Semantic Blocks Research Articles

FARN: Fetal Anatomy Reasoning Network for Detection With Global Context Semantic and Local Topology Relationship.

Accurate recognition of fetal anatomical structure is a pivotal task in ultrasound (US) image analysis. Sonographers naturally apply anatomical knowledge and clinical expertise to recognizing key anatomical structures in complex US images. However, mainstream object detection approaches usually treat each structure recognition separately, overlooking anatomical correlations between different structures in fetal US planes. In this work, we propose a Fetal Anatomy Reasoning Network (FARN) that incorporates two kinds of relationship forms: a global context semantic block summarized with visual similarity and a local topology relationship block depicting structural pair constraints. Specifically, by designing the Adaptive Relation Graph Reasoning (ARGR) module, anatomical structures are treated as nodes, with two kinds of relationships between nodes modeled as edges. The flexibility of the model is enhanced by constructing the adaptive relationship graph in a data-driven way, enabling adaptation to various data samples without the need for predefined additional constraints. The feature representation is further refined by aggregating the outputs of the ARGR module. Comprehensive experimental results demonstrate that FARN achieves promising performance in detecting 37 anatomical structures across key US planes in tertiary obstetric screening. FARN effectively utilizes key relationships to improve detection performance, demonstrates robustness to small-scale, similar, and indistinct structures, and avoids some detection errors that deviate from anatomical norms. Overall, our study serves as a resource for developing efficient and concise approaches to model inter-anatomy relationships.

Dual-TranSpeckle: Dual-pathway transformer based encoder-decoder network for medical ultrasound image despeckling

The majority of existing deep learning-based image denoising algorithms mainly focus on processing the overall image features, ignoring the fine differences between the semantic and pixel features. Hence, we propose Dual-TranSpeckle (DTS), a medical ultrasound image despeckling network built on a dual-path Transformer. The DTS introduces two different paths, named “semantic path” and “pixel path,” to facilitate the parallel transfer of feature information within the image. The semantic path passes a global view of the input semantic features, and the image features are passed through a Semantic Block to extract global semantic information from pixel-level features. The pixel path is employed to transmit finer-grained pixel features. Within the dual-path network framework, two essential modules, namely Dual Block and Merge Block, are designed. These leverage the Transformer architecture during the encoding and decoding stages. The Dual Block module facilitates information interaction between the semantic and pixel features by considering the interdependencies across both paths. Meanwhile, the Merge Block module enables parallel transfer of feature information by merging the dual path features, thereby facilitating the self-attention calculations for the overall feature representation. Our DTS is extensively evaluated on two public datasets and one private dataset. The DTS network demonstrates significant enhancements in quantitative evaluation results in terms of peak signal-to-noise ratio (PSNR), structural similarity (SSIM), feature similarity (FSIM), and naturalness image quality evaluator (NIQE). Furthermore, our qualitative analysis confirms that the DTS has significant improvements in despeckling performance, effectively suppressing speckle noise while preserving essential image structures.

Translation and Equivalence: An Argumentative Approach

Purpose: This article aims at establishing a dialogue between the Theory of Semantic Blocks (TSB), developed by Ducrot and Carel, and translation theories (the notions of equivalence, skopo, and translators’ role), seeking a possible strategy for solving difficult situations when translating humoristic texts that have polysemy or homonymy relations.
 Methodology: The research methodology involved a literature review, and in the end, a humorous statement containing polysemy was chosen to illustrate how the application of TSB would work in a translation. In this paper, we do not aim to choose the most correct approach but try to match the positive aspects of each one with TSB in order to find strategies that might help translators.
 Findings: We understood that establishing argumentative meaning for enunciates enables a more proper selection of linguistic entities because it is done based on an argumentative equivalence. This study is ongoing. Given its relatively lengthy nature, it may not be applicable in situations requiring simultaneous translation.
 Unique Contribution to Theory, Practice and Policy: However, further investigation could explore its use as a means of assessing the adequacy of written translations. A more comprehensive study is also essential to discover additional ways of streamlining the translator's tasks and to determine if TSB can address various translation challenges across different textual genres. In conclusion, studies like this play a crucial role in expanding the range of possibilities to enhance a translator's work. This enables them to navigate between languages and cultures more confidently, linguistically supported, without the need to remain invisible to be recognized as proficient professionals.

Содержательно-структурные особенности эпических произведений российских хори-бурят

This article examines the plot-compositional structure of uligers, epics of Hori Buryats. The composition of Hori Buryat uligers is centered on a primary epic core that forms the basis of the plot for each text. The events in these texts are organized into semantic blocks, each comprising motifs or sets of motifs. The content-structural features of the epics are characterized by analyzing the sources from the eastern regions of Ethnic Buryatia. Emphasis is placed on the local peculiarity of uligers of Hori Buryats of Russia, with fewer records of the Eastern Buryat texts compared to the Western Buryat epics. An attempt is made to identify the plot-motif units used in the Hori uligers in the context of the main narrative core. These are the search for a betrothed or kidnapped wife and the process of matchmaking or passing repeated tests. Systematizing and describing the plots and motifs of the Hori Buryat uligers required the identification of the concept of “epic motif.” According to the theoretical judgments of scholars, a motif is the smallest narrative unit that serves a specific function in the plot development and has its own semantics within the implementation of the narrative outline of the epic tradition. The plot is formed by combining different motifs. The plot is defined as a certain model combining different motifs.

Retracted: English Characteristic Semantic Block Processing Based on English-Chinese Machine Translation

Retracted: English Characteristic Semantic Block Processing Based on English-Chinese Machine Translation

Efficient Training of Large-Scale Industrial Fault Diagnostic Models through Federated Opportunistic Block Dropout

Artificial intelligence (AI)-empowered industrial fault diagnostics is important in ensuring the safe operation of industrial applications. Since complex industrial systems often involve multiple industrial plants (possibly belonging to different companies or subsidiaries) with sensitive data collected and stored in a distributed manner, collaborative fault diagnostic model training often needs to leverage federated learning (FL). As the scale of the industrial fault diagnostic models are often large and communication channels in such systems are often not exclusively used for FL model training, existing deployed FL model training frameworks cannot train such models efficiently across multiple institutions. In this paper, we report our experience developing and deploying the Federated Opportunistic Block Dropout (FedOBD) approach for industrial fault diagnostic model training. By decomposing large-scale models into semantic blocks and enabling FL participants to opportunistically upload selected important blocks in a quantized manner, it significantly reduces the communication overhead while maintaining model performance. Since its deployment in ENN Group in February 2022, FedOBD has served two coal chemical plants across two cities in China to build industrial fault prediction models. It helped the company reduce the training communication overhead by over 70% compared to its previous AI Engine, while maintaining model performance at over 85% test F1 score. To our knowledge, it is the first successfully deployed dropout-based FL approach.

ReGR: Relation-aware graph reasoning framework for video question answering

As one of the challenging cross-modal tasks, video question answering (VideoQA) aims to fully understand video content and answer relevant questions. The mainstream approach in current work involves extracting appearance and motion features to characterize videos separately, ignoring the interactions between them and with the question. Furthermore, some crucial semantic interaction details between visual objects are overlooked. In this paper, we propose a novel Relation-aware Graph Reasoning (ReGR) framework for video question answering, which first combines appearance–motion and location–semantic multiple interaction relations between visual objects. For the interaction between appearance and motion, we design the Appearance–Motion Block, which is question-guided to capture the interdependence between appearance and motion. For the interaction between location and semantics, we design the Location–Semantic Block, which utilizes the constructed Multi-Relation Graph Attention Network to capture the geometric position and semantic interaction between objects. Finally, the question-driven Multi-Visual Fusion captures more accurate multimodal representations. Extensive experiments on three benchmark datasets, TGIF-QA, MSVD-QA, and MSRVTT-QA, demonstrate the superiority of our proposed ReGR compared to the state-of-the-art methods.

The Attachment of the Neighbor and the Accusative Objection in the Holy Qur'an - a Semantic Grammatical Study

This research aims to comprehensively monitor the cases of attachment (the neighbor, the traitor, and the adverb) in the Holy Qur'an, exclude the unproblematic attachments as an abbreviation of the research material, present the abstaining attachments as a sign in the views of the commentators by analyzing them grammatically and semantically, and to determine the grammatical attachments of the neighbor and the drawer that are authenticated by the sayings of the grammarians, abstaining semantically while providing valid alternatives.This research is based on a comprehensive monitoring of the cases of attachment of the two types of semi-sentence (the neighbor, the traitor and the adverb) in the Noble Qur'an, and then excludes the unresolved attachments as a shortcut to the subject of the research. The accusative and the adverb which are authenticated by the sayings of grammarians by refraining from semantics, while providing valid alternatives for them.
 Keywords: neighbor and drawer, semi-sentence - Attached, - semantic block, - the meaning

A Slope Structural Plane Extraction Method Based on Geo-AINet Ensemble Learning with UAV Images

In the construction of large-scale water conservancy and hydropower transportation projects, the rock mass structural information is often used to evaluate and analyze various engineering geological problems such as high and steep slope stability, dam abutment stability, and natural rock landslide geological disasters. The complex shape and extremely irregular distribution of the structural planes make it challenging to identify and extract automatically. This study proposes a method for extracting structural planes from UAV images based on Geo-AINet ensemble learning. The UAV images of the slope are first used to generate a dense point cloud through a pipeline of SfM and PMVS; then, the multiple geological semantics, including color and texture from the image and local geological occurrence and surface roughness from the dense point cloud, are integrated with Geo-AINet for ensemble learning to obtain a set of semantic blocks; finally, the accurate extraction of structural planes is achieved through a multi-semantic hierarchical clustering strategy. Experimental results show that the structural planes extracted by the proposed method perform better integrity and edge adherence than that extracted by the AINet algorithm. In comparison with the results from the laser point cloud, the geological occurrence differences are less than three degrees, which proves the reliability of the results. This study widens the scope for surveying and mapping using remote sensing in engineering geological applications.

BSNet: Boundary-semantic-fusion network for farmland parcel mapping in high-resolution satellite images

Mapping farmland parcels using satellite images is essential for agricultural remote sensing applications. Loss of spatial details and positioning of parcel boundaries are the main challenges in available deep convolution network (DCN) models. This study developed a boundary-semantic-fusion DCN (BSNet) model for delineating farmland parcels from high-resolution satellite images. Central to this method is the combination between shallow-level boundary features with accurate spatial positioning and deep-level semantic features for category identification. First, a general deep convolution framework consisting of boundary, semantic and fusion blocks was implemented for farmland parcel mapping. Second, a particular serial structure with a detaching operation for linking the boundary and semantic blocks was explored to maintain the spatial details and fine-scale boundaries in feature learning. Third, an encoder-decoder fusion block was developed to integrate the boundary and semantic features to produce the final parcel maps. We validated the proposed model with different high-resolution satellite images in two study areas. The experimental results, with improvements greater than 4% in the F1 score and 6% in the IoU score relative to other comparative methods, illustrate the effectiveness of the proposed model for fine-scale farmland parcel mapping.

СОВЕТСКИЕ ИКОНЫ: ТЕМАТИЧЕСКИЙ ОПРОСНИК ДЛЯ ИССЛЕДОВАНИЯ ЛОКАЛЬНЫХ ТРАДИЦИЙ

The article presents a questionnaire related to “Soviet icons”, that is, folezhny (foil) icons (in image cases) crafted in the Soviet years. The questionnaire is preceded by an introduction with a brief characterization of the social, material and technological aspects of the craft of the Soviet icon as a unique phenomenon of religious life in the Soviet decades. The authors give references to existing research on that issue. The published methodology provides a framework for conducting interviews on Soviet icons in any region. The questionnaire consists of four semantic blocks: 1) the name, morphology, types of foil icons; 2) the creators of foil icons; 3) foil icons in the Soviet years; 4) foil icons in the post-Soviet era. In addition, the questionnaire provides a basis for collecting information about modern moderators who deal in own, collect or dispose Soviet icons, and about the semiotic ideologies that determine their assessments and actions. The proposed sequence of questions reflects the desired course of the conversation and takes into account logical links between topics. The article is recommended as a practical guide for expedition work and research of local traditions of Soviet icons in different regions of Russia and in other post-Soviet countries where Orthodox traditions were maintained during the Soviet era

MEMOIRS OF V. MATTIS AS A SOURCE ON THE HISTORY OF MENNONITES OF THE ALEKSANDRTAL VOLOST OF THE SAMARA GOVERNORATE

This study analyzes unpublished memoirs by Wilhelm Mattis «The History of the Formation of the Mennonite Colony Alt-Samara (Old Samara)». The article presents the circumstances of writing this memoirs, it's semantic blocks with a brief description. The author concluded that «The History» has a high scientific value both on the problem of studying the history of the Mennonites of Aleksandrtal, and on the history of the Samara region.

Digital Technologies as a Means of Improving the Efficiency of Higher Education

Today, the practical application of digitalisation in higher education and finding ways to optimize the use of digital technologies to improve the management of the educational process is a relevant issue for the modern research paradigm. This research aims to study the unique ways in which digital technologies are utilised in higher education and create a conceptual framework for their adoption to enhance the efficiency of the educational process. The study applied the method of expert assessments using a semi-structured questionnaire, with two groups of respondents acting as experts. The questionnaire responses were evaluated using the Likert scale, and the Student’s t-test was used for statistical analysis of the research results. Both students and teachers recognise blended learning as the most effective method for organising the educational process since it combines traditional distance learning with the implementation of digital educational technologies. The respondents recognised the communicational aspect to be the most crucial advantage of digitalisation. The study findings are summarised into a conceptual model of digitalisation in higher education, comprising interconnected semantic blocks of generation, accumulation, and management of educational information.

Личностная зрелость: модель исследования в контексте событийного подхода

Introduction. The problem of personal maturity, its criteria and mechanisms of achievement, acts as one of the significant and urgent problems in modern psychological science. A large number of scientific papers are devoted to the interpretation and definition of this concept, the search for its content and structural elements. Theoretical analysis. Based on the systematization of theoretical material, the author builds a model for the analysis of personal maturity (in the context of the event approach). In this model, there are blocks that can act as parameters of personal maturity: event block, reflexive block, semantic block, behavioral block. Conclusion. Conclusions are drawn that significant personality events can act as possible initiators of the formation of personal maturity, and are defined in the event block of the study. The mechanisms of experiencing a crisis event, forming unity with reflexive processes, constitute (a reflexive block of research). Comprehension of the situation, construction of new meanings (semantic block of research). Adaptation to new conditions, situational activity (behavioral research unit). The author believes that the data obtained can be used for a more detailed analysis of personal maturity, the conditions for its actualization, as well as for the construction of models of empirical research of personal maturity.

A semantic blocks model for human activity prediction in smart environments using time-windowed contextual data

Complex human activity prediction is a difficult problem for computer science. Simple behaviours can be mapped to sequence prediction algorithms with good results; however, real-world examples of activity are generally stochastic and much more computationally difficult to infer. One method for solving this problem is to utilise contextual data—clues surrounding the actual activity—to decipher what is about to happen next; in much the same way humans do. In this paper, we present the semantic blocks model (SBM), a method for using contextual data to infer the next activity in a smart home environment by augmenting the inference with contextual data, but also segmenting it into time-windowed sections of activity—or semantic blocks. Our proof-of-concept produces 74.55% accuracy on the CASAS smart home dataset, an increase on the comparable CRAFFT algorithm which produces 66.91% on the same dataset. We detail how our experimental prototype works using intersecting contextual data, and explore opportunities for further work by the research community.

Peculiarities of Virtual Internationalzation of Novosibirsk Region Higher Education Institutions in the Context of Modern Agenda

The article foregrounds the issue of the development of virtual internationalization on the example of universities in Novosibirsk region. The article focuses on the key trends in the export of Russian higher education. The purpose of the article is to analyze the websites of the universities in Novosibirsk region as a key mechanism for recruiting international students and to develop recommendations for their modernization. Methodology. The study was conducted on the basis of the methodology of the RIAC report “Digital Internationalization: English-language Internet Resources of Russian Universities” (2015), which implies the identification of 10 target groups of potential audience of a university website and 16 semantic blocks filled with specific questions which allow to assess the degree of virtual internationalization. The binary evaluation system (yes/no) enables the formation of a cumulative score and conducting a comparative analysis of universities in the region both in terms of the overall rating and within the semantic blocks. The result of the implementation of this methodology is an analytical report on the features of the virtual internationalization of universities in modern conditions on the example of the Novosibirsk region. The developed recommendations are useful both for the international departments of universities and their administration, and for the regional ministries of education, since they might serve as a basis for developing a strategy for improving the websites of universities and thus favoring the export of higher education in the Russian Federation coming not only from capital universities, but also in the regions. In conclusion, it is admitted that self-positioning of a university in a virtual environment in the context of education export cannot be overestimated, since today the success in increasing the international students’ inflow to the regions of the Russian Federation depends on the virtual internationalization.

Технологический суверенитет и подготовка будущей технической интеллигенции

One of conditions for the formation and strengthening of technological sovereignty of our country is the high-quality training of engineers and IT-specialists as representatives of the technical intelligentsia. The article, based on a signal survey of technical university students studying in the specialty «Applied Mathematics», analyzes the problems of artificial intelligence, which is part of the need to ensure technological sovereignty. The study presents discussions on such semantic blocks as engineering and scientific activities, impact on the economy, legal support for the development of artificial intellectual systems and social and humanitarian responsibility.

Task-Oriented Image Transmission for Scene Classification in Unmanned Aerial Systems

The vigorous developments of the Internet of Things make it possible to extend its computing and storage capabilities to computing tasks in the aerial system with the collaboration of cloud and edge, especially for artificial intelligence (AI) tasks based on deep learning (DL). Collecting a large amount of image/video data, unmanned aerial vehicles (UAVs) can only hand over intelligent analysis tasks to the back-end mobile edge computing (MEC) server due to their limited storage and computing capabilities. How to efficiently transmit the most correlated information for the AI model is a challenging topic. Inspired by task-oriented communication in recent years, we propose a new aerial image transmission paradigm for the scene classification task. A lightweight model is developed on the front-end UAV for semantic block transmission with the perception of images and channel states. To achieve the tradeoff between transmission latency and classification accuracy, deep reinforcement learning (DRL) is applied to explore the semantic blocks which have the greatest contribution to the back-end classifier under various channel states. Experimental results show that the proposed method can significantly improve classification accuracy by more than 4% under the same conditions, compared to other semantic saliency learning methods.

FUNCTIONS OF INAUGURAL SPEECH IN UKRAINIAN POLITICAL DISCOURSE

The article is devoted to defining the main functions of inaugural speech as a speech genre of Ukrainian political discourse. The functions – integrative, inspiring, declarative and performative – are distinguished. The function of integration is realized as calls to unite the Ukrainian people and appeal to the people as a single community. The inspiring function is to form state values ​​and calls for a better future that has a long historical tradition. In the inaugural speech, this function is subordinated to the integral structural and compositional element, which is quite a large semantic block. Inspirational function is manifested in Ukrainian in two forms: praise of historical events and traditions and criticism of the experience of predecessors. The declarative function is to formulate the principles on which the new president will work, ie the program part of the inaugural speech is subordinated to it. The performative function indicates that the new president swears allegiance to the people, swears to take care of the country and acts as the leader of the state.

English Characteristic Semantic Block Processing Based on English-Chinese Machine Translation

In order to solve the problem that the current English-Chinese machine translation software cannot understand the characteristics of English sentences repeatedly, a semantic block processing method for English-Chinese machine translation was proposed. In the process of the English sentence comprehension, English semantic block, which played an important role, was analyzed in detail. On the basis of this, the core content and characteristics of English semantic block were discussed. And with the help of the corresponding processing algorithms, taking verbs and business English as the research object, three kinds of semantic models were summarized. A lexical chunk database model based on English characteristic semantic block processing was proposed. The open test results showed that the matching success rate of the model for the semantic pattern database was about 90%.