With the rapid development of online courses, the requirements of personalized course recommendation have been increasing. The traditional collaborative filtering algorithm confronts with the challenge of cold start, which is difficult to settle on online course recommendation effectively. In this paper, we propose a novel click through rate (CTR) model for personalized online course recommendation, with discriminative user features, item features and cross features. The feature representation ability of the CTR model is improved and the serious challenge of cold start is alleviated. Furthermore, transfer learning is introduced to deal with the problem of insufficient data in models training. More specially, eye tracking technology is applied to capture the users' cognitive styles, which are visualized with the heat map and fixation point trajectory. Finally, the recommendation interface sent to the learners, according to the user's cognitive style. The experiments show that the novel CTR model improves the performance of the personalized online course recommendation.

Scaffold filling is a new combinatorial optimization problem in genome sequencing. The one-sided scaffold filling problem can be described as given an incomplete genome I and a complete (reference) genome G, fill the missing genes into I such that the number of common (string) adjacencies between the resulting genome I' and G is maximized. This problem is NP-complete for genome with duplicated genes and the best known approximation factor is 1.33, which uses a greedy strategy. In this paper, we prove a better lower bound of the optimal solution, and devise a new algorithm by exploiting the maximum matching method and a local improvement technique, which improves the approximation factor to 1.25. For genome with gene repetitions, this is the only known NP-complete problem which admits an approximation with a small constant factor (less than 1.5).