Semantic Pattern Detection in COVID-19 Using Contextual Clustering and Intelligent Topic Modeling

The Covid-19 pandemic is the deadliest outbreak in our living memory. So, it is need of hour, to prepare the world with strategies to prevent and control the impact of the epidemics. In this paper, a novel semantic pattern detection approach in the Covid-19 literature using contextual clustering and intelligent topic modeling is presented. For contextual clustering, three level weights at term level, document level, and corpus level are used with latent semantic analysis. For intelligent topic modeling, semantic collocations using pointwise mutual information(PMI) and log frequency biased mutual dependency(LBMD) are selected and latent dirichlet allocation is applied. Contextual clustering with latent semantic analysis presents semantic spaces with high correlation in terms at corpus level. Through intelligent topic modeling, topics are improved in the form of lower perplexity and highly coherent. This research helps in finding the knowledge gap in the area of Covid-19 research and offered direction for future research.

Semantic Pattern Detection in Covid-19 using Contextual Clustering and Intelligent Topic Modeling

The Covid-19 pandemic is the deadliest outbreak in our living memory. So, it is need of hour, to prepare the world with strategies to prevent and control the impact of the epidemics. In this paper, a novel semantic pattern detection approach in the Covid-19 literature using contextual clustering and intelligent topic modeling is presented. For contextual clustering, three level weights at term level, document level, and corpus level are used with latent semantic analysis. For intelligent topic modeling, semantic collocations using pointwise mutual information(PMI) and log frequency biased mutual dependency(LBMD) are selected and latent dirichlet allocation is applied. Contextual clustering with latent semantic analysis presents semantic spaces with high correlation in terms at corpus level. Through intelligent topic modeling, topics are improved in the form of lower perplexity and highly coherent. This research helps in finding the knowledge gap in the area of Covid-19 research and offered direction for future research.

A Co-Embedding Model with Variational Auto-Encoder for Knowledge Graphs

Knowledge graph (KG) embedding has been widely studied to obtain low-dimensional representations for entities and relations. It serves as the basis for downstream tasks, such as KG completion and relation extraction. Traditional KG embedding techniques usually represent entities/relations as vectors or tensors, mapping them in different semantic spaces and ignoring the uncertainties. The affinities between entities and relations are ambiguous when they are not embedded in the same latent spaces. In this paper, we incorporate a co-embedding model for KG embedding, which learns low-dimensional representations of both entities and relations in the same semantic space. To address the issue of neglecting uncertainty for KG components, we propose a variational auto-encoder that represents KG components as Gaussian distributions. In addition, compared with previous methods, our method has the advantages of high quality and interpretability. Our experimental results on several benchmark datasets demonstrate our model’s superiority over the state-of-the-art baselines.

Multipath Cross Graph Convolution for Knowledge Representation Learning

In the past, most of the entity prediction methods based on embedding lacked the training of local core relationships, resulting in a deficiency in the end-to-end training. Aiming at this problem, we propose an end-to-end knowledge graph embedding representation method. It involves local graph convolution and global cross learning in this paper, which is called the TransC graph convolutional network (TransC-GCN). Firstly, multiple local semantic spaces are divided according to the largest neighbor. Secondly, a translation model is used to map the local entities and relationships into a cross vector, which serves as the input of GCN. Thirdly, through training and learning of local semantic relations, the best entities and strongest relations are found. The optimal entity relation combination ranking is obtained by evaluating the posterior loss function based on the mutual information entropy. Experiments show that this paper can obtain local entity feature information more accurately through the convolution operation of the lightweight convolutional neural network. Also, the maximum pooling operation helps to grasp the strong signal on the local feature, thereby avoiding the globally redundant feature. Compared with the mainstream triad prediction baseline model, the proposed algorithm can effectively reduce the computational complexity while achieving strong robustness. It also increases the inference accuracy of entities and relations by 8.1% and 4.4%, respectively. In short, this new method can not only effectively extract the local nodes and relationship features of the knowledge graph but also satisfy the requirements of multilayer penetration and relationship derivation of a knowledge graph.

Zero-Shot Learning for IMU-Based Activity Recognition Using Video Embeddings

The Activity Recognition Chain generally precludes the challenging scenario of recognizing new activities that were unseen during training, despite this scenario being a practical and common one as users perform diverse activities at test time. A few prior works have adopted zero-shot learning methods for IMU-based activity recognition, which work by relating seen and unseen classes through an auxiliary semantic space. However, these methods usually rely heavily on a hand-crafted attribute space which is costly to define, or a learnt semantic space based on word embedding, which lacks motion-related information crucial for distinguishing IMU features. Instead, we propose a strategy to exploit videos of human activities to construct an informative semantic space. With our approach, knowledge from state-of-the-art video action recognition models is encoded into video embeddings to relate seen and unseen activity classes. Experiments on three public datasets find that our approach outperforms other learnt semantic spaces, with an additional desirable feature of scalability, as recognition performance is seen to scale with the amount of data used. More generally, our results indicate that exploiting information from the video domain for IMU-based tasks is a promising direction, with tangible returns in a zero-shot learning scenario.

The Heaven and Earth Concepts in Women Beauty Comparison Phraseological Expressions of Different Cultures

Research relevance in this article is the study of concepts Heaven and Earth, through phraseological units belonging to carriers of different-structured languages, which reflect female beauty, determine their universal and national-unique characteristics. Research purpose is to study and analyze the features of stable expressions about the beauty of women associated with the concept Heaven and Earth in different cultures. Research methods: we tried to understand and identify how the beauty of women is reflected in the stable expressions of different peoples, where the culture and assessment of female beauty is preserved in comparison with heavenly bodies and with all earthly beauty on our planet. Research results can be used: in the practice of teaching the course of comparative typology, lexicology of the Russian, Kyrgyz and English languages, as well as in teaching Russian, Kyrgyz and English on a linguacultural basis, both in foreign and national audiences. Conclusions: the semantic spaces of different languages made it possible to compare them with the subsequent allocation of universal universals, the national specifics of the concept sphere, since the concept sphere and the semantic space of a language have a common nature, since they are mental entities.

REPRESENTATION OF A DIFFICULT SITUATION BY THE SUBJECT: FEATURES OF FORMAL AND CONCEPTUAL INDICATORS

The article analyzes formal and conceptual indicators of the representation of a difficult situation. There was carried out а theoretical analysis of the representation of a difficult situation. Fundamental methodological provisions of our research are: the main postulates of the theory of mental reflection (B. G. Ananiev, B. F. Lomov, S. L. Rubinstein, B. M. Teplov, etc.); theses of experimental psychosemantics on semantic units and methods of analysis of subjective semantic spaces (V. P. Serkin, V. A. Skleinis, etc.); provisions on the psychological validity of formal and conceptual indicators of psychological representation (V. V. Znakov, A. B. Kupreichenko, G. V. Shukova); the provisions of the approach on the cognitive assessment of a difficult life situation (E. V. Bityutskaya). The purpose of the article is to determine the indicators of representation of a difficult situation and to analyze the severity of these indicators. The modern situation in psychology demonstrates the activity of addressing the interpretation of the phenomenon of a difficult situation, which is especially significant in the complex, constantly changing conditions of the subject's vital activities. In the broadest sense, representation is understood as a cognitive procedure that enables the subject to construct and model both reality as a whole and its individual elements. It is worth mentioning that there are many semantic shades in the definition of the concept "difficult situation", since the researchers actualize different components of the construct "difficult". According to the most general universal interpretation, "difficult" is defined as "requiring a lot of work, effort, and intensity". On the basis of empirical material collected in the structural unit of the railway, the article analyzes the features of formal and conceptual indicators of the representation of a difficult situation. The article contains the results of the empirical research. 300 respondents took part in the research. There were used the following methodological tools : associative experiment, method of semantic universals, content analysis, graphical representation of representation and a technique aimed at obtaining data on the subjective assessment of a difficult situation. The data obtained allow us to conclude that the formal indicators of the representation are represented by size and structure (represented by the scales "simplicity-complexity" and "core-periphery"); conceptual indicators of representation are represented by a qualitative composition of elements (technological, emotional, communicative components) and a subjective assessment of a difficult situation (a general assessment of the difficulty of the situation and the adequacy of the subject's resources with the requirements of the situation).

Residual Self-Calibration and Self-Attention Aggregation Network for Crop Disease Recognition

The correct diagnosis and recognition of crop diseases play an important role in ensuring crop yields and preventing food safety. The existing methods for crop disease recognition mainly focus on accuracy while ignoring the algorithm’s robustness. In practice, the acquired images are often accompanied by various noises. These noises lead to a huge challenge for improving the robustness and accuracy of the recognition algorithm. In order to solve this problem, this paper proposes a residual self-calibration and self-attention aggregation network (RCAA-Net) for crop disease recognition in actual scenarios. The proposed RCAA-Net is composed of three main modules: (1) multi-scale residual module, (2) feedback self-calibration module, and (3) self-attention aggregation module. Specifically, the multi-scale residual module is designed to learn multi-scale features and provide both global and local information for the appearance of the disease to improve the performance of the model. The feedback self-calibration is proposed to improve the robustness of the model by suppressing the background noise in the original deep features. The self-attention aggregation module is introduced to further improve the robustness and accuracy of the model by capturing multi-scale information in different semantic spaces. The experimental results on the challenging 2018ai_challenger crop disease recognition dataset show that the proposed RCAA-Net achieves state-of-the-art performance on robustness and accuracy for crop disease recognition in actual scenarios.

IMAGE OF A MIGRANT IN THE POPULATION OF THE BORDER REGION OF RUSSIA'S NOTIONS

The issues of adaptation and integration of migrants are one of the main directions of the sociology of migration. The success of a migrant's adaptation depends not only on himself, but also on the local community. Each of them faces the consequences and difficulties of migration to varying degrees. And the actions of each of the parties determine the success of migration processes. The article examines the issue of the adaptive potential of the host community through the study of migrant images in the perception of the population of the border region. The paper presents the results of a psychosemantic experiment conducted in the Altai Territory in 2020-2021 (n = 85). The average age of the respondents is 31.4 years. The image of a migrant in the perceptions of the population is explored through the role positions "migrant", "migrant from the CIS countries", "labor migrant". As scales, 28 pairs of categories were used, describing persons with different social activity. Based on the analysis of average values and factor analysis, the semantic spaces for assessing the mental representations of the "image of a migrant", "the image of a migrant from the CIS countries", "the image of a labor migrant" were built. There is a negative perception of the images of “migrant” and “migrant from the CIS countries”. They are characterized by such categories as "hardy", "alien", "distant", "impatient", "cunning", "arouses hostility", "warlike". A labor migrant is defined by the population as honest, responsible, hardworking, religious, sociable, easy-going and ready to help. The image of a “labor migrant” inspires more confidence in the population and is perceived more positively than the images of a “migrant” and “a migrant from the CIS countries”.