🎓 AI Researcher focused on HAR, Agriculture 4.0, and Generative Models
💡 Passionate about LLMs, Diffusion Models, and Edge AI
🔬 Published at ICML 2024 and International Journals
🚀 Building impactful solutions with cutting-edge technologies
🌱 Constantly learning and pushing the boundaries of AI
|
An Approach for Data Augmentation in HAR with Wearable Sensors Using TIMEGAN Focuses on generating realistic synthetic data from wearable sensors using TimeGAN for Human Activity Recognition. |
Using Mobile Edge AI to Detect and Map Diseases in Citrus Orchards A systematic study of Deep Learning architectures applied to disease detection and fruit counting in orchards. |
🧩 LLMs & NLP
Prompt Engineering: OpenAI, Hugging Face, Ollama, Anthropic
Fine-tuning: LoRA, QLoRA, PEFT
Advanced Techniques: RAG (Retrieval-Augmented Generation)
Vector Databases: FAISS, Chroma, Weaviate, Pinecone
Model Serving: FastAPI, LangChain, Docker, MLflowModels Used:
🎨 Diffusion Models & Generative AI
- ✨ Stable Diffusion: text-to-image, inpainting, img2img, ControlNet, LoRA
- 🎛️ ComfyUI: Custom pipeline design, workflow automation, model chaining
- 🤗 Hugging Face Diffusers: Deployment and experimentation
- 🎯 DreamBooth & LoRA: Fine-tuning for personalized generation
- 🎨 Leonardo.AI & DALL·E 3: API-based content generation
- 📝 Prompt Engineering: Marketing, branding, and storytelling
- 🔧 Post-processing: Upscalers, attention masking, aesthetic scoring
- 💾 Model Management: .safetensors, .ckpt, .onnx optimization
🤖 Machine Learning & Deep Learning
Machine Learning:
- Supervised & Unsupervised Learning
- Regression, Classification, Clustering
- Time Series Forecasting & Anomaly Detection
- Recommender Systems
- Model Evaluation & Feature Engineering
Deep Learning:
- Artificial Neural Networks (ANN)
- Convolutional Neural Networks (CNN)
- Recurrent Neural Networks (RNN/LSTM)
- Computer Vision (TensorFlow, PyTorch, OpenCV)
- Transfer Learning & Model Fine-tuning
📊 Data Analytics & Visualization
Python Data Stack:
Capabilities:
- 🔍 Data Wrangling & Cleaning
- 📈 Exploratory Data Analysis (EDA)
- 📊 Statistical Analysis & Hypothesis Testing
- 🎨 Visual Dashboards & Storytelling
- ⚡ Reporting Automation (Power BI, Streamlit, Tableau)
🚀 MLOps & Model Deployment
Key Practices:
- 📦 Model versioning & registry (MLflow, DVC)
- 📊 Experiment tracking & parameter logging
- 🌐 REST API deployment (FastAPI + Docker)
- 📈 Monitoring & Logging (Prometheus, Grafana, Kibana)
- ⚙️ CI/CD pipelines (GitHub Actions, CircleCI)
- 🐳 Container orchestration (Kubernetes, Docker Compose)
- 🔄 Workflow automation (Apache Airflow)
- 🔒 Secure API scaling with NGINX
- 🏗️ Microservices architecture for modular AI services
⚙️ Embedded Systems & Edge AI
Hardware Platforms:
- 🚀 NVIDIA Jetson Nano – AI edge computing with GPU acceleration
- 📡 ESP32 / ESP32-C3 – Low-power microcontrollers with Wi-Fi + BLE
- 🔌 Arduino – Prototyping with C/C++ and sensor integration
- 🍓 Raspberry Pi – Full-stack embedded Linux systems
- 🧠 Sipeed M1s Dock – RISC-V with AI co-processor (Kendryte K210)
Applications:
- Real-time sensor data collection
- Edge AI for activity recognition (HAR)
- IoT integration with mobile apps (Flutter + BLE)
- Offline AI inference with optimized models
⭐️ From Jonathan Cristovão with 💜