Large-scale antenna systems are considered as a viable technology to compensate for huge pathloss in millimeter-wave (mmWave) communications. However, due to the massive antennas, the channel state information (CSI) acquisition is costly and challenging. In this paper, we develop a novel compressive channel estimation framework based on multiple measurement vectors (MMV). Compared with conventional single measurement vector (SMV)-based approach, the proposed framework exploits the structural sparsity exhibited in the relatively rich local scattering mmWave channels to greatly reduce the training and computational overheads. Moreover, we propose a channel subspace matching pursuit (CSMP) algorithm based on the MUltiple SIgnal Classification (MUSIC) as an MMV solver. By leveraging the benefits of MUSIC, the proposed CSMP can properly exploit the diversity gain from structural sparsity, and further improve the estimation quality via the super-resolution capability. Meanwhile, an efficient implementation method of the proposed CSMP is also presented. Compared to the conventional MMV solver, the proposed CSMP exhibits much lower complexity. Finally, several simulation results show that the MMV-based CSMP achieves significant performance gains over other estimation algorithms, especially when the angular resolutions are high. Regarding the computational cost, the simulation result shows that the MMV-based estimation algorithms are approximately two orders of magnitude smaller than the SMV-based estimation algorithms.
2 December 2020 in IEEE Transactions on Vehicular Technology
In next-generation communications, massive machine-type communications (mMTC) induce severe burden on base stations. To address such an issue, automatic modulation classification (AMC) can help to reduce signaling overhead by blindly recognizing the modulation types without handshaking. Thus, it plays an important role in future intelligent modems. The emerging deep learning (DL) technique stores intelligence in the network, resulting in superior performance over traditional approaches. However, DL-based approaches suffer from heavy training overhead, memory overhead, and computational complexity, which severely hinder practical applications for resource-limited scenarios, such as Internet-of-Things (IoT) networks and unmanned aerial vehicle (UAV)-aided systems. Furthermore, the overhead of online retraining under time-varying fading channels has not been studied in the prior arts. In this work, an accumulated polar feature-based DL with a channel compensation mechanism is proposed to cope with the aforementioned issues. Firstly, the simulation results show that learning features from the polar domain with historical data information can approach near-optimal performance while reducing training overhead by 99.8 times. Secondly, the proposed neural network-based channel estimator (NN-CE) can learn the channel response and compensate for the distorted channel with 13% improvement. Moreover, in applying this lightweight NN-CE in a time-varying fading channel, two efficient mechanisms of online retraining are proposed, which can reduce transmission overhead and retraining overhead by 90% and 76%, respectively. Finally, the performance of the proposed approach is evaluated and compared with prior arts on a public dataset to demonstrate its great efficiency and lightness. The lightweight and efficient learning features of the proposed mechanism will be very attractive for future resource-constrained/aware IoT and Vehicle-to-Everying (V2X) applications.
6 February 2023 in IEEE Journal on Emerging and Selected Topics in Circuits and Systems
Brain-inspired Hyperdimensional Computing (HDC) is an emerging framework in low-energy designs for solving classification tasks at the edge. Unlike mainstream neural networks (NNs) with high computational complexity, HDC offers a fast training strategy and an energy-efficient inference mechanism by computing data in the high-dimensional space with high parallelism. However, the original computing method of HDC results in weak accuracy due to its simplicity. Therefore, many works have proposed algorithmic innovations to improve the accuracy of HDC, while maintaining its efficiency with dedicated hardware architectures. Given this period of rapid evolution, this review paper presents a comprehensive study of recent developments improving the accuracy-efficiency trade-off of HDC, covering both algorithm and hardware-level approaches. Besides, as the amount of data generated by the Internet of the Things (IoT) devices keeps increasing, edge-cloud collaboration has become a key area of research. The emerging federated learning (FL) has become a key enabler in overcoming security and privacy issues by exchanging locally trained models for global aggregation. However, the energy constraint of edge devices hinders them from the real-time training of NN models. Alternatively, adopting HDC as a local model can be a potential solution to alleviating this issue since the computational requirements of HDC are affordable to most edge devices. In addition, HDC-based coding for wireless communication has been gaining traction due to its noise robustness. Therefore, this paper also covers recent works on HDC-based edge-cloud collaborative learning. Finally, we conclude this paper by highlighting the possible applications and future directions of HDC.
28 December 2021 in IEEE Journal of Biomedical and Health Informatics
Heart rate variability (HRV) has been used in assessing mental workload(MW) level. Compared with ECG, photoplethysmogram (PPG) provides convenient in assessing MW with wearable devices, which is more suitable for daily usage. However, PPG collected by smartwatches are prone to suffer from artifacts. Those signal corruptions cause invalid Inter-beat Intervals (IBI), making it challenging to evaluate the HRV feature. Hence, the PPG-based MW assessment system is difficult to obtain a sustainable and reliable assessment of MW. In this paper, we propose a pre- and post- processing technique, called outlier removal and uncertainty estimation, respectively, to reduce the negative influences of invalid IBIs. The proposed method helps to acquire accurate HRV features and evaluate the reliability of incoming IBIs, rejecting possibly misclassified data. We verified our approach in two open datasets, which are CLAS and MAUS. Experiment results show proposed method achieved higher accuracy (66.7% v.s. 74.2%) and lower variance (11.3% v.s. 10.8%) among users, which has comparable performance to an ECG-based MW system.
21 November 2019 in IEEE Transactions on Circuits and Systems I: Regular Papers
Compressive sensing (CS) is applied to electrocardiography (ECG) telemonitoring system to address the energy constraint of signal acquisition in sensors. In addition, on-sensor-analysis transmitting only abnormal data further reduces the energy consumption. To combine both advantages, ``On-CS-sensor-analysis'' can be achieved by compressed learning (CL), which analyzes signals directly in compressed domain. Extreme learning machine (ELM) provides an effective solution to achieve the goal of low-complexity CL. However, single ELM model has limited accuracy and is sensitive to the quality of data. Furthermore, hardware non-idealities in CS sensors result in learning performance degradation. In this work, we propose the ensemble of sub-eigenspace-ELM (SE-ELM), including two novel approaches: 1) We develop the eigenspace transformation for compressed noisy data, and further utilize a subspace-based dictionary to remove the interferences, and 2) Hardware-friendly design for ensemble of ELM provides high accuracy while maintaining low complexity. The simulation results on ECG-based atrial fibrillation show the SE-ELM can achieve the highest accuracy with 61.9% savings of the required multiplications compared with conventional methods. Finally, we implement this engine in TSMC 90 nm technology. The postlayout results show the proposed CL engine can provide competitive area- and energy-efficiency compared to existing machine learning engines.
25 January 2021 in IEEE Open Journal of Circuits and Systems
Extreme learning machine (ELM) has shown to be an effective and low-power approach for real-time electrocardiography (ECG) anomaly detection. However, prior ELM inference chips are noise-prone and lacking in reconfigurability. In this article, we present an arbitrarily reconfigurable ELM inference engine fabricated in 40-nm CMOS technology for robust ECG anomaly detection. By combining Adaptive boosting (Adaboost) and Eigenspace denoising with ELM (AE-ELM), robust classification under noisy conditions is achieved and saves the number of required multiplications by 95.9%. For chip implementation, a reconfigurable VLSI architecture is designed to support arbitrary complexity of AE-ELM, accounting for dynamic change in application requirements. On the other hand, we propose to construct the input weight matrix of ELM as a Bernoulli random matrix, which further reduces the number of multiplications by 55.2%. For real-time detection, parallel computing is exploited to reduce the latency by up to 86.8%. Overall, the 0.21-mm 2 AE-ELM inference engine shows its robustness against noisy signals and achieves $1.83\times$ AEE compared with the state-of-the-art ELM design.