Space Representation Research Articles

Novel CNN-based transformer integrating Boruta algorithm for production prediction modeling and energy saving of industrial processes

Industrial process data collected by sensors have characteristics of high dimensionality, non-linearity and dynamics. Consequently, the selection extraction is regarded as a critical part for reducing the dimension of the data and removing irrelevant variables of constructing the production prediction model of industrial processes. Therefore, a novel production prediction model using the Boruta algorithm integrating the convolutional neural network-based Transformer (BCT) is proposed in this paper. Primarily, the Boruta algorithm maps nonlinear high-dimensional data to a low-dimensional space to select features that are meaningful to the yield of the industrial process. Then, the features are extracted adaptively using a convolutional neural network (CNN), which is encoded based on the transformer layer to learn relevant information about the different representation spaces. Furthermore, a linear layer with highway connections is employed to obtain prediction results. Finally, the BCT method is applied to establish a realistic production prediction model of actual liquefied petroleum gas plants for energy saving. Compared with back propagation neural networks, the radial basis function, the extreme learning machine, and the transformer based on the CNN, the BCT method achieves a state-of-the-art level. Furthermore, the BCT method provides the operation guidance on the actual liquefied petroleum gas (LPG) production process with increasing the LPG yield by 17.21%, which can improve production efficiency and reducing energy consumption.

Temporal information in the anterior cingulate cortex relates to accumulated experiences

Anterior cingulate cortex (ACC) activity is important for operations that require the ability to integrate multiple experiences over time, such as rule learning, cognitive flexibility, working memory, and long-term memory recall. To shed light on this, we analyzed neuronal activity while rats repeated the same behaviors during hour-long sessions to investigate how activity changed over time. We recorded neuronal ensembles as rats performed a decision-free operant task with varying reward likelihoods at three different response ports (n= 5). Neuronal state space analysis revealed that each repetition of a behavior was distinct, with more recent behaviors more similar than those further apart in time. ACC activity was dominated by a slow, gradual change in low-dimensional representations of neural state space aligning with the pace of behavior. Temporal progression, or drift, was apparent on the top principal component for every session and was driven by the accumulation of experiences and not an internal clock. Notably, these signals were consistent across subjects, allowing us to accurately predict trial numbers based on a model trained on data from a different animal. We observed that non-continuous ramping firing rates over extended durations (tens of minutes) drove the low-dimensional ensemble representations. 40% of ACC neurons' firing ramped over a range of trial lengths and combinations of shorter duration ramping neurons created ensembles that tracked longer durations. These findings provide valuable insights into how the ACC, at an ensemble level, conveys temporal information by reflecting the accumulation of experiences over extended periods.

Automatic fault detection in grid-connected photovoltaic systems via variational autoencoder-based monitoring

Anomaly detection is indispensable for ensuring the reliable operation of grid-connected photovoltaic (PV) systems. This study introduces a semi-supervised deep learning approach for fault detection in such systems. The method leverages a variational autoencoder (VAE) to extract features and identify anomalies. By training the VAE on normal operation data, a compact latent space representation is created. Abnormal observations, indicating faults, exhibit distinct feature vectors in this latent space. Multiple anomaly detection algorithms, including Isolation Forest, Epileptic Envelope, Local Outlier Factor, and One-Class SVM, are employed to discern normal and abnormal observations. This semi-supervised approach only requires fault-free data for training, without labeled faults, making it attractive in practice. A publicly available dataset, the Grid-connected PV System Faults (GPVS-Faults) dataset, which includes data from a PV plant operating in both maximum power point tracking (MPPT) and intermediate power point tracking (IPPT) switching modes, is used for evaluation. The proposed approach is assessed across various fault scenarios, such as partial shading, inverter faults, and MPPT/IPPT controller faults in boost converters. The outcomes underscore the effectiveness of VAE-based techniques in accurately identifying these faults, with accuracy rates reaching up to 92.90% for MPPT mode and 92.99% for IPPT mode, thus contributing to the robustness of fault detection in grid-connected PV systems.

Social, Religious, and Economic Interaction Spaces as a Community Representational Space

Social, Religious, and Economic Interaction Spaces as a Community Representational Space

Unleashing the potential of cheminformatic analysis for Mycobacterium tuberculosis inhibitors: Insights into chemical space and structural diversity

Mycobacterium tuberculosis (Mtb) remains a major global health concern, causing millions of infections and deaths annually. Drug-resistant tuberculosis poses significant challenges, necessitating the search for new Mtb inhibitors. In this context, a cheminformatic analysis of the currently available antimycobacterial chemical space can be performed to discover structural diversity and new scaffolds. This study conducts a comprehensive cheminformatic analysis of two datasets containing Mtb inhibitors (Mtbs and Phytochemicals), comparing them with Approved drugs and Nutraceuticals datasets. The analysis includes physicochemical properties, molecular scaffolds, structural fingerprints, and structural similarities. The analysis of physicochemical property distributions revealed that Mtb inhibitors are generally less polar or equally polar compared to approved drugs and have similar flexibility. The visual representation of the property space illustrates that the Mtbs dataset is confined to a narrower area, whereas certain compounds within the Phytochemical dataset broaden the scope of the traditional medicinal space. Scaffold analysis identifies several promising candidates in both the Mtbs and Phytochemical datasets. Additionally, employing SkelSpheres descriptors and rubber band scaling for similarity analysis reveals a limited depiction of the chemical space. The analysis of structural diversity indicates that the compounds in the Mtbs dataset exhibit less structural diversity. These findings underscore the necessity to broaden the chemical space of Mtb-targeting molecules by incorporating representative molecules from diverse scaffolds to effectively tackle the issue of drug resistance.

Molecular sharing and molecular-specific representations for multimodal molecular property prediction

Molecular property prediction plays a crucial role in drug discovery and development. However, traditional experimental measurements and Quantitative Structure-Activity Relationship (QSAR) models are often expensive, time-consuming, and data acquisition is challenging. To overcome these limitations and challenges, this study innovatively proposes a fusion molecular property prediction method called molecular property prediction model (MSSP) to address the non-uniqueness of Simplified Molecular Input Line Entry System (SMILES) string representation and the difficulty of capturing global information in molecular graphs. This method extracts multiple fingerprint features and utilizes graph neural network encoding to map different modalities of molecules into molecular sharing and molecular-specific representation spaces, achieving modal alignment and fusion of molecules by combining molecular invariance and representation specificity. To enhance the interpretability and visualization capabilities of the model, graph attention mechanisms are introduced, enabling the identification and inference of important chemical fragments within molecules. Experimental results on publicly available cell line phenotype and kinase activity datasets demonstrate that MSSP outperforms the current state-of-the-art methods in molecular property prediction. Additionally, MSSP exhibits strong competitiveness across nine benchmark molecular property prediction datasets. Furthermore, in the task of predicting SRC kinase data properties, this study successfully screens promising therapeutic compounds from compound libraries by validating the predictions of the MSSP model and combining them with traditional methods such as molecular docking and molecular dynamics simulations. Multiple potential Lyn inhibitors have been discovered through this approach. The application of MSSP model is helpful to discover new molecules with new drug properties or functions, accelerate the process of drug discovery, save time and resources, and provide important guidance for drug discovery.

Generative AI unlocks PET insights: brain amyloid dynamics and quantification.

Studying the spatiotemporal patterns of amyloid accumulation in the brain over time is crucial in understanding Alzheimer's disease (AD). Positron Emission Tomography (PET) imaging plays a pivotal role because it allows for the visualization and quantification of abnormal amyloid beta (Aβ) load in the living brain, providing a powerful tool for tracking disease progression and evaluating the efficacy of anti-amyloid therapies. Generative artificial intelligence (AI) can learn complex data distributions and generate realistic synthetic images. In this study, we demonstrate for the first time the potential of Generative Adversarial Networks (GANs) to build a low-dimensional representation space that effectively describes brain amyloid load and its dynamics. Using a cohort of 1,259 subjects with AV45 PET images from the Alzheimer's Disease Neuroimaging Initiative (ADNI), we develop a 3D GAN model to project images into a latent representation space and generate back synthetic images. Then, we build a progression model on the representation space based on non-parametric ordinary differential equations to study brain amyloid evolution. We found that global SUVR can be accurately predicted with a linear regression model only from the latent representation space (RMSE = 0.08 ± 0.01). We generated synthetic PET trajectories and illustrated predicted Aβ change in four years compared with actual progression. Generative AI can generate rich representations for statistical prediction and progression modeling and simulate evolution in synthetic patients, providing an invaluable tool for understanding AD, assisting in diagnosis, and designing clinical trials. The aim of this study was to illustrate the huge potential that generative AI has in brain amyloid imaging and to encourage its advancement by providing use cases and ideas for future research tracks.

MCRNet: Underwater image enhancement using multi-color space residual network

The selective attenuation and scattering of light in underwater environments cause color distortion and contrast reduction in underwater images, which can impede the ever-growing demand for underwater robot operations. To address these issues, we propose a Multi-Color space Residual Network (MCRNet) for underwater image enhancement. Our method takes advantage of the unique features of color representation in the RGB, HSV, and Lab color spaces. By utilizing the distinct feature representations of images in different color spaces, we can highlight and fuse the most informative features of the three color spaces. Our approach employs a self-attention mechanism in the multi-color space feature fusion module. Extensive experiments demonstrate that our method achieves satisfactory results in color correction and contrast improvement of underwater images, particularly in severely degraded scenes. Consequently, our method outperforms state-of-the-art methods in both subjective visual comparison and objective evaluation metrics.

Node2vec2rank: Large Scale and Stable Graph Differential Analysis via Multi-Layer Node Embeddings and Ranking.

Computational methods in biology can infer large molecular interaction networks from multiple data sources and at different resolutions, creating unprecedented opportunities to explore the mechanisms driving complex biological phenomena. Networks can be built to represent distinct conditions and compared to uncover graph-level differences-such as when comparing patterns of gene-gene interactions that change between biological states. Given the importance of the graph comparison problem, there is a clear and growing need for robust and scalable methods that can identify meaningful differences. We introduce node2vec2rank (n2v2r), a method for graph differential analysis that ranks nodes according to the disparities of their representations in joint latent embedding spaces. Improving upon previous bag-of-features approaches, we take advantage of recent advances in machine learning and statistics to compare graphs in higher-order structures and in a data-driven manner. Formulated as a multi-layer spectral embedding algorithm, n2v2r is computationally efficient, incorporates stability as a key feature, and can provably identify the correct ranking of differences between graphs in an overall procedure that adheres to veridical data science principles. By better adapting to the data, node2vec2rank clearly outperformed the commonly used node degree in finding complex differences in simulated data. In the real-world applications of breast cancer subtype characterization, analysis of cell cycle in single-cell data, and searching for sex differences in lung adenocarcinoma, node2vec2rank found meaningful biological differences enabling the hypothesis generation for therapeutic candidates. Software and analysis pipelines implementing n2v2r and used for the analyses presented here are publicly available.

“It Might Have a Little to Do with Wish Fulfillment”: The Life-Giving Force of Queer Performance in TTRPG Spaces

In Cruel Optimism, Lauren Berlant asserts that “fantasy [can serve] as a life-sustaining defense against the attritions of ordinary violent history,” which is a statement that holds true for many queer role-players in TTRPG spaces (Berlant 2012, 45). Around the table, these worlds enable players to discover and render their identities legible in social utopian spaces and rehearse their performance for life outside of them. Through engaging with scholarship, autoethnographic writing, and cultural production surrounding TTRPGs, queer identity, avatars, and gender performance, this project asserts that TTRPGs function as safe spaces for becoming, due in part to the ability to create an avatar, or “flexible representational stand-in” for the self, that is queer and embodied through role-play (McMillan, 2015 13). This is achieved through tracking the author’s experience of discovering and forming their queer and trans identity through role-playing various characters and disciplining their function through related interdisciplinary theory across queer, feminist, and role-playing studies. Additionally, through utilizing additional ethnographic accounts and analyzing TTRPG-based media in theatre and actual play spaces, this project further establishes how the emancipatory potential in escapist TTRPG fantasy spaces can ultimately alter queer role-players’ engagement with material reality in a world adversarial to their existence and visibility, especially in light of the past few years.

Exploring Image Representation and Color Spaces in Computer Vision: A Comprehensive Review

This paper presents a comprehensive review of image representation and color spaces in the domain ofcomputer vision. Image representation serves as the foundation of computer vision systems, encompassingtechniques such as pixel-based, vector-based, and feature-based representations. Color spaces provide astandardized framework for encoding color information in digital images, with popular models includingRGB, HSV, Lab, and CMYK. The paper explores fundamental concepts, comparative analysis, practicalapplications, and future directions in image representation and color spaces. Insights gained from the reviewhighlight the significance of these concepts in various computer vision applications, including objectrecognition, image segmentation, and image enhancement. Future research directions include addressingchallenges such as achieving color constancy and developing adaptive color space selection techniques. Byleveraging the findings from this review, researchers and practitioners can advance the state-of-the-art incomputer vision and develop more robust and effective systems for real-world applications.

Comprehensive consensus representation learning for incomplete multiview subspace clustering

Incomplete multiview clustering (IMVC) aims to address clustering problems caused by missing views. While some progress has been made, the current approaches still have some problems. First, the existing IMVC methods excessively rely on the original high-dimensional multiview data, leading to suboptimal results when the data are heavily contaminated. Second, the utilization of high-dimensional data often overlooks the complementarity of and consistency across multiple views. Third, the cluster structure of the input data is not adequately considered, which is detrimental to the resulting clustering performance. To address these problems, we propose a novel method: comprehensive consensus representation learning for incomplete multiview subspace clustering (CLR-IMVC). Specifically, CLR-IMVC assumes that all views are generated from a latent representation space. We model the original incomplete multiple views and the latent space to explore their correlations. Subsequently, we use the latent space to generate complete views and construct a subspace self-representation matrix for each view. Moreover, we innovatively treat the latent representation itself as new a view and likewise extract its self-representation matrix. Furthermore, we construct a third-order tensor by using these self-representation matrices and impose low-rank constraints on the tensor to explore the high-order correlations among the matrices. In addition, a consensus representation learning term is added to explore the consistency information between the views and the latent space, ultimately generating a robust clustering structure. Finally, the proposed method can be effectively solved by the augmented Lagrangian multiplier (ALM). Extensive experiments conducted on diverse datasets demonstrate the effectiveness of CLR-IMVC.

Meta-state–space learning: An identification approach for stochastic dynamical systems

Available methods for identification of stochastic dynamical systems from input–output data generally impose restricting structural assumptions on either the noise structure in the data-generating system or the possible state probability distributions. In this paper, we introduce a novel identification method of such systems, which results in a dynamical model that is able to produce the time-varying output distribution accurately without taking restrictive assumptions on the data-generating process. The method is formulated by first deriving a novel and exact representation of a wide class of nonlinear stochastic systems in a so-called meta-state–space form, where the meta-state can be interpreted as a parameter vector of a state probability function space parameterization. As the resulting representation of the meta-state dynamics is deterministic, we can capture the stochastic system based on a deterministic model, which is highly attractive for identification. The meta-state–space representation often involves unknown and heavily nonlinear functions, hence, we propose an artificial neural network (ANN)-based identification method capable of efficiently learning nonlinear meta-state–space models. We demonstrate that the proposed identification method can obtain models with a log-likelihood close to the theoretical limit even for highly nonlinear, highly stochastic systems.

Mobile Phone Based Indoor Mapping

Abstract. We presented a mobile phone scanning solution that offers a workflow for scanning not only small spaces, where drift can be neglected, but also larger spaces where it becomes a major accuracy issue. The LiDAR and image data is combined to build 3D representations of indoor spaces. The paper does focus on the drift compensation for larger scans on the mobile phone by using AutoTags detections. We show that those can also be used to combine scans from multiple independent scans.

Cyclostationary harmonic product spectrum with its application for rolling bearing fault resonance frequency band adaptive location

Harmonic product spectrum (HPS) is an important tool in bearing fault diagnosis because it can quickly locate the fault resonance frequency band. However, its frequency band division strategy easily leads to over- or under-decomposition. This might cause the decomposed signal to contain too little fault information or too much interference. Although an adaptive HPS based on scale space representation for frequency band division is proposed, its frequency band division is driven by the data characteristics of the signal itself, rather than the fault characteristics in signal. It is difficult to completely separate faults from signals by frequency band division without considering fault characteristics. Therefore, an adaptive frequency band segmentation strategy aiming at fault characteristic, i.e., cyclostationarity, maximization is designed and introduced to improve HPS, thus proposing a new optimal fault resonance band location technique. It can achieve fault resonance band location accurately and resist the influence of various noise interferences.

Comparing receptor binding properties of SARS-CoV-2 and of SARS-CoV virus by using unsupervised machine learning models

This work continues our recent molecular dynamics investigation of the three systems of the human ACE2 receptor interacting with the viral RBDs of SARS-CoV virus and two variants of SARS-CoV-2 viruses. The simulations are extended and analyzed using unsupervised machine learning models to give complementary descriptions of hidden features of the viral binding mechanism. Specifically, the principal component analysis (PCA) and the variational autoencoder (VAE) models are employed, both are classified as dimensionality reduction approaches with different focuses. The results support the molecular dynamics results that the two variants of SARS-CoV-2 bind stronger and more stable to the human ACE2 receptor than SARS-CoV virus does. Moreover, stronger bindings also affect the structure of the human receptor, making it fluctuate more, a sensitive feature which is hard to detect using standard analyses. Unexpectedly, it is found that the VAE model can learn and arrange randomly shuffled protein structures obtained from molecular dynamics in time order in the latent space representation. This result potentially has promising application in computational biomolecules. One could use this VAE model to jump forward in time during a molecular dynamics simulation, and to enhance the sampling of protein configuration space.

„Der Park als Problemraum“. Regieren städtischer Drogenkulturen am Beispiel des Görlitzer Parks

Abstract. The governing of urban drug use and its economies represents a central aspect of urban governmentality and has played an important role in the production and control of public space in numerous cities of the Global North since the 1970s. Urban drug cultures are often the subject of moral panics and urban policing. At the same time, geographical engagement with the spatial dimensions and effects of governing urban drug cultures is surprisingly rare. Using the example of Görlitzer Park in Berlin's Friedrichshain-Kreuzberg district, this paper examines the spatializing discourses and practices of urban drug policies and shows how looking at the governing of illicit drugs provides a productive lens for analysing forms of urban exclusion, marginalization, and normalization. From a geographical perspective, it is particularly interesting to examine how this form of urban governance mobilizes spatial approaches and representations of space, i.e., how urban drug cultures are spatialized in multiple ways.

CAT: A causal graph attention network for trimming heterophilic graphs

The local attention-guided message passing mechanism (LAMP) adopted in graph attention networks (GATs) can adaptively learn the importance of neighboring nodes and perform local aggregation better, thus demonstrating a stronger discrimination ability. However, existing GATs suffer from significant discrimination ability degradations in heterophilic graphs. The reason is that a high proportion of dissimilar neighbors can weaken the self-attention of the central node, resulting in the central node deviating from its similar nodes in the representation space. This type of influence caused by neighboring nodes is referred to as Distraction Effect (DE) in this paper. To estimate and weaken the DE induced by neighboring nodes, we propose a Causal graph Attention network for Trimming heterophilic graphs (CAT). To estimate the DE, since DE is generated through two paths, we adopt the total effect as the metric for estimating DE; To weaken the DE, we identify the neighbors with the highest DE (we call them Distraction Neighbors) and remove them. We adopt three representative GATs as the base model within the proposed CAT framework and conduct experiments on seven heterophilic datasets of three different sizes. Comparative experiments show that CAT can improve the node classification accuracies of all base GAT models. Ablation experiments and visualization further validate the enhanced discrimination ability of CATs. In addition, CAT is a plug-and-play framework and can be introduced to any LAMP-driven GAT because it learns a trimmed graph in the attention-learning stage, instead of modifying the model architecture or globally searching for new neighbors.

Analysis of Gender Discourse Bias and Gender Discrimination in Social Media: A Case Study of the TikTok Platform

In the contemporary landscape of new media, social media platforms, particularly exemplified by TikTok, offer female users accessible and cost-effective means for self-expression and communication. However, this study reveals that such platforms, despite their apparent openness and liberality, have not effectively challenged or changed the persistent and deep-rooted issue of gender discrimination that women face. This research adopts a qualitative content analysis and specifically focuses on the TikTok platform, where female users frequently encounter various forms of gender discourse bias and discrimination. The findings suggest that female users on TikTok often face stigmatization through the internet lexicon and the commodification of physical appearance, reflecting broader societal issues of gender inequality and objectification. Simultaneously, a segment of the female user base on TikTok is actively engaging in challenging and negotiating these entrenched stereotypes, striving to redefine their representation in the digital space. Furthermore, the research highlights how the anonymity of the internet, the media’s role in encoding and perpetuating gender stereotypes, and the consumerist traps set by capitalist market dynamics, collectively contribute to an illusory facade of gender equality. This facade obscures the underlying realities of discourse bias and gender discrimination that persist in the digital realm.

Vertical prism adaptation, but not sound presentation, modulates the visuospatial representation: A manual line-bisection study

The present study aimed at testing whether vertical prism adaptation (PA) can modulate vertical visuospatial representation, assessed with a vertical manual line-bisection (MLB) task (Experiment 1). In a second time, we wanted to investigate the potential influence of sound presentation during such a task. Sound is a spatially valued element that has previously been reported to modify horizontal visuospatial representation. In Experiment 2, we presented either a high pitch, a low pitch, or no sound during the same MLB as in Experiment 1. With this experiment, we also searched for an eventual interaction between the effect of sound presentation and the potential cognitive aftereffects of vertical PA on visual representation.Both Experiments 1 and 2 were constructed with the same design and conducted with two distinct groups of young healthy right-handed participants. First, we assessed the initial sensorimotor state with an open-loop pointing task, and the initial representational state through a vertical MLB (with addition of sound for Experiment 2). Then participants were submitted to a 16-minute PA procedure and were tested again on the open-loop pointing task and the MLB to assess the aftereffects following prism removal.Our results showed sensorimotor aftereffects following both upward and downward PA, in a direction opposed to the optical deviation used. The early aftereffects measured following PA were symmetrical, but at the end of the experiment the residual aftereffects were smaller following downward PA than upward PA. We also provide a new insight on the aftereffects of vertical PA on visuospatial representation, showing that downward PA (but not upward PA) can produce an upward bias on the manual line-bisection task. This is the first proof of such cognitive aftereffects following vertical PA. However, we found no effect of sound presentation on the vertical visual space representation and no interaction between PA and sound presentation.