arXiv subjects

Yan Zhao

Publications and source records attributed to Yan Zhao.

At least 109 records · Page 6Linked to original sources

arXiv2023

LightCTS: A Lightweight Framework for Correlated Time Series Forecasting

Correlated time series (CTS) forecasting plays an essential role in many practical applications, such as traffic management and server load control. Many deep learning models have been proposed to improve the accuracy of CTS forecasting. However, while models have become increasingly complex and computationally intensive, they struggle to improve accuracy. Pursuing a different direction, this study aims instead to enable much more efficient, lightweight models that preserve accuracy while being able to be deployed on resource-constrained devices. To achieve this goal, we characterize popular CTS forecasting models and yield two observations that indicate directions for lightweight CTS forecasting. On this basis, we propose the LightCTS framework that adopts plain stacking of temporal and spatial operators instead of alternate stacking that is much more computationally expensive. Moreover, LightCTS features light temporal and spatial operator modules, called L-TCN and GL-Former, that offer improved computational efficiency without compromising their feature extraction capabilities. LightCTS also encompasses a last-shot compression scheme to reduce redundant temporal features and speed up subsequent computations. Experiments with single-step and multi-step forecasting benchmark datasets show that LightCTS is capable of nearly state-of-the-art accuracy at much reduced computational and storage overheads.

cs.LG↗

arXiv2023

Deep Implicit Distribution Alignment Networks for Cross-Corpus Speech Emotion Recognition

In this paper, we propose a novel deep transfer learning method called deep implicit distribution alignment networks (DIDAN) to deal with cross-corpus speech emotion recognition (SER) problem, in which the labeled training (source) and unlabeled testing (target) speech signals come from different corpora. Specifically, DIDAN first adopts a simple deep regression network consisting of a set of convolutional and fully connected layers to directly regress the source speech spectrums into the emotional labels such that the proposed DIDAN can own the emotion discriminative ability. Then, such ability is transferred to be also applicable to the target speech samples regardless of corpus variance by resorting to a well-designed regularization term called implicit distribution alignment (IDA). Unlike widely-used maximum mean discrepancy (MMD) and its variants, the proposed IDA absorbs the idea of sample reconstruction to implicitly align the distribution gap, which enables DIDAN to learn both emotion discriminative and corpus invariant features from speech spectrums. To evaluate the proposed DIDAN, extensive cross-corpus SER experiments on widely-used speech emotion corpora are carried out. Experimental results show that the proposed DIDAN can outperform lots of recent state-of-the-art methods in coping with the cross-corpus SER tasks.

cs.SD↗

arXiv2023

Kainate receptor modulation by NETO2

Glutamate-gated kainate receptors (KARs) are ubiquitous in the central nervous system of vertebrates, mediate synaptic transmission on post-synapse, and modulate transmitter release on pre-synapse. In the brain, the trafficking, gating kinetics, and pharmacology of KARs are tightly regulated by Neuropilin and tolloid-like proteins (Netos). Here we report cryo-EM structures of homo-tetrameric GluK2 in complex with Neto2 at inhibited and desensitized states, illustrating variable stoichiometry of GluK2-Neto2 complexes, with one or two Neto2 subunits associate with the GluK2. We find that Neto2 accesses only two broad faces of KARs, intermolecularly crosslinking the lower-lobe of ATDA/C, upper-lobe of LBDB/D, and lower-lobe of LBDA/C, illustrating how Neto2 regulates receptor-gating kinetics. The transmembrane helix of Neto2 is positioned proximal to the selectivity filter and competes with the amphiphilic H1-helix after M4 for interacting with an ICD formed by the M1-M2 linkers of the receptor, revealing how rectification is regulated by Neto2.

q-bio.BM↗

arXiv2022

Power of Sine Hamiltonian Operator for Estimating the Eigenstate Energies on Quantum Computers

Quantum computers have been shown to have tremendous potential in solving difficult problems in quantum chemistry. In this paper, we propose a new classical quantum hybrid method, named as power of sine Hamiltonian operator (PSHO), to evaluate the eigenvalues of a given Hamiltonian (H). In PSHO, for any reference state, the normalized energy of the sine Hamiltonian power state can be determined. With the increase of the power, the initial reference state can converge to the eigenstate with the largest absolute eigenvalue in the coefficients of the expansion of reference state, and the normalized energy of the sine Hamiltonian power state converges to Ei. The ground and excited state energies of a Hamiltonian can be determined by taking different t values. The performance of the PSHO method is demonstrated by numerical calculations of the H4 and LiH molecules. Compared with the current popular variational quantum eigensolver method, PSHO does not need to design the ansatz circuits and avoids the complex nonlinear optimization problems. PSHO has great application potential in near term quantum devices.

quant-ph↗

arXiv2022

Speech Emotion Recognition via an Attentive Time-Frequency Neural Network

Spectrogram is commonly used as the input feature of deep neural networks to learn the high(er)-level time-frequency pattern of speech signal for speech emotion recognition (SER). \textcolor{black}{Generally, different emotions correspond to specific energy activations both within frequency bands and time frames on spectrogram, which indicates the frequency and time domains are both essential to represent the emotion for SER. However, recent spectrogram-based works mainly focus on modeling the long-term dependency in time domain, leading to these methods encountering the following two issues: (1) neglecting to model the emotion-related correlations within frequency domain during the time-frequency joint learning; (2) ignoring to capture the specific frequency bands associated with emotions.} To cope with the issues, we propose an attentive time-frequency neural network (ATFNN) for SER, including a time-frequency neural network (TFNN) and time-frequency attention. Specifically, aiming at the first issue, we design a TFNN with a frequency-domain encoder (F-Encoder) based on the Transformer encoder and a time-domain encoder (T-Encoder) based on the Bidirectional Long Short-Term Memory (Bi-LSTM). The F-Encoder and T-Encoder model the correlations within frequency bands and time frames, respectively, and they are embedded into a time-frequency joint learning strategy to obtain the time-frequency patterns for speech emotions. Moreover, to handle the second issue, we also adopt time-frequency attention with a frequency-attention network (F-Attention) and a time-attention network (T-Attention) to focus on the emotion-related frequency band ranges and time frame ranges, which can enhance the discriminability of speech emotion features.

cs.SD↗

arXiv2022

A Comparative Study on Unsupervised Anomaly Detection for Time Series: Experiments and Analysis

The continued digitization of societal processes translates into a proliferation of time series data that cover applications such as fraud detection, intrusion detection, and energy management, where anomaly detection is often essential to enable reliability and safety. Many recent studies target anomaly detection for time series data. Indeed, area of time series anomaly detection is characterized by diverse data, methods, and evaluation strategies, and comparisons in existing studies consider only part of this diversity, which makes it difficult to select the best method for a particular problem setting. To address this shortcoming, we introduce taxonomies for data, methods, and evaluation strategies, provide a comprehensive overview of unsupervised time series anomaly detection using the taxonomies, and systematically evaluate and compare state-of-the-art traditional as well as deep learning techniques. In the empirical study using nine publicly available datasets, we apply the most commonly-used performance evaluation metrics to typical methods under a fair implementation standard. Based on the structuring offered by the taxonomies, we report on empirical studies and provide guidelines, in the form of comparative tables, for choosing the methods most suitable for particular application settings. Finally, we propose research directions for this dynamic field.

cs.LG↗

arXiv2022

Design Automation for Fast, Lightweight, and Effective Deep Learning Models: A Survey

Deep learning technologies have demonstrated remarkable effectiveness in a wide range of tasks, and deep learning holds the potential to advance a multitude of applications, including in edge computing, where deep models are deployed on edge devices to enable instant data processing and response. A key challenge is that while the application of deep models often incurs substantial memory and computational costs, edge devices typically offer only very limited storage and computational capabilities that may vary substantially across devices. These characteristics make it difficult to build deep learning solutions that unleash the potential of edge devices while complying with their constraints. A promising approach to addressing this challenge is to automate the design of effective deep learning models that are lightweight, require only a little storage, and incur only low computational overheads. This survey offers comprehensive coverage of studies of design automation techniques for deep learning models targeting edge computing. It offers an overview and comparison of key metrics that are used commonly to quantify the proficiency of models in terms of effectiveness, lightness, and computational costs. The survey then proceeds to cover three categories of the state-of-the-art of deep model design automation techniques: automated neural architecture search, automated model compression, and joint automated design and compression. Finally, the survey covers open issues and directions for future research.

cs.LG↗

arXiv2022

Uncertainty Quantification for Traffic Forecasting: A Unified Approach

Uncertainty is an essential consideration for time series forecasting tasks. In this work, we specifically focus on quantifying the uncertainty of traffic forecasting. To achieve this, we develop Deep Spatio-Temporal Uncertainty Quantification (DeepSTUQ), which can estimate both aleatoric and epistemic uncertainty. We first leverage a spatio-temporal model to model the complex spatio-temporal correlations of traffic data. Subsequently, two independent sub-neural networks maximizing the heterogeneous log-likelihood are developed to estimate aleatoric uncertainty. For estimating epistemic uncertainty, we combine the merits of variational inference and deep ensembling by integrating the Monte Carlo dropout and the Adaptive Weight Averaging re-training methods, respectively. Finally, we propose a post-processing calibration approach based on Temperature Scaling, which improves the model's generalization ability to estimate uncertainty. Extensive experiments are conducted on four public datasets, and the empirical results suggest that the proposed method outperforms state-of-the-art methods in terms of both point prediction and uncertainty quantification.

cs.LG↗

arXiv2022

Learning to Predict Diverse Human Motions from a Single Image via Mixture Density Networks

Human motion prediction, which plays a key role in computer vision, generally requires a past motion sequence as input. However, in real applications, a complete and correct past motion sequence can be too expensive to achieve. In this paper, we propose a novel approach to predicting future human motions from a much weaker condition, i.e., a single image, with mixture density networks (MDN) modeling. Contrary to most existing deep human motion prediction approaches, the multimodal nature of MDN enables the generation of diverse future motion hypotheses, which well compensates for the strong stochastic ambiguity aggregated by the single input and human motion uncertainty. In designing the loss function, we further introduce the energy-based formulation to flexibly impose prior losses over the learnable parameters of MDN to maintain motion coherence as well as improve the prediction accuracy by customizing the energy functions. Our trained model directly takes an image as input and generates multiple plausible motions that satisfy the given condition. Extensive experiments on two standard benchmark datasets demonstrate the effectiveness of our method in terms of prediction diversity and accuracy.

cs.CV↗

arXiv2022

Intra Encoding Complexity Control with a Time-Cost Model for Versatile Video Coding

For the latest video coding standard Versatile Video Coding (VVC), the encoding complexity is much higher than previous video coding standards to achieve a better coding efficiency, especially for intra coding. The complexity becomes a major barrier of its deployment and use. Even with many fast encoding algorithms, it is still practically important to control the encoding complexity to a given level. Inspired by rate control algorithms, we propose a scheme to precisely control the intra encoding complexity of VVC. In the proposed scheme, a Time-PlanarCost (viz. Time-Cost, or T-C) model is utilized for CTU encoding time estimation. By combining a set of predefined parameters and the T-C model, CTU-level complexity can be roughly controlled. Then to achieve a precise picture-level complexity control, a framework is constructed including uneven complexity pre-allocation, preset selection and feedback. Experimental results show that, for the challenging intra coding scenario, the complexity error quickly converges to under 3.21%, while keeping a reasonable time saving and rate-distortion (RD) performance. This proves the efficiency of the proposed methods.

eess.IV↗

arXiv2022

VoiceFixer: A Unified Framework for High-Fidelity Speech Restoration

Speech restoration aims to remove distortions in speech signals. Prior methods mainly focus on a single type of distortion, such as speech denoising or dereverberation. However, speech signals can be degraded by several different distortions simultaneously in the real world. It is thus important to extend speech restoration models to deal with multiple distortions. In this paper, we introduce VoiceFixer, a unified framework for high-fidelity speech restoration. VoiceFixer restores speech from multiple distortions (e.g., noise, reverberation, and clipping) and can expand degraded speech (e.g., noisy speech) with a low bandwidth to 44.1 kHz full-bandwidth high-fidelity speech. We design VoiceFixer based on (1) an analysis stage that predicts intermediate-level features from the degraded speech, and (2) a synthesis stage that generates waveform using a neural vocoder. Both objective and subjective evaluations show that VoiceFixer is effective on severely degraded speech, such as real-world historical speech recordings. Samples of VoiceFixer are available at https://haoheliu.github.io/voicefixer.

eess.AS↗

arXiv2022

Robust and Explainable Autoencoders for Unsupervised Time Series Outlier Detection---Extended Version

Time series data occurs widely, and outlier detection is a fundamental problem in data mining, which has numerous applications. Existing autoencoder-based approaches deliver state-of-the-art performance on challenging real-world data but are vulnerable to outliers and exhibit low explainability. To address these two limitations, we propose robust and explainable unsupervised autoencoder frameworks that decompose an input time series into a clean time series and an outlier time series using autoencoders. Improved explainability is achieved because clean time series are better explained with easy-to-understand patterns such as trends and periodicities. We provide insight into this by means of a post-hoc explainability analysis and empirical studies. In addition, since outliers are separated from clean time series iteratively, our approach offers improved robustness to outliers, which in turn improves accuracy. We evaluate our approach on five real-world datasets and report improvements over the state-of-the-art approaches in terms of robustness and explainability. This is an extended version of "Robust and Explainable Autoencoders for Unsupervised Time Series Outlier Detection", to appear in IEEE ICDE 2022.

cs.LG↗

arXiv2022

VAT-Mart: Learning Visual Action Trajectory Proposals for Manipulating 3D ARTiculated Objects

Perceiving and manipulating 3D articulated objects (e.g., cabinets, doors) in human environments is an important yet challenging task for future home-assistant robots. The space of 3D articulated objects is exceptionally rich in their myriad semantic categories, diverse shape geometry, and complicated part functionality. Previous works mostly abstract kinematic structure with estimated joint parameters and part poses as the visual representations for manipulating 3D articulated objects. In this paper, we propose object-centric actionable visual priors as a novel perception-interaction handshaking point that the perception system outputs more actionable guidance than kinematic structure estimation, by predicting dense geometry-aware, interaction-aware, and task-aware visual action affordance and trajectory proposals. We design an interaction-for-perception framework VAT-Mart to learn such actionable visual representations by simultaneously training a curiosity-driven reinforcement learning policy exploring diverse interaction trajectories and a perception module summarizing and generalizing the explored knowledge for pointwise predictions among diverse shapes. Experiments prove the effectiveness of the proposed approach using the large-scale PartNet-Mobility dataset in SAPIEN environment and show promising generalization capabilities to novel test shapes, unseen object categories, and real-world data. Project page: https://hyperplane-lab.github.io/vat-mart

cs.CV↗

arXiv2022

Influence-aware Task Assignment in Spatial Crowdsourcing (Technical Report)

With the widespread diffusion of smartphones, Spatial Crowdsourcing (SC), which aims to assign spatial tasks to mobile workers, has drawn increasing attention in both academia and industry. One of the major issues is how to best assign tasks to workers. Given a worker and a task, the worker will choose to accept the task based on her affinity towards the task, and the worker can propagate the information of the task to attract more workers to perform it. These factors can be measured as worker-task influence. Since workers' affinities towards tasks are different and task issuers may ask workers who performed tasks to propagate the information of tasks to attract more workers to perform them, it is important to analyze worker-task influence when making assignments. We propose and solve a novel influence-aware task assignment problem in SC, where tasks are assigned to workers in a manner that achieves high worker-task influence. In particular, we aim to maximize the number of assigned tasks and worker-task influence. To solve the problem, we first determine workers' affinities towards tasks by identifying workers' historical task-performing patterns. Next, a Historical Acceptance approach is developed to measure workers' willingness of performing a task, i.e., the probability of workers visiting the location of the task when they are informed. Next, we propose a Random reverse reachable-based Propagation Optimization algorithm that exploits reverse reachable sets to calculate the probability of workers being informed about tasks in a social network. Based on worker-task influence derived from the above three factors, we propose three influence-aware task assignment algorithms that aim to maximize the number of assigned tasks and worker-task influence. Extensive experiments on two real-world datasets offer detailed insight into the effectiveness of our solutions.

cs.SI↗

arXiv2022

Quantitative characterisation of the layered structure within lithium-ion batteries using ultrasonic resonance

Lithium-ion batteries (LIBs) are becoming an important energy storage solution to achieve carbon neutrality, but it remains challenging to characterise their internal states for the assurance of performance, durability and safety. This work reports a simple but powerful non-destructive characterisation technique, based on the formation of ultrasonic resonance from the repetitive layers within LIBs. A physical model is developed from the ground up, to interpret the results from standard experimental ultrasonic measurement setups. As output, the method delivers a range of critical pieces of information about the inner structure of LIBs, such as the number of layers, the average thicknesses of electrodes, the image of internal layers, and the states of charge variations across individual layers. This enables the quantitative tracking of internal cell properties, potentially providing new means of quality control during production processes, and tracking the states of health and charge during operation.

physics.class-ph↗

arXiv2022

Stability of Superconducting Nd0.8Sr0.2NiO2 Thin Films

The discovery of superconducting states in the nickelate thin film with infinite-layer structure has paved a new way for studying unconventional superconductivity. So far, research in this field is still very limited due to difficulties in sample preparation. Here we report on the successful preparation of superconducting Nd0.8Sr0.2NiO2 thin film (Tc = 8.0 - 11.1 K) and study the stability of such films in ambient environment, water and under electrochemical conditions. Our work demonstrates that the superconducting state of Nd0.8Sr0.2NiO2 is remarkably stable, which can last for at least 47 days continuous exposure to air at 20 degree Celsius and 35% relative humidity. Further we show the superconductivity disappears after being immersed in de-ionized water at room temperature for 5 hours. Surprisingly, it can also survive under ionic liquid gating conditions with applied voltage up to 4 V, which is even more stable than conventional perovskite complex oxides.

cond-mat.supr-con↗

arXiv2022

Attentional Feature Refinement and Alignment Network for Aircraft Detection in SAR Imagery

Aircraft detection in Synthetic Aperture Radar (SAR) imagery is a challenging task in SAR Automatic Target Recognition (SAR ATR) areas due to aircraft's extremely discrete appearance, obvious intraclass variation, small size and serious background's interference. In this paper, a single-shot detector namely Attentional Feature Refinement and Alignment Network (AFRAN) is proposed for detecting aircraft in SAR images with competitive accuracy and speed. Specifically, three significant components including Attention Feature Fusion Module (AFFM), Deformable Lateral Connection Module (DLCM) and Anchor-guided Detection Module (ADM), are carefully designed in our method for refining and aligning informative characteristics of aircraft. To represent characteristics of aircraft with less interference, low-level textural and high-level semantic features of aircraft are fused and refined in AFFM throughly. The alignment between aircraft's discrete back-scatting points and convolutional sampling spots is promoted in DLCM. Eventually, the locations of aircraft are predicted precisely in ADM based on aligned features revised by refined anchors. To evaluate the performance of our method, a self-built SAR aircraft sliced dataset and a large scene SAR image are collected. Extensive quantitative and qualitative experiments with detailed analysis illustrate the effectiveness of the three proposed components. Furthermore, the topmost detection accuracy and competitive speed are achieved by our method compared with other domain-specific,e.g., DAPN, PADN, and general CNN-based methods,e.g., FPN, Cascade R-CNN, SSD, RefineDet and RPDet.

cs.CV↗

arXiv2021

VoiceFixer: Toward General Speech Restoration with Neural Vocoder

Speech restoration aims to remove distortions in speech signals. Prior methods mainly focus on single-task speech restoration (SSR), such as speech denoising or speech declipping. However, SSR systems only focus on one task and do not address the general speech restoration problem. In addition, previous SSR systems show limited performance in some speech restoration tasks such as speech super-resolution. To overcome those limitations, we propose a general speech restoration (GSR) task that attempts to remove multiple distortions simultaneously. Furthermore, we propose VoiceFixer, a generative framework to address the GSR task. VoiceFixer consists of an analysis stage and a synthesis stage to mimic the speech analysis and comprehension of the human auditory system. We employ a ResUNet to model the analysis stage and a neural vocoder to model the synthesis stage. We evaluate VoiceFixer with additive noise, room reverberation, low-resolution, and clipping distortions. Our baseline GSR model achieves a 0.499 higher mean opinion score (MOS) than the speech enhancement SSR model. VoiceFixer further surpasses the GSR baseline model on the MOS score by 0.256. Moreover, we observe that VoiceFixer generalizes well to severely degraded real speech recordings, indicating its potential in restoring old movies and historical speeches. The source code is available at https://github.com/haoheliu/voicefixer_main.

cs.SD↗