Embedding Method Research Articles

Hierarchical-design coating on C/C composite with excellent combination of autonomously self-healing ability and low oxygen permeability from 973 K to 1273 K

Antioxidant SiO2 coating exhibits low cost and great compatibility with existing uses, but is strongly limited by its poor fluidity and high oxygen permeability from 973 K to 1273 K. Therefore, the hierarchical-design Glass/MoSi2-B2O3@SiO2-SiC coating was fabricated on C/C composite by a simple embedding method, and followed by a hot dip process. This composite yielded excellent combination of long-term antioxidant abilities and thermal shock resistances. As oxidized at 973 K for 1500 h, its mass loss was 0.35 %, and only 0.66 % at 1073 K for 2600 h. After thermal shocks 270 times, the weight loss was only 0.56 %. Interestingly, the Glass/MoSi2 coating acted as a self-healing encapsulation shelter against oxygen, whilst the B2O3@SiO2 layer yielded stable healing effect. The B2O3@SiO2 microcapsule facilitated the activation of B2O3, SiO2 phases, and borosilicate glass sequentially as temperature rose, leveraging their unique advantages in defect healing. Through the synergistic effects of interface encapsulation and defect self-healing, the oxygen kept osmotic diffusion. This study underscores the significance of hierarchical designs in coatings, facilitating structure optimizations and enhancing antioxidant capabilities at multiple levels.

Local core expanding-based label diffusion and local deep embedding for fast community detection algorithm in social networks

Community detection is a key task in social network analysis, as it reveals the underlying structure and function of the network. Various global and local techniques exist for uncovering community structures in social networks wherein diffusion-based algorithms are proposed as novel methods for local community detection, particularly suited for large-scale networks. The efficacy of diffusion processes and initial detection is paramount in the successful identification of community structures within social networks. This effectiveness hinges significantly on the meticulous selection of the label diffuser core, which serves as the foundation for propagating labels through the network, and the precise labeling of boundary nodes. Addressing the constraints of current community detection algorithms, notably their time complexity and efficiency, this paper proposes a novel local community detection algorithm that combines core expansion with label diffusion, and deep embedding techniques. In the proposed method, a new centrality measure is introduced for appropriate core selection to facilitate precise label diffusion in the initial phase. Subsequently, a deep embedding technique is employed for updating labels of boundary and core nodes using the GraphSage embedding method. Finally, a rapid merging step is executed to amalgamate initially proximate communities into finalized community structures in large-scale social networks. We evaluate our algorithm on 14 real-world and 4 synthetic networks and show that it outperforms existing methods in terms of NMI, F-measure, ARI, and modularity. According to numerical results, the proposed method shows approximately 1.04 %, 1.03 %, and 1.12 % improvement in F-measure, NMI, and ARI measures respectively, compared to the second-best method, LBLD, in the networks with ground-truth. In addition, our method is able to accurately identify communities in large-scale networks such as Orkut, YouTube, and LiveJournal, where it ranks among the top-performing methods. Our approach exhibits the best performance in terms of ARI compared to other algorithms under comparison.

Incorporating informatively collected laboratory data from EHR in clinical prediction models

BackgroundElectronic Health Records (EHR) are widely used to develop clinical prediction models (CPMs). However, one of the challenges is that there is often a degree of informative missing data. For example, laboratory measures are typically taken when a clinician is concerned that there is a need. When data are the so-called Not Missing at Random (NMAR), analytic strategies based on other missingness mechanisms are inappropriate. In this work, we seek to compare the impact of different strategies for handling missing data on CPMs performance.MethodsWe considered a predictive model for rapid inpatient deterioration as an exemplar implementation. This model incorporated twelve laboratory measures with varying levels of missingness. Five labs had missingness rate levels around 50%, and the other seven had missingness levels around 90%. We included them based on the belief that their missingness status can be highly informational for the prediction. In our study, we explicitly compared the various missing data strategies: mean imputation, normal-value imputation, conditional imputation, categorical encoding, and missingness embeddings. Some of these were also combined with the last observation carried forward (LOCF). We implemented logistic LASSO regression, multilayer perceptron (MLP), and long short-term memory (LSTM) models as the downstream classifiers. We compared the AUROC of testing data and used bootstrapping to construct 95% confidence intervals.ResultsWe had 105,198 inpatient encounters, with 4.7% having experienced the deterioration outcome of interest. LSTM models generally outperformed other cross-sectional models, where embedding approaches and categorical encoding yielded the best results. For the cross-sectional models, normal-value imputation with LOCF generated the best results.ConclusionStrategies that accounted for the possibility of NMAR missing data yielded better model performance than those did not. The embedding method had an advantage as it did not require prior clinical knowledge. Using LOCF could enhance the performance of cross-sectional models but have countereffects in LSTM models.

Natural gas pipeline leak diagnosis based on manifold learning

Natural gas pipeline leakage is a common safety hazard, which can have a great impact on the economy and the environment. This paper proposed a novel manifold learning-enabled feature extraction method for natural gas pipeline leakage diagnosis. Firstly, the natural gas pipeline working condition signal is decomposed and denoised by Variational mode decomposition (VMD). Secondly, the denoised pipeline signals were constructed into a form expressed by the Symmetric positive definite matrix (SPD) using the VMD reconstruction technique, and the geodesic distance measurement method was applied to the SPD matrix to make the data located on the SPD manifold. Then feature extraction is carried out by Local linear embedding (LLE) method based on asymmetric distance. Finally, pattern recognition of the features extracted in this paper by Support vector machine (SVM) can achieve 100% recognition accuracy. By enabling faster and more accurate leak detection, the method minimizes gas loss, as well as mitigating the environmental risks caused by this potent greenhouse gas.

Deep hyperbolic convolutional model for knowledge graph embedding

Recent advancements in knowledge graph embedding have enabled the representation of entities and relations in continuous vector spaces. Performing link prediction on incomplete knowledge graphs using these embeddings has emerged as a challenging task, drawing considerable research interest. Knowledge graphs in the real world typically exhibit a natural hierarchical structure. Hyperbolic embedding methods have shown promising results in modeling hierarchical data, especially in low-dimensional representations. However, existing hyperbolic models for knowledge graph embedding are generally shallow, resulting in limited expressiveness. Additionally, some deep hyperbolic models exist but are often constrained to fixed curvature spaces, which may not optimally capture varying hierarchical structures. In this work, we propose DeER, a novel multi-layer hyperbolic model that leverages a trainable curvature space, marking an advancement in the depth and adaptability of hyperbolic modeling for knowledge graph embeddings. We specifically design a hyperbolic convolutional neural network to learn the heterogeneous interactions between entities and relations within this adaptable hyperbolic space. Additionally, we introduce a hyperbolic feedforward neural network to transform hyperbolic features across multiple layers, enhancing the model’s ability to capture complex hierarchical relationships. Experimental results on three benchmark datasets demonstrate that DeER significantly enhances expressiveness and hierarchical modeling performance when compared to both shallow and other deep baseline approaches.

A Reversible Data-Hiding Method for Encrypted Images Based on Adaptive Quadtree Partitioning and MSB Prediction

To address the vulnerability of the widely used block permutation and co-XOR (BPCX) encryption algorithm in reversible data-hiding in the encrypted domain (RDH-ED), which is susceptible to known-plaintext attacks (KPAs), and to enhance embedding capacity, we propose a novel technique of reversible data-hiding in encrypted images (RDH-EI). This method incorporates adaptive quadtree partitioning and most significant bit (MSB) prediction. To counteract KPAs, we introduce pixel modulation specifically targeting pixels within blocks of the same level during the encryption phase. During data embedding, we utilize tagging bits to indicate the state of the pixel blocks, capitalizing on pixel redundancy within those blocks to augment embedding capacity. Our experimental results demonstrate that our method not only achieves reversibility and separability but also significantly boosts embedding capacity and method security. Notably, the average embedding rate across the 10,000 images tested stands at 2.4731, surpassing previous methods by 0.2106 and 0.037, respectively.

Combined matrix-assisted laser desorption/ionisation-mass spectrometry imaging with liquid chromatography-tandem mass spectrometry for observing spatial distribution of lipids in whole Caenorhabditis elegans.

Matrix-assisted laser desorption/ionisation-mass spectrometry imaging (MALDI-MSI) is a powerful label-free technique for biomolecule detection (e.g., lipids), within tissue sections across various biological species. However, despite its utility in many applications, the nematode Caenorhabditis elegans is not routinely used in combination with MALDI-MSI. The lack of studies exploring spatial distribution of biomolecules in nematodes is likely due to challenges with sample preparation. This study developed a sample preparation method for whole intact nematodes, evaluated using cryosectioning of nematodes embedded in a 10% gelatine solution to obtain longitudinal cross sections. The slices were then subjected to MALDI-MSI, using a RapifleX Tissuetyper in positive and negative polarities. Samples were also prepared for liquid chromatography-tandem mass spectrometry (LC-MS/MS) analysis using an Exploris 480 coupled to a HPLC Vanquish system to confirm the MALDI-MSI results. An optimised embedding method was developed for longitudinal cross-sectioning of individual worms. To obtain longitudinal cross sections, nematodes were frozen at -80°C so that all worms were rod shaped. Then, the samples were defrosted and transferred to a 10% gelatine matrix in a cryomold; the worms aligned, and the whole cryomold submerged in liquid nitrogen. Using MALDI-MSI, we were able to observe the distribution of lipids within C. elegans, with clear differences in their spatial distribution at a resolution of 5μm. To confirm the lipids from MALDI-MSI, age-matched nematodes were subjected to LC-MS/MS. Here, 520 lipids were identified using LC-MS/MS, indicating overlap with MALDI-MSI data. This optimised sample preparation technique enabled (un)targeted analysis of spatially distributed lipids within individual nematodes. The possibility to detect other biomolecules using this method thus laid the basis for prospective preclinical and toxicological studies on C. elegans.

Transformer-based models for combating rumours on microblogging platforms: a review

The remarkable success of Transformer-based embeddings in natural language tasks has sparked interest among researchers in applying them to classify rumours on social media, particularly microblogging platforms. Unlike traditional word embedding methods, Transformers excel at capturing a word’s contextual meaning by considering words from both the left and right of a word, resulting in superior text representations ideal for tasks like rumour detection on microblogging platforms. This survey aims to provide a thorough and well-organized overview and analysis of existing research on implementing Transformer-based models for rumour detection on microblogging platforms. The scope of this study is to offer a comprehensive understanding of this topic by systematically examining and organizing the existing literature. We start by discussing the fundamental reasons and significance of automating rumour detection on microblogging platforms. Emphasizing the critical role of text embedding in converting textual data into numerical representations, we review current approaches to implement Transformer models for rumour detection on microblogging platforms. Furthermore, we present a novel taxonomy that covers a wide array of techniques and approaches employed in the deployment of Transformer-based models for identifying misinformation on microblogging platforms. Additionally, we highlight the challenges associated with this field and propose potential avenues for future research. Drawing insights from the surveyed articles, we anticipate that promising results will continue to emerge as the challenges outlined in this study are addressed. We hope that our efforts will stimulate further interest in harnessing the capabilities of Transformer models to combat the spread of rumours on microblogging platforms.

Online Spatial-Temporal EV Charging Scheduling with Incentive Promotion

The growing adoption of electric vehicles (EVs) has resulted in an increased demand for public EV charging infrastructure. Currently, the collaboration between these stations has become vital for efficient charging scheduling and cost reduction. However, most existing scheduling methods primarily focus on recommending charging stations without considering users’ charging preferences. Adopting these strategies may require considerable modifications to how people charge their EVs, which could lead to a reluctance to follow the scheduling plan from charging services in real-world situations. To address these challenges, we propose the POSKID framework in this paper. It focuses on spatial-temporal charging scheduling, aiming to recommend a feasible charging arrangement, including a charging station and a charging time slot, to each EV user while minimizing overall operating costs and ensuring users’ charging satisfaction. The framework adopts an online charging mechanism that provides recommendations without prior knowledge of future electricity information or charging requests. To enhance users’ willingness to accept the recommendations, POSKID incorporates an incentive strategy and a novel embedding method combined with Bayesian personalized analysis. These techniques reveal users’ implicit charging preferences, enhancing the success probability of the charging scheduling task. Furthermore, POSKID integrates an online candidate arrangement selection and an explore-exploit strategy to improve the charging arrangement recommendations based on users’ feedback. Experimental results using real-world datasets validate the effectiveness of POSKID in optimizing charging management, surpassing other strategies. The results demonstrate that POSKID benefits each charging station while ensuring user charging satisfaction.

An approach for identifying complementary patents based on deep learning

Current studies on technology mining and analysis often focus on patent similarity, with relatively limited research on patent complementarity. Specifically, the hierarchical relationships among patents are seldom used and a standardized complementary patents dataset has not been established. In addition, it is necessary to utilize both network structure features and text content features of patents, and find the most suitable representation learning method for them. Finally, the relationships among different dimensions of feature representations are complex, making it essential to learn the contributions of each dimension considering complex interactions. Therefore, this paper first constructs a complementary patents dataset using hierarchical relationships contained in IPC numbers. Secondly, we design three types of embedding methods for patent semantic representation, including network embedding, text embedding and fusion embedding. Thirdly, we propose a deep learning framework enhanced by the CBAM (Convolutional Block Attention Module) to deal with the complex interactions between different dimensions of patent representation. The result shows that the proposed method CompGCN combined with ESimCSE_Attention performs best for complementary patent identification and the F1 score reaches 95.76 %. In addition, HeGAN and ESimCSE_Attention are the most suitable embedding methods for network structure and text content respectively. These results not only validate the effectiveness of the proposed approach, but also provide helpful and useful suggestions for method selection and complex relationships mining.

Deep network embedding with dimension selection

Network embedding is a general-purpose machine learning technique that converts network data from non-Euclidean space to Euclidean space, facilitating downstream analyses for the networks. However, existing embedding methods are often optimization-based, with the embedding dimension determined in a heuristic or ad hoc way, which can cause potential bias in downstream statistical inference. Additionally, existing deep embedding methods can suffer from a nonidentifiability issue due to the universal approximation power of deep neural networks. We address these issues within a rigorous statistical framework. We treat the embedding vectors as missing data, reconstruct the network features using a sparse decoder, and simultaneously impute the embedding vectors and train the sparse decoder using an adaptive stochastic gradient Markov chain Monte Carlo (MCMC) algorithm. Under mild conditions, we show that the sparse decoder provides a parsimonious mapping from the embedding space to network features, enabling effective selection of the embedding dimension and overcoming the nonidentifiability issue encountered by existing deep embedding methods. Furthermore, we show that the embedding vectors converge weakly to a desired posterior distribution in the 2-Wasserstein distance, addressing the potential bias issue experienced by existing embedding methods. This work lays down the first theoretical foundation for network embedding within the framework of missing data imputation.

Visually secure encryption embedded with multiple types of images using semi-tensor product compressed sensing

An image encryption scheme with visual security is designed by combining the semi-tensor product compressed sensing (STP-CS) with multi-embedding strategy. Specifically, the optimized measurement matrix is firstly generated by chaotic system and singular value decomposition (SVD), and the optimized measurement matrix is used to obtain the measurement value matrix by STP-CS operation on the color image. Next, the reorganized measurement value matrix is scrambled and diffused with the key matrix generated by 2D Logistic-Sine-coupling map (2D-LSCM) to obtain the noise-like encrypted image. Finally, an image embedding method is introduced to embed the compressed noise-like encrypted image into a color or grayscale carrier image to obtain a visually secure color or grayscale encrypted image. SHA-256 is used to generate the initial values of chaotic systems, which are embedded into the carrier image to effectively reduce transmission and storage. The simulation results show that the visually secure encryption scheme is more reliable and outperforms other encryption algorithms.

A task‐centric knowledge graph construction method based on multi‐modal representation learning for industrial maintenance automation

AbstractMaintenance manuals are crucial information sources for maintenance and repair. Prior studies explored factual knowledge extraction from textual documents. However, maintenance knowledge in manuals is more task‐centric rather than factual knowledge and often documented in an unstructured Portable Document Format (PDF), posing challenges for knowledge extraction. Addressing this, this research develops effective methods to extract task‐centric maintenance knowledge from unstructured PDF manuals. A new Task‐centric Knowledge Graph (TCKG) schema centralized on maintenance task components (MTCs) is proposed to address the need for structured knowledge representation. A method (Heterogeneous Graph‐based Method, HGM) for knowledge extraction is then proposed, which is enhanced by incorporating visual and spatial information. In the experiments, the proposed HGM exhibits robust performance in the knowledge extraction process, surpassing the baseline Graph‐based Interaction Model with a Tracker (GIT) method in MTCs extraction by 13.3%, and the baseline Translate Embedding (TransE) method in MTCs' relation extraction by 3.8%. A series of ablation studies also prove that including visual and spatial information through the proposed method can improve the relation extraction performance by over 10%. This research supplies valuable insights for future developments in information extraction from maintenance manuals.

Errorless robust JPEG steganography using steganographic polar codes

Recently, a robust steganographic algorithm that achieves errorless robustness against JPEG recompression has been proposed. The method employs a lattice embedding scheme and utilizes the syndrome-trellis code (STC) for practical embedding. However, we have noticed that errorless robust embedding with STC may encounter failures due to modifications on wet coefficients, especially when a high quality factor is used by the compression channel. To solve this problem, we have discovered that using steganographic polar code (SPC) for embedding has better performance in avoiding modifications on wet coefficients. In this paper, we conduct theoretical analysis to prove the better performance of SPC in wet paper embedding. We establish the condition of avoiding modifications on wet coefficients, followed by presenting a recursive calculation method for determining the distribution of columns in the generator matrix of SPC. The findings reveal that SPC can avoid modifications on wet coefficients under a larger number of wet coefficients compared with STC, and therefore we propose a better errorless robust embedding method employing SPC. The experimental results demonstrate that under close security performance, the proposed method achieves a higher success rate compared with embedding with STC. Specifically, when the quality factor of the compressor is 95 and the payload size is 0.4 bpnzac, our method achieves a success rate of 99.85%, surpassing the 91.95% success rate of the embedding with STC.

Integrated Amphibious Distributed Acoustic Sensing for Seismic Monitoring in the Xinfengjiang Reservoir

Abstract The rapidly advancing technology of distributed acoustic sensing (DAS) has profoundly impacted the field of underwater geophysics. Our study investigates the effectiveness of DAS in underwater geological stability monitoring, with a particular focus on microseismic monitoring in the Xinfengjiang reservoir. The 6.2 km long acquisition setup, covering both land and reservoir bottom, was verified using temporary shore-based short-period seismometers to ensure reliable data acquisition in various environments. Higher background noise was observed on the land section compared with the lakebed section during the day, whereas both sections exhibited similar noise levels at night. We confirmed that the DAS system was capable of detecting distant microseismic events, some of which were previously unreported. These detections exhibited temporal and phase consistency with neighboring seismometers. Comparison of signal-to-noise ratios indicates that the lakebed section demonstrates higher sensitivity. This system delivers cost-effective performance through natural settling, negating the requirement for costly embedding methods. Moreover, the DAS system identified “comet-like” small-scale signals on the lakebed that had eluded shore-based seismometers. This exemplifies the exceptional high-density and high-resolution capabilities of DAS technology in both aquatic and terrestrial environments. This study underscores the pivotal role of the DAS technology in conducting underwater microseismic monitoring, real-time seismic monitoring, seismic mechanism research, and earthquake hazard assessment.

Network embedding based on DepDist contraction

Networks provide an understandable and, in the case of small size, visualizable representation of data, which allows us to obtain essential information about the relationships between pairs of nodes, e.g., their distances. In visualization, networks have an alternative two-dimensional vector representation to which various machine-learning methods can be applied. More generally, networks can be transformed into a low-dimensional space using so-called embedding methods, which bridge the gap between network analysis and traditional machine learning by creating numerical representations that capture the essence of the network structure. In this article, we present a new embedding method that uses non-symmetric dependency to find the distance between nodes and applies an iterative procedure to find a satisfactory distribution of nodes in space. For dimension 2 and the visualization of the result, we demonstrate the method’s effectiveness on small networks. For higher dimensions and several larger networks, we present the results of two experiments comparing our results with two well-established methods in the research community, namely node2vec and DeepWalk. The first experiment focuses on a qualitative comparison of the methods, while the second focuses on applying and comparing the classification results to embeddings in a higher dimension. Although the presented method does not outperform the two chosen methods, its results are still comparable. Therefore, we also explain the limitations of our method and a possible way to overcome them.

Incremental minimum distortion embedding for online structural damage classification.

The damage detection problem in structures diminishes the maintenance cost and extends the life of the structures. Online structural damage classification is a relevant topic in structural health monitoring since monitoring the structure using sensors can help decision-makers can rely on empirical evidence for making informed choices regarding the maintenance, repair, or replacement of structural components. Sensors generate high-dimensional data. To address this challenge, employing dimensionality reduction methods becomes essential. These methods help obtain a low-dimensional representation of the data. Traditional dimensionality reduction methods are trained on a fixed data set, and incorporating new data may require retraining the entire model. This study employed the Minimum Distortion Embedding (MDE) method incrementally, ensuring the maintenance of a consistent embedding as new data becomes available. This incremental embedding took advantage of an anchor constraint to pin the existing embedding in place, then embed the new points. An online structural classification methodology was developed using the incremental MDE and a stream based hoeffding tree classifier. Stream data processing differs from batch processing, as it involves the real-time consumption of each incoming data. The developed methodology was tested with data obtained by accelerometers in a laboratory scaled jacket-type wind turbine foundation. The structural damage classification problems had 5 different classes including the undamaged class and 4 different damage classes. The damage corresponded to a 5mm crack in four different structural elements of the wind turbine foundation. The results indicate the good behavior of the damage classification methodology supported by the high values of the classification metrics obtained.

DualNetGO: a dual network model for protein function prediction via effective feature selection.

Protein-protein interaction (PPI) networks are crucial for automatically annotating protein functions. As multiple PPI networks exist for the same set of proteins that capture properties from different aspects, it is a challenging task to effectively utilize these heterogeneous networks. Recently, several deep learning models have combined PPI networks from all evidence, or concatenated all graph embeddings for protein function prediction. However, the lack of a judicious selection procedure prevents the effective harness of information from different PPI networks, as these networks vary in densities, structures, and noise levels. Consequently, combining protein features indiscriminately could increase the noise level, leading to decreased model performance. We develop DualNetGO, a dual-network model comprised of a Classifier and a Selector, to predict protein functions by effectively selecting features from different sources including graph embeddings of PPI networks, protein domain, and subcellular location information. Evaluation of DualNetGO on human and mouse datasets in comparison with other network-based models shows at least 4.5%, 6.2%, and 14.2% improvement on Fmax in BP, MF, and CC gene ontology categories, respectively, for human, and 3.3%, 10.6%, and 7.7% improvement on Fmax for mouse. We demonstrate the generalization capability of our model by training and testing on the CAFA3 data, and show its versatility by incorporating Esm2 embeddings. We further show that our model is insensitive to the choice of graph embedding method and is time- and memory-saving. These results demonstrate that combining a subset of features including PPI networks and protein attributes selected by our model is more effective in utilizing PPI network information than only using one kind of or concatenating graph embeddings from all kinds of PPI networks. The source code of DualNetGO and some of the experiment data are available at: https://github.com/georgedashen/DualNetGO.

Multi-Dimensional Holomorphic Embedding Method for Probabilistic Energy Flow Calculation in Integrated Distribution Power and Heating System

Multi-Dimensional Holomorphic Embedding Method for Probabilistic Energy Flow Calculation in Integrated Distribution Power and Heating System

SPECE: Subject Position Encoder in Complex Embedding for Relation Extraction

As a crucial component of many natural language processing tasks, extracting entities and relations transforms unstructured text information into structured data, providing essential support for constructing knowledge graphs (KGs). However, current entity relation extraction models often prioritize the extraction of richer semantic features or the optimization of relation extraction methods, overlooking the significance of positional information and subject characteristics in this task. To solve this problem, we introduce the subject position-based complex exponential embedding for entity relation extraction model (SPECE). The encoder module of this model ingeniously combines a randomly initialized dilated convolutional network with a BERT encoder. Notably, it determines the initial position of the predicted subject based on semantic cues. Furthermore, it achieves a harmonious integration of positional encoding features and textual features through the adoption of the complex exponential embedding method. The experimental outcomes on both the NYT and WebNLG datasets reveal that, when compared to other baseline models, our proposed SPECE model demonstrates significant improvements in the F1 score on both datasets. This further validates its efficacy and superiority.