Classification Tree Regression Research Articles

Multiplexed Serum Biomarkers to Discriminate Nonviable and Ectopic Pregnancy

ObjectiveThe use of multiplexed biomarkers may improve the diagnosis of normal and abnormal early pregnancies. In this study we assessed 24 markers with multiple machine learning-based methodologies to evaluate combinations of top candidates to develop a multiplexed prediction model for identification of 1) viability and 2) location of an early pregnancy. DesignA nested case-control design evaluating the predictive ability and discrimination of biomarkers in patients at risk of early pregnancy failure in the first trimester to classify viability and location Subjects218 individuals with a symptomatic (pain and/or bleeding) early pregnancy: 75 with an ongoing intrauterine gestation, 68 ectopic pregnancies, and 75 miscarriages. InterventionsSerum values of 24 biomarkers were assessed in the same patients. Multiple machine learning-based methodologies to evaluate combinations of these top candidates to develop a multiplexed prediction model for identification of 1) a nonviable pregnancy (ongoing intrauterine pregnancy vs miscarriage or ectopic pregnancy) and 2) an ectopic pregnancy (ectopic pregnancy vs ongoing intrauterine pregnancy or miscarriage). Main Outcome MeasuresThe predicted classification by each model was compared to actual diagnosis and sensitivity, specificity, positive predictive value (PPV), negative predictive value (NPV), conclusive classification, and accuracy were calculated. ResultsModels using classification regression tree analysis using three markers (PSG3, CG-Alpha and PAPPA) were able to predict a maximum sensitivity 93.3%, a maximum specificity 98.6%. The model with the highest accuracy was 97.4% (with 70.2% receiving classification). Models using an overlapping group of three markers (sFLT, PSG3 and TFP12) achieved a maximum sensitivity of 98.5%. and a maximum specificity of 95.3%. The model with the highest accuracy was 94.4% (with 65.6% receiving classification). When the models were used simultaneously the conclusive classification increased to 72.7% with an accuracy 95.9%. The predictive ability of the biomarkers random forest produced similar test characteristics when using 11 predictive markers. ConclusionWe have demonstrated a pool of biomarkers from divergent biological pathways that can be used to classify individuals with potential early pregnancy loss. The biomarkers CG-Alpha, PAPPA and PSG3 can be used to predict viability and sFLT, TPFI2 and PSG3 can be used to predict pregnancy location.

Gender classification based on gait analysis using ultrawide band radar augmented with artificial intelligence

The identification of individuals based on their walking patterns, also known as gait recognition, has garnered considerable interest as a biometric trait. The use of gait patterns for gender classification has emerged as a significant research domain with diverse applications across multiple fields. The present investigation centers on the classification of gender based on gait utilizing data from Ultra-wide band radar. A total of 181 participants were included in the study, and data was gathered using Ultra-wide band radar technology. This study investigates various preprocessing techniques, feature extraction methods, and dimensionality reduction approaches to efficiently process Ultra-wide band radar data. The data quality is improved through the utilization of a two-pulse canceller and discrete wavelet transform. The hybrid feature dataset is generated through the creation of gray-level co-occurrence matrices and subsequent extraction of statistical features. Principal Component Analysis is utilized for dimensionality reduction, and prediction probabilities are incorporated as features for classification optimization. The present study employs k-fold cross-validation to train and assess machine learning classifiers, Decision Tree, Random Forest, Support Vector Machine, Logistic Regression, Multi-Layer Perceptron, K-Nearest Neighbors, and Extra Tree Classifier. The Multilayer Perceptron exhibits superior performance, achieving an accuracy of 0.936. The Support Vector Machine and k-Nearest Neighbors classifiers closely trail behind, both achieving an accuracy of 0.934. This research is of the utmost importance due to its capacity to offer solutions to crucial problems in multiple domains. The findings indicate that the utilization of UWB radar data for gait-based gender classification holds promise in diverse domains, including biometrics, surveillance, and healthcare. The present study makes a valuable contribution to the progress of gender classification systems that rely on gait patterns.

Fake Job Posting Detection

In the realm of online job platforms, the rise of fraudulent job postings poses a significant challenge, undermining the credibility and reliability of these platforms. To address this issue, we propose a machine learning- based solution that leverages the power of Random Forest, Logistic Regression, and Decision Tree classifiers. Through the compilation of a comprehensive dataset containing labeled job postings, we embark on a journey of preprocessing and feature engineering to extract pertinent information from the postings, including textual attributes, geographic details, salary indications, and company profiles. Splitting the dataset into training and testing subsets enables us to meticulously train and evaluate the performance of each classifier, utilizing established metrics such as accuracy, precision, recall, and F1-score to quantify their efficacy in discerning between authentic and fake job listings. Our study goes beyond mere model training and evaluation, delving into the intricacies of imbalanced data handling and the practicalities of model deployment and maintenance. By examining the comparative strengths and weaknesses of Random Forest, Logistic Regression, and Decision Tree classifiers, we provide actionable insights for enhancing the integrity of online job platforms through advanced machine learning techniques. With our approach, we aim to not only detect and mitigate the prevalence of fake job postings but also to fortify the trust and credibility of online job- seeking platforms, thereby fostering a more secure and reliable environment for both job seekers and employers alike.

Evolution of Crop Planting Structure in Traditional Agricultural Areas and Its Influence Factors: A Case Study in Alar Reclamation

This research provides a comprehensive analysis of the spatiotemporal evolution of the regional cropping structure and its influencing factors. Using Landsat satellite images, field surveys, and yearbook data, we developed a planting structure extraction model employing the classification regression tree algorithm to obtain data on the major crop cultivation and structural characteristics of Alar reclamation from 1990 to 2023. A dynamic model and transfer matrix were used to analyze temporal changes, and a centroid migration model was used to study spatial changes in the cropping structure. Nonparametric mutation tests and through-traffic coefficient analysis were utilized to quantify the main driving factors influencing the cropping structure. During the period of 1990–2023, the cotton area in the Alar reclamation region expanded by 722.08 km2, while the jujube exhibited an initial increase followed by a decrease in the same period. The primary reasons are linked to the cost of purchase, agricultural mechanization, and crop compatibility. In the Alar reclamation area, cotton, chili, and jujube are the primary cultivated crops. Cotton is mainly grown on the southern side of the Tarim River, while chili cultivation is concentrated on the northern bank of the river. Over the years, there has been a noticeable spatial complementarity in the distribution and density of rice and cotton crops in this region. In the Alar reclamation, the main factors influencing the change in cultivated land area are cotton price, agricultural machinery gross power, and population. Consequently, implementing measures such as providing planting subsidies and other policy incentives to enhance planting income can effectively stimulate farmers’ willingness to engage in planting activities.

Fusion of airborne multimodal point clouds for vegetation parameter correction extraction in burned areas.

Most experimental studies use unimodal data for processing, the RGB image point cloud cannot separate the shrub and tree layers according to the visible vegetation index, and the airborne laser point cloud is difficult to distinguish between the ground and grass ranges, to address the above problems, a multi-band information image fusing the LiDAR point cloud and the RGB image point cloud is constructed. In this study, data collected from UAV platforms, including RGB image point clouds and laser point clouds, were used to construct a fine canopy height model (using laser point cloud data) and high-definition digital orthophotos (using image point cloud data), and the orthophotos were fused with a canopy height model (CHM) by selecting the Difference Enhancement Vegetation Index (DEVI) and Normalised Green-Blue Discrepancy Index (NGBDI) after comparing the accuracy of different indices. Morphological reconstruction of CHM + DEVI/NGBDI fusion image, remove unreasonable values; construct training samples, using classification regression tree algorithm, segmentation of the range of the burned areas and adaptive extraction of vegetation as trees, shrubs and grasslands, tree areas as foreground markers using the local maximum algorithm to detect the tree apexes, the non-tree areas are assigned to be the background markers, and the Watershed Transform is performed to obtain the segmentation contour; the original laser point cloud is divided into chunks according to the segmented single-tree contour, and the highest point is traversed to search for the highest point, and corrected for the height of the single-tree elevations one by one. Accuracy analysis of the vegetation information extracted by the method with the measured data showed that the improved method increased the overall recall rate by 4.1%, the overall precision rate by 3.7%, the overall accuracy F1 score by 3.9%, and the tree height accuracy by 8.8%, 1.4%, 1.7%, 6.4%, 1.8%, and 0.3%, respectively, in the six sampling plots. The effectiveness of the improved method is verified, while the higher the degree of vegetation mixing in the region the better the extraction effect of the improved algorithm.

Examining the Determinants of Poland’s Middle Class Life Satisfaction

Recent works suggest that the increasing income inequalities decreased the middle class size and threatened life satisfaction (LS). However, no such studies link LS with middle-income class problems. The present study aims to fill this gap and characterize LS across the middle-income class in Poland. The main novelties are the Satisfaction with Life Scale (SWLS) to measure LS of the middle-income class in Poland and the methodological approach based on classification-regression trees (CART) to identify the determinants of LS. The analysis is conducted on the new database obtained from the survey of members of the middle-income class in Poland divided into three subgroups: the lower-middle-income class, the mid-income middle class, and the higher-middle-income class. For comparison, the low-income and high-income classes were also considered. Based on the SWLS results, relatively low diversity in middle-income class LS was identified. However, the inter-class comparison revealed that LS increased with belonging to a higher income class. The CART results support the primary importance of economic conditions such as, for instance, wealth and the level of savings in determining the middle-income class LS and show that their effect depends on their characteristics like professional status.

The Exploration of Modelling for The Student Achievement Predictor

The project is rooted in the analysis of historical student data. It encompasses a comprehensive approach involving data observation, meticulous analysis, thorough comparison, systematic processing, and efficient coding techniques. The ultimate goal is to harness the power of machine learning to predict students' academic achievements and discern the key features that exert the most significant influence on their learning outcomes. In terms of the machine learning model, this study explored and assessed several machine learning algorithms, including but not limited to the K-Neighbors Classifier, Logistic Regression, and Decision Tree Classifier. These models are scrutinized and fine-tuned to ensure their suitability for the task at hand. Furthermore, a pivotal aspect of this project is identifying the features that wield the greatest impact on students' learning achievements. By employing feature selection techniques, this study aims to uncover the critical factors that can make a difference in educational outcomes. This information can guide educational institutions in designing targeted interventions to support student success. The experimental results obtained from this study demonstrated the effectiveness of the employed machine learning methods.

Research on Digital Inclusive Finance, Innovative Factor Allocation and High Quality Economic Development Based on Artificial Intelligence

Abstract This paper firstly organizes and summarizes the random forest model algorithm in artificial intelligence and secondly uses the XGBoost algorithm with the classification regression tree as the base classifier to explore the relationship between digital financial inclusion, innovative factor allocation and high-quality economic development. Major databases and relevant websites are used to establish the evaluation index system, and the index homogenization is done. The economic high-quality development score is measured using the principal component analysis next. Finally, the principal component scores are weighted and summed according to the proportion of the variance contribution ratio of each principal component to the cumulative variance contribution ratio of the extracted principal components. After calculating the score, it was found that the innovation indicator, which had risen year after year between 2014 and 2018, decreased significantly from 2019 onwards, with the score falling from 2.21 to 1.48, a decrease of 33%. The growth rate of digital financial inclusion declined from 0.93 and finally maintained at 0.45 to 0.47. The economic development index first grew from -11.88 to 2.41, increasing by 3 to 5 each year, and then the growth rate was maintained at about 66%, growing to 6.58 in 2022.

Predição do índice de maturidade da manga cultivar ‘Ataulfo’ usando o sensor espectral AS7262

Abstract ‘Ataulfo’ mango is highly produced in Mexico, being harvested when it reaches its physiological maturity. This process takes at least another month for the fruit to reach consumption maturity. Warehouses and markets present important losses as the ready-to-eat status is unknown. Maturity status is determined by measuring slow and destructive physicochemical variables. An optical device based on the AS7262 spectral sensor was connected to the ESP32 microcontroller and measurements were correlated with soluble solids content (SSC), dry matter (DM) and firmness of mangoes obtained from the local market. Data analysis was carried out by partial least squares (PLS) regression, classification, regression tree (CART) and random forest (RF) models. With PLS, SST and firmness were predicted with R2 of 0.61 and 0.76, respectively. The root mean squared error of prediction (RMSEP) was 0.91 for SSC and 0.67 for firmness. With the CART model, classification accuracy was 90% for SSC and 87% for firmness of intact mango fruits.

Study on the Spatial and Temporal Evolution of Regional Green Space Morphology Outside Built-Up Areas based on the Google Earth Engine and Biophysical Component Modeling

The spatial pattern of regional green space is an important dimension to describe and quantitatively express the characteristics of regional green spaces outside the built-up area of a city. With the expansion of urban and rural construction land, regional green space has been continuously encroached upon. This leads to a decline in regional ecological well-being and the loss of biodiversity. Based on the remote sensing data of Shanghai city from 2000 to 2020, we quantitatively studied the spatial morphological change characteristics of regional green space outside the built-up area of Shanghai city. Firstly, with the help of the GEE platform, the optimal decoding accuracy classification method was selected through machine learning (random forest, support vector machine, classification regression tree); then, based on the biophysical component (BCI) and CA binarization, the built-up area ranges for up to five time nodes were obtained; finally, through GIS spatial data analysis and processing technology, the regional green space dynamic data of Shanghai for five time nodes were extracted. Based on the above data, an analysis index system was constructed to quantitatively analyze the spatial morphology characteristics of the regional green space outside the built-up area of Shanghai. The results show that (1) the area of regional green space outside the built-up area of Shanghai had a fluctuating growth pattern of “decreasing and then increasing”. The arable land and water areas in Shanghai decreased, and the woodland area increased steadily, while the wetland and grassland areas showed a trend of first decreasing and then increasing. (2) The regional green patch fragmentation shows a fluctuating development trend of increasing, decreasing, and increasing. (3) The change in the spatial center of gravity of the regional green space in Shanghai had a high degree of consistency with the overall green space change. The center of gravity of the grasslands in the regional green space moved substantially to the northwest, while the center of gravity of the other types remained basically unchanged. This study reveals the spatial morphology characteristics of regional green spaces and provides a research method to study the dynamic changes in regional ecological resources. The results of this study can provide a scientific basis for the identification, protection, and development of regional ecological resources.

Mapping Paddy Cropland in Guntur District using Machine Learning and Google Earth Engine utilizing Images from Sentinel-1 and Sentinel-2

Ensuring global food security necessitates vigilant monitoring of crop quantity and quality. Therefore, the reliable classification of croplands and diverse Land Covers (LC) becomes pivotal in fostering sustainable agricultural progress and safeguarding national food security. The Seasonal Crop Inventory (SCI) emerges as a strong asset. In this study, Sentinel-1 (S1) and Sentinel-2 (S2) image data were used to show varied land uses and paddy crops in Guntur district, Andhra Pradesh, India, during the 2021 growing season. Employing a technologically advanced space-based remote sensing approach, this study exploited the Google Earth Engine (GEE) and a range of classification techniques, including Random Forest (RF) and Classification Regression Trees (CART), to generate pixel-based SCI tailored to the area under investigation. The results underscored the reliability of GEE-based cropland mapping in the region, demonstrating a satisfactory level of classification accuracy, surpassing 97% across distinct time intervals in overall accuracy values, Kappa coefficients, and F1-Score.

Characterization of the shape of aggregates using image analysis and machine learning classification tools

ABSTRACT Engineering applications including pervious concrete require effective packing of aggregates to optimize strength. Size and shape distribution of aggregates significantly affect the performance. Computational methods numerically represent shape of aggregates, from image analysis, the effectiveness of has not been compared and verified. This study aims to analyse the representability of shape aspects of aggregates by different computational methods. Crushed aggregates were grouped into 5 clusters, and each group was milled in a Los Angeles machine for different degrees (0–2000) to induce morphological changes on the aggregates. Aggregates ranging from 5 to 30mm in diameter were obtained (7191 in total). imageJTM, was used to compute dimensions and shape factors of aggregates from 14 computational methods. Statistical tests, Pearson’s Correlations and Principal Components Analysis and machine learning classification tools, Decision-tree, Random-Forest, Naïve-Bayes, Support-Vector-Machines, K-Nearest-Neighbours and Perceptron were employed to assess. In conclusion, no shape factor could be singularly used to numerically represent the morphological changes on aggregate particles but a combination of shape factors is required. Data matrix had three primary dimensions. Combination of Circularity, Kumbrein-Solidity and Barksdale-Shape-Factor yield best representation of aggregate shape. Regression Tree classification method had the highest accuracy (0.9) in classifying milled and unmilled aggregates.

Perbandingan Klasifikasi Citra Daun Herbal Menggunakan Metode Logistic Regression dan Decision Tree Classifier Berdasarkan Fitur (Warna, GLCM, Bentuk)

The development of plant science is growing rapidly regarding herbal plants. Herbs have many benefits for life to prevent, cure diseases. To find out the types of herbal plants is done by the classification process. Classification of herbal plants can be done by identifying the shape of the leaf image of herbal plants by extracting color features, GLCM and shape from herbal leaves. The 275 dataset consists of 25 leaf types with 11 total datasets. There are several kinds of classification methods that can be used. In this study, the classification methods used were the Logistic Regression and Decision Tree Classifier methods. Based on the results of trials conducted using the Logistic Regression method, the train classification accuracy value was 72.9% and the classification test accuracy was 60.24%, while the Decision Tree Classifier method had a train classification accuracy value of 100% and the accuracy of the classification test was 78.31. This shows that the performance of the Decision Tree Classifier method is better than the Logistic Regression method

Detrimental impact of immunosuppressive burden on clinical course in patients with Cytomegalovirus infection after liver transplantation.

Cytomegalovirus (CMV)-infection and reactivation remain a relevant complication after liver transplantation (LT). The recipient and donor serum CMV-IgG-status has been established for risk stratification when choosing various pharmaceutical regimens for CMV-prophylaxis in the last two decades. However, factors influencing course of CMV-infection in LT remain largely unknown. In this study, the impact of immunosuppressive regimen was examined in a large cohort of patients. All patients that underwent primary LT between 2006 and 2018 at the Charité-Universitaetsmedizin, Berlin, were included. Clinical course as well as histological and laboratory findings of patients were analyzed our prospectively maintained database. Univariate and multivariate regression analysis for impact of variables on CMV-occurrence was conducted, and survival was examined using Kaplan-Meier analysis. Overall, 867 patients were included in the final analysis. CMV-infection was diagnosed in 325 (37.5%) patients after transplantation. Significantly improved overall survival was observed in these patients (Log rank=0.03). As shown by correlation and regression tree classification and regression tree analysis, the recipient/donor CMV-IgG-status with either positivity had the largest influence on CMV-occurrence. Analysis of immunosuppressive burden did not reveal statistical impact on CMV-infection, but statistically significant inverse correlation of cumulative tacrolimus trough levels and survival was found (Log rank<.001). Multivariate analysis confirmed these findings (p=.02). CMV-infection remains of clinical importance after LT. Undergone CMV-infection of either recipient or donor requires prophylactic treatment. Additionally, we found a highly significant, dosage-dependent impact of immunosuppression (IS) on long-term outcomes for these patients, underlying the importance of minimization of IS in liver transplant recipients.

Classifying health issues in Eucalyptus miniclonal gardens in Uruguay

Clonal propagation is extensively used in the Eucalyptus pulp industry in Uruguay. Mother plants are maintained in clonal minigardens and they constitute the source of cuttings that are harvested continuously and sent to shaded greenhouses for rooting. Environmental conditions within the minigarden are optimized for plant growth, but such conditions can also promote the emergence of pests and diseases which can affect the mother plants and impair cutting production. However, comprehensive studies on health status within minigardens are scarce in the country. We carried out a seasonal survey on three clonal minigardens along the country to check for epidemiological patterns connected to the time of the year, the conditions within the clonal garden and the genetic material in propagation. We visited each minigarden at least once per season during 2019 and the beginning of 2020. During each visit, we inspected all the mother plants along three transects (two on the edges and one in the centre of the minigarden). We counted the number of plants with symptoms of disease and of insect attacks, and collected samples of affected plants for further identification in the laboratory, if necessary. We looked for a way to classify nurseries and species all together, according to the incidence of the different health issues surveyed. Thus, the dataset obtained from the surveys was assessed under different classification algorithms based on machine learning: neural networks, discriminant analysis models, classification regression tree, support vector machine, and random forest. We observed attack by arthropods such as mites, whiteflies, scales and aphids and caterpillars. We also recorded powdery mildew and disease symptoms such as dead plants and dry shoots. The different materials assessed during the survey belonged to E. grandis, E. dunnii, and E. grandis × E. globulus hybrids. The most common symptoms observed in all the minigardens and throughout the entire survey period were powdery mildew and damage from mites. The support vector machine model performed best, being able to classify the dataset with an accuracy of 76%. We discuss the relevance of these findings within the context of miniclonal garden health management.

Effect of DC grounding electrode currents on the corrosion interference behavior of cathodic protection of nearby pipelines

When operating a direct current (DC) transmission grounding electrode in single-pole return ground mode, transient currents traverse the soil, generating stray currents. These currents can intensify the corrosion of long-distance transmission pipelines near the grounding electrode, subsequently altering the pipeline’s cathodic protection potential. Previous investigations into the interference of grounding electrodes on pipeline cathodic protection have overlooked the cathodic protection systems themselves. Addressing this gap, we integrated COMSOL’s electrochemical module with its AC/DC module. To corroborate the accuracy of our COMSOL-based models, we devised specific validation experiments. Additionally, we crafted a COMSOL application builder interface to streamline computations. Consequently, we derived a multi-regression function to express the cathodic protection potential of the pipeline under varied factors and executed a regression tree classification for soil resistivity. To pinpoint optimal corrosion protection for pipelines, we simulated the cathodic protection of segmentally isolated pipelines, determining that potential excursions can be notably mitigated. This research offers insights into both disturbance evaluation and protective strategies for DC transmission and pipelines.

Evaluation of different machine learning algorithms for LULC classification in heterogeneous landscape by using remote sensing and GIS techniques

Remote sensing land cover classification plays a crucial role in detecting changes, urbanization planning, mapping and monitoring land cover on earth surface. It is very challenging to get accurate result in remote sensing data because different classifiers are very much area dependent. Different classifiers such as decision tree (DT), K-nearest neighbor (KNN), artificial neural network (ANN), support vector machine (SVM), boosted decision tree (BDT), random forest (RF), classification and regression tree (CART) and maximum likelihood classifiers (MLC), have different accuracies for the same classes. Several studies have utilized remote sensing and GIS tools to investigate changes in land use and land cover (LULC) using different classifiers. Seasonal rivers which should be classified as water bodies are mostly classified as urban area with the conventional land cover classification schemes because spectral reflectance of these river bodies is similar to urban area due to stones present in their river bed. It is very difficult to distinguish between these river beds (which are mostly found in various districts of Uttarakhand, India) and urban area in remote sensing images. In this paper, we present a new method to distinguish these river beds with the urban area and to separate other classes easily. First of all different spectral indices such as NDVI, NDBI, EVI and MNDWI are extracted from a high resolution Sentinel-2 MSI image then these indices are integrated with Sentinel-2 MSI image for classification of different land cover classes by using four different machine learning classifiers such as RF, SVM, DT and CART. The obtained results confirm the performance strength of the suggested method as there is much improvement in accuracy.

A combined molecular approach utilizing microbial DNA and microRNAs in a qPCR multiplex for the classification of five forensically relevant body fluids.

Body fluid identification is an essential step in the forensic biology workflow that can assist DNA analysts in determining where to collect DNA evidence. Current presumptive tests lack the specificity that molecular techniques can achieve; therefore, molecular methods, including microRNA (miRNA) and microbial signature characterization, have been extensively researched in the forensic community. Limitations of each method suggest combining molecular markers to increase the discrimination efficiency of multiple body fluids from a single assay. While microbial signatures have been successful in identifying fluids with high bacterial abundances, microRNAs have shown promise in fluids with low microbial abundance (blood and semen). This project synergized the benefits of microRNAs and microbial DNA to identify multiple body fluids using DNA extracts. A reverse transcription (RT)-qPCR duplex targeting miR-891a and let-7g was validated, and miR-891a differential expression was significantly different between blood and semen. The miRNA duplex was incorporated into a previously reported qPCR multiplex targeting 16S rRNA genes of Lactobacillus crispatus, Bacteroides uniformis, and Streptococcus salivarius to presumptively identify vaginal/menstrual secretions, feces, and saliva, respectively. The combined classification regression tree model resulted in the presumptive classification of five body fluids with 94.6% overall accuracy, now including blood and semen identification. These results provide proof of concept that microRNAs and microbial DNA can classify multiple body fluids simultaneously at the quantification step of the current forensic DNA workflow.

Unraveling the relationship between key aroma components and sensory properties of fragrant peanut oils based on flavoromics and machine learning

Key aroma components of 33 fragrant peanut oils with different aroma types were screened by combined using flavoromics and machine learning. A total of 108 volatile compounds were identified and 100 kinds of them were accurately quantified, and 38 compounds out of them were with odorant activity value ≥1. The 33 peanut oils presented varied intensity of ‘fresh peanuts’, ‘roasted nut’, ‘burnt’, ‘over-burnt’, ‘sweet’, ‘peanut butter-like’, ‘puffed food’ and ‘exotic flavor’, and could be classified into four aroma types, namely raw, light, thick and salty. Partial least squares regression analysis, random forest and classification regression tree revealed that 2-acetyl pyrazine had a negative effect on ‘fresh peanuts’ and could distinguish raw flavor samples well; 2-methylbutanal and 4-vinylguaiacol were key compounds of ‘roasted nut’ and had significant differences (P < 0.0001) in thick and raw flavor samples; furfural contributed to the ‘puffed food’ as well as key compound of salty flavor.

An Artificial Intelligence Algorithm to Optimize the Classification of the Hepatitis Type

Hepatitis is one of the diseases that has become more developed in recent years in terms of the high number of infections. Hepatitis causes inflammation that destroys liver cells, and it occurs as a result of viruses, bacteria, blood transfusions, and others. There are five types of hepatitis viruses, which are (A, B, C, D, E) according to their severity. The disease varies by type. Accurate and early diagnosis is the best way to prevent disease, as it allows infected people to take preventive steps so that they do not transmit the difference to other people, and diagnosis using artificial intelligence gives an accurate and rapid diagnostic result. Where the analytical method of the data relied on the radial basis network to diagnose the disease, in addition to using the classification of the regression tree as well as the use of the genetic algorithm to improve the classification accuracy of both methods and by comparing the methods used to find out the most efficient methods of classification through criteria. Classification error, mean square root error, and average absolute relative error, and concluded that the experimental results are that the methods are good in terms of classification, as they gave results with less classification of error, and that the radial basis network was superior to the classification regression tree, and that the addition of the genetic algorithm led to an improvement classification accuracy.&#x0D; Paper type: Research paper.