| spelling |
oapen-20.500.12657-891502024-04-03T02:24:11Z Chapter Prediction of Cognitive Load during Industry-Academia Collaboration via a Web Platform Yusuf, Anthony Akanmu, Abiola Afolabi, Adedeji Murzi, Homero Cognitive load electroencephalogram industry-academia collaboration long short-term memory web platform thema EDItEUR::U Computing and Information Technology::UT Computer networking and communications::UTV Virtualization Web platforms are increasingly being used to connect communities, including construction industry and academia. Design features of such platforms could impose excessive cognitive workload thereby impacting the use of the platform. This is a crucial consideration especially for new web platforms to secure users’ interest in continuous usage. Understanding users’ cognitive workloads while using web platforms could help make necessary modifications and adapt the features to users’ preferences. Users’ usage patterns can be leveraged to predict the needs of users. Hence, the pattern of cognitive demand that users experience can be used to predict the cognitive load of web platform users. This could provide insights, generate feedback, and identify areas of modification that are critical for sustaining acceptability of web platforms. Using recurrent neural network, this study adopts electroencephalogram (EEG) data as a physiological measure of brain activity to predict brain signals (cognitive load) of users while interacting with a web platform designed to connect industry and academia for future workforce development. This paper presents a Long Short-Term Memory (LSTM) based approach to develop a model for predicting users’ cognitive load via EEG signals. Nineteen (19) potential end-users of the proposed web platform were recruited as participants in this study. The participants interacted with the web-platform in a real case scenario and their brain signals were captured using a five-channel EEG device. The validity of the proposed method was evaluated using root mean square error (RMSE), coefficient of determination (R2), and comparison of the predicted and actual EEG signals and mental workload. The results revealed the reliability of the model and provided a suitable method for predicting users brain signals while using web platforms. This could be leveraged to understand users’ cognitive demand which could provide insights for web platform improvements to engender users’ continuous usage 2024-04-02T15:48:03Z 2024-04-02T15:48:03Z 2023 chapter ONIX_20240402_9791221502893_119 2704-5846 9791221502893 https://library.oapen.org/handle/20.500.12657/89150 eng Proceedings e report application/pdf n/a 9791221502893_06.pdf https://books.fupress.com/doi/capitoli/979-12-215-0289-3_6 Firenze University Press 10.36253/979-12-215-0289-3.06 10.36253/979-12-215-0289-3.06 bf65d21a-78e5-4ba2-983a-dbfa90962870 9791221502893 137 12 Florence open access
|
| description |
Web platforms are increasingly being used to connect communities, including construction industry and academia. Design features of such platforms could impose excessive cognitive workload thereby impacting the use of the platform. This is a crucial consideration especially for new web platforms to secure users’ interest in continuous usage. Understanding users’ cognitive workloads while using web platforms could help make necessary modifications and adapt the features to users’ preferences. Users’ usage patterns can be leveraged to predict the needs of users. Hence, the pattern of cognitive demand that users experience can be used to predict the cognitive load of web platform users. This could provide insights, generate feedback, and identify areas of modification that are critical for sustaining acceptability of web platforms. Using recurrent neural network, this study adopts electroencephalogram (EEG) data as a physiological measure of brain activity to predict brain signals (cognitive load) of users while interacting with a web platform designed to connect industry and academia for future workforce development. This paper presents a Long Short-Term Memory (LSTM) based approach to develop a model for predicting users’ cognitive load via EEG signals. Nineteen (19) potential end-users of the proposed web platform were recruited as participants in this study. The participants interacted with the web-platform in a real case scenario and their brain signals were captured using a five-channel EEG device. The validity of the proposed method was evaluated using root mean square error (RMSE), coefficient of determination (R2), and comparison of the predicted and actual EEG signals and mental workload. The results revealed the reliability of the model and provided a suitable method for predicting users brain signals while using web platforms. This could be leveraged to understand users’ cognitive demand which could provide insights for web platform improvements to engender users’ continuous usage
|
