Simple Embedding Research Articles

Mode-locked soliton pulse generation using copper phthalocyanine absorber in long erbium-doped fibre laser cavity

We present the development of a mode-locked erbium-doped fibre laser (EDFL) utilizing Copper Phthalocyanine (CuPc) as a saturable absorber (SA). CuPc exhibits unique optical properties, including its high nonlinear optical response and rapid recovery time. To seamlessly integrate CuPc into the laser cavity, we employed a simple embedding technique within a polymer film. The SA demonstrates a modulation depth of 3.1% and a saturation intensity of 17 MW/cm2. Operating within a pump power range of 90.6 to 122.9 mW, the laser achieves mode-locked operation, producing a soliton pulse train with a fundamental frequency of 1.82 MHz and a pulse width of 6.4 ps at a wavelength of 1561.5 nm. It attains a maximum output power of 13.97 mW and a pulse energy of 7.67 nJ. These results underscore CuPc's potential as a promising material for generating mode-locked pulses, suggesting new avenues in ultrafast laser development for diverse applications.

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.

DECNet: Dense embedding contrast for unsupervised semantic segmentation

Unsupervised semantic segmentation is important for understanding that each pixel belongs to known categories without annotation. Recent studies have demonstrated promising outcomes by employing a vision transformer backbone pre-trained on an image-level dataset in a self-supervised manner. However, those methods always depend on complex architectures or meticulously designed inputs. Naturally, we are attempting to explore the investment with a straightforward approach. To prevent over-complication, we introduce a simple Dense Embedding Contrast network (DECNet) for unsupervised semantic segmentation in this paper. Specifically, we propose a Nearest Neighbor Similarity strategy (NNS) to establish well-defined positive and negative pairs for dense contrastive learning. Meanwhile, we optimize a contrastive objective named Ortho-InfoNCE to alleviate the false negative problem inherent in contrastive learning for further enhancing dense representations. Finally, extensive experiments conducted on COCO-Stuff and Cityscapes datasets demonstrate that our approach outperforms state-of-the-art methods.

Semi-Automated Nonresponse Detection for Open-Text Survey Data

Open-ended survey questions can enable researchers to gain insights beyond more commonly used closed-ended question formats by allowing respondents an opportunity to provide information with few constraints and in their own words. Open-ended web probes are also increasingly used to inform the design and evaluation of survey questions. However, open-ended questions are more susceptible to insufficient or irrelevant responses that can be burdensome and time-consuming to identify and remove manually, often resulting in underuse of open-ended questions and, when used, potential inclusion of poor-quality data. To address these challenges, we developed and publicly released the Semi-Automated Nonresponse Detection for Survey text (SANDS), an item nonresponse detection approach based on a Bidirectional Transformer for Language Understanding model, fine-tuned using Simple Contrastive Sentence Embedding and targeted human coding, to categorize open-ended text data as valid or likely nonresponse. This approach is powerful in that it uses natural language processing as opposed to existing nonresponse detection approaches that have relied exclusively on rules or regular expressions or used bag-of-words approaches that tend to perform less well on short pieces of text, typos, or uncommon words, often prevalent in open-text survey data. This paper presents the development of SANDS and a quantitative evaluation of its performance and potential bias using open-text responses from a series of web probes as case studies. Overall, the SANDS model performed well in identifying a dataset of likely valid results to be used for quantitative or qualitative analysis, particularly on health-related data. Developed for generalizable use and accessible to others, the SANDS model can greatly improve the efficiency of identifying inadequate and irrelevant open-text responses, offering expanded opportunities for the use of open-text data to inform question design and improve survey data quality.

Deposition voltages on the phase evolutions, microstructures, and oxidation behaviors of thermal-resistance Glass-MoSi2-SiC coating

ABSTRACT Due to the high oxidation activities at high temperatures, traditional SiC coating was difficult to act as an antioxidant material for ages. In this case, the multilayered Glass-MoSi2-SiC coating was fabricated on the C/C substrate, combined with hydrothermal electrophoresis deposition and simple embedding process. It was found that the composite obtained at 10 V performed outstanding combinations of oxidation resistance and thermal shock resistance properties. The weight loss of this Glass-MoSi2-SiC-C/C composite was only 0.99% after 212 h oxidation at 1773 K. After thermal shock for 130 times, the mass was just 0.05% lower than that of the initial. These excellent heat-resistant performances were much better than those in similar reports, which was attributed to the suitable coating composition and dense interlayer structure. As oxidized at 1773 K, the in-situ SiO2 phases had a self-healing ability to fill micropores and microcracks to protect the structure. The structure failure was related to SiO2 volatilization. This study emphasized the importance of simple techniques in the thermal-resistance coating fields at multiple length scales.

SEDD: Robust Blind Image Watermarking With Single Encoder And Dual Decoders

Abstract Blind image watermarking is regarded as a vital technology to provide copyright of digital images. Due to the rapid growth of deep neural networks, deep learning-based watermarking methods have been widely studied. However, most existing methods which adopt simple embedding and extraction structures cannot fully utilize the image features. In this paper, we propose a novel Single-Encoder-Dual-Decoder (SEDD) watermarking architecture to achieve high imperceptibility and strong robustness. Precisely, the single encoder utilizes normalizing flow to realize watermark embedding, which can effectively fuse the watermark and cover image. For watermark extraction, we introduce a parallel dual-decoder to improve the imperceptibility and extracting ability. Extensive experiments demonstrate that better watermark robustness and imperceptibility are obtained by SEDD architecture. Our method achieves a bit error rate less than 0.1% under most attacks such as JPEG compression, Gaussian blur and crop. Besides, the proposed method also obtains strong robustness under combined attacks and social platform processing.

Graph embedding approach to analyze sentiments on cryptocurrency

This paper presents a comprehensive exploration of graph embedding techniques for sentiment analysis. The objective of this study is to enhance the accuracy of sentiment analysis models by leveraging the rich contextual relationships between words in text data. We investigate the application of graph embedding in the context of sentiment analysis, focusing on it is effectiveness in capturing the semantic and syntactic information of text. By representing text as a graph and employing graph embedding techniques, we aim to extract meaningful insights and improve the performance of sentiment analysis models. To achieve our goal, we conduct a thorough comparison of graph embedding with traditional word embedding and simple embedding layers. Our experiments demonstrate that the graph embedding model outperforms these conventional models in terms of accuracy, highlighting it is potential for sentiment analysis tasks. Furthermore, we address two limitations of graph embedding techniques: handling out-of-vocabulary words and incorporating sentiment shift over time. The findings of this study emphasize the significance of graph embedding techniques in sentiment analysis, offering valuable insights into sentiment analysis within various domains. The results suggest that graph embedding can capture intricate relationships between words, enabling a more nuanced understanding of the sentiment expressed in text data.

Embedding a surface acoustic wave sensor and venting into a metal additively manufactured injection mould tool for targeted temperature monitoring

Injection moulding (IM) tools with embedded sensors can significantly improve the process efficiency and quality of the fabricated parts through real-time monitoring and control of key process parameters such as temperature, pressure and injection speed. However, traditional mould tool fabrication technologies do not enable the fabrication of complex internal geometries. Complex internal geometries are necessary for technical applications such as sensor embedding and conformal cooling which yield benefits for process control and improved cycle times. With traditional fabrication techniques, only simple bore-based sensor embedding or external sensor attachment is possible. Externally attached sensors may compromise the functionality of the injection mould tool, with limitations such as the acquired data not reflecting the processes inside the part. The design freedom of additive manufacturing (AM) enables the fabrication of complex internal geometries, making it an excellent candidate for fabricating injection mould tools with such internal geometries. Therefore, embedding sensors in a desired location for targeted monitoring of critical mould tool regions is easier to achieve with AM. This research paper focuses on embedding a wireless surface acoustic wave (SAW) temperature sensor into an injection mould tool that was additively manufactured from stainless steel 316L. The laser powder bed fusion (L-PBF) “stop-and-go” approach was applied to embed the wireless SAW sensor. After embedding, the sensor demonstrated full functionality by recording real-time temperature data, which can further enhance process control. In addition, the concept of novel print-in-place venting design, applying the same L-PBF stop-and-go approach, for vent embedding was successfully implemented, enabling the IM of defectless parts at faster injection rates, whereas cavities designed and tested without venting resulted in parts with burn marks.

A Practical Contrastive Learning Framework for Single-Image Super-Resolution.

Contrastive learning has achieved remarkable success on various high-level tasks, but there are fewer contrastive learning-based methods proposed for low-level tasks. It is challenging to adopt vanilla contrastive learning technologies proposed for high-level visual tasks to low-level image restoration problems straightly. Because the acquired high-level global visual representations are insufficient for low-level tasks requiring rich texture and context information. In this article, we investigate the contrastive learning-based single-image super-resolution (SISR) from two perspectives: positive and negative sample construction and feature embedding. The existing methods take naive sample construction approaches (e.g., considering the low-quality input as a negative sample and the ground truth as a positive sample) and adopt a prior model (e.g., pretrained very deep convolutional networks proposed by visual geometry group (VGG) model) to obtain the feature embedding. To this end, we propose a practical contrastive learning framework for SISR (PCL-SR). We involve the generation of many informative positive and hard negative samples in frequency space. Instead of utilizing an additional pretrained network, we design a simple but effective embedding network inherited from the discriminator network, which is more task-friendly. Compared with the existing benchmark methods, we retrain them by our proposed PCL-SR framework and achieve superior performance. Extensive experiments have been conducted to show the effectiveness and technical contributions of our proposed PCL-SR thorough ablation studies. The code and resulting models will be released via https://github.com/Aitical/PCL-SISR.

Attention-based multi attribute matrix factorization for enhanced recommendation performance

In E-commerce platforms, auxiliary information containing several attributes (e.g., price, quality, and brand) can improve recommendation performance. However, previous studies used a simple combined embedding approach that did not consider the importance of each attribute embedded in the auxiliary information or only used some attributes of the auxiliary information. However, user purchasing behavior can vary significantly depending on the attributes. Thus, we propose multi attribute-based matrix factorization (MAMF), which considers the importance of each attribute embedded in various auxiliary information. MAMF obtains more representative and specific attention features of the user and item using a self-attention mechanism. By acquiring attentive representation, MAMF learns a high-level interaction precisely between users and items. To evaluate the performance of the proposed MAMF, we conducted extensive experiments using three real-world datasets from amazon.com. The experimental results show that MAMF exhibits excellent recommendation performance compared with various baseline models.

GCRec: Graph-Augmented Capsule Network for Next-Item Recommendation.

Next-item recommendation has been a hot research, which aims at predicting the next action by modeling users' behavior sequences. While previous efforts toward this task have been made in capturing complex item transition patterns, we argue that they still suffer from three limitations: 1) they have difficulty in explicitly capturing the impact of inherent order of item transition patterns; 2) only a simple and crude embedding is insufficient to yield satisfactory long-term users' representations from limited training sequences; and 3) they are incapable of dynamically integrating long-term and short-term user interest modeling. In this work, we propose a novel solution named graph-augmented capsule network (GCRec), which exploits sequential user behaviors in a more fine-grained manner. Specifically, we employ a linear graph convolution module to learn informative long-term representations of users. Furthermore, we devise a user-specific capsule module and a position-aware gating module, which are sensitive to the relative sequential order of the recently interacted items, to capture sequential patterns at union-level and point-level. To aggregate the long-term and short-term user interests as a representative vector, we design a dual-gating mechanism, which could decide the contribution ratio of each module given different contextual information. Through extensive experiments on four benchmarks, we validate the rationality and effectiveness of GCRec on the next-item recommendation task.

Entity and Entity Type Composition Representation Learning for Knowledge Graph Completion

This paper proposes a simple knowledge graph embedding (KGE) framework that considers the entity type information without additional resources. The KGE is used to obtain vector representations of entities and relations by learning structured information in triples. The obtained vectors are used to predict the missing links in a knowledge graph (KG). Although many KGs contain entity type information, most of the existing methods ignored the potential of the entity type information for the link prediction task. The proposed framework, which is called entity and entity type composition representation learning (EETCRL), obtains vector representations of both entities and entity types, which are combined and used for link prediction. Experimental results on three datasets show that the EETCRL outperforms the baseline methods in most cases. Furthermore, the results obtained from tests with different model sizes show that the proposed framework can achieve high performance even with a small model size. This paper also discusses the effect of considering information about entity types on the link prediction task by analyzing the experimental results.

Efficient degradation of thiocyanate by persulfate activation of a novel SA@Fe-Ni-C composite: Properties, mechanisms and DFT calculations

The existing microelectrolytic materials are hindered in applying advanced oxidation processes due to their poor stability and easy bonding. Therefore, ternary iron-carbon microelectrolytic microspheres (SA@Fe-Ni-C) have been prepared by a simple embedding process and used to activate persulfate (PDS) to degrade thiocyanate (SCN-). The doping of Ni not only accelerates the electron transport and promotes the effective reduction of Fe3+ but also forms the cycle system of Fe2+/Fe3+ and Ni2+/Ni3+, which ensures the high catalytic activity of the catalyst. It was found that both free radicals (SO4•-, •OH and O2•-) and non-free radicals (1O2 and electron transfer) contributed to the removal of SCN-. The DFT results showed that Fe was the leading activation site of PDS, and Ni could also promote the activation of PDS. Finally, the high stability of SA@Fe-Ni-C and its anti-interference ability were verified by 5-cycle and coexistence ion experiments. This study provides some guidance for the synthesis of new micro-electrolytic materials and the treatment of industrial wastewater by an advanced oxidation process.

Benign Structures. The Worldview of Danish National Poet, Pastor, and Politician N.F.S. Grundtvig (1783-1872)

This paper presents a study of the central Danish 19th-century figure N.F.S. Grundtvig (1783-1872) and his worldview. More precisely, by way of simple neural word embeddings we seek to plot Grundtvig’s worldview in attempt to tease out factors explaining for his cultural and religious success as a poet. We arrive at the conclusion that one factor for Grundtvig’s relative success could be found in his explicitly positive worldview fit for modern conditions.

ER-LAC: Span-Based Joint Entity and Relation Extraction Model with Multi-Level Lexical and Attention on Context Features

In recent years, joint entity–relation extraction (ERE) models have become a hot research topic in natural language processing (NLP). Several studies have proposed a span-based ERE framework, which utilizes simple span embeddings for entity and relation classification. This framework addresses the issues of overlap and error propagation that were present in previous entity–relation extraction models. However, span-based models overlook the influence of lexical information on the semantic representation of the span and fail to consider relations with a strong intrinsic connection between span pairs. To tackle these aforementioned issues, we present a new ERE model called ER-LAC (Span-based Joint Entity and Relation Extraction Model with Multi-level Lexical and Attention on Context Features). This model is designed with multi-granularity lexical features to enhance the semantic representation of spans, and a transformer classifier is employed to capture the internal connections between span pairs, thereby improving the performance of relational classification. To demonstrate the effectiveness of the proposed model, ablation experiments were conducted on the CoNLL04 dataset. The proposed model was also compared with other models on three datasets, showcasing its computational efficiency. The results indicate that the introduced lexical features and classifier enhance the F1 score for entity extraction by 0.84% to 2.04% and improve the F1 score for relationship classification by 0.96% to 2.26% when compared to the previous state-of-the-art (SOTA) model and the baseline SpERT model, respectively.

Exploring latent weight factors and global information for food-oriented cross-modal retrieval

Food-oriented cross-modal retrieval aims to retrieve relevant recipes given food images or vice versa. The modality semantic gap between recipes and food images (text and image modalities) is the main challenge. Though several studies are introduced to bridge this gap, they still suffer from two major limitations: 1) The simple embedding concatenation only can capture the simple interactions rather than complex interactions between different recipe components. 2) The image feature extraction based on convolutional neural networks only considers the local features and ignores the global features of an image, as well as the interactions between different extracted features. This paper proposes a novel method based on Latent Component Weight Factors and Global Information (LCWF-GI) to learn the robust recipe and image representations for food-oriented cross-modal retrieval. This proposed method integrates the textual embeddings of different recipe components into a compact embedding to represent the recipes with the latent component-specific weight factors. A transformer encoder is utilised to capture the intra-modality interactions and the importance of different extracted image features for enhanced image representations. Finally, the bi-directional triplet loss is further used to perform retrieval learning. Experimental results on the Recipe 1M dataset show that our LCWF-GI method achieves competent improvements.

Neighbor group structure preserving based consensus graph learning for incomplete multi-view clustering

In the area of clustering, multi-view clustering has drawn a lot of research attention by making full use of information from different views. In many practical applications, collecting complete multi-view data without missing views is sometimes expensive and impossible. Therefore, the study in incomplete multi-view clustering has become a trend in the field of clustering analysis. Graph learning-based approach is one of the most effective tools. The essence of graph learning is how to construct the affinity graph or similarity matrix, whose elements depict the similarity of the corresponding sample pairs. In this paper, we propose a new method, called Neighbor Group Structure Preserving-based Consensus Graph Learning (NGSP_CGL), to learn a high-quality consensus graph for incomplete multi-view clustering. Different from the existing graph learning-based works which only focus on the relationship between isolated sample pairs, NGSP_CGL seeks to explore the neighbor group structure corresponding to the nearest neighbor sets of sample pairs and designs a novel but simple nearest neighbor group structure embedding constraint so as to enhance the quality of consensus graph. The experimental results on several datasets demonstrate the effectiveness of NGSP_CGL.

Application of natural language processing and machine learning in prediction of deviations in the HAZOP study worksheet: A comparison of classifiers

The HAZOP (Hazard and Operability) study is one of the most well-known approaches in process hazard analysis. The HAZOP study is a systematic procedure a multidisciplinary team uses to find hazards and operability issues through brainstorming. The conventional HAZOP study requires much time, is also knowledge-intensive, and is susceptible to human mistakes. Therefore, there is a significant incentive to automate the HAZOP study. This study investigated the effectiveness of Natural Language Processing (NLP) and Machine Learning (ML) in HAZOP study automation. The case study used in this contribution is based on a conventional HAZOP study report. Initially, the causes were converted into feature vectors using NLP's simple sentence embedding technique (Bag of Words). Random oversampling was employed to manage the limited and imbalanced dataset. Finally, ML classifiers such as Decision Tree, linear Support Vector Machine, Random Forest, Logistic Regression, Gaussian Naïve Bays, and K-Nearest Neighbors were applied to predict deviations. Decision Tree outperformed other classifiers with 92% accuracy. This study's integrative approach applies even to small units and companies with limited training datasets. This is because it does not require a large training dataset.

Characterization of excited states in time-dependent density functional theory using localized molecular orbitals.

Localized molecular orbitals are often used for the analysis of chemical bonds, but they can also serve to efficiently and comprehensibly compute linear response properties. While conventional canonical molecular orbitals provide an adequate basis for the treatment of excited states, a chemically meaningful identification of the different excited-state processes is difficult within such a delocalized orbital basis. In this work, starting from an initial set of supermolecular canonical molecular orbitals, we provide a simple one-step top-down embedding procedure for generating a set of orbitals, which are localized in terms of the supermolecule but delocalized over each subsystem composing the supermolecule. Using an orbital partitioning scheme based on such sets of localized orbitals, we further present a procedure for the construction of local excitations and charge-transfer states within the linear response framework of time-dependent density functional theory (TDDFT). This procedure provides direct access to approximate diabatic excitation energies and, under the Tamm-Dancoff approximation, also their corresponding electronic couplings-quantities that are of primary importance in modeling energy transfer processes in complex biological systems. Our approach is compared with a recently developed diabatization procedure based on subsystem TDDFT using projection operators, which leads to a similar set of working equations. Although both of these methods differ in the general localization strategies adopted and the type of basis functions (Slaters vs Gaussians) employed, an overall decent agreement is obtained.

Hyper-node Relational Graph Attention Network for Multi-modal Knowledge Graph Completion

Knowledge graphs often suffer from incompleteness, and knowledge graph completion (KGC) aims at inferring the missing triplets through knowledge graph embedding from known factual triplets. However, most existing knowledge graph embedding methods only use the relational information of knowledge graph and treat the entities and relations as IDs with simple embedding layer, ignoring the multi-modal information among triplets, such as text descriptions, images, etc. In this work, we propose a novel network to incorporate different modal information with graph structure information for more precise representation of multi-modal knowledge graph, termed as hyper-node relational graph attention (HRGAT) network. In HRGAT, we use low-rank multi-modal fusion to model the intra-modality and inter-modality dynamics, which transforms the original knowledge graph to a hyper-node graph. Then, relational graph attention (RGAT) network is used, which contains relation-specific attention and entity-relation fusion operation to capture the graph structure information. Finally, we aggregate the updated multi-modal information and graph structure information to generate the final embeddings of knowledge graph to achieve KGC. By exploring multi-modal information and graph structure information, HRGAT embraces faster convergence speed and achieves the state-of-the-art for KGC on the standard datasets. Implementation code is available at https://github.com/broliang/HRGAT.