Knowledge tracing predicts students' performance in future tasks by evaluating their previous responses to questions.Current approaches obtain a hidden state vector as the student's mastery of knowledge, but they lack interpretability of the relationship between this state and the student's actual knowledge level.In addition, they ignore the phenomenon of transfer during the learning process, which makes it difficult to derive real gains for students.In this paper, we propose a method called IDSKT, which integrates learning theories in psychology to better access the dynamic knowledge level.What's more, we adapt the content of priori knowledge, adopt selfsupervised learning to improve the knowledge changes due to transfer in the process of learning interactions, and obtain the global performance of students' knowledge as the model's inputs.Experimental results on real datasets show that our method outperforms all baseline methods.

How to design a robotic hand reflecting human hand motion information as much as possible is a constantly exploring problem. In this paper, we propose an approach to mechanical design of compliant underactuated finger for prosthetic hand based on the decomposition of human hand movements. Hand movements are decomposed into primary and secondary motion in PCA coordinate system. The primary motion is achieved in free motion via actuators, and the secondary motion is implemented with mechanical compliance matching statistics characteristic of human motion data. Although analysis and design of single finger is always throughout this paper, the same method can be generalized to the whole hand design and the parameters design of other mechanical configuration.