behavior analysis

The Cross-Domain Deception Dataset (CD3) contains frame-level features extracted from video data using OpenFace and OpenPose to support research in deception detection through facial expressions, facial action units, body and hand gestures, and gaze coordinates. Using a commercial off-the-shelf laptop and Microsoft Teams, we collected video data of 45 participants completing mock interviews where they answered questions related to biographical information, academic success, and well-being across two sessions.

This data was collected using a Bosch Parking Lot Sensor (TPS110 EU) placed in a time-limited public parking space over a period of two months. Each time the sensor detected a change in the parking status, it transmitted the new state via The Things Stack LoRaWAN network to the server. When a car parked in the space, the sensor changed its state from "free" to "occupied," and when the car vacated the space, the state changed back to "free." The sensor communicated its data through a Multitech LoRa Gateway, located 960 meters away from the sensor with a height difference of 116 meters.