5 December 2023 in IEEE Transactions on Wireless Communications
Deep learning (DL) has shown great potential in revolutionizing the traditional communications system. Many applications in communications have adopted DL techniques due to their powerful representation ability. However, the learning-based methods can be dependent on the training dataset and perform worse on unseen interference due to limited model generalizability and complexity. In this paper, we consider the semantic communication (SemCom) system with multiple users, where there is a limited number of training samples and unexpected interference. To improve the model generalization ability and reduce the model size, we propose a knowledge distillation (KD) based system where Transformer based encoder-decoder is implemented as the semantic encoder-decoder and fully connected neural networks are implemented as the channel encoder-decoder. Specifically, four types of knowledge transfer and model compression are analyzed. Important system and model parameters are considered, including the level of noise and interference, the number of interfering users and the size of the encoder and decoder. Numerical results demonstrate that KD significantly improves the robustness and the generalization ability when applied to unexpected interference, and it reduces the performance loss when compressing the model size.
11 March 2022 in IEEE Transactions on Vehicular Technology
Due to the increasing demand for spectrum resources, the co-existence of communications and radar systems has been proposed that allows radar and communications systems to operate in the same frequency band. On the other hand, deep learning has shown great potential in revolutionizing communications systems. In this work, we investigate the use of deep learning in communications systems subject to interference from radar systems. Specifically, we consider a single-carrier communications system. Linear frequency-modulated (LFM) and frequency-modulated continuous-wave (FMCW) are considered for radar. Several important system parameters, including the level of noise and interference, the radar interference coverage, the symbol duration, feature extraction methods and the number of hidden layers are investigated for the performance of the detector. Fully connected deep neural network (FCDNN) and long short-term memory (LSTM) detectors are implemented, where principle component analysis (PCA) is applied to preprocess the observed signals for the FCDNN detector. Numerical results show that the learning-based detector achieves comparable performance in the radar-communication system to the traditional detector but without interference cancellation. Preprocessing the received signals with PCA can improve the performance of FCDNN when interference is strong. Also, LSTM shows more robust performance than FCDNN when the channel has time-related distortion.
14 July 2023 in IEEE Wireless Communications Letters
Cooperative perception has been widely used in autonomous driving to alleviate the inherent limitation of single automated vehicle perception. To enable cooperation, vehicle-to-vehicle (V2V) communication plays an indispensable role. This work analyzes the performance of cooperative perception accounting for communications channel impairments. Different fusion methods and channel impairments are evaluated. A new late fusion scheme is proposed to leverage the robustness of intermediate features. In order to compress the data size incurred by cooperation, a convolution neural network-based autoencoder is adopted. Numerical results demonstrate that intermediate fusion is more robust to channel impairments than early fusion and late fusion, when the SNR is greater than 0 dB. Also, the proposed fusion scheme outperforms the conventional late fusion using detection outputs, and autoencoder provides a good compromise between detection accuracy and bandwidth usage.
20 December 2023 in IEEE Transactions on Intelligent Vehicles
Perception of the driving environment is critical for collision avoidance and route planning to ensure driving safety. Cooperative perception has been widely studied as an effective approach to addressing the shortcomings of single-vehicle perception. However, the practical limitations of vehicle-to-vehicle (V2V) communications have not been adequately investigated. In particular, current cooperative fusion models rely on supervised models and do not address dynamic performance degradation caused by arbitrary channel impairments. In this paper, a self-supervised adaptive weighting model is proposed for intermediate fusion to mitigate the adverse effects of channel distortion. The performance of cooperative perception is investigated in different system settings. Rician fading and imperfect channel state information (CSI) are also considered. Numerical results demonstrate that the proposed adaptive weighting algorithm significantly outperforms the benchmarks without weighting. Visualization examples validate that the proposed weighting algorithm can flexibly adapt to various channel conditions. Moreover, the adaptive weighting algorithm demonstrates good generalization to untrained channels and test datasets from different domains.
1 August 2021 in Physical Communication
22 March 2024 in IEEE Transactions on Multimedia
Crowd gathering events deeply affect public safety. To enhance city management and avoid potential risks, many algorithms are designed for crowd analysis and deployed on video surveillance. Widely applied deep learning models also can be trained for crowd analysis. However, there are still few works focusing on crowd gathering behavior. Furthermore, as a result of the lack of interpretability of deep learning models, which also brings potential risk of being rejected by the users. In this paper, we categorize crowd behaviors into wandering, merging, walking gathering, standing gathering, and dispersing. Also, we propose an interpretable framework for crowd gathering understanding based on crowd density estimation model and proposed crowd descriptors, named Irregularity, Sparsity, Randomness, and Volatility. The experiments on the PETS2009 dataset demonstrate our method has outperformed the previous works on the crowd gathering understanding task. Moreover, we further analyze the framework performance with different crowd feature extraction models and the relations between our descriptors and crowd behavior. Besides, an ablation study is conducted to investigate the effectiveness of the descriptors and differences between density estimation models. The results demonstrate the effectiveness and the much better interpretability of our framework. Our descriptors also show significant contributions to the quantification of crowd gathering behaviors.