This project is a Python-based automation tool that detects tagged birds, controls access to a shared resource, and logs all events to structured data files. It replaces manual observation with reliable, timestamped data collection and saved approximately 270 hours of manual work.
This project automates the collection of event-based interaction data. The system detects uniquely tagged individuals in real time, applies simple rules to decide how the system responds, and records all activity to CSV files for later analysis.
The system was originally built to automate a bird feeder for a behavioral experiment, where access to food and visit events needed to be tightly controlled and logged. The tool was designed to run continuously with minimal human involvement and to produce clean, analysis-ready data.
Manually recording who triggered events and when they occurred during experiments is slow, tiring, and prone to error. This project replaces manual data collection with an automated system that captures every event consistently and with precise timestamps.
-
A Python automation tool running on a Raspberry Pi
-
Radio Frequency Identification (RFID) tag detection to identify individuals at each visit
-
Condition-based logic to control system behavior
-
Motor control to trigger food release when conditions are met
-
CSV logging for both detections of individuals and motor activations
All events are saved with timestamps in a format designed for later analysis.
The system records two main types of events:
-
Detection events: individual ID and timestamp for each RFID scan
-
Activation events: individual ID and timestamp for each motor activation
Using timestamps, interaction sequences (such as one individual following another to the feeder) can be reconstructed during analysis.
By automating detection, control, and logging, this tool:
-
Eliminated approximately 270 hours of manual observation
-
Improved data accuracy and consistency
-
Allowed data to be collected continuously over long periods
-
Freed time for analysis and modeling instead of manual recording
This project demonstrates skills that are useful in data analyst, product analytics, and product data science roles, including:
-
Workflow automation: Turning manual processes into automated pipelines
-
Event logging: Capturing user or system actions with timestamps
-
Rule-based logic: Implementing rules that affect system behavior
-
Data quality: Producing clean, structured datasets for analysis
-
System integration: Connecting software, hardware, and data outputs
-
Python
-
RFID reader
-
Raspberry Pi
-
Motor control (General-Purpose Input/Output - GPIO)
-
CSV-based logging
RFID detection code was adapted from vendor-provided scripts and extended to support event logging and motor control logic.