Rich Information Research Articles

Memory Updating in Dreams

Abstract Robert Stickgold’s research was among the earliest to rigorously quantify the effect of learning on dream content. As a result, we learned that dreaming is influenced by the activation of newly formed memory traces in the sleeping brain. Exactly how this happens is an ongoing area of investigation. Here we test the hypothesis that participants are especially likely to dream of recent experiences which overlap with well-established semantic networks. We created an artificial situation in which participants encountered new information about a person with which they have extensive past experience – a favorite celebrity. We tracked the effect of novel information about a favorite celebrity on participants’ dream content across 3 consecutive nights, and queried participants about other recent and remote memory sources of their dreams. While the celebrity manipulation failed to affect dream content, this dataset provides rich descriptive information about how recent and remote memory fragments are incorporated into dreams, and how multiple memory sources combine to create bizarre, imaginative scenarios. We discuss these observations in light of the proposed “memory updating” function of sleep-dependent memory consolidation, as well as Stickgold and Zadra’s NEXTUP (Network Exploration to Understand Possibilities) model of dreaming. This paper is part of the Festschrift in honor of Dr. Robert Stickgold.

The Pulse of Mood Online: Unveiling Emotional Reactions in a Dynamic Social Media Landscape

The rich and dynamic information environment of social media provides researchers, policymakers, and entrepreneurs with opportunities to learn about social phenomena in a timely manner. However, using these data to understand social behavior is difficult due to heterogeneity of topics and events discussed in the highly dynamic online information environment. To address these challenges, we present a method for systematically detecting and measuring emotional reactions to offline events using change point detection on the time series of collective affect, and further explaining these reactions using a transformer-based topic model. We demonstrate the utility of the method by successfully detecting major and smaller events on three different datasets, including (1) a Los Angeles Tweet dataset between Jan. and Aug. 2020, in which we revealed the complex psychological impact of the BlackLivesMatter movement and the COVID-19 pandemic, (2) a dataset related to abortion rights discussions in USA, in which we uncovered the strong emotional reactions to the overturn of Roe v. Wade and state abortion bans, and (3) a dataset about the 2022 French presidential election, in which we discovered the emotional and moral shift from positive before voting to fear and criticism after voting. We further demonstrate the importance of disaggregating data by topics and populations to mitigate potential biases when studying collective emotions. The capability of our method allows for better sensing and monitoring of population’s reactions during crises using online data.

Spectral graph model for fMRI: A biophysical, connectivity-based generative model for the analysis of frequency-resolved resting-state fMRI

Abstract Resting-state functional MRI (rs-fMRI) is a popular and widely used technique to explore the brain’s functional organization and to examine whether it is altered in neurological or mental disorders. The most common approach for its analysis targets the measurement of the synchronized fluctuations between brain regions, characterized as functional connectivity (FC), typically relying on pairwise correlations in activity across different brain regions. While hugely successful in exploring state- and disease-dependent network alterations, these statistical graph theory tools suffer from two key limitations. First, they discard useful information about the rich frequency content of the fMRI signal. The rich spectral information now achievable from advances in fast multiband acquisitions is consequently being underutilized. Second, the analyzed FCs are phenomenological without a direct neurobiological underpinning in the underlying structures and processes in the brain. There does not currently exist a complete generative model framework for whole brain resting fMRI that is informed by its underlying biological basis in the structural connectome. Here we propose that a different approach can solve both challenges at once: the use of an appropriately realistic yet parsimonious biophysics-informed signal generation model followed by graph spectral (i.e., eigen) decomposition. We call this model a spectral graph model (SGM) for fMRI, using which we can not only quantify the structure–function relationship in individual subjects, but also condense the variable and individual-specific repertoire of fMRI signal’s spectral and spatial features into a small number of biophysically interpretable parameters. We expect this model-based analysis of rs-fMRI that seamlessly integrates with structure can be used to examine state and trait characteristics of structure–function relationships in a variety of brain disorders.

CaLiJD: Camera and LiDAR Joint Contender for 3D Object Detection

Three-dimensional object detection has been a key area of research in recent years because of its rich spatial information and superior performance in addressing occlusion issues. However, the performance of 3D object detection still lags significantly behind that of 2D object detection, owing to challenges such as difficulties in feature extraction and a lack of texture information. To address this issue, this study proposes a 3D object detection network, CaLiJD (Camera and Lidar Joint Contender for 3D object Detection), guided by two-dimensional detection results. CaLiJD creatively integrates advanced channel attention mechanisms with a novel bounding-box filtering method to improve detection accuracy, especially for small and occluded objects. Bounding boxes are detected by the 2D and 3D networks for the same object in the same scene as an associated pair. The detection results that satisfy the criteria are then fed into the fusion layer for training. In this study, a novel fusion network is proposed. It consists of numerous convolutions arranged in both sequential and parallel forms and includes a Grouped Channel Attention Module for extracting interactions among multi-channel information. Moreover, a novel bounding-box filtering mechanism was introduced, incorporating the normalized distance from the object to the radar as a filtering criterion within the process. Experiments were conducted using the KITTI 3D object detection benchmark. The results showed that a substantial improvement in mean Average Precision (mAP) was achieved by CaLiJD compared with the baseline single-modal 3D detection model, with an enhancement of 7.54%. Moreover, the improvement achieved by our method surpasses that of other classical fusion networks by an additional 0.82%. In particular, CaLiJD achieved mAP values of 73.04% and 59.86%, respectively, thus demonstrating state-of-the-art performance for challenging small-object detection tasks such as those involving cyclists and pedestrians.

Research on the approximate equation inversion method for the physical properties parameters of OA media with decoupling of stress and fracture effects

Pre-stack seismic inversion is an effective method for predicting reservoir physical parameters. At the same time, azimuth seismic data is a reliable source of information for predicting underground reservoir elastic parameters, fracture parameters, and interface parameters and has rich underground information. However, it is difficult to determine whether the anisotropy of the reservoir is caused by stress or the original fractures. Therefore, distinguishing the influence of fractures and initial stress in the reservoir from azimuth seismic data is the key to predicting reservoir parameters. Because of the problem of insufficient consideration of the influence of stress and fracture weakness in OA media, based on Born's first-order scattering theory and Bayesian inversion framework, an approximate equation for the reflection coefficient decoupling fracture anisotropy and stress-induced anisotropy was constructed, and a linear inversion method based on the approximate equation was developed, realizing the exploration of methods for predicting fracture weakness and stress action parameters. Model testing and actual work area application have verified the feasibility and practicability of predicting underground medium parameters from seismic response characteristics.

Multi-channel fused vision transformer network for bearing fault diagnosis under different working conditions

Abstract Many of the current fault diagnosis methods rely on time-domain signals. While the richest information are contained in these signals, their complexity poses challenges to network learning and limits the ability to fully characterize them. To address these issues, a novel multi-channel fused vision transformer network (MFVTN) is proposed in this paper. Firstly, the overlapping patch embedding module is introduced to overlap the time-domain map with edge information, preserving the global continuous features of the time-domain map and adding positional encoding for sorting. This integration helps the vision transformer merge detailed features and construct the global mapping. Secondly, multiple dimensional time domain signal features are extracted and fused in parallel, enabling multi-domain fault diagnosis of bearings. In order to enhance the network ability to extract domain-invariant features, an adversarial training strategy combined with Wasserstein distance is utilized. The results demonstrate that the diagnostic accuracy of the proposed MFVTN can reach 98.2%.

Cell Painting: a decade of discovery and innovation in cellular imaging.

Modern quantitative image analysis techniques have enabled high-throughput, high-content imaging experiments. Image-based profiling leverages the rich information in images to identify similarities or differences among biological samples, rather than measuring a few features, as in high-content screening. Here, we review a decade of advancements and applications of Cell Painting, a microscopy-based cell-labeling assay aiming to capture a cell's state, introduced in 2013 to optimize and standardize image-based profiling. Cell Painting's ability to capture cellular responses to various perturbations has expanded owing to improvements in the protocol, adaptations for different perturbations, and enhanced methodologies for feature extraction, quality control, and batch-effect correction. Cell Painting is a versatile tool that has been used in various applications, alone or with other -omics data, to decipher the mechanism of action of a compound, its toxicity profile, and other biological effects. Future advances will likely involve computational and experimental techniques, new publicly available datasets, and integration with other high-content data types.

Enhancing Competitiveness in the Business Sector and its Role in Supporting Economic Development: The Sultanate of Oman as A Model

Due to the remarkable technological development, the world has witnessed great interest in the areas of the business sector and competition between companies and organizations of all types and sizes. Therefore, this has a significant impact on the economic development of countries. The Sultanate of Oman is currently witnessing a huge economic and technological changes that and working to achieve the provisions of Vision 2040, which revolves around developing the local business sector to become the basic base for economic development. Therefore, this research aimed to clarify the role of the business sector in enhancing competitiveness and supporting economic development in the Sultanate of Oman. The researcher will rely on a group of previous studies that discuss and focus on the variables of the study, especially in the Sultanate of Oman. The results of previous studies found that there is a weakness in the ability of the Omani market to seize opportunities that enhance competitiveness due to the government’s control over a number of economic activities available for investment and implementation of local projects. There is also a clear gap in studies that contain the variables of the current research, so our research will be a wealth of information that will benefit other researchers and academics. The current research aims to clarify the role of the business sector in enhancing competitiveness and supporting economic development in the Sultanate of Oman. Therefore, the researcher will rely on a group of previous Arab and foreign studies that discuss the research variables to rely on valuable and rich information that supports our current research.

Abnormal nonlinear features of EEG microstate sequence in obsessive–compulsive disorder

BackgroundAt present, only a few studies have explored electroencephalography (EEG) microstates of patients with obsessive–compulsive disorder (OCD) and the results are inconsistent. Additionally, the nonlinear features of EEG microstate sequences contain rich information about the brain, yet how the nonlinear features of EEG microstate sequences abnormally change in patients with OCD is still unknown.MethodsResting-state EEG data were collected from 48 OCD patients and macheted 48 healthy controls (HC). Subsequently, EEG microstate analysis was used to extract the microstate temporal parameters (duration, occurrence, coverage) and nonlinear features of EEG microstate sequences (sample entropy, Lempel–Ziv complexity, Hurst index). Finally, the temporal parameters and nonlinear features of EEG microstate sequences were sent to three kinds of machine learning models to classify OCD patients.ResultsBoth groups obtained four typical EEG microstate topographies. The duration of microstates A, B, and C in OCD patients decreased significantly, while the occurrence of microstate D increased significantly compared to HC. Sample entropy and Lempel–Ziv complexity of microstate sequences in OCD patients increased significantly, while Hurst index decreased significantly compared to HC. The classification accuracy using the nonlinear features of microstate sequences reached up to 85%, significantly higher than that based on microstate temporal parameter models.ConclusionThis study provides supplementary findings on EEG microstates in OCD patients with a larger sample size. We found that the nonlinear features of EEG microstate sequences in OCD patients can serve as potential electrophysiological biomarkers for distinguishing OCD patients.

Mechanically Twisting-Induced Top-Down Chirality Transfer for Tunable Full-Color Circularly Polarized Luminescent Fibers.

Circularly polarized luminescence (CPL) materials with rich optical information are highly attractive for optical display, information storage, and encryption. Although previous investigations have shown that external force fields can induce CPL activity in nonchiral systems, the unique role of macroscopic external forces in inducing CPL has not been demonstrated at the level of molecule or molecular aggregate. Here, a canonical example of CPL generation by mechanical twisting in an achiral system consisting of a polymer matrix with embedded fluorescent molecules is presented. By carefully adjusting the twisting parameters in time and space, in conjunction with circular dichroism (CD), CPL, and 2D wide-angle X-ray scattering (2D WAXS) studies, a twisting-induced top-down chiral transfer mechanism derived from the molecular-level asymmetric rearrangement of fluorescent units is elucidated within polymers under external torsional forces. This top-down chiral transfer provides a simple, scalable, and versatile mechanical twisting strategy for the fabrication of CPL materials, allowing for fabricating full-color and handedness-tunable CPL fibers, where the macroscopic twist direction determines the CPL handedness. Moreover, the weavability of CPL fibers greatly extend their applications in anti-counterfeit encryption, as demonstrated by using embroidery techniques to design multilevel encryption patterns.

MSDFNet: multi-scale detail feature fusion encoder–decoder network for self-supervised monocular thermal image depth estimation

Abstract Currently available thermal image depth estimation methods are difficult to efficiently extract fine multi-scale feature information from thermal images and suffer from the problem of blurring details at the edges of the estimated depth map. To address these challenges, this paper proposes MSDFNet, a multi-scale detail feature fusion encoder–decoder network, for self-supervised monocular thermal image depth estimation. The model is based on a channel expansion hourglass residual lightweight feature encoder, which can capture rich and fine-grained multi-scale feature information with low computational effort. MSDFNet utilizes a detail feature weight evaluation decoder to fuse cross-scale features and reevaluate the importance of each feature, thereby emphasizing critical edge information at multiple scales. Additionally, MSDFNet incorporates a depth consistency loss function, which provides self-supervised signals for the detailed features of thermal images and improves the optimization of network performance. The method is applied to the ViViD++ and MS2 datasets and achieves state-of-the-art depth estimation performance compared to existing state-of-the-art algorithms. In the Indoor Dark scenario of the ViViD++ dataset, the Abs Rel, Sq Rel, RMSE, and RMSE log error metric values of MSDFNet are reduced by 6.71%, 11.92%, 9.09%, and 5.73%, respectively, while the accuracy metric values δ < 1.25 i , i = 1 , 2 , 3 were improved by 4.18%, 1.13%, and 0.2%, respectively. In addition, MSDFNet proves its excellent generalization ability on the MS2 dataset. The Abs Rel and RMSE error values in the night scene are reduced by 45.6% and 30.09%, respectively, and the accuracy δ < 1.25 i , i = 1 , 3 is improved by 20.95% and 1.33%, respectively. The Abs Rel and RMSE values in the rainy day scenario are reduced by 1.33% and 1.21%, respectively, and the accuracy δ < 1.25 i , i = 1 , 3 is improved by 0.24% and 0.83%, respectively.

Aluminum Product Surface Defect Detection Method Based on Improved CenterNet

In order to realize real‐time detection of aluminum defects during aluminum production, the target detection algorithm needs to be able to run on locally deployed hardware. Convolutional neural networks can effectively extract representative features from high‐dimensional data such as images and videos, and capture spatial information in the data, making it easier to locate aluminum defects. Moreover, running CNN model inference on local hardware has high real‐time performance. Due to the advantages of convolutional neural network in anomaly detection, an improved CenterNet aluminum surface defect detection method was proposed. The algorithm combines common convolution and depthwise separable convolution to design a lightweight convolution module. Then, the Convolutional Block Attention Module is added to the feature extraction network to make the network better capture the rich input feature information of the image. Ultimately, the α‐DIoU loss function is implemented to enhance the precision of bounding box predictions. The experimental findings demonstrate that the proposed algorithm achieves an average detection accuracy (mAP) of 86.02%, which is 5.95% higher than the average detection accuracy of the traditional algorithm, and has a good detection effect on aluminum surface defects. Furthermore, there is an 11.9% reduction in model parameters and a 15.2% decrease in floating‐point computations, which helps to promote the deployment of embedded device platforms. © 2024 Institute of Electrical Engineers of Japan and Wiley Periodicals LLC.

Exploring Named Entity Recognition via MacBERT-BiGRU and Global Pointer with Self-Attention

Named Entity Recognition (NER) is a fundamental task in natural language processing that aims to identify and categorize named entities within unstructured text. In recent years, with the development of deep learning techniques, pre-trained language models have been widely used in NER tasks. However, these models still face limitations in terms of their scalability and adaptability, especially when dealing with complex linguistic phenomena such as nested entities and long-range dependencies. To address these challenges, we propose the MacBERT-BiGRU-Self Attention-Global Pointer (MB-GAP) model, which integrates MacBERT for deep semantic understanding, BiGRU for rich contextual information, self-attention for focusing on relevant parts of the input, and a global pointer mechanism for precise entity boundary detection. By optimizing the number of attention heads and global pointer heads, our model achieves an effective balance between complexity and performance. Extensive experiments on benchmark datasets, including ResumeNER, CLUENER2020, and SCHOLAT-School, demonstrate significant improvements over baseline models.

Multimodal Contrastive Learning for Remote Sensing Image Feature Extraction Based on Relaxed Positive Samples

Traditional multimodal contrastive learning brings text and its corresponding image closer together as a positive pair, where the text typically consists of fixed sentence structures or specific descriptive statements, and the image features are generally global features (with some fine-grained work using local features). Similar to unimodal self-supervised contrastive learning, this approach can be seen as enforcing a strict identity constraint in a multimodal context. However, due to the inherent complexity of remote sensing images, which cannot be easily described in a single sentence, and the fact that remote sensing images contain rich ancillary information beyond just object features, this strict identity constraint may be insufficient. To fully leverage the characteristics of remote sensing images, we propose a multimodal contrastive learning method for remote sensing image feature extraction, based on positive sample tripartite relaxation, where the model is relaxed in three aspects. The first aspect of relaxation involves both the text and image inputs. By introducing learnable parameters in the language and image branches, instead of relying on fixed sentence structures and fixed image features, the network can achieve a more flexible description of remote sensing images in text and extract ancillary information from the image features, thereby relaxing the input constraints. Second relaxation is achieved through multimodal alignment of various features. By aligning semantic information with the corresponding semantic regions in the images, the method allows for the relaxation of local image features under semantic constraints. This approach addresses the issue of selecting image patches in unimodal settings, where there is no semantic constraint. The proposed method for remote sensing image feature extraction has been validated on four datasets. On the PatternNet dataset, it achieved a 91.1% accuracy with just one-shot.

Improving prediction accuracy in agricultural markets through the CIMA-AttGRU model.

In the Chinese futures market, agricultural product futures play a crucial role. While previous studies have primarily relied on historical price data and fundamental financial indicators of agricultural product futures, there is a growing recognition of the value that lies within the vast amounts of textual data generated in the financial domain. Our study specifically focuses on the limitations of existing methods in capturing the complex relationships and rich semantic information embedded in these textual sources. This article designs a CIMA AttGRU (CIMA-AttGRU) model for soybean futures, which is a forecasting method for the agricultural product market. This model uniquely integrates Collective Intrinsic Mode Analysis (CIMA) with an Attention-Gated Recurrent Unit (AttGRU), leveraging the strengths of both techniques to enhance predictive accuracy and adaptability. The rationale behind employing the CIMA-AttGRU model lies in its ability to effectively tackle the inherent challenges of financial market analysis. By incorporating CIMA, the model adeptly filters out market noise, directly addressing the challenge of high volatility. Additionally, with its attention mechanism, the CIMA-AttGRU targets the issue of non-linear patterns by allowing dynamic adjustment to temporal dependencies, offering differential learning capabilities crucial for capturing the nuanced fluctuations in futures prices. Complementing the CIMA and AttGRU, the integration of Class-wise Adversarial Domain Adaptation (CADA) further refines the model's robustness, addressing the critical challenge of domain adaptivity. This aspect is particularly vital for edamame futures, where price determinants can vary significantly over time and across regions. Our empirical results demonstrate a significant improvement in forecasting precision, with the CIMA-AttGRU model achieving a Mean Absolute Error (MAE) reduction of 15% and a Mean Squared Error (MSE) reduction of 20% compared to conventional models. This superior performance, especially in terms of prediction accuracy and handling market fluctuations, highlights the improve of the model compared to existing methods and has made significant explorations in agricultural market forecasting.

CLFNet: a multi-modal data fusion network for traffic sign extraction

Abstract When using image data for signage extraction, poor visibility conditions such as insufficient light, rainy days, and low light intensity are encountered, leading to low accuracy and poor boundary segmentation in vision-based detection methods. To address this problem, we propose a cross-modal latent feature fusion network for signage detection, which obtains rich boundary information by combining images with light detection and ranging depth images, thus compensating for the pseudo-boundary phenomenon that may occur when using a single RGB image segmentation. First, HRNet is utilized as the backbone network to extract the boundary information of the point cloud depth map and RGB image by introducing the boundary extraction module; Second, the sensitivity to the boundary is enhanced by applying the feature aggregation module to deeply fuse the extracted boundary information with the image features; Finally, boundary Intersection over Union (IOU) is introduced as an evaluation index. The results show that the method performs more superiorly compared to the mainstream RGBD network, with an improvement of 5.5% and 6.1% in IOU and boundary IOU, and an accuracy of 98.3% and 96.2%, respectively, relative to the baseline network.

Utilizing Deep Learning for Field-Level Information Extraction from German Real Estate Tax Notices

ABSTRACT Document processing and related tasks such as information extraction represent a large portion of business workloads and therefore offer high potential for efficiency improvements and process automation. Although semistructured documents such as invoices and receipts have been extensively studied, tax notices represent a largely unexplored area due to their information richness and layout complexity. This article presents a study investigating the potential of deep learning-based information extraction for German real estate tax notices. We propose a hybrid approach based on the LayoutLM transformer model that uses textual, positional, and visual information as well as a rule-based information extraction. We show how such a system can be developed and integrated into the business workflow of organizations on the example of a German tax consulting firm. We also discuss the implications and key challenges that organizations face when planning to adopt such technologies. Data Availability: Custom data and code are not publicly available. Relevant public source code is cited in the text. JEL Classifications: M15; M40; M41.

Breaking dimensional barriers in hyperspectral target detection: Atrous convolution with Gramian Angular field representations

Hyperspectral images contain extensive spectral bands with rich spectral information that reflects object properties. Leveraging state-of-the-art deep learning techniques has proven to be effective in hyperspectral target detection. However, compared to two-dimensional matrix data, the one-dimensional nature of spectral sequence limits the information that can be extracted, posing a challenge for deep learning-based hyperspectral target detection methodologies. To address this issue, a novel hyperspectral target detection method employing atrous convolution with gramian angular field representations is proposed in this paper. This approach breaks the barrier between one-dimensional vector and two-dimensional matrix by gramian angular field, transforming the spectral sequences from one-dimensional vectors into two-dimensional matrices, enabling the exploration of multidimensional relationships within spectral band relations through an atrous convolution-based spectral feature extraction network. The proposed model transcends the traditional one-dimensional spectral target detection limitations, offering a new perspective for spectral-based hyperspectral target detection. Experimental results on four real-world hyperspectral datasets demonstrate that the proposed method significantly outperforms existing state-of-the-art methods in detection performance, showcasing its potential for advancing hyperspectral target detection.

Remaining useful life prediction with spatio-temporal graph transform and weakly supervised adversarial network: An application in power components

Remaining useful life (RUL) prediction is crucial in improving the reliability of insulated gate bipolar transistors (IGBTs) and has attracted widespread attention all over the world. Owing to the heterogeneity and complex internal connectivity of the IGBTs, accurate RUL prediction by traditional deep learning (DL) methods remains challenging. Herein, a novel prognostic framework is proposed for their RUL prediction. In brief, the non-smooth spike voltage of IGBTs is transformed into a graph matrix that contains rich correlation information. Then, spatio-temporal fusion graph network (STFGN) is proposed to realize RUL prediction. It contains spatial-scale and temporal-scale extractors, where the former one based on GraphSage can obtain unique IGBTs data structure information, while the latter based on bidirectional long short-term memory (BiLSTM) captures the time-series degradation features of IGBTs. Moreover, the weakly supervised adversarial learning strategy is considered to realize cross-domain prediction using scarce labeled data, which enhance the positive transfer. Four transfer tasks under variable working conditions are considered to prove the proposed method. The experimental results demonstrate that the average SF and RMSE metrics of the proposed method are 0.429 and 0.108, which is superior to other related methods.

Towards Context-Aware Emotion Recognition Debiasing From a Causal Demystification Perspective via De-Confounded Training.

Understanding emotions from diverse contexts has received widespread attention in computer vision communities. The core philosophy of Context-Aware Emotion Recognition (CAER) is to provide valuable semantic cues for recognizing the emotions of target persons by leveraging rich contextual information. Current approaches invariably focus on designing sophisticated structures to extract perceptually critical representations from contexts. Nevertheless, a long-neglected dilemma is that a severe context bias in existing datasets results in an unbalanced distribution of emotional states among different contexts, causing biased visual representation learning. From a causal demystification perspective, the harmful bias is identified as a confounder that misleads existing models to learn spurious correlations based on likelihood estimation, limiting the models' performance. To address the issue, we embrace causal inference to disentangle the models from the impact of such bias, and formulate the causalities among variables in the CAER task via a customized causal graph. Subsequently, we present a Contextual Causal Intervention Module (CCIM) to de-confound the confounder, which is built upon backdoor adjustment theory to facilitate seeking approximate causal effects during model training. As a plug-and-play component, CCIM can easily integrate with existing approaches and bring significant improvements. Systematic experiments on three datasets demonstrate the effectiveness of our CCIM.