LLLin Lu

Lin Lu

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

Current Organizations / Institutes

The organizations/institutes from the scholar's latest article

Previous Organizations / Institutes

The organizations / institutes from the scholar's other articles in the past ten years


Lin Lu has a total of 48 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Open Access

    EVFaultNet: A Cell-Decay Recurrent–Convolutional Architecture for Imbalanced Electric Vehicle Battery Fault Diagnosis Under Sparse Telemetry

    by Li Nie, Xiaofeng Li, Chengming Xu, Yongming Huang, Lin Lu

    Battery telemetry from electric vehicles arrives at a low sampling rate and is severely imbalanced, making fault diagnosis a long-memory, long-tailed classification problem. This paper presents EVFaultNet, a recurrent–convolutional architecture for this setting. Its key innovation is a learned resting point for the recurrent hidden state: before each gate update, the state relaxes toward a learnable per-unit baseline rather than zero, which lets stale information decay to a neutral value. A causal temporal convolution then refines local trajectory patterns, and a deferred imbalance-aware objective handles the long-tailed labels. On the CH-BatteryGen benchmark (500 LFP vehicles, four fault classes, 10-second cadence), EVFaultNet achieves the highest mean battery-level F1 at two of three window lengths (0.903 at L=64, 0.895 at L=256) and is statistically comparable to the strongest baseline at L=128 (0.892 vs. 0.911, p=0.38), while using roughly four times fewer parameters. Ablations confirm that both the resting-state decay and periodic within-window time encoding contribute to the result. Battery-level aggregation resolves ambiguity for high resistance and self-discharge faults, but low-capacity detection remains the main limitation: 7.0% of healthy vehicles are false-flagged, at 0.500 precision and 0.933 recall. Measured workstation-GPU cost ranges from 0.57 to 2.42 ms per window; automotive embedded performance is not yet characterized.

  • Open Access

    A Survey on Urban Governance Data Engineering

    by Taowei Li, Yun Bai, Qin Tang, Lu Bian, Lin Lu, Tao Wei, Shulin Liu, Fei Xu

  • Open Access

    Addressing Data Sparsity in EV Charging Load Forecasting: A Novel Zero-Inflated Neural Network Approach

    by Huiya Xiang, Zhe Li, Lisha Liu, Yujin Yang, Lin Lu, Binxin Zhu

    Accurate electric vehicle (EV) charging load forecasting is essential for grid planning and resource allocation, yet existing approaches struggle with the inherent sparsity of charging data—a phenomenon characterized by excessive zeros representing periods of no charging activity. This paper addresses this challenge through a novel framework combining a Zero-Inflated Neural Network (ZINN) architecture with an Evolutionary Neural Architecture Search (ENAS) algorithm. ZINN explicitly decomposes the forecasting problem into binary classification (predicting charging occurrence) and regression (estimating energy magnitude conditioned on occurrence), enabling the model to learn distinct patterns for the absence and presence of charging events. Rather than relying on manually designed architectures, ENAS automatically discovers optimal encoder and decoder configurations from a comprehensive search space encompassing modern architectures (LSTM, GRU, Transformer, and iTransformer), layer configurations, activation functions, and hyperparameters. The evolutionary algorithm balances prediction accuracy with computational efficiency through multi-objective optimization. Extensive experiments on real-world EV charging data from 30 stations in Wuhan demonstrate that the ZINN+ENAS framework achieves the lowest prediction error compared to conventional baselines, with the discovered optimal configuration substantially outperforming hand-crafted designs. Comprehensive ablation studies reveal that the asymmetric dual-head architecture and adaptive regularization strategies are critical for handling data sparsity. These findings highlight the importance of explicit zero-inflation modeling and automated architecture discovery for specialized forecasting tasks, providing practitioners with an open-source framework for practical EV charging load prediction.


  • Open Access

    A robust and adaptive driver identification framework for intelligent transportation systems

    by Wenze Shi, Ao Guo, Xufei Chu, Siyu Yang, Zilin Huang, Lin Lu


  • Cross-Vehicle Federated Learning for Unsupervised Scoring of Driver Behavior Under Privacy Constraint

    by Lin Lu, Xufei Chu, Ao Guo, Yukun Fang, Beatriz Martinez-Pastor, Rui Teixeira

    Scoring driver behavior is crucial for profiling drivers to improve driving habits with beneficial feedback, significantly reducing the risks of accidents, fuel consumption, and traffic emissions. Although connected vehicles enable extensive collection of driving data for accurate scoring models, two key challenges persist: the absence of target scores for traditional regression algorithms and privacy concerns that hinder centralized learning to build unsupervised scoring models. We introduce FedDriveScore, a privacy-preserving unsupervised scoring framework tailored for the Internet of Vehicles context. This solution leverages a mixed distribution approach to form an objective scoring model that utilizes probability distributions and statistical weights to assess driver behavior. Homomorphic encryption-based federated learning is employed to collaboratively implement the scoring model across multiple vehicles without sharing raw data. To mitigate the detrimental effects of skewed metric distributions, an enhanced federated learning method is developed to ensure utility consistency between models generated through federated learning and centralized learning. Experimental results from two real-world datasets show that the proposed solution achieves remarkable performance, with scoring utility losses of less than 0.0001 (mean squared error) and 0.01 (mean absolute error), representing approximately a 99% improvement over traditional federated learning benchmark. Our solution demonstrates high alignment with centralized learning outcomes while effectively profiling drivers in an objective and equitable manner.


  • Open Access

    Learning driving style embedding from GPS-derived moving patterns for driver identification

    by Lin Lu

    Learning fingerprint-like driving style representations is crucial to accurately identify who is behind the wheel in open driving situations. This study explores the learning of driving styles with GPS signals that are currently available in connected vehicles for short-term driver identification. First, an input driving trajectory is windowed into subtrajectories with fixed time lengths. Then, each subtrajectory is further divided into overlapping dynamic segments. For each segment, the local features are obtained by combining statistical and state transitional patterns. Finally, the driving style embedded in each subtrajectory is learned with the proposed regularized recurrent neural network (RNN) for short-term driver identification. We evaluate the impacts of key factors and the effectiveness of the proposed approach on the identification performance of 5 and 10 drivers. The results show that our proposed neural network structure, which complements movement statistics (MS) with state transitions (ST), provides better prediction performance than existing deep learning methods.

  • The interaction of financial toxicity and social support on social functioning in post-chemotherapy breast cancer patients: a cross-sectional study

    by Lu Lin, Qiuyun Chen, Fengxia Lai, Daoxia Guo, Jie Wang, Li Tian

    Purpose To explore the correlation between financial toxicity, social support, and social functioning in post-chemotherapy breast cancer patients, as well as any possible interaction of financial toxicity and social support on social functioning. Methods Post-chemotherapy breast cancer patients admitted to the thyroid and breast surgery departments of three first-class general hospitals in East China from December 2020 to January 2022 were recruited by convenience sampling for a cross-sectional survey. The survey instruments included the general information form, the comprehensive scores for financial toxicity based on the patient-reported outcome measures (COST-PROM), the social roles and activity participation subscale from the patient-reported outcomes measurement system-breast-chemotherapy (PROMS-B-C) (score range: 8–40), and the social support subscale from PROMS-B-C (score range: 16–80). Results The results showed that low social functioning (low score) in post-chemotherapy breast cancer patients was positively correlated with high financial toxicity (low score) as well as poor economic resources (low score) and poor psychosocial responses (low score) (PPP<0.01). The interaction analysis results showed an additive interaction between financial toxicity and social support in social functioning. Conclusion There was an additive interaction of financial toxicity and social support in the social functioning of post-chemotherapy breast cancer patients. Those patients with high financial toxicity and low social support are the most likely to benefit from relevant intervention measures compared to other breast cancer populations.


  • Open Access

    Unsupervised Transformer Balanced Hashing for Multispectral Remote Sensing Image Retrieval

    by Yaxiong Chen, Fan Wang, Lin Lu, Shengwu Xiong

    For Remote Sensing (RS) image retrieval task, hashing technology have been extensively researched in recent works. Unsupervised hashing approaches has attracted much attention in the RS data processing field because label collection takes a lot of time. Most of which fail to consider the interactions among the multi-channel information of multispectral RS images and the disparity between the hash-like codes space and the Hamming space, which lead to the poor performance of multispectral RS image retrieval. In this paper, we tackle these dilemmas with a novel unsupervised hashing approach, namely Unsupervised Transformer Balanced Hashing (UTBH), to utilize a convolutional variational autoencoder architecture with a novel RS Transformer to perform effective hash codes learning. We first integrate a convolutional variational autoencoder architecture with a novel RS Transformer, which can guide the interactions among the multi-channel information of multispectral RS images. Meanwhile, a new objective function is proposed to preserve discrimination of hash codes in the hashing learning process and reduce the disparity between the hash-like codes space and the Hamming space effectively. Finally, experimental results on two multispectral RS image datasets indicate that UTBH approach achieves superior performance over other unsupervised image retrieval approaches.