On automatic recommender algorithm with regularized convolutional neural network and IR technology in the self-regulated learning process

Abstract

Automatic recommendation algorithm is prominent component of many of today’s IR spectral signal educational applications. The most effective approaches for recommendation algorithm are based on the deep learning technology. The recommender system plays an important role in the field of IR spectral signal recognition. However, the infrared spectrometers often exist the problem of the low signal-to-noise and overlapped peaks. To address those issues, we propose an IR spectrum signal reconstruction approach with the framelet transform regularization. First, the famous framelet transform is introduced to reveal the difference between the overlap IR spectral signal and the high-resolution one. We find that the framelet coefficient distribution of the high-resolution IR spectral signal is sparser than that of the overlap one. Furthermore, to optimize the developed method, the alternating-direction-method-of-multipliers is introduced to calculate the IR spectral signals and the overlap function. Simulated and real experiments on the IR spectral signals illustrate that the developed method outperform the existed popular algorithms. The proposed approach is applied in the automatic recommender system that is crucial for IR spectrum teaching in the self-regulated learning process.