IoB: Internet of Behaviors

Permanent URI for this collection


Recent Submissions

Now showing 1 - 3 of 3
  • Item
    Webcam Eye Tracking for Desktop and Mobile Devices: A Systematic Review
    ( 2023-01-03) Heck, Melanie ; Becker, Christian ; Deutscher, Viola
    Building the Internet of Behaviors (IOB) obviously requires capturing human behavior. Sensor input from eye tracking has been widely used for profiling in market research, adaptive user interfaces, and other smart systems, but requires dedicated hardware. The wide spread of webcams in consumer devices like phones, tablets, notebooks, and smart TVs has fostered eye tracking with commodity cameras. In this paper, we present a systematic review across the IEEE and ACM databases -- complemented by snowballing and input from eye tracking experts at CHI 2021 -- to list and characterize publicly available webcam eye trackers that estimate the point-of-regard on devices with no additional hardware. Information from articles was supplemented by searching author websites and code repositories, and contacting authors. 16 eye trackers were found that can be used. The restrictions regarding license terms and technical performance are presented, enabling developers to choose an appropriate software for their IoB application.
  • Item
    Introduction to the Minitrack on IoB: Internet of Behaviors
    ( 2023-01-03) Kjærgaard, Mikkel ; Muccini, Henry ; Alipour, Mina ; Tourchi Moghaddam, Mahyar
  • Item
    Input Output HMM for Indoor Temperature Prediction in Occupancy Management Under User Preferences
    ( 2023-01-03) Shahin, Kamrul Islam ; Das, Anooshmita ; Kjærgaard, Mikkel
    In this paper, a probabilistic machine learning method is proposed to predict the indoor temperature of an office environment. An IOHMM-based model is developed to represent the office environment under different circumstances of heating sources. One year of time series data is observed and studied to learn the dynamics of the indoor thermal states. The uncertainty associated with the changing aspects of the indoor temperature and its dependence on the outdoor temperature is considered in the model development. The well-known Baum Welch and forward-backward algorithms are adapted to learn the model parameters. Then, the Viterbi algorithm is used to predict the maximum path of hidden states, leading to predicting the most likely future temperatures. A numerical application is presented to demonstrate the model development steps and the training and testing results. Finally, the model's performance is validated using leave-one-out cross-validation, which shows that the model has a prediction accuracy of about 78%.