arXiv subjects

Yan Shi

Publications and source records attributed to Yan Shi.

46 records · Page 3Linked to original sources

arXiv2022

Color Segmentation on FPGA Using Minimum Distance Classifier for Automatic Road Sign Detection

Classification is an important step in machine vision systems; it reveals the true identity of an object using features extracted in pre-processing steps. Practical usage requires the operation to be fast, energy efficient and easy to implement. In this paper, we present a design of the Minimum Distance Classifier based on an FPGA platform. It is optimized by the pipelined structure to strike a balance between device utilization and computational speed. In addition, the dimension of the feature space is modeled as a generic parameter, making it possible for the design to re-generate hardware to cope with feature space with arbitrary dimensions. Its primary application is demonstrated in color segmentation on FPGA in the form of efficient classification using color as a feature. This result is further extended by introducing a multi-class component labeling module to label the segmented color components and measure their geometric properties. The combination of these two modules can effectively detect road signs as the region of interests.

eess.IV↗

arXiv2022

GCNs-Net: A Graph Convolutional Neural Network Approach for Decoding Time-resolved EEG Motor Imagery Signals

Towards developing effective and efficient brain-computer interface (BCI) systems, precise decoding of brain activity measured by electroencephalogram (EEG), is highly demanded. Traditional works classify EEG signals without considering the topological relationship among electrodes. However, neuroscience research has increasingly emphasized network patterns of brain dynamics. Thus, the Euclidean structure of electrodes might not adequately reflect the interaction between signals. To fill the gap, a novel deep learning framework based on the graph convolutional neural networks (GCNs) is presented to enhance the decoding performance of raw EEG signals during different types of motor imagery (MI) tasks while cooperating with the functional topological relationship of electrodes. Based on the absolute Pearson's matrix of overall signals, the graph Laplacian of EEG electrodes is built up. The GCNs-Net constructed by graph convolutional layers learns the generalized features. The followed pooling layers reduce dimensionality, and the fully-connected softmax layer derives the final prediction. The introduced approach has been shown to converge for both personalized and group-wise predictions. It has achieved the highest averaged accuracy, 93.06% and 88.57% (PhysioNet Dataset), 96.24% and 80.89% (High Gamma Dataset), at the subject and group level, respectively, compared with existing studies, which suggests adaptability and robustness to individual variability. Moreover, the performance is stably reproducible among repetitive experiments for cross-validation. The excellent performance of our method has shown that it is an important step towards better BCI approaches. To conclude, the GCNs-Net filters EEG signals based on the functional topological relationship, which manages to decode relevant features for brain motor imagery.

eess.SP↗

arXiv2022

Symmetry breaking and anomalous conductivity in a double moiré superlattice

A double moiré superlattice can be realized by stacking three layers of atomically thin two-dimensional materials with designer interlayer twisting or lattice mismatches. In this novel structure, atomic reconstruction of constituent layers could introduce significant modifications to the lattice symmetry and electronic structure at small twist angles. Here, we employ conductive atomic force microscopy (cAFM) to investigate symmetry breaking and local electrical properties in twisted trilayer graphene. We observe clear double moiré superlattices with two distinct moire periods all over the sample. At neighboring domains of the large moiré, the current exhibit either two- or six-fold rotational symmetry, indicating delicate symmetry breaking beyond the rigid model. Moreover, an anomalous current appears at the 'A-A' stacking site of the larger moiré, contradictory to previous observations on twisted bilayer graphene. Both behaviors can be understood by atomic reconstruction, and we also show that the cAFM signal of twisted graphene samples is dominated by the tip-graphene contact resistance that maps the local work function of twisted graphene and the metallic tip qualitatively. Our results unveil cAFM is an effective probe for visualizing atomic reconstruction and symmetry breaking in novel moiré superlattices, which could provide new insights for exploring and manipulating more exotic quantum states based on twisted van der Waals heterostructures.

cond-mat.mes-hall↗

arXiv2021

DoubleStar: Long-Range Attack Towards Depth Estimation based Obstacle Avoidance in Autonomous Systems

Depth estimation-based obstacle avoidance has been widely adopted by autonomous systems (drones and vehicles) for safety purpose. It normally relies on a stereo camera to automatically detect obstacles and make flying/driving decisions, e.g., stopping several meters ahead of the obstacle in the path or moving away from the detected obstacle. In this paper, we explore new security risks associated with the stereo vision-based depth estimation algorithms used for obstacle avoidance. By exploiting the weaknesses of the stereo matching in depth estimation algorithms and the lens flare effect in optical imaging, we propose DoubleStar, a long-range attack that injects fake obstacle depth by projecting pure light from two complementary light sources. DoubleStar includes two distinctive attack formats: beams attack and orbs attack, which leverage projected light beams and lens flare orbs respectively to cause false depth perception. We successfully attack two commercial stereo cameras designed for autonomous systems (ZED and Intel RealSense). The visualization of fake depth perceived by the stereo cameras illustrates the false stereo matching induced by DoubleStar. We further use Ardupilot to simulate the attack and demonstrate its impact on drones. To validate the attack on real systems, we perform a real-world attack towards a commercial drone equipped with state-of-the-art obstacle avoidance algorithms. Our attack can continuously bring a flying drone to a sudden stop or drift it away across a long distance under various lighting conditions, even bypassing sensor fusion mechanisms. Specifically, our experimental results show that DoubleStar creates fake depth up to 15 meters in distance at night and up to 8 meters during the daytime. To mitigate this newly discovered threat, we provide discussions on potential countermeasures to defend against DoubleStar.

cs.CR↗

arXiv2020

Synchronized Fractionation and Phase Separation in Binary Colloids

Fractionation is necessary for self-assembly in multicomponent mixtures. Here, reversible fractionation and crystallization are realized and studied in a two-dimensional binary colloids which is supersaturated by enhancing the attraction between colloidal particles. As a deep and fast supersaturation results in gels with a uniform distribution of binary particles, a gradual quasistatic supersaturating process leads to a two-step crystallization in which small particles and large particles are fractionated as coexisting crystal and liquid phases respectively. Fractionation occurs as well in the quasistatic melting of gel. We show that the synchronized fractionation and phase separation arises from the competition between the size-dependent repulsion and the tunable attraction. The results in this study demonstrate a robust mechanism of fractionation via phase separation, and have important implication in understanding the reversible formation of membraneless organelles in living cells.

cond-mat.soft↗

arXiv2020

Attention-based Graph ResNet for Motor Intent Detection from Raw EEG signals

In previous studies, decoding electroencephalography (EEG) signals has not considered the topological relationship of EEG electrodes. However, the latest neuroscience has suggested brain network connectivity. Thus, the exhibited interaction between EEG channels might not be appropriately measured via Euclidean distance. To fill the gap, an attention-based graph residual network, a novel structure of Graph Convolutional Neural Network (GCN), was presented to detect human motor intents from raw EEG signals, where the topological structure of EEG electrodes was built as a graph. Meanwhile, deep residual learning with a full-attention architecture was introduced to address the degradation problem concerning deeper networks in raw EEG motor imagery (MI) data. Individual variability, the critical and longstanding challenge underlying EEG signals, has been successfully handled with the state-of-the-art performance, 98.08% accuracy at the subject level, 94.28% for 20 subjects. Numerical results were promising that the implementation of the graph-structured topology was superior to decode raw EEG data. The innovative deep learning approach was expected to entail a universal method towards both neuroscience research and real-world EEG-based practical applications, e.g., seizure prediction.

eess.SP↗

arXiv2020

Access Points in the Air: Modeling and Optimization of Fixed-Wing UAV Network

Fixed-wing unmanned aerial vehicles (UAVs) are of great potential to serve as aerial access points (APs) owing to better aerodynamic performance and longer flight endurance. However, the inherent hovering feature of fixed-wing UAVs may result in discontinuity of connections and frequent handover of ground users (GUs). In this work, we model and evaluate the performance of a fixed-wing UAV network, where UAV APs provide coverage to GUs with millimeter wave backhaul. Firstly, it reveals that network spatial throughput (ST) is independent of the hover radius under real-time closest-UAV association, while linearly decreases with the hover radius if GUs are associated with the UAVs, whose hover center is the closest. Secondly, network ST is shown to be greatly degraded with the over-deployment of UAV APs due to the growing air-to-ground interference under excessive overlap of UAV cells. Finally, aiming to alleviate the interference, a projection area equivalence (PAE) rule is designed to tune the UAV beamwidth. Especially, network ST can be sustainably increased with growing UAV density and independent of UAV flight altitude if UAV beamwidth inversely grows with the square of UAV density under PAE.

cs.IT↗

arXiv2020

A Vision of C-V2X: Technologies, Field Testing and Challenges with Chinese Development

C-V2X (Cellular Vehicle-to-Everything) is the important enabling technology for autonomous driving and intelligent transportation systems. It evolves from LTE (Long Term Evolution)-V2X to NR (New Radio)-V2X, which will coexist and be complementary with each other to provide low latency, high reliability, and high throughput communications for various C-V2X applications. In this article, a vision of C-V2X is presented. The requirements of the basic road safety and advanced applications, the architecture, the key technologies, and the standards of C-V2X are introduced, highlighting the technical evolution path from LTE-V2X to NR-V2X. Especially, based on the continual and active promotion of C-V2X research, field testing and development in China, the related works and progresses are also presented. Lastly, the trends of C-V2X applications with technical challenges are envisioned.

eess.SP↗

arXiv2019

A Natural Language-Inspired Multi-label Video Streaming Traffic Classification Method Based on Deep Neural Networks

This paper presents a deep-learning based traffic classification method for identifying multiple streaming video sources at the same time within an encrypted tunnel. The work defines a novel feature inspired by Natural Language Processing (NLP) that allows existing NLP techniques to help the traffic classification. The feature extraction method is described, and a large dataset containing video streaming and web traffic is created to verify its effectiveness. Results are obtained by applying several NLP methods to show that the proposed method performs well on both binary and multilabel traffic classification problems. We also show the ability to achieve zero-shot learning with the proposed method.

eess.SP↗

arXiv2016

Modeling and Analysis of SCMA Enhanced D2D and Cellular Hybrid Network

Sparse code multiple access (SCMA) has been recently proposed for the future wireless networks, which allows non-orthogonal spectrum resource sharing and enables system overloading. In this paper, we apply SCMA into device-to-device (D2D) communication and cellular hybrid network, targeting at using the overload feature of SCMA to support massive device connectivity and expand network capacity. Particularly, we develop a stochastic geometry based framework to model and analyze SCMA, considering underlaid and overlaid mode. Based on the results, we analytically compare SCMA with orthogonal frequency-division multiple access (OFDMA) using area spectral efficiency (ASE) and quantify closed-form ASE gain of SCMA over OFDMA. Notably, it is shown that system ASE can be significantly improved using SCMA and the ASE gain scales linearly with the SCMA codeword dimension. Besides, we endow D2D users with an activated probability to balance cross-tier interference in the underlaid mode and derive the optimal activated probability. Meanwhile, we study resource allocation in the overlaid mode and obtain the optimal codebook allocation rule. It is interestingly found that the optimal SCMA codebook allocation rule is independent of cellular network parameters when cellular users are densely deployed. The results are helpful in the implementation of SCMA in the hybrid system.

cs.IT↗