Accurate Classification System Research Articles

Multi-view expressive graph neural networks for 3D CAD model classification

The creation of effective content-based retrieval systems for the 3D models of engineering components created by Mechanical Computer Aided Design (MCAD) systems has been a subject of academic investigation since the 1990 s. Recently some of the most promising results have been reported by researchers using Deep Neural Nets (DNN) to classify industrial parts represented by collections of images generated from different viewpoints. Known as Multi-View Convolutional Neural Network (MVCNN) these systems have extended the architectures developed for 2D images analysis to handle 3D data by using a series of pictures rendered from different viewpoints. In 2016 Monti et al. used Graph Neural Networks (GNN) to classify the superpixel images for the first time and reported results which suggested that the approach could produce good classification accuracy (an observation confirmed by the application of GNNs to 2D image datasets of common objects such as MNIST and Cifar). To investigate the potential for GNNs to reason about spatial adjacency relationships this paper reports, for the first time, the application of GNNs to classifications of 3D MCAD models of mechanical components. Viewing GNN as a convolution operator, parallel GNN can be applied to multiple views of a 3D shape in the same way as CNN is structured in a MVCNN. After outlining the architecture implemented to support MVGNNs the impact of various hyperparameters on the expressive power are explored. When optimised these hyperparameters (located in both intra-layer and inter-layer structures) combined with the multi-view architecture produced a classification accuracy superior to previous methods. The results also suggest that GNNs have the potential to produce fast, accurate classification systems for 3D MCAD data using significantly smaller datasets than those used for transfer learning in MVCNNs.

New Electronic Tongue Sensor Array System for Accurate Liquor Beverage Classification.

The use of sensors in different applications to improve the monitoring of a process and its variables is required as it enables information to be obtained directly from the process by ensuring its quality. This is now possible because of the advances in the fabrication of sensors and the development of equipment with a high processing capability. These elements enable the development of portable smart systems that can be used directly in the monitoring of the process and the testing of variables, which, in some cases, must evaluated by laboratory tests to ensure high-accuracy measurement results. One of these processes is taste recognition and, in general, the classification of liquids, where electronic tongues have presented some advantages compared with traditional monitoring because of the time reduction for the analysis, the possibility of online monitoring, and the use of strategies of artificial intelligence for the analysis of the data. However, although some methods and strategies have been developed, it is necessary to continue in the development of strategies that enable the results in the analysis of the data from electrochemical sensors to be improved. In this way, this paper explores the application of an electronic tongue system in the classification of liquor beverages, which was directly applied to an alcoholic beverage found in specific regions of Colombia. The system considers the use of eight commercial sensors and a data acquisition system with a machine-learning-based methodology developed for this aim. Results show the advantages of the system and its accuracy in the analysis and classification of this kind of alcoholic beverage.

Mathematical Approach in Image Classification using Regression

This study presents a comprehensive evaluation of logistic regression in contrast to a hybrid model combining VGG16 with logistic regression for image classification tasks. The research findings illuminate a striking performance disparity between these two approaches, shedding light on the profound impact of integrating deep learning techniques into image classification. The transition from logistic regression to the VGG16-based hybrid model marks a notable turning point in our investigation. The VGG16 architecture, renowned for its prowess as a feature extractor, showcases an impressive 53.33% surge in accuracy compared to the conventional logistic regression model. This substantial leap underscores the model's capacity to decipher complex image characteristics that elude traditional statistical methods. Furthermore, precision, a crucial metric in classification tasks, experiences a substantial 53% augmentation when adopting the VGG16 hybrid approach. This enhancement signifies the hybrid model's ability to minimize false positives, making it particularly valuable in scenarios where precision holds paramount importance. Equally noteworthy is the substantial 54% improvement observed in both recall and F1-score, emphasizing the VGG16 hybrid model's remarkable capacity to identify and retrieve a higher proportion of true positives while maintaining a balance between precision and recall. This not only amplifies the model's ability to correctly classify images but also mitigates the risk of overlooking relevant instances. These compelling findings underscore the critical role of deep learning, specifically convolutional neural networks (CNNs), in the realm of image classification. The utilization of CNNs, exemplified by the VGG16 architecture, emerges as a game-changer, enabling the capture of intricate image features and patterns that traditional logistic regression struggles to discern. Generally, this study advocates for the integration of advanced deep learning techniques, like VGG16, in image classification endeavors. The substantial performance gains witnessed in accuracy, precision, recall, and F1-score reinforce the pivotal role of convolutional neural networks in enhancing the effectiveness of image classification tasks. By harnessing the power of deep learning, we unlock new horizons in image analysis, paving the way for more accurate and efficient classification systems

PROClass: The Development and Validation of a Novel Prosthetic Component Sophistication Classification System

ObjectiveTo develop a lower limb prosthesis (LLP) sophistication classification system that categorizes prosthetic component prescriptions into “basic,” “intermediate,” and “advanced” and assess its content validity, reliability, and accuracy. DesignClassification development and validation study. SettingThe Veterans Affairs (VA) Corporate Data Warehouse database and National Prosthetics Patient Database were used to identify patients undergoing their first amputation at the transtibial or transfemoral level due to diabetes or peripheral artery disease and to identify the associated codes for each LLP. ParticipantsAn expert panel of 6 nationally recognized certified prosthetists, a national expert in VA prosthetics data and coding, a physical medicine and rehabilitation physician, and an epidemiologist developed an LLP classification system (PROClass) using 30 transfemoral and transtibial lower limb amputees. Main Outcome MeasuresThe expert panel reviewed 20 consecutive participants meeting study criteria for the development of the PROClass system and a subsequent 30 consecutive cases for assessing the inter- and intra-rater reliability and accuracy. ResultsThe interrater and intrarater reliability was almost perfect with Gwet's AC1 values ranging from .82 to .96 for both expert panel members and research assistants. The accuracy of the research assistant's classifications to the “criterion standard” was excellent with Gwet's AC1 values ranging between .75 and .92. ConclusionsPROClass is a pragmatic, reliable, and accurate prosthetic classification system with strong face validity that will enable the classification of prosthetic components used for large data set research aimed at evaluating important clinical questions such as the effects of sophistication on patient outcomes.

Comparison of Soil Taxonomy (2022) and WRB (2022) Systems for Classifying Paddy Soils with Different Drainage Grades in South Korea

Soil classification is the systematic classification of soils based on distinguishing the characteristics of soil, aiding in understanding the properties of soils through soil survey and establishing appropriate strategies for effective soil utilization and management. Globally, the Soil Taxonomy (ST) and the World Reference Base for soil resources (WRB) are widely used for soil classification. However, the two classification systems have differences in criteria, thus exhibiting difficulties in exchanging classification results. In South Korea, soil classification has been steadily implemented to provide useful soil information to farmers for efficient soil management, contributing to the sustainability of paddy lands, but it has not been easy to establish an accurate classification system due to intensive soil management and variation in soil redox conditions. In this study, two paddy soils with different drainage grades, pedon 1 and pedon 2, were classified using the ST and WRB, and based on the comparative results, a classification criterion for paddy soil in Korea was recommended. According to ST, pedon 1 was classified as a coarse loamy, mesic family (the mean annual soil temperature, 11–14 °C) of Anthroaquic Eutrudepts (artificially irrigated, base saturation > 60%), whereas pedon 2 was a coarse loamy, mesic family of Fluvaquentic Endoaquepts (organic carbon content > 0.2%, water-saturated across the soil profile). Based on the WRB, the two soils were categorized as follows: Stagnic Hydragric Anthrosols (Eutric, Loamic, Oxyaquic) (saturated with surface water, subsurface horizon that is wet-field and human-affected) for pedon 1 and Stagnic Gleyic Hydragric Anthrosols (Eutric, Loamic, Oxyaquic) (saturated with surface and ground water, subsurface horizon that is wet-field and human-affected) for pedon 2. Overall, the two classification systems categorized these pedons consistently by judging the soil properties according to depth, but there was a difference in layer classification upon saturation by water across the soil horizons. Poor soil drainage hinders rice growth in paddies due to lowering soil and water temperature and the occurrence of harmful reduction products. In this regard, we proposed a draft of the classification criteria specialized for paddy soils in Korea based on drainage grades. This will contribute to sustainable paddy soil management by accurately classifying paddy soils and providing better soil information to farmers.

Deep CNN‐based classification of motor imagery tasks from EEG signals using 2D wavelet transformed images of adaptively reconstructed signals from MVMD decomposed modes

AbstractBrain–computer interfaces (BCI) have begun to revolutionize many aspects of human life, ranging from health to smart living and communication devices. Therefore, BCI technologies require accurate recognition and classification systems of the brain responses to a variety of motor imagery (MI) movements through electroencephalogram (EEG) signals. Nowadays, deep learning models have received a lot of interest for learning features and classifying numerous kinds of data. However, it has not been thoroughly investigated for EEG signal classification. In this study, to reach an improved performance in MI‐EEG signal classification, we proposed a new strategy based on continuous wavelet transform (CWT)‐based time‐frequency maps to generate two‐dimensional (2D) EEG images of adaptively reconstructed signals from the extracted multivariate mode decomposition (MVMD) modes. In the next step, the extracted signals are projected in the new space using the proposed multiclass common spatial pattern (MCCSP) filtering. The resulting images are then fed to the convolutional neural network (CNN) architectures (AlexNet and LeNet). The proposed framework has the benefit of achieving high classification accuracy to be attained even with a significant amount of input data. LeNet and AlexNet reach the best average accuracy rates of 95.33% and 93.66% on dataset 1 from BCI competition IV and the results on dataset 2a from competition IV are more promising than the current state of the arts. Our results depict that MI‐EEG task recognition using image classification approaches, along with CNNs, is as comparable or even superior to other existing traditional approaches and provides high potential for upcoming research.

Experimental Exploration of Multilevel Human Pain Assessment Using Blood Volume Pulse (BVP) Signals.

Critically ill patients often lack cognitive or communicative functions, making it challenging to assess their pain levels using self-reporting mechanisms. There is an urgent need for an accurate system that can assess pain levels without relying on patient-reported information. Blood volume pulse (BVP) is a relatively unexplored physiological measure with the potential to assess pain levels. This study aims to develop an accurate pain intensity classification system based on BVP signals through comprehensive experimental analysis. Twenty-two healthy subjects participated in the study, in which we analyzed the classification performance of BVP signals for various pain intensities using time, frequency, and morphological features through fourteen different machine learning classifiers. Three experiments were conducted using leave-one-subject-out cross-validation to better examine the hidden signatures of BVP signals for pain level classification. The results of the experiments showed that BVP signals combined with machine learning can provide an objective and quantitative evaluation of pain levels in clinical settings. Specifically, no pain and high pain BVP signals were classified with 96.6% accuracy, 100% sensitivity, and 91.6% specificity using a combination of time, frequency, and morphological features with artificial neural networks (ANNs). The classification of no pain and low pain BVP signals yielded 83.3% accuracy using a combination of time and morphological features with the AdaBoost classifier. Finally, the multi-class experiment, which classified no pain, low pain, and high pain, achieved 69% overall accuracy using a combination of time and morphological features with ANN. In conclusion, the experimental results suggest that BVP signals combined with machine learning can offer an objective and reliable assessment of pain levels in clinical settings.

Third molar eruption in orthopantomograms as a feature for forensic age assessment—a comparison study of different classification systems

Evaluation of third molar eruption represents an established method for age assessment of living individuals. Different classification systems are available for the radiological assessment of third molar eruption. The aim of this study was to identify the most accurate and reliable classification system for the mandibular third molar eruption on orthopantomograms (OPG). We compared the method of Olze et al. (2012) with the method of Willmot et al. (2018) and a newly derived classification system using OPGs from 211 individuals aged 15–25 years. The assessments were performed by three experienced examiners. One examiner evaluated all radiographs twice. The correlation between age and stage was investigated and the inter- and intra-rater reliability was estimated for all three methods. Correlation between stage and age was similar between classification systems, although higher in the data from males (Spearman’s rho ranging from 0.568 to 0.583) than from females (0.440 to 0.446). Inter- and intra-rater reliability measures were similar across methods and invariant on sex, with overlapping confidence intervals, although the highest point estimates for both intra- and inter-rater reliability were for the method by Olze et al. with Krippendorf’s alpha values of 0.904 (95% confidence interval 0.854, 0.954) and 0.797 (95% confidence interval 0.744, 0.850). It was concluded that the method of Olze et al. from 2012 is a reliable method for practical application and future studies.

Comparison among Soil Taxonomy (2014), WRB (2014), and WRB (2022) Systems on Anthropogenic Soils in Korea

The remodeling agricultural land in South Korea is an anthropogenic soils created by reclaimed dredging generated from the Four Major River Restoration Project. The area of ​​the remodeled agricultural land is 7,727 ha, and many of the area are located near the Four Major Rivers. Soils made artificially by human activities differ from natural soil in terms of development as well as soil properties. Thus, this study attempted to classify the soil of the remodeled agricultural land using 3 soil classification system 1) Soil Taxonomy, 2) WRB (2014), 3) WRB (2022). Inchang series, a remodeled agricultural land, is fine, mesic family of Anthroportic Udorthents for Soil Taxonomy. WRB (2014) is recognized as Spolic Urbic Technosols (Siltic, Anthraquic, Gleyic, Transportic) and WRB (2022) is classified as Stagnic Gleyic Spolic Urbic Technosols (Siltic, Anthraquic, Transportic). Soil Taxonomy is limited in understanding soil properties because it categorizes anthropogenic soils into subgroups. On the other hand, WRB classifies anthropogenic soils into Anthrosols and Technosols into RSG, and continuously revises the classification system for accurate classification of anthropogenic soils. Therefore, it is necessary to revise classification of Korean soils according to the revised classification system for accurate soil classification. Furthermore, for soil classification suitable for Korean soil, it is necessary to create a soil classification system by referring to the WRB as well as Soil Taxonomy.Results of classification of Inchang series using Soil Taxonomy (2014), WRB (2014) and WRB (2022) are fine, mesic family of Anthroportic Udorthent, Spolic Urbic Technosols (Siltic, Anthraquic, Gleyic, Transportic) and Stagnic Gleyic Spolic Urbic Technosols (Siltic, Anthraquic, Transportic).

Determining meteorologically-favorable zones for seasonal influenza activity in Hong Kong.

Investigations of simple and accurate meteorology classification systems for influenza epidemics, particularly in subtropical regions, are limited. To assist in preparing for potential upsurges in the demand on healthcare facilities during influenza seasons, our study aims to develop a set of meteorologically-favorable zones for epidemics of influenza A and B, defined as the intervals of meteorological variables with prediction performance optimized. We collected weekly detection rates of laboratory-confirmed influenza cases from four local major hospitals in Hong Kongbetween 2004 and 2019. Meteorological and air quality records for hospitals were collected from their closest monitoring stations. We employed classificationandregression trees to identify zones that optimize the prediction performance of meteorological data in influenza epidemics, defined as a weekly rate > 50th percentile over a year. According to the results, a combination of temperature > 25.1℃ and relative humidity > 79% was favorable to epidemics in hot seasons, whereas either temperature < 16.4℃ or a combination of < 20.4℃ and relative humidity > 76% was favorable to epidemics in cold seasons. The area under the receiver operating characteristic curve (AUC) in model training achieved 0.80 (95% confidence interval [CI], 0.76-0.83) and was kept at 0.71 (95%CI, 0.65-0.77) in validation. The meteorologically-favorable zones for predicting influenza A or A and B epidemics together were similar, but the AUC for predicting influenza B epidemics was comparatively lower. In conclusion, we established meteorologically-favorable zones for influenza A and B epidemics with a satisfactory prediction performance, even though the influenza seasonality in this subtropical setting was weak and type-specific.

Smart Farm-Care using a Deep Learning Model on Mobile Phones

Deep learning and its models have provided exciting solutions in various image processing applications like image segmentation, classification, labeling, etc., which paved the way to apply these models in agriculture to identify diseases in agricultural plants. The most visible symptoms of the disease initially appear on the leaves. To identify diseases found in leaf images, an accurate classification system with less size and complexity is developed using smartphones. A labeled dataset consisting of 3171 apple leaf images belonging to 4 different classes of diseases, including the healthy ones, is used for classification. In this work, four variants of MobileNet models - pre-trained on the ImageNet database, are retrained to diagnose diseases. The model’s variants differ based on their depth and resolution multiplier. The results show that the proposed model with 0.5 depth and 224 resolution performs well - achieving an accuracy of 99.6%. Later, the K-means algorithm is used to extract additional features, which helps improve the accuracy to 99.7% and also measures the number of pixels forming diseased spots, which helps in severity prediction. Doi: 10.28991/ESJ-2023-07-02-013 Full Text: PDF

Deep learning models for automatic identification of plant-parasitic nematode

Plant-parasitic nematodes cause various diseases that can be fatal to the infected plants. It causes losses to the agricultural industry, such as crop failure and poor crop quality. Developing an accurate nematode classification system is vital for pest identification and control. Deep learning classification techniques can help speed up Nematode identification as it can perform tasks directly from images. In the present study, four state-of-the-art deep learning models (ResNet101v2, CoAtNet-0, Effi- cientNetV2B0, and EfficientNetV2M) were evaluated in plant-parasitic nematode classification from microscopic image. The models were trained using a combination of three different optimizers (Adam, SGD, dan RMSProp) and several data augmentation with image transformations, such as image flip, blurring, noise addition, brightness, and contrast adjustment. The performance of the trained models was varied. Regarding test accuracy, EfficientNetV2B0 and EfficientNetV2M using RMSProp and brightness augmentation give the best result of 97.94% However, the overall performance of EfficientNetV2M was superior, with 98.66% mean class accuracy, 97.99%F1 score, 98.26% average precision, and 97.94% average recall.

Enhanced Computer-Aided Diagnosis Model on Ultrasound Images through Transfer Learning and Data Augmentation Techniques for an Accurate Breast Tumors Classification

Cancer is a critical global public health problem with meager median survival. It is therefore quite essential to detect this disease at an early stage to improve diagnostic results and consequently avoid serious complications. For this purpose, various researchers have implemented automated methods with the use of different medical imaging modalities. Accordingly, the expansion of deep learning techniques grants opportunities to enhance diagnosis, cure, and prevention. In this study, a diagnostic system for accurate classification of ultrasound breast abnormalities based on the powerful ResNet-50 CNN is proposed with the aim of providing early detection of breast cancer decease. The contribution of this work lies in the novel approach taken to improve the performance of the ResNet50 model in the classification of ultrasound breast cancer images. Transfer learning allows for the model to leverage pre-existing knowledge, while the application of data augmentation techniques enhances the diversity and quality of the training data. Additionally, the optimization of the batch size as a hyperparameter ensures that the model is able to effectively learn from the training data, leading to improved accuracy and efficiency in the classification process. This approach is crucial in the early detection and treatment of breast cancer. Quantitative and qualitative evaluations have been detailed in this study using Breast Ultrasound Dataset BUSI. Our presented work shows interesting results in terms of accuracy, specificity, sensitivity, and AUC which exceed the performance of other compared works. Moreover, the proposed method helps boost the clinical diagnosis of breast cancer. It may integrate a radiologist network, allowing them to constantly follow up on the patient's medical history.

Measuring patient acuity and nursing care needs in South Korea: application of a new patient classification system

BackgroundAn accurate and reliable patient classification system (PCS) can help inform decisions regarding adequate assignments for nurse staffing. This study aimed to evaluate the criterion validity of the Asan Patient Classification System (APCS), a new tertiary hospital-specific PCS, by comparing its rating and total scores with those of KPCS-1 and KPCS-GW for measuring patient activity and nursing needs.MethodsWe performed a retrospective analysis of the medical records of 50,314 inpatients admitted to the general wards of a tertiary teaching hospital in Seoul, South Korea in March, June, September, and December 2019. Spearman’s correlation and Kappa statistics according to quartiles were calculated to examine the criterion validity of the APCS compared with the KPCS-1 and KPCS-GW.ResultsThe average patient classification score was 28.3 points for APCS, 25.7 points for KPCS-1, and 21.6 points for KPCS-GW. The kappa value between APCS and KPCS-1 was 0.91 (95% CI:0.9072, 0.9119) and that between APCS and KPCS-GW was 0.88 (95% CI:0.8757, 0.8810). Additionally, Spearman's correlation coefficients among APCS, KPCS-1, and KPCS-GW showed a very strong correlation. However, 10.8% of the participants’ results were inconsistent, and KPCS-1 tended to classify patients into groups with lower nursing needs compared to APCS.ConclusionThis study showed that electronic health record-generated APCS can provide useful information on patients’ severity and nursing activities to measure workload estimation. Additional research is needed to develop and implement a real-world EHR-based PCS system to accommodate for direct and indirect nursing care while considering diverse population and dynamic healthcare system.

Optimal BMI cutoff points in obesity screening for Chinese college students.

An accurate BMI classification system specific to the population is of great value in health promotion. Existing studies have shown that the BMI recommended cut-off value for adults is not suitable for college students. Thus, the current study aims to identify optimal BMI cutoff points in obesity screening for Chinese college students. Anthropometric assessments were performed on 6,798 college students (Male = 3,408, Female = 3,390) from three universities in Jiangsu, China. Exploratory factor analysis (EFA) was conducted to establish the standardized models to estimate anthropometry for male and female students. Further indices were derived from the assessments, including body mass index (BMI), relative fat mass (RFM), obesity degree percentage (OBD%), waist-to-hip ratio (WHR), waist circumference (WC), and body fat percentage (BF%). The anthropometric index with the highest correlation to the models for male and female students were selected as the gold standard for obesity screening. Receiver operating characteristic (ROC) curve was applied to evaluate diagnostic value of each anthropometric index according to the area under curve (AUC). Youden index maximum points determined the optimal cutoff points with the highest accuracy in obesity screening. The anthropometric models for both male and female students consisted of three factors. Vervaeck index was selected as the gold standard for obesity screening. By comparing AUC of the anthropometric indices, we found BMI provided the highest value in obesity screening. Further analysis based on Youden index identified the optimal BMI of 23.53 kg/m2 for male and 23.41 kg/m2 for female. Compared with the universal standard recommended by World Health Organization (WHO), the adjusted BMI criteria were characterized by high sensitivity as well as specificity. BMI is the most appropriate anthropometric index of obesity screening for Chinese college students. The optimal cutoff points were lower than the WHO reference. Evidence substantiated the adjusted BMI criteria as an effective approach to improve accuracy of obesity screening for this population.

Classification of Atrial Fibrillation and Congestive Heart Failure Using Convolutional Neural Network with Electrocardiogram

Atrial fibrillation (AF) and congestive heart failure (CHF) are the most prevalent types of cardiovascular disorders as the leading cause of death due to delayed diagnosis. Early diagnosis of these cardiac conditions is possible by manually analyzing electrocardiogram (ECG) signals. However, manual diagnosis is complex, owing to the various characteristics of ECG signals. An accurate classification system for AF and CHF has the potential to save patient lives. Therefore, this study proposed an ECG signal classification system for AF and CHF using a one-dimensional convolutional neural network (1-D CNN) to provide a robust classification system performance. This study used ECG signal recording of AF, CHF, and NSR, which can be accessed on the Physionet website. A total of 5600 ECG signal segments were obtained from 56 subjects, divided into train sets from 42 subjects (N = 4200 ECG segments), and test sets from 14 subjects (N = 1400). We applied for leave-one-out cross-validation in training to select the best model. The proposed 1-D CNN algorithm successfully classified raw data of ECG signals into normal sinus rhythm (NSR), AF, and CHF by providing the highest classification accuracy of 99.643%, f1-score, recall, and precision of 0.996, respectively, with an AUC score of 0.999. The results showed that the proposed method extracted the ECG signal information directly without needing several preprocessing steps and feature extraction methods that potentially reduce the information contained in the ECG signals. Furthermore, the proposed method outperformed previous studies in classifying AF, CHF, and NSR. Therefore, this approach can be considered as an adjunct for medical personnel to diagnose AF, CHF, and NSR.

Characterization of the complete chloroplast genome of Euphorbia pekinensis Rupr. (Euphorbiaceae)

Euphorbia pekinensis Rupr. 1859 is a medicinal herb endemic to China and distributed throughout the country, particularly across the northern part of the mainland. However, the systematic classification of Euphorbiaceae remains controversial. Therefore, studying the chloroplast genome of E. pekinensis is crucial for the resolution of this taxonomic dispute, clarification of the systematic status of Euphorbia, and establishment of an accurate classification system for Euphorbiaceae. In this study, we sequenced the complete chloroplast genome of E. pekinensis using Illumina sequencing technology and annotated it using GeSeq. The complete chloroplast genome was 162,002-bp-long with a guanine–cytosine (GC) content of 35.7%. It included one large single-copy (LSC), one small single-copy (SSC), and two inverted repeat sequence regions (IRa and IRb), which were 90,225 bp, 18,067 bp, and 26,855 bp in length, respectively, and are indicative of a typical tetrad structure. The genome encoded 129 functional genes, comprising 85 protein-coding genes, 36 tRNA genes, and eight rRNA genes. According to the maximum-likelihood phylogenetic tree that was constructed using 16 complete chloroplast genomes, E. pekinensis was found to be closely related to E. ebracteolata. Therefore, the complete chloroplast genome of E. pekinensis provides a better understanding of Euphorbia genetics.

Accurate automatic classification system for 3D CT images of some vertebrate remains from Egypt

Vertebrate fossils/remains became recently significant in various study fields for determining the ecological biodiversity. However, with the great abundance of fossils/remains and their classes, there is a difficulty in identifying and detecting these classes. Hence, in this paper, an accurate machine learning classification technique is presented to differentiate automatically some types of 3D vertebrate remain images. A computed tomography (CT) scanner is utilized to construct a dataset of 3D images of some vertebrate remains found in Egypt. Adaptive enhancement and segmentation processes are applied to the dataset. The different selected geometric features are then extracted. Thus, the extracted features are classified using suitable machine learning classifiers (SVM, KNN, DTs). The automatic detection for the remains class, according to the extracted features, is obtained using the confusion matrix for the training and testing data points and the receiver operating characteristic (ROC) curve. The results confirmed an accurate technique with high performance.

Examining Techniques to Solving Imbalanced Datasets in Educational Data Mining Systems

The educational data mining research attempts have contributed in developing policies to improve student learning in different levels of educational institutions. One of the common challenges to building accurate classification and prediction systems is the imbalanced distribution of classes in the data collected. This study investigates data-level techniques and algorithm-level techniques. Six classifiers from each technique are used to explore their effectiveness to handle the imbalanced data problem while predicting students’ graduation grade based on their performance at the first stage. The classifiers are tested using the k-fold cross-validation approach before and after applying the data-level and algorithm-level techniques. For the purpose of evaluation, various evaluation metrics have been used such as accuracy, precision, recall, and f1-score. The results showed that the classifiers do not perform well with imbalanced dataset, and the performance could be improved by using these techniques. As for the level of improvement, it varies from one technique to another. Additionally, the results of the statistical hypothesis testing confirmed that there were no statistically significant differences for classifiers of the two techniques.

The Prognostic Value of the Circulating Tumor Cell-Based Four mRNA Scoring System: A New Non-Invasive Setting for the Management of Bladder Cancer.

Simple SummaryBladder cancer with similar diagnosis based on traditional classification exhibits different behaviors and therapeutic outcomes. Thus, circulating tumor cells (CTCs) represent a more accurate approach to investigate bladder cancer features. Our results demonstrate that risk score based on EGFR, TRPM4, TWIST1, and ZEB1 four-gene signature in CTCs is markedly and undoubtedly associated with recurrence, suggesting an innovative and non-invasive strategy to manage both non muscle invasive and muscle invasive bladder cancer progression without the necessity of repetitive and onerous cystoscopies.Bladder cancer (BC) is one of the most expensive lifetime cancers to treat because of the high recurrence rate, repeated surgeries, and long-term cystoscopy monitoring and treatment. The lack of an accurate classification system predicting the risk of recurrence or progression leads to the search for new biomarkers and strategies. Our pilot study aimed to identify a prognostic gene signature in circulating tumor cells (CTCs) isolated by ScreenCell devices from muscle invasive and non-muscle invasive BC patients. Through the PubMed database and Cancer Genome Atlas dataset, a panel of 15 genes modulated in BC with respect to normal tissues was selected. Their expression was evaluated in CTCs and thanks to the univariate and multivariate Cox regression analysis, EGFR, TRPM4, TWIST1, and ZEB1 were recognized as prognostic biomarkers. Thereafter, by using the risk score model, we demonstrated that this 4-gene signature significantly grouped patients into high- and low-risk in terms of recurrence free survival (HR = 2.704, 95% CI = 1.010–7.313, Log-rank p < 0.050). Overall, we identified a new prognostic signature that directly impacted the prediction of recurrence, improving the choice of the best treatment for BC patients.