8 June 2022 in IEEE Transactions on Network Science and Engineering
In this paper, we investigate how to deploy computational intelligence and deep learning (DL) in edge-enabled industrial IoT networks. In this system, the IoT devices can collaboratively train a shared model without compromising data privacy. However, due to limited resources in the industrial IoT networks, including computational power, bandwidth, and channel state, it is challenging for many devices to accomplish local training and upload weights to the edge server in time. To address this issue, we propose a novel multi-exit-based federated edge learning (ME-FEEL) framework, where the deep model can be divided into several sub-models with different depths and output prediction from the exit in the corresponding sub-model. In this way, the devices with insufficient computational power can choose the earlier exits and avoid training the complete model, which can help reduce computational latency and enable devices to participate into aggregation as much as possible within a latency threshold. Moreover, we propose a greedy approach-based exit selection and bandwidth allocation algorithm to maximize the total number of exits in each communication round. Simulation experiments are conducted on the classical Fashion-MNIST dataset under a non-independent and identically distributed (non-IID) setting, and it shows that the proposed strategy outperforms the conventional FL. In particular, the proposed ME-FEEL can achieve an accuracy gain up to 32.7% in the industrial IoT networks with the severely limited resources.
12 February 2021 in IEEE Transactions on Communications
This paper aims to devise a generalized maximum likelihood (ML) estimator to robustly detect signals with unknown noise statistics in multiple-input multiple-output (MIMO) systems. In practice, there is little or even no statistical knowledge on the system noise, which in many cases is non-Gaussian, impulsive and not analyzable. Existing detection methods have mainly focused on specific noise models, which are not robust enough with unknown noise statistics. To tackle this issue, we propose a novel ML detection framework to effectively recover the desired signal. Our framework is a fully probabilistic one that can efficiently approximate the unknown noise distribution through a normalizing flow. Importantly, this framework is driven by an unsupervised learning approach, where only the noise samples are required. To reduce the computational complexity, we further present a low-complexity version of the framework, by utilizing an initial estimation to reduce the search space. Simulation results show that our framework outperforms other existing algorithms in terms of bit error rate (BER) in non-analytical noise environments, while it can reach the ML performance bound in analytical noise environments.
10 February 2020 in IEEE Transactions on Vehicular Technology
In this paper, we investigate the classical detection problem for vehicle networks with multiple antennas, by considering practical communication scenarios, where the noises are correlated over time or frequency. In such cases, the conventional detector requires to estimate the joint distribution of the noises, which imposes a huge computational complexity. To tackle this issue, we propose the joint use of a maximum likelihood detector (MLD) and a deep convolutional neural network (DCNN), where MLD is used to produce an initial detection result and DCNN improves the detection by exploiting the local correlation to suppress the noise. Furthermore, the improved DCNN is enhanced by devising the loss function through the cross-entropy of the detection, which can help to suppress the noises and simultaneously force the residual noise to approach the Gaussian distribution. Simulation results are presented to verify the effectiveness of the proposed detector compared to the conventional one. The trained model and source code for this work are available at https://github.com/skypitcher/project_dcnnmld.
1 December 2020 in Physical Communication
2 November 2021 in Cluster Computing
10 February 2020 in IEEE Access
To support the and development and application of the fifth-generation (5G) communication and internet of things (IoT) networks, high data-rate wireless transmission is required. To meet the demand of high data-rate, multiple antennas are equipped at the transmitter and receiver, forming multiple-input multiple-output (MIMO) systems. A big challenge of MIMO is the detector design in correlated noise environments, which should achieve a fine performance with moderate computational complexity. To this end, we employ an iterative framework of a deep convolutional neural network (DCNN) and a linear detector for MIMO systems over correlated noise environments. In this framework, the linear detector can be zero-forcing (ZF), minimum mean square error (MMSE), ZF with successive interference cancellation (ZF-SIC), or MMSE-SIC, which produces an initial estimate of transmitted signals. The DCNN is used to capture the local correlation among noise, and it can produce a more accurate estimate of transmitted signals. Simulation results are finally provided to show that the proposed detector can outperform the conventional linear detectors substantially through capturing the local correlation characteristics among noise.