HRHang Ruan

Hang Ruan

*This is an algorithmically generated author record based on publicly available information.

Current Organizations / Institutes

The organizations/institutes from the scholar's latest article

Previous Organizations / Institutes

The organizations / institutes from the scholar's other articles in the past ten years


Hang Ruan has a total of 17 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Open Access

    Semantic segmentation using Firefly Algorithm-based evolving ensemble deep neural networks

    by Li Zhang, Sam Slade, Chee Peng Lim, Houshyar Asadi, Saeid Nahavandi, Haoqian Huang, Hang Ruan


  • Open Access

    Deep Learning-Based Fault Prediction in Wireless Sensor Network Embedded Cyber-Physical Systems for Industrial Processes

    by Hang Ruan, Bogdan Dorneanu, Harvey Arellano-Garcia, Pei Xiao, Li Zhang

    This paper investigates the challenging fault prediction problem in process industries that adopt autonomous and intelligent cyber-physical systems (CPS), which is in line with the emerging developments of industrial internet of things (IIoT) and Industry 4.0. Particularly, we developed an end-to-end deep learning approach based on a large volume of real-time sensory data collected from a chemical plant equipped with wireless sensors. Firstly, a novel recursive architecture with multi-lookback inputs is proposed to perform autoregression on imbalanced time-series data as a preliminary prediction. In this process, a novel learning algorithm named recursive gradient descent (RGD) is developed for the proposed architecture to reduce cumulative prediction uncertainties. Subsequently, a classification model based on temporal convolutions over multiple channels with decay effect is proposed to perform multi-class classification for fault root cause identification and localization. The overall network is named the cumulative uncertainty reduction network (CURNet), for its superior capacity in reducing prediction uncertainties accumulated over multiple prediction steps. Performance evaluations show that CURNet is able to achieve superior performance especially in terms of fault prediction recall and fault type classification accuracy, compared to the existing techniques.


  • Joint Iterative Optimization-Based Low-Complexity Adaptive Hybrid Beamforming for Massive MU-MIMO Systems

    by Hang Ruan, Pei Xiao, Lixia Xiao, James R. Kelly

    This paper proposes a joint iterative optimization based hybrid beamforming technique for massive MU-MIMO systems. The proposed technique jointly and iteratively optimizes the transmitter precoders and combiners, aiming to approach the global optimum solution for the system sum-rate maximization problem. The proposed technique develops an adaptive algorithm exploiting the stochastic gradients (SG) of the local beamformers and provides low-complexity closed-form solutions. Furthermore, an efficient adaptive scheme is developed based on the proposed adaptive algorithm and the closed-form solutions. The proposed algorithm requires the signal-to-interference-plus-noise ratio (SINR) feedback from each user and a limited size transition vector to be exchanged between the transmitter and receivers at each step to update beamformers locally. Analytic result shows that the proposed adaptive algorithm achieves low-complexity when the array size is large and is able to converge within a small number of iterations. Simulation result shows that the proposed technique is able to achieve superior performance comparing to the existing state-of-art techniques. In addition, the knowledge of instantaneous channel state information (CSI) is not required as the channels are also adaptively estimated with each coherence time which is a practical assumption since the CSI is usually unavailable or have time-varying nature in real-time applications.


  • Differentially-Encoded Rectangular Spatial Modulation Approaches the Performance of Its Coherent Counterpart

    by Lixia Xiao, Pei Xiao, Hang Ruan, Naoki Ishikawa, Lei Lu, Yue Xiao, Lajos Hanzo

    A simplified rectangular differential spatial modulation (S-RDSM) scheme is conceived for massive multiple-input multiple-output (MIMO) systems dispensing with the channel state information (CSI). In the proposed S-RDSM scheme, the information bits are first mapped to a conventional SM symbol and then rectangular differential encoding is invoked between a pair of SM symbols. Then a non-coherent detector relying on a forgetting factor is developed, which requires no CSI at the receiver. Explicitly, a low-complexity hard limited maximum likelihood (HL-ML) detector is conceived for our generalized SRDSM scheme, which is characterized by our theoretical analysis. Furthermore, we derive the optimal forgetting factor in closed form, which is capable of significantly reducing the complexity of the associated optimization. Finally, the upper bounds of the average bit error probability (ABEP) are derived using the moment generating function (MGF), and are validated by our simulation results. Both the theoretical and simulation results have shown that the proposed S-RDSM system outperforms the existing non-coherent schemes, despite operating at 10% of the benchmarker’s complexity, whilst approaching the performance of its coherent SM counterpart at a comparable complexity.


  • Distributed Robust Beamforming Based on Low-Rank and Cross-Correlation Techniques: Design and Analysis

    by Hang Ruan, Rodrigo C. de Lamare

    In this work, we present a novel robust distributed beamforming (RDB) approach based on low-rank and cross-correlation techniques. The proposed RDB approach mitigates the effects of channel errors in wireless networks equipped with relays based on the exploitation of the cross-correlation between the received data from the relays at the destination and the system output and low-rank techniques. The relay nodes are equipped with an amplify-and-forward (AF) protocol and the channel errors are modeled using an additive matrix perturbation, which results in degradation of the system performance. The proposed method, denoted low-rank and cross-correlation RDB (LRCC-RDB), considers a total relay transmit power constraint in the system and the goal of maximizing the output signal-to-interference-plus-noise ratio (SINR). We carry out a performance analysis of the proposed LRCC-RDB technique along with a computational complexity study. The proposed LRCC-RDB doesnot require any costly online optimization procedure and simu-lations show an excellent performance as compared to previouslyreported algorithms.


  • Open Access

    Robust Adaptive Beamforming Based on Low-Rank and Cross-Correlation Techniques

    by Hang Ruan, Rodrigo C. de Lamare

    This paper presents cost-effective low-rank techniques for designing robust adaptive beamforming (RAB) algorithms. The proposed algorithms are based on the exploitation of the cross-correlation between the array observation data and the output of the beamformer. First, we construct a general linear equation considered in large dimensions whose solution yields the steering vector mismatch. Then, we employ the idea of the full orthogonalization method (FOM), an orthogonal Krylov subspace based method, to iteratively estimate the steering vector mismatch in a reduced-dimensional subspace, resulting in the proposed orthogonal Krylov subspace projection mismatch estimation (OKSPME) method. We also devise adaptive algorithms based on stochastic gradient (SG) and conjugate gradient (CG) techniques to update the beamforming weights with low complexity and avoid any costly matrix inversion. The main advantages of the proposed low-rank and mismatch estimation techniques are their cost-effectiveness when dealing with high-dimension subspaces or large sensor arrays. Simulations results show excellent performance in terms of the output signal-to-interference-plus-noise ratio (SINR) of the beamformer among all the compared RAB methods.