Classification Analysis Research Articles

2022 개정 특수교육 기본 교육과정 수학과 성취기준 분석: Bloom의 신교육목표분류학에 기초하여

Objectives This study aims to provide implications for the achievement standards of the basic curriculum for mathematics in the 2022 Revised Special Education Basic Curriculum by analyzing them based on Bloom's revised taxonomy of educational objectives. Methods To this end, a total of 182 mathematics achievement standards of the revised 2022 special education basic curriculum were analyzed for five grade groups and five mathematics areas based on Bloom's new taxonomy of educational objectives. Results First, the achievement standards for each grade were analyzed. As a result, among Bloom's knowledge dimensions in all grade groups, ‘factual knowledge’ was the highest with 104 (57.1%), and among the cognitive process dimensions, ‘Understanding’ was the highest with 89 (48.9%). A binary classification analysis of knowledge and cognitive process levels, the achievement standards for remembering factual knowledge were found in 55 achievement standards(30.2%). There were no achievement standards for ‘Meta-cognitive knowledge’, ‘Evaluation’, and ‘Create’. Second, as a result of analyzing the achievement standards by mathematics area, ‘Factual knowledge’ was the highest in the knowledge dimension with 45 achievement standards (48.9%) for numbers and operations, 28 (87.5%) for shapes, and 24 (92.2%) for measurement. ‘Conceptual knowledge’ was the highest with 12 (70.5%) in the regularity area and 9 (60%) in the data and probability area. In the cognitive process, ‘Remember’ was the highest with 29 (31.5%) in the number and calculation areas and 18 (56.3%) in the measurement areas was the highest with 17 achievement standards (65.3%), the regularity area with 7 achievement standards (41.1%), and the data and probability area with 9 achievement standards(60.0%). There were no achievement standards for ‘Meta-cognitive knowledge’, ‘Evaluation’, and ‘Create’. Conclusions Based on the results of this study, implications for the development of mathematics achievement standards of the basic curriculum for special education and suggestions for future research were made.

Scoping review of sustainable diets research reveals a thematic and disciplinary emphasis on nutrition and environment

Abstract Sustainable diets have been identified as an important component of a food systems transformation that is urgently needed to meet global sustainability and development goals. This study addresses the lack of a comprehensive synthesis and overview of the sustainable diets literature, including its evolution over time and across disciplines, and sheds light on whether and how this body of work addresses dimensions of sustainability as defined by the Food and Agriculture Organization of the United Nation’s (FAO) sustainable diets framework. Topic modeling, a type of natural language processing, was used to perform a thematic scoping review of 855 articles published between 2000-2022 to identify trends and themes in a way that was rapid, transparent, reliable, and reproducible. This research finds demonstrated growth in the field of sustainable diets research, with the majority (66%) of sustainable diets articles considered in this study published in the last three years of the study period. Sixty-three percent of the sustainable diets research articles can be characterized by two topics, “sustainability impacts of dietary patterns” and “sustainable diets and food system policy.” FAO components of sustainable diets related to local and seasonal foods, culture, and equity receive relatively little research attention, whereas components of health, environment, and food security each align with approximately a third of the research literature. This is also reflected in the subject classification analysis, in which nearly half of the research (44%) was classified as Nutrition and Dietetics and/or Environmental Studies. This research highlights the need for more transdisciplinary research that addresses areas of equity, culture, social processes, and context as well as the intersections of sustainability dimensions to better understand the need for, implications, and directions of sustainable diets to support a sustainable food systems transformation.

Identification of Phospholipids Relevant to Cancer Tissue Using Differential Ion Mobility Spectrometry

Phospholipids are the main building components of cell membranes and are also used for cell signaling and as energy storages. Cancer cells alter their lipid metabolism, which ultimately leads to an increase in phospholipids in cancer tissue. Surgical energy instruments use electrical or vibrational energy to heat tissues, which causes intra- and extracellular water to expand rapidly and degrade cell structures, bursting the cells, which causes the formation of a tissue aerosol or smoke depending on the amount of energy used. This gas phase analyte can then be analyzed via gas analysis methods. Differential mobility spectrometry (DMS) is a method that can be used to differentiate malignant tissue from benign tissues in real time via the analysis of surgical smoke produced by energy instruments. Previously, the DMS identification of cancer tissue was based on a ‘black box method’ by differentiating the 2D dispersion plots of samples. This study sets out to find datapoints from the DMS dispersion plots that represent relevant target molecules. We studied the ability of DMS to differentiate three subclasses of phospholipids (phosphatidylcholine, phosphatidylinositol, and phosphatidylethanolamine) from a control sample using a bovine skeletal muscle matrix with a 5 mg addition of each phospholipid subclass to the sample matrix. We trained binary classifiers using linear discriminant analysis (LDA) and support vector machines (SVM) for sample classification. We were able to identify phosphatidylcholine, -inositol, and -ethanolamine with SVM binary classification accuracies of 91%, 73%, and 66% and with LDA binary classification accuracies of 82%, 74%, and 72%, respectively. Phosphatidylcholine was detected with a reliable classification accuracy, but ion separation setups should be adjusted in future studies to reliably detect other relevant phospholipids such as phosphatidylinositol and phosphatidylethanolamine and improve DMS as a microanalysis method and identify other phospholipids relevant to cancer tissue.

Integrating color histogram analysis and convolutional neural networks for skin lesion classification

The color of skin lesions is a crucial diagnostic feature for identifying malignant melanoma and other skin diseases. Typical colors associated with melanocytic lesions include tan, brown, black, red, white, and blue-gray. This study introduces a novel feature: the number of colors present in lesions, which can indicate the severity of skin diseases and help distinguish melanomas from benign lesions. We propose a color histogram analysis, a traditional image processing technique, to analyze the pixels of skin lesions from three publicly available datasets: PH2, ISIC2016, and Med-Node, which include dermoscopic and non-dermoscopic images. While the PH2 dataset contains ground truth about skin lesion colors, the ISIC2016 and Med-Node datasets lack such annotations; our algorithm establishes this ground truth using the color histogram analysis based on the PH2 dataset. We then design and train a 19-layer Convolutional Neural Network (CNN) with different skip connections of residual blocks to classify lesions into three categories based on the number of colors present. The DeepDream algorithm is utilized to visualize the learned features of different layers, and multiple configurations of the proposed CNN are tested, achieving the highest weighted F1-score of 75.00 % on the test set. LIME is subsequently applied to identify the most important features influencing the model's decision-making. The findings demonstrate that the number of colors in lesions is a significant feature for describing skin conditions. The proposed CNN, particularly with three skip connections, shows strong potential for clinical application in diagnosing melanoma, supporting its use alongside traditional diagnostic methods.

Investigating the effect of non-resonant background variation on the CARS data analysis of bacteria samples and classification using machine learning

Investigating the effect of non-resonant background variation on the CARS data analysis of bacteria samples and classification using machine learning

Plant-Based Beverages: Consumption Habits, Perception and Knowledge on a Sample of Portuguese Citizens.

Plant-based beverages (PBB) consumption has increased significantly worldwide due to an interest in vegetarian/vegan diets, taste preferences, health and ethical and environmental issues. Therefore, this study intends to investigate consumption habits, consumer preferences and consumers' level of knowledge about PBB. In this study, a voluntary, anonymous questionnaire survey was applied to a sample of participants from Portugal. The sample was recruited by convenience, and therefore, the distribution among the groups was not even. Data analysis involved different statistical techniques: basic statistics, chi-square tests, factor analysis, cluster analysis and tree classification analysis. The results indicated that the most consumed PBB were almond, soy and oat beverages. The majority of consumers chose these beverages for nutritional and health reasons, while a smaller number consumed them as part of a vegetarian or vegan diet. The main motivations for consuming PBB are mainly associated with sustainability and health benefits. The results regarding the respondents' knowledge about PBB revealed that a health-related profession was the most significant predictor. These results allowed us to conclude that the factors of nutrition, health, ethics and practice of a vegetarian/vegan diet influence the consumption of PBB. It was also concluded that being in a healthcare profession, along with age and professional status within this field, were significant factors influencing the level of knowledge about PBB.

Hierarchical Classification of Factors Associated With Noninvasive Prenatal Testing Failures and Its Impact on Pregnancy Outcomes

Abstract Objective To conduct a hierarchical classification analysis of the nonreportable results of noninvasive prenatal testing in an attempt to reduce failure rates and provide pregnant women with accurate information to alleviate their anxiety. Methods In this study, 30,039 singleton pregnancies who underwent noninvasive prenatal testing in a single center from May 2019 to April 2022 were collected, and 811 samples with initial noninvasive prenatal testing failure were retrospectively analyzed. Grouping was based on the reasons for initial test failure; tracking the noninvasive prenatal testing results and prenatal diagnosis results (if any) of the “z-scores in the gray area” group and analyzing the possible influencing factors of the “low fetal fraction” group in the pre-experimental and experimental period by using one-way analysis of variance, Mann-Whitney U test, and χ2 test; and tracking the pregnancy outcomes of the test failures samples to analyze the risk of perinatal complications and adverse pregnancy outcomes of the different types of test failures. Results None of the samples' initial nonresults because of z-scores in the gray area were ultimately found to have chromosomal aneuploidy. However, pregnancy complications (P = 0.018) and a high likelihood of adverse pregnancy outcomes (P = 0.048) may still occur. Maternal gestational age (P < 0.001), body mass index (P < 0.001), library concentration (P < 0.001), and fetal gender (P < 0.001) were considered to be the associated factors for the initial low fetal fraction results. This may be associated with pregnancy complications (P < 0.001) and a high likelihood of adverse pregnancy outcomes (P = 0.034). The body mass index (P = 0.015) and time between draws (P = 0.001) were associated with the second test’s success. The incidence of low fetal fraction samples was more frequent with blood collection tubes of the G type than with the K type (P < 0.001). Conclusion Initial nonresults because of z-scores in the gray area did not imply an increased risk of aneuploidy, but vigilance is needed for an increased risk of pregnancy complications and adverse pregnancy outcomes. Because of the low fetal fraction, the initial absence of results may be related to the assay method, as well as the effect of blood collection tubes and the need to be alert to the risk of pregnancy complications and adverse pregnancy outcomes.

Clinical factors associated with genetic diagnosis in suspected neurogenetic disorders in a tertiary care clinic.

This study aimed to identify phenotypic factors associated with genetic diagnoses in patients with neurodevelopmental disorders and generate a decision tree to assist clinicians in identifying patients most likely to receive a positive result on genetic testing. We retrospectively reviewed the charts of 316 patients evaluated in a neurodevelopmental clinic between 2014 and 2019. Patients were categorized based on genetic test results. Analyses were performed to identify variables that discriminate between patients with and without a genetic diagnosis. Patients with a genetic diagnosis were more likely to be female and have a history of motor delay, hypotonia, congenital heart disease, and early intervention. Classification and regression tree analysis revealed that 75% of patients with motor delay had a genetic diagnosis. In patients without motor delay, hypotonia, age of walking, and age at initial evaluation were important indicators of a genetic diagnosis. Our findings suggest that motor delay and hypotonia are associated with genetic diagnoses in children with neurodevelopmental disorders. The decision tree highlights patient subsets at greater risk and suggests possible phenotypic screens. Future studies could develop validated decision trees based on phenotypic data to assist clinicians in stratifying patients for genetic testing.

Multifractal Analysis in Age-Based Classification for COVID-19 Patients’ CT-Scan Images with Different Noise Levels

Recently, many number of people various countries contracted the COVID-19 (C-19) disease. The identification of this harmful disease and other pneumonia diseases is an important process in the medical world. CT-Scan is mainly prescribed to predict the severity of lung diseases affected by C-19 and other pneumonia diseases. Generally, a CT-Scan image is represented as a grayscale image (GI). Biomedical-oriented GIs are more complex and they are too difficult to recognize the status of lung diseases directly from the experimental images. To address this type of medical problem, a multifractal approach can be applied to analyze and illustrate the GIs in detail. Therefore, the multifractal dimensional analysis is used to diagnose and explore the vehemence of the contamination levels in the lungs. In this study, the complexity of CT-Scan images of C-19 patients is analyzed in order to perform a comparison in terms of age and noise levels. It was also discovered that the intricate of CT-Scan images is considerably varied for patients aged 50 and above when compared to younger subjects. This comparative study indicates that the deadly virus affects elderly persons compared to youngsters. The proposed age-based classification is supported by image processing techniques, qualitative measures, and statistical tools. The obtained results are demonstrated graphically by Generalized Fractal Dimensions (GFD) spectrum, 3D visualization, ANOVA table, and box plots to expose the rate of discrimination of complexity in CT-Scan lung images.

Dynamic modeling of human error in industrial maintenance through structural analysis and system dynamics.

Human error constitutes a significant cause of accidents across diverse industries, leading to adverse consequences and heightened disruptions in maintenance operations. Organizations can enhance their decision-making process by quantifying human errors and identifying the underlying influencing factors, thereby mitigating their repercussions. Consequently, it becomes crucial to examine the value of human error probability (HEP) during these activities. The objective of this paper is to determine and simulate HEP in maintenance tasks at a cement factory, utilizing performance shaping factors (PSFs). The research employs the cross-impact matrix multiplication applied to classification (MICMAC) analysis method to evaluate the dependencies, impacts, and relationships among the factors influencing human error. This approach classifies and assesses the dependencies and impacts of different factors on HEP, occupational accidents, and related costs. The study also underscores that PSFs can dynamically change under the influence of other variables, emphasizing the necessity to forecast the behavior of human error over time. Therefore, this paper utilizes the MICMAC method to analyze the interdependencies, relationships, and impact levels among different variables. These relationships are then utilized to optimize the implementation of the system dynamics (SD) method. An SD model is employed to forecast the system's behavior, and multiple scenarios are presented. By considering the HEP value, managers can adjust organizational conditions and personnel to ensure acceptability. The paper also presents various scenarios related to HEP to assist managers in making informed decisions.

Future prospectives in plantain agro-chain by foresight-by-scenarios and Delphi analysis

Purpose This paper aims to identify future scenarios and convergent technologies regarding the plantain chain in the region of Quindío, Colombia. It proposes the definition of key variables, convergent technologies, future objectives, future scenarios and hypotheses based on stakeholders’ and experts’ opinions collected through questionnaires, surveys and workshops. Design/methodology/approach The present analysis seeks to identify and anticipate the future routes for the improvement of scientific, technological, innovative and skills management of the plantain agroindustrial chain in the region of Quindío, Colombia using the foresight-by-scenarios and, Delphi methodologies and finally validating the results with artificial intelligence code and natural language processing. Findings After the analysis of 100 initial variables, the results suggested the identification of five key variables defined by the stakeholders and matrix-based multiplication applied to a classification (MICMAC) analysis such as “weather,” “financing and economy,” “grouping and associativity,” “crop” and “territorial planning and raw material.” Moreover, the definition of four future objectives along with the matrix of alliances and conflicts, tactics, objectives and recommendations (MACTOR) analysis suggested scenarios according to the probability. The most possible, probable and desirable scenario, was the cooccurrence of the five proposed hypotheses. Furthermore, the Delphi analysis allowed us to define nine subgroups from 116 subtopics including: “plantain varieties,” “plantain agroindustry,” “waste use” and “crop,” among others. Research limitations/implications Due to the specificity of the analyzed agro-chain, the study only encompasses the plantain and banana sectors. However, the implications are related to the generation of projects in the selected technologies. Practical implications This paper includes implications for the development of prospective studies combining two or more different methodologies such as foresight-by-scenarios and Delphi method at the same time and further comparing the results with artificial intelligence analysis. Social implications The generation of public policies in the sector and input for governmental analysis and tools for decision-making with a well-grounded, systematic and rational point of view. Originality/value This work describes for the first time, the implementation of the Delphi method regarding an important agroindustry sector such as plantain and banana prospective study. Furthermore, it explains the alignment of two methodologies; foresight-by-scenarios and the Delphi method related to the sectorial approaches, and convergent technologies and innovations, respectively. Moreover, a complementary bibliometric analysis with global terms related to the plantain or banana agroindustry was also included. In a novel way, we also applied an artificial intelligence code using Python software to contrast the results previously obtained in the foresight-by-scenarios method.

Diffusion MRI is superior to quantitative T2-FLAIR mismatch in predicting molecular subtypes of human non-enhancing gliomas.

This study compared the classification performance of normalized apparent diffusion coefficient (nADC) with percentage T2-FLAIR mismatch-volume (%T2FM-volume) for differentiating between IDH-mutant astrocytoma (IDHm-A) and other glioma molecular subtypes. A total of 105 non-enhancing gliomas were studied. T2-FLAIR digital subtraction maps were used to identify T2FM and T2-FLAIR non-mismatch (T2FNM) subregions within tumor volumes of interest (VOIs). Median nADC from the whole tumor, T2FM, and T2NFM subregions and %T2FM-volume were obtained. IDHm-A classification analyses using receiver-operating characteristic curves and multiple logistic regression were performed in addition to exploratory survival analyses. T2FM subregions had significantly higher nADC than T2FNM subregions within IDHm-A with ≥ 25% T2FM-volume (P < 0.0001). IDHm-A with ≥ 25% T2FM-volume demonstrated significantly higher whole tumor nADC compared to IDHm-A with < 25% T2FM-volume (P < 0.0001), and both IDHm-A subgroups demonstrated significantly higher nADC compared to IDH-mutant oligodendroglioma and IDH-wild-type gliomas (P < 0.05). For classification of IDHm-A vs. other gliomas, the area under curve (AUC) of nADC was significantly greater compared to the AUC of %T2FM-volume (P = 0.01, nADC AUC = 0.848, %T2FM-volume AUC = 0.714) along with greater sensitivity. In exploratory survival analyses within IDHm-A, %T2FM-volume was not associated with overall survival (P = 0.2), but there were non-significant trends for nADC (P = 0.07) and tumor volume (P = 0.051). T2-FLAIR subtraction maps are useful for characterizing IDHm-A imaging characteristics. nADC outperforms %T2FM-volume for classifying IDHm-A amongst non-enhancing gliomas with preserved high specificity and increased sensitivity, which may be related to inherent diffusivity differences regardless of T2FM. In line with previous findings on visual T2FM-sign, quantitative %T2FM-volume may not be prognostic.

Structural disruption in subjective cognitive decline and mild cognitive impairment.

Subjective cognitive decline (SCD) marks the initial stage in Alzheimer's disease continuum. Nonetheless, current research findings regarding brain structural changes in the SCD are inconsistent. In this study, 37 SCD patients, 28 mild cognitive impairment (MCI) patients, and 42 healthy controls (HC) were recruited to investigate structural alterations. Morphological and microstructural differences among the three groups were analyzed based on T1- and diffusion-weighted images, correlating them with neuropsychological assessments. Additionally, classification analysis was performed by using support vector machines (SVM) categorize participants into three groups based on MRI features. Both SCD and MCI showed decreased volume in left inferior parietal lobe (IPL) compared to HC, while SCD showed altered morphologies in the right inferior temporal gyrus (ITG), right insula and right amygdala, and microstructures in fiber tracts of the right ITG, lateral occipital cortex (LOC) and insula relative to MCI. Moreover, the volume in the left IPL, right LOC, right amygdala and diffusivity value in fiber tracts of right LOC were significantly correlated with cognitive functions across all subjects. The classification models achieved an accuracy of > 0.7 (AUC = 0.8) in distinguishing the three groups. Our findings suggest that SCD and MCI share similar atrophy in the IPL but show more differences in morphological and microstructural features of cortical-subcortical areas.

The Complete Chloroplast Genome of Meconopsis simplicifolia and Its Genetic Comparison to Other Meconopsis Species.

Background: Chloroplasts, due to their high conservation and lack of recombination, serve as important genetic resources for the classification and evolutionary analysis of closely related species that are difficult to distinguish based on their morphological features. Meconopsis simplicifolia (M. simplicifolia), an endangered herb within the Meconopsis genus, has demonstrated therapeutic potential in treating various diseases. However, the highly polymorphic morphology of this species poses a challenge for accurate identification. Methods: In this study, the complete chloroplast genome of M. simplicifolia was sequenced and assembled using Illumina sequencing technology. Simple sequence repeats (SSRs) and repetitive sequences were characterized. In addition, a comparative analysis was conducted with the chloroplast genomes of six other Meconopsis species. Results: The chloroplast genome of M. simplicifolia has a quadripartite circular structure with a total length of 152,772 bp. It consists of a large single-copy region of 83,824 bp and a small single-copy region of 17,646 bp, separated by a pair of inverted repeat sequences (IRa and IRb, 25,651 bp). The genome contains 131 genes, 33 SSRs, and 27 long repetitive sequences. Comparative analysis with six other chloroplast genomes of Meconopsis revealed that M. simplicifolia is closely related to M. betonicifolia and that the rpl2 (ribosomal protein L2) gene in the IRb region has been deleted. This deletion is of significant importance for future taxonomic studies of M. simplicifolia. Conclusions: This study provides a valuable reference for the identification of M. simplicifolia and contributes to a deeper understanding of the phylogeny and evolution of the Meconopsis genus.

Exploring corporate reputation and crisis communication

AbstractCorporate reputation, the collective perception of company attractiveness towards stakeholders, impacts business outcomes, while effective communication strategies play a critical role in shaping and maintaining the reputation. The role of communication is highlighted during crises, crisis communication being a strategic approach to managing and mitigating the impact of unexpected or adverse events on the reputation, operations, and stakeholders. These concepts are deeply interrelated with interactive marketing. This study explores the dynamics of corporate reputation and crisis communication during a recent global crisis by combining a literature review, opinion mining, and classification analysis. This is because stakeholders rely on various information sources and engage in online discussions, which can impact the reputation, and pose new challenges. The opinion mining analysis draws from the media communication of selected stock-listed companies during a crisis. The key findings shed light on the dynamics of corporate reputation and crisis communication and the impacts on interactive marketing. Critical components of crisis communication are identified to include monitoring, tactics of responding, and response management. Linkages between these, crisis communication theories, and corporate reputation are synthesised. Indications are provided on how the crisis can affect the corporate reputation and the significance of the speed of preventive communication measures.

Performance analysis of classification between a particular number and average using the same distance measurements

Performance analysis of classification between a particular number and average using the same distance measurements

Interference of Cultural Codes of the CIS Countries of Central Asia: Civilizational Transformations

For centuries, Turkic peoples have lived in close interaction, which contributed to the formation of similar cultural traditions, languages and customs. This has made them a unique and distinctive historical and cultural area on the map of Eurasia. The study of the interpenetration of cultural codes of the CIS countries of the Central Asian region becomes particularly relevant, as it allows us to identify the main trends and patterns of interference of interacting cultures.The novelty of the study lies in the methodological approach to the analysis of cultural codes of nations, according to which the interference of cultural codes is considered here as an instrument of cultural interpenetration, which reveals the specific relationship between cultural codes and national identity, as well as identifies the reasons for the universalization of cultural codes of border cultures.The purpose of this paper is to explore precisely those features of cross-border cultural interaction that fall under the description of cultural interference in its original sense, which implies spontaneous, uncontrolled cultural interpenetration resulting in the strengthening of some characteristics and weakening of others, in the absence of a dominant culture and deliberate influence on the qualitative characteristics of each of the interacting cultures. This publication offers an analysis of the spontaneity and uncontrollability of civilizational transformations of border cultures, acting as a natural process of interference of cultural codes. The research material is the cultural practices of the CIS countries of the Central Asian region.The main study measures used are conceptual and phenomenological analysis, axiological and analytical research techniques, method of classification analysis, etc.The study of the CIS countries of Central Asia revealed a number of coinciding elements of culture of these countries, indicating the presence of their common national cultural and civilizational identity, which stem not only from the cultural roots common to these peoples, but also a consequence of cultural interference and integration in the process of centuries of coexistence in the neighboring territories.

Predictive modeling and benchmarking for diamond price estimation: integrating classification, regression, hyperparameter tuning and execution time analysis

Predictive modeling and benchmarking for diamond price estimation: integrating classification, regression, hyperparameter tuning and execution time analysis

Combining Quantitative Susceptibility Mapping With the Gray Matter Volume to Predict Neurological Deficits in Patients With Small Artery Occlusion.

Currently, there is still a lack of valuable neuroimaging markers to assess the clinical severity of stroke patients with small artery occlusion (SAO). Quantitative susceptibility mapping (QSM) is a quantitative processing method for neuroradiological diagnostics. Gray matter (GM) volume changes in stroke patients are also proved to be associated with neurological deficits. This study aims to explore the predictive value of QSM and GM volume in neurological deficits of patients with SAO. As neurological deficits, the National Institutes of Health Stroke Scale (NIHSS) was used. Sixty-six SAO participants within 24h of first onset were enrolled and divided into mild and moderate groups based on NIHSS. QSM values of infarct area and GM volume were calculated from magnetic resonance imaging (MRI) data. Two-sample t-tests were used to compare differences in QSM value and GM volume between the two groups, and the diagnostic efficacy of the combination of QSM value and GM volume was evaluated. The results revealed both the QSM value and GM volume within the infarct area of the moderate group were lower compared to the mild group. Moderate group exhibited lower GM volume in some specific gyrus compared with mild group in the case of voxel-wise GM volume on whole-brain voxel level. The support vector machine (SVM) classifier's analysis showed a high power for the combination of QSM value, GM volume within the infarct area, and voxel-wise GM volume. Our research first reported the combination of QSM value, GM volume within the infarct area, and voxel-wise GM volume could be used to predict neurological impairment of patients with SAO, which provides new insights for further understanding the SAO stroke.

Early monitoring of drought stress in safflower (Carthamus tinctorius L.) using hyperspectral imaging: a comparison of machine learning tools and feature selection approaches

Early detection of drought stress is essential for preventing permanent plant damage and minimizing yield loss. This study utilized hyperspectral imaging at the leaf level to visualize drought stress in safflower plants (Carthamus tinctorius L.). Three safflower genotypes, Palenus, A82, and IL-111, were cultivated under three irrigation levels. Stress conditions were simulated by depleting 50%, 70%, and 90% of soil water content, representing unstressed (US), mild stress (MS), and severe stress (SS) conditions, respectively. Hyperspectral images of leaf samples were captured before any visible signs of water scarcity emerged. Classification analysis was performed using the full mean spectral data with partial least squares discriminant analysis, soft independent modeling of class analogy (SIMCA), support vector machines, and artificial neural network (ANN) classifiers. Feature selection methods were applied to extract the most informative wavebands, and ANN was used to build predictive models. Spatial analysis involved pixel-wise classification using both unsupervised (k-means clustering) and supervised (best classifiers) approaches. ANN outperformed other classifiers using the entire spectral data, effectively distinguishing US, MS, and SS classes in the Palenus, A82, and IL-111 genotypes, achieving F1-scores of 92.22%, 96.01%, and 96.47%, respectively. Among the feature selection methods, SIMCA-based features excelled in monitoring stress conditions in the Palenus and A82 genotypes. In supervised spatial analysis, ANN models clearly depicted the progression of stress in leaves across different genotypes. This study demonstrates the potential of hyperspectral imaging to differentiate various levels of drought stress in safflower, an important oilseed crop.