arXiv subjects

Weijian Zhou

Publications and source records attributed to Weijian Zhou.

3 recordsLinked to original sources

arXiv2026

From SQL Errors to Concept Gaps: An AI-Powered Knowledge Graph Analytics Platform for Personalized Feedback

This innovative practice full paper describes an AI-powered knowledge graph platform that connects SQL errors to conceptual gaps in undergraduate and graduate database systems courses. Students learning Structured Query Language (SQL) frequently struggle with semantic errors that reflect conceptual misunderstandings rather than syntax mistakes. A query may execute yet return incorrect results due to gaps spanning related concepts; misusing NATURAL JOIN in place of an explicit subquery reflects intertwined misunderstandings of JOIN, GROUP BY, and HAVING. Autograding systems detect correctness but provide surface-level feedback without connecting errors to the conceptual structure of the course. Educational knowledge graph research has shown the value of structured concept representations for curriculum analysis and adaptive learning, but these approaches have not been applied to diagnosing SQL misconceptions from student submissions. We present a platform that automatically extracts course concepts and relations from instructional materials, links them to student submission traces through a graph database, and classifies errors at the concept level. We evaluate the platform across two database systems courses at two universities, one using real student submissions and one using simulated submissions, through an expert study with five participants and an automated evaluation using an LLM as a judge. Results show that 95.7% of extracted nodes were rated as at least somewhat valid and 63.8% of triplets were rated fully correct. Expert feedback confirmed that the generated graphs align with instructor mental models and that mapping errors to course concepts provides actionable diagnostic insight; evaluating impact on student learning remains future work.

cs.CL↗

arXiv2021

Tuning Elastic Waves in Soft Phononic Crystal Cylinders via Large Deformation and Electromechanical Coupling

Soft electroactive materials can undergo large deformation subjected to either mechanical or electrical stimulus, and hence they can be excellent candidates for designing extremely flexible and adaptive structures and devices. This paper proposes a simple one-dimensional soft phononic crystal cylinder made of dielectric elastomer to show how large deformation and electric field can be used jointly to tune the longitudinal waves propagating in the PC. A series of soft electrodes are placed periodically along the dielectric elastomer cylinder, and hence the material can be regarded as uniform in the undeformed state. This is also the case for the uniformly pre-stretched state induced by a static axial force only. The effective periodicity of the structure is then achieved through two loading paths, i.e. by maintaining the longitudinal stretch and applying an electric voltage over any two neighbouring electrodes, or by holding the axial force and applying the voltage. All physical field variables for both configurations can be determined exactly based on the nonlinear theory of electroelasticity. An infinitesimal wave motion is further superimposed on the pre-deformed configurations and the corresponding dispersion equations are derived analytically by invoking the linearized theory for incremental motions. Numerical examples are finally considered to show the tunability of wave propagation behavior in the soft PC cylinder. The outstanding performance regarding the band gap (BG) property of the proposed soft dielectric PC is clearly demonstrated by comparing with the conventional design adopting the hard piezoelectric material. Note that soft dielectric PCs are susceptible to various kinds of failure (buckling, electromechanical instability, electric breakdown, etc.), imposing corresponding limits on the external stimuli.

cond-mat.soft↗

arXiv2020

Actively controllable topological phase transition in phononic beam systems

Topological insulators, which allow edge or interface waves but forbid bulk waves, have revolutionized our scientific cognition of acoustic/elastic systems. Due to their nontrivial topological characteristics, edge (interface)waves are topologically protected against defects and disorders. This superior and unique characteristic could lead to a wealth of new opportunities in applications of quantum and acoustic/elastic information processing. However, current acoustic/elastic topological insulators are still at an infancy stage where the theory and prediction only work in laboratories and there are still many problems left open before promoting their practical applications. One of the apparent disadvantages is their narrow working frequency range, which is the main concern in this paper. We design a one-dimensional phononic beam system made of a homogeneous epoxy central beam sandwiched by two homogeneous piezoelectric beams, and covered with extremely thin electrodes, periodically and separately placed. These electrodes are connected to external electric circuits with negative capacitors. We show that a topological phase transition can be induced and tuned by changing the values of the negative capacitors. It follows that the working frequency of the topologically protected interface mode can be widely changed, such that the working frequency range of the topological insulator can be considerably `broadened'. This intelligent topological device may also find wide applications in intelligent technologies that need controllable information processing of high precision.

physics.app-ph↗