Semantic Expression Research Articles

A Non-Intrusive Automated Testing System for Internet of Vehicles App Based on Deep Learning

In the non-intrusive automated testing system for Internet of Vehicles (IoV) applications, automatic recognition of text and icons on vehicle central control screens is of paramount importance. However, the detection and recognition of content on vehicle central control screens are inherently complex. Additionally, during non-intrusive vehicle central control screen image testing, there is a deficiency of suitable datasets and detection methods. This deficiency renders information within vehicle application images difficult to be accurately extracted by the detection network. To address this problem, this study first constructs a dataset tailored for text detection and recognition on vehicle screens. This dataset encompasses a variety of vehicle central control images, enabling the generic text detection and recognition network to more effectively identify and interpret text within vehicle screens. Subsequently, this research proposes an enhanced Fully Convolutional Networks for Text Detection (FOTS) method for vehicle central control screen text detection and recognition. This method elevates the semantic expression capabilities of features by sharing vehicle central control screen text detection and recognition features. Furthermore, it improves multi-scale feature processing capabilities through the utilization of a feature transformation module. Validation through visual and quantitative experiments demonstrates that the proposed method can effectively accomplish text detection and recognition tasks on vehicle screens. This achievement bears significant implications for the field of automated testing in IoV applications.

Research on Construction and Application of Ocean Circulation Spatial–Temporal Ontology

Due to the absence of a comprehensive knowledge system for modeling ocean circulation, there is ambiguity and diversity in the semantic expression of ocean circulation. This makes it difficult to organize and share relevant spatiotemporal data effectively. This paper addresses the issue of ocean circulation by introducing ontological theory and methodology based on a comprehensive analysis of domain knowledge. Through a comprehensive analysis of the conceptual and relational characteristics of different elements, we define classes, properties, spatiotemporal relationships, and inference conditions with which to formally express concepts and relationships in ocean circulation, and finally complete the construction of ocean circulation ontology. The formal expression of the Equatorial Counter Current is presented as an example with which to validate the effectiveness of ontological construction. Additionally, an ontology-based knowledge base of ocean circulation is proposed. The construction framework is described, and several examples of knowledge base queries are also illustrated. The results demonstrate that this ontology can effectively represent the relevant knowledge within ocean circulation and provide a meaningful reference for investigating knowledge sharing and semantic integration within this field.

Gearbox Fault Diagnosis Based on Gramian Angular Field and CSKD-ResNeXt

For most rotating mechanical transmission systems, condition monitoring and fault diagnosis of the gearbox are of great significance to avoid accidents and maintain stability in operation. To strengthen the comprehensiveness of feature extraction and improve the utilization rate of fault signals to accurately identify the different operating states of a gearbox, a gearbox fault diagnosis model combining Gramian angular field (GAF) and CSKD-ResNeXt (channel shuffle and kernel decomposed ResNeXt) was proposed. The original one-dimensional vibration signal of the gearbox was converted into a two-dimensional image by GAF transformation, and the image was used as the input of the subsequent diagnosis network. To solve the problem of channel independence and incomplete information caused by group convolution, the idea of channel shuffle is introduced to enable the branches of the group convolution part to establish information exchange. In addition, to improve the semantic expression ability of the model, the convolutional kernel of the network backbone is split and replaced. The model is verified under the different working conditions of the gearbox and compared with other methods. The experimental results show that the diagnostic accuracy of the model is up to 99.75%, and the precise identification of gearbox faults is realized.

HTSE: hierarchical time-surface model for temporal knowledge graph embedding

Representation learning based on temporal knowledge graphs (TKGs) has attracted widespread interest, and temporal knowledge graph embedding (TKGE) expresses time entity and relation tokens and exhibit strong dynamics. Despite the significance of the dynamics and the persistent updates in TKGs, most studies have been devoted to static knowledge graphs. Moreover, previous temporal works ignored the semantic hierarchies observed in knowledge modelling cases, which are common in real-world applications. Inaccurate semantic expressions caused by incomplete projections might not capture complex topological structures very well. To solve this problem, a novel hierarchical time-surface embedding (HTSE) model is proposed for the representation learning of entities, relations and time. Specifically, a unified relation-oriented hierarchical space aims to distinguish relations at different semantic levels of a hierarchy, and entities can naturally reflect the corresponding hierarchy. Then, a time surface aims to enhance the temporal characteristics, and quadruples are learned through exponential mapping and tangent planes in the time surface. According to extensive experiments, HTSE can achieve remarkable performance on five benchmark datasets, outperforming baseline models for time scope prediction, temporal link prediction and hierarchical relation embedding tasks.Furthermore, the qualitative analysis is used to demonstrate the explainable strategy for hierarchical embeddings and their significance in TKGs.

Metarepresentational phenomena in Japanese and English

Abstract Contrastive studies of languages usually focus on differences in lexical items, syntactic structures, semantic expressions, collocations, and so on. In the present paper we take a cognitive pragmatic approach, assuming that metarepresentation in the sense of Sperber (2000) and Wilson (2000) offers a crucial perspective in such studies. We discuss how the speech act component of higher-level explicatures is linguistically realized in Japanese and English, focusing on sentence adverbials, ‘because’ clauses, speech act particles, reported speech, private predicates, and desiderative predicates. We conclude that in the Japanese language, information concerning the speech act component tends to be linguistically realized, while such information is not necessarily realized in English. We suggest that this cognitive pragmatic approach can be applied to other languages where higher-level explicatures are basically explicit as in Japanese or implicit as in English.

Modelling with AAS and RDF in Industry 4.0

Industry 4.0 has proposed the Asset Administration Shell (AAS) model for digital twins. This model should help to solve interoperability issues, a topic that is also addressed by the Semantic Web and its Resource Description Framework (RDF). AAS and RDF-based models have their own strengths. AAS models are easier to integrate with operational technologies in a production environment, whereas RDF-based models offer more semantic expressiveness and advanced querying. In the Horizon MAS4AI project we found that both modelling paradigms can complement each other to develop agentbased digital twins for modular production environments. In this work we propose two different approaches to bridge both modelling paradigms. First we define a set of mapping rules to generate an AAS model from a given RDF-based model, supporting model development. Secondly, we propose to use RDF-based models to generate a digital shadow of AASs to improve semantic discoverability. Preliminary results demonstrate that heterogeneity of metamodels does not exclude achieving semantic interoperability, as well as that greater functionality can be obtained compared to using both models in isolation. The solutions will be further developed in collaboration with pilot lines in the MAS4AI project.

The CANDOR corpus: Insights from a large multimodal dataset of naturalistic conversation.

People spend a substantial portion of their lives engaged in conversation, and yet, our scientific understanding of conversation is still in its infancy. Here, we introduce a large, novel, and multimodal corpus of 1656 conversations recorded in spoken English. This 7+ million word, 850-hour corpus totals more than 1 terabyte of audio, video, and transcripts, with moment-to-moment measures of vocal, facial, and semantic expression, together with an extensive survey of speakers' postconversation reflections. By taking advantage of the considerable scope of the corpus, we explore many examples of how this large-scale public dataset may catalyze future research, particularly across disciplinary boundaries, as scholars from a variety of fields appear increasingly interested in the study of conversation.

SymptomGraph: Identifying Symptom Clusters from Narrative Clinical Notes using Graph Clustering.

Patients with cancer or other chronic diseases often experience different symptoms before or after treatments. The symptoms could be physical, gastrointestinal, psychological, or cognitive (memory loss), or other types. Previous research focuses on understanding the individual symptoms or symptom correlations by collecting data through symptom surveys and using traditional statistical methods to analyze the symptoms, such as principal component analysis or factor analysis. This research proposes a computational system, SymptomGraph, to identify the symptom clusters in the narrative text of written clinical notes in electronic health records (EHR). SymptomGraph is developed to use a set of natural language processing (NLP) and artificial intelligence (AI) methods to first extract the clinician-documented symptoms from clinical notes. Then, a semantic symptom expression clustering method is used to discover a set of typical symptoms. A symptom graph is built based on the co-occurrences of the symptoms. Finally, a graph clustering algorithm is developed to discover the symptom clusters. Although SymptomGraph is applied to the narrative clinical notes, it can be adapted to analyze symptom survey data. We applied Symptom-Graph on a colorectal cancer patient with and without diabetes (Type 2) data set to detect the patient symptom clusters one year after the chemotherapy. Our results show that SymptomGraph can identify the typical symptom clusters of colorectal cancer patients' post-chemotherapy. The results also show that colorectal cancer patients with diabetes often show more symptoms of peripheral neuropathy, younger patients have mental dysfunctions of alcohol or tobacco abuse, and patients at later cancer stages show more memory loss symptoms. Our system can be generalized to extract and analyze symptom clusters of other chronic diseases or acute diseases like COVID-19.

Liturgical Translation in Europe’s Medieval East: Matters of Civilization and Textual Praxis

The paper focuses on the medieval period of the history of liturgical translation in Ukraine and Poland. In the ninth century, the evangelizing mission of SS Cyril and Methodius brought Christian translations to the east of what was then Europe. Although religious translations were not cherished in Moravia and Poland, they flourished in Bulgaria, Serbia, and Ukraine. The Roman corpus of liturgical texts existed only in Latin, and socio-political conditions stimulated the emergence of translations from Latin to Polish. The Byzantine corpus was introduced in Old Church Slavonic, which was understood by and accepted among Slavs. Different nations modified these texts according to their local visions and the necessities of their churches. Poland’s and Ukraine’s liturgical praxis under the aegis of the Roman and Byzantine Mother-Churches defined the shaping of different corpora of liturgical books, but the quality of translations was high in all Slavonic translations. The (typically) negatively judged strategy of literalism prepared a foundation for lingual experimentation in semantic expression and helped to spread the local melodies of liturgical tradition. The Church Slavonic language gave a more fruitful impetus to the development of early Ukrainian literature than the Latin language provided to early Polish literature. In fact, the Latin language restrained a similar development of early Polish literature for two centuries.

Analisis Multimodal pada Teks Iklan untuk Mengidentifikasi Aspek Ketulusan Iklan

This study aims to analyze the sincerity aspect of Indonesian and Korean advertisements through multimodal analysis. This study uses a content analysis research method using the FCB Grid Model on several products, namely fast food, tobacco, and telecommunications. The selection of ad samples was carried out based on the FCB Grid Model. The results of the study show that some products such as tobacco and fast food are included in the category of products that involve low emotions and thoughts when consumers consider these products. However, telecommunications products fall into the category of products that involve high rational thinking skills, thus requiring serious consideration from consumers. Other findings show that there are several semantic and pragmatic expressions that make consumers confused in choosing a product. The most frequent violations found in products are false expressions and explanations that lead consumers astray. In addition, other violations are expression omissions, exaggerated expressions, fictitious, and omission of important information, thus making consumers feel lost in choosing products.

Improving Biomedical Question Answering by Data Augmentation and Model Weighting.

Biomedical Question Answering aims to extract an answer to the given question from a biomedical context. Due to the strong professionalism of specific domain, it's more difficult to build large-scale datasets for specific domain question answering. Existing methods are limited by the lack of training data, and the performance is not as good as in open-domain settings, especially degrading when facing to the adversarial sample. We try to resolve the above issues. First, effective data augmentation strategies are adopted to improve the model training, including slide window, summarization and round-trip translation. Second, we propose a model weighting strategy for the final answer prediction in biomedical domain, which combines the advantage of two models, open-domain model QANet and BioBERT pre-trained in biomedical domain data. Finally, we give adversarial training to reinforce the robustness of the model. The public biomedical dataset collected from PubMed provided by BioASQ challenge is used to evaluate our approach. The results show that the model performance has been improved significantly compared to the single model and other models participated in BioASQ challenge. It can learn richer semantic expression from data augmentation and adversarial samples, which is beneficial to solve more complex question answering problems in biomedical domain.

Ventral-Dorsal Attention Capsule Network for facial expression recognition

Recent deep learning-based approaches on facial expression recognition face challenges on achieving optimal solution due to ineffective extraction of semantic expression features and difficulty in perceiving the positional relationship among facial expression features. In this paper we propose a novel framework, named Ventral-Dorsal Attention Capsule Network (VDACaps) to address the challenges. VDACaps adopts ResNet18 with a ventral channel attention and dilated spatial attention mechanism to strengthen the feature extraction. A novel attention layer containing multiple groups of ventral and dorsal attention is also designed to focus on the key features of facial expressions at the channel and spatial levels, exploring optimal sizes of receptive fields. Experiments on three well-known public expression datasets (CK+, JAFFE, and SFEW) have demonstrated that VDACaps achieves better or competitive performance on facial expression recognition against the state-of-the-art, with the accuracy of 98.98%, 98.44% and 54.07% respectively.

Automated Generation of Discrete Event Simulation Models for the Economic Assessment of Interventions for Rare Diseases Using the RaDiOS Ontology

Collection and synthesis of evidence is a key task in the development of the simulation models required for health technology assessment (HTA). The implementation of some of these models, such as discrete event simulation (DES) models, presents technical difficulties and requires higher technical skills. This work presents a method to extract the knowledge stored in an ontology, Rare Disease Ontology for Simulation (RaDiOS), to generate a DES model. RaDiOS is a domain ontology focused on collecting evidence on rare diseases for simulation models. We reviewed and enhanced the ontology to increase its semantic expressiveness. Besides, we developed a transformation tool (RaDiOS-MTT) to automatically generate DES models from the knowledge stored in the ontology. We defined a set of “synthetic” diseases, with simple natural histories, represented them in RaDiOS, and compared the results of the automatically generated simulation models with their manually created counterparts. Afterwards, we used a case study on a real intervention (newborn screening for profound biotinidase deficiency) to validate our approach. The automatically generated models for the synthetic diseases mimicked their programmatic counterparts in structure and results. The same happened to the model for profound biotinidase deficiency.

Extracting and Formalizing Criminal-law Terminology Using DEXTER

In this article we discuss the processes of terminology extraction and specialized knowledge conceptualization taking the field of criminal law as an illustrative case in point. Regarding the first process, we provide an overview of DEXTER, a tool that has proven effective in detecting specialized units from a collection of texts with minimal effort on the part of the user. Regarding the conceptualization phase, this article illustrates the conceptual definition of some representative units belonging to the field of "criminal offenders". The purpose of conceptual modeling along these lines is the inclusion of specialized units of thought into a knowledge base known as FunGramKB. The aim of this paper is to show that the combination of an extractor such as DEXTER with the semantic expressiveness of FunGramKB constitutes a solid basis for the improvement of specialized technological tools aimed at jurists, legal specialists, or other practitioners interested in legal terminology.

Facial image inpainting for big data using an effective attention mechanism and a convolutional neural network.

Big data facial image is an important identity information for people. However, facial image inpainting using existing deep learning methods has some problems such as insufficient feature mining and incomplete semantic expression, leading to output image artifacts or fuzzy textures. Therefore, it is of practical significance to study how to effectively restore an incomplete facial image. In this study, we proposed a facial image inpainting method using a multistage generative adversarial network (GAN) and the global attention mechanism (GAM). For the overall network structure, we used the GAN as the main body, then we established skip connections to optimize the network structure, and used the encoder-decoder structure to better capture the semantic information of the missing part of a facial image. A local refinement network has been proposed to enhance the local restoration effect and to weaken the influence of unsatisfactory results. Moreover, GAM is added to the network to magnify the interactive features of the global dimension while reducing information dispersion, which is more suitable for restoring human facial information. Comparative experiments on CelebA and CelebA-HQ big datasets show that the proposed method generates realistic inpainting results in both regular and irregular masks and achieves peak signal-to-noise ratio (PSNR) and structural similarity (SSIM), as well as other evaluation indicators that illustrate the performance and efficiency of the proposed model.

Agricultural Text Classification Method Based on Dynamic Fusion of Multiple Features

The traditional text classification method, which treats the values in agricultural text as characters, will lose the original semantic expression of numerical features. In order to fully mine the deep latent semantic features in agricultural text, a novel text classification method based on multivariate feature dynamic fusion is proposed. The Bi-directional Long Short Term Memory network (Bi-LSTM) model with attention mechanism was used to extract the global key semantic features of the text; the multiple windows Convolution Neural Network were used to extract the local semantic information of the text at different levels; Numerical value features containing essential semantic expression were extracted by artificial method to construct the numerical value feature vector. By introducing the attention mechanism to dynamically fuse the extracted multiple semantic features, which can further enrich the deep semantic expression of agricultural text and effectively improve the effect of agricultural text classification with phenotypic numerical type.

Деепричастие как зона риска

The article is devoted to the Russian adverbial participle and the peculiarities of its functioning. The article deals with the reasons for the difficult perception of this grammatical topic by Czech students. The Russian adverbial participle is more actively used in modern speech in comparison with the Czech, which is perceived today rather as archaism. For this reason, Czech students hardly understand the features of the functioning of Russian adverbial participle, expression of taxis semantics in combination with a predicate. The complexity of the perception of this topic is also connected, according to the author, with the discrepancy between Czech and Russian linguistic terminology. The article presents data from various Czech textbooks on the Russian language. Recommendations and practical tasks are offered that will help the teacher when working on this complex grammatical material.

Information Retrieval Method of Natural Resources Data based on Hash Algorithm

In order to improve the ability of searching and identifying information in natural resources data, this paper puts forward a method of searching information in natural resources data based on hash algorithm. Through the data center technology, the problems of information source positioning, data directory organization, data semantic definition and expression, and data entity relationship construction in natural resource data center are solved. Combined with the distribution of resource data stream, the information structure reorganization and data encryption in natural resource data center are realized by using hash algorithm, and the parameters of information quality control model in natural resource data center are established. Through natural resource data governance and semantic reconstruction, the characteristics detection and redundancy arrangement of information data in natural resource data center are realized by standardizing data collection rules, and they are stored in the intermediate database. Through data governance rules, the information in the natural resources data is structured and managed, and stored in the publishing library. Through all kinds of data processing tools, all kinds of data are processed, cleaned and reconstructed, and through Hash algorithm and data aggregation processing, information detection in natural resources data is realized. The simulation results show that the precision rate of natural resource data retrieval by this method is high.

Knowledge graph completion method for hydraulic engineering coupled with spatial transformation and an attention mechanism.

In response to the limited capability of extracting semantic information in knowledge graph completion methods, we propose a model that combines spatial transformation and attention mechanisms (STAM) for knowledge graph embedding. Firstly, spatial transformation is applied to reorganize entity embeddings and relation embeddings, enabling increased interaction between entities and relations while preserving shallow information. Next, a two-dimensional convolutional neural network is utilized to extract complex latent information among entity relations. Simultaneously, a multi-scale channel attention mechanism is constructed to enhance the capture of local detailed features and global semantic features. Finally, the surface-level shallow information and latent information are fused to obtain feature embeddings with richer semantic expression. The link prediction results on the public datasets WN18RR, FB15K237 and Kinship demonstrate that STAM achieved improvements of 8.8%, 10.5% and 6.9% in the mean reciprocal rank (MRR) evaluation metric compared to ConvE, for the respective datasets. Furthermore, in the link prediction experiments on the hydraulic engineering dataset, STAM achieves better experimental results in terms of MRR, Hits@1, Hits@3 and Hits@10 evaluation metrics, demonstrating the effectiveness of the model in the task of hydraulic engineering knowledge graph completion.

РАЗВИТИЕ СЛУХОВОГО ВОСПРИЯТИЯ МУЗЫКАНТОВ-ИНСТРУМЕНТАЛИСТОВ С НАРУШЕНИЯМИ ЗРЕНИЯ

The article focuses on the auditory perception of students with profound visual impairments. The category of "perception" is considered in psychology as a process of reflection in the consciousness of an integral sensual image of an object or phenomenon. In the musical-aural perception of musicians with visual impairments, the subjective image of an object, phenomenon or process directly affects the auditory analyzer, and in a latent form the system of motor and tactile analyzers. Musical sound is understood as a pitch or noise sound, carrying the function of a means of a specific semantic expression. The auditory sensations appear due to the effects of periodic oscillations of sound waves on the auditory receptor. The shape of a sound wave's oscillations is reflected in a specific quality — the timbre of sound. When playing a musical instrument, the performer extracts a sound with a certain pitch, dynamics, timbre and duration. The article emphasizes that the development of musical ear of visually impaired musicians, as the ability to perceive and represent musical images, are inextricably linked to the images of memory. It is important that perceptual skills at the level of sensations and auditory perception are formed and developed under the influence of living conditions, training and the requirements of musical and practical activity.