Dianhui Mao

Dianhui Mao

Auto-generated profile, based on publicly available information

Dianhui Mao

Beijing Technology and Business University

Research Focus & Metrics

Academic Career Length

14Years (2013-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
12 July 2013 in Journal of Zhejiang University SCIENCE C
Verified
Journal Article
Closed access
PDF file
JCJian Cao
Jian Cao
DMDian-Hui Mao
Dian-Hui Mao
QCQiang Cai
Qiang Cai
HLHaisheng LI
Haisheng LI
JDJunping Du
Junping Du
Object representation based on local features is a topical subject in the domain of image understanding and computer vision. We discuss the defects of global features in present methods and the advantages of local features in object recognition, and briefly explore state-of-the-art recognition methods using local features, especially the main approaches of local feature extraction and object representation. To clearly explain these methods, the problem of local feature extraction is divided into feature region detection, feature region description, and feature space optimization. The main components and merits of these steps are presented. Technologies for object presentation are classified into three types: vector space, sliding window, and structure relationship models. Future development trends are discussed briefly.

30 September 2024 in IEEE Access
Verified
Journal Article
Open access
XZXinyi Zhao
Xinyi Zhao
DZDi Zhang
Di Zhang
HYhuanpu yin
huanpu yin
DMDianhui Mao
Dianhui Mao
HLHaisheng LI
Haisheng LI
Millimeter wave (mmWave) radar is an attractive solution for non-contact vital sign monitoring due to its characteristics of robustness against noise, interference, and high-range resolutions. However, due to the attenuation of mmWave signal strength with distance, most previous methods require users to be relatively close to the radar (<2.5m), and the estimation of vital signs is inaccurate due to the influence of surrounding objects. In this paper, we propose a vital sign remote monitoring method based on mmWave sensing, which can estimate the heart rate of multiple users at a long distance. We first propose an object location detection method based on windowing minimum variance distortionless response to enhance the signal SNR from weak human body reflections and obtain fine-grained each user’s location. Then we design a vital sign estimation method based on wavelet packet decomposition to extract precision vital sign from composite reflection signal. We evaluate the system performance and the impact of different factors, including the distance,angle, and multi-users scenario. Experimental results show that our method can achieve the heart rate accurately with a mean absolute error (MAE) of 3.5Bpm and mean absolute percentage error (MAPE) of 4% within 8m.

11 May 2026 in ICST Transactions on Scalable Information Systems
Verified
Journal Article
Open access
PDF file
CGChenchen Guo
Chenchen Guo
KWKehao Wang
Kehao Wang
DMDianhui Mao
Dianhui Mao
YXYunlong Xiong
Yunlong Xiong
YLYiwen Lyu
Yiwen Lyu
JCJunhua Chen
Junhua Chen
INTRODUCTION: Question answering tasks in the Standard Essential Patent (SEP) domain impose high demands on models for professional terminology comprehension, regulatory interpretation, and factual accuracy. Existing general-purpose large language models show limitations in this field, mainly in knowledge retrieval accuracy, semantic matching, and legal compliance of generated content. Therefore, there is an urgent need to develop a specialized intelligent QA system tailored for the SEP domain.OBJECTIVES: This paper aims to develop an intelligent QA system for the SEP domain, SEP-LLM, to improve knowledge retrieval, semantic matching, and content compliance, providing high-quality automated answers to SEP-related questions.METHODS: We collected and curated a large set of SEP-related regulations, technical standards, and judicial cases to build a high-quality QA dataset. Leveraging the LightRAG framework, a large language model was used to extract entities and relationships from documents, constructing a structured SEP knowledge graph with incremental updates to ensure dynamic completeness. In retrieval, a two-layer strategy addresses both fine-grained entity queries and broader thematic searches, improving accuracy and coverage. In generation, DeepSeek-LLM-7B was fine-tuned with LoRA on SEP-specific instructions and terminology, enhancing the model’s understanding and generation capabilities while significantly reducing training and inference resource requirements.RESULTS: Experimental results demonstrate that SEP-LLM significantly outperforms leading general-purpose models, including GPT-4o and Qwen3-235B, across three key metrics: BLEU-4, ROUGE-L, and Accuracy. These findings underscore its superior performance and promising potential for professional Quality Assurance within SEP domain.CONCLUSION: The LightRAG-based SEP-LLM system effectively enhances knowledge retrieval, semantic understanding, and compliance in SEP QA tasks, demonstrating the potential of retrieval-augmented generation techniques in specialized domains and providing a practical solution for intelligent information services in the SEP field.

15 September 2024
Verified
Conference Paper
Open access
JYJiajie Yang
Jiajie Yang
DMDianhui Mao
Dianhui Mao
DZDenghui Zhang
Denghui Zhang
In the field of computational intelligence and data analytics, the detection of fake food reviews has emerged as a pressing challenge, exacerbated by the widespread use of social media. These fraudulent reviews, particularly prevalent in the food and beverage industry, distort consumer decision-making and disrupt market fairness. To address this, we propose GMF-R, an innovative multimodal fusion framework based on Graph Attention Network (GAT), designed to effectively detect fake food reviews. The framework features end-to-end trainability and introduces advanced multimodal feature processing mechanisms, including fine-grained cross-modal interactions, a shared feature space, and multimodal graph construction. By utilizing GAT, GMF-R can adaptively assign attention weights to key nodes and accurately capture complex inter-modal relationships. Experimental results demonstrate that GMF-R achieves a 97.4% accuracy rate and a 98.1% F1 score on the Yelp reviews website dataset, significantly outperforming previous state-of-the-art models.