Huiqun Yu

TL;DR: A data-efficient learning approach that combines several techniques of machine learning and statistics for performance prediction of configurable systems is proposed, called DECART, and a sample quality metric is proposed and introduced to introduce a quantitative analysis of the quality of a sample forperformance prediction.

TL;DR: This paper proposes a general IoT-fog-cloud architecture that fully exploits the advantages of fog and cloud, and proposes an ETCORA algorithm to solve the problem, improving the energy consumption and completion time of application requests.

TL;DR: This paper proposes a framework called defect prediction via attention-based recurrent neural network (DP-ARNN), which first parses abstract syntax trees of programs and extracts them as vectors and employs the attention mechanism to further generate significant features for accurate defect prediction.

TL;DR: A novel SDN-based geographic routing protocol for VANET, based on node location, vehicles density and digital map is proposed, which performs much better than related routing protocols in terms of both packet delivery ratio and delivery delay time.

TL;DR: A hybrid multi-objective optimization algorithm called SMTIBEA that combines the indicator-based evolutionary algorithm (IBEA) with the satisfiability modulo theories (SMT) solving is proposed that significantly extends the expressiveness of constraints and simultaneously achieves a comparable performance.