Feng Liu

Fuzzy Transfer Learning Using an Infinite Gaussian Mixture Model and Active Learning

2018 · IEEE Transactions on Fuzzy Systems

Transfer learning is gaining considerable attention due to its ability to leverage previously acquired knowledge to assist in completing a prediction task in a related domain. Fuzzy transfer learning, which is based on fuzzy system …

Design and Implementation of Personalized Recommendation System under Big Data Platform

2018

To realize the seamless connection between educational resources and the era of big data, the personalized recommendation system is used as an important tool to solve information overload. This system can help people to automatically …

Research and Design of the Mutual Aid Tokenized Economy Structure Based on Blockchain Technology

2020

In the current time bank system, problems such as difficult time token to circulate, difficult to trust data, and insecure data exist. In order to solve these problems, a design and implementation of a time …

How does the Combined Risk Affect the Performance of Unsupervised Domain Adaptation Approaches?

2020 · arXiv (Cornell University)

Unsupervised domain adaptation (UDA) aims to train a target classifier with labeled samples from the source domain and unlabeled samples from the target domain. Classical UDA learning bounds show that target risk is upper bounded …

Semi-Supervised Heterogeneous Domain Adaptation: Theory and Algorithms

2022 · IEEE Transactions on Pattern Analysis and Machine Intelligence

Semi-supervised heterogeneous domain adaptation (SsHeDA) aims to train a classifier for the target domain, in which only unlabeled and a small number of labeled data are available. This is done by leveraging knowledge acquired from …

Exploration on curriculum reform of "power electronic technology" based on engineering education certification under the background of new engineering

2021 · 2021 2nd International Conference on Information Science and Education (ICISE-IE)

This paper analyzes the current situation and problems in the teaching of "power electronic technology" in our university according to the goal and orientation of talent training in Application-oriented Universities under the background of new …

Hypertension and Obesity: Risk Factors for Thyroid Disease

2022 · Frontiers in Endocrinology

Thyroid disease instances have rapidly increased in the past few decades; however, the cause of the disease remains unclear. Understanding the pathogenesis of thyroid disease will potentially reduce morbidity and mortality rates. Currently, the identified …

Research on patent classification based on hierarchical label semantics

2022 · 2022 3rd International Conference on Education, Knowledge and Information Management (ICEKIM)

Patent classification is an essential task in patent information management and knowledge mining. Most existing studies are based on the textual content of individual patent texts (e.g., titles and abstracts) for classification, but the patent …

Span extraction and contrastive learning for coreference resolution

2022

Coreference resolution is a primary task in natural language processing (NLP), designed to automatically identifyand classify noun phrases or pronouns that represent thesame mention. Most of the recent coreference resolution models extraction or cluster mentions. …

Learning to Augment Distributions for Out-of-Distribution Detection

2023 · arXiv (Cornell University)

Open-world classification systems should discern out-of-distribution (OOD) data whose labels deviate from those of in-distribution (ID) cases, motivating recent studies in OOD detection. Advanced works, despite their promising progress, may still fail in the open …

A novel prediction approach driven by graph representation learning for heavy metal concentrations

2024 · The Science of The Total Environment

The potential risk of heavy metals (HMs) to public health is an issue of great concern. Early prediction is an effective means to reduce the accumulation of HMs. The current prediction methods rarely take internal …

Research on Computer Image Recognition Technology Based on Artificial Intelligence

2024

In order to solve the problem of fast processing for ultra-high-resolution images in embedded systems, this paper proposes a multi-mode tracking and recognition method based on embedded processing architecture, through the construction of a multi-GPU …

Bridging the Gap: Self-Optimized Fine-Tuning for LLM-based Recommender Systems

2025 · arXiv (Cornell University)

Recent years have witnessed extensive exploration of Large Language Models (LLMs) on the field of Recommender Systems (RS). There are currently two commonly used strategies to enable LLMs to have recommendation capabilities: 1) The "Guidance-Only" …

BAMT-Net: a boundary-aware multi-task framework for 3D breast ultrasound lesion segmentation and classification

2026 · Medical & Biological Engineering & Computing

Mammography and ultrasound have long been the primary modalities for breast cancer screening; however, both methods still have certain limitations. In mammography, high breast density can sometimes obscure the visualization of lesions [ 1 , …