JFJinglong Fang

Jinglong Fang

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

Current Organizations / Institutes

The organizations/institutes from the scholar's latest article


Jinglong Fang has a total of 43 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Secure Fusion Estimation of Energy-Constrained Multisensor System Against Hybrid Attacks

    by Zhouqiang Zheng, Haiyu Song, Wen-An Zhang, Jinglong Fang, Li Yu

    This article presents a comprehensive theoretical framework for addressing the problem of secure fusion estimation in energy-constrained multisensor systems, specifically targeting hybrid attacks in multiple transmission levels. The lifespan of sensor nodes is constrained by the availability of energy supply, and all the sensors have the flexibility to choose between high-energy or low-energy levels for transmitting their measurements. Sensor data becomes vulnerable to malicious tampering when operating in a low-energy level, whereas the high-energy transmission level enables accurate data transmission. By introducing a set of Bernoulli random variables and ternary random variables, a novel measurement model is proposed to characterize scenarios involving both dual-energy transmission modes and hybrid attacks, including three statuses: safe, deception attacks, and DoS attacks. Based on the innovation analysis approach, local secure estimators are designed to ensure that the estimation errors are minimized locally. Then, an optimal secure fusion algorithm is provided to generate the final estimated value by fusing all the local estimates. Additionally, the proposed secure fusion estimation algorithm’s stability and steady-state properties are investigated. Finally, two simulation cases are conducted to provide the empirical evidence of the superior performance of the proposed approach.


  • CoAdapt: Collaborative Adaptation between Latent EEG Feature Representation and Annotation for Emotion Decoding

    by Xiaoxiao Gong, Yuxin Chen, Pengfei Zhang, Yong Peng, Jinglong Fang, Andrzej Cichocki

    Electroencephalogram (EEG) data contains rich neurophysiological information that can objectively express the emotional state of human beings. However, the inherent EEG characteristics such as non-stationarity and weakness, combined with the possible limited immersion and carry-over effect of subjects during data-collection experiments, may cause that the semantic meaning of extracted EEG feature vector cannot well match its annotated emotional state, dubbed the ‘feature-label inconsistency dilemma in EEG-based emotion decoding. To this end, this paper proposes to alleviate the side effect of ‘feature-label inconsistency from both feature and label aspects. On one hand, we explore more meaningful emotion-related EEG representation by the latent low-rank representation. On the other hand, enhance the correspondence between explored EEG representation and its annotated emotional state by a label dragging strategy. As a result, a collaborative adaptation (CoAdapt) model between latent EEG feature representation and its annotation is formed for efficient emotion decoding, which is implemented within the semi-supervised framework to better capture the properties of both the labeled and unlabeled EEG data. Experimental results on three publicly available datasets, SEED-IV, SEED-V and MPED, depict that 1) CoAdapt achieves better emotion recognition performance in comparison with some related models; 2) the improvements of inter-class separability and label margin are empirically evaluated, indicating the effectiveness of the purified EEG feature representation and rectified emotion annotation; 3) some task-related results are identified from data-driven perspective, including the emotion carry-over effect and the discriminative spatial patterns in emotion decoding.


  • Open Access

    PRFC: Program Repair combining Fix patterns and Code language models

    by Dan Wei, Xinjian Cao, Jinglong Fang, Xingqi Wang, Bin Chen

    Automated program repair (APR) significantly improves development efficiency by automatically generating patches for defects in software. Recently, learning-based automatic program repair methods have been extensively studied. However, this approach still suffers from two obvious limitations: first, it is affected by the long-range dependency problem, which makes it difficult to handle long sequences of complex errors. The second is that the current patch ranking strategy does not consider the overall patch information, resulting in too many anomalously high-scoring patches in the candidate patch list, and thus ignoring the correct patches. To address the above limitations, we propose a novel automated program repair method PRFC (Program Repair combining Fix patterns and Code language models), which consists of three components:(1) By generalizing and organizing common fix patterns, we propose novel mask templates for enhancing the patch generation capability of code language models. (2) PRFC treats the repair task as a cloze task and utilizes the code language model to generate candidate patches based on the mask templates. (3) A novel patch reranking approach, which utilizes template coefficients to rerank candidate patches, greatly alleviates the problem of abnormally high-scoring patches. Experimental results show that PRFC correctly fixes 141 Defects4J bugs and 36 QuixBugs bugs under perfect fault localization conditions, which improves 11.02\% and 33.33\% over the optimal baseline, respectively.

  • Open Access

    Malicious Code Classification Method Based on Deep Residual Network and Hybrid Attention Mechanism for Edge Security

    by Yanli Shao, Yang Lu, Dan Wei, Jinglong Fang, Feiwei Qin, Bin Chen

    Edge computing is a feasible solution for effectively collecting and processing data in industrial Internet of Things (IIoT) systems, and edge security is an important guarantee for edge computing. Fast and accurate classification of malicious code in the whole lift cycle of edge computing is of great significance, which can effectively prevent malicious code from attacking wireless sensor networks and ensure the stable and secure transmission of data in smart devices. Considering that there is a large amount of code reuse in the same malicious code family, making their visual feature similar, many studies use visualization technology to assist malicious code classification. However, traditional malicious code visual classification schemes have the problems such as single image source, weak ability of deep‐level feature extraction, and lack of attention to key image details. Therefore, an innovative malicious code visual classification method based on a deep residual network and hybrid attention mechanism for edge security is proposed in this study. Firstly, the malicious code visualization scheme integrates the bytecode file and assembly file of the malware and converts them into a four‐channel RGBA image to fully represent malicious code feature information without increasing the computational complexity. Secondly, a hybrid attention mechanism is introduced into the deep residual network to construct an effective classification model, which extracts image texture features of malicious code from two dimensions of the channel and spatial to improve the classification performance. Finally, the experimental results on the BIG2015 and Malimg datasets show that the proposed scheme is feasible and effective and can be widely applied used in various malicious code classification issues, and the classification accuracy rate is relatively higher than the existing better‐performing malicious code classification methods.


  • JPEG Image Steganalysis Using Weight Allocation from Block Evaluation

    by Weiwei Luo, Wenpeng Zhou, Jinglong Fang, Lingyan Fan

    Recently, channel-aware steganography has been presented for high security. The corresponding selection-channel-aware (SCA) detecting algorithms have also been proposed for improving the detection performance. In this paper, we propose a novel detecting algorithm of JPEG steganography, where the embedding probability and block evaluation are integrated into the new probability. This probability can embody the change due to data embedding. We choose the same high-pass filters as maximum diversity cascade filter residual (MD-CFR) to obtain different image residuals and a weighted histogram method is used to extract detection features. Experimental results on detecting two typical steganographic methods show that the proposed method can improve the performance compared with the state-of-art methods.

  • Self-Weighted Semi-Supervised Classification for Joint EEG-Based Emotion Recognition and Affective Activation Patterns Mining

    by Yong Peng, Wanzeng Kong, Feiwei Qin, Feiping Nie, Jinglong Fang, Bao-Liang Lu, Andrzej Cichocki

    In electroencephalography (EEG)-based affective brain–computer interfaces (aBCIs), there is a consensus that EEG features extracted from different frequency bands and channels have different abilities in emotion expression. Besides, EEG is so weak and non-stationary that easily causes distribution discrepancies for EEG data collected at different times; therefore, it is necessary to explore the affective activation patterns in cross-session emotion recognition. To address these two problems, we propose a self-weighted semi-supervised classification (SWSC) model in this article for joint EEG-based cross-session emotion recognition and affective activation patterns mining, whose merits include: 1) using both the labeled and unlabeled samples from different sessions for better capturing data characteristics; 2) introducing a self-weighted variable to learn the importance of EEG features adaptively and quantitatively; and 3) mining the activation patterns including the critical EEG frequency bands and channels automatically based on the learned self-weighted variable. Extensive experiments are conducted on the benchmark SEED_IV emotional dataset and SWSC obtained excellent average accuracies of 77.40%, 79.55%, and 81.52% in three cross-session emotion recognition tasks. Moreover, SWSC identifies that the Gamma frequency band contributes the most and the EEG channels in prefrontal, left/right temporal, and (central) parietal lobes are more important for cross-session emotion recognition.


  • Open Access

    Research on Cross-Company Defect Prediction Method to Improve Software Security

    by Yanli Shao, Jingru Zhao, Xingqi Wang, Weiwei Wu, Jinglong Fang

    As the scale and complexity of software increase, software security issues have become the focus of society. Software defect prediction (SDP) is an important means to assist developers in discovering and repairing potential defects that may endanger software security in advance and improving software security and reliability. Currently, cross-project defect prediction (CPDP) and cross-company defect prediction (CCDP) are widely studied to improve the defect prediction performance, but there are still problems such as inconsistent metrics and large differences in data distribution between source and target projects. Therefore, a new CCDP method based on metric matching and sample weight setting is proposed in this study. First, a clustering-based metric matching method is proposed. The multigranularity metric feature vector is extracted to unify the metric dimension while maximally retaining the information contained in the metrics. Then use metric clustering to eliminate metric redundancy and extract representative metrics through principal component analysis (PCA) to support one-to-one metric matching. This strategy not only solves the metric inconsistent and redundancy problem but also transforms the cross-company heterogeneous defect prediction problem into a homogeneous problem. Second, a sample weight setting method is proposed to transform the source data distribution. Wherein the statistical source sample frequency information is set as an impact factor to increase the weight of source samples that are more similar to the target samples, which improves the data distribution similarity between the source and target projects, thereby building a more accurate prediction model. Finally, after the above two-step processing, some classical machine learning methods are applied to build the prediction model, and 12 project datasets in NASA and PROMISE are used for performance comparison. Experimental results prove that the proposed method has superior prediction performance over other mainstream CCDP methods.


  • Open Access

    The Traffic Flow Prediction Method Using the Incremental Learning-Based CNN-LTSM Model: The Solution of Mobile Application

    by Yanli Shao, Yiming Zhao, Feng Yu, Huawei Zhu, Jinglong Fang

    With the acceleration of urbanization and the increase in the number of motor vehicles, more and more social problems such as traffic congestion have emerged. Accordingly, efficient and accurate traffic flow prediction has become a research hot spot in the field of intelligent transportation. However, traditional machine learning algorithms cannot further optimize the model with the increase of the data scale, and the deep learning algorithms perform poorly in mobile application or real-time application; how to train and update deep learning models efficiently and accurately is still an urgent problem since they require huge computation resources and time costs. Therefore, an incremental learning-based CNN-LTSM model, IL-TFNet, is proposed for traffic flow prediction in this study. The lightweight convolution neural network-based model architecture is designed to process spatiotemporal and external environment features simultaneously to improve the prediction performance and prediction efficiency of the model. Especially, the K-means clustering algorithm is applied as an uncertainty feature to extract unknown traffic accident information. During the model training, instead of the traditional batch learning algorithm, the incremental learning algorithm is applied to reduce the cost of updating the model and satisfy the requirements of high real-time performance and low computational overhead in short-term traffic prediction. Furthermore, the idea of combining incremental learning with active learning is proposed to fine-tune the prediction model to improve prediction accuracy in special situations. Experiments have proved that compared with other traffic flow prediction models, the IL-TFNet model performs well in short-term traffic flow prediction.