ZWZhize Wu

Zhize Wu

*This is an algorithmically generated author record based on publicly available information.

Current Organizations / Institutes

The organizations/institutes from the scholar's latest article


Zhize Wu has a total of 34 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • A Novel Outlier Detection and Reconstruction Method for State of Health Prediction of Lithium-Ion Batteries

    by Ziwang Wang, Jie Meng, Yajun Zhao, Ding Li, Zhize Wu

    Accurate prediction of lithium-ion battery SOH is critical for the safety and lifespan extension of a battery system. Feature noise and insufficient model accuracy remain major obstacles. To address these challenges, this study proposes a correlation-driven outlier detection and reconstruction method grounded in multidimensional feature engineering to enhance SOH prediction. First, from five dimensions—constant current charging, constant voltage charging, incremental capacity, temperature, and unit time voltage change rate—this work systematically defines 45 degradation features, with 33 applicable to CALCE and 38 to NASA datasets due to dataset-specific signal availability. Second, for each target feature, it screens highly correlated feature subsets using the Pearson correlation coefficient. A linear mapping is then established through regression analysis to model the expected values, enabling identification and reconstruction of outliers. Finally, based on the reconstructed feature dataset, this study conducts comparative experiments to systematically evaluate the effects of different noise-filtering strategies on model prediction accuracy and robustness. Experimental results showed that the proposed method significantly improved both the accuracy and robustness of SOH prediction. On the CALCE dataset, relative to raw data, the average RMSE, MAE, and MAPE decreased by 9.40%, 4.30%, and 6.30%, respectively. Compared with the traditional 3σ filtering method, the improvements reached 10.60%, 3.78%, and 5.63%, respectively. On the NASA dataset, the standalone gain was smaller; however, when combined with 3σ filtering, the average improvements in RMSE, MAE, and MAPE reached about 8.5%, exceeding the 3σ filtering alone by approximately 7%. Comprehensive SHAP analysis further revealed that, compared with the 3σ filtering scheme, the features processed by CorODR exhibited more stable and interpretable importance distributions.

  • SC-CAMamba: Multi-objective classroom behaviour recognition based on parallel state space models and self-attention

    by Xiangqin Xiang, Jianfei Ning, Xiaofeng Wang, Jianhua Shu, Zhize Wu, Xinyu Wu, Xinqing Tang, Le Zou

  • Open Access

    WDNet: A Bio-Inspired Neural Network for Low-Light Image Enhancement

    by Xudong Zhou, Zhiming Zhang, Yan Zhang, Zhize Wu, Nian Wang

    Low-light image enhancement (LLIE) aims to recover normal-light images that conform to human visual perception from degraded observations. However, most existing deep models still rely on experience-driven architectures and often treat the enhancement process as a black-box pipeline from input to output. In contrast, the human visual system achieves stable low-light perception through a coordinated processing pathway, which can be functionally abstracted into retinal collecting, cortical processing, and nonlinear modulation in higher-level visual area. Motivated by this, we propose a Wavelet-prompted Dendritic-driven Network (WDNet), an end-to-end bioinspired enhancement framework. Specifically, WDNet leverages a wavelet prompter and a cross-level Soft-MoE adapter to model progressive hierarchical processing and high-order feature interactions in the visual cortex. Additionally, a dendritic-driven higher-level visual neuron (HVN) module is designed to model neural computations in higher-level visual areas under low-light conditions. This not only captures long-range dependencies among multi-level features and enhances attention to high-frequency salient regions, but also enables learnable nonlinear modulation and multi-scale integration. Finally, extensive experiments on public benchmarks demonstrate that WDNet achieves competitive enhancement performance, while ablation results further verify the rationality of the proposed network architecture. Our complete code is available on https://github.com/MFIDteam/WDNet.

  • Vision-language adaptation with imbalance mitigation for generalizable face anti-spoofing

    by Fan Cheng, Yuze Qiao, Fanjun Meng, Xianliang Wang, Mingsha Peng, Kaixuan Li, Zhize Wu, Meiwen Chen

  • Efficient Cross-Shard Blockchain Atomic Submission Scheme Based on Pledge Transactions

    by Ziwang Wang, Huili Yan, Zhize Wu, Liang Wang

    To address the substantial coordination overhead and communication latency inherent in cross-shard transaction commits within contemporary multi-shard blockchain architectures, this paper presents an efficient cross-shard atomic commit scheme (PledgeACS), grounded in the use of pledge transactions. The proposed scheme introduces a pledge transaction mechanism that employs a null recipient address and synchronizes these transactions across shards to an auxiliary chain through a global consensus protocol. Additionally, a cross-shard transaction protocol is developed, securing recipient funds via pledge transactions within the global consensus framework. Furthermore, a batch pledge transaction record and settlement protocol tailored for shard blockchains is designed, followed by rigorous feasibility analysis and performance evaluation. Experimental results indicate that the proposed scheme markedly decreases the user-perceived latency in cross-shard transactions and enhances security relative to current solutions, providing an innovative approach for achieving high throughput and scalability in blockchain systems.

  • Open Access

    SREHA: An Efficient Handover Authentication Scheme Based on Social Relationships in Mobile Edge Computing

    by Ziwang Wang, Liang Wang, Huili Yan, Zhize Wu

    Handover authentication in mobile scenarios refers to the process of re-authentication when a mobile device switches from one edge server to another. However, existing handover authentication schemes fail to optimize handover latency, security, and energy consumption comprehensively. To ensure continuity, security, and lightweight operation during switching, we propose SREHA, an efficient handover authentication scheme based on social relationships. First, the edge server builds its own social circle through bidirectional identity and integrity authentication, saving the social relationships in the public blockchain. Second, when the mobile device performs handover authentication, it evaluates the trustworthiness of the target node based on the social relationships of the current edge server node and filters the nodes that satisfy the trustworthiness criteria. By transferring the authentication load to the server side, SREHA prevents the device from expending significant resources to maintain reputation and authentication information, thereby achieving a lightweight handover authentication process. Third, we propose a malicious node detection model based on heuristic algorithms, which enhances the security of the handover authentication-free framework. Lastly, we implement a prototype of the proposed scheme and validate its security using the Scyther formal validation tool. The results demonstrate that our scheme effectively reduces the time delay of the handover authentication process, and exhibits lower computational overhead and higher security compared to existing schemes.