Fall Detection System Based on Point Cloud Enhancement Model for 24 GHz FMCW Radar.

Automatic fall detection plays a significant role in monitoring the health of senior citizens. In particular, millimeter-wave radar sensors are relevant for human pose recognition in an indoor environment due to their advantages of privacy protection, low hardware cost, and wide range of working conditions. However, low-quality point clouds from 4D radar diminish the reliability of fall detection. To improve the detection accuracy, conventional methods utilize more costly hardware. In this study, we propose a model that can provide high-quality three-dimensional point cloud images of the human body at a low cost. To improve the accuracy and effectiveness of fall detection, a system that extracts distribution features through small radar antenna arrays is developed. The proposed system achieved 99.1% and 98.9% accuracy on test datasets pertaining to new subjects and new environments, respectively.

SSGCNet: A Sparse Spectra Graph Convolutional Network for Epileptic EEG Signal Classification.

In this article, we propose a sparse spectra graph convolutional network (SSGCNet) for epileptic electroencephalogram (EEG) signal classification. The goal is to develop a lightweighted deep learning model while retaining a high level of classification accuracy. To do so, we propose a weighted neighborhood field graph (WNFG) to represent EEG signals. The WNFG reduces redundant edges between graph nodes and has lower graph generation time and memory usage than the baseline solution. The sequential graph convolutional network is further developed from a WNFG by combining sparse weight pruning and the alternating direction method of multipliers (ADMM). Compared with the state-of-the-art method, our method has the same classification accuracy on the Bonn public dataset and the spikes and slow waves (SSW) clinical real dataset when the connection rate is ten times smaller.

EEG Signal Epilepsy Detection With a Weighted Neighbor Graph Representation and Two-Stream Graph-Based Framework.

Epilepsy is one of the most common neurological diseases. Clinically, epileptic seizure detection is usually performed by analyzing electroencephalography (EEG) signals. At present, deep learning models have been widely used for single-channel EEG signal epilepsy detection, but this method is difficult to explain the classification results. Researchers have attempted to solve interpretive problems by combining graph representation of EEG signals with graph neural network models. Recently, the combination of graph representations and graph neural network (GNN) models has been increasingly applied to single-channel epilepsy detection. By this methodology, the raw EEG signal is transformed to its graph representation, and a GNN model is used to learn latent features and classify whether the data indicates an epileptic seizure episode. However, existing methods are faced with two major challenges. First, existing graph representations tend to have high time complexity as they generally require each vertex to traverse all other vertices to construct a graph structure. Some of them also have high space complexity for being dense. Second, while separate graph representations can be derived from a single-channel EEG signal in both time and frequency domains, existing GNN models for epilepsy detection can learn from a single graph representation, which makes it hard to let the information from the two domains complement each other. For addressing these challenges, we propose a Weighted Neighbour Graph (WNG) representation for EEG signals. Reducing the redundant edges of the existing graph, WNG can be both time and space-efficient, and as informative as its less efficient counterparts. We then propose a two-stream graph-based framework to simultaneously learn features from WNG in both time and frequency domain. Extensive experiments demonstrate the effectiveness and efficiency of the proposed methods.

The spike gating flow: A hierarchical structure-based spiking neural network for online gesture recognition.

Action recognition is an exciting research avenue for artificial intelligence since it may be a game changer in emerging industrial fields such as robotic visions and automobiles. However, current deep learning (DL) faces major challenges for such applications because of the huge computational cost and inefficient learning. Hence, we developed a novel brain-inspired spiking neural network (SNN) based system titled spiking gating flow (SGF) for online action learning. The developed system consists of multiple SGF units which are assembled in a hierarchical manner. A single SGF unit contains three layers: a feature extraction layer, an event-driven layer, and a histogram-based training layer. To demonstrate the capability of the developed system, we employed a standard dynamic vision sensor (DVS) gesture classification as a benchmark. The results indicated that we can achieve 87.5% of accuracy which is comparable with DL, but at a smaller training/inference data number ratio of 1.5:1. Only a single training epoch is required during the learning process. Meanwhile, to the best of our knowledge, this is the highest accuracy among the non-backpropagation based SNNs. Finally, we conclude the few-shot learning (FSL) paradigm of the developed network: 1) a hierarchical structure-based network design involves prior human knowledge; 2) SNNs for content-based global dynamic feature detection.

A 340 nW/Channel 110 dB PSRR Neural Recording Analog Front-End Using Replica-Biasing LNA, Level-Shifter Assisted PGA, and Averaged LFP Servo Loop in 65 nm CMOS.

This paper presents an 8-channel energy-efficient analog front-end (AFE) for neural recording, with improvements in power supply rejection ratio (PSRR) and dynamic range. The input stage in the low noise amplifier (LNA) adopts low voltage supply (0.35 V) and current-reusing to achieve ultralow power. To maintain a high PSRR performance while using such a low-voltage supply, a replica-biasing scheme is proposed to generate a stable bias current for the input stage of the LNA despite large supply interference. By exploiting the signal characteristics in the tetrode recording, an averaged local field potential (A-LFP) servo loop is introduced to extend the dynamic range without consuming too much extra power and chip area. The A-LFP signal is generated by integrating the four-channel PGA outputs from the same tetrode. Furthermore, the outputs of the programmable gain amplifier (PGA) are level shifted to bias the input nodes of the amplifier through large pseudo resistors, thus increase the maximum output range without distortion under the low-voltage supply. The proof-of-concept prototype is fabricated in a 65 nm CMOS process. Each recording channel including an LNA and a PGA occupies 0.04 mm 2 and consumes 340 nW from the 0.35 V and 0.7 V supply. Each A-LFP servo loop, which is shared by four recording channels, occupies 0.04 mm 2 and consumes 190 nW. The maximum gain of the AFE is 54 dB, and the input-referred noise is 6.7 µV over the passband from 0.5 Hz to 6.5 kHz. Measurement also shows that the 0.35 V replica-biasing input stage can tolerate a large interferer up to 200 mVpp with a PSRR of 74 dB, which has been improved to 110 dB with a silicon respin that shields critical wires in the layout.