Project

Swallow Counting

Swallow’s nest is one of the commodities that have various benefits for health. To obtain the nest, one could provide a strategic place for the bird to build its nest. To calculate how many nests could be built, it is necessary to count the swallows that settle in the building. One of the options to count the swallows is through AI technology. Here, we use deep learning in computer vision to accomplish the mission. The deep learning architecture we use is specifically named YOLOv5. First, YOLOv5 will detect the existing swallows in the scene. Then, real-time counting will be carried out.

Edge AI Inference Framework

Devising an Edge AI inference framework. The framework offers CLI commands that create and execute a project template, convert an optimized deep learning model into a consumable file, and inspect the model. The framework is written in Python.

Data Science Project in the Insurance Industry

Implementing ensemble machine learning models on large-scale data. The models are maintained and deployed with orchestrated microservices. The models are trained at a scheduled interval. The prediction results are visualized and interpreted through the informative graphical UI.