AI Model Development Projects in Wah CanttAI Model Development Projects in Wah CanttMachine Learning Model Evaluation for Soft Biometric Prediction
Developed and evaluated machine learning models to predict physical characteristics from human gait data collected using inertial sensors. The project compares Random Forest Regression (RFR), XGBoost, Support Vector Regression (SVR), and Artificial Neural Networks (ANN) using engineered gait features.
To assess model generalization to unseen individuals, multiple subject-wise validation strategies were applied, including hold-out validation, 10-fold cross-validation, and Leave-One-Subject-Out (LOSO). Performance was evaluated using MAE, RMSE, and R², with visual comparisons of actual and predicted values.
The project demonstrates an end-to-end workflow for data preprocessing, feature engineering, predictive modelling, and systematic performance evaluation. Designed and built Aixen AI a unified communication and lead management platform powered by multiple LLMs working in coordination. The system monitors and manages inbound leads across email, Instagram DM, WhatsApp, and Telegram simultaneously. Each channel has a dedicated AI agent that reads incoming messages, understands context and intent, generates appropriate responses, and escalates or routes leads based on qualification criteria. A central Lead Manager Agent maintains a live unified inbox view deduplicating contacts across channels, tracking conversation history, and scoring lead quality in real-time. Sales-ready leads are pushed to the CRM with a full conversation summary automatically. The client — a digital marketing agency — replaced a 4-person response team with this system, achieving sub-2-minute response times across all channels 24/7. Built on n8n with GPT-4o, Claude, and WhatsApp Business API. 
