Latent Information Research Articles

Probing Three-dimensional Magnetic Fields. III. Synchrotron Emission and Machine Learning

Synchrotron observation serves as a tool for studying magnetic fields in the interstellar medium and intracluster medium, yet its ability to unveil three-dimensional (3D) magnetic fields, meaning probing the field’s plane-of-the-sky (POS) orientation, inclination angle relative to the line of sight, and magnetization from one observational data, remains largely underexplored. Inspired by the latest insights into anisotropic magnetohydrodynamic (MHD) turbulence, we found that synchrotron emission’s intensity structures inherently reflect this anisotropy, providing crucial information to aid in 3D magnetic field studies: (i) the structure’s elongation gives the magnetic field’s POS orientation and (ii) the structure’s anisotropy degree and topology reveal the inclination angle and magnetization. Capitalizing on this foundation, we integrate a machine learning approach—convolutional neural network (CNN)—to extract this latent information, thereby facilitating the exploration of 3D magnetic fields. The model is trained on synthetic synchrotron emission maps, derived from 3D MHD turbulence simulations encompassing a range of sub-Alfvénic to super-Alfvénic conditions. We show that the CNN is physically interpretable and the CNN is capable of obtaining the POS orientation, inclination angle, and magnetization. Additionally, we test the CNN against the noise effect and the missing low-spatial frequency. We show that this CNN-based approach maintains a high degree of robustness even when only high-spatial frequencies are maintained. This renders the method particularly suitable for application to interferometric data lacking single-dish measurements. We applied this trained CNN to the synchrotron observations of a diffuse region. The CNN-predicted POS magnetic field orientation shows a statistical agreement with that derived from synchrotron polarization.

Prior cocaine use diminishes encoding of latent information by orbitofrontal, but not medial, prefrontal ensembles.

Maladaptive decision-making is a hallmark of substance use disorders (SUDs), though how drugs of abuse alter neural representations supporting adaptive behavior remains poorly understood. Past studies show that the orbitofrontal (OFC) and prelimbic (PL) cortices are important for decision-making, tracking both task-relevant and latent information. However, previous studies have focused on how drugs of abuse impact the firing rates of individual units. More work at the ensemble level is necessary to accurately characterize potential drug-induced changes. Using single-unit recordings in rats during a multidimensional decision-making task and then applying population- and ensemble-level analyses, we show that prior use of cocaine altered the strength and structure of task-relevant and latent representations in the OFC, changes relatable to suboptimal decision-making in this and perhaps other settings. These data expand our understanding of the neuropathological underpinnings of maladaptive decision-making in SUDs, potentially enabling enhanced future treatment strategies.

A Method for Electrical Stimulus Artifact Removal Exploiting Neural Refractoriness: Validation by Contrasting Cathodic and Anodic Stimulation.

To present a novel method for removing stimulus transient that exploits the absolute refractory period of electrically excitable neural tissues. Electrical stimulation often generates significant signal artifacts that can obscure important physiological signals. Removal of the artifact and understanding latent information from these signals could provide objective measures of circuit engagement, potentially driving advancements in neuromodulation research and therapies. We conducted intracranial physiology studies on five consecutive patients with Parkinson's disease who underwent deep brain stimulation (DBS) surgery as part of their routine care. Monopolar stimuli (either cathodic or anodic) were delivered in pairs through the DBS electrode across a range of inter-stimulus intervals. Recordings from adjacent unused electrode contacts used broadband sampling and precise synchronization to generate a robust template for the stimulus transient during the absolute refractory period. These templates of stimulus transient were then subtracted from recordings at different intervals to extract and analyze the residual neural potentials. After artifact removal, the residual signals exhibited absolute and relative refractory periods with timing indicative of neural activity. Cathodic and anodic DBS pulses generated distinct patterns of local tissue activation, showing phase independence from the prior stimulus. The earliest detectable neural responses occurred at short peak latencies (ranging from 0.19 to 0.38 ms post-stimulus) and were completely or partially obscured by the stimulus artifact prior to removal. Cathodic stimuli produced stronger local tissue responses than anodic stimuli, aligning with clinical observations of lower activation thresholds for cathodic stimulation. However, cathodic and anodic pulses induced artifact patterns that were equivalent but opposite. The proposed artifact removal technique enhances prior approaches by allowing direct measurement of local tissue responses without requirements for stimulus polarity reversal, template scaling, or specialized filters. This approach could be integrated into future neuromodulation systems to visualize stimulus-evoked neural potentials that would otherwise be obscured by stimulus artifacts.

Reliability modeling for perception systems in autonomous vehicles: A recursive event-triggering point process approach

Ensuring the reliability of sensor-fusion-based perception systems is crucial for the safe deployment of autonomous vehicles. Such systems function through a sequence of interconnected stages, where errors in upstream stages may propagate to downstream stages and trigger additional errors. The cross-stage error propagation conceptually exists and makes errors in different stages, not independent, posing model challenges, estimation challenges, and data challenges for reliability modeling. The existing methods cannot be applied to address all these challenges. Thus, this paper presents a recursive event-triggering point process to explicitly consider the error propagation based on the simulated data. The data are simulated from a proposed error injection framework, which can generate various errors from a sequence of interconnected stages in a perception system. The latent and probabilistic error propagation information is incorporated into a modified expectation–maximization (EM) algorithm for parameter estimation. The numerical and physics-based simulation case studies demonstrate the prediction accuracy and interpretability of the proposed modeling methodology.

End‐to‐end speech‐denoising deep neural network based on residual‐attention gated linear units

AbstractIn this letter, an improved gated linear unit (GLU) structure for end‐to‐end (E2E) speech enhancement is proposed. In the U‐Net structure, which is widely used as the foundational architecture for E2E deep neural network‐based speech denoising, the input noisy speech signal undergoes multiple layers of encoding and is compressed into essential potential representative information at the bottleneck. The latent information is then transmitted to the decoder stage for the restoration of the target clean speech. Among these approaches, CleanUNet, a prominent state‐of‐the‐art (SOTA) method, enhances temporal attention in latent space by employing multi‐head self‐attention. However, unlike the approach of applying the attention mechanism to the potentially compressed representative information of the bottleneck layer, the proposed method instead assigns the attention module to the GLU of each encoder/decoder block layer. The proposed method is validated by measuring short‐term objective speech intelligibility and sound quality. The objective evaluation results indicated that the proposed method using residual‐attention GLU outperformed existing methods using SOTA models such as FAIR‐denoiser and CleanUNet across signal‐to‐noise ratios ranging from 0 to 15 dB.

A novel hybrid model for multi-step-ahead forecasting of wind speed based on univariate data feature enhancement

Reliable multistep ahead wind speed forecasting (MAWSF) is critical for the energy management of wind farms and the long-term maintenance of wind power systems. However, relying on inherent meteorological features such as temperature and atmospheric pressure often fails to meet the deep learning model’s feature requirements for accurate wind speed forecasting (WSF). This paper introduces a hybrid multistep forecasting model that constructs a univariate wind speed feature enhancement framework, combining random forest (RF) and Transformer models for WSF. Initially, the hybrid enhancement framework decomposes the univariate wind speed data and extracts time-series features, effectively mining the latent features information. Subsequently, the RF feature selector filters out significant features contributing to WSF and eliminates redundant features to provide stable features data. Finally, Transformer model is utilized for both short-term and long-term MAWSF. This study conducted MAWSF on data with sampling intervals of 20 min, 30 min and 1 h. The results indicate that, compared to existing state-of-the-art models, the hybrid model in MAWSF tasks reduces the dependency of models on inherent meteorological features, achieving more accurate forecasting and faster computation speeds. Ultimately, the proposed model can provide reliable technical support for energy management and maintenance guidance in real-world wind farms.

Exploring nonlinear dynamics in brain functionality through phase portraits and fuzzy recurrence plots.

Much of the complexity and diversity found in nature is driven by nonlinear phenomena, and this holds true for the brain. Nonlinear dynamics theory has been successfully utilized in explaining brain functions from a biophysics standpoint, and the field of statistical physics continues to make substantial progress in understanding brain connectivity and function. This study delves into complex brain functional connectivity using biophysical nonlinear dynamics approaches. We aim to uncover hidden information in high-dimensional and nonlinear neural signals, with the hope of providing a useful tool for analyzing information transitions in functionally complex networks. By utilizing phase portraits and fuzzy recurrence plots, we investigated the latent information in the functional connectivity of complex brain networks. Our numerical experiments, which include synthetic linear dynamics neural time series and a biophysically realistic neural mass model, showed that phase portraits and fuzzy recurrence plots are highly sensitive to changes in neural dynamics and can also be used to predict functional connectivity based on structural connectivity. Furthermore, the results showed that phase trajectories of neuronal activity encode low-dimensional dynamics, and the geometric properties of the limit-cycle attractor formed by the phase portraits can be used to explain the neurodynamics. Additionally, our results showed that the phase portrait and fuzzy recurrence plots can be used as functional connectivity descriptors, and both metrics were able to capture and explain nonlinear dynamics behavior during specific cognitive tasks. In conclusion, our findings suggest that phase portraits and fuzzy recurrence plots could be highly effective as functional connectivity descriptors, providing valuable insights into nonlinear dynamics in the brain.

Multi-view support vector machine classifier via [formula omitted] soft-margin loss with structural information

Multi-view learning seeks to leverage the advantages of various views to complement each other and make full use of the latent information in the data. Nevertheless, effectively exploring and utilizing common and complementary information across diverse views remains challenging. In this paper, we propose two multi-view classifiers: multi-view support vector machine via L0/1 soft-margin loss (MvL0/1-SVM) and structural MvL0/1-SVM (MvSL0/1-SVM). The key difference between them is that MvSL0/1-SVM additionally fuses structural information, which simultaneously satisfies the consensus and complementarity principles. Despite the discrete nature inherent in the L0/1 soft-margin loss, we successfully establish the optimality theory for MvSL0/1-SVM. This includes demonstrating the existence of optimal solutions and elucidating their relationships with P-stationary points. Drawing inspiration from the P-stationary point optimality condition, we design and integrate a working set strategy into the proximal alternating direction method of multipliers. This integration significantly enhances the overall computational speed and diminishes the number of support vectors. Last but not least, numerical experiments show that our suggested models perform exceptionally well and have faster computational speed, affirming the rationality and effectiveness of our methods.

Exploring Nonlinear Dynamics In Brain Functionality Through Phase Portraits And Fuzzy Recurrence Plots.

Much of the complexity and diversity found in nature is driven by nonlinear phenomena, and this holds true for the brain. Nonlinear dynamics theory has been successfully utilized in explaining brain functions from a biophysics standpoint, and the field of statistical physics continues to make substantial progress in understanding brain connectivity and function. This study delves into complex brain functional connectivity using biophysical nonlinear dynamics approaches. We aim to uncover hidden information in high-dimensional and nonlinear neural signals, with the hope of providing a useful tool for analyzing information transitions in functionally complex networks. By utilizing phase portraits and fuzzy recurrence plots, we investigated the latent information in the functional connectivity of complex brain networks. Our numerical experiments, which include synthetic linear dynamics neural time series and a biophysically realistic neural mass model, showed that phase portraits and fuzzy recurrence plots are highly sensitive to changes in neural dynamics and can also be used to predict functional connectivity based on structural connectivity. Furthermore, the results showed that phase trajectories of neuronal activity encode low-dimensional dynamics, and the geometric properties of the limit-cycle attractor formed by the phase portraits can be used to explain the neurodynamics. Additionally, our results showed that the phase portrait and fuzzy recurrence plots can be used as functional connectivity descriptors, and both metrics were able to capture and explain nonlinear dynamics behavior during specific cognitive tasks. In conclusion, our findings suggest that phase portraits and fuzzy recurrence plots could be highly effective as functional connectivity descriptors, providing valuable insights into nonlinear dynamics in the brain.

When latent features meet side information: A preference relation based graph neural network for collaborative filtering

As recommender systems shift from rating-based to interaction-based models, graph neural network-based collaborative filtering models are gaining popularity due to their powerful representation of user-item interactions. However, these models may not produce good item ranking since they focus on explicit preference predictions. Further, these models do not consider side information since they only capture latent feature information of user-item interactions. This study proposes an approach to overcome these two issues by employing preference relation in the graph neural network model for collaborative filtering. Using preference relation ensures the model will generate a good ranking of items. The item side information is integrated into the model through a trainable matrix, which is crucial when the data is highly sparse. The main advantage of this approach is that the model can be generalized to any recommendation scenario where a graph neural network is used for collaborative filtering. Experimental results obtained using the recent RS datasets show that the proposed model outperformed the related baselines.

Block-term tensor decomposition in array signal processing

The ability of tensor decomposition (TD)-based methods to recover latent information, including channel parameters and transmitted symbols in the array signal processing (ASP) context, in a deterministic manner and with little or no training overhead, fits well with the data efficiency needs of future-generation multi-user massive multiple-input multiple-output systems. However, such methods have mostly relied on a few classical TD models, notably the canonical polyadic decomposition (CPD), which can be quite restrictive in realistic scenarios. In this paper, a generalized CPD model, known as block-term decomposition (BTD), is re-visited in the context of ASP, and shown to be the natural choice in sensor arrays of increased dimensionality that also involve channel multipath. Semi-blind joint channel estimation/data detection (JCD) is addressed in this context via efficient algorithms that wed existing JCD schemes with BTD approximation. Robust to sensor failures and recursive versions are also developed. The special yet important case of the uniform rectangular array (URA) configuration is adopted to illustrate the ideas and results. The signal detection performance of the BTD-inspired semi-blind JCD schemes is evaluated under various conditions with the aid of simulations and seen to be favorably compared with that of the training-only-based solution.

Adaptive denoising graph contrastive learning with memory graph attention for recommendation

Graph contrastive learning has emerged as a powerful technique for dealing with graph noise and mining latent information in networks, that has been widely applied in GNN-based collaborative filtering. Traditional graph contrastive learning methods commonly generate multiple augmented views, and then learn node representations by maximizing the consistency between these views. However, on one hand, manual view construction methods necessitate expert knowledge and a trial-and-error process. On the other hand, adaptive view construction methods require decoders which results in increased training costs. To address the aforementioned limitations, in this paper, we propose the Adaptive Denoising Graph Contrastive Learning with Memory Graph Attention for Recommendation (ADGA) framework. Firstly, we introduce the memory graph attention mechanism to capture node attention during multi-hop information aggregation. Then, unlike previous methods that required additional node representations to generate views, ADGA proposes, for the first time, directly using attention to adaptively generate structure-aware contrastive learning views. It reduces the training cost of the model and improves the cross-view consistency of node representations, that offers a new paradigm for adaptive graph contrastive learning. Experimental results on three real-world datasets demonstrate that ADGA achieves state-of-the-art performance in recommendation tasks. The code is available at https://github.com/Andrewsama/ADGA.

Sequential Reservoir Computing for Log File‐Based Behavior Process Data Analyses

AbstractThe use of process data in assessment has gained attention in recent years as more assessments are administered by computers. Process data, recorded in computer log files, capture the sequence of examinees' response activities, for example, timestamped keystrokes, during the assessment. Traditional measurement methods are often inadequate for handling this type of data. In this paper, we proposed a sequential reservoir method (SRM) based on a reservoir computing model using the echo state network, with the particle swarm optimization and singular value decomposition as optimization. Designed to regularize features from process data through a computational self‐learning algorithm, this method has been evaluated using both simulated and empirical data. Simulation results suggested that, on one hand, the model effectively transforms action sequences into standardized and meaningful features, and on the other hand, these features are instrumental in categorizing latent behavioral groups and predicting latent information. Empirical results further indicate that SRM can predict assessment efficiency. The features extracted by SRM have been verified as related to action sequence lengths through the correlation analysis. This proposed method enhances the extraction and accessibility of meaningful information from process data, presenting an alternative to existing process data technologies.

Enhancing visual reinforcement learning with State–Action Representation

Despite the remarkable progress made in visual reinforcement learning (RL) in recent years, sample inefficiency remains a major challenge. Many existing approaches attempt to address this by extracting better representations from raw images using techniques like data augmentation or introducing some auxiliary tasks. However, these methods overlook the environmental dynamic information embedded in the collected transitions, which can be crucial for efficient control. In this paper, we present STAR: State-Action Representation Learning, a simple yet effective approach for visual continuous control. STAR learns a joint state–action representation by modeling the dynamics of the environment in the latent space. By incorporating the learned joint state–action representation into the critic, STAR enhances the value estimation with latent dynamics information. We theoretically show that the value function can still converge to the optima when involving additional representation inputs. On various challenging visual continuous control tasks from DeepMind Control Suite, STAR achieves significant improvements in sample efficiency compared to strong baseline algorithms.

Rational design of fluorescent nanoparticles: From wavelength redshift to increased water solubility for stable and high-resolution imaging of latent fingerprints

Efficient and accurate visual identification of latent fingerprints is crucial in areas such as criminal investigation and information security. Aggregation-induced luminescence (AIE) fluorescent materials are widely used in this field because of their strong fluorescence and easy functionalization. They have attracted significant interest and emerged as a promising area since the introduction of the AIE concept. Here a new water-soluble fluorescent nanoparticle, flu-p-DITPA, through amphiphilic self-assembly with amphiphilic polymers macro-CTA-mPEG2000 (P1) and exhibits typical AIE properties. The core molecule, indo-DITPA, derived from the triphenylamine backbone, was obtained through rational molecular design and theoretical calculations, and the calculated results were confirmed with experimental results. The photophysical properties of indo-DITPA and flu-p-DITPA have been meticulously studied, revealing their remarkable characteristics. Taking advantage of their favorable photophysical properties, good water solubility, and biocompatibility, the researchers have devised a simple yet effective method for visualizing latent fingerprints (LFPs) with high resolution under UV light. This method enables the easy decoding of latent fingerprint information at primary, secondary, and tertiary levels. Importantly, this technique is simple, rapid, and user-friendly, marking a significant step forward in the field of forensic science and fingerprint analysis.

ER-GET: Emotion Recognition Based on Global ECG Trajectory.

In recent years, the recognition of human emotions based on electrocardiogram (ECG) signals has been considered a novel area of study among researchers. Despite the challenge of extracting latent emotion information from ECG signals, existing methods are able to recognize emotions by calculating the heart rate variability (HRV) features. However, such local features have drawbacks, as they do not provide a comprehensive description of ECG signals, leading to suboptimal recognition performance. For the first time, we propose a new strategy to extract hidden emotional information from the global ECG trajectory for emotion recognition. Specifically, a period of ECG signals is decomposed into sub-signals of different frequency bands through ensemble empirical mode decomposition (EEMD), and a series of multi-sequence trajectory graphs is constructed by orthogonally combining these sub-signals to extract latent emotional information. Additionally, to better utilize these graph features, a network has been designed that includes self-supervised graph representation learning and ensemble learning for classification. This approach surpasses recent notable works, achieving outstanding results, with an accuracy of 95.08% in arousal and 95.90% in valence detection. Additionally, this global feature is compared and discussed in relation to HRV features, with the intention of providing inspiration for subsequent research.

Graph Contrastive Learning with Node-Level Accurate Difference

Graph contrastive learning (GCL) has attracted extensive research interest due to its powerful ability to capture latent structural and semantic information of graphs in a self-supervised manner. Existing GCL methods commonly adopt predefined graph augmentations to generate two contrastive views. Subsequently, they design a contrastive pretext task between these views with the goal of maximizing their agreement. These methods assume the augmented graph can fully preserve the semantics of the original. However, typical data augmentation strategies in GCL, such as random edge dropping, may alter the properties of the original graph. As a result, previous GCL methods overlooked graph differences, potentially leading to difficulty distinguishing between graphs that are structurally similar but semantically different. Therefore, we argue that it is necessary to design a method that can quantify the dissimilarity between the original and augmented graphs to more accurately capture the relationships between samples. In this work, we propose a novel graph contrastive learning framework, named Accurate Difference-based Node-Level Graph Contrastive Learning (DNGCL), which helps the model distinguish similar graphs with slight differences by learning node-level differences between graphs. Specifically, we train the model to distinguish between original and augmented nodes via a node discriminator and employ cosine dissimilarity to accurately measure the difference between each node. Furthermore, we employ multiple types of data augmentation commonly used in current GCL methods on the original graph, aiming to learn the differences between nodes under different augmentation strategies and help the model learn richer local information. We conduct extensive experiments on six benchmark datasets and the results show that our DNGCL outperforms most state-of-the-art baselines, which strongly validates the effectiveness of our model.

3D Multimodal Fusion Network with Disease-induced Joint Learning for Early Alzheimer's Disease Diagnosis.

Multimodal neuroimaging provides complementary information critical for accurate early diagnosis of Alzheimer's disease (AD). However, the inherent variability between multimodal neuroimages hinders the effective fusion of multimodal features. Moreover, achieving reliable and interpretable diagnoses in the field of multimodal fusion remains challenging. To address them, we propose a novel multimodal diagnosis network based on multi-fusion and disease-induced learning (MDL-Net) to enhance early AD diagnosis by efficiently fusing multimodal data. Specifically, MDL-Net proposes a multi-fusion joint learning (MJL) module, which effectively fuses multimodal features and enhances the feature representation from global, local, and latent learning perspectives. MJL consists of three modules, global-aware learning (GAL), local-aware learning (LAL), and outer latent-space learning (LSL) modules. GAL via a self-adaptive Transformer (SAT) learns the global relationships among the modalities. LAL constructs local-aware convolution to learn the local associations. LSL module introduces latent information through outer product operation to further enhance feature representation. MDL-Net integrates the disease-induced region-aware learning (DRL) module via gradient weight to enhance interpretability, which iteratively learns weight matrices to identify AD-related brain regions. We conduct the extensive experiments on public datasets and the results confirm the superiority of our proposed method. Our code will be available at: https://github.com/qzf0320/MDL-Net.

Efficient and Effective One-Step Multiview Clustering.

Multiview clustering algorithms have attracted intensive attention and achieved superior performance in various fields recently. Despite the great success of multiview clustering methods in realistic applications, we observe that most of them are difficult to apply to large-scale datasets due to their cubic complexity. Moreover, they usually use a two-stage scheme to obtain the discrete clustering labels, which inevitably causes a suboptimal solution. In light of this, an efficient and effective one-step multiview clustering (E2OMVC) method is proposed to directly obtain clustering indicators with a small-time burden. Specifically, according to the anchor graphs, the smaller similarity graph of each view is constructed, from which the low-dimensional latent features are generated to form the latent partition representation. By introducing a label discretization mechanism, the binary indicator matrix can be directly obtained from the unified partition representation which is formed by fusing all latent partition representations from different views. In addition, by coupling the fusion of all latent information and the clustering task into a joint framework, the two processes can help each other and obtain a better clustering result. Extensive experimental results demonstrate that the proposed method can achieve comparable or better performance than the state-of-the-art methods. The demo code of this work is publicly available at https://github.com/WangJun2023/EEOMVC.

LatLBP: Spatial-spectral latent local binary pattern for hyperspectral image classification

The rich spatial and spectral information brings great potential for pixel-wise classification of hyperspectral image (HSI). Recently, Local Binary Pattern (LBP) as a prominent texture operator has been introduced for discriminative feature extraction of complex volumetric HSI. However, the popular two-dimensional LBP series can only capture spatial structure features and lack pattern descriptions of the spectral domain. The extended three-dimensional LBP series are capable of local multidimensional descriptions, while the information mining for narrow and continuous bands in the spectral domain is still limited. To tackle these issues, we develop a novel local binary pattern named LatLBP for investigating spatial-spectral latent information, which provides a low-dimensional, fine-grained, high-level representation of dual-domain latent semantic information by exploring the group structure of data. LatLBP consists of representative spatial latent (RSLat) LBP encoding and grouped spectral latent (GSLat) LBP encoding, where RSLat describes the local spatial potential features of each grouped representative band, and GSLat characterizes information about each group of latent spectral factors. Besides, a supporting neighborhood band grouping (NBG) algorithm is also designed to provide a finer group structure. Extensive experiments conducted on four HSI datasets indicate that the optimal classification results, i.e., 86.94% for Pavia University, 88.66% for Indian Pines, 77.75% for HanChuan, and 85.54% for HongHu, are achieved by either the proposed LatLBP or GSLat compared to competitive operators.