LDLiang Dong

Liang Dong

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

Current Organizations / Institutes

The organizations/institutes from the scholar's latest article


Liang Dong has a total of 33 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • CIM: Interpretable model with consistency representation and prompt learning

    by Liang Dong, Zhen Li, Leiyang Chen, Chengliang Zheng, Xiangzhen Peng, Yuqing Li, Xiaohui Cui


  • Open Access

    A Review on Blockchain Applications in Operational Technology for Food and Agriculture Critical Infrastructure

    by Chengliang Zheng, Xiangzhen Peng, Ziyue Wang, Tianyu Ma, Jiajia Lu, Leiyang Chen, Liang Dong, Long Wang, Xiaohui Cui, Zhidong Shen

    The food and agriculture sector is a cornerstone of critical infrastructure (CI), underpinning global food security, public health, and economic stability. However, the increasing digitalization and connectivity of operational technologies (OTs) in this sector expose it to significant cybersecurity risks. Blockchain technology (BT) has emerged as a transformative solution for addressing these challenges by enhancing network security, traceability, and system resilience. This study presents a comprehensive review of BT applications in OT security for food and agriculture CI, employing bibliometric and content analysis methods. A total of 124 relevant articles were identified from six databases, including the Web of Science Core Collection and MEDLINE®. Bibliometric analysis was conducted across five dimensions: publication year, literature type, journal distribution, country contributions, and keyword trends. The findings are meticulously organized through tables, charts, and graphs. The year 2018 marked a surge in research within this domain, with the IEEE Internet of Things Journal and IEEE ACESS emerging as the most prolific journals, each boasting nine publications. The United States, China, and India are at the forefront in terms of journal citation counts. Our analysis determined that a reference count of 37 serves as an appropriate threshold. Otoum Safa stands out as the author with the highest number of published articles, totaling four. Keywords such as “blockchain”, “internet of things”, “smart contract”, “security”, and “critical infrastructure” appear with significant frequency. The statistics, trends, and insights gleaned from this bibliometric analysis can guide researchers in the OTCI field to forge a coherent and logical research trajectory. Content analysis further identified six key research areas within this domain: identity authentication and data verification, secure access control, attack detection and perception, data security and protection, data backup and recovery, and attack assessment and attribution. Based on these insights, a general framework is proposed to guide future research and practical applications of BT in securing OT within food and agriculture CI. This study systematically analyzes the current research landscape, challenges, and opportunities for BT in securing the OT critical to food and agriculture CI. By bridging the gap between blockchain innovations and the operational needs of the food and agriculture sector, this work contributes to advancing strategic implementation and improving the security of CI systems.


  • Open Access

    Food Public Opinion Prevention and Control Model Based on Sentiment Analysis

    by Leiyang Chen, Xiangzhen Peng, Liang Dong, Zhenyu Wang, Zhidong Shen, Xiaohui Cui

    Food public opinion is characterized by its low ignition point, high diffusibility, persistence, and strong negativity, which significantly impact food safety and consumer trust. This paper introduces the Food Public Opinion Prevention and Control (FPOPC) model driven by deep learning and personalized recommendation algorithms, rigorously tested and analyzed through experimentation. Initially, based on an analysis of food public opinion development, a comprehensive FPOPC framework addressing all stages of food public opinion was established. Subsequently, a sentiment prediction model for food news based on user comments was developed using a Stacked Autoencoder (SAE), enabling predictions about consumer sentiments toward food news. The sentiment values of the food news were then quantified, and improvements were made in allocating Pearson correlation coefficient weights, leading to the design of a collaborative filtering-based personalized food news recommendation mechanism. Furthermore, an enhanced Bloom filter integrated with HDFS technology devised a rapid recommendation mechanism for food public opinion. Finally, the designed FPOPC model and its associated mechanisms were validated through experimental verification and simulation analysis. The results demonstrate that the FPOPC model can accurately predict and control the development of food public opinion and the entire food supply chain, providing regulatory agencies with effective tools for managing food public sentiment.


  • OCIE: Augmenting model interpretability via Deconfounded Explanation-Guided Learning

    by Liang Dong, Leiyang Chen, Chengliang Zheng, Zhongwang Fu, Umer Zukaib, Xiaohui Cui, Zhidong Shen


  • Leveraging saliency priors and explanations for enhanced consistent interpretability

    by Liang Dong, Leiyang Chen, Zhongwang Fu, Chengliang Zheng, Xiaohui Cui, Zhidong Shen


  • Stealthy dynamic backdoor attack against neural networks for image classification

    by Liang Dong, Jiawei Qiu, Zhongwang Fu, Leiyang Chen, Xiaohui Cui, Zhidong Shen


  • Emotion Recognition Using Three-Dimensional Feature and Convolutional Neural Network from Multichannel EEG Signals

    by Hao Chao, Liang Dong

    Using electroencephalogram (EEG) signal to recognize emotional states has become a research hotspot of affective computing. Previous emotion recognition methods almost ignored the correlation and interaction among multichannel EEG signals, which may provide salient information related to emotional states. This paper proposes a novel approach based on rearranged EEG features and deep learning algorithm. In particular, each channel EEG signal is first processed in time domain to get time-domain features. Then, features of all channels are treated as a three-dimensional (3D) feature matrix, according to positions of electrode sensors. This makes the features closer to the real response of the cerebral cortex. Subsequently, an advanced convolutional neural network (CNN) designed with univariate convolution layer and multivariate convolution layer is employed to deal with the 3D feature matrix for emotion recognition. A benchmark dataset for emotion analysis using physiological signal is employed to evaluate this method. The experimental results proved that the 3D feature matrix can effectively represent the emotion-related features in multichannel EEG signals and the proposed CNN can efficaciously mine the unique features of each channel and the correlation among channels for emotion recognition.


  • Open Access

    Improved Deep Feature Learning by Synchronization Measurements for Multi-Channel EEG Emotion Recognition

    by Hao Chao, Liang Dong, Yongli Liu, Baoyun Lu

    Emotion recognition based on multichannel electroencephalogram (EEG) signals is a key research area in the field of affective computing. Traditional methods extract EEG features from each channel based on extensive domain knowledge and ignore the spatial characteristics and global synchronization information across all channels. This paper proposes a global feature extraction method that encapsulates the multichannel EEG signals into gray images. The maximal information coefficient (MIC) for all channels was first measured. Subsequently, an MIC matrix was constructed according to the electrode arrangement rules and represented by an MIC gray image. Finally, a deep learning model designed with two principal component analysis convolutional layers and a nonlinear transformation operation extracted the spatial characteristics and global interchannel synchronization features from the constructed feature images, which were then input to support vector machines to perform the emotion recognition tasks. Experiments were conducted on the benchmark dataset for emotion analysis using EEG, physiological, and video signals. The experimental results demonstrated that the global synchronization features and spatial characteristics are beneficial for recognizing emotions and the proposed deep learning model effectively mines and utilizes the two salient features.


  • Top Cited Papers
    Open Access

    Emotion Recognition from Multiband EEG Signals Using CapsNet

    by Hao Chao, Liang Dong, Yongli Liu, Baoyun Lu

    Emotion recognition based on multi-channel electroencephalograph (EEG) signals is becoming increasingly attractive. However, the conventional methods ignore the spatial characteristics of EEG signals, which also contain salient information related to emotion states. In this paper, a deep learning framework based on a multiband feature matrix (MFM) and a capsule network (CapsNet) is proposed. In the framework, the frequency domain, spatial characteristics, and frequency band characteristics of the multi-channel EEG signals are combined to construct the MFM. Then, the CapsNet model is introduced to recognize emotion states according to the input MFM. Experiments conducted on the dataset for emotion analysis using EEG, physiological, and video signals (DEAP) indicate that the proposed method outperforms most of the common models. The experimental results demonstrate that the three characteristics contained in the MFM were complementary and the capsule network was more suitable for mining and utilizing the three correlation characteristics.


  • Open Access

    Recognition of Emotions Using Multichannel EEG Data and DBN-GC-Based Ensemble Deep Learning Framework

    by Hao Chao, Huilai Zhi, Liang Dong, Yongli Liu

    Fusing multichannel neurophysiological signals to recognize human emotion states becomes increasingly attractive. The conventional methods ignore the complementarity between time domain characteristics, frequency domain characteristics, and time-frequency characteristics of electroencephalogram (EEG) signals and cannot fully capture the correlation information between different channels. In this paper, an integrated deep learning framework based on improved deep belief networks with glia chains (DBN-GCs) is proposed. In the framework, the member DBN-GCs are employed for extracting intermediate representations of EEG raw features from multiple domains separately, as well as mining interchannel correlation information by glia chains. Then, the higher level features describing time domain characteristics, frequency domain characteristics, and time-frequency characteristics are fused by a discriminative restricted Boltzmann machine (RBM) to implement emotion recognition task. Experiments conducted on the DEAP benchmarking dataset achieve averaged accuracy of 75.92% and 76.83% for arousal and valence states classification, respectively. The results show that the proposed framework outperforms most of the above deep classifiers. Thus, potential of the proposed framework is demonstrated.