Feng Wang

Research on the Strategic Development of the Reform and Transformation of Independent College to Application-Oriented College-Deepen the reform of the system and mechanism of application-oriented college

2016

Independent colleges as local colleges, after more than 10 years of development, from initial infrastructure development to the current internal development, based on Parent College rapid promotion, has playing a great role in the whole …

Exploiting semantic knowledge base for patent retrieval

2017

Patent retrieval is considered as recall-oriented retrieval that aims to find all relevant patent documents for a patent query. However, current methods encounter the term mismatch problem, because of the frequent use of nonstandard technical …

Fuzzy Comprehensive Evaluation Method for On-line Monitoring Data Quality of Substation Equipment

2019

This paper analyses the existing problems in on-line monitoring and data quality evaluation of substation equipment, and proposes a multi-dimensional fuzzy comprehensive evaluation method for on-line monitoring data quality of substation equipment. The evaluation index …

DP2Net: Defense Against Adversarial Examples by Detecting Perturbed Pixels

2022 · 2022 7th International Conference on Signal and Image Processing (ICSIP)

Deep neural network technology is becoming more and more powerful, and its technical performance is obvious to all. However, the emergence of adversarial samples has raised concerns about the security of deep neural networks. In …

A Data Storage Method of Intelligent Substation Based on Physical Model

2023

In view of the sharp increase in the amount of data in intelligent substations at present, the gap between the data transmission mode and the data storage mode is large, resulting in the problem of …

YuLan: An Open-source Large Language Model

2024 · arXiv (Cornell University)

Large language models (LLMs) have become the foundation of many applications, leveraging their extensive capabilities in processing and understanding natural language. While many open-source LLMs have been released with technical reports, the lack of training …

SDT: Towards a Blockchain-Based Secure Data Trading Application

2024

Advances in AI, IoT, and 5G/6G technologies have made data increasingly valuable for industrial and academic purposes. Data trading is evolving with blockchain adoption, which offers key security features like non-repudiation and traceability. However, challenges …

Adapting Large Language Models to Forecast in Frequency Domain

2025

Large language models (LLMs) have recently been applied to time series forecasting to leverage their reasoning and pattern recognition capabilities. Compared to task-specific forecasting models, LLMs exhibit generalizability and a broad understanding of cross-domain knowledge. …

Design of Fault Diagnosis and Fault Prediction System for Stacker Traveling Mechanism Based on Digital Twin

2025 · 電腦學刊

This paper addresses the typical fault diagnosis and prediction problems of stacker cranes in the intelligent manufacturing process. Firstly, a digital twin of the target object is constructed, achieving the modeling of physical space modules, …

Explaining Recommendations Based on Feature Sentiments in Product Reviews

2017

The explanation interface has been recognized important in recommender systems as it can help users evaluate recommendations in a more informed way for deciding which ones are relevant to their interests. In different decision environments, …

Improving Neural Machine Translation with Conditional Sequence Generative Adversarial Nets

2018

Zhen Yang, Wei Chen, Feng Wang, Bo Xu. Proceedings of the 2018 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long Papers). 2018.

Joint Extraction of Entities and Relations Based on a Novel Tagging Scheme

2017 · arXiv (Cornell University)

Joint extraction of entities and relations is an important task in information extraction. To tackle this problem, we firstly propose a novel tagging scheme that can convert the joint extraction task to a tagging problem. …

Self-attention Aligner: A Latency-control End-to-end Model for ASR Using Self-attention Network and Chunk-hopping

2019

Self-attention network, an attention-based feedforward neural network, has recently shown the potential to replace recurrent neural networks (RNNs) in a variety of NLP tasks. However, it is not clear if the self-attention network could be …