arXiv subjects

Zhi Liu

Publications and source records attributed to Zhi Liu.

At least 127 records · Page 7Linked to original sources

arXiv2023

Precise determination of $^{210}$Pb $β$ Decay Spectrum at 0 keV and its Implication to Theoretical Calculations

The atomic exchange effect will lead to a significant increase in the probability density of $β$ decays below a few keV. This effect is very important for scientific experiments that performed by low-energy electron spectroscopy measurements. However, the atomic exchange effect involves multi-electron interactions, especially for a system with 82 electrons such as lead. Different parameters will lead to different trends in the energy spectrum predicted by the theory, so it is urgent to carry out experimental measurements to provide parameter limits for the theory. The probability increase brought about by the atomic exchange effect is most obvious near 0keV, and the $β$ energy spectrum is accurately measured near this energy point, so as to provide constraints for the physical model of atomic exchange. However, it is extremely difficult to measure the $β$ energy spectrum at 0keV due to the limitations of electronic noise and internal conversion effects. The excited decay path of $^{210}$Pb was taken as the observation object,by measuring the total energy spectrum of $β$ rays and cascaded gamma rays, the precise measurement of the $β$ energy spectrum near 0keV has been completed. The analysis of the $β$ energy spectrum of $^{210}$Pb gives the following conclusions. The experimental results first verified the theory that the exchange effect causes the probability increase at the low energy end near 0keV. At the same time, the experimental results are higher than the existing predictions of the atomic exchange effect. At least for Pb element, all the electron shells have played a role in improving the probability density of the low end of the $β$ energy spectrum. This discovery will promote the theoretical calculation of the $β$ energy spectrum of $^{214}$Pb, at the same time, it also indicates that the reactor neutrinos have a higher probability density at the omnipotent end.

nucl-ex↗

arXiv2023

Multimodal Sentiment Analysis: A Survey

Multimodal sentiment analysis has become an important research area in the field of artificial intelligence. With the latest advances in deep learning, this technology has reached new heights. It has great potential for both application and research, making it a popular research topic. This review provides an overview of the definition, background, and development of multimodal sentiment analysis. It also covers recent datasets and advanced models, emphasizing the challenges and future prospects of this technology. Finally, it looks ahead to future research directions. It should be noted that this review provides constructive suggestions for promising research directions and building better performing multimodal sentiment analysis models, which can help researchers in this field.

cs.CL↗

arXiv2023

No-Service Rail Surface Defect Segmentation via Normalized Attention and Dual-scale Interaction

No-service rail surface defect (NRSD) segmentation is an essential way for perceiving the quality of no-service rails. However, due to the complex and diverse outlines and low-contrast textures of no-service rails, existing natural image segmentation methods cannot achieve promising performance in NRSD images, especially in some unique and challenging NRSD scenes. To this end, in this paper, we propose a novel segmentation network for NRSDs based on Normalized Attention and Dual-scale Interaction, named NaDiNet. Specifically, NaDiNet follows the enhancement-interaction paradigm. The Normalized Channel-wise Self-Attention Module (NAM) and the Dual-scale Interaction Block (DIB) are two key components of NaDiNet. NAM is a specific extension of the channel-wise self-attention mechanism (CAM) to enhance features extracted from low-contrast NRSD images. The softmax layer in CAM will produce very small correlation coefficients which are not conducive to low-contrast feature enhancement. Instead, in NAM, we directly calculate the normalized correlation coefficient between channels to enlarge the feature differentiation. DIB is specifically designed for the feature interaction of the enhanced features. It has two interaction branches with dual scales, one for fine-grained clues and the other for coarse-grained clues. With both branches working together, DIB can perceive defect regions of different granularities. With these modules working together, our NaDiNet can generate accurate segmentation map. Extensive experiments on the public NRSD-MN dataset with man-made and natural NRSDs demonstrate that our proposed NaDiNet with various backbones (i.e., VGG, ResNet, and DenseNet) consistently outperforms 10 state-of-the-art methods. The code and results of our method are available at https://github.com/monxxcn/NaDiNet.

cs.CV↗

arXiv2023

Deep Neural Networks in Video Human Action Recognition: A Review

Currently, video behavior recognition is one of the most foundational tasks of computer vision. The 2D neural networks of deep learning are built for recognizing pixel-level information such as images with RGB, RGB-D, or optical flow formats, with the current increasingly wide usage of surveillance video and more tasks related to human action recognition. There are increasing tasks requiring temporal information for frames dependency analysis. The researchers have widely studied video-based recognition rather than image-based(pixel-based) only to extract more informative elements from geometry tasks. Our current related research addresses multiple novel proposed research works and compares their advantages and disadvantages between the derived deep learning frameworks rather than machine learning frameworks. The comparison happened between existing frameworks and datasets, which are video format data only. Due to the specific properties of human actions and the increasingly wide usage of deep neural networks, we collected all research works within the last three years between 2020 to 2022. In our article, the performance of deep neural networks surpassed most of the techniques in the feature learning and extraction tasks, especially video action recognition.

cs.CV↗

arXiv2023

Lightweight Salient Object Detection in Optical Remote-Sensing Images via Semantic Matching and Edge Alignment

Recently, relying on convolutional neural networks (CNNs), many methods for salient object detection in optical remote sensing images (ORSI-SOD) are proposed. However, most methods ignore the huge parameters and computational cost brought by CNNs, and only a few pay attention to the portability and mobility. To facilitate practical applications, in this paper, we propose a novel lightweight network for ORSI-SOD based on semantic matching and edge alignment, termed SeaNet. Specifically, SeaNet includes a lightweight MobileNet-V2 for feature extraction, a dynamic semantic matching module (DSMM) for high-level features, an edge self-alignment module (ESAM) for low-level features, and a portable decoder for inference. First, the high-level features are compressed into semantic kernels. Then, semantic kernels are used to activate salient object locations in two groups of high-level features through dynamic convolution operations in DSMM. Meanwhile, in ESAM, cross-scale edge information extracted from two groups of low-level features is self-aligned through L2 loss and used for detail enhancement. Finally, starting from the highest-level features, the decoder infers salient objects based on the accurate locations and fine details contained in the outputs of the two modules. Extensive experiments on two public datasets demonstrate that our lightweight SeaNet not only outperforms most state-of-the-art lightweight methods but also yields comparable accuracy with state-of-the-art conventional methods, while having only 2.76M parameters and running with 1.7G FLOPs for 288x288 inputs. Our code and results are available at https://github.com/MathLee/SeaNet.

cs.CV↗

arXiv2023

Fraudulent User Detection Via Behavior Information Aggregation Network (BIAN) On Large-Scale Financial Social Network

Financial frauds cause billions of losses annually and yet it lacks efficient approaches in detecting frauds considering user profile and their behaviors simultaneously in social network . A social network forms a graph structure whilst Graph neural networks (GNN), a promising research domain in Deep Learning, can seamlessly process non-Euclidean graph data . In financial fraud detection, the modus operandi of criminals can be identified by analyzing user profile and their behaviors such as transaction, loaning etc. as well as their social connectivity. Currently, most GNNs are incapable of selecting important neighbors since the neighbors' edge attributes (i.e., behaviors) are ignored. In this paper, we propose a novel behavior information aggregation network (BIAN) to combine the user behaviors with other user features. Different from its close "relatives" such as Graph Attention Networks (GAT) and Graph Transformer Networks (GTN), it aggregates neighbors based on neighboring edge attribute distribution, namely, user behaviors in financial social network. The experimental results on a real-world large-scale financial social network dataset, DGraph, show that BIAN obtains the 10.2% gain in AUROC comparing with the State-Of-The-Art models.

cs.SI↗

arXiv2023

SGDA: Towards 3D Universal Pulmonary Nodule Detection via Slice Grouped Domain Attention

Lung cancer is the leading cause of cancer death worldwide. The best solution for lung cancer is to diagnose the pulmonary nodules in the early stage, which is usually accomplished with the aid of thoracic computed tomography (CT). As deep learning thrives, convolutional neural networks (CNNs) have been introduced into pulmonary nodule detection to help doctors in this labor-intensive task and demonstrated to be very effective. However, the current pulmonary nodule detection methods are usually domain-specific, and cannot satisfy the requirement of working in diverse real-world scenarios. To address this issue, we propose a slice grouped domain attention (SGDA) module to enhance the generalization capability of the pulmonary nodule detection networks. This attention module works in the axial, coronal, and sagittal directions. In each direction, we divide the input feature into groups, and for each group, we utilize a universal adapter bank to capture the feature subspaces of the domains spanned by all pulmonary nodule datasets. Then the bank outputs are combined from the perspective of domain to modulate the input group. Extensive experiments demonstrate that SGDA enables substantially better multi-domain pulmonary nodule detection performance compared with the state-of-the-art multi-domain learning methods.

eess.IV↗

arXiv2023

Incipient Fault Detection in Power Distribution System: A Time-Frequency Embedded Deep Learning Based Approach

Incipient fault detection in power distribution systems is crucial to improve the reliability of the grid. However, the non-stationary nature and the inadequacy of the training dataset due to the self-recovery of the incipient fault signal, make the incipient fault detection in power distribution systems a great challenge. In this paper, we focus on incipient fault detection in power distribution systems and address the above challenges. In particular, we propose an ADaptive Time-Frequency Memory(AD-TFM) cell by embedding wavelet transform into the Long Short-Term Memory (LSTM), to extract features in time and frequency domain from the non-stationary incipient fault signals.We make scale parameters and translation parameters of wavelet transform learnable to adapt to the dynamic input signals. Based on the stacked AD-TFM cells, we design a recurrent neural network with ATtention mechanism, named AD-TFM-AT model, to detect incipient fault with multi-resolution and multi-dimension analysis. In addition, we propose two data augmentation methods, namely phase switching and temporal sliding, to effectively enlarge the training datasets. Experimental results on two open datasets show that our proposed AD-TFM-AT model and data augmentation methods achieve state-of-the-art (SOTA) performance of incipient fault detection in power distribution system. We also disclose one used dataset logged at State Grid Corporation of China to facilitate future research.

eess.SP↗

arXiv2023

Estimating spot volatility under infinite variation jumps with dependent market microstructure noise

Jumps and market microstructure noise are stylized features of high-frequency financial data. It is well known that they introduce bias in the estimation of volatility (including integrated and spot volatilities) of assets, and many methods have been proposed to deal with this problem. When the jumps are intensive with infinite variation, the efficient estimation of spot volatility under serially dependent noise is not available and is thus in need. For this purpose, we propose a novel estimator of spot volatility with a hybrid use of the pre-averaging technique and the empirical characteristic function. Under mild assumptions, the results of consistency and asymptotic normality of our estimator are established. Furthermore, we show that our estimator achieves an almost efficient convergence rate with optimal variance when the jumps are either less active or active with symmetric structure. Simulation studies verify our theoretical conclusions. We apply our proposed estimator to empirical analyses, such as estimating the weekly volatility curve using second-by-second transaction price data.

econ.EM↗

arXiv2023

FRAS: Federated Reinforcement Learning empowered Adaptive Point Cloud Video Streaming

Point cloud video transmission is challenging due to high encoding/decoding complexity, high video bitrate, and low latency requirement. Consequently, conventional adaptive streaming methodologies often find themselves unsatisfactory to meet the requirements in threefold: 1) current algorithms reuse existing quality of experience (QoE) definitions while overlooking the unique features of point cloud video thus failing to provide optimal user experience, 2) most deep learning approaches require long-span data collections to learn sufficiently varied network conditions and result in long training periods and capacity occupation, 3) cloud training approaches pose privacy risks caused by leakage of user reported service usage and networking conditions. To overcome the limitations, we present FRAS, the first federated reinforcement learning framework, to the best of our knowledge, for adaptive point cloud video streaming. We define a new QoE model which takes the unique features of point cloud video into account. Each client uses reinforcement learning (RL) to train video quality selection with the objective of optimizing the user's QoE under multiple constraints. Then, a federated learning framework is integrated with the RL algorithm to enhance training performance with privacy preservation. Extensive simulations using real point cloud videos and network traces reveal the superiority of the proposed scheme over baseline schemes. We also implement a prototype that demonstrates the performance of FRAS via real-world tests.

cs.MM↗

arXiv2022

Singing Voice Synthesis with Vibrato Modeling and Latent Energy Representation

This paper proposes an expressive singing voice synthesis system by introducing explicit vibrato modeling and latent energy representation. Vibrato is essential to the naturalness of synthesized sound, due to the inherent characteristics of human singing. Hence, a deep learning-based vibrato model is introduced in this paper to control the vibrato's likeliness, rate, depth and phase in singing, where the vibrato likeliness represents the existence probability of vibrato and it would help improve the singing voice's naturalness. Actually, there is no annotated label about vibrato likeliness in existing singing corpus. We adopt a novel vibrato likeliness labeling method to label the vibrato likeliness automatically. Meanwhile, the power spectrogram of audio contains rich information that can improve the expressiveness of singing. An autoencoder-based latent energy bottleneck feature is proposed for expressive singing voice synthesis. Experimental results on the open dataset NUS48E show that both the vibrato modeling and the latent energy representation could significantly improve the expressiveness of singing voice. The audio samples are shown in the demo website.

cs.SD↗

arXiv2022

RGB-T Semantic Segmentation with Location, Activation, and Sharpening

Semantic segmentation is important for scene understanding. To address the scenes of adverse illumination conditions of natural images, thermal infrared (TIR) images are introduced. Most existing RGB-T semantic segmentation methods follow three cross-modal fusion paradigms, i.e. encoder fusion, decoder fusion, and feature fusion. Some methods, unfortunately, ignore the properties of RGB and TIR features or the properties of features at different levels. In this paper, we propose a novel feature fusion-based network for RGB-T semantic segmentation, named \emph{LASNet}, which follows three steps of location, activation, and sharpening. The highlight of LASNet is that we fully consider the characteristics of cross-modal features at different levels, and accordingly propose three specific modules for better segmentation. Concretely, we propose a Collaborative Location Module (CLM) for high-level semantic features, aiming to locate all potential objects. We propose a Complementary Activation Module for middle-level features, aiming to activate exact regions of different objects. We propose an Edge Sharpening Module (ESM) for low-level texture features, aiming to sharpen the edges of objects. Furthermore, in the training phase, we attach a location supervision and an edge supervision after CLM and ESM, respectively, and impose two semantic supervisions in the decoder part to facilitate network convergence. Experimental results on two public datasets demonstrate that the superiority of our LASNet over relevant state-of-the-art methods. The code and results of our method are available at https://github.com/MathLee/LASNet.

cs.CV↗

arXiv2022

Few-Shot Learning of Compact Models via Task-Specific Meta Distillation

We consider a new problem of few-shot learning of compact models. Meta-learning is a popular approach for few-shot learning. Previous work in meta-learning typically assumes that the model architecture during meta-training is the same as the model architecture used for final deployment. In this paper, we challenge this basic assumption. For final deployment, we often need the model to be small. But small models usually do not have enough capacity to effectively adapt to new tasks. In the mean time, we often have access to the large dataset and extensive computing power during meta-training since meta-training is typically performed on a server. In this paper, we propose task-specific meta distillation that simultaneously learns two models in meta-learning: a large teacher model and a small student model. These two models are jointly learned during meta-training. Given a new task during meta-testing, the teacher model is first adapted to this task, then the adapted teacher model is used to guide the adaptation of the student model. The adapted student model is used for final deployment. We demonstrate the effectiveness of our approach in few-shot image classification using model-agnostic meta-learning (MAML). Our proposed method outperforms other alternatives on several benchmark datasets.

cs.LG↗

arXiv2022

DeepTLS: comprehensive and high-performance feature extraction for encrypted traffic

Feature extraction is critical for TLS traffic analysis using machine learning techniques, which it is also very difficult and time-consuming requiring huge engineering efforts. We designed and implemented DeepTLS, a system which extracts full spectrum of features from pcaps across meta, statistical, SPLT, byte distribution, TLS header and certificates. The backend is written in C++ to achieve high performance, which can analyze a GB-size pcap in a few minutes. DeepTLS was thoroughly evaluated against two state-of-the-art tools Joy and Zeek with four well-known malicious traffic datasets consisted of 160 pcaps. Evaluation results show DeepTLS has advantage of analyzing large pcaps with half analysis time, and identified more certificates with acceptable performance loss compared with Joy. DeepTLS can significantly accelerate machine learning pipeline by reducing feature extraction time from hours even days to minutes. The system is online at https://deeptls.com, where test artifacts can be viewed and validated. In addition, two open source tools Pysharkfeat and Tlsfeatmark are also released.

cs.CR↗

arXiv2022

Deep Reinforcement Learning for Optimal Power Flow with Renewables Using Graph Information

Renewable energy resources (RERs) have been increasingly integrated into large-scale distributed power systems. Considering uncertainties and voltage fluctuation issues introduced by RERs, in this paper, we propose a deep reinforcement learning (DRL)-based strategy leveraging spatial-temporal (ST) graphical information of power systems, to dynamically search for the optimal operation, i.e., optimal power flow (OPF), of power systems with a high uptake of RERs. Specifically, we formulate the OPF problem as a multi-objective optimization problem considering generation cost, voltage fluctuation, and transmission loss, and employ deep deterministic policy gradient (DDPG) to learn an optimal allocation strategy for OPF. Moreover, given that the nodes in power systems are self-correlated and interrelated in temporal and spatial views, we develop a multi-grained attention-based spatial-temporal graph convolution network (MG-ASTGCN) for extracting ST graphical correlations and features, aiming to provide prior knowledge of power systems for its sequential DDPG algorithm to more effectively solve OPF. We validate our algorithm on modified IEEE 33, 69, and 118-bus radial distribution systems and demonstrate that our algorithm outperforms other benchmark algorithms. Our experimental results also reveal that our MG-ASTGCN can significantly accelerate DDPG's training process and performance in solving OPF.

cs.LG↗

arXiv2022

Vision-based Uneven BEV Representation Learning with Polar Rasterization and Surface Estimation

In this work, we propose PolarBEV for vision-based uneven BEV representation learning. To adapt to the foreshortening effect of camera imaging, we rasterize the BEV space both angularly and radially, and introduce polar embedding decomposition to model the associations among polar grids. Polar grids are rearranged to an array-like regular representation for efficient processing. Besides, to determine the 2D-to-3D correspondence, we iteratively update the BEV surface based on a hypothetical plane, and adopt height-based feature transformation. PolarBEV keeps real-time inference speed on a single 2080Ti GPU, and outperforms other methods for both BEV semantic segmentation and BEV instance segmentation. Thorough ablations are presented to validate the design. The code will be released at \url{https://github.com/SuperZ-Liu/PolarBEV}.

cs.CV↗

arXiv2022

Autonomous Smart Grid Fault Detection

Smart grid plays a crucial role for the smart society and the upcoming carbon neutral society. Achieving autonomous smart grid fault detection is critical for smart grid system state awareness, maintenance and operation. This paper focuses on fault monitoring in smart grid and discusses the inherent technical challenges and solutions. In particular, we first present the basic principles of smart grid fault detection. Then, we explain the new requirements for autonomous smart grid fault detection, the technical challenges and their possible solutions. A case study is introduced, as a preliminary study for autonomous smart grid fault detection. In addition, we highlight relevant directions for future research.

cs.DC↗

arXiv2022

Layer-by-layer growth of bilayer graphene single-crystals enabled by self-transmitting catalytic activity

Direct growth of large-area vertically stacked two-dimensional (2D) van der Waal (vdW) materials is a prerequisite for their high-end applications in integrated electronics, optoelectronics and photovoltaics. Currently, centimetre- to even metre-scale monolayers of single-crystal graphene (MLG) and hexagonal boron nitride (h-BN) have been achieved by epitaxial growth on various single-crystalline substrates. However, in principle, this success in monolayer epitaxy seems extremely difficult to be replicated to bi- or few-layer growth, as the full coverage of the first layer was believed to terminate the reactivity of those adopting catalytic metal surfaces. Here, we report an exceptional layer-by-layer chemical vapour deposition (CVD) growth of large size bi-layer graphene single-crystals, enabled by self-transmitting catalytic activity from platinum (Pt) surfaces to the outermost graphene layers. In-situ growth and real-time surveillance experiments, under well-controlled environments, unambiguously verify that the growth does follow the layer-by-layer mode on open surfaces of MLG/Pt(111). First-principles calculations indicate that the transmittal of catalytic activity is allowed by an appreciable electronic hybridisation between graphene overlayers and Pt surfaces, enabling catalytic dissociation of hydrocarbons and subsequently direct graphitisation of their radicals on the outermost sp2 carbon surface. This self-transmitting catalytic activity is also proven to be robust for tube-furnace CVD in fabricating single-crystalline graphene bi-, tri- and tetra-layers, as well as h-BN few-layers. Our findings offer an exceptional strategy for potential controllable, layer-by-layer and wafer-scale growth of vertically stacked few-layered 2D single crystals.

cond-mat.mtrl-sci↗