In this paper, a unitary precoder is proposed to suppress the out-of-subband (OOSB) spectral leakage and reduce the peak-to-average-power-ratio (PAPR) for DFT-based orthogonal frequency division multiple access uplink signal. The optimum precoder is developed by solving a multi-objective optimization problem and a method which includes two steps is presented. First, employ eigenvalue decomposition to design the precoder with minimizing OOSB power radiation. Then search for the optimum permutation of columns to reduce the PAPR sufficiently. Besides, an iterative decoding algorithm for the proposed precoder is designed to improve the system performance on bit-error-rate (BER). Simulations show that the proposed precoding and decoding method offers significant performance advantages of spectral leakage suppression, PAPR reduction, and BER improvement at the same time.

Decoding neural activities related to voluntary and involuntary movements is fundamental to understanding human brain motor circuits and neuromotor disorders and can lead to the development of neuromotor prosthetic devices for neurorehabilitation. This study explores using recorded deep brain local field potentials (LFPs) for robust movement decoding of Parkinson’s disease (PD) and Dystonia patients. The LFP data from voluntary movement activities such as left and right hand index finger clicking were recorded from patients who underwent surgeries for implantation of deep brain stimulation electrodes. Movement-related LFP signal features were extracted by computing instantaneous power related to motor response in different neural frequency bands. An innovative neural network ensemble classifier has been proposed and developed for accurate prediction of finger movement and its forthcoming laterality. The ensemble classifier contains three base neural network classifiers, namely, feedforward, radial basis, and probabilistic neural networks. The majority voting rule is used to fuse the decisions of the three base classifiers to generate the final decision of the ensemble classifier. The overall decoding performance reaches a level of agreement (kappa value) at about0.729±0.16for decoding movement from the resting state and about0.671±0.14for decoding left and right visually cued movements.

Multi-sensor fusion perception plays a pivotal role in advancing autonomous driving. While most existing LiDAR-Camera (LC) fusion methods achieve high detection accuracy, LiDAR is inherently vulnerable to extreme weather conditions and is costlier compared to microwave radar. In this work, we introduce a robust Radar-Camera (RC) fusion model, RCFusionNet, aimed at delivering enhanced and robust detection performances under adverse weather conditions. Specifically, we introduce a Camera Feature Encoder (CFE) to enhance the capability of visual representations which incorporate multi-scale Bird’s Eye View (BEV) features to further enhance the detection performance. Additionally, a Radar Feature Encoder (RFE) is introduced to fully exploit radar point cloud data by selectively extracting informative radar features. Furthermore, we adopt a Radar-Guided Two-Stage fusion strategy (RGTSFS), applied during both the BEV feature generation and the radar-camera feature fusion phases. Extensive evaluations on the nuScenes benchmark demonstrate the effectiveness of our RCFusionNet.