Selected Publications

You can also find my articles on my Google Scholar profile.
MotionDecipher: LLM-Assisted Clinical Interpretation of Human Motion Signals for Efficient Gait Analysis

MotionDecipher: LLM-Assisted Clinical Interpretation of Human Motion Signals for Efficient Gait Analysis Accepted

ACM International Joint Conference on Pervasive and Ubiquitous Computing (UbiComp 2027) / Proceedings of the ACM on Interactive, Mobile, Wearable and Ubiquitous Technologies (IMWUT 2026)

TLDR: This paper introduces MotionDecipher, an LLM-based framework that translates continuous human motion signals into clinical gait descriptions through a Human Motion Tokenizer, a Meta Feature Selector, and a Hybrid Context Constructor for In-Context Learning. Evaluated on gait lab data from 122 patients and 46 controls, MotionDecipher achieves 0.91 BERTScore (13% over GPT-5) and is ranked highest by clinical experts in Correctness, Completeness, and Conciseness.

DOI: https://doi.org/10.1145/3857982 (The paper will be officially published in December 2026; this DOI link will become active after publication.)

CausalGait: Towards Personalized Gait Interpretation via Causality-Informed Knowledge Graphs Accepted

HumanSys '26: Proceedings of the 4th International Workshop on Human-Centered Sensing, Modeling, and Intelligent Systems, 2026

TLDR: This paper introduces CausalGait, a framework that integrates clinical rules and measured gait data into personalized causal knowledge graphs, combining a Global Causal Graph, Patient-Specific Graphs, and Bayesian causal inference to identify the neuromuscular impairments behind each gait abnormality. Evaluated on 200 children with spastic Cerebral Palsy, CausalGait outperforms the Data-Driven baseline in faithfulness (0.868), infidelity (0.0023), and normalized AOPC (0.950).

Recommended citation: Ma M, Yang M, Clewes K, Lowe E, Rose J, Dong Y. CausalGait: Towards Personalized Gait Interpretation via Causality-Informed Knowledge Graphs[C]//Proceedings of the 4th International Workshop on Human-Centered Sensing, Modeling, and Intelligent Systems (HumanSys '26). 2026: 99-104. https://doi.org/10.1145/3842436.3843806 (Pending Publication)

BTAD: A binary transformer deep neural network model for anomaly detection in multivariate time series data

Published in Advanced Engineering Informatics, 2023

TLDR: This article introduces the Bi-Transformer anomaly detection method for anomaly detection in multivariate time series data, and proposes corresponding enhancements such as an adaptive multi-head attention mechanism and a modified Decoder structure to further improve the performance of BTAD. Experimental results on multiple mainstream multivariate time series datasets demonstrate that BTAD exhibits outstanding overall anomaly detection performance.

Recommended citation: Ma M, Han L, Zhou C. BTAD: A binary transformer deep neural network model for anomaly detection in multivariate time series data[J]. Advanced Engineering Informatics, 2023, 56: 101949.

Research and application of Transformer based anomaly detection model: A literature review

Published in Arxiv Preprint, 2024

TLDR: This article offers a detailed summary, synthesis, and analysis of transformer-based research and applications in the field of anomaly detection. To the best of our knowledge, this is also the first comprehensive review that focuses on the research related to Transformer in the context of anomaly detection.

Recommended citation: Ma M, Han L, Zhou C. Research and application of Transformer based anomaly detection model: A literature review[J]. arXiv preprint arXiv:2402.08975, 2024.