Spatial Vector Research Articles

A simple approach to rotationally invariant machine learning of a vector quantity.

Unlike with the energy, which is a scalar property, machine learning (ML) prediction of vector or tensor properties poses the additional challenge of achieving proper invariance (covariance) with respect to molecular rotation. For the energy gradients needed in molecular dynamics (MD), this symmetry is automatically fulfilled when taking analytic derivative of the energy, which is a scalar invariant (using properly invariant molecular descriptors). However, if the properties cannot be obtained by differentiation, other appropriate methods should be applied to retain the covariance. Several approaches have been suggested to properly treat this issue. For nonadiabatic couplings and polarizabilities, for example, it was possible to construct virtual quantities from which the above tensorial properties are obtained by differentiation and thus guarantee the covariance. Another possible solution is to build the rotational equivariance into the design of a neural network employed in the model. Here, we propose a simpler alternative technique, which does not require construction of auxiliary properties or application of special equivariant ML techniques. We suggest a three-step approach, using the molecular tensor of inertia. In the first step, the molecule is rotated using the eigenvectors of this tensor to its principal axes. In the second step, the ML procedure predicts the vector property relative to this orientation, based on a training set where all vector properties were in this same coordinate system. As the third step, it remains to transform the ML estimate of the vector property back to the original orientation. This rotate-predict-rotate (RPR) procedure should thus guarantee proper covariance of a vector property and is trivially extensible also to tensors such as polarizability. The RPR procedure has an advantage that the accurate models can be trained very fast for thousands of molecular configurations, which might be beneficial where many training sets are required (e.g., in active learning). We have implemented the RPR technique, using the MLatom and Newton-X programs for ML and MD, and performed its assessment on the dipole moment along MD trajectories of 1,2-dichloroethane.

State geometric adjustability for interval max‐plus linear systems

AbstractThis article investigates the state geometric adjustability for interval max‐plus linear systems, which means that the state vector sequence is transformed into a geometric vector sequence by using the state feedback control. It is pointed out that the geometric state vector sequence and its common ratio are closely related to the eigenvectors and eigenvalues of the special interval state matrix, respectively. Such an interval state matrix is determined by the eigen‐robust interval matrix, which has a universal eigenvector relative to a universal eigenvalue. The state geometric adjustability is characterized by the solvability of interval max‐plus linear equations, and a necessary and sufficient condition for the adjustability is given. A polynomial algorithm is provided to find the state feedback matrix. Several numerical examples and simulations are presented to demonstrate the results. At the same time, the proposed method is applied for the regulation of battery energy storage systems to optimize the start time of executing tasks for all processing units in each activity.

IMPLEMENTATION OF VECTOR MODULATION APPLIED TO THE THREE-PHASE DC-AC CONVERTER VSI USING A FOUR-STATE SWITCHING CELL

This article presents the implementation of spatial vector modulation applied to the three-phase VSI converter with four-state switching cell. The methodology used is shown in detail, indicating the vectors used, the applied switching sequence and the calculations of the vector activation times. It also contains the results of the converter operation in simulation, showing the main waveforms. The following presents the results obtained by experimentation with the assembled prototype.

VIEPred: Predicting Viral Immune Evasion with Multimodal Representation Learning

Abstract Predicting coronaviral immune evasion is crucial for identifying and responding to new COVID-19 variants in advance, thereby optimizing vaccine development and public health strategies to prevent further outbreaks. Hence, we present VIEPred, a model designed to predict mutations in every amino acid of the RBD. However, protein representation learning is a challenge task due to the hierarchical structure of proteins. Our method uses a sequence encoder based on dilated convolutions and attention mechanisms to generate sequence embeddings and a structure encoder employing geometric vector perceptrons (GVP) and graph neural networks (GNN) to produce protein structure representations. These features are combined using a cross-attention fusion module and subsequently processed through a fully connected layer to output the probability of viral immune evasion. Extensive ablation studies led to an optimal model with ACC of 88.4% and AUC of 86.8%. Compared to existing prediction methods, VIEPred demonstrates superior predictive performance across most evaluation metrics for both SARS-CoV-2 and influenza viruses.

Prognostic significance of global electrical heterogeneity (GEH) parameters between coronary microvascular dysfunction (CMD) and obstructive coronary artery disease (OCAD): a retrospective cohort study

BackgroundBoth coronary microvascular dysfunction (CMD) and obstructive coronary artery disease (OCAD) cause myocardial ischemia, making accurate diagnosis of CMD an unmet challenge. AimWe investigate whether electrocardiogram (ECG)-constructed global electrical heterogeneity (GEH) can differentiate CMD and OCAD. MethodsThis retrospective study comprised 74 OCAD and 77 CMD patients with their clinical characteristics and ECGs. QRS onset and offset, R-peak, and T-wave offset were marked on vector-magnitude (VM) derived from ECG-constructed time-coherent global XYZ median beats. 22 GEH parameters (i.e., QT Interval, area and peak QRS-T angles, the area under curve of QT interval on VM (AUC_QT_VM), the direction (azimuth and elevation) and magnitudes of the spatial peak and area vectors for QRS, T, and spatial ventricular gradient (SVG) were calculated and tested using logistic regression analyses to identify significant predictors. ResultsSix GEH parameters (i.e., QT Interval, Peak QRS Azimuth, Area QRS Azimuth, Area T Elevation, Area T, and Area SVG Elevation) were identified as significant predictors. After multivariable adjustment, AUC_QT_VM (odds ratio (OR) = 0.979, [95 % confidence interval (CI) 0.964–0.995], P = 0.009), Area SVG Elevation (OR = 0.978, [95 % CI 0.959–0.998], P = 0.031), and QT Interval (OR = 1.014, [95 % CI 1.000–1.024], P = 0.010) were selected, with the area under curve (AUC) of 0.717 ([95 % CI 0.636–0.798], P < 0.0001) and accuracy of 0.645 on the training dataset and accuracy of 0.608 on the validation dataset. ConclusionsArea SVG Elevation and QT Interval could differentiate CMD and OCAD, indicating that our proposed GEH-based method may offer a new possibility and pathway for non-invasive detection of CMD.

GGN-GO: geometric graph networks for predicting protein function by multi-scale structure features.

Recent advances in high-throughput sequencing have led to an explosion of genomic and transcriptomic data, offering a wealth of protein sequence information. However, the functions of most proteins remain unannotated. Traditional experimental methods for annotation of protein functions are costly and time-consuming. Current deep learning methods typically rely on Graph Convolutional Networks to propagate features between protein residues. However, these methods fail to capture fine atomic-level geometric structural features and cannot directly compute or propagate structural features (such as distances, directions, and angles) when transmitting features, often simplifying them to scalars. Additionally, difficulties in capturing long-range dependencies limit the model's ability to identify key nodes (residues). To address these challenges, we propose a geometric graph network (GGN-GO) for predicting protein function that enriches feature extraction by capturing multi-scale geometric structural features at the atomic and residue levels. We use a geometric vector perceptron to convert these features into vector representations and aggregate them with node features for better understanding and propagation in the network. Moreover, we introduce a graph attention pooling layer captures key node information by adaptively aggregating local functional motifs, while contrastive learning enhances graph representation discriminability through random noise and different views. The experimental results show that GGN-GO outperforms six comparative methods in tasks with the most labels for both experimentally validated and predicted protein structures. Furthermore, GGN-GO identifies functional residues corresponding to those experimentally confirmed, showcasing its interpretability and the ability to pinpoint key protein regions. The code and data are available at: https://github.com/MiJia-ID/GGN-GO.

Super Magnetic Induction : Therapeutic Efficacy in Osteoarticular Pathologies

In order to talk about super magnetic induction, I think it is appropriate to refer to what magnetic fields are. As already intuited by Faraday, electricity is a vector quantity. Bohr then proposes an ideal model of an atom with a central nucleus and the electrons arranged on orbits that continuously revolve around it. Because of this motion the electron becomes charged creating an electric force, the electric field.

High accuracy patient-specific 3D coronary reconstruction from angiography and intravascular optical coherence tomography.

The integration of digital subtraction angiography (DSA) with intravascular optical coherence tomography (IVOCT) offers a comprehensive 3D arterial model, which is invaluable for the analysis of vascular anatomy and biomechanics. However, the process of image fusion is often hindered by the challenge of accurately orienting IVOCT images. This paper introduces a novel, to our knowledge, dual-path 3D reconstruction method that leverages the guidewire and the vessel's centerline to establish cross sectional direction vectors within the IVOCT images and spatial direction vectors along the guidewire's trajectory. This approach minimizes the accumulation of reconstruction errors by ensuring the precise orientation of each vascular cross section. The efficacy of the proposed method is validated through vascular phantom experiments and the reconstruction of patient-specific 3D coronary models.

Design transformations in monuments and memorials as monumental buildings: new perspectives on the place-making model

The monument, or the memorial, as a place of memory and emotional support, has been the focus of scholarly attention. Although existing studies have explored its space’s materialization, identity, history, and memory content, the materials about its design transformation have yet to be deeply excavated. Based on the relevant theories of place and place-making, the researchers constructed a knowledge system of the place-making model, the spatial vector pattern, and the worship behaviors of monuments. On this basis, a qualitative research methodology is adopted. Through case studies and participant observation, the design transformation of the monument/memorial is interpreted in the following five dimensions: function theme, morphology style, spatial relationship, visitor experience, and symbolic meaning. The results of this study show that the monument/memorial tends to promote in-depth public reflection and critical engagement with history, reflecting changes in how society perceives historical events. This research provides new perspectives for understanding the multidimensionality of the monument/memorial but also emphasizes the need to continue exploring its interaction with the socio-cultural context.

FedGST: An Efficient Federated Graph Neural Network for Spatio-temporal PoI Recommendation

With the proliferation of sensor networks in urban areas, vast amounts of data from location-based social network platforms are now available, thus enabling the stakeholders to develop location-aware services for the end users. PoI (Point of Interests) recommendation is one of the most trending services. PoI recommendation models are developed by considering geographical information and historical records. More recently, with the demand for achieving PoI recommendations on mobile devices, embedded devices, or Internet of Things (IoT) devices, the challenges posed by the limited computational resources, malicious clients, and data silos, the model performance gets immensely affected. To address the above challenges and achieve efficient PoI recommendations, we propose an efficient federated graph learning-based model for mining complex spatiotemporal features to generate recommendations. We implement a GRU-based encoder-decoder to learn the temporal hidden state embeddings. Simultaneously, a 2-layer graph network is used to understand spatial embedding vectors. We also introduce an efficient contribution evaluation method to speed up the training process and improve the recommendation performance. Experiments on the PoI recommendation task based on real-life check-in data validate the effectiveness of our proposed model, and the results indicate that our recommendation model can achieve competitive results with lower computational costs.

Learning Joint 2-D and 3-D Graph Diffusion Models for Complete Molecule Generation.

Designing new molecules is essential for drug discovery and material science. Recently, deep generative models that aim to model molecule distribution have made promising progress in narrowing down the chemical research space and generating high-fidelity molecules. However, current generative models only focus on modeling 2-D bonding graphs or 3-D geometries, which are two complementary descriptors for molecules. The lack of ability to jointly model them limits the improvement of generation quality and further downstream applications. In this article, we propose a joint 2-D and 3-D graph diffusion model (JODO) that generates geometric graphs representing complete molecules with atom types, formal charges, bond information, and 3-D coordinates. To capture the correlation between 2-D molecular graphs and 3-D geometries in the diffusion process, we develop a diffusion graph transformer (DGT) to parameterize the data prediction model that recovers the original data from noisy data. The DGT uses a relational attention mechanism that enhances the interaction between node and edge representations. This mechanism operates concurrently with the propagation and update of scalar attributes and geometric vectors. Our model can also be extended for inverse molecular design targeting single or multiple quantum properties. In our comprehensive evaluation pipeline for unconditional joint generation, the experimental results show that JODO remarkably outperforms the baselines on the QM9 and GEOM-Drugs datasets. Furthermore, our model excels in few-step fast sampling, as well as in inverse molecule design and molecular graph generation. Our code is provided in https://github.com/GRAPH-0/JODO.

MEMPSEP‐III. A Machine Learning‐Oriented Multivariate Data Set for Forecasting the Occurrence and Properties of Solar Energetic Particle Events Using a Multivariate Ensemble Approach

AbstractWe introduce a new multivariate data set that utilizes multiple spacecraft collecting in‐situ and remote sensing heliospheric measurements shown to be linked to physical processes responsible for generating solar energetic particles (SEPs). Using the Geostationary Operational Environmental Satellites (GOES) flare event list from Solar Cycle (SC) 23 and part of SC 24 (1998–2013), we identify 252 solar events (&gt;C‐class flares) that produce SEPs and 17,542 events that do not. For each identified event, we acquire the local plasma properties at 1 au, such as energetic proton and electron data, upstream solar wind conditions, and the interplanetary magnetic field vector quantities using various instruments onboard GOES and the Advanced Composition Explorer spacecraft. We also collect remote sensing data from instruments onboard the Solar Dynamic Observatory, Solar and Heliospheric Observatory, and the Wind solar radio instrument WAVES. The data set is designed to allow for variations of the inputs and feature sets for machine learning (ML) in heliophysics and has a specific purpose for forecasting the occurrence of SEP events and their subsequent properties. This paper describes a data set created from multiple publicly available observation sources that is validated, cleaned, and carefully curated for our ML pipeline. The data set has been used to drive the newly‐developed Multivariate Ensemble of Models for Probabilistic Forecast of SEPs (MEMPSEP; see MEMPSEP‐I (Chatterjee et al., 2024, https://doi.org/10.1029/2023SW003568) and MEMPSEP‐II (Dayeh et al., 2024, https://doi.org/10.1029/2023SW003697) for accompanying papers).

Acoustic Feature Extraction Based on Wavelet Transform for Industrial Induction Motor-Driven Belt Conveyor Condition Monitoring

The industrial induction motor-driven belt conveyor is an essential component in manufacturing facilities. Any unexpected shutdown can lead to significant disruptions, resulting in financial losses amounting to thousands of dollars per hour. Unfortunately, efficient mechanisms for monitoring the conveyor's condition are often lacking. Therefore, it is crucial to ensure early, precise, and effective detection of malfunctions in belt conveyors. This necessitates the identification of distinctive anomalies stemming from initial damage to the rotating machinery and motor components. This paper presents a non-invasive acoustic monitoring technique designed specifically for industrial belt conveyors. The method employed relies on wavelet transform-based feature extraction, offering notable advantages in terms of classification accuracy, time efficiency, and the quantity of feature vectors required for classifier training.

Research on the coupling coordination and spatial spillover effect of industrial development and environmental protection

ABSTRACT Analysing the coordination and spatial spillover effects between industrial development and environmental protection is crucial for regional sustainable development. This paper examines the spatial and temporal evolution characteristics of the coupling coordination level between industrial development and environmental protection, as well as the evolution of the decoupling type within this system. under the evolution of the coupling coordination mode and decoupling model. Additionally, it analyzes the spatial spillover effects using the spatial panel vector autoregression model. The main conclusions are as follows: First, the coordination level between industrial development and environmental protection is increasing over time in each province. Second, the decoupling status of industrial development and environmental protection shows distinct stages, progressing towards strong decoupling over time. Third, regional industrial development has a positive spillover effect on both industrial development and environmental protection in neighbouring regions, whereas regional environmental protection has a negative spillover effect on industrial development but a positive spillover effect on environmental protection in neighbouring regions. This paper suggests that provinces should focus on the synchronisation industrial development and environmental protection and implement differentiated strategies based on their specific conditions. Additionally, joint management and governance should be pursued between neighbouring provinces.

Multi-view scene matching with relation aware feature perception

For scene matching, the extraction of metric features is a challenging task in the face of multi-source and multi-view scenes. Aiming at the requirements of multi-source and multi-view scene matching, a siamese network model for Spatial Relation Aware feature perception and fusion is proposed. The key contributions of this work are as follows: (1) Seeking to enhance the coherence of multi-view image features, we investigate the relation aware feature perception. With the help of spatial relation vector decomposition, the distribution consistency perception of image features in the horizontal H→ and vertical W→ directions is realized. (2) In order to establish the metric consistency relationship, the large-scale local information perception strategy is studied to realize the relative trade-off scale selection under the size of mainstream aerial images and satellite images. (3) After obtaining the multi-scale metric features, in order to improve the metric confidence, the feature selection and fusion strategy is proposed. The significance of distinct feature levels in the backbone network is systematically assessed prior to fusion, leading to an enhancement in the representation of pivotal components within the metric features during the fusion process. The experimental results obtained from the University-1652 dataset and the collected real scene data affirm the efficacy of the proposed method in enhancing the reliability of the metric model. The demonstrated effectiveness of this method suggests its applicability to diverse scene matching tasks.

A novel hybrid features grey incidence model and its application in identifying key factors influencing air pollution in Jiangsu Province

Accurately assessing the key factors influencing air pollution is crucial for effective air pollution control. To address this need, we propose a novel Hybrid Features Grey Incidence Model (HFGIM), which integrates geometric feature differences from both proximity and similarity perspectives. Firstly, we extract geometric feature difference vectors of proximity and similarity from time series data and measure the overall feature difference degree by calculating vector norms. Secondly, we calculate the relative feature differences and information contribution rates of proximity and similarity to derive the hybrid feature differences coefficient between sequences, thereby obtaining the hybrid features incidence degree. After detailing the model’s properties and modelling steps, we introduce the Cross-sectional Data Hybrid Features Grey Incidence Model (C-HFGIM) and the Panel Data Hybrid Features Grey Incidence Model (P-HFGIM) for handling cross-sectional and panel data, respectively. Applying HFGIM, we identified the key pollutants and primary pollution source indicators of air pollution in Jiangsu Province. We also compared HFGIM with other classical grey incidence models to verify the proposed model’s effectiveness. Based on the analysis results, we propose policy recommendations for air pollution control in Jiangsu Province.

CuGBasis: High-performance CUDA/Python library for efficient computation of quantum chemistry density-based descriptors for larger systems.

CuGBasis is a free and open-source CUDA®/Python library for efficient computation of scalar, vector, and matrix quantities crucial for the post-processing of electronic structure calculations. CuGBasis integrates high-performance Graphical Processing Unit (GPU) computing with the ease and flexibility of Python programming, making it compatible with a vast ecosystem of libraries. We showcase its utility as a Python library and demonstrate its seamless interoperability with existing Python software to gain chemical insight from quantum chemistry calculations. Leveraging GPU-accelerated code, cuGBasis exhibits remarkable performance, making it highly applicable to larger systems or large databases. Our benchmarks reveal a 100-fold performance gain compared to alternative software packages, including serial/multi-threaded Central Processing Unit and GPU implementations. This paper outlines various features and computational strategies that lead to cuGBasis's enhanced performance, guiding developers of GPU-accelerated code.

Collision Avoidance of UAV Formation Using Geometric Approach and Relative Velocity Vector in Three-dimensional Space

Collision Avoidance of UAV Formation Using Geometric Approach and Relative Velocity Vector in Three-dimensional Space

New asymptotic stability theory for real order systems and applications

Metzler asymptotic stability of real order systems gives hidden paths of nontrivial solutions to geometric constant solutions as time tends to ∞ in positive and negative orthants of Euclidean space when associated with random initial-time. Suppose that there is a governing law that describes the flow of geometric variables described by a real-order system in Euclidean space and a geometric solution zero vector that satisfies such a system. We introduce the concepts of orthant Metzler asymptotic stability that give rise to the notion of so-called new L-asymptotic stability. We prove that there exist order-dependent conditions that give a new L-asymptotic stability. The main results of this paper are comparison theorems that give L-asymptotic stability, which is essential in finding convergence of non-negative and non-positive solutions to geometric constant solutions. We establish upper and lower theoretical α-order Mittag-Leffler bounds of the Euclidean norm measure of non-trivial solutions to such systems, which characterize the Mittag-Leffler rate of decay. As applications of some theoretical results, we provide three examples that include a feedback method to control cancer in a cancer chemotherapy model to illustrate the effectiveness.

Classification and risk estimation of osteoarthritis using deep learning methods

The classification of knee osteoarthritis is solely based on contextual factors, with image processing algorithms playing a significant role in computer-aided diagnosis (CAD) systems. The inconsistent real-time pre-processing, on the other hand, has a significant impact on the diagnosing process. In this work, a Densely Connected Fully Convolutional Network (DFCN) for knee osteoarthritis classifier based on multiple learning (ML) strategies effectively classify knee osteoarthritis on the basis of risk estimation. Spatial osteoarthritis contextual vectors extracted by identifying the relationship between contextual variables using a machine learning approach. The hidden convolutional layers are used to compute edge interpretation, contextual cues, and input correction. The fused layer, which is simply a concentration of derived features, supports automatic learning of contextual features of osteoarthritis classification. The standard datasets from the Osteoarthritis Initiative (OAI) and the Multicentre Osteoarthritis Study (MOST) are used for experimental purposes to validate the proposed method. The results shows that the proposed DFCN is significantly improves the feature recognition for accurate classification around 94 % which is significantly higher than existing CNN results and flexibility to real-time implementation in the CAD system. It can also be used to automatically detect osteoarthritis types using a lightweight CNN architecture.