Fang Liu

A Novel Method of DS Evidence Theory for Multi-Sensor Conflicting Information

2018

The multi-sensor data fusion technique plays a significant role in fault diagnosis and in a variety of applications. Conflict management is an open issue in Dempster-Shafer evidence theory. In this paper, a novel multi-sensor data …

Design of Foreign Language Evaluation System for Application-Oriented Colleges Based on MOOC

2018 · Proceedings of the 2018 2nd International Conference on Education, Economics and Management Research (ICEEMR 2018)

As an essential aspect of foreign language teaching, evaluation model plays an important role in the promotion of teaching quality and effect. The paper explores the evaluation model in the MOOC environment and its influence …

An entanglement-based quantum network based on symmetric dispersive optics quantum key distribution

2019 · arXiv (Cornell University)

Quantum key distribution (QKD) is a crucial technology for information security in the future. Developing simple and efficient ways to establish QKD among multiple users are important to extend the applications of QKD in communication …

A Patch Diversity Transformer for Domain Generalized Semantic Segmentation

2023 · IEEE Transactions on Neural Networks and Learning Systems

Domain generalization (DG) is one of the critical issues for deep learning in unknown domains. How to effectively represent domain-invariant context (DIC) is a difficult problem that DG needs to solve. Transformers have shown the …

Stability and Stabilization of T–S Fuzzy Systems With a Periodic Variable Delay via Monotone Delay-Interval-Based Functional

2023 · IEEE Transactions on Fuzzy Systems

The stability and stabilization problems for T–S fuzzy systems with a periodic variable delay are analyzed in this article. First, an improved delay-dependent reciprocally convex inequality is presented to deal with the periodic variable delay, …

A Differentially Private Weighted Empirical Risk Minimization Procedure and Its Application to Outcome Weighted Learning

2026 · IEEE Transactions on Information Forensics and Security

Data used to train predictive models via empirical risk minimization (ERM) often contain sensitive personal information. While differential privacy (DP) provides mathematically provable bounds to protect such data, previous work has focused almost exclusively on …

Unsupervised Domain Adaption for Remote Sensing Semantic Segmentation with Self-Attention Mechanism

2023

The domain shift between the source and target domains limits the performance of traditional convolutional neural networks (CNNs) for feature extraction in remote sensing tasks. We propose an image translation network that uses generative adversarial …

Design of a Virtual Reality-Based Professional Simulation Training System for Elderly Care

2024

To address the current issues of limited practical training conditions, narrow scenarios, and a disconnect between theory and practice in elderly care professional training, this article proposes the design of an immersive virtual simulation system …

Imperfect Code Generation: Uncovering Weaknesses in Automatic Code Generation by Large Language Models

2024

The task of code generation has received significant attention in recent years, especially when the pre-trained large language models (LLMs) for code have consistently achieved state-of-the-art performance. However, there is currently a lack of a …

Delving into Parameter-Efficient Fine-Tuning in Code Change Learning: An Empirical Study

2024

Compared to Full-Model Fine-Tuning (FMFT), Parameter Efficient Fine-Tuning (PEFT) has demonstrated superior performance and lower computational overhead in several code understanding tasks, such as code summarization and code search. This advantage can be attributed to …

LONGCODEU: Benchmarking Long-Context Language Models on Long Code Understanding

2025 · arXiv (Cornell University)

Current advanced long-context language models offer great potential for real-world software engineering applications. However, progress in this critical domain remains hampered by a fundamental limitation: the absence of a rigorous evaluation framework for long code …