Interactive Tool in Digital Learning Ecosystem for Adaptive Online Learning Performance

The objective of this research was as follows: 1) to develop an interactive tool in a digital learning ecosystem for adaptive online learning performance; 2) to carry out a suitability assessment of this process. The documentary research method was used in this study. The results showed a model of an interactive tool in a digital learning ecosystem for adaptive online learning performance consisted of two phases. Phase 1: The development of an interactive tool in a digital learning ecosystem for adaptive online learning performance. This includes the following four design steps: 1) Reviewed literature and previous studies regarding an interactive tool, a digital learning ecosystem, and adaptive online learning performance to study the model, characteristics, and previous research. 2) Studied relevant research of an interactive tool in a digital learning ecosystem for adaptive online learning performance. 3) Designed an adaptive online learning performance model using an interactive tool in a digital learning ecosystem. 4) Developed a digital learning ecosystem. Phase 2: Evaluated the appropriateness of the interactive tool for an adaptive online learning performance model; this was checked for suitability by twelve experts and resulted in a conclusion. The results of the suitability evaluation revealed that the interactive tool for adaptive online learning performance was at the highest level.

Adaptive Online Learning for the Autoregressive Integrated Moving Average Models

This paper addresses the problem of predicting time series data using the autoregressive integrated moving average (ARIMA) model in an online manner. Existing algorithms require model selection, which is time consuming and unsuitable for the setting of online learning. Using adaptive online learning techniques, we develop algorithms for fitting ARIMA models without hyperparameters. The regret analysis and experiments on both synthetic and real-world datasets show that the performance of the proposed algorithms can be guaranteed in both theory and practice.

Adaptive Online Learning for Time Series Prediction

We study the problem of predicting time series data using the autoregressive integrated moving average (ARIMA) model in an online manner. Existing algorithms require model selection, which is time consuming and inapt for the setting of online learning. Using adaptive online learning techniques, we develop algorithms for fitting ARIMA models with fewest possible hyperparameters. We analyse the regret bound of the proposed algorithms and examine their performance using experiments on both synthetic and real world datasets