Wei Liu

An android application implementing the integration of a cloud server and an iBeacon

2015

The objective of the project was to develop an android based mobile application which is targeted to be used in MICE (Meetings, incentives, conferencing, and exhibitions) applications. A cloud server is set up and is …

An Event Ontology Description Framework Based on SKOS

2015

Event ontology is a new paradigm for describing event-based knowledge in web, including action, time, place and objects in event. But it lacks a unified language for description of event classes or event individuals. Simple …

An Ensemble Multilabel Classification for Disease Risk Prediction

2017 · Journal of Healthcare Engineering

It is important to identify and prevent disease risk as early as possible through regular physical examinations. We formulate the disease risk prediction into a multilabel classification problem. A novel Ensemble Label Power-set Pruned datasets …

Bilingual Education Transformation on Textiles Material Experiment

2017 · DEStech Transactions on Social Science Education and Human Science

Bilingual education is a great attempt of high education reform in our country, and becomes the new question facing by many teachers. This study discuss a bilingual education of Textile Material Experiment on teaching efficiency …

Homomorphic Consortium Blockchain for Smart Home System Sensitive Data Privacy Preserving

2019 · IEEE Access

The relative low level of smart home system (SHS) device information security may threaten the privacy of users. In this paper, we propose a homomorphic consortium blockchain for SHS sensitive data privacy preserving (HCB-SDPP), which …

Fast Stochastic Ordinal Embedding With Variance Reduction and Adaptive Step Size

2019 · IEEE Transactions on Knowledge and Data Engineering

Learning representation from relative similarity comparisons, often called ordinal embedding, gains rising attention in recent years. Most of the existing methods are based on semi-definite programming (SDP), which is generally time-consuming and degrades the scalability, …

Improved DNN-HMM English Acoustic Model Specially For Phonotactic Language Recognition

2019

The now-acknowledged sensitive of Phonotactic Language Recognition (PLR) to the performance of the phone recognizer front-end have spawned interests to develop many methods to improve it. In this paper, improved Deep Neural Networks Hidden Markov …

Environment-induced sudden change of coherence in quantum systems

2020 · Physical Review A

Manipulating dynamical evolution is an important task in quantum information. The sudden death phenomenon (SDP), which is predicted to be unattainable beyond entanglement [T. Yu and J. H. Eberly, Sudden death of entanglement, Science 323, …

Towards Practical Adam: Non-Convexity, Convergence Theory, and Mini-Batch Acceleration

2021 · arXiv (Cornell University)

Adam is one of the most influential adaptive stochastic algorithms for training deep neural networks, which has been pointed out to be divergent even in the simple convex setting via a few simple counterexamples. Many …

Targeted Physical-World Attention Attack on Deep Learning Models in Road Sign Recognition

2020 · arXiv (Cornell University)

Real world traffic sign recognition is an important step towards building autonomous vehicles, most of which highly dependent on Deep Neural Networks (DNNs). Recent studies demonstrated that DNNs are surprisingly susceptible to adversarial examples. Many …

Structure-Aware Feature Generation for Zero-Shot Learning

2021 · arXiv (Cornell University)

Zero-Shot Learning (ZSL) targets at recognizing unseen categories by leveraging auxiliary information, such as attribute embedding. Despite the encouraging results achieved, prior ZSL approaches focus on improving the discriminant power of seen-class features, yet have …

CO2Sum:Contrastive Learning for Factual-Consistent Abstractive Summarization

2021 · arXiv (Cornell University)

Generating factual-consistent summaries is a challenging task for abstractive summarization. Previous works mainly encode factual information or perform post-correct/rank after decoding. In this paper, we provide a factual-consistent solution from the perspective of contrastive learning, …

MR-DBIFOA: a parallel Density-based Clustering Algorithm by Using Improve Fruit Fly Optimization

2022 · 電腦學刊

<p>Clustering is an important technique for data analysis and knowledge discovery. In the context of big data, the density-based clustering algorithm faces three challenging problems: unreasonable division of data gridding, poor parameter optimization ability and …

A feature lightweight method in optimized acoustic encoder

2023

This paper is based on end-to-end speech recognition based on convolutional neural network technology. The problem that convolutional neural networks are difficult to balance accuracy and model size is analysed and studied. A new acoustic …

Runtime verification of self-adaptive multi-agent system using probabilistic timed automata

2023 · Journal of Intelligent & Fuzzy Systems

The self-adaptive multi-agent system requires adaptive adjustments based on the dynamic environment during its runtime. Heterogeneous agent can accomplish different task goals, enhance the efficiency of system operation, but its complex collaboration problem poses new …

DetermLR: Augmenting LLM-based Logical Reasoning from Indeterminacy to Determinacy

2023 · arXiv (Cornell University)

Recent advances in large language models (LLMs) have revolutionized the landscape of reasoning tasks. To enhance the capabilities of LLMs to emulate human reasoning, prior studies have focused on modeling reasoning steps using various thought …

A Blockchain-based Smart Contract Model for Secured Energy Trading management in Smart Microgrids

2024

The extension of emerging renewable energy sources such as wind and water turbines, solar panels, and the increasing usage of electric vehicles requires the supply and distribution of energy in a small device on local …

ToolRerank: Adaptive and Hierarchy-Aware Reranking for Tool Retrieval

2024 · arXiv (Cornell University)

Tool learning aims to extend the capabilities of large language models (LLMs) with external tools. A major challenge in tool learning is how to support a large number of tools, including unseen tools. To address …

Implementation of Multidimensional Interactive Teaching Model in College English Teaching

2024 · Advances in Educational Technology and Psychology

This paper aims to explore the practical implementation of the multidimensional interactive teaching model in college English teaching and its impact on students' learning outcomes. Through literature review and empirical research, we find that the …

Single-shot readout of a superconducting qubit using a thermal detector

2024 · Nature Electronics

Abstract Measuring the state of a qubit is a key fundamental operation of a quantum computer. High-fidelity single-shot readout of superconducting qubits can be achieved using parametric amplifiers at millikelvin temperatures. However, scaling parametric amplifiers …

Method for rock fracture prediction and early warning: Insight from fusion of multi-physics field information

2024 · Heliyon

. Subsequently, the study defines the probability function of rock damage during loading and fracture, enabling the realization of probability-based warnings for rock fracture. This approach introduces a new perspective on rock fracture prediction, significantly …

Wasserstein Discriminant Dictionary Learning for Graph Representation

2024 · IEEE Transactions on Pattern Analysis and Machine Intelligence

Mining discriminative graph topological information plays an important role in promoting graph representation ability. However, it suffers from two main issues: (1) the difficulty/complexity of computing global inter-class/intra-class scatters, commonly related to mean and covariance …

Ontologies-based Knowledge Representation Method for Improving Learning Performance in the Engineering Drawing Course

2024 · Computer-Aided Design and Applications

Computer-Aided Design and Applications is an international journal on the applications of CAD and CAM. It publishes papers in the general domain of CAD plus in emerging fields like bio-CAD, nano-CAD, soft-CAD, garment-CAD, PLM, PDM, …

AutoFAIR : Automatic Data FAIRification via Machine Reading

2024 · arXiv (Cornell University)

The explosive growth of data fuels data-driven research, facilitating progress across diverse domains. The FAIR principles emerge as a guiding standard, aiming to enhance the findability, accessibility, interoperability, and reusability of data. However, current efforts …

ChemVLM: Exploring the Power of Multimodal Large Language Models in Chemistry Area

2024 · arXiv (Cornell University)

Large Language Models (LLMs) have achieved remarkable success and have been applied across various scientific fields, including chemistry. However, many chemical tasks require the processing of visual information, which cannot be successfully handled by existing …

Sequential Recommendation via Adaptive Robust Attention with Multi-dimensional Embeddings

2024 · arXiv (Cornell University)

Sequential recommendation models have achieved state-of-the-art performance using self-attention mechanism. It has since been found that moving beyond only using item ID and positional embeddings leads to a significant accuracy boost when predicting the next …

Learning Triple-View Representation Discrepancy for Multivariate Time Series Anomaly Detection with Multi-Scale Patching

2024

Multivariate time series anomaly detection is a longstanding but crucial technology, holding significant potential for system security and stability. Prior studies focus on designing sophisticated architectures, integrating advanced modules (e.g., CNN, LSTM, and Transformer), and …

Time-enhanced Dynamic Graph Network for Next POI Recommendation

2024

Predicting the next Point-of-Interest (POI) is crucial for location-based services. In this paper, we propose the Time-enhanced Sequence Prediction Model (TSPM) to improve the accuracy of next POI recommendations by incorporating temporal information and dynamic …

Graph-Based Multimodal Contrastive Learning for Chart Question Answering

2025 · arXiv (Cornell University)

Chart question answering (ChartQA) is challenged by the heterogeneous composition of chart elements and the subtle data patterns they encode. This work introduces a novel joint multimodal scene graph framework that explicitly models the relationships …

An Effect Study of Random Disturbances on Attractive Region Boundary of Chaotic Attractors in Wind Power Systems

2025

The stochasticity of wind-based power generation systems brings new challenges to power systems. The stochasticity can be regarded as an external disturbance, which will have an impact on the wind-based power generation systems. The attractive …

Discrete Collaborative Filtering

2016

We address the efficiency problem of Collaborative Filtering (CF) by hashing users and items as latent vectors in the form of binary codes, so that user-item affinity can be efficiently calculated in a Hamming space. …

Attentive Collaborative Filtering

2017

Multimedia content is dominating today's Web information. The nature of multimedia user-item interactions is 1/0 binary implicit feedback (e.g., photo likes, video views, song downloads, etc.), which can be collected at a larger scale with …

Lexicon Enhanced Chinese Sequence Labeling Using BERT Adapter

2021

Wei Liu, Xiyan Fu, Yue Zhang, Wenming Xiao. Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 1: Long Papers). 2021.

ERNIE 3.0: Large-scale Knowledge Enhanced Pre-training for Language Understanding and Generation

2021 · arXiv (Cornell University)

Pre-trained models have achieved state-of-the-art results in various Natural Language Processing (NLP) tasks. Recent works such as T5 and GPT-3 have shown that scaling up pre-trained language models can improve their generalization abilities. Particularly, the …