Yan Feng Feng

Prof. Yan Feng Feng


Research Focus & Metrics

Academic Career Length

5Years (2022-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
16 August 2024 in Electronics
Verified
Journal Article
Open access
PDF file
张张张少华 少华 张
张少华 少华 张
YFYan Feng Feng
Yan Feng Feng
艺任艺昊 任
艺昊 任
GFGuo Ze Fei
Guo Ze Fei
RYRenjie Yu
Renjie Yu
PXPeiran Xing
Peiran Xing
Emotion recognition plays an increasingly important role in today’s society and has a high social value. However, current emotion recognition technology faces the problems of insufficient feature extraction and imbalanced samples when processing speech and text information, which limits the performance of existing models. To overcome these challenges, this paper proposes a multi-modal emotion recognition method based on speech and text. The model is divided into two channels. In the first channel, the extended Geneva Minimalistic Acoustic Parameter Set (eGeMAPS) feature set is extracted from OpenSmile, and the original eGeMAPS feature set is merged with the wavelet transformed eGeMAPS feature set. Then, speech features are extracted through a sparse autoencoder. The second channel extracts text features through the BERT-RoBERTa model. Then, deeper text features are extracted through a gated recurrent unit (GRU), and the deeper text features are fused with the text features. Emotions are identified by the attention layer, the dual-layer Bidirectional Long Short-Term Memory (BiLSTM) model, and the loss function, combined with cross-entropy loss and focus loss. Experiments show that, compared with the existing model, the WA and UA of this model are 73.95% and 74.27%, respectively, on the imbalanced IEMOCAP dataset, which is superior to other models. This research result effectively solves the problem of feature insufficiency and sample imbalance in traditional sentiment recognition methods, and provides a new way of thinking for sentiment analysis application.

12 September 2022 in IEEE Transactions on Network Science and Engineering
Verified
Journal Article
Closed access
JZJieheng Zheng
Jieheng Zheng
LZLin Zhang
Lin Zhang
YFYan Feng Feng
Yan Feng Feng
ZWZhiqiang Wu
Zhiqiang Wu
Internet of Things (IoT) systems have the great advantage of connecting massive low energy-consumption devices for the information delivery via wireless channels. However, IoT devices suffer from malicious attacks or eavesdropping due to the broadcasting property of wireless channels. With the aim of enhancing the security performances, we first propose a chaotic scrambler, which utilizes the natural high security property of chaotic sequences being aperiodic and sensitive to initial values, to improve the security of signal transmissions. Then, we propose to utilize the traceable and tamper-proof blockchain to integrate the confidential chaotic key into the chain for user identify management and authentications. Subsequently, theoretical security, reliability and throughput capacities are analyzed, and simulation results are provided to validate the design and the theoretical analysis. Furthermore, we present the practical hardware implementation board for the proposed secure chaotic scrambling following the long range wide area network (LoRaWAN) specifications, which demonstrates that the security performances of IoT devices can be effectively enhanced.

16 June 2025 in Frontiers in Computational Neuroscience
Verified
Journal Article
Open access
PDF file
SZShaohua Zhang
Shaohua Zhang
YFYan Feng Feng
Yan Feng Feng
RCRuzhen Chen
Ruzhen Chen
SHSong Huang
Song Huang
QWQianchu Wang
Qianchu Wang
EEG emotion recognition has important applications in human-computer interaction and mental health assessment, but existing models have limitations in capturing the complex spatial and temporal features of EEG signals. To overcome this problem, we propose an innovative model that combines CNN-BiLSTM and DC-IGN and fused both outputs for sentiment classification via a fully connected layer. In addition, we use a piecewise exponential decay strategy to optimize the training process. We conducted a comprehensive comparative experiment on the SEED and DEAP datasets, it includes traditional models, existing advanced models, and different combination models (such as CNN + LSTM, CNN + LSTM+DC-IGN). The results show that our model achieves 94.35% accuracy on SEED dataset, 89.84% on DEAP-valence, 90.31% on DEAP-arousal, which is significantly better than other models. In addition, we further verified the superiority of the model through subject independent experiment and learning rate scheduling strategy comparison experiment. These results not only improve the performance of EEG emotion recognition, but also provide new ideas and methods for research in related fields, and prove the significant advantages of our model in capturing complex features and improving classification accuracy.

12 September 2022 in IEEE Access
Verified
Journal Article
Open access
WQWenduo Qiu
Wenduo Qiu
YFYan Feng Feng
Yan Feng Feng
YZYou Zhang
You Zhang
In this paper, in order to improve the reliability of Multi-User Multiple-Input Multiple-Output Visible Light Communication (MU-MIMO-VLC) system, we propose a precoding scheme that based on Singular Value Decomposition (SVD) and Geometric Mean Decomposition (GMD) assisted Orthogonal Transformation (OT). In this design, we use SVD to conduct the decomposition of the user’s complementary channel matrix. Then, the equivalent channel matrix is obtained by multiplying the user’s channel matrix and the decomposed component. After that, the GMD is carried out to decompose the equivalent channel matrix. Finally, the precoding matrix of the proposed scheme is obtained. We then derive the theoretical Symbol Error Rate (SER) of the proposed scheme. The simulation results are provided to validate the effectiveness of the proposed scheme, and to demonstrate that the reliability of the proposed design is superior to benchmark schemes.

2 August 2022 in IEEE Transactions on Cognitive Communications and Networking
Verified
Journal Article
Closed access
XYXiaoling Yang
Xiaoling Yang
LZLin Zhang
Lin Zhang
YFYan Feng Feng
Yan Feng Feng
ZWZhiqiang Wu
Zhiqiang Wu
The noise existent in practical systems degrades reliability performances, especially when delivering data over fast fading channels with the correlated noise. To address this issue, we propose a residual convolutional neural network aided denoiser (ResCNND) to suppress the noise for more reliable information recovery. The intelligent ResCNND is composed by convolutional layers, batch normalization layers and nonlinear activation functions. The ResCNND aided denoiser is then integrated with different types of channel decoders, and we propose a data preprocessing module to embed the statistical characteristics of channel conditions in terms of channel state information (CSI) as inputs to the neural network. Additionally, we propose the loss function by combining the mean square error loss and the normality test loss to simultaneously reduce the noise power and preserve the Gaussian distribution of residual noises. Then the well trained ResCNND can be used to suppress the noise in real time. In simulations, three types of channel codes, including LDPC, Polar and Turbo codes, are considered. The results demonstrate that the proposed ResCNND-aided receiver can effectively improve the signal-to-noise ratio and bit error rate performances with no requirement of perfect CSI, thereby achieving better reliability and robustness performances than benchmark schemes.

23 September 2022 in Electronics
Verified
Journal Article
Open access
PDF file
YZYou Zhang
You Zhang
YFYan Feng Feng
Yan Feng Feng
LZLin Zhang
Lin Zhang
ZWZhiqiang Wu
Zhiqiang Wu
Turbulence in natural environments affects the reliability of communication. In this paper, we propose a symmetric matrix-assisted multiple-input multiple-output (MIMO) maritime visible light communication (VLC) system to confront turbulence and improve reliability. In our design, by exploiting the repeatability of elements in the symmetric matrix, the matrix can expand the Euclidean distance between signals and effectively restrains the interference between signals, thus improving the reliability of maritime VLC systems. In addition, we derive the theoretical symbol error rate (SER) of the proposed scheme. Then, simulation results are provided to validate the theoretical SER. In addition, the SER performances of the proposed system are compared with the three benchmark schemes of repetitive coding (RC), spatial modulation (SM), and spatial multiplexing (SMP), and the transmission performances in VLC systems with different link distances, water qualities, and wind speeds are also investigated. The proposed symmetric matrix-assisted MIMO maritime VLC system can combat interferences effectively and enhance reliability performance.