transformer-based detector optimized for accurate, real-time edge performance on SECO platforms.

Deep-learning gesture recognition for touchless HMI in dynamic environments.

Lightweight on-device AI agent for natural interaction and local decision-making without cloud.

On-device fine-tuning/validation of ResNet classifiers—customize without cloud dependency.

Predictive modeling for TBM settlement to enhance safety and planning in tunneling projects.

AI-based detection for product recognition and user interaction in smart vending systems.

Facial emotion analysis for adaptive, personalized HMI experiences.

Efficient edge analytics using Qualcomm HW to extract facial attributes for personalization and safety.