Level Classification Research Articles

Automatic Extraction of Skin and Soft Tissue Infection Status from Clinical Notes.

The reliable identification of skin and soft tissue infections (SSTIs) from electronic health records is important for a number of applications, including quality improvement, clinical guideline construction, and epidemiological analysis. However, in the United States, types of SSTIs (e.g. is the infection purulent or non-purulent?) are not captured reliably in structured clinical data. With this work, we trained and evaluated a rule-based clinical natural language processing system using 6,576 manually annotated clinical notes derived from the United States Veterans Health Administration (VA) with the goal of automatically extracting and classifying SSTI subtypes from clinical notes. The trained system achieved mention- and document-level performance metrics of the range 0.39 to 0.80 for mention level classification and 0.49 to 0.98 for document level classification.

Application of Naive Bayes Algorithm for Physical Fitness Level Classification

The implementation of physical fitness tests requires adequate facilities, so technology is needed to make it easier without having to provide facilities. The purpose of this study is to make it easier to get the results of a person's physical fitness level using age, gender, height and weight data through an intelligent system using the naïve Bayes algorithm without having to do a physical fitness test. This research is included in the Experimental research. The method used in this study used machine learning and classification with the naïve Bayes algorithm. Data analysis techniques use probability by using data tests and evaluations. The evaluation used uses accuracy. The population in this study was 100 college students. Training model scheme 98 and test 2 get an accuracy value when training is 100%, on testing an accuracy value of 50%. The best model is used as a reference in predicting new data, using 5 new data where 3 data already know the VO2Max value with the same prediction value and actual value, then 2 new data are not yet known VO2Max value, the 4th data gets a value of 44.2 and the 5th data gets a value of 33.2. The results of VO2Max testing using the naïve Bayes algorithm are declared accountable. Contribution to future research is to multiply research datasets to improve accuracy and improve user interface quality through development research.

Study on the positivity rate and influencing factors of anxiety in pregnant women during the first fetal magnetic resonance examination: A cross-sectional study.

This study investigated the positive rate and related influencing factors of anxiety screening in pregnant women during the first fetal magnetic resonance examination. A total of 303 pregnant women who met the criteria for magnetic resonance pregnancy examination in a Grade III maternity hospital from December 2021 to December 2022 were included by the convenience sampling method. A cross-sectional survey was conducted before the examination using the General Situation Questionnaire and Self-rating Anxiety Scale (SAS). The positive rate of anxiety was 31.02% (94/303), and the average score of anxiety was 45.71±9.84. Univariate analysis results showed that age, educational level, occupation, place of residence, per capita monthly income, and number of pregnancies were related to the anxiety status of pregnant women in the fetal magnetic resonance examination (P<0.05). The results of logistic regression analysis showed that the factor of college degree [OR: 2.168, 95% CI: (1.119, 4.273)] in the classification of cultural level and country factor [OR: 2.162, 95% CI: (1.066, 4.385)] in the classification of place of residence had an impact on the anxiety score of pregnant women in the fetal magnetic resonance examination (P<0.05). The positive rate of anxiety screening of pregnant women before the first prenatal magnetic resonance examination is high. A low education level and living in the countryside will increase the probability of anxiety in pregnant women during magnetic resonance examination. Based on the above research results, it is suggested that medical institutions pay attention to the mental health of pregnant women, improve mental health care services, and reduce the adverse psychological problems caused by prenatal examination.

EEG-based hierarchical classification of level of demand and modality of auditory and visual sensory processing

Objective. To date, most research on electroencephalography (EEG)-based mental workload detection for passive brain-computer interface (pBCI) applications has focused on identifying the overall level of cognitive resources required, such as whether the workload is high or low. We propose, however, that being able to determine the specific type of cognitive resources being used, such as visual or auditory, would also be useful. This would enable the pBCI to take more appropriate action to reduce the overall level of cognitive demand on the user. For example, if a high level of workload was detected and it is determined that the user is primarily engaged in visual information processing, then the pBCI could cause some information to be presented aurally instead. In our previous work we showed that EEG could be used to differentiate visual from auditory processing tasks when the level of processing is high, but the two modalities could not be distinguished when the level of cognitive processing demand was very low. The current study aims to build on this work and move toward the overall objective of developing a pBCI that is capable of predicting both the level and the type of cognitive resources being used. Approach. Fifteen individuals undertook carefully designed visual and auditory tasks while their EEG data was being recorded. In this study, we incorporated a more diverse range of sensory processing conditions including not only single-modality conditions (i.e. those requiring one of either visual or auditory processing) as in our previous study, but also dual-modality conditions (i.e. those requiring both visual and auditory processing) and no-task/baseline conditions (i.e. when the individual is not engaged in either visual or auditory processing). Main results. Using regularized linear discriminant analysis within a hierarchical classification algorithm, the overall cognitive demand was predicted with an accuracy of more than 86%, while the presence or absence of visual and auditory sensory processing were each predicted with an accuracy of approximately 70%. Significance. The findings support the feasibility of establishing a pBCI that can determine both the level and type of attentional resources required by the user at any given moment. This pBCI could assist in enhancing safety in hazardous jobs by triggering the most effective and efficient adaptation strategies when high workload conditions are detected.

Detecting Dehydration Based on Urine Color Using Fuzzy Logic Image Processing and Regulating Water Intake with an Automatic Water Pump According to Dehydration Level Using an IoT-Based

Dehydration is a condition where the body lacks the fluids it needs to carry out its functions optimally. Dehydration can cause various health problems, including decreased mental and physical performance, and can even cause death if not treated immediately. Therefore, it is important to be able to detect and treat dehydration early. One way to detect dehydration is through urine color analysis. Urine that is darker than normal can be a sign of dehydration. The classification of dehydration level according to urine color is as follows: 1-2: Hydrated, 3-4: Mildly dehydrated, 5-6: Dehydrated, 7-8: Very dehydrated. This research aims to develop an IoT-based dehydration detection system that can detect the level of dehydration in a person based on urine color and regulate water intake automatically using a water pump. The novelty of this research is the method of integrating drinking water intake with dehydration detection based on real-time urine color based on IoT using the Fuzzy Logic method. The results of this research are used by the Jember State Polytechnic TeFa Nutrition Care Center (NCC) in serving patients. The methodology used in this research is Fuzzy Logic image processing to process urine color data and determine a person's level of dehydration. After carrying out this research, the following conclusions were obtained: Based on the literature study in this research, 8 levels of hydration status according to NSW Health were obtained, then from this literature a method was obtained to measure a person's hydration based on urine color using image processing using the Fuzzy Logic method.

The Classification of Aflatoxin Contamination Level in Cocoa Beans using Fluorescence Imaging and Deep learning

Aflatoxin contamination in cacao is a significant problem in terms of trade losses and health effects. This calls for the need for a non-invasive, precise, and effective detection strategy. This research contribution is to determine the best deep-learning model to classify the aflatoxin contamination level in cocoa beans based on fluorescence images and deep learning to improve performance in the classification. The process involved inoculating and incubating Aspergillus flavus (6mL/100g) to obtain aflatoxin-contaminated cocoa beans for 7 days during the incubation period. Liquid Mass Chromatography (LCMS) was used to quantify the aflatoxin in order to categorize the images into different levels including “free of aflatoxin”, “contaminated below the limit”, and “contaminated above the limit”. 300 images were acquired through a mini studio equipped with UV lamps. The aflatoxin level was classified using several pre-trained CNN approaches which has high accuracy such as GoogLeNet, SqueezeNet, AlexNet, and ResNet50. The sensitivity analysis showed that the highest classification accuracy was found in the GoogLeNet model with optimizer: Adam and learning rate: 0.0001 by 96.42%. The model was tested using a testing dataset and obtain accuracy of 96% based on the confusion matrix. The findings indicate that combining CNN with fluorescence images improved the ability to classify the amount of aflatoxin contamination in cacao beans. This method has the potential to be more accurate and economical than the current approach, which could be adapted to reduce aflatoxin's negative effects on food safety and cacao trade losses.

Classification of the Crosslink Density Level of Para Rubber Thick Film of Medical Glove by Using Near-Infrared Spectral Data.

Classification of the crosslink density level of para rubber medical gloves by using near-infrared spectral data combined with machine learning is the first time reported in this paper. The spectra of medical glove samples with different crosslink densities acquired by an ultra-compact portable MicroNIR spectrometer were correlated with their crosslink density levels, which were referencely evaluated by the toluene swell index (TSI). The machine learning protocols used to classify the 3 groups of TSI were specified as less than 80% TSI, 80-88% TSI, and more than 88% TSI. The 80-88% TSI group was the group in which the compounded latex was suitable for medical glove production, which made the glove specification comply with the requirements of customers as indicated by the tensile test. The results show that when comparing the algorithms used for modeling, the linear discriminant analysis (LDA) developed by 2nd derivative spectra with 15 k-best selected wavelengths fairly accurately predicted the class but was most reliable among other algorithms, i.e., artificial neural networks (ANN), support vector machines (SVM), and k-nearest neighbors (kNN), due to higher prediction accuracy, precision, recall, and F1-score of the same value of 0.76 and no overfitting or underfitting prediction. This developed model can be implemented in the glove factory for screening purposes in the production line. However, deep learning modeling should be explored with a larger sample number required for better model performance.

Applying cluster analysis in Bulgarian chemical industry for the period 2010-2020

This paper discusses the territorial organization of the chemical industry in Bulgaria. Using the ESRI ArcGIS software and applying cluster analysis, the study aims to group (cluster) the 28 Bulgarian districts (NUTS 3 level classification) based on produced output, persons employed, and Bulgarian lev (BGN) equivalent of foreign exchange earnings from exports for the period 2010-2020. Three reference years, 2010, 2015, and 2020, have been selected for the observed period. The general conclusion is that the chemical industry in Bulgaria is characterized by high territorial concentration. Varna was the leading district in developing the chemical industry in the observed period from 2010 to 2020, followed by Plovdiv, Ruse, and Sofia (the capital). At the other pole were the districts of Vidin, Montana, Vratsa, Pleven, Lovech, Razgrad, Silistra, Targoviste, Dobrich, Pernik, Kyustendil, Blagoevgrad, Sliven, Yambol, and Kardzhali. The findings of the research show that territorial polarization is linked with several factors that can be grouped according to their impact into four groups: 1) raw material and energy, 2) transport infrastructure and proximity to the end user, 3) state and environmental regulations, and 4) provision of skilled labor.

Index and Sustainability Status of Agricultural Mechanization for Paddy Field in Indonesia

The use of agricultural machinery is one of the important factors in increasing agricultural production. A quantitative assessment of the agricultural mechanization index and its impact on agricultural production is needed in planning the development of agricultural mechanization nationally. This study aims to determine the value of the agricultural mechanization index which consists of the degree, level, and capacity of agricultural mechanization for tools and agricultural machinery for pre-harvest rice (2-wheel tractor, 4-wheel tractor, water pump, and rice transplanter). This research was conducted in several stages, namely collecting data, observing the working capacity of 3 units of machinery for each type of machinery, processing data and making agricultural mechanization index maps. Based on the results of the study, it was found that the average value of the degree of agricultural mechanization for 2-wheel tractors, 4-wheel tractors, water pumps and rice transplanters was 56.68%, 55.13%, 10.55 % and 13.94%. The average value of mechanization level in Indonesia is 0.45 hp/ha and the average value of mechanization capacity for rice pre-harvest activities in Indonesia is 1.28 kW hour/ha. In addition, based on the results of the classification of mechanization level, cropping index and rice productivity, it can be seen that the provinces of East Java, Central Java, West Java, Banten, DI Yogyakarta and Aceh are provinces that are recommended to increase the number of agricultural machinery, especially 2-wheel tractors, 4-wheel tractors. water pump and rice transplanter.

Near infrared spectroscopy for the classification of vigor level of soybean seed

Near infrared spectroscopy for the classification of vigor level of soybean seed

Evaluation of the relationship between end-tidal carbon dioxide level and heart failure classification.

Heart failure is a disease with cardiac dysfunction, and its morbidity and mortality are associated with the degree of dysfunction. The New York Heart Association classifies the heart failure stages based on the severity of symptoms and physical activity. End-tidal carbon dioxide refers to the level of carbon dioxide that a person exhales with each breath. End-tidal carbon dioxide levels can be used in many clinical conditions such as heart failure, asthma, and chronic obstructive pulmonary disease. The aim of the study was to reveal the relationship between end-tidal carbon dioxide levels and the New York Heart Association classification of heart failure stages. This study was conducted at Kahramanmaraş Sütçü İmam University Faculty of Medicine Adult Emergency Department between 01/03/2019 and 01/09/2019. A total of 80 patients who presented to the emergency department with a history of heart failure or were diagnosed with heart failure during admission were grouped according to the New York Heart Association classification of heart failure stages. The laboratory parameters, ejection fraction values, and end-tidal carbon dioxide levels of the patients were measured and recorded in the study forms. End-tidal carbon dioxide levels and ejection fraction values were found to be significantly lower in the stage 4 group compared to the other groups. Furthermore, pro-B-type natriuretic peptide (BNP) values were found to be significantly higher in stage 4 group compared to the other groups. It was concluded that end-tidal carbon dioxide levels could be used together with pro-BNP and ejection fraction values in determining the severity of heart failure.

Using 2 Versions of the Test of Gross Motor Development to Classify and Screen Young Children's Motor Skills: A Comparison Study.

The purpose of this study was to examine comparability between 2 editions of the Test of Gross Motor Development (TGMD-second and TGMD-third edition) on (1) how children's motor skills were categorized as average or below average, and (2) how children are screened for being at-risk for motor delay or with delayed motor skills. Participants were 226 children (Mage = 53.4mo, 125 boys). All children completed full TGMD-2 and TGMD-3. Children were classified as average or above (>25th percentile) or below average (≤25th percentile) and, when applicable, as developmental delay (≤5th percentile) or at-risk for developmental delay (6-25th percentile). We compared children's classifications across TGMD editions using percent agreement and chi-squared tests. The TGMD-2 and TGMD-3 had moderate agreement when categorizing children as below average (72.2% for total skills, 76.0% for locomotor skills, and 73% for ball skills). The TGMD-3 was significantly more likely to categorize children's motor skill performance as average or above (all P < .01). TGMD-2 and TGMD-3 similarly screen children who demonstrate below average skills (≤25th percentile), but not for specific skill level classifications, including above average, at-risk for delays, and delayed.

An Analysis of Challenges Facing the Implementation of Namibia Senior Secondary Certificate Advanced Subsidiary

The study intended to explore the readiness of the implementation of Namibia Senior Secondary Certificate Advanced Subsidiary in secondary schools in Ohangwena region. A qualitative research methodology was used, carried out through a case study design. Purposive sampling was used to select participants for the study. Questionnaires and interview were used as data collection methods. The collected data was analysed using thematic analysis. Key findings revealed that participants were unaware of the criteria’s used to select the schools that shall offer Advanced Subsidiary Curricullum. Schools that offer Advanced Subsidiary seemed to have been selected based on assumptions such as human capital, availability of resources and infrastructures, teachers experience and former Namibia Senior Secondary School Certificate Higher level classification. Teachers experienced difficulties in implementing and managing the Advanced Subsidiary curriculum due to numerous factors such as late release of grade 11 Namibia Senior Secondary School Certificate Ordinary level results, lack of teaching and learning resources, dilapidated facilities, shortage of teachers who are experienced in teaching higher level subjects, complex and lengthy Advanced Subsidiary content that cannot be covered within the time frame allocated for instruction and assessment. The study concluded that curriculum planning and rolling out of the AS-Level curriculum was not done after proper consultations. If consultations were done, schools could have been provided with enough resources before introducing the curriculum. This would have ensured that schools were prepared to roll-out the implementation of the AS-Level curriculum with minimum to no hurdles at all.

Movement Representation Learning for Pain Level Classification

Movement Representation Learning for Pain Level Classification

Exploration of image level classification based on semantic segmentation

Semantic segmentation is a fundamental computer vision task where an image is divided into segments, with each segment assigned a class label based on its visual content. The objective is to achieve a pixel-level understanding of the image, enhancing machines' ability to comprehend and interpret visual scenes. This technique finds utility across diverse domains such as autonomous driving, medical image analysis, scene comprehension, and image editing, among others. Traditional per-pixel classification methods often encounter challenges related to class imbalances within segmentation datasets. To address this, a novel approach has been proposed, leveraging human-provided hints or auxiliary training signals derived from contextual modeling in segmentation. Human-in-the-loop techniques are employed to validate subtasks, correcting segmentation errors and enhancing mean Intersection over Union (mIoU) metrics without the need for additional trained parameters.

Research on Multidimensional Data Analysis and Predictive Modeling for International Political Stability Assessment

Abstract International political stability has been a hot issue of global concern. Starting from the factors influencing international political stability, the study constructs a prediction model based on the CNN neural network and takes some international countries as the case study objects to predict the political stability of each country. The system of political stability influencing factor indicators is constructed. 13 influencing factor indicators are selected and divided into three categories, and the warning intervals of early warning indicators are determined. The study trained and validated the CNN neural network model, and the results showed that the mean square error of the prediction model was 1.862 × 108, the average accuracy of the model was 1.53%, and the relative error of each year was within ±4%, which reached the set model accuracy, and thus the prediction model proposed in this paper can be highly accurate. Subsequently, 44 countries along the route were selected to carry out political stability prediction research using the early warning model, and finally, the political stability of some countries was investigated according to the stability interval level classification method, and the results showed that the political stability of Syria, Iran, and many other countries had a high-risk phenomenon.

Phenotyping of Drought-Stressed Poplar Saplings Using Exemplar-Based Data Generation and Leaf-Level Structural Analysis.

Drought stress is one of the main threats to poplar plant growth and has a negative impact on plant yield. Currently, high-throughput plant phenotyping has been widely studied as a rapid and nondestructive tool for analyzing the growth status of plants, such as water and nutrient content. In this study, a combination of computer vision and deep learning was used for drought-stressed poplar sapling phenotyping. Four varieties of poplar saplings were cultivated, and 5 different irrigation treatments were applied. Color images of the plant samples were captured for analysis. Two tasks, including leaf posture calculation and drought stress identification, were conducted. First, instance segmentation was used to extract the regions of the leaf, petiole, and midvein. A dataset augmentation method was created for reducing manual annotation costs. The horizontal angles of the fitted lines of the petiole and midvein were calculated for leaf posture digitization. Second, multitask learning models were proposed for simultaneously determining the stress level and poplar variety. The mean absolute errors of the angle calculations were 10.7° and 8.2° for the petiole and midvein, respectively. Drought stress increased the horizontal angle of leaves. Moreover, using raw images as the input, the multitask MobileNet achieved the highest accuracy (99% for variety identification and 76% for stress level classification), outperforming widely used single-task deep learning models (stress level classification accuracies of <70% on the prediction dataset). The plant phenotyping methods presented in this study could be further used for drought-stress-resistant poplar plant screening and precise irrigation decision-making.

상수관망 관리를 위한 3D 공간정보 시스템 및 모델 프로토타입 개발

Recently, water supply problems and the advent of the 4th Industrial Revolution, smart water supply network management using digital twin technology is becoming needs. In this study, to develop a prototype of the model and system 3D visualization information system for water supply network management based on own technology without restrictions on licenses. Based on the data from the ME(2017), an inventory DB according to the Level classification was established, and for 3D visualization based on 2D information systems, 9-steps of implementation process and verification were conducted. Comparing and analyzing the values of latitude and longitude of polygons, it was confirmed that the reliability and accuracy of the two-dimensional information system implemented in this study were secured. Therefore, 3D visualization was performed using this, and the process of designing data linkage plans within the program and implementing 3D visualization was established. The results of this study are considered insignificant in the construction of a network management space server with high economic benefits and high reliability and accuracy of GIS.

BD-SKUNet: Selective-Kernel UNets for Building Damage Assessment in High-Resolution Satellite Images

When natural disasters occur, timely and accurate building damage assessment maps are vital for disaster management responders to organize their resources efficiently. Pairs of pre- and post-disaster remote sensing imagery have been recognized as invaluable data sources that provide useful information for building damage identification. Recently, deep learning-based semantic segmentation models have been widely and successfully applied to remote sensing imagery for building damage assessment tasks. In this study, a two-stage, dual-branch, UNet architecture, with shared weights between two branches, is proposed to address the inaccuracies in building footprint localization and per-building damage level classification. A newly introduced selective kernel module improves the performance of the model by enhancing the extracted features and applying adaptive receptive field variations. The xBD dataset is used to train, validate, and test the proposed model based on widely used evaluation metrics such as F1-score and Intersection over Union (IoU). Overall, the experiments and comparisons demonstrate the superior performance of the proposed model. In addition, the results are further confirmed by evaluating the geographical transferability of the proposed model on a completely unseen dataset from a new region (Bam city earthquake in 2003).

Extracapsular dissection via single cervical incision for parotid pleomorphic adenoma.

Surgical management of parotid pleomorphic adenoma ranges from total parotidectomy to extracapsular dissection (ECD). Minimalistic techniques aim to preserve function and minimize the rate of recurrence. This study assesses functional, aesthetic, and disease control outcomes post-ECD through a sole transverse cervical incision for parotid pleomorphic adenoma. This longitudinal analysis enrolled 36 consecutive patients with pleomorphic adenoma who underwent ECD via a single cervical incision. Complications, satisfaction, salivary function, and tumor recurrence were evaluated. Salivary gland function was assessed using scintigraphy at 6 months post-surgery. Tumors occurred in superficial (83%) or deep (17%) parotid inferior parts according to the European Salivary Gland Society level classification. The median tumor size was 2.8 cm (1.8-6.0 cm); the median operation time was 42 min (30-65 min). No tumor spillage or facial nerve injuries occurred. Facial nerve paralysis was only temporary in two (6%) patients, with minimal other complications. Operated parotid gland function matched the unoperated side. No recurrence was found during the median follow-up of 44 months (24-60 months). ECD via a single transverse cervical incision is a safe approach for benign parotid tumors, yielding excellent functional and disease control outcomes. These findings can provide clinically meaningful minimally invasive recommendations to treat pleomorphic adenoma with minimal complications.