Home-based learning during school closure in Singapore: perceptions from the language classrooms

The outbreak of the COVID-19 pandemic in Singapore has resulted in the adoption of home-based learning (similar to remote or distance learning' worldwide) due to periodic school closures in Singapore. The media and academia have diverse views on the effectiveness of this alternative mode of education. This study draws data from teachers' interviews and students' focus group discussions of an ongoing large-scale baseline study on mother tongue education to reveal teachers' and students' perceptions of home-based learning. Findings showed that the participating teachers generally mimicked physical lessons online during home-based learning, and they faced difficulties in monitoring students' tasks online. Though students enjoyed the freedom of doing their learning tasks at their own pace, they were concerned with the lack of teachers' support and the social-emotional support from peers. With the feedback and reflections from teachers and students, it was observed that despite the availability of technology and online infrastructure, teachers need readiness for transiting between physical teaching and online instruction, whereas students need readiness for self-directed learning. From students' feedback, it was also noted that parents need readiness for educational technology and support for their children. To better prepare teachers, students, and parents for home-based learning, it is recommended that the developers provide more dedicated resources that take into consideration the different characteristics (e.g. orthography) of each language subject. Parents should also assume a greater role in monitoring their children's learning on behalf of the teachers for better effect in home-based learning.

General short-term load forecasting based on multi-task temporal convolutional network in COVID-19

The spread of the global COVID-19 epidemic has resulted in significant shifts in electricity consumption compared to regular days. It is unknown if standard single-task, single-indicator load forecasting algorithms can accurately reflect COVID-19 load patterns. Power practitioners urgently want a simple, efficient, and accurate solution for anticipating reliable load. In this paper, we first propose a unique collaborative TCN-LSTM-MTL short-term load forecasting model based on mobility data, temporal convolutional networks, and multi-task learning. The addition of the parameter sharing layers and the structure with residual convolution improves the data input diversity of the forecasting model and enables the model to obtain a wider time series receptive field. Then, to demonstrate the usefulness of the mobility optimized TCN-LSTM-MTL, tests were conducted in three levels and twelve base regions using 19 different benchmark models. It is capable of controlling predicting mistakes to within 1 % in the majority of tasks. Finally, to rigorously explain the model, the Shapley additive explanations (SHAP) visual model interpretation technology based on game theory is introduced. It examines the TCN-LSTM-MTL model's internal mechanism at various time periods and establishes the validity of the mobility indicators as well as the asynchronous relationship between indicator significance and real contribution.