Classification Protocol Research Articles

Prevalence and risk factors associated with dysglycemia among overweight and obese Palestinian adolescents in the Hebron governorate

Background: The prevalence of dysglycemia among adolescents and younger children has been rising, yet health professionals are still unaware of the significance of this problem. According to the Palestinian Ministry of Health (MOH) records, most diabetic children under the age of 20 in Palestine are classified as type 1; nonetheless, very limited data are available for policymakers to frame cost-effective screening programs. This study aims to determine the prevalence of dysglycemia in a sample of obese and overweight Palestinian adolescents, identify risk factors associated with dysglycemia, and examine risk factors variance by gender. Methods: A cross-sectional sample of observed obese and overweight adolescents was selected from public schools in the Hebron governorate. Informed consent, physical examination, anthropometric, and laboratory tests (Random Blood Glucose Level (BGL) and fasting BGL ) were performed on a sample of 511 students (44.6% boys and 55.4% girls) aged 13–18-years (13-15 years =46.2% and 16-18 years =53.8%). Results: The prevalence of confirmed overweight and obese cases was 73.2%, and dysglycemia prevalence among the confirmed cases was 3.7% (5.3% boys and 2.5% girls). The BMI classifications of the dysglycemic children indicated that 42.1% were overweight and 31.1% were obese. Furthermore, 64.6% reported high systolic and/or diastolic blood pressure readings. Conclusions: The results of this study provide valuable information about the rising problem of dysglycemia among Palestinian adolescents and underlines the need for rapid screening programs and protocols for early detection and classification of the disease, leading to initiation of early prevention and treatment plans.

Development of a risk classification protocol for cancer patients in Home-based Palliative Care

RESUMO Os serviços de Cuidados Paliativos Domiciliares especializados no tratamento de pacientes oncológicos têm como objetivo identificar e controlar sintomas físicos, psicossociais e espirituais em domicílio. Alguns desafios encontrados são a complexidade de sintomas, a sobrevida reduzida dos pacientes com câncer avançado e limitações do sistema de saúde. Para estratificar a prioridade de atendimento dos pacientes com câncer avançado em Cuidados Paliativos Domiciliares, foi elaborado um protocolo de classificação de risco. Este artigo é um relato de experiência sobre o processo de elaboração de um protocolo de classificação de risco para pacientes com câncer avançado atendidos em um serviço de Cuidados Paliativos Domiciliares no Rio de Janeiro. A etapa inicial envolveu reuniões da equipe da Assistência Domiciliar de um hospital oncológico e buscas estruturadas na literatura. Depois, foram listadas as situações clínicas de manejo mais complexo no domicílio, chamadas de sinais e sintomas de alerta: dor, falta de ar, náuseas/ vômitos, sangramento e confusão mental aguda. Elaborou-se um protocolo de avaliação e classificação de risco com cinco categorias/cores, para determinar a prioridade de atendimento dos pacientes. O sistema de triagem desenvolvido possui fácil aplicabilidade e requer um treinamento breve do profissional de saúde para que possa ser utilizado durante os atendimentos domiciliares.

Elaboração de um protocolo de classificação de risco para pacientes oncológicos em Cuidados Paliativos Domiciliares

ABSTRACT Home-based Palliative Care services specialized in the treatment of cancer patients aim to identify and control physical, psychosocial, and spiritual symptoms at home. Some challenges encountered are the complexity of symptoms, reduced survival of patients with advanced cancer, and limitations of the health care system. To stratify the priority of care for patients with advanced cancer in home Palliative Care, a risk classification protocol was developed. This article is an experience report on the process of creating a risk classification protocol for patients with advanced cancer treated at a home Palliative Care service in Rio de Janeiro. The initial stage involved meetings of the home care team at an oncology hospital and structured searches in the literature. Afterwards, the clinical situations of more complex management at home were listed and named as warning signs and symptoms: pain, shortness of breath, nausea/ vomiting, bleeding, and acute mental confusion. An assessment and triage protocol was developed with five categories/colors to determine the priority of patient care. The developed triage system has easy applicability and requires a brief training of the health professional so that it can be used during home visits.

Automated characterization of spatial and dynamical heterogeneity in supercooled liquids via implementation of machine learning

A computational approach by an implementation of the principle component analysis (PCA) with K-means and Gaussian mixture (GM) clustering methods from machine learning algorithms to identify structural and dynamical heterogeneities of supercooled liquids is developed. In this method, a collection of the average weighted coordination numbers () of particles calculated from particles’ positions are used as an order parameter to build a low-dimensional representation of feature (structural) space for K-means clustering to sort the particles in the system into few meso-states using PCA. Nano-domains or aggregated clusters are also formed in configurational (real) space from a direct mapping using associated meso-states’ particle identities with some misclassified interfacial particles. These classification uncertainties can be improved by a co-learning strategy which utilizes the probabilistic GM clustering and the information transfer between the structural space and configurational space iteratively until convergence. A final classification of meso-states in structural space and domains in configurational space are stable over long times and measured to have dynamical heterogeneities. Armed with such a classification protocol, various studies over the thermodynamic and dynamical properties of these domains indicate that the observed heterogeneity is the result of liquid–liquid phase separation after quenching to a supercooled state.

A proposed methodology for detecting the malignant potential of pulmonary nodules in sarcoma using computed tomographic imaging and artificial intelligence-based models.

The presence of lung metastases in patients with primary malignancies is an important criterion for treatment management and prognostication. Computed tomography (CT) of the chest is the preferred method to detect lung metastasis. However, CT has limited efficacy in differentiating metastatic nodules from benign nodules (e.g., granulomas due to tuberculosis) especially at early stages (<5mm). There is also a significant subjectivity associated in making this distinction, leading to frequent CT follow-ups and additional radiation exposure along with financial and emotional burden to the patients and family. Even 18F-fluoro-deoxyglucose positron emission technology-computed tomography (18F-FDG PET-CT) is not always confirmatory for this clinical problem. While pathological biopsy is the gold standard to demonstrate malignancy, invasive sampling of small lung nodules is often not clinically feasible. Currently, there is no non-invasive imaging technique that can reliably characterize lung metastases. The lung is one of the favored sites of metastasis in sarcomas. Hence, patients with sarcomas, especially from tuberculosis prevalent developing countries, can provide an ideal platform to develop a model to differentiate lung metastases from benign nodules. To overcome the lack of optimal specificity of CT scan in detecting pulmonary metastasis, a novel artificial intelligence (AI)-based protocol is proposed utilizing a combination of radiological and clinical biomarkers to identify lung nodules and characterize it as benign or metastasis. This protocol includes a retrospective cohort of nearly 2,000-2,250 sample nodules (from at least 450 patients) for training and testing and an ambispective cohort of nearly 500 nodules (from 100 patients; 50 patients each from the retrospective and prospective cohort) for validation. Ground-truth annotation of lung nodules will be performed using an in-house-built segmentation tool. Ground-truth labeling of lung nodules (metastatic/benign) will be performed based on histopathological results or baseline and/or follow-up radiological findings along with clinical outcome of the patient. Optimal methods for data handling and statistical analysis are included to develop a robust protocol for early detection and classification of pulmonary metastasis at baseline and at follow-up and identification of associated potential clinical and radiological markers.

Mapping and analysis of volatomes from pearl millet (Pennisetum gaucum L.) grains during different storage conditions with solid‐phase microextraction–gas chromatography–mass spectrometry

AbstractBackground and ObjectivesVolatile organic compounds (VOCs) are considered biomarkers for the metabolic activities of biological entities. This work analyzed the impact of storage period and temperature (5°C, 25°C, and 45°C) on the VOC profile of pearl millet grains stored for 120 days through headspace gas analysis using solid‐phase microextraction–gas chromatography–mass spectroscopy (SPME‐GC‐MS).FindingsThe major groups identified in the pearl millet grains belonged to acid, alcohol, aldehyde, alkane, and ester groups. VOC data were analyzed using principal component analysis, partial least square discriminant analysis (PLS‐DA), cluster heat map, and network analysis of metabolite–metabolite interactions. The PLS‐DA could distinctly classify the VOCs generated with respect to different storage conditions. The VOCs generated during storage indicated the four most significant metabolic pathways, that is, fatty acid biosynthesis, cutin, suberine and wax biosynthesis, arginine biosynthesis, and arginine and proline metabolism.ConclusionsThe SPME‐GC‐MS protocol developed for mapping VOC through this study and the classification protocol developed can be used for developing quality monitoring systems in pearl millet grains.Significance and NoveltyIdentification of VOCs at a particular period will be helpful for the recommendation of appropriate remedial measures at the right time to avoid the spoilage of grains.

Prevalence and risk factors associated with dysglycemia among overweight and obese Palestinian children in the Hebron governorate

Background: The prevalence of dysglycemia among adolescents and younger children has been rising, yet health professionals are still unaware of the significance of this problem. According to the Palestinian Ministry of Health (MOH) records, most diabetic children under the age of 20 in Palestine are classified as type I; nonetheless, very limited data are available for policymakers to frame cost-effective screening programs. This study aims to determine the prevalence of dysglycemia in a sample of obese and overweight Palestinian children, identify risk factors associated with dysglycemia, and examine risk factors variance by gender. Methods: A cross-sectional sample of observed obese and overweight children was selected from public schools in the Hebron governorate. Informed consent, physical examination, anthropometric, and laboratory tests (Blood Glucose Level (BGL) and fasting BGL ) were performed on a sample of 511 students (44.6% boys and 55.4% girls) aged 13–18-years (13-15 years =46.2% and 16-18 years =53.8%). Results: The prevalence of confirmed overweight and obese cases was 73.2%, and dysglycemia prevalence among the confirmed cases was 3.7% (5.3% boys and 2.5% girls). The BMI classifications of the prediabetic children indicated that 42.1% were overweight and 31.1% were obese. Furthermore, 6.7% reported hypertension (both systolic and diastolic hypertension). Conclusions: The results of this study provide valuable information about the rising problem of dysglycemia among Palestinian children and underlines the need for rapid screening programs and protocols for early detection and classification of the disease, leading to initiation of early prevention and treatment plans.

Sociodemographic and clinical characteristics of hospital admissions for COVID-19: A retrospective cohort of patients in two hospitals in the south of Brazil

Background: This database aims to present the sociodemographic and clinical profile of a cohort of 799 patients hospitalized with coronavirus disease 2019 (COVID-19) in two hospitals in southern Brazil. Methods: Data were collected, retrospectively, from November 2020 to January 2021, from the medical records of all hospital admissions that occurred from 1 April 2020 to 31 December 2020. The analysis of these data can contribute to the definition of the clinical and sociodemographic profile of patients with COVID-19. Data description: This dataset covers 799 patients hospitalized for COVID-19, characterized by the following sociodemographic variables: sex, age group, race, marital status and paid work. The sex variable was collected as sex assigned at birth from medical records data. Clinical variables included: admission to clinical ward, hospitalization in the Intensive Care Unit, COVID-19 diagnosis, number of times hospitalized due to COVID, hospitalization time in days and risk classification protocol. Other clinical variables include: pulmonary impairment; patients ventilation pattern; high-flow oxygen mask; pulmonary thromboembolism; cardiovascular disease; pulmonary sepsis; influenza exam results. Other health problems: diabetes, systemic arterial hypertension, chronic obstructive pulmonary disease, obesity, tabaco smoking, asthma, chronic kidney disease, overweight, vascular accident, sedentary lifestyle, HIV/AIDS, cancer, Alzheimer's disease, Parkinson's disease. Conclusions: The analysis of these data can contribute to the definition of the clinical and sociodemographic profile of patients with COVID-19. Thus, a great social impact is demonstrated when databases are published. Open data accelerates the research process, facilitates reuse and enriches datasets, in addition to optimizing the application of public resources, that is, enabling more use of the same investment.

Terahertz Meets AI: The State of the Art.

Terahertz (THz) is a promising technology for future wireless communication networks, particularly for 6G and beyond. The ultra-wide THz band, ranging from 0.1 to 10 THz, can potentially address the limited capacity and scarcity of spectrum in current wireless systems such as 4G-LTE and 5G. Furthermore, it is expected to support advanced wireless applications requiring high data transmission and quality services, i.e., terabit-per-second backhaul systems, ultra-high-definition streaming, virtual/augmented reality, and high-bandwidth wireless communications. In recent years, artificial intelligence (AI) has been used mainly for resource management, spectrum allocation, modulation and bandwidth classification, interference mitigation, beamforming, and medium access control layer protocols to improve THz performance. This survey paper examines the use of AI in state-of-the-art THz communications, discussing the challenges, potentials, and shortcomings. Additionally, this survey discusses the available platforms, including commercial, testbeds, and publicly available simulators for THz communications. Finally, this survey provides future strategies for improving the existing THz simulators and using AI methods, including deep learning, federated learning, and reinforcement learning, to improve THz communications.

Predictive effect of TCED-HFV grading and imaging biomarkers on anti-VEGF therapy in diabetic macular edema

BackgroundTo evaluate the predictive effect of TCED-HFV grading and imaging biomarkers on anti-vascular endothelial growth factor (anti-VEGF) treatment in diabetic macular edema (DME).Methods81 eyes of 81 DME patients who were treated with anti-VEGF were included in this retrospective cohort study. All patients underwent a comprehensive ophthalmic examination at baseline and follow-up, including best-corrected visual acuity (BCVA), fundus photography, and spectral domain–optical coherence tomography (SD-OCT). Baseline imaging biomarkers were qualitatively and quantitatively graded according to the TCED-HFV classification protocol, and DME was divided into early stage, advanced stage, severe stage, and atrophy stage.ResultsSix months post treatment, central subfield thickness (CST) in 49 eyes (60.5%) had decreased by 10% from baseline, 30 eyes (37.0%) had achieved CST < 300 μm, and 45 eyes (55.6%) had BCVA improved by more than five letters. Multivariate regression analysis revealed that eyes with baseline CST ≥ 390 μm had a higher probability of ≥ 10% reduction in CST from baseline, and eyes with abundant hyperreflective dots (HRD) had a lower probability of 10% reduction in CST (all P < 0.05). Eyes with vitreomacular traction (VMT) or epiretinal membrane (ERM) at baseline were less likely to reach the end point of CST < 300 μm (P < 0.05). BCVA increases of more than five letters were less likely in eyes with baseline BCVA ≥ 69 letters, complete or partial destruction of ellipsoid zone (EZ) at baseline (all P < 0.05). TCED-HFV staging was negatively correlated with BCVA at both baseline and 6 months (Kendall’s tau-b=-0.39 and − 0.55, all P < 0.01). TCED-HFV staging was positively correlated with CST at 6 months (Kendall’s tau-b = 0.19, P = 0.049) and negatively correlated with the reduction of CST (Kendall’s tau-b=-0.32, P < 0.01).ConclusionThe TCED-HFV grading protocol facilitates a comprehensive assessment of DME severity, standardizes the grading of multiple imaging biomarkers, and predicts the anatomical and functional outcomes of anti-VEGF treatment.

SPINAL MUSCULAR ATROPHY CLINICAL FEATURES, CLASSIFICATION, NATURAL HISTORY, GENETICS, DIAGNOSIS, COMPLICATIONS AND TREATMENT OF THE DISEASE

Introduction: Spinal muscular atrophy (SMA) is a complex neuromuscular disorder, it is the most usual autosomal recessively inherited lethal neuromuscular disease in pediatrics, it presents a defective alteration in the survival motor neuron 1 (SMN1) gene. Spinal muscular atrophy clinically shows progressive weakness of skeletal and respiratory muscles. In recent years, drugs with encouraging results from phase II and III clinical trials have been presented. Objective: to detail current information related to spinal muscular atrophy, clinical features, classification, natural history, genetics, diagnosis, complications and treatment of the disease. Methodology: a total of 40 articles were analyzed in this review, including review and original articles, as well as clinical cases, of which 31 bibliographies were used because the other articles were not relevant to this study. The sources of information were PubMed, Google Scholar and Cochrane; the terms used to search for information in Spanish, Portuguese and English were: spinal muscular atrophy, Spinal Muscular Atrophy, spinal muscular atrophy and spinal muscular atrophy. Results: About 95 % of the occurrences of spinal muscular atrophy are generated by homozygous deletions. Individuals with 5q mutation make up 95% of cases of spinal muscular atrophy and the remaining 5% are generated by mutations in 5q1-5. Targeted treatments may prevent or delay the progression of some symptoms of spinal muscular atrophy. Conclusions: Spinal muscular atrophy (SMA) is an autosomal recessive neuromuscular disease characterized by muscle atrophy and weakness resulting from irreversible loss and progressive degeneration of the brainstem nuclei and anterior horn cells in the spinal cord (lower motor neurons). Clinically it presents with symmetrical proximal limb weakness that also impacts the axial muscles, intercostal and bulbar musculature and is progressive, and the classification protocol is important in genetics, as well as providing prognostic and clinical information. The natural history of the disease is variable and complicated. It is made by demonstrating a history of proximal muscle weakness, motor difficulties or regression, diminished or absent deep tendon reflexes. Among the most frequent complications in unsupported individuals are those previously mentioned such as poor weight gain with growth retardation, scoliosis, restrictive lung disease, joint contractures and sleep difficulties. In terms of treatment, several different compounds have been investigated in recent years, focused on increasing muscle strength and function. Proactive supportive treatment involving a multidisciplinary team is paramount to decrease the severity of symptoms. KEY WORDS: muscle atrophy, spine, spinal, spinal cord, motor neuron.

Ultra-low dose computed tomography protocols using spectral shaping for lung cancer screening: Comparison with low-dose for volumetric LungRADS classification

PurposeTo compare Low-Dose Computed Tomography (LDCT) with four different Ultra-Low-Dose Computed Tomography (ULDCT) protocols for PN classification according to the Lung Reporting and Data System (LungRADS). MethodsThree hundred sixty-one participants of an ongoing lung cancer screening (LCS) underwent single-breath-hold double chest Computed Tomography (CT), including LDCT (120kVp, 25mAs; CTDIvol 1,62 mGy) and one ULDCT among: fully automated exposure control (“ULDCT1”); fixed tube-voltage and current according to patient size (“ULDCT2”); hybrid approach with fixed tube-voltage (“ULDCT3”) and tube current automated exposure control (“ULDCT4”).Two radiologists (R1, R2) assessed LungRADS 2022 categories on LDCT, and then after 2 weeks on ULDCT using two different kernels (R1: Qr49ADMIRE 4; R2: Br49ADMIRE 3).Intra-subject agreement for LungRADS categories between LDCT and ULDCT was measured by the k-Cohen Index with Fleiss-Cohen weights. ResultsLDCT-dominant PNs were detected in ULDCT in 87 % of cases on Qr49ADMIRE 4 and 88 % on Br49ADMIRE 3. The intra-subject agreement was: κULDCT1 = 0.89 [95 %CI 0.82–0.96]; κULDCT2 = 0.90 [0.81–0.98]; κULDCT3 = 0.91 [0.84–0.99]; κULDCT4 = 0.88 [0.78–0.97] on Qr49ADMIRE 4, and κULDCT1 = 0.88 [0.80–0.95]; κULDCT2 = 0.91 [0.86–0.96]; κULDCT3 = 0.87 [0.78–0.95]; and κULDCT4 = 0.88 [0.82–0.94] on Br49ADMIRE 3.LDCT classified as LungRADS 4B were correctly identified as LungRADS 4B at ULDCT3, with the lowest radiation exposure among the tested protocols (median effective doses were 0.31, 0.36, 0.27 and 0.37 mSv for ULDCT1, ULDCT2, ULDCT3, and ULDCT4, respectively). ConclusionsULDCT by spectral shaping allows the detection and characterization of PNs with an excellent agreement with LDCT and can be proposed as a feasible approach in LCS.

Privacy-Preserving Decision-Tree Evaluation with Low Complexity for Communication

Due to the rapid development of machine-learning technology, companies can build complex models to provide prediction or classification services for customers without resources. A large number of related solutions exist to protect the privacy of models and user data. However, these efforts require costly communication and are not resistant to quantum attacks. To solve this problem, we designed a new secure integer-comparison protocol based on fully homomorphic encryption and proposed a client-server classification protocol for decision-tree evaluation based on the secure integer-comparison protocol. Compared to existing work, our classification protocol has a relatively low communication cost and requires only one round of communication with the user to complete the classification task. Moreover, the protocol was built on a fully homomorphic-scheme-based lattice that is resistant to quantum attacks, as opposed to conventional schemes. Finally, we conducted an experimental analysis comparing our protocol with the traditional approach on three datasets. The experimental results showed that the communication cost of our scheme was 20% of the cost of the traditional scheme.

AlphaFold2 reveals commonalities and novelties in protein structure space for 21 model organisms

Deep-learning (DL) methods like DeepMind’s AlphaFold2 (AF2) have led to substantial improvements in protein structure prediction. We analyse confident AF2 models from 21 model organisms using a new classification protocol (CATH-Assign) which exploits novel DL methods for structural comparison and classification. Of ~370,000 confident models, 92% can be assigned to 3253 superfamilies in our CATH domain superfamily classification. The remaining cluster into 2367 putative novel superfamilies. Detailed manual analysis on 618 of these, having at least one human relative, reveal extremely remote homologies and further unusual features. Only 25 novel superfamilies could be confirmed. Although most models map to existing superfamilies, AF2 domains expand CATH by 67% and increases the number of unique ‘global’ folds by 36% and will provide valuable insights on structure function relationships. CATH-Assign will harness the huge expansion in structural data provided by DeepMind to rationalise evolutionary changes driving functional divergence.

HBV-infected hepatocellular carcinoma can be robustly classified into three clinically relevant subgroups by a novel analytical protocol.

Liver cancer is the third leading cause of cancer-related death worldwide, and hepatocellular carcinoma (HCC) accounts for a relatively large proportion of all primary liver malignancies. Among the several known risk factors, hepatitis B virus (HBV) infection is one of the important causes of HCC. In this study, we demonstrated that the HBV-infected HCC patients could be robustly classified into three clinically relevant subgroups, i.e. Cluster1, Cluster2 and Cluster3, based on consistent differentially expressed mRNAs and proteins, which showed better generalization. The proposed three subgroups showed different molecular characteristics, immune microenvironment and prognostic survival characteristics. The Cluster1 subgroup had near-normal levels of metabolism-related proteins, low proliferation activity and good immune infiltration, which were associated with its good liver function, smaller tumor size, good prognosis, low alpha-fetoprotein (AFP) levels and lower clinical stage. In contrast, the Cluster3 subgroup had the lowest levels of metabolism-related proteins, which corresponded with its severe liver dysfunction. Also, high proliferation activity and poor immune microenvironment in Cluster3 subgroup were associated with its poor prognosis, larger tumor size, high AFP levels, high incidence of tumor thrombus and higher clinical stage. The characteristics of the Cluster2 subgroup were between the Cluster1 and Cluster3 groups. In addition, MCM2-7, RFC2-5, MSH2, MSH6, SMC2, SMC4, NCPAG and TOP2A proteins were significantly upregulated in the Cluster3 subgroup. Meanwhile, abnormally high phosphorylation levels of these proteins were associated with high levels of DNA repair, telomere maintenance and proliferative features. Therefore, these proteins could be identified as potential diagnostic and prognostic markers. In general, our research provided a novel analytical protocol and insights for the robust classification, treatment and prevention of HBV-infected HCC.

Privacy-preserving Naive Bayes classification based on secure two-party computation

&lt;abstract&gt;&lt;p&gt;With the proliferation of data and machine learning techniques, there is a growing need to develop methods that enable collaborative training and prediction of sensitive data while preserving privacy. This paper proposes a new protocol for privacy-preserving Naive Bayes classification using secure two-party computation (STPC). The key idea is to split the training data between two non-colluding servers using STPC to train the model without leaking information. The servers secretly share their data and the intermediate computations using cryptographic techniques like Beaver's multiplication triples and Yao's garbled circuits. We implement and evaluate our protocols on the MNIST dataset, demonstrating that they achieve the same accuracy as plaintext computation with reasonable overhead. A formal security analysis in the semi-honest model shows that the scheme protects the privacy of the training data. Our work advances privacy-preserving machine learning by enabling secure outsourced Naive Bayes classification with applications such as fraud detection, medical diagnosis, and predictive analytics on confidential data from multiple entities. The modular design allows embedding different secure matrix multiplication techniques, making the framework adaptable. This line of research paves the way for practical and secure data mining in a distributed manner, upholding stringent privacy regulations.&lt;/p&gt;&lt;/abstract&gt;

A Two-Step Ensemble-Based Genetic Algorithm for Land Cover Classification

Accurate land use and land cover (LULC) maps are effective tools to help achieve sound urban planning and precision agriculture. As an intelligent optimization technology, genetic algorithm (GA) has been successfully applied to various image classification tasks in recent years. However, simple GA faces challenges, such as complex calculation, poor noise immunity, and slow convergence. This research proposes a two-step ensemble protocol for LULC classification using a grayscale-spatial-based GA model. The first ensemble framework uses fuzzy c-means to classify pixels into those that are difficult to cluster and those that are easy to cluster, which aids in reducing the search space for evolutionary computation. The second ensemble framework uses neighborhood windows as heuristic information to adaptively modify the objective function and mutation probability of the GA, which brings valuable benefits to the discrimination and decision of GA. In this study, three research areas in Dangyang, China, are utilized to validate the effectiveness of the proposed method. The experiments show that the proposed method can effectively maintain the image details, restrain noise, and achieve rapid algorithm convergence. Compared with the reference methods, the best overall accuracy obtained by the proposed algorithm is 88.72%.

A importância do protocolo de classificação de risco e dor torácica em unidade de pronto atendimento

The aim was to understand and emphasize the importance of the risk classification and chest pain protocol in hospital institutions. This is an integrative literature review with descriptive analysis and a qualitative approach. carried out between August and September in the year 2022, with a search in the databases Medical Literature Analysis and Retrieval System Online, Latin American and Caribbean Literature in Health Sciences, Nursing Database and Scientific Electronic Library Online. For the search strategy, the following descriptors were used: Chest Pain, Emergency Room, Nursing, Emergency and their synonyms. Of the 132 articles found, 14 were selected to compose the sample. It was evidenced that risk classification and chest pain protocols are instruments that optimize patient care time, and in addition to guiding the team, offer autonomy to nurses and guarantee quality and effectiveness in care.

Physical and sensorial quality of arabica coffee cultivars submitted to two types of post-harvesting processing

The growing demand for better quality coffees has driven changes in the coffee production chain, mainly through the adoption of new technologies and management. Thus, this work was carried out aiming to evaluate the physical and sensorial quality of Arabica coffee cultivars, submitted to natural and pulped post-harvesting processing. The experiment was carried out following a randomized block design with three replications, in a split-plot scheme, with the plots consisting of five cultivars (Catucaí 2 SL, Catucaí 24/137, Catuaí IAC 44, Arara and Acauã); and the subplots by two processes, pulped and natural cherry. The harvest was carried out manually, harvesting the cherry fruits (ripe) in a sieve. The coffees were processed by the natural and pulped cherry methods. Drying was carried out on a covered suspended terrace, until the grains reached 11% ± 1 moisture (wet basis, bu). The following evaluations were carried out: sensorial analysis of the beverage according to the SCAA methodology, analysis of grain sieves according to the Official BrazilianCoffee Classification Protocol. The results show that all evaluated cultivars have a great potential for the production of specialty coffees in that studied environment. Differences were observed between cultivars both in the sensory quality of the beverage and in the grain size. Cultivar Arara presents a general average of final beverage grade higher than the other cultivars. Key-words: Arabica coffee; Coffee sieve size; natural processing; pulped cherries; specialty coffee.

Knowledge Conditioned Variational Learning for One-Class Facial Expression Recognition.

The openness of application scenarios and the difficulties of data collection make it impossible to prepare all kinds of expressions for training. Hence, detecting expression absent during the training (called alien expression) is important to enhance the robustness of the recognition system. So in this paper, we propose a facial expression recognition (FER) model, named OneExpressNet, to quantify the probability that a test expression sample belongs to the distribution of training data. The proposed model is based on variational auto-encoder and enjoys several merits. First, different from conventional one class classification protocol, OneExpressNet transfers the useful knowledge from the related domain as a constraint condition of the target distribution. By doing so, OneExpressNet will pay more attention to the descriptive region for FER. Second, features from both source and target tasks will aggregate after constructing a skip connection between the encoder and decoder. Finally, to further separate alien expression from training expression, empirical compact variation loss is jointly optimized, so that training expression will concentrate on the compact manifold of feature space. The experimental results show that our method can achieve state-of-the-art results in one class facial expression recognition on small-scale lab-controlled datasets including CFEE and KDEF, and large-scale in-the-wild datasets including RAF-DB and ExpW.