Related papers: Low Complexity Neural Network Structures for Self-…

In order to support experimentation with full-duplex (FD) wireless, we recently integrated an open-access FD transceiver in the ORBIT testbed. In this report, we present the design and implementation of the FD transceiver and interfaces,…

We propose to execute deep neural networks (DNNs) with dynamic and sparse graph (DSG) structure for compressive memory and accelerative execution during both training and inference. The great success of DNNs motivates the pursuing of…

Current dynamic networks and dynamic pruning methods have shown their promising capability in reducing theoretical computation complexity. However, dynamic sparse patterns on convolutional filters fail to achieve actual acceleration in…

A multi-cell cluster-free NOMA framework is proposed, where both intra-cell and inter-cell interference are jointly mitigated via flexible cluster-free successive interference cancellation (SIC) and coordinated beamforming design. The joint…

Deep neural networks (DNNs) based automatic speech recognition (ASR) systems are often designed using expert knowledge and empirical evaluation. In this paper, a range of neural architecture search (NAS) techniques are used to automatically…

{Robust transceiver design against unresolvable system uncertainties is of crucial importance for reliable communication. We consider a MIMO multi-hop system, where the source, the relay, and the destination are equipped with multiple…

Loop interference (LI) in wireless communications, is a notion resulting from the full-duplex (FD) operation. In a large-scale network, FD also increases the multiuser interference due to the large number of active wireless links that…

Traditional self-interference cancellation (SIC) methods are common in full-duplex (FD) integrated sensing and communication (ISAC) systems. However, exploring new SIC schemes is important due to the limitations of traditional approaches.…

The quality of wireless communication will directly affect the performance of federated learning (FL), so this paper analyze the influence of wireless communication on FL through symbol error rate (SER). In FL system, non-orthogonal…

Speaker-independent speech separation has achieved remarkable performance in recent years with the development of deep neural network (DNN). Various network architectures, from traditional convolutional neural network (CNN) and recurrent…

Graph neural networks (GNNs) have been shown promising in improving the efficiency of learning communication policies by leveraging their permutation properties. Nonetheless, existing works design GNNs only for specific wireless policies,…

Recently, deep neural networks have achieved impressive performance in terms of both reconstruction accuracy and efficiency for single image super-resolution (SISR). However, the network model of these methods is a fully convolutional…

Recently, full duplex (FD) has been studied in 5G LTE millimeter wave (mmWave) cellular communications for New Radio in 3GPP releases 15-17. FD allows bidirectional transmission over the same resources and has the potential to reduce…

Recently, recurrent neural networks (RNNs) as powerful sequence models have re-emerged as a potential acoustic model for statistical parametric speech synthesis (SPSS). The long short-term memory (LSTM) architecture is particularly…

Modern radio systems and transceivers utilize carrier aggregation (CA) to meet the demands for higher and higher data rates. However, the adoption of CA in the existing Long Term Evolution (LTE)-Advanced and emerging 5G New Radio (NR)…

Graph Neural Networks (GNNs) have demonstrated remarkable success in various applications, yet they often struggle to capture long-range dependencies (LRD) effectively. This paper introduces GraphMinNet, a novel GNN architecture that…

In the above paper, the optimal-ordered successive interference cancellation (SIC) detector proposed for multiple input multiple output (MIMO) systems was claimed to require a lower computational complexity than the optimal-ordered SIC…

In this paper, we propose a novel recurrent neural network architecture for speech separation. This architecture is constructed by unfolding the iterations of a sequential iterative soft-thresholding algorithm (ISTA) that solves the…

Full-duplex (FD) communication is a promising candidate to address the data rate limitations in underwater acoustic (UWA) channels. Because of transmission at the same time and on the same frequency band, the signal from the local…

Magnetic resonance imaging (MRI) reconstruction has largely been dominated by deep neural networks (DNN); however, many state-of-the-art architectures use black-box structures, which hinder interpretability and improvement. Here, we propose…