Topological Relations Research Articles

Baseline-free assisted lamb wave-based damage detection in CFRP composites using graph convolutional networks and Transformer models

Carbon fiber-reinforced polymer (CFRP) composites are widely used in aerospace but are susceptible to damage, threatening structural safety. Thus, developing an effective structural health monitoring system is essential. This study presents CFRP-former, a novel deep learning framework that detects damage in CFRP composites by constructing spatio-temporal representation graphs of Lamb waves (LWs). The CFRP-former comprises three key modules: graph convolutional neural network (GCNN), a multi-layer perceptron (MLP), and a Transformer Encoder. The GCNN models the topological relationships between LW nodes and sensors. The MLP reduces data dimensionality while preserving key information for subsequent analysis. Meanwhile, the Transformer Encoder, employing multi-head attention mechanisms, captures global time-series patterns in the LW signals. Additionally, the CFRP-former framework includes a parallel module that separately predicts both the size and location of damage. Experiments using only four sensors show that CFRP-former achieves high accuracy in detecting and quantifying damage, with robustness confirmed through ablation tests.

Fluid Grey 2: How Well Does Generative Adversarial Networks Learn Deeper Topology Structure in Architecture That Matches Images?

Taking into account the regional characteristics of ‘intrinsic’ and ‘extrinsic’ properties of space is an essential issue in architectural design and urban renewal, which is often achieved step by step using image and graph-based GANs. However, each model nesting and data conversion may cause information loss, and it is necessary to streamline the tools to facilitate architects and users to participate in the design. Therefore, this study hopes to prove that I2I GAN also has the potential to recognize topological relationships autonomously. Therefore, this research proposes a method for quickly detecting the ability of pix2pix to learn topological relationships, which is achieved by adding two Grasshopper-based detection modules before and after GAN. At the same time, quantitative data is provided and its learning process is visualized, and changes in different input modes such as greyscale and RGB affect its learning efficiency. There are two innovations in this paper: 1) It proves that pix2pix can automatically learn spatial topological relationships and apply them to architectural design. 2) It fills the gap in detecting the performance of Image-based Generation GAN from a topological perspective. Moreover, the detection method proposed in this study takes a short time and is simple to operate. The two detection modules can be widely used for customizing image datasets with the same topological structure and for batch detection of topological relationships of images. In the future, this paper may provide a theoretical foundation and data support for the application of architectural design and urban renewal that use GAN to preserve spatial topological characteristics.

TIWMFLP: Two-Tier Interactive Weighted Matrix Factorization and Label Propagation Based on Similarity Matrix Fusion for Drug-Disease Association Prediction.

Accurately identifying new therapeutic uses for drugs is crucial for advancing pharmaceutical research and development. Matrix factorization is often used in association prediction due to its simplicity and high interpretability. However, existing matrix factorization models do not enable real-time interaction between molecular feature matrices and similarity matrices, nor do they consider the geometric structure of the matrices. Additionally, efficiently integrating multisource data remains a significant challenge. To address these issues, we propose a two-tier interactive weighted matrix factorization and label propagation model based on similarity matrix fusion (TIWMFLP) to assist in personalized treatment. First, we calculate the Gaussian and Laplace kernel similarities for drugs and diseases using known drug-disease associations. We then introduce a new multisource similarity fusion method, called similarity matrix fusion (SMF), to integrate these drug/disease similarities. SMF not only considers the different contributions represented by each neighbor but also incorporates drug-disease association information to enhance the contextual topological relationships and potential features of each drug/disease node in the network. Second, we innovatively developed a two-tier interactive weighted matrix factorization (TIWMF) method to process three biological networks. This method realizes for the first time the real-time interaction between the drug/disease feature matrix and its similarity matrix, allowing for a better capture of the complex relationships between drugs and diseases. Additionally, the weighted matrix of the drug/disease similarity matrix is introduced to preserve the underlying structure of the similarity matrix. Finally, the label propagation algorithm makes predictions based on the three updated biological networks. Experimental outcomes reveal that TIWMFLP consistently surpasses state-of-the-art models on four drug-disease data sets, two small molecule-miRNA data sets, and one miRNA-disease data set.

A Study on Guesthouse Interior Space Planning Method Based on BIM Topological Relationships

Building Information Modeling (BIM) technology has revolutionized the architectural and construction industries by providing detailed digital representations of buildings, enhancing design efficiency and project management. Despite its widespread application, the utilization of BIM in optimizing interior space planning, particularly in boutique accommodations like guesthouses, remains underexplored. This research addresses the gap by introducing a novel method for interior environment space planning of guesthouses based on the topological relationships derived from BIM data. This study developed a new algorithm that utilizes detailed topology information from BIM in order to make space planning decisions more efficiently, thereby improving space utilization efficiency and guest experience. Through a comprehensive analysis of BIM topological relationships and the application of advanced optimization techniques, our method aims to optimize the use of space while considering the unique constraints and requirements of guesthouse environments. The proposed algorithm demonstrates significant improvements in spatial efficiency and design quality when tested against traditional planning methods on real-world BIM datasets. This research not only contributes a novel approach to the field of architectural design and planning but also offers practical implications for the enhancement of interior spaces in guesthouses, potentially influencing future applications of BIM technology in the hospitality industry.

Simulation and experimental verification of the orthogonal friction continuous wear of PTFE-Kevlar fabric liner

Woven fabric liners, which are customizable and maintenance-free, have extensive applications in self-lubricating spherical bearings. However, owing to the orthogonal anisotropy and non-homogeneous characteristics, their frictional and wear behaviors are complex. Currently, average performance testing is primarily based on long-term macroscopic wear experiments. However, unobservable parameters such as mesoscopic stress and pressure distribution in liners are bottlenecks in the experimental exploration of wear sources and mechanisms. Therefore, an innovative strategy for modeling orthogonal friction and continuous wear in non-homogeneous liners is presented. This approach has the potential to overcome experimental limitations and significantly expedite liner design and cost-effective validation. The initial step involves establishing a mesoscopic voxel-based planar model of the liner that maintains the topological relationship during wear processes. This is achieved by introducing a circular voxel mesh and spatial transformation methods. Based on orthogonal friction and wear assumptions, separate constitutive models for orthogonal friction and wear are developed. Using the CETR UMT-3 friction and wear testing machine, GCr15 is selected as the counterface material, the pin disc wear method is adopted to conduct sliding test on PTFE and Kevlar fibers, and the required wear constitutive parameters are fitted. Furthermore, incremental equations for the total wear are derived. An element wear fusion strategy is introduced. This approach leads to the development of a continuous wear algorithm for liners and subsequently to the establishment of a voxel-based finite element model with continuous wear capability in the form of a circular voxel grid. This method transcends experimental methods and allows for the determination of the mesoscopic contact pressure, stress distribution, and variations in the contact material composition patterns of liner. The accuracy of the average macroscopic wear prediction is validated experimentally. This method has the potential for practical applications in bearing design.

Phylogenetic tree instability after taxon addition: empirical frequency, predictability, and consequences for online inference.

Online phylogenetic inference methods add sequentially arriving sequences to an inferred phylogeny without the need to recompute the entire tree from scratch. Some online method implementations exist already, but there remains concern that additional sequences may change the topological relationship among the original set of taxa. We call such a change in tree topology a lack of stability for the inferred tree. In this paper, we analyze the stability of single taxon addition in a Maximum Likelihood framework across 1, 000 empirical datasets. We find that instability occurs in almost 90% of our examples, although observed topological differences do not always reach significance under the AU-test. Changes in tree topology after addition of a taxon rarely occur close to its attachment location, and are more frequently observed in more distant tree locations carrying low bootstrap support. To investigate whether instability is predictable, we hypothesize sources of instability and design summary statistics addressing these hypotheses. Using these summary statistics as input features for machine learning under random forests, we are able to predict instability and can identify the most influential features. In summary, it does not appear that a strict insertion-only online inference method will deliver globally optimal trees, although relaxing insertion strictness by allowing for a small number of final tree rearrangements or accepting slightly suboptimal solutions appears feasible.

Indoor Scene Intelligent Identification System Based on Spatial Topological Relationship Constraints

Abstract. Indoor scene identification can provide prior environmental information for indoor positioning applications, achieving positioning enhancement. Due to the similarity of wireless signals in adjacent spaces, it can lead to incorrect identification in neighbouring scenario units. To address this problem, this paper first employs a Naive Bayes classifier to train and classify wireless signal strength data from different scenes, constructing a scene identification algorithm. Secondly, a topological relationship adjacency matrix and adjacency list tailored for indoor positioning are constructed, imposing spatial topological constraints to assist scene identification. Finally, an indoor scene intelligent identification system is developed and implemented. The experimental results indicate that the scene identification method based on spatial topological relationship constraints can effectively improve identification accuracy. The overall accuracy for 8 scenario units is 98.2%, and the identification accuracy is increased by 1.1% compared with the original method.

Geometry, Topology and p-Adic Numbers in Geospatial Data Modelling, Management and Processing: Review and Future Approaches

Abstract. Geometry and topology are both central concepts in geospatial data modelling and management. While geometry is the central concept for computational geometry applications, e.g. to intersect surfaces and solids in 3D space, topology is helpful for many application classes starting from city modelling to subsurface modelling and indoor navigation. Furthermore, p-adic numbers are useful for describing hierarchical processes on topological models. In this paper we first shortly review geometry- and topology-based approaches used for geospatial applications. We then describe our approach on turning geometry “upside down” focusing on topology during the whole process of distributed geospatial computing, data modelling, data management, and simulation. Furthermore, the way to use p-adic numbers for the description of hierarchical processes on topological models is shown for the example of simulation and the idea of p-adic analysis in distributed simulations is presented in the context of topological city and building models. The approach opens new insights such as topological relationships, components, and efficiently studying of the approximate behaviour of processes in the built environment using distributed computational systems. Finally, exemplary applications are presented to underline the importance of this new approach.

STCA: High-Altitude Tracking via Single-Drone Tracking and Cross-Drone Association

In this paper, we introduce a high-altitude multi-drone multi-target (HAMDMT) tracking method called STCA, which aims to collaboratively track similar targets that are easily confused. We approach this challenge by categorizing the HAMDMT tracking into two principal tasks: Single-Drone Tracking and Cross-Drone Association. Single-Drone Tracking employs positional and appearance data vectors to overcome the challenges arising from similar target appearances within the field of view of a single drone. The Cross-Drone Association employs image-matching technology (LightGlue) to ascertain the topological relationships between images captured by disparate drones, thereby accurately determining the associations between targets across multiple drones. In Cross-Drone Association, we enhanced LightGlue into a more efficacious method, designated T-LightGlue, for cross-drone target tracking. This approach markedly accelerates the tracking process while reducing indicator dropout. To narrow down the range of targets involved in the cross-drone association, we develop a Common View Area Model based on the four vertices of the image. Considering to mitigate the occlusion encountered by high-altitude drones, we design a Local-Matching Model that assigns the same ID to the mutually nearest pair of targets from different drones after mapping the centroids of the targets across drones. The MDMT dataset is the only one captured by a high-altitude drone and contains a substantial number of similar vehicles. In the MDMT dataset, the STCA achieves the highest MOTA in Single-Drone Tracking, with the IDF1 system achieving the second-highest performance and the MDA system achieving the highest performance in Cross-Drone Association.

Research on cargo volume prediction and personnel scheduling optimization of sorting center based on BP neural network and improved genetic algorithm

With the development of Internet technology, e-commerce has become the primary choice for consumers to shop, and the huge order transaction volume has generated logistics problems. As an important part of the logistics network, the sorting platform is essential to improve its management efficiency. To enhance the efficiency of the sorting center, the topological relationship diagram is used to show the logistics network, and the cargo volume of the sorting center in the next 30 days and every hour is predicted based on the BP neural network model. Based on the mixed integer linear programming model and the improved genetic algorithm SCAGA model, the total man-days are minimized to ensure that the cargo volume is processed. At the same time, to ensure that the actual hourly efficiency is as balanced as possible, the optimization problem of personnel scheduling is studied. To maintain the efficient operation of the logistics industry, the accurate prediction of the number of goods and the reasonable scheduling of personnel, to provide a set of efficient and economical personnel scheduling programs for the logistics company, thus improving the overall operational efficiency and service quality.

A spatial data model of blind outdoor navigation for path optimization

Current navigational aids for blind people do not provide spatial information that meets the requirements of blind and visually impaired people (BVIP) for travel, and traditional map-based navigation services cannot be used directly for navigation. The purpose of this paper is to establish a spatial data model that aligns with their outdoor travel requirements to assist them in accessing spatial information. In alignment with the analysis of spatial information requirements for blind people during outdoor travel, the proposed data model divides the outdoor space into the path layer, the functional layer, the obstacle layer, and the transport and weather layer. Areas such as schools and sports fields, which fulfill certain requirements for them, are categorized as functional features. Essential public transportation stations for outdoor travel are included in transport station features, while obstacles that pose threats to their safety constitute obstacle features. Various features in space are spatially connected through different paths. The proposed semantic information properties enhance the information content representation of the features. The geometry of the features and the topological relationships between them are recorded and used for path planning and navigation in combination with the path layer. Finally, the eastern campus of Jiangxi University of Science and Technology served as an experimental area for the development of a prototype system based on the data model, and a case analysis was provided.

Topological edge states of acoustic zigzag tubes with triangle scatterers

Tubular geometries in phononic crystals have the advantages of hosting topological edge states without breaking the underlying symmetry of the lattice. The topological relationships between the acoustic zigzag tubes and the dispersion relation of the planar phononic crystal with a zigzag edge boundary are theoretically revealed through 2D k space analysis, circumferential pressure analysis, and lattice symmetry analysis. New cutting lines of the tubes are obtained, which link the winding number of the tubes with the dispersion relation of topological edge states in the planar phononic crystal. The eigenstates analysis shows that the circumferential periodic number of a tubular edge state is regular and corresponds to a specific wavenumber in the circumferential direction. On the basis of the unveiled topological relationships, tubular edge states with tunable properties are obtained by controlling the characteristic length of the boundary scatterers. Moreover, the tubular edge states are confirmed to be highly confined and robust along the designed transmission channel. This study may present a new way to design acoustic tubes with tunability and have potential applications in robust wave propagation and miniaturized phononic devices.

Simulating judicial trial logic: Dual residual cross-attention learning for predicting legal judgment in long documents

Legal Judgment Prediction (LJP) plays a vital role in judicial assistance systems, aiming to predict judgment outcomes automatically from the fact descriptions in legal cases. A key challenge in LJP lies in effectively capturing decisive information that influences legal judgments — such as criminal events, behaviors, and consequences — especially from lengthy legal documents. Existing approaches, which incorporate domain-specific knowledge, have attempted to improve the ability to capture decisive information but often fail to adequately address the complexities of longer texts and may introduce noise, leading to incorrect predictions. To overcome these limitations, we propose a novel method, JuriSim, for predicting Chinese criminal legal judgments in long documents by incorporating the knowledge of judicial trial logic. Specifically, JuriSim extracts legal events and generates rationales based on fact descriptions to capture the decisive information that influences judgment outcomes. Then, a dual residual cross-attention mechanism is introduced to interactively process facts, events, and rationales for predicting relevant legal statutes, charges, and term of penalties. This mechanism allows the model to reduce the loss of important information and the retention of incorrect information during the aggregation process. Furthermore, we present a constrained cross-entropy loss, utilizing the topological relationship between charges, terms, and applicable law statutes. Experiments conducted on the publicly available CAIL-Long criminal dataset demonstrate the efficiency of the JuriSim framework in predicting legal judgments, especially for cases involving long documents. JuriSim_Lawformer shows a relative improvement of 3.45% in Macro-F1 for charge prediction and 3.05% for term of penalty prediction, compared to Lawformer.

A Representation-Learning-Based Graph and Generative Network for Hyperspectral Small Target Detection

Hyperspectral small target detection (HSTD) is a promising pixel-level detection task. However, due to the low contrast and imbalanced number between the target and the background spatially and the high dimensions spectrally, it is a challenging one. To address these issues, this work proposes a representation-learning-based graph and generative network for hyperspectral small target detection. The model builds a fusion network through frequency representation for HSTD, where the novel architecture incorporates irregular topological data and spatial–spectral features to improve its representation ability. Firstly, a Graph Convolutional Network (GCN) module better models the non-local topological relationship between samples to represent the hyperspectral scene’s underlying data structure. The mini-batch-training pattern of the GCN decreases the high computational cost of building an adjacency matrix for high-dimensional data sets. In parallel, the generative model enhances the differentiation reconstruction and the deep feature representation ability with respect to the target spectral signature. Finally, a fusion module compensates for the extracted different types of HS features and integrates their complementary merits for hyperspectral data interpretation while increasing the detection and background suppression capabilities. The performance of the proposed approach is evaluated using the average scores of AUCD,F, AUCF,τ, AUCBS, and AUCSNPR. The corresponding values are 0.99660, 0.00078, 0.99587, and 333.629, respectively. These results demonstrate the accuracy of the model in different evaluation metrics, with AUCD,F achieving the highest score, indicating strong detection performance across varying thresholds. Experiments on different hyperspectral data sets demonstrate the advantages of the proposed architecture.

Edge-featured multi-hop attention graph neural network for intrusion detection system

With the development of the Internet, the application of computer technology has rapidly become widespread, driving the progress of Internet of Things (IoT) technology. The attacks present on networks have become more complex and stealthy. However, traditional network intrusion detection systems with singular functions are no longer sufficient to meet current demands. While some machine learning-based network intrusion detection systems have emerged, traditional machine learning methods cannot effectively respond to the complex and dynamic nature of network attacks. Intrusion detection systems utilizing deep learning can better enhance detection capabilities through diverse data learning and training. To capture the topological relationships in network data, using graph neural networks (GNNs) is most suitable. Most existing GNNs for intrusion detection use multi-layer network training, which may lead to over-smoothing issues. Additionally, current intrusion detection solutions often lack efficiency. To mitigate the issues mentioned above, this paper proposes an Edge-featured Multi-hop Attention Graph Neural Network for Intrusion Detection System (EMA-IDS), aiming to improve detection performance by capturing more features from data flows. Our method enhances computational efficiency through attention propagation and integrates node and edge features, fully leveraging data characteristics. We carried out experiments on four public datasets, which are NF-CSE-CIC-IDS2018-v2, NF-UNSW-NB15-v2, NF-BoT-IoT, and NF-ToN-IoT. Compared with existing models, our method demonstrated superior performance.

Indoor scene reconstruction from LiDAR point cloud based on roof extraction

Indoor scene reconstruction from LiDAR point clouds is crucial for indoor navigation, scan-to-BIM, and virtual reality. However, occlusions caused by furniture and clutter make this task challenging. This paper introduces a novel framework for reconstructing 3D models using typically unoccluded ceiling point clouds, because the ceiling is difficult to be obstructed by indoor objects and is relatively well preserved. This framework starts with extracting the roof, roof is extracted by a proposed method based on cloth simulation which can extract various shape of roofs. Then a room instance map of the scene is obtained by input the point cloud density map to Mask R-CNN. By overlapping the roof point cloud and room instance map, the whole roof is segmented into roof points of different rooms. Next, we extracted the contours of every room's roof and a new algorithm was proposed to detect connections between different rooms to restore the topological relationship between rooms, generating the scene's floor plan. Finally, by detecting the contours and connections' height, the floor plan is stretched to detected height to generate a 3D model. To evaluate the proposed method's effectiveness, experiments were conducted on two indoor LiDAR point cloud datasets, GibLayout and ISPRS Benchmark, comprising a total of 13 scenes. The results were compared with representative methods, including Floor-sp and Heat for floor plan extraction, and Polyfit and KSR for 3D model reconstruction. The experimental results show that the new method outperform existing approaches, enabling the reconstruction of highly overlapping 3D models of real scenes.

Research on Public Space Interior Environmental Planning and Design Method Based on BIM Topological Relationships

With the wide application of building information modeling (BIM) technology in the field of architectural design, this study aims to explore the planning and design method of public space internal environment based on BIM topological relationship. Through in-depth analysis of the data structure and spatial topological relationships of BIM models, this study proposes a public space design framework that combines user needs and environmental standards. Collect and convert relevant data of public spaces into BIM models, use BIM technology to establish detailed models of spatial elements and their topological relationships, combine spatial connectivity, line of sight, and flow simulation analysis, and consider key factors such as spatial layout, lighting, and ventilation. Realize the planning and design of indoor environments in public spaces. The experimental results indicate that the method can effectively improve the quality of public space design and promote the sustainable development of the environment. This study not only highlights the application potential of BIM in public space design, but also provides a new design methodology for the internal environmental planning of public space.

Investigating the Interrelationships among Factors Associated with Automated Vehicle Crashes Using Additive Bayesian Network

Although automated vehicles (AVs) were considered a promising solution to enhance traffic safety by eliminating human errors, AV crashes still happen in mixed traffic consisting of human-driven vehicles and AVs. Thus, to reduce AV-involved crashes, it is necessary to understand the factors leading to AV crashes. However, traditional regression-based methods may not reveal a structured relationship among leading factors of AV crashes, which hinders the exploration of countermeasures to AV crashes. Based on the 246 AV crash records collected by the National Highway Traffic Safety Administration, this study investigated the factors associated with AV crashes. An additive Bayesian network (ABN) approach was utilized to construct the topological relationship among potential influential factors of AV crashes, followed by post-ABN regression analyses. Results show that, though AV technologies have developed rapidly in the past few years, rear-end crashes are still dominant among AV-involved crashes, potentially because of the discrepancy in the driving behaviors between AV and human-driven vehicles. The crash type of AV-involved crashes is more related to the pre-crash movements of crash partners than it is to the pre-crash movements of AVs, while crash outcomes (e.g., injury severity) are associated with the environmental factors (e.g., operating entities) and crash-procedure-related factors (e.g., crash type). Findings from this study aid in understanding AV crash patterns, which can inform targeted interventions and technology advancements to improve safety outcomes for all road users.

Efficient Multi-View Graph Convolutional Network with Self-Attention for Multi-Class Motor Imagery Decoding.

Research on electroencephalogram-based motor imagery (MI-EEG) can identify the limbs of subjects that generate motor imagination by decoding EEG signals, which is an important issue in the field of brain-computer interface (BCI). Existing deep-learning-based classification methods have not been able to entirely employ the topological information among brain regions, and thus, the classification performance needs further improving. In this paper, we propose a multi-view graph convolutional attention network (MGCANet) with residual learning structure for multi-class MI decoding. Specifically, we design a multi-view graph convolution spatial feature extraction method based on the topological relationship of brain regions to achieve more comprehensive information aggregation. During the modeling, we build an adaptive weight fusion (Awf) module to adaptively merge feature from different brain views to improve classification accuracy. In addition, the self-attention mechanism is introduced for feature selection to expand the receptive field of EEG signals to global dependence and enhance the expression of important features. The proposed model is experimentally evaluated on two public MI datasets and achieved a mean accuracy of 78.26% (BCIC IV 2a dataset) and 73.68% (OpenBMI dataset), which significantly outperforms representative comparative methods in classification accuracy. Comprehensive experiment results verify the effectiveness of our proposed method, which can provide novel perspectives for MI decoding.

Optimizing graph neural network architectures for schizophrenia spectrum disorder prediction using evolutionary algorithms

Background and Objective:The accurate diagnosis of schizophrenia spectrum disorder plays an important role in improving patient outcomes, enabling timely interventions, and optimizing treatment plans. Functional connectivity analysis, utilizing functional magnetic resonance imaging data, has been demonstrated to offer invaluable biomarkers conducive to clinical diagnosis. However, previous studies mainly focus on traditional machine learning methods or hand-crafted neural networks, which may not fully capture the spatial topological relationship between brain regions. Methods:This paper proposes an evolutionary algorithm (EA) based graph neural architecture search (GNAS) method. EA-GNAS has the ability to search for high-performance graph neural networks for schizophrenia spectrum disorder prediction. Moreover, we adopt GNNExplainer to investigate the explainability of the acquired architectures, ensuring that the model’s predictions are both accurate and comprehensible. Results:The results suggest that the graph neural network model, derived using genetic algorithm search, outperforms under five-fold cross-validation, achieving a fitness of 0.1850. Relative to conventional machine learning and other deep learning approaches, the proposed method yields superior accuracy, F1 score, and AUC values of 0.8246, 0.8438, and 0.8258, respectively. Conclusion:Based on a multi-site dataset from schizophrenia spectrum disorder patients, the findings reveal an enhancement over prior methods, advancing our comprehension of brain function and potentially offering a biomarker for diagnosing schizophrenia spectrum disorder.