Le He

Bio: Le He is an academic researcher from Guangzhou University. The author has contributed to research in topics: Computer science & Tree (data structure). The author has an hindex of 2, co-authored 4 publications receiving 36 citations.

Learning-Based Signal Detection for MIMO Systems With Unknown Noise Statistics

Abstract: 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.

Efficient Memory-Bounded Optimal Detection for GSM-MIMO Systems

Abstract: We investigate the optimal signal detection problem in large-scale multiple-input multiple-output (MIMO) system with the generalized spatial modulation (GSM) scheme, which can be formulated as a closest lattice point search (CLPS). To identify invalid signals, an efficient pruning strategy is needed while searching on the GSM decision tree. However, the existing algorithms have exponential complexity, whereas they are infeasible in large-scale GSM-MIMO systems. In order to tackle this problem, we propose a memory-efficient pruning strategy by leveraging the combinatorial nature of the GSM signal structure. Thus, the required memory size is squared to the number of transmit antennas. We further propose an efficient memory-bounded maximum likelihood (ML) search (EM-MLS) algorithm by jointly employing the proposed pruning strategy and the memory-bounded best-first algorithm. Theoretical and simulation results show that our proposed algorithm can achieve the optimal bit error rate (BER) performance, while its memory size can be bounded. Moreover, the expected time complexity decreases exponentially with increasing the signal-to-noise ratio (SNR) as well as the system’s excess degree of freedom, and it often converges to squared time under practical scenarios.

Towards Optimally Efficient Search with Deep Learning for Large-Scale MIMO Systems

Abstract: This paper investigates the optimal signal detection problem with a particular interest in large-scale multiple-input multiple-output (MIMO) systems. The problem is NP-hard and can be solved optimally by searching the shortest path on the decision tree. Unfortunately, the existing optimal search algorithms often involve prohibitively high complexities, which indicates that they are infeasible in large-scale MIMO systems. To address this issue, we propose a general heuristic search algorithm, namely, hyperaccelerated tree search (HATS) algorithm. The proposed algorithm employs a deep neural network (DNN) to estimate the optimal heuristic, and then use the estimated heuristic to speed up the underlying memory-bounded search algorithm. This idea is inspired by the fact that the underlying heuristic search algorithm reaches the optimal efficiency with the optimal heuristic function. Simulation results show that the proposed algorithm reaches almost the optimal bit error rate (BER) performance in large-scale systems, while the memory size can be bounded. In the meanwhile, it visits nearly the fewest tree nodes. This indicates that the proposed algorithm reaches almost the optimal efficiency in practical scenarios, and thereby it is applicable for large-scale systems. Besides, the code for this paper is available at https://github.com/skypitcher/hats.

Learning-based MIMO Detection with Dynamic Spatial Modulation

Abstract: —In this paper, we investigate signal detection in emerging dynamic spatial modulation (DSM) based MIMO systems, where existing mapping methods do not work efficiently. Therefore, we propose a combinatorial mapping-based DSM (CM-DSM) scheme in this work. The proposed CM-DSM scheme employs a combinatorial 3D mapping to avoid the detection ambiguity and achieve a lower average number of active antennas in the system. Additionally, this mapping helps construct an appropriate decision tree for optimal signal detection. By leveraging the combinatorial nature of CM-DSM, we propose a memory-bounded tree search (METS) algorithm, which efficiently finds the maximum likelihood (ML) estimate. To further enhance detection efficiency, we propose a deep learning boosted version of METS (DL-METS) that learns the optimal heuristic function from implicit data patterns. Simulation results indicate that both the proposed METS and DL-METS work well in the system. In particular, the proposed DL-METS achieves nearly optimal detection performance while maintaining almost the lowest expected computational complexity. This strongly validates the effectiveness of the algorithm proposed in this work.

Distributed Machine Learning for Multiuser Mobile Edge Computing Systems

Abstract: In this paper, we investigate a distributed machine learning approach for a multiuser mobile edge computing (MEC) network in a cognitive eavesdropping environment, where multiple secondary devices (SDs) have some tasks with different priorities to be computed. The SDs can be allowed to use the wireless spectrum as long as the interference to the primary user is tolerated, and an eavesdropper in the network can overhear the confidential message from the SDs, which threatens the data offloading. For the considered system, we firstly present three optimization criteria, whereas criterion I aims to minimize the linear combination of latency and energy consumption, criterion II tries to minimize the latency under a constraint on the energy consumption, and criterion III is to minimize the energy consumption under a constraint on the latency. We then exploit a federated learning framework to solve these optimization problems, by optimizing the offloading ratio, bandwidth and computational capability allocation ratio. Simulation results are finally demonstrated to show that the proposed method can effectively reduce the system cost in terms of latency and energy consumption, and meanwhile ensure more bandwidth and computational capability allocated to the user with a higher taskpriority.

Analytical offloading design for mobile edge computing-based smart internet of vehicle

Abstract: Abstract In this paper, we investigate how to analytically design an analytical offloading strategy for a multiuser mobile edge computing (MEC)-based smart internet of vehicle (IoV), where there are multiple computational access points (CAPs) which can help compute tasks from the vehicular users. As it is difficult to derive an analytical offloading ratio for a general MEC-based IoV network, we turn to provide an analytical offloading scheme for some special MEC networks including one-to-one, one-to-two and two-to-one cases. For each case, we study the system performance by using the linear combination of latency and energy consumption, and derive the analytical offloading ratio through minimizing the system cost. Simulation results are finally presented to verify the proposed studies. In particular, the proposed analytical offloading scheme can achieve the optimal performance of the brute force (BF) scheme. The analytical results in this paper can serve as an important reference for the analytical offloading design for a general MEC-based IoV.