Author name cluster

Jianjun Wu

Possible papers associated with this exact author name in Arrow. This page groups case-insensitive exact name matches and is not a full identity disambiguation profile.

3 papers

1 author row

EAAI Journal 2026 Journal Article

Fusing acoustic emission and deep learning for automatic identification of progressive rock fracture

Tongxiaoyu Wang
Jiang Xiao
Xiao Wang
Sen Zhang
Xiaofei Li
Yujiang Liu
Wenkai Bai
Jianjun Wu

Accurate and continuous identification of progressive rock fracture stages is critical for instability early warning in geotechnical engineering. Traditional acoustic emission (AE) parameters often fail to fully characterize the nonlinear and dynamic nature of rock failure. This study proposes a data-driven framework integrating Mel-frequency cepstral coefficients (MFCCs) with a hybrid deep learning model for automatic, point-wise recognition of fracture stages. Full-waveform AE signals from sandstone under uniaxial compression were transformed into MFCC sequences and synchronized with normalized stress. MFCC-3 showed the strongest correlation with stress (Pearson r = 0. 52) and served as the optimal spectral descriptor. A convolutional neural network (CNN)-Transformer-bidirectional gated recurrent unit (BiGRU) hybrid model was developed to extract local time-frequency features, capture long-range dependencies, and model bidirectional temporal dynamics. Evaluated on 35, 318 time-aligned samples via stratified five-fold cross-validation, the model achieved a mean accuracy of 96. 95% (±0. 15%) and a macro-F1 score of 0. 97, significantly outperforming baseline models as confirmed by statistical testing. Ablation studies verified each module's contribution and the robustness of MFCC-3. Interpretability analyses revealed physically meaningful decision patterns, and early-warning evaluation reliably identified unstable crack propagation approximately 27. 5% of the loading duration prior to peak stress. The experiments were conducted under controlled laboratory conditions (sandstone, uniaxial compression); further validation in complex in-situ environments and diverse lithologies is required. This work establishes a transparent and extensible foundation for intelligent AE-based monitoring of progressive rock fracture.

Details DOI

AAAI Conference 2026 Conference Paper

Neural Architecture for Fast and Reliable Coagulation Assessment in Clinical Settings: Leveraging Thromboelastography

Yulu Wang
Ziqian Zeng
Jianjun Wu
Zhifeng Tang

In an ideal medical environment, real-time coagulation monitoring can enable early detection and prompt remediation of risks. However, traditional Thromboelastography (TEG), a widely employed diagnostic modality, can only provide such outputs after nearly 1 hour of measurement. The delay might lead to elevated mortality rates. These issues clearly point out one of the key challenges for medical AI development: Making reasonable predictions based on very small data sets and accounting for variation between different patient populations, a task where conventional deep learning methods typically perform poorly. We present Physiological State Reconstruction (PSR), a new algorithm specifically designed to take advantage of dynamic changes between individuals and to maximize useful information produced by small amounts of clinical data through mapping to reliable predictions and diagnosis. We develop MDFE to facilitate integration of varied temporal signals using multi-domain learning, and jointly learn high-level temporal interactions together with attentions via HLA; furthermore, the parameterized DAM we designed maintains the stability of the computed vital signs. PSR evaluates with 4 TEG-specialized data sets and establishes remarkable performance -- predictions of R^2 > 0.98 for coagulation traits and error reduction around half compared to the state-of-the-art methods, and halving the inferencing time too. Drift-aware learning suggests a new future, with potential uses well beyond thrombophilia discovery towards medical AI applications with data scarcity.

PDF Details DOI

AAAI Conference 2019 Short Paper

DSINE: Deep Structural Influence Learning via Network Embedding

Jianjun Wu
Ying Sha
Bo Jiang
Jianlong Tan

Structural representations of user social influence are critical for a variety of applications such as viral marketing and recommendation products. However, existing studies only focus on capturing and preserving the structure of relations, and ignore the diversity of influence relations patterns among users. To this end, we propose a deep structural influence learning model to learn social influence structure via mining rich features of each user, and fuse information from the aligned selfnetwork component for preserving global and local structure of the influence relations among users. Experiments on two real-world datasets demonstrate that the proposed model outperforms the state-of-the-art algorithms for learning rich representations in multi-label classification task.

PDF Details