Search

In this article, we study knowledge concept recommendation in Massive Open Online Courses (MOOCs) in an explainable manner. Knowledge concepts, composing course units (e.g., videos) in MOOCs, refer to topics and skills that students are expected to master. Compared to traditional course recommendation in MOOCs, knowledge concepts recommendation has drawn more attention because students' interests over knowledge concepts can better revealstudents' real intention in a more refined granularity. However, there are three unique challenges in knowledge concept recommendation: (1) How to design an appropriate data structure to capture complex relationships between knowledge concepts, course units, and other participants (e.g., students, teachers)? (2) How to model interactions between students and knowledge concepts? (3) How to make explainable recommendation results to students? To tackle these challenges, we formulate the knowledge concept recommendation as a reinforcement learning task integrated with MOOC knowledge graph (KG). Specifically, we first construct MOOC KG as the environment to capture all the relationships and behavioral histories by considering all the entities (e.g., students, teachers, videos, courses, and knowledge concepts) on the MOOC provider. Then, to model the interactions between students and knowledge concepts, we train an agent to mimic students' learning behavioral patterns facing the complex environment. Moreover, to provide explainable recommendation results, we generate recommended knowledge concepts in the format of a path from MOOC KG to indicate semantic reasons. Finally, we conduct extensive experiments on a real-world MOOC dataset to demonstrate the effectiveness of our proposed method. [ABSTRACT FROM AUTHOR]

Inorganic halide perovskites such as cesium lead halide are promising due to their excellent thermal stability. Cesium lead iodide (CsPbI3) has a bandgap of 1.73 eV and is very suitable for making efficient tandem solar cells, either with low-bandgap perovskite or silicon. However, the phase instability of CsPbI3 is hindering the further optimization of device performance. Here, we show that high quality and stable α-phase CsPbI3 film is obtained via solvent-controlled growth of the precursor film in a dry environment. A 15.7% power conversion efficiency of CsPbI3 solar cells is achieved, which is the highest efficiency reported for inorganic perovskite solar cells up to now. And more importantly, the devices can tolerate continuous light soaking for more than 500 h without efficiency drop. [ABSTRACT FROM AUTHOR]

Perovskite light-emitting diodes (LEDs) are attracting great attention due to their efficient and narrow emission. Quasi-two-dimensional perovskites with Ruddlesden-Popper-type layered structures can enlarge exciton binding energy and confine charge carriers and are considered good candidate materials for efficient LEDs. However, these materials usually contain a mixture of phases and the phase impurity could cause low emission efficiency. In addition, converting three-dimensional into quasi-two-dimensional perovskite introduces more defects on the surface or at the grain boundaries due to the reduction of crystal sizes. Both factors limit the emission efficiency of LEDs. Here, firstly, through composition and phase engineering, optimal quasi-two-dimensional perovskites are selected. Secondly, surface passivation is carried out by coating organic small molecule trioctylphosphine oxide on the perovskite thin film surface. Accordingly, green LEDs based on quasi-two-dimensional perovskite reach a current efficiency of 62.4 cd A-1 and external quantum efficiency of 14.36%. [ABSTRACT FROM AUTHOR]

Inorganic perovskites such as CsPbX3 (X=Cl, Br, I) have attracted attention due to their excellent thermal stability and high photoluminescence quantum efficiency. However, the electroluminescence quantum efficiency of their light-emitting diodes was <1%. We posited that this low efficiency was a result of high leakage current caused by poor perovskite morphology, high non-radiative recombination at interfaces and perovskite grain boundaries, and also charge injection imbalance. Here, we incorporated a small amount of methylammonium organic cation into the CsPbBr3 lattice and by depositing a hydrophilic and insulating polyvinyl pyrrolidine polymer atop the ZnO electron-injection layer to overcome these issues. As a result, we obtained light-emitting diodes exhibiting a high brightness of 91,000 cd m−2 and a high external quantum efficiency of 10.4% using a mixed-cation perovskite Cs0.87MA0.13PbBr3 as the emitting layer. To the best of our knowledge, this is the brightest and most-efficient green perovskite light-emitting diodes reported to date. [ABSTRACT FROM AUTHOR]