Zhiqiu Huang

TL;DR: This paper proposes an automated approach to detect defects of API documents by leveraging techniques from program comprehension and natural language processing, and focuses on the directives of the API documents which are related to parameter constraints and exception throwing declarations.

TL;DR: A neighborhood based decision-theoretic rough set model (NDTRS) under the framework of DTRS is proposed and a new neighborhood classifier based on three-way decisions is constructed and compared with other classifiers.

TL;DR: A coupled matrix and tensor factorization model named TCE_R is proposed to more accurately complete the sparse traffic congestion matrix by collaboratively factorizing it with other matrices and tensors formed by other data.

TL;DR: A network-scale deep traffic prediction model called TrafficGAN is proposed, in which Generative Adversarial Nets (GAN) is utilized to predict traffic flows under an adversarial learning framework, which significantly outperforms both traditional statistical models and state-of-the-art deep learning models in network- scale short-term traffic flow prediction.

TL;DR: A multi-task adversarial spatial-temporal network model entitled MT-ASTN is proposed to effectively address the novel problem of predicting the crowd flow and flow OD simultaneously, and significantly outperforms state-of-the-art methods on both tasks.