When performing canine operant conditioning studies, the delivery of the reward can be a limiting factor of the study. While there are a few commercially available options for automatically delivering rewards, they generally require manual input, such as using a remote control, in accordance with the experiment script. This means that human reaction times and transmission distances can cause interruptions to the flow of the experiment. The potential for development of non-supervised conditioning studies is limited by this same factor. To remedy this, we retrofitted an off-the-shelf treat dispenser with new electronics that allow it to be remotely controllable as well as act as an experiment computation, data storage, and networking center. We present a fully integrated dispenser driver board with a complementary Raspberry Pi. With rather simple modifications, the commercial treat dispenser can be modified into a computercontrolled dispenser for canine cognition experiments or for other forms of canine training or games.
Cometrics is a Microsoft Windows compatible clinical tool for the collection and recording of frequency- and duration-based target behaviors, physiological signals, and video data. This software package is designed to record in-vivo observational and physiological data. In addition, we have included features that allow observers to capture video from real-time camera feeds and import saved video for retroactive data collection. By using Microsoft Excel-based spreadsheets, also called keystroke files, assessment and treatment sessions are exported into a single document using the click of a button. Integrated interobserver agreement metrics allow comparisons across primary and reliability observers, with the output exported into a spreadsheet for easy reference. All file system interactions are handled by the user interface, so files and folders are created and managed without manual intervention. This software is available free-of-charge through the Microsoft Store for Windows 10 and 11 and the source code is publicly available on GitHub.
This study's purpose is to introduce a new measurement system that objectively assesses the social validity of behavioral feeding intervention from the child's perspective via the concurrent measurement of two dimensions of emotion. To date, the primary measures of social validity for behavioral feeding intervention are caregiver treatment acceptability and satisfaction surveys. This is the first study to objectively measure two dimensions of emotion, physiological arousal and emotional valence, while children received behavioral intervention for feeding difficulties. Data collectors used a new open‐source data collection software, cometrics, developed to synchronize and record physiological and observational data. Physiological data was collected using a wearable biosensor and observers recorded an index of child happiness, unhappiness, or neither using definitions by Phipps et al. (2022) for six children with a pediatric feeding disorder. Two out of six children needed programmed habituation to the device before data collection. All children assented to wearing the device during data collection. Recorded indices mapped to separable physiological states using electrodermal activity and its constituent components, skin conductance responses and skin conductance level, in addition to skin temperature. Findings demonstrated the feasibility of measuring two dimensions of child emotions during behavioral feeding intervention and revealed that children's physiological responses were distinctly different during intervals scored as happy, unhappy, or neither. This new data collection system has implications for future research on the child's emotional experience of behavioral feeding treatment and increases the possibilities for improving clinical practice.
22 November 2023 in Machine Learning with Applications