arXiv subjects

Juan Liu

Publications and source records attributed to Juan Liu.

At least 55 records · Page 3Linked to original sources

arXiv2024

Module control of network analysis in psychopathology

The network approach to characterizing psychopathology departs from traditional latent categorical and dimensional approaches. Causal interplay among symptoms contributed to dynamic psychopathology system. Therefore, analyzing the symptom clusters is critical for understanding mental disorders. Furthermore, despite extensive research studying the topological features of symptom networks, the control relationships between symptoms remain largely unclear. Here, we present a novel systematizing concept, module control, to analyze the control principle of the symptom network at a module level. We introduce Module Control Network (MCN) to identify key modules that regulate the network's behavior. By applying our approach to a multivariate psychological dataset, we discover that non-emotional modules, such as sleep-related and stress-related modules, are the primary controlling modules in the symptom network. Our findings indicate that module control can expose central symptom cluster governing psychopathology network, offering novel insights into the underlying mechanisms of mental disorders and individualized approach to psychological interventions.

q-bio.NC↗

arXiv2024

Automatic Assessment of Dysarthria Using Audio-visual Vowel Graph Attention Network

Automatic assessment of dysarthria remains a highly challenging task due to high variability in acoustic signals and the limited data. Currently, research on the automatic assessment of dysarthria primarily focuses on two approaches: one that utilizes expert features combined with machine learning, and the other that employs data-driven deep learning methods to extract representations. Research has demonstrated that expert features are effective in representing pathological characteristics, while deep learning methods excel at uncovering latent features. Therefore, integrating the advantages of expert features and deep learning to construct a neural network architecture based on expert knowledge may be beneficial for interpretability and assessment performance. In this context, the present paper proposes a vowel graph attention network based on audio-visual information, which effectively integrates the strengths of expert knowledges and deep learning. Firstly, various features were combined as inputs, including knowledge based acoustical features and deep learning based pre-trained representations. Secondly, the graph network structure based on vowel space theory was designed, allowing for a deep exploration of spatial correlations among vowels. Finally, visual information was incorporated into the model to further enhance its robustness and generalizability. The method exhibited superior performance in regression experiments targeting Frenchay scores compared to existing approaches.

eess.AS↗

arXiv2024

Are We in The Zone? Exploring The Features and Method of Detecting Simultaneous Flow Experiences Based on EEG Signals

When executing interdependent personal tasks for the team's purpose, simultaneous individual flow(simultaneous flow) is the antecedent condition of achieving shared team flow. Detecting simultaneous flow helps better understanding the status of team members, which is thus important for optimizing multi-user interaction systems. However, there is currently a lack exploration on objective features and methods for detecting simultaneous flow. Based on brain mechanism of flow in teamwork and previous studies on electroencephalogram (EEG)-based individual flow detection, this study aims to explore the significant EEG features related to simultaneous flow, as well as effective detection methods based on EEG signals. First, a two-player simultaneous flow task is designed, based on which we construct the first multi-EEG signals dataset of simultaneous flow. Then, we explore the potential EEG signal features that may be related to individual and simultaneous flow and validate their effectiveness in simultaneous flow detection with various machine learning models. The results show that 1) the inter-brain synchrony features are relevant to simultaneous flow due to enhancing the models' performance in detecting different types of simultaneous flow; 2) the features from the frontal lobe area seem to be given priority attention when detecting simultaneous flows; 3) Random Forests performed best in binary classification while Neural Network and Deep Neural Network3 performed best in ternary classification.

cs.HC↗

arXiv2023

Meta-Reinforcement Learning for Timely and Energy-efficient Data Collection in Solar-powered UAV-assisted IoT Networks

Unmanned aerial vehicles (UAVs) have the potential to greatly aid Internet of Things (IoT) networks in mission-critical data collection, thanks to their flexibility and cost-effectiveness. However, challenges arise due to the UAV's limited onboard energy and the unpredictable status updates from sensor nodes (SNs), which impact the freshness of collected data. In this paper, we investigate the energy-efficient and timely data collection in IoT networks through the use of a solar-powered UAV. Each SN generates status updates at stochastic intervals, while the UAV collects and subsequently transmits these status updates to a central data center. Furthermore, the UAV harnesses solar energy from the environment to maintain its energy level above a predetermined threshold. To minimize both the average age of information (AoI) for SNs and the energy consumption of the UAV, we jointly optimize the UAV trajectory, SN scheduling, and offloading strategy. Then, we formulate this problem as a Markov decision process (MDP) and propose a meta-reinforcement learning algorithm to enhance the generalization capability. Specifically, the compound-action deep reinforcement learning (CADRL) algorithm is proposed to handle the discrete decisions related to SN scheduling and the UAV's offloading policy, as well as the continuous control of UAV flight. Moreover, we incorporate meta-learning into CADRL to improve the adaptability of the learned policy to new tasks. To validate the effectiveness of our proposed algorithms, we conduct extensive simulations and demonstrate their superiority over other baseline algorithms.

cs.IT↗

arXiv2023

StoryTrans: Non-Parallel Story Author-Style Transfer with Discourse Representations and Content Enhancing

Non-parallel text style transfer is an important task in natural language generation. However, previous studies concentrate on the token or sentence level, such as sentence sentiment and formality transfer, but neglect long style transfer at the discourse level. Long texts usually involve more complicated author linguistic preferences such as discourse structures than sentences. In this paper, we formulate the task of non-parallel story author-style transfer, which requires transferring an input story into a specified author style while maintaining source semantics. To tackle this problem, we propose a generation model, named StoryTrans, which leverages discourse representations to capture source content information and transfer them to target styles with learnable style embeddings. We use an additional training objective to disentangle stylistic features from the learned discourse representation to prevent the model from degenerating to an auto-encoder. Moreover, to enhance content preservation, we design a mask-and-fill framework to explicitly fuse style-specific keywords of source texts into generation. Furthermore, we constructed new datasets for this task in Chinese and English, respectively. Extensive experiments show that our model outperforms strong baselines in overall performance of style transfer and content preservation.

cs.CL↗

arXiv2023

Unsupervised Deep Probabilistic Approach for Partial Point Cloud Registration

Deep point cloud registration methods face challenges to partial overlaps and rely on labeled data. To address these issues, we propose UDPReg, an unsupervised deep probabilistic registration framework for point clouds with partial overlaps. Specifically, we first adopt a network to learn posterior probability distributions of Gaussian mixture models (GMMs) from point clouds. To handle partial point cloud registration, we apply the Sinkhorn algorithm to predict the distribution-level correspondences under the constraint of the mixing weights of GMMs. To enable unsupervised learning, we design three distribution consistency-based losses: self-consistency, cross-consistency, and local contrastive. The self-consistency loss is formulated by encouraging GMMs in Euclidean and feature spaces to share identical posterior distributions. The cross-consistency loss derives from the fact that the points of two partially overlapping point clouds belonging to the same clusters share the cluster centroids. The cross-consistency loss allows the network to flexibly learn a transformation-invariant posterior distribution of two aligned point clouds. The local contrastive loss facilitates the network to extract discriminative local features. Our UDPReg achieves competitive performance on the 3DMatch/3DLoMatch and ModelNet/ModelLoNet benchmarks.

cs.CV↗

arXiv2023

Cooperative Data Collection with Multiple UAVs for Information Freshness in the Internet of Things

Maintaining the freshness of information in the Internet of Things (IoT) is a critical yet challenging problem. In this paper, we study cooperative data collection using multiple Unmanned Aerial Vehicles (UAVs) with the objective of minimizing the total average Age of Information (AoI). We consider various constraints of the UAVs, including kinematic, energy, trajectory, and collision avoidance, in order to optimize the data collection process. Specifically, each UAV, which has limited on-board energy, takes off from its initial location and flies over sensor nodes to collect update packets in cooperation with the other UAVs. The UAVs must land at their final destinations with non-negative residual energy after the specified time duration to ensure they have enough energy to complete their missions. It is crucial to design the trajectories of the UAVs and the transmission scheduling of the sensor nodes to enhance information freshness. We model the multi-UAV data collection problem as a Decentralized Partially Observable Markov Decision Process (Dec-POMDP), as each UAV is unaware of the dynamics of the environment and can only observe a part of the sensors. To address the challenges of this problem, we propose a multi-agent Deep Reinforcement Learning (DRL)-based algorithm with centralized learning and decentralized execution. In addition to the reward shaping, we use action masks to filter out invalid actions and ensure that the constraints are met. Simulation results demonstrate that the proposed algorithms can significantly reduce the total average AoI compared to the baseline algorithms, and the use of the action mask method can improve the convergence speed of the proposed algorithm.

cs.IT↗

arXiv2022

Deeply Supervised Layer Selective Attention Network: Towards Label-Efficient Learning for Medical Image Classification

Labeling medical images depends on professional knowledge, making it difficult to acquire large amount of annotated medical images with high quality in a short time. Thus, making good use of limited labeled samples in a small dataset to build a high-performance model is the key to medical image classification problem. In this paper, we propose a deeply supervised Layer Selective Attention Network (LSANet), which comprehensively uses label information in feature-level and prediction-level supervision. For feature-level supervision, in order to better fuse the low-level features and high-level features, we propose a novel visual attention module, Layer Selective Attention (LSA), to focus on the feature selection of different layers. LSA introduces a weight allocation scheme which can dynamically adjust the weighting factor of each auxiliary branch during the whole training process to further enhance deeply supervised learning and ensure its generalization. For prediction-level supervision, we adopt the knowledge synergy strategy to promote hierarchical information interactions among all supervision branches via pairwise knowledge matching. Using the public dataset, MedMNIST, which is a large-scale benchmark for biomedical image classification covering diverse medical specialties, we evaluate LSANet on multiple mainstream CNN architectures and various visual attention modules. The experimental results show the substantial improvements of our proposed method over its corresponding counterparts, demonstrating that LSANet can provide a promising solution for label-efficient learning in the field of medical image classification.

cs.CV↗

arXiv2022

Exploring domain adaptation for deep neural network trained QSM

Quantitative susceptibility mapping (QSM) is a MRI technique that estimates tissue magnetic susceptibility. The generation of QSM requires solving a challenging ill-posed field-to-source inversion problem. Recently, several deep learning (DL) QSM techniques have been proposed and demonstrated impressive performance. Due to the inherent non-existent ground-truth QSM references, these techniques used either COSMOS maps or synthetic data for network training. Synthetic data is easy to generate but often adapt poorly to in-vivo data due to domain shifts. Here, we introduce an easy domain adaptation technique using domain-specific batch normalization to address this problem.

physics.med-ph↗

arXiv2022

Cubic Metric Reduction for Repetitive CAZAC Sequences in frequency domain

In NR-based Access to Unlicensed Spectrum (NR-U) of 5G system, to satisfy the rules of Occupied Channel Bandwidth (OCB) of unlicensed spectrum, the channels of PRACH and PUCCH have to use some sequence repetition mechanisms in frequency domain. These repetition mechanisms will cause serious cubic metric(CM) problems for these channels, although these two types of channels are composed of Constant Amplitude Zero Auto-correlation(CAZAC) sequences.. Based on the characteristics of CAZAC sequences, which are used for PRACH and PUCCH (refer to PUCCH format 0 and format 1) in 5G NR, in this paper, we propose some new mechanisms of CM reduction for these two types of channels considering the design principles to ensure the sequence performance of the auto-correlation and cross-correlation. Then the proposed CM schemes are evaluated and the optimized parameters are further provided considering CM performance and the complexity.

cs.IT↗

arXiv2021

Artificial Intelligence-Based Image Enhancement in PET Imaging: Noise Reduction and Resolution Enhancement

High noise and low spatial resolution are two key confounding factors that limit the qualitative and quantitative accuracy of PET images. AI models for image denoising and deblurring are becoming increasingly popular for post-reconstruction enhancement of PET images. We present here a detailed review of recent efforts for AI-based PET image enhancement with a focus on network architectures, data types, loss functions, and evaluation metrics. We also highlight emerging areas in this field that are quickly gaining popularity, identify barriers to large-scale adoption of AI models for PET image enhancement, and discuss future directions.

eess.IV↗

arXiv2021

Improved Padding in CNNs for Quantitative Susceptibility Mapping

Recently, deep learning methods have been proposed for quantitative susceptibility mapping (QSM) data processing: background field removal, field-to-source inversion, and single-step QSM reconstruction. However, the conventional padding mechanism used in convolutional neural networks (CNNs) can introduce spatial artifacts, especially in QSM background field removal and single-step QSM which requires inference from total fields with extreme large values at the edge boundaries of volume of interest. To address this issue, we propose an improved padding technique which utilizes the neighboring valid voxels to estimate the invalid voxels of feature maps at volume boundaries in the neural networks. Studies using simulated and in-vivo data show that the proposed padding greatly improves estimation accuracy and reduces artifacts in the results in the tasks of background field removal, field-to-source inversion, and single-step QSM reconstruction.

cs.CV↗

arXiv2021

Holographic Maxwellian near-eye display with adjustable and continuous eye-box replication

The Maxwellian display presents always-focused images to the viewer, alleviating the vergence-accommodation conflict (VAC) in near-eye displays (NEDs). However, the limited eyebox of the typical Maxwellian display prevents it from wider applications. We propose a holographic Maxwellian near-eye display with adjustable and continuous eye-box replication. Holographic display provides a way to match the human pupil size with the interval of the replicated eyeboxes, making it possible to eliminate or alleviate double image or blind area problem, which exists long in eyebox expansion for Maxwellian display. Besides, seamless image conversion between viewing points has been achieved through hologram pre-processing. Optical experiment confirms that the interval between replicated eyeboxes is dynamically adjustable, ranging from 2mm to 6mm. The proposed display can present always-focused images and seamless conversion among viewpoints with 5.32$^\circ$ horizontal field of view, and 9mmH * 3mmV eyebox.

physics.optics↗

arXiv2021

A multi-plane augmented reality head-up display system based on volume holographic optical elements with large area

The traditional head-up display (HUD) system has the disadvantages of a small area and a single display plane, here we propose and design an augmented reality (AR) HUD system with multi-plane, large area, high diffraction efficiency and a single picture generation unit (PGU) based on holographic optical elements (HOEs). Since volume HOEs have excellent angle selectivity and wavelength selectivity, HOEs of different wavelengths can be designed to display images in different planes. Experimental and simulated results verify the feasibility of this method. Experimental results show that the diffraction efficiencies of the red, green and blue HOEs are 75.2%, 73.1% and 67.5%. And the size of HOEs is 20cm*15cm. Moreover, the three HOEs of red, green and blue display images at different depths of 150cm, 500cm and 1000cm, respectively. In addition, the field of view (FOV) and eye-box (EB) of the system are 12°*10° and 9.5cm*11.2cm. Furthermore, the light transmittance of the system has reached 60%. It is believed that this technique can be applied to the augmented reality navigation display of vehicles and aviation.

cs.HC↗

arXiv2021

The dynamic energy balance in earthquakes expressed by fault surface morphology

The dynamic energy balance is essential for earthquake studies. The energy balance approach is one of the most famous developments in fracture mechanics. To interpret seismological data, crack models and sliding on a frictional surface (fault) models are widely used. The macroscopically observable energy budget and the microscopic processes can be related through the fracture energy $G_c$. The fault surface morphology is the direct result of the microscopic processes near the crack tip or on the frictional interface. Here we show that the dynamic energy balance in earthquakes can be expressed by fault surface morphology, and that they are quantitatively linked. The direct shear experiments proves the predictions of the theoretical discussions, and show that the strain rate has crucial influence on the dynamic energy balance.

physics.geo-ph↗

arXiv2020

Spatial transient behavior in waveguides with lossy impedance boundary conditions

Attenuation in acoustic waveguides with lossy impedance boundary conditions are associated with non-Hermitian and non-normal operators. This subject has been extensively studied in fundamental and engineering research, and it has been traditionally assumed that the attenuation behavior of total sound power can be totally captured by considering the decay of each transverse mode individually. One of the classical tools in this context is the Cremer optimum concept that aims to maximize the attenuation of the least attenuated mode. However, a typical sound field may be a superposition of a large number of transverse modes which are nonorthogonal, and the individual mode attenuation may have little to do with the total sound power attenuation. By using singular value decomposition, we link the least attenuated total sound power to the maximum singular value of the non-normal propagator. The behaviors of the least attenuated total sound power depend only on the lossy boundary conditions and frequency, but are independent of sources. The sound may be almost non-decaying along the waveguide transition region for any lossy impedance boundary conditions although all modes attenuate exponentially. This spatial transient appears particularly strongly if the impedance is close to an exceptional point of the propagator, at which a pair of adjacent modes achieve maximum attenuation predicted by Cremer optimum concept. These results are confirmed using non-modal numerical calculations and a two-by-two toy model.

physics.class-ph↗

arXiv2020

Model-based Learning for Quantitative Susceptibility Mapping

Quantitative susceptibility mapping (QSM) is a magnetic resonance imaging (MRI) technique that estimates magnetic susceptibility of tissue from Larmor frequency offset measurements. The generation of QSM requires solving a challenging ill-posed field-to-source inversion problem. Inaccurate field-to-source inversion often causes large susceptibility estimation errors that appear as streaking artifacts in the QSM, especially in massive hemorrhagic regions. Recently, several deep learning (DL) QSM techniques have been proposed and demonstrated impressive performance. Due to the inherent non-existent ground-truth QSM references, these DL techniques used either calculation of susceptibility through multiple orientation sampling (COSMOS) maps or synthetic data for network training. Therefore, they were constrained by the availability and accuracy of COSMOS maps, or suffered from performance drop when the training and testing domains were different. To address these limitations, we present a model-based DL method, denoted as uQSM. Without accessing to QSM labels, uQSM is trained using the well-established physical model. When evaluating on multi-orientation QSM datasets, uQSM achieves higher levels of quantitative accuracy compared to TKD, TV-FANSI, MEDI, and DIP approaches. When qualitatively evaluated on single-orientation datasets, uQSM outperforms other methods and reconstructed high quality QSM.

physics.med-ph↗

arXiv2020

Weakly-supervised Learning for Single-step Quantitative Susceptibility Mapping

Quantitative susceptibility mapping (QSM) utilizes MRI phase information to estimate tissue magnetic susceptibility. The generation of QSM requires solving ill-posed background field removal (BFR) and field-to-source inversion problems. Because current QSM techniques struggle to generate reliable QSM in clinical contexts, QSM clinical translation is greatly hindered. Recently, deep learning (DL) approaches for QSM reconstruction have shown impressive performance. Due to inherent non-existent ground-truth, these DL techniques use either calculation of susceptibility through multiple orientation sampling (COSMOS) maps or synthetic data for training, which are constrained by the availability and accuracy of COSMOS maps or domain shift when training data and testing data have different domains. To address these limitations, we propose a weakly-supervised single-step QSM reconstruction method, denoted as wTFI, to directly reconstruct QSM from the total field without BFR. wTFI uses the BFR method RESHARP local fields as supervision to perform a multi-task learning of local tissue fields and QSM, and is capable of recovering magnetic susceptibility estimates near the edges of the brain where are eroded in RESHARP and realize whole brain QSM estimation. Quantitative and qualitative evaluation shows that wTFI can generate high-quality local field and susceptibility maps in a variety of neuroimaging contexts.

eess.IV↗