Categories Of Features Research Articles

A sequence-based machine learning model for predicting antigenic distance for H3N2 influenza virus.

Seasonal influenza A H3N2 viruses are constantly changing, reducing the effectiveness of existing vaccines. As a result, the World Health Organization (WHO) needs to frequently update the vaccine strains to match the antigenicity of emerged H3N2 variants. Traditional assessments of antigenicity rely on serological methods, which are both labor-intensive and time-consuming. Although numerous computational models aim to simplify antigenicity determination, they either lack a robust quantitative linkage between antigenicity and viral sequences or focus restrictively on selected features. Here, we propose a novel computational method to predict antigenic distances using multiple features, including not only viral sequence attributes but also integrating four distinct categories of features that significantly affect viral antigenicity in sequences. This method exhibits low error in virus antigenicity prediction and achieves superior accuracy in discerning antigenic drift. Utilizing this method, we investigated the evolution process of the H3N2 influenza viruses and identified a total of 21 major antigenic clusters from 1968 to 2022. Interestingly, our predicted antigenic map aligns closely with the antigenic map generated with serological data. Thus, our method is a promising tool for detecting antigenic variants and guiding the selection of vaccine candidates.

Utilizing a single-temporal full polarimetric Gaofen-3 SAR image to map coseismic landslide inventory following the 2017 Mw 7.0 Jiuzhaigou earthquake (China)

On August 8, 2017, a magnitude 7.0 earthquake struck Jiuzhaigou County in Sichuan Province, triggering numerous coseismic landslides. The prompt identification of these landslides is imperative for emergency rescue efforts and post-earthquake hazard assessments. Optical satellite and unmanned aerial vehicle (UAV) images are often obstructed by cloud cover and fog following earthquakes. In contrast, polarimetric synthetic aperture radar (PolSAR), unaffected by adverse weather conditions, emerges as an indispensable tool. However, the utilization of spaceborne single-temporal SAR for mapping the inventory of coseismic landslides is infrequent and encounters constraints due to several limitations. In this study, we analyzed the amplitude feature and polarimetric decomposition of multiple ground categories in a full PolSAR image, and proposed an automated method to accurately identify coseismic landslides using a single-temporal full PolSAR image. The coseismic landslide inventory following the Jiuzhaigou Earthquake was mapped and validated using high-resolution UAV images. Detailed analysis was conducted to identify error sources leading to omissions and false positives. Additionally, we evaluated various machine learning models to compare their performance with our proposed method. Finally, we conducted a comprehensive discussion on the strengths and weaknesses of different data types (PolSAR, optical satellite, and UAV) for coseismic landslide identification. Our results indicate that the proposed PolSAR-based method achieves high accuracy in coseismic landslide inventory mapping, offering an effective solution for timely post-earthquake emergency responses in complex environments and all weather conditions in the future.

The successive dimension, without elegance

Experience shows that the poset of levels (or dimensions) of the topos of presheaves on some elegant Reedy categories may be equipped with a monotone increasing ‘successor’ function which, as the case of simplicial sets illustrates, is different from Lawvere’s Aufhebung in general. We prove that a similar result holds for the topos of presheaves on a small category with split-epi/mono factorizations; a typical feature of categories that are Reedy elegant, or skeletal, or graphic (von Neumann-)regular, but more general. In fact, we show that the more general ‘successor’ may be described as a function on the poset of full subcategories of the site that are closed under subobjects.

Enhancing supply chain resilience: A machine learning approach for predicting product availability dates under disruption

The COVID-19 pandemic and ongoing political and regional conflicts have a highly detrimental impact on the global supply chain and cause significant delays in logistics operations and international shipments. One of the most pressing concerns is the uncertainty surrounding the availability dates of products, which is critical information for companies to generate effective logistics and shipment plans. Therefore, accurately predicting availability dates plays a pivotal role in executing successful logistics operations, ultimately minimizing total transportation and inventory costs. We investigate the prediction of product availability dates for General Electric (GE) Gas Power’s inbound shipments for gas and steam turbine service and manufacturing operations, utilizing both numerical and categorical features. We evaluate several regression models, including Simple Regression, Lasso Regression, Ridge Regression, Elastic Net, Random Forest (RF), Gradient Boosting Machine (GBM), and Neural Network models. Based on real-world data, our experiments demonstrate that the tree-based algorithms (i.e., RF and GBM) provide the best generalization error and outperforms all other regression models tested. We anticipate that our prediction models will assist companies in managing supply chain disruptions and reducing supply chain risks on a broader scale.

Considering the role of speech processing in cleft-related speech sound disorders: Implications for causal pathways and classification systems.

Classification systems in healthcare support shared understanding of conditions for clinical communication, service monitoring and development, and research. Children born with cleft palate with or without cleft lip (CP+/-L) are at high risk of developing cleft-related speech sound disorder (SSD). The way cleft-related SSD is represented and described in SSD classification systems varies. Reflecting on the potential causal pathways for different cleft-related speech features, including the role of speech processing skills, may inform how cleft-related SSD is represented in classification systems. To explore and reflect on how cleft-related SSD is represented in current SSD classification systems in the context of considering how speech processing skills and other factors may be involved in causal pathways of cleft speech characteristics (CSCs). Variation in the representation of cleft-related SSD in classification systems is described. Potential causal pathways for passive cleft- related speech features and different active CSCs are explored. The factors involved in the development and/or persistence of different active CSCs may vary. Some factors may be specific to children born with CP+/-L, but if speech processing skills are also involved, this is an overlap with other SSD subtypes. Current evidence regarding relationships between different speech processing skills and active CSCs is limited. Implications for the representation of cleft-related SSD in SSD classification systems are discussed. There are different categories of cleft-related speech features which are essential to understand and identify in children with cleft-related SSD to ensure appropriate management. Representation of these feature categories in classification systems could support understanding of speech in this population. Speech processing skills could be involved in the development and/or persistence of different active CSCs in individual children. Reflection and discussion on how cleft-related SSD is represented in classification systems in relation to other SSD subtypes may inform future iterations of these systems. Further work is needed to understand factors influencing the development and/or persistence of active CSCs, including speech processing skills. What is already known on the subject Cleft-related speech sound disorder (SSD) is commonly described as being of known origin. The features of cleft-related SSD have been described extensively and several authors have also examined factors which may contribute to speech development and outcomes in children born with cleft palate +/- lip. There is limited evidence regarding the role of speech processing in the development and persistence of cleft-related SSD. What this study adds This paper reflects on how cleft-related SSD is represented in SSD classification systems in relation to key feature categories of cleft-related SSD and possible causal pathways for passive features and active cleft speech characteristics (CSCs). The role of cognitive speech processing skills is specifically considered alongside other factors that may contribute to the development of active CSCs. What are the clinical implications of this work? Causal pathways for different features of cleft-related SSD may vary, particularly between passive and active features, abut also between different active CSCs. Speech and language therapists (SLTs) need to differentially diagnose passive speech features and active CSCs. Consideration of the role of different speech processing skills and interactions with other potentially influencing factors in relation to active CSCs may inform clinical hypotheses and speech and language therapy (SLT) intervention. Representing key features of cleft-related SSD in classification systems may support understanding of cleft-related SSD in relation to other SSD subtypes.

Testing and characterization of herding dogs' behaviors.

Breeding for phenotype in herding dogs (HDs) mainly relies on their performance in national field trial competitions, which has been shown to be inadequate for identifying HDs suited for real livestock farming conditions. In this study, a different field trial with a new scoring system consisting of 28 items to consider was designed to assess young HDs, the results of which culminated in a statement of adequate phenotype (AP) or non-adequate phenotype (NAP). An AP HD was defined as being able: to control the direction of a flock, to keep it grouped close to a handler when needed, to confront animals it is dealing with in a respectful manner, and able to create movement of the flock without excessive disturbance, threatening or attacking it through chasing, or uncontrolled biting. This innovative trial is composed of a pre-test (PT) and a test (T) phase. To evaluate its efficiency in detecting AP/NAP, 460 French Border Collies aged between 8 and 24 mo, underwent the trial. Its average duration (PT + T) was 3min and 16s (SD = 26s). According to experts' assessments (Gold Standard), 16.5% of tested HD reached an AP score, and the Idele scoring system correctly identified 93.3% of them (sensitivity). Specificity and accuracy values were of 96.1% and 95.7%, respectively (P value < 0.0004). Recursive feature elimination identified 25 of the 118 features (categories of items) from the scoring system as significant predictors of AP/NAP. An AP HD was statistically defined as a dog who completed the PT and T phases, showed keenness, correct position in relation to the handler, and absence of prey drive. Four environmental effects significantly influenced AP/NAP: the field trial session, the owner's experience with HDs, the conditions of the HD's first contact with livestock, and the type of livestock with which the HD is accustomed to working (P-values <0.0005, <0.05, <0.05, and <0.007, respectively). Inter-evaluator agreement was substantial (0.70). The field trial proved to be a short, easily implemented, standardized, reproducible method for detecting AP/NAP. Hence, the field trial and its scoring system could provide a basis for a breeding program based on phenotype pending additional testing of HDs and genetic analyses.

Modeling neurophysiological and psychomotor relevant criteria in children with motor dysfunction

Background. Cerebral palsy is the most common cause of childhood disability among diseases of the nervous system, the prevalence of which averages 2.5 cases per 1,000 children.Aim. To identify relevant indicators in relation to the prediction of delayed rates of neuropsychic development in children and the formation of cerebral palsy in children 5–8 years old using mathematical modeling.Materials and methods. The study included 100 patients aged 5–8 years: 79 patients with neurological disorders and deviations in psycho-speech development, 21 patients – comparison group. The examination of children in both groups included: analysis of the child’s life history, analysis of psychomotor development in the first year of life, analysis of morbidity in the first year of life, assessment of psychomotor development at the time of the study, electroneuromyography using stimulation and superficial electroneuromyography, as well as ultrasound examination of the lower leg muscles with assessment of the functional state and muscle density using fibroscan.For statistical processing of the obtained data, descriptive statistics were performed. Determination of the statistical significance of indicators was carried out using the Kolmogorov–Smirnov test for continuously distributed values and Fisher’s exact test for discrete values. One-hot coding was used to represent categorical features. The analysis of the obtained data was carried out using a Python program using the pandas, numpy, scikit-learn, and boruta libraries.Results and conclusion. For children with deviations in neuropsychic development, significant early diagnostic markers are parameters of psychomotor development and neurological status (age when the child began to hold his head, decreased strength of the flexors of the foot and hip, level of walking) and instrumental examination (ultrasound of muscles thighs, electroneuromyography) – changes in the density and parameters of electrical excitability of muscles, which can serve as an early diagnostic sign of the development of motor dysfunction and an indicator for the formation of a trajectory of rehabilitation therapy.

The Effect of Feature Selection on the Accuracy of X-Platform User Credibility Detection with Supervised Machine Learning

In the era of digital information, online platforms play a crucial role in shaping public opinion. However, the extensive spread of misinformation and fake news poses a significant challenge, largely fueled by non-credible users. Detecting user credibility is vital for ensuring the reliability of information on these platforms. This study employs supervised machine learning algorithms, leveraging key user features to enhance credibility detection. Feature selection methods, specifically SelectKBest and correlation-based algorithms, are explored for their impact on X-Platform user credibility detection. Utilizing various classifiers, including support vector machine, logistic regression, and XGBoost, experiments are conducted on the ArPFN dataset, which is a labeled, balanced, publicly available dataset. The evaluation includes measures like accuracy, precision, recall, and F1-score to assess efficiency. This research considers feature categories and selection methods with SML to detect their impact on the accuracy of X-Platform user credibility detection, making this research a reference for researchers and practitioners working in the field of SML, feature engineering, and social media analysis. We aim to advance the field’s understanding of effective strategies for mitigating the spread of fake news. The novelty of this study lies in the comprehensive exploration of feature selection methods and their influence on credibility detection, contributing valuable insights for future research in this domain.

Retinal Vascular Measurements and Mortality Risk: Evidence From the UK Biobank Study.

This study aimed to investigate the association between quantitative retinal vascular measurements and the risk of all-cause and premature mortality. In this population-based cohort study using the UK Biobank data, we employed the Retina-based Microvascular Health Assessment System to assess fundus images for image quality and extracted 392 retinal vascular measurements per fundus image. These measurements encompass six categories of vascular features: caliber, density, length, tortuosity, branching angle, and complexity. Univariate Cox regression models were used to identify potential indicators of mortality risk using data on all-cause and premature mortality from death registries. Multivariate Cox regression models were then used to test these associations while controlling for confounding factors. The final analysis included 66,415 participants. After adjusting for demographic, health, and lifestyle factors and genetic risk score, 18 and 10 retinal vascular measurements were significantly associated with all-cause mortality and premature mortality, respectively. In the fully adjusted model, the following measurements of different vascular features were significantly associated with all-cause mortality and premature mortality: arterial bifurcation density (branching angle), number of arterial segments (complexity), interquartile range and median absolute deviation of arterial curve angle (tortuosity), mean and median values of mean pixel widths of all arterial segments in each image (caliber), skeleton density of arteries in macular area (density), and minimum venular arc length (length). The study revealed 18 retinal vascular measurements significantly associated with all-cause mortality and 10 associated with premature mortality. Those identified parameters should be further studied for biological mechanisms connecting them to increased mortality risk. This study identifies retinal biomarkers for increased mortality risk and provides novel targets for investigating the underlying biological mechanisms.

Exkurs zur Analyse der Korrelat konstruktionen

The main idea that led me to write such research paper within the framework of Germanic linguistics is that I have not found any topic dealing with the term correlate in the German language, except in several articles in linguistic journals as well as one topic in a book describing the use of such a linguistic phenomenon in the language system. The research initially deals with the definition of the correlate at the level of the German language system. Correlate is unity describes specific relation of two sentences and identifies denoted constructs. Correlate is called a placeholder at the syntactic level because it does not occupy its original topological fields in the syntactic structure. The correlate (es) or the prepositional adverbs or adverbs can occur in the matrix clause, it is the second feature. The third categorical feature of the correlate is morphological, in that the correlate is inflexible and the last feature shows that the correlate does not confer case features on its syntactic environment, where the correlate possesses the matrix clause. The correlate can appear as the first part of the complex connector in the subordinate clause or the infinitive construction. The last feature refers to the fact that the correlate construction can be attributive in the complex sentence, whereby the sentence structure, which is the constituent of attributively formed correlate specifiers, is embedded. The research presents the conceptual content of the linguistic expression described by the correlate, functioning as a pro-element in the major premise and considered as a dentate. It is a matter of denotation of the correlate and deictic expressions. Furthermore, the present research sheds light on the obligatory and optional use of the correlate constructions in the German sentence. In German there are correlates when using certain verbs. In addition, certain linguistic constructions or expressions require correlates of both particles and prepositional adverbs. The reasons for this are contextual and communicative aspects. In relation to the contextual-communicative aspects such as verbs affect the connection with the correlate. She signals the connection through the grade particles. Compared to other verbs, the use of the correlate (es) is reduced. The reason for this is the appearance of degree particles as well, even, at most, only, only. This can be the case if the grading of the text passage does not focus on the extreme predicate, but rather on the infinitive construction or the subordinate clause. This was studied at work. Then it was examined how the correlate constructions occur with certain subjunctives by dividing them into two forms, namely attributive correlate constructions and left displacement constructions. If the correlate occurs before the subjunctive phrase, it is called an attributive correlate construction. This form is also called a correlate specifier. The subjunctive phrase has the function of being an attribute for the correlate. They can be directly followed by the correlate, whereby it is possible that the correlate alone carries the main clause after deducting the so-called phrase.

UniParser: Multi-Human Parsing With Unified Correlation Representation Learning.

Multi-human parsing is an image segmentation task necessitating both instance-level and fine-grained category-level information. However, prior research has typically processed these two types of information through distinct branch types and output formats, leading to inefficient and redundant frameworks. This paper introduces UniParser, which integrates instance-level and category-level representations in three key aspects: 1) we propose a unified correlation representation learning approach, allowing our network to learn instance and category features within the cosine space; 2) we unify the form of outputs of each modules as pixel-level results while supervising instance and category features using a homogeneous label accompanied by an auxiliary loss; and 3) we design a joint optimization procedure to fuse instance and category representations. By unifying instance-level and category-level output, UniParser circumvents manually designed post-processing techniques and surpasses state-of-the-art methods, achieving 49.3% AP on MHPv2.0 and 60.4% AP on CIHP. We have released our source code, pretrained models, and demos to facilitate future studies on https://github.com/cjm-sfw/Uniparser.

Properties of the conjunction "though... although ..." and the structure he organizes in the structure of syntactic units of the modern Russian language

The object of the article is the disjunctive conjunction “though... although...”, and the subject is the property “though... although...” in the system of syntactic units: phrases, simple and complex sentences. In addition, the textual features of this union are considered. Particular attention is paid to the qualification of the coordinating series with the conjunction “though... although...” in terms of its relevance/non-relatedness to the phrase. In a simple sentence, the place of a series with the conjunction “though... although...” in the system of minor parts of the sentence, as part of participial phrases, as well as when expressing additional predicate is explored. When turning to a complex sentence, the reasons for the limited functioning of “though... although...” in a given syntactic unit are clarified. In relation to the text, the textual possibilities of “though... although...” are considered as a secondary textual anchor. The research is based on the methodology of the Far Eastern syntactic school. It consists in a multidimensional description of a particular function word at the morphological-syntactic, actual syntactic and communicative-pragmatic levels. As a result, connections between the function word and both the near and far syntactic environment are established. The data obtained are used for its extended lexicographic portraiture. The main conclusions of the study are the following. A coordinating sequence with the conjunction “though... although” is not a phrase, and the word form with which it is connected by subordinating relations should be qualified as a general member of its syntactic structure. A row with the conjunction “though... although...” can occupy the positions of various members of a sentence, function as part of participial phrases, and also participate in the organization of additional predicativity. The connection of the coordinating series-subject with the common member-predicate can be coordinated or uncoordinated. The speaker's solution to the problem is to "agree on meaning." The facts of complex sentences with the conjunction “though... although” have not been recorded. In the case of parcellation, a series with the conjunction “though... although...” becomes the organizing center of a communicative-pragmatic situation, presented in the form of a complex syntactic whole. The author’s special contribution to the study of the topic is the establishment of a correlation between the syntactic properties of the construction with the conjunction “though... although...” and its categorical features. The novelty of the study lies in the inclusion of the conjunction “though... although...” into the system of a current modern trend - an integral description of linguistic units.

Unveiling the Secrets of Big Data Projects: Harnessing Machine Learning Algorithms and Maturity Domains to Predict Success

Aim/Purpose: While existing literature has extensively explored factors influencing the success of big data projects and proposed big data maturity models, no study has harnessed machine learning to predict project success and identify the critical features contributing significantly to that success. The purpose of this paper is to offer fresh insights into the realm of big data projects by leveraging machine-learning algorithms. Background: Previously, we introduced the Global Big Data Maturity Model (GBDMM), which encompassed various domains inspired by the success factors of big data projects. In this paper, we transformed these maturity domains into a survey and collected feedback from 90 big data experts across the Middle East, Gulf, Africa, and Turkey regions regarding their own projects. This approach aims to gather firsthand insights from practitioners and experts in the field. Methodology: To analyze the feedback obtained from the survey, we applied several algorithms suitable for small datasets and categorical features. Our approach included cross-validation and feature selection techniques to mitigate overfitting and enhance model performance. Notably, the best-performing algorithms in our study were the Decision Tree (achieving an F1 score of 67%) and the Cat Boost classifier (also achieving an F1 score of 67%). Contribution: This research makes a significant contribution to the field of big data projects. By utilizing machine-learning techniques, we predict the success or failure of such projects and identify the key features that significantly contribute to their success. This provides companies with a valuable model for predicting their own big data project outcomes. Findings: Our analysis revealed that the domains of strategy and data have the most influential impact on the success of big data projects. Therefore, companies should prioritize these domains when undertaking such projects. Furthermore, we now have an initial model capable of predicting project success or failure, which can be invaluable for companies. Recommendations for Practitioners: Based on our findings, we recommend that practitioners concentrate on developing robust strategies and prioritize data management to enhance the outcomes of their big data projects. Additionally, practitioners can leverage machine-learning techniques to predict the success rate of these projects. Recommendation for Researchers: For further research in this field, we suggest exploring additional algorithms and techniques and refining existing models to enhance the accuracy and reliability of predicting the success of big data projects. Researchers may also investigate further into the interplay between strategy, data, and the success of such projects. Impact on Society: By improving the success rate of big data projects, our findings enable organizations to create more efficient and impactful data-driven solutions across various sectors. This, in turn, facilitates informed decision-making, effective resource allocation, improved operational efficiency, and overall performance enhancement. Future Research: In the future, gathering additional feedback from a broader range of big data experts will be valuable and help refine the prediction algorithm. Conducting longitudinal studies to analyze the long-term success and outcomes of Big Data projects would be beneficial. Furthermore, exploring the applicability of our model across different regions and industries will provide further insights into the field.

An Interpretable Deep Embedding Model for Few and Imbalanced Biomedical Data.

In healthcare, training examples are usually hard to obtain (e.g., cases of a rare disease), or the cost of labelling data is high. With a large number of features ( p) be measured in a relatively small number of samples ( N), the "big p, small N" problem is an important subject in healthcare studies, especially on the genomic data. Another major challenge of effectively analyzing medical data is the skewed class distribution caused by the imbalance between different class labels. In addition, feature importance and interpretability play a crucial role in the success of solving medical problems. Therefore, in this paper, we present an interpretable deep embedding model (IDEM) to classify new data having seen only a few training examples with highly skewed class distribution. IDEM model consists of a feature attention layer to learn the informative features, a feature embedding layer to directly deal with both numerical and categorical features, a siamese network with contrastive loss to compare the similarity between learned embeddings of two input samples. Experiments on both synthetic data and real-world medical data demonstrate that our IDEM model has better generalization power than conventional approaches with few and imbalanced training medical samples, and it is able to identify which features contribute to the classifier in distinguishing case and control.

Hierarchical Self-Distilled Feature Learning for Fine-Grained Visual Categorization.

Fine-grained visual categorization (FGVC) relies on hierarchical features extracted by deep convolutional neural networks (CNNs) to recognize closely alike objects. Particularly, shallow layer features containing rich spatial details are vital for specifying subtle differences between objects but are usually inadequately optimized due to gradient vanishing during backpropagation. In this article, hierarchical self-distillation (HSD) is introduced to generate well-optimized CNNs features for accurate fine-grained categorization. HSD inherits from the widely applied deep supervision and implements multiple intermediate losses for reinforced gradients. Besides that, we observe that the hard (one-hot) labels adopted for intermediate supervision hurt the performance of FGVC by enforcing overstrict supervision. As a solution, HSD seeks self-distillation where soft predictions generated by deeper layers of the network are hierarchically exploited to supervise shallow parts. Moreover, self-information entropy loss (SIELoss) is designed in HSD to adaptively soften intermediate predictions and facilitate better convergence. In addition, the gradient detached fusion (GDF) module is incorporated to produce an ensemble result with multiscale features via effective feature fusion. Extensive experiments on four challenging fine-grained datasets show that, with neglectable parameter increase, the proposed HSD framework and the GDF module both bring significant performance gains over different backbones, which also achieves state-of-the-art classification performance.

Category Alignment Mechanism for Few-Shot Image Classification.

While humans can excel at image classification tasks by comparing a few images, existing metric-based few-shot classification methods are still not well adapted to novel tasks. Performance declines rapidly when encountering new patterns, as feature embeddings cannot effectively encode discriminative properties. Moreover, existing matching methods inadequately utilize support set samples, focusing only on comparing query samples to category prototypes without exploiting contrastive relationships across categories for discriminative features. In this work, we propose a method where query samples select their most category-representative features for matching, making feature embeddings adaptable and category-related. We introduce a category alignment mechanism (CAM) to align query image features with different categories. CAM ensures features chosen for matching are distinct and strongly correlated to intra-and inter-contrastive relationships within categories, making extracted features highly related to their respective categories. CAM is parameter-free, requires no extra training to adapt to new tasks, and adjusts features for matching when task categories change. We also implement a cross-validation-based feature selection technique for support samples, generating more discriminative category prototypes. We implement two versions of inductive and transductive inference and conduct extensive experiments on six datasets to demonstrate the effectiveness of our algorithm. The results indicate that our method consistently yields performance improvements on benchmark tasks and surpasses the current state-of-the-art methods.

Clinical value of ACR O-RADS combined with CA125 in the risk stratification of adnexal masses.

To develop a combined diagnostic model integrating the subclassification of the 2022 version of the American College of Radiology (ACR) Ovarian-Adnexal Reporting and Data System (O-RADS) with carbohydrate antigen 125 (CA125) and to validate whether the combined model can offer superior diagnostic efficacy than O-RADS alone in assessing adnexal malignancy risk. A retrospective analysis was performed on 593 patients with adnexal masses (AMs), and the pathological and clinical data were included. According to the large differences in malignancy risk indices for different image features in O-RADS category 4, the lesions were categorized into groups A and B. A new diagnostic criterion was developed. Lesions identified as category 1, 2, 3, or 4A with a CA125 level below 35 U/ml were classified as benign. Lesions identified as category 4A with a CA125 level more than or equal to 35 U/ml and lesions with a category of 4B and 5 were classified as malignant. The sensitivity, specificity, positive predictive value (PPV), negative predictive value (NPV), accuracy, and area under the curve (AUC) of O-RADS (v2022), CA125, and the combined model in the diagnosis of AMs were calculated and compared. The sensitivity, specificity, PPV, NPV, accuracy, and AUCs of the combined model were 92.4%, 96.5%, 80.2%, 98.8%, 94.1%, and 0.945, respectively. The specificity, PPV, accuracy, and AUC of the combined model were significantly higher than those of O-RADS alone (all P < 0.01). In addition, both models had acceptable sensitivity and NPV, but there were no significant differences among them (P > 0.05). The combined model integrating O-RADS subclassification with CA125 could improve the specificity and PPV in diagnosing malignant AMs. It could be a valuable tool in the clinical application of risk stratification of AMs.

Наративи про перших леді США як інструмент формування еталону жіночності

Narratives play a fundamental role in forming the system of values of any society; therefore, highlighting the mechanisms of their creation and functioning is in the focus of attention of representatives of various scientific areas, including cognitive science, cognitive linguistics and poetics, as well as gender studies, with cognitive linguistics providing information about ways of organizing our experience in memory and using the structures of this experience to perform social actions and achieve certain social goals. The article aims at clarifying constitutive features of narratives about the first ladies of the United States created by the US mass media. The objectives of the article are to develop methodology for analyzing narratives based on the integration of the achievements of narratology and cognitive linguistics, as well as establishing verbal and non-verbal means of forming ideas about the ideal-prototype characteristics of first ladies. The object-matter of analysis is the narratives about the US first ladies created by the American media, the subject-matter being multimodal means of forming the standards of femininity in American society. The scientific novelty of the research reveals itself in the combination of narrative and cognitive methods of analysis. The results of the analysis of the multimodal discursive contexts representing the narratives about the first ladies of the United States in the English mass media reflect the connection between the narratives and radial categorization: the actors of social events that become the subjects of the narratives are evaluated by average Americans as positive or negative according to their conformity or non-conformity with their expectations in relation to the ideal/prototypical features of radial categories to which these actors belong. Evaluating is carried out verbally with the support of images performing illustrative and reinforcing functions. This evaluation reflects expectations of Americans society regarding ideal/prototypical characteristics of social actors such as first ladies. Among these expectations there are manifestations of racism and sexism.

Searching Discriminative Regions for Convolutional Neural Networks in Fundus Image Classification With Genetic Algorithms.

Deep convolutional neural networks (CNNs) have been widely used for fundus image classification and have achieved very impressive performance. However, the explainability of CNNs is poor because of their black-box nature, which limits their application in clinical practice. In this paper, we propose a novel method to search for discriminative regions to increase the confidence of CNNs in the classification of features in specific category, thereby helping users understand which regions in an image are important for a CNN to make a particular prediction. In the proposed method, a set of superpixels is selected in an evolutionary process, such that discriminative regions can be found automatically. Many experiments are conducted to verify the effectiveness of the proposed method. The average drop and average increase obtained with the proposed method are 0 and 77.8%, respectively, in fundus image classification, indicating that the proposed method is very effective in identifying discriminative regions. Additionally, several interesting findings are reported: 1) Some superpixels, which contain the evidence used by humans to make a certain decision in practice, can be identified as discriminative regions via the proposed method; 2) The superpixels identified as discriminative regions are distributed in different locations in an image rather than focusing on regions with a specific instance; and 3) The number of discriminative superpixels obtained via the proposed method is relatively small. In other words, a CNN model can employ a small portion of the pixels in an image to increase the confidence for a specific category.

A Semiotic Exploration of the Evolving Messaging in the Shona Traditional Songs: the Elusive Context, Categorization and Paralinguistic Features of the Song 'Nyama Yekugocha'

A Semiotic Exploration of the Evolving Messaging in the Shona Traditional Songs: the Elusive Context, Categorization and Paralinguistic Features of the Song 'Nyama Yekugocha'