Independent Vectors Research Articles

A fronto-insular network underlies individual variations in anger expression and control

Abstract Anger can be deconstructed into distinct components: a tendency to outwardly express it (anger-out) and the capability to manage it (anger control). These aspects exhibit individual differences that vary across a continuum. Notably, the capacity to express and control anger is of great importance to modulate our reactions in interpersonal situations. The aim of this study was to test the hypothesis that anger expression and control are negatively correlated and that both can be decoded by the same patterns of grey and white matter features of a fronto-temporal brain network. To this aim, a data fusion unsupervised machine learning technique, known as transposed Independent Vector Analysis (tIVA), was used to decompose the brain into covarying GM–WM networks and then backward regression was used to predict both anger expression and control from a sample of 212 healthy subjects. Confirming our hypothesis, results showed that anger control and anger expression are negatively correlated, the more individuals control anger, the less they externalize it. At the neural level, individual differences in anger expression and control can be predicted by the same GM–WM network. As expected, this network included lateral and medial frontal regions, the insula, temporal regions, and the precuneus. The higher the concentration of GM–WM in this brain network, the higher the level of externalization of anger, and the lower the anger control. These results expand previous findings regarding the neural bases of anger by showing that individual differences in anger control and expression can be predicted by morphometric features.

All-loop group-theory constraints for four-point amplitudes of SU(N), SO(N), and Sp(N) gauge theories

In the decomposition of gauge-theory amplitudes into kinematic and color factors, the color factors (at a given loop order L) span a proper subspace of the extended trace space (which consists of single and multiple traces of generators of the gauge group, graded by powers of N). Using an iterative process, we systematically construct the L-loop color space of four-point amplitudes of fields in the adjoint representation of SU(N), SO(N), or Sp(N). We define the null space as the orthogonal complement of the color space. For SU(N), we confirm the existence of four independent null vectors (for L ≥ 2) and for SO(N) and Sp(N), we establish the existence of seventeen independent null vectors (for L ≥ 5). Each null vector corresponds to a group-theory constraint on the color-ordered amplitudes of the gauge theory.

Multimodal subspace independent vector analysis effectively captures the latent relationships between brain structure and function.

A key challenge in neuroscience is to understand the structural and functional relationships of the brain from high-dimensional, multimodal neuroimaging data. While conventional multivariate approaches often simplify statistical assumptions and estimate one-dimensional independent sources shared across modalities, the relationships between true latent sources are likely more complex - statistical dependence may exist within and between modalities, and span one or more dimensions. Here we present Multimodal Subspace Independent Vector Analysis (MSIVA), a methodology to capture both joint and unique vector sources from multiple data modalities by defining both cross-modal and unimodal subspaces with variable dimensions. In particular, MSIVA enables flexible estimation of varying-size independent subspaces within modalities and their one-to-one linkage to corresponding sub-spaces across modalities. As we demonstrate, a main benefit of MSIVA is the ability to capture subject-level variability at the voxel level within independent subspaces, contrasting with the rigidity of traditional methods that share the same independent components across subjects. We compared MSIVA to a unimodal initialization baseline and a multimodal initialization baseline, and evaluated all three approaches with five candidate subspace structures on both synthetic and neuroimaging datasets. We show that MSIVA successfully identified the ground-truth subspace structures in multiple synthetic datasets, while the multimodal baseline failed to detect high-dimensional subspaces. We then demonstrate that MSIVA better detected the latent subspace structure in two large multimodal neuroimaging datasets including structural MRI (sMRI) and functional MRI (fMRI), compared with the unimodal baseline. From subsequent subspace-specific canonical correlation analysis, brain-phenotype prediction, and voxelwise brain-age delta analysis, our findings suggest that the estimated sources from MSIVA with optimal subspace structure are strongly associated with various phenotype variables, including age, sex, schizophrenia, lifestyle factors, and cognitive functions. Further, we identified modality- and group-specific brain regions related to multiple phenotype measures such as age (e.g., cerebellum, precentral gyrus, and cingulate gyrus in sMRI; occipital lobe and superior frontal gyrus in fMRI), sex (e.g., cerebellum in sMRI, frontal lobe in fMRI, and precuneus in both sMRI and fMRI), schizophrenia (e.g., cerebellum, temporal pole, and frontal operculum cortex in sMRI; occipital pole, lingual gyrus, and precuneus in fMRI), shedding light on phenotypic and neuropsychiatric biomarkers of linked brain structure and function.

Determination of Velocities of Thread Axis Points When Interacting with a Direct Large Curvature Taking into Account the Deformation in the Contact Zone

The theoretical study of the process of the movement of the thread, which is deformed in the contact zone with the guide, from the point of view of determining the speed, is of great importance for solving a number of specific applied problems. When determining the speed, it was assumed that the start of the Lagrangian and Euler coordinates coincided. Taking into account that the crumpling of the thread in the contact zone occurs at forces much lower than the forces required to stretch the thread, the thread was considered as non-extensible. To determine the law of the distribution of the speed of the points of the thread, an independent vector, which is always connected to the main triangle, was introduced into consideration. The relationship between the vector of total curvature and the vector of absolute angular velocity is obtained. The obtained values of the speed at an arbitrary point of the axis of the thread as a function of the deformation vector, which determines the degree of twisting of the thread in the contact zone. The obtained results can be used to study various technological processes in the sewing, knitting, and textile industries, where the movement of the thread takes place along the guide surface of great curvature.

DOA-informed switching independent vector extraction and beamforming for speech enhancement in underdetermined situations

This paper proposes novel methods for extracting a single Speech signal of Interest (SOI) from a multichannel observed signal in underdetermined situations, i.e., when the observed signal contains more speech signals than microphones. It focuses on extracting the SOI using prior knowledge of the SOI’s Direction of Arrival (DOA). Conventional beamformers (BFs) and Blind Source Separation (BSS) with spatial regularization struggle to suppress interference speech signals in such situations. Although Switching Minimum Power Distortionless Response BF (Sw-MPDR) can handle underdetermined situations using a switching mechanism, its estimation accuracy significantly decreases when it relies on a steering vector determined by the SOI’s DOA. Spatially-Regularized Independent Vector Extraction (SRIVE) can robustly enhance the SOI based solely on its DOA using spatial regularization, but its performance degrades in underdetermined situations. This paper extends these conventional methods to overcome their limitations. First, we introduce a time-varying Gaussian (TVG) source model to Sw-MPDR to effectively enhance the SOI based solely on the DOA. Second, we introduce the switching mechanism to SRIVE to improve its speech enhancement performance in underdetermined situations. These two proposed methods are called Switching weighted MPDR (Sw-wMPDR) and Switching SRIVE (Sw-SRIVE). We experimentally demonstrate that both surpass conventional methods in enhancing the SOI using the DOA in underdetermined situations.

An MLWE-Based Cut-and-Choose Oblivious Transfer Protocol.

The existing lattice-based cut-and-choose oblivious transfer protocol is constructed based on the learning-with-errors (LWE) problem, which generally has the problem of inefficiency. An efficient cut-and-choose oblivious transfer protocol is proposed based on the difficult module-learning-with-errors (MLWE) problem. Compression and decompression techniques are introduced in the LWE-based dual-mode encryption system to improve it to an MLWE-based dual-mode encryption framework, which is applied to the protocol as an intermediate scheme. Subsequently, the security and efficiency of the protocol are analysed, and the security of the protocol can be reduced to the shortest independent vector problem (SIVP) on the lattice, which is resistant to quantum attacks. Since the whole protocol relies on the polynomial ring of elements to perform operations, the efficiency of polynomial modulo multiplication can be improved by using fast Fourier transform (FFT). Finally, this paper compares the protocol with an LWE-based protocol in terms of computational and communication complexities. The analysis results show that the protocol reduces the computation and communication overheads by at least a factor of n while maintaining the optimal number of communication rounds under malicious adversary attacks.

A New Method for Constructing Self-Dual Codes over Finite Commutative Rings with Characteristic 2

In this work, we present a new method for constructing self-dual codes over finite commutative rings R with characteristic 2. Our method involves searching for k×2k matrices M over R satisfying the conditions that its rows are linearly independent over R and MM⊤=α⊤α for an R-linearly independent vector α∈Rk. Let C be a linear code generated by such a matrix M. We prove that the dual code C⊥ of C is also a free linear code with dimension k, as well as C/Hull(C) and C⊥/Hull(C) are one-dimensional free R-modules, where Hull(C) represents the hull of C. Based on these facts, an isometry from Rx+Ry onto R2 is established, assuming that x+Hull(C) and y+Hull(C) are bases for C/Hull(C) and C⊥/Hull(C) over R, respectively. By utilizing this isometry, we introduce a new method for constructing self-dual codes from self-dual codes of length 2 over finite commutative rings with characteristic 2. To determine whether the matrix MM⊤ takes the form of α⊤α with α being a linearly independent vector in Rk, a necessary and sufficient condition is provided. Our method differs from the conventional approach, which requires the matrix M to satisfy MM⊤=0. The main advantage of our method is the ability to construct nonfree self-dual codes over finite commutative rings, a task that is typically unachievable using the conventional approach. Therefore, by combining our method with the conventional approach and selecting an appropriate matrix construction, it is possible to produce more self-dual codes, in contrast to using solely the conventional approach.

Independent Vector Analysis for Feature Extraction in Motor Imagery Classification.

Independent vector analysis (IVA) can be viewed as an extension of independent component analysis (ICA) to multiple datasets. It exploits the statistical dependency between different datasets through mutual information. In the context of motor imagery classification based on electroencephalogram (EEG) signals for the brain-computer interface (BCI), several methods have been proposed to extract features efficiently, mainly based on common spatial patterns, filter banks, and deep learning. However, most methods use only one dataset at a time, which may not be sufficient for dealing with a multi-source retrieving problem in certain scenarios. From this perspective, this paper proposes an original approach for feature extraction through multiple datasets based on IVA to improve the classification of EEG-based motor imagery movements. The IVA components were used as features to classify imagined movements using consolidated classifiers (support vector machines and K-nearest neighbors) and deep classifiers (EEGNet and EEGInception). The results show an interesting performance concerning the clustering of MI-based BCI patients, and the proposed method reached an average accuracy of 86.7%.

Generalized collaborative relevance vector regression for soft sensors

Soft sensors often struggle to adapt to changing conditions due to their overreliance on single data sources, severely undermining the generalizability and applicability of models. This paper proposes a novel generalized collaborative relevance vector regression (GCRVR) framework to substantially improve the accuracy and adaptability of soft sensors under varying conditions. The core innovation of GCRVR lies in an adaptive collaborative strategy designed to combine complementary predictive distributions based on analyzed variance differences, enabling the acquisition of more reasonable and reliable results. The GCRVR approach leverages both smoothed and unsmoothed process data to train independent relevance vector regression models, generating probabilistic predictions. A theoretical analysis provides insight into ensuring the stability of the model. In an evaluation conducted across four sophisticated industrial processes, the proposed GCRVR method outperformed a suite of conventional methods—namely, linear regression, support vector regression, Gaussian process regression, a stacked autoencoder, long short-term memory, attention-based long short-term memory, and extreme gradient boosting. The GCRVR method exhibited substantial predictive accuracy enhancements, as evidenced by average reductions of 39% in the root mean square error (RMSE), 43% in the mean absolute error (MAE), and 42% in the mean absolute percentage error (MAPE). This work addresses the generalization and adaptability limitations of soft sensors through an integrated framework that capitalizes on the collaborative use of complementary models. GCRVR constitutes a major advancement in real-time monitoring and optimization for industrial process control.

MIGP: Metapath Integrated Graph Prompt Neural Network

Graph neural networks (GNNs) leveraging metapaths have garnered extensive utilization. Nevertheless, the escalating parameters and data corpus within graph pre-training models incur mounting training costs. Consequently, GNN models encounter hurdles including diminished generalization capacity and compromised performance amidst small sample datasets. Drawing inspiration from the efficacy demonstrated by self-supervised learning methodologies in natural language processing, we embark on an exploration. We endeavor to imbue graph data with augmentable, learnable prompt vectors targeting node representation enhancement to foster superior adaptability to downstream tasks. This paper proposes a novel approach, the Metapath Integrated Graph Prompt Neural Network (MIGP), which leverages learnable prompt vectors to enhance node representations within a pretrained model framework. By leveraging learnable prompt vectors, MIGP aims to address the limitations posed by mall sample datasets and improve GNNs’ model generalization. In the pretraining stage, we split symmetric metapaths in heterogeneous graphs into short metapaths and explicitly propagate information along the metapaths to update node representations. In the prompt-tuning stage, the parameters of the pretrained model are fixed, a set of independent basis vectors is introduced, and an attention mechanism is employed to generate task-specific learnable prompt vectors for each node. Another notable contribution of our work is the introduction of three patent datasets, which is a pioneering application in related fields. We will make these three patent datasets publicly available to facilitate further research on large-scale patent data analysis. Through comprehensive experiments conducted on three patent datasets and three other public datasets, i.e., ACM, IMDB, and DBLP, we demonstrate the superior performance of the MIGP model in enhancing model applicability and performance across a variety of downstream datasets. The source code and datasets are available in the website.11https://github.com/hzw-ai/MIGP, with password: MIGPNN2024.

On the probability of a Pareto record

Abstract Given a sequence of independent random vectors taking values in ${\mathbb R}^d$ and having common continuous distribution function F, say that the $n^{\rm \scriptsize}$ th observation sets a (Pareto) record if it is not dominated (in every coordinate) by any preceding observation. Let $p_n(F) \equiv p_{n, d}(F)$ denote the probability that the $n^{\rm \scriptsize}$ th observation sets a record. There are many interesting questions to address concerning pn and multivariate records more generally, but this short paper focuses on how pn varies with F, particularly if, under F, the coordinates exhibit negative dependence or positive dependence (rather than independence, a more-studied case). We introduce new notions of negative and positive dependence ideally suited for such a study, called negative record-setting probability dependence (NRPD) and positive record-setting probability dependence (PRPD), relate these notions to existing notions of dependence, and for fixed $d \geq 2$ and $n \geq 1$ prove that the image of the mapping pn on the domain of NRPD (respectively, PRPD) distributions is $[p^*_n, 1]$ (resp., $[n^{-1}, p^*_n]$ ), where $p^*_n$ is the record-setting probability for any continuous F governing independent coordinates.

Exploring large language model for generic and robust state-of-charge estimation of Li-ion batteries: A mixed prompt learning method

State-of-charge (SOC) estimation is important to ensure safe functioning of Li-ion batteries (LIBs). However, distinct measurements, harsh temperatures, and dynamic operations pose challenges in estimating intricate SOC changes of multiple LIBs with one estimator. Hence, this paper proposes a novel mixed prompt learning method to explore a large-scale pretrained language model (PLM) for SOC estimation. A new hard prompt generator is proposed to translate LIB data into instruction and answer text, eliciting the inherent representational capability of PLM to jointly learn the sequential patterns and contextual semantics of measurements through language modeling for accurate SOC estimation. A new soft prompt adapter is proposed to encode task-specific information of different LIBs into a small set of independent vectors, ensuring PLM adaptation with minimal parameters while maintaining good generalization. By integrating soft prompt vectors along the forward propagation, the hidden states of PLM are dynamically regulated to characterize volatile and variable SOC for robust estimation. Extensive experiments show that by leveraging mixed hard-soft prompts, PLM can make accurate, generic, and robust estimates for multiple LIBs simultaneously in subzero temperature, charge-pause-discharge, and low-capacity discharge scenarios, with the average MAE, RMSE, and MAX of all tasks as low as 1.20 %, 1.51 %, and 5.29 %, respectively.

Anonymizing medical case-based explanations through disentanglement

Case-based explanations are an intuitive method to gain insight into the decision-making process of deep learning models in clinical contexts. However, medical images cannot be shared as explanations due to privacy concerns. To address this problem, we propose a novel method for disentangling identity and medical characteristics of images and apply it to anonymize medical images. The disentanglement mechanism replaces some feature vectors in an image while ensuring that the remaining features are preserved, obtaining independent feature vectors that encode the images’ identity and medical characteristics. We also propose a model to manufacture synthetic privacy-preserving identities to replace the original image’s identity and achieve anonymization. The models are applied to medical and biometric datasets, demonstrating their capacity to generate realistic-looking anonymized images that preserve their original medical content. Additionally, the experiments show the network’s inherent capacity to generate counterfactual images through the replacement of medical features.

A novel hybrid ICA-SVM method for detection and identification of shift in multivariate processes

Detecting shifts in the mean vector of a multivariate statistical process control is crucial, and equally important is identifying the source of such a signal. This study introduces a novel approach that combines independent components analysis with support vector machines to address the challenge of multivariate process monitoring. In this hybrid independent components analysis-support vector machines method, statistical metrics $I^2$ derived from the independent components extracted through independent components analysis from observed data serve as input variables for the support vector machines. The probabilistic outputs generated by the support vector machines model are utilized as monitoring statistics for the proposed control chart, referred to as $I^2-\text{PoC}$. Simulation results validate the effectiveness of the independent components analysis with support vector machines approach in both detecting and identifying shifts in multivariate control processes, whether they follow a normal or non-normal distribution. Furthermore, the results demonstrate the robustness of this method in handling various challenges, including complex relationships between process variables, shifts of varying sizes, and different distribution shapes, when compared to existing approaches in the literature.

Optimization heart disease prediction using independent component analysis and support vector machine

Prediction models play a crucial role in early detection and intervention for cardiac diseases. However, their effectiveness is often hindered by limitations inherent in current methodologies. This paper proposes a novel approach to address these challenges by integrating Independent Component Analysis (ICA) with the Support Vector Machine (SVM) technique. Utilizing a comprehensive Cleveland dataset, our model achieves notable performance metrics, including an accuracy of 90.16%, an Area Under the Curve (AUC) of 96.66%, precision of 90.02%, recall of 90.00%, F1-score of 90.00%, and a minimal log loss of 3.54. Our methodology not only surpasses previous methodologies through extensive comparative analysis but also addresses common constraints identified in existing literature. These limitations encompass insufficient feature representation, overfitting, and a lack of proactive intervention strategies. By amalgamating ICA with SVM, our model enhances feature extraction, mitigates overfitting, and facilitates proactive diagnosis and intervention in individuals suspected of having heart disease. This study underscores the importance of mitigating current literature limitations and underscores the potential of integrating contemporary machine-learning techniques to advance prediction models for heart disease.

ConvTKG: A query-aware convolutional neural network-based embedding model for temporal knowledge graph completion

Temporal knowledge graphs (TKGs) are still far from completeness although they have benefited many artificial intelligence applications successfully. To alleviate the incompleteness of TKGs, temporal knowledge graph completion (TKGC) aims to perform link prediction and reason new time-sensitive facts from existing facts. Among the various TKGC methods, temporal knowledge graph embedding (TKGE) methods represent entities, relations, and timestamps in low-dimensional spaces, which are known for their high reasoning performance and robust scalability. Some previous researches on TKGE aim to endow the embedding quadruple with the translational characteristic by modeling the global relationship in the embedding quadruple. However, the weights of same dimensional entries of the embedding quadruple are fixed and unique, which limits the ability to capture diverse global relationships. Besides, most TKGE models view timestamps as a kind of general feature and overlook their interrelations and correlations with the queries. Moreover, the distinct characteristics of an entity as the subject entity and the object entity of facts have not been fully leveraged. In this paper, we propose a query-aware embedding model based on the convolutional neural network (CNN) named ConvTKG to perform TKGE, thus tackling the TKGC task. We design a new temporal information encoder based on the Gated Recurrent Unit (GRU) and attention mechanism to learn the query-aware representation of temporal information. More importantly, we utilize a CNN-based decoder where multiple one-dimensional convolution kernels are operated on the matrix composed of entity embedding, relation embedding, and temporal representation to capture global relationships among them. In addition, we assign two independent vectors for each entity and take advantage of the inverse relation to allow them to be learned dependently. Experiments show that ConvTKG achieves better link prediction performance than previous state-of-the-art baseline methods for TKGC on three benchmark datasets: ICEWS14, ICEWS05-15, and GDELT.

On the Equivalence of Linear Discriminant Analysis and Least Squares Regression.

Studying the relationship between linear discriminant analysis (LDA) and least squares regression (LSR) is of great theoretical and practical significance. It is well-known that the two-class LDA is equivalent to an LSR problem, and directly casting multiclass LDA as an LSR problem, however, becomes more challenging. Recent study reveals that the equivalence between multiclass LDA and LSR can be established based on a special class indicator matrix, but under a mild condition which may not hold under the scenarios with low-dimensional or oversampled data. In this article, we show that the equivalence between multiclass LDA and LSR can be established based on arbitrary linearly independent class indicator vectors and without any condition. In addition, we show that LDA is also equivalent to a constrained LSR based on the data-dependent indicator vectors. It can be concluded that under exactly the same mild condition, such two regressions are both equivalent to the null space LDA method. Illuminated by the equivalence of LDA and LSR, we propose a direct LDA classifier to replace the conventional framework of LDA plus extra classifier. Extensive experiments well validate the above theoretic analysis.

Novel approach for ECG separation using adaptive constrained IVABMGGMM

In this paper, we introduce the constrained independent vector analysis integrated with the bounded multivariate generalized Gaussian mixture model (cIVABMGGMM) to tackle the limitations of independent component analysis (ICA) when applied to multivariate data, accompanied by its adaptive version, the acIVABMGGMM, aimed at alleviating associated constraints. The acIVABMGGMM employs a full covariance matrix that considers feature correlations, effectively addressing the challenges posed by ICA and independent vector analysis (IVA) models when analyzing multivariate data. The innovative acIVABMGGMM framework merges the adaptability inherent in data-driven methods with the capability to manage noise and other artifacts often encountered in model-based approaches. This technique effectively employs prior knowledge to guide the solution, avoiding the imposition of inaccurate constraints. To overcome these challenges, our set of two constrained methods incorporates prior source information into the IVA model, effectively mitigating its limitations in data with a high number of sources. We assess the efficacy of our proposed models through three distinct ECG separation experiments, which include heartbeat separation, fetal ECG extraction, and arrhythmia detection. Notably, the performance metrics demonstrate the superiority of our models over the baseline approaches in the conducted experiments.

A deep targeted transfer network with clustering pseudo-label learning for fault diagnosis across different Machines

In recent years, deep transfer models have addressed the issue of distribution shift between the source and target domains by learning domain-invariant features. However, in cross-machine fault diagnosis scenarios, existing deep learning models struggle to fit the conditional distribution of target domain samples, limiting the performance and generalization of domain adaptation models. To address these problems, we propose a deep targeted transfer network with clustering pseudo-label learning (DTTN-CPLL). DTTN-CPLL consists of three parts. First, a deep transfer network is constructed to extract cross-domain features. To reduce the intra-class distribution gap, a clustering pseudo-label learning algorithm is proposed to create subdomain labels within the target domain features. Then, we simultaneously minimize and maximize the entropy of features and the number of linearly independent vectors in the target domain to reduce the distance between subdomain features. Finally, under the constraint of local maximum mean discrepancy, we reduce the distribution discrepancy between the source and target domains at the subdomain feature level. We conducted 12 cross-machine transfer tasks on three open bearing datasets and a private high-speed train traction motor bearing dataset. The results demonstrate that, compared to other state-of-the-art models, DTTN-CPLL is effective and superior in cross-machine fault diagnosis.

On the von Bahr–Esseen inequality for pairwise independent random vectors in Hilbert spaces with applications to mean convergence

Abstract In this correspondence, we prove the von Bahr–Esseen moment inequality for pairwise independent random vectors in Hilbert spaces. Our constant in the von Bahr–Esseen moment inequality is better than that obtained for the real-valued random variables by Chen et al. [The von Bahr–Esseen moment inequality for pairwise independent random variables and applications, J. Math. Anal. Appl. 419 (2014), 1290–1302], and Chen and Sung [Generalized Marcinkiewicz–Zygmund type inequalities for random variables and applications, J. Math. Inequal. 10(3) (2016), 837–848]. The result is then applied to obtain mean convergence theorems for triangular arrays of rowwise and pairwise independent random vectors in Hilbert spaces. Some results in the literature are extended.