Ming Liu

VRCA: a clustering algorithm for massive amount of texts

2015 · International Conference on Artificial Intelligence

There are lots of texts appearing in the web every day. This fact enables the amount of texts in the web to explode. Therefore, how to deal with large-scale text collection becomes more and more …

Knowledge-oriented semantics modelling towards uncertainty reasoning

2016 · SpringerPlus

Distributed reasoning in M2M leverages the expressive power of ontology to enable semantic interoperability between heterogeneous systems of connected devices. Ontology, however, lacks the built-in, principled support to effectively handle the uncertainty inherent in M2M …

Towards continuous control of flippers for a multi-terrain robot using deep reinforcement learning

2017 · arXiv (Cornell University)

In this paper we focus on developing a control algorithm for multi-terrain tracked robots with flippers using a reinforcement learning (RL) approach. The work is based on the deep deterministic policy gradient (DDPG) algorithm, proven …

Topic-to-Essay Generation with Neural Networks

2018

We focus on essay generation, which is a challenging task that generates a paragraph-level text with multiple topics.Progress towards understanding different topics and expressing diversity in this task requires more powerful generators and richer training …

Advances in writing analytics : mapping the state of the field

2019 · Zürcher Hochschule für Angewandte Wissenschaften digital collection (Zurich University of Applied Sciences)

Writing analytics as a field is growing in terms of the tools and technologies developed to support student writing, methods to collect and analyze writing data, and the embedding of tools in pedagogical contexts to …

Design of double intelligent parking garage based on HuiYu technology

2019 · IOP Conference Series Materials Science and Engineering

Abstract In view of the ubiquitous parking problem in the city, a double-layer intelligent parking garage that saves space, is smart and labor-saving. On the basis of the existing parking garage, the first problem to …

Sentiment Analysis of Movie Reviews Based on LSTM-Adaboost

2022 · 2022 IEEE 5th Advanced Information Management, Communicates, Electronic and Automation Control Conference (IMCEC)

With the improvement of public living standards and the rapid development of the Internet, film works as cultural carriers have become an integral part of people's cultural and spiritual life. The booming movie industry has …

Fabric-Centric Computing

2023

Emerging memory fabrics and the resulting composable infrastructures have fundamentally challenged our conventional wisdom on how to build efficient rack/cluster-scale systems atop. This position paper proposes a new computing paradigm-called Fabric-Centric Computing (FCC)-that views the …

A cross-domain recommendation model by unified modelling high-order information and rating information

2023 · Journal of Information Science

Cross-domain recommendation models are proposed to enrich the knowledge in the target domain by taking advantage of the data in the auxiliary domain to mitigate sparsity and cold-start user problems. However, most of the existing …

Satellite Unsupervised Anomaly Detection Based on Deconvolution-Reconstructed Temporal Convolutional Autoencoder

2023 · IEEE Transactions on Consumer Electronics

Anomaly detection for orbiting satellites has become a paramount research focus in the aerospace domain. Data-driven methodologies, employing high-dimensional telemetry data, have exhibited significant potential for timely anomaly detection without the need for pre-existing models …

CogGPT: Unleashing the Power of Cognitive Dynamics on Large Language Models

2024 · arXiv (Cornell University)

Cognitive dynamics are pivotal to advance human understanding of the world. Recent advancements in large language models (LLMs) reveal their potential for cognitive simulation. However, these LLM-based cognitive studies primarily focus on static modeling, overlooking …

Multi-Channel CNN-Based Open-Set RF Fingerprint Identification for LTE Devices

2024 · IEEE Transactions on Cognitive Communications and Networking

Radio frequency fingerprint identification (RFFI) is a promising technique that exploits the transmitter-specific characteristics of the RF chain for identification. Disregarding its massive deployment, long-term evolution (LTE) systems have not fully benefited from RFFI. In …

From Aleatoric to Epistemic: Exploring Uncertainty Quantification Techniques in Artificial Intelligence

2025 · arXiv (Cornell University)

Uncertainty quantification (UQ) is a critical aspect of artificial intelligence (AI) systems, particularly in high-risk domains such as healthcare, autonomous systems, and financial technology, where decision-making processes must account for uncertainty. This review explores the …

Research on Dynamic Response and Electrical Collaborative Optimization of Firefighting Water Supply Equipment Based on Intelligent Edge Computing - Breakthrough with Multimodal Perception and Digital Twin Technology

2025

Traditional electrical interlocking control technology faces numerous challenges in its application to firefighting water supply systems, such as sensor signal delays, mismatched logic for pump start-stop with fire scenarios, excessive energy consumption, and increased equipment …

Learning to Actively Learn Neural Machine Translation

2018

Traditional active learning (AL) methods for machine translation (MT) rely on heuristics. However, these heuristics are limited when the characteristics of the MT problem change due to e.g. the language pair or the amount of …

Neural Speech Synthesis with Transformer Network

2019 · Proceedings of the AAAI Conference on Artificial Intelligence

Although end-to-end neural text-to-speech (TTS) methods (such as Tacotron2) are proposed and achieve state-of-theart performance, they still suffer from two problems: 1) low efficiency during training and inference; 2) hard to model long dependency using …