Performance Of Different Models Research Articles

Automatic diagnosis of Parkinson's disease using artificial intelligence base on routine T1-weighted MRI.

Parkinson's disease (PD) is the second most common neurodegenerative disease. An objective diagnosis method is urgently needed in clinical practice. In this study, deep learning and radiomics techniques were studied to automatically diagnose PD from healthy controls (HCs). 155 PD patients and 154 HCs were randomly divided into a training set (246 patients) and a testing set (63 patients). The brain subregions identification and segmentation were automatically performed with a VB-net, and radiomics features of billateral thalamus, caudatum, putamen and pallidum were extracted. Five independent machine learning classifiers [Support Vector Machine (SVM), Stochastic gradient descent (SGD), random forest (RF), quadratic discriminant analysis (QDA) and decision tree (DT)] were trained on the training set, and validated on the testing. Delong test was used to compare the performance of different models. Our VB-net could automatically identify and segment the brain into 109 regions. 2,264 radiomics features were automatically extracted from the billateral thalamus, caudatum, putamen or pallidum of each patient. After four step of features dimensionality reduction, Delong tests showed that the SVM model based on combined features had the best performance, with AUCs of 0.988 (95% CI: 0.979 ~ 0.998, specificity = 91.1%, sensitivity =100%, accuracy = 89.4% and precision = 88.2%) and 0.976 (95% CI: 0.942 ~ 1.000, specificity = 100%, sensitivity = 87.1%, accuracy = 93.5% and precision = 88.6%) in the training set and testing set, respectively. Decision curve analysis showed that the clinical benefit of the line graph model was high. The SVM model based on combined features could be used to diagnose PD with high accuracy. Our fully automatic model could rapidly process the MRI data and distinguish PD and HCs in one minute. It greatly improved the diagnostic efficiency and has a great potential value in clinical practice to help the early diagnosis of PD.

Feasibility of the Anchor‐Free Deep Learning Method in Coronary Stenosis Automatic Detection

Background. Coronary artery disease (CAD) is a type of cardiovascular disease which is one of the leading causes of death around the world. The presence of coronary stenosis is considered a pivotal indicator in the diagnosis of various CADs. The main purpose of this paper was to investigate the feasibility of an anchor‐free deep learning (DL) method, fully convolutional one‐stage object detection (FCOS), in coronary artery stenosis automatic detection. Methods. First, 2786 invasive coronary angiography (ICA) images from 130 patients were randomly divided into training, validation, and testing datasets using the 10‐fold cross‐validation approach. Then, FCOS was compared with other three widely used anchor‐based DL models: single shot multibox detector (SSD), faster region‐based convolutional network (Faster R‐CNN), and you only look once (YOLOv3), in terms of precision, recall, F1 score, average precision (AP), and average recall (AR). Finally, the performances of different models in the detection of stenosis were compared in either single or multiple lesion scenarios using statistical tests. Results. FCOS achieved significantly superior precision (96.14% ± 0.53%), recall (94.36% ± 0.79%), F1 score (95.22% ± 0.56%), AP0.50 (93.36% ± 0.93%), AR0.50:0.95 (64.73% ± 1.46%), APsmall (55.04 ± 0.96%), APmedium (59.97 ± 1.13%), and APlarge (68.09 ± 5.18%) compared to Faster R‐CNN and YOLOv3. Moreover, FCOS demonstrated significantly higher AR0.50:0.95 and APsmall compared to SSD. Regardless of the presence of single or multiple coronary stenoses in ICA images, FCOS also outperformed Faster R‐CNN and YOLOv3. Furthermore, it showed significantly higher AR0.50:0.95 compared to SSD when in the multiple stenosis scenario. Conclusions. It is feasible to use the anchor‐free DL model FCOS in detecting coronary stenosis based on ICA images.

Laminar burning velocities of rich NH3+N2+O2 flames: Comparing the effects of elevated temperatures and oxygen ratios on model validation

Ammonia (NH3) is a promising carbon-free alternative fuel. One of its fundamental combustion properties, the laminar burning velocity (SL), is widely used to validate the combustion kinetic models. This study investigates the SL across varying unburned mixture temperature Tu and oxygen ratio xO2, particularly regarding their impact on the model validation. The focus is on the fuel-rich conditions that exhibit noticeable discrepancies among different kinetic model predictions. To provide accurate experimental data for the analyses, atmospheric measurements were carried out using the heat flux method, covering equivalence ratios ranging from 1.2 to 1.9, Tu from 298 K to 448 K, and xO2 from 0.30 to 0.38. Notably, many of these conditions have not been thoroughly explored in existing literature. Seven kinetic models were used to compare with the experimental data and assess the simulation discrepancies, where the increment parameters were used to compare the effect of SL vs. Tu and SL vs. xO2 dependences on the model validations. Through these analyses, the α coefficient, describing the SL vs. Tu dependence, is found too difficult to distinguish the performances of the various models and serve as validation targets. Sensitivity analyses reveal that the reactions governing the dependences of SL on both Tu and xO2 are fundamentally the same. Similar flame conditions with nearly identical sensitivity values were identified, suggesting that a model accurately reproducing the SL vs. Tu trend is promised to replicate the SL vs. xO2 trend, and vice versa. Consequently, the SL measurement with elevated Tu, which is difficult in experiments and in distinguishing the performance of different models, is suggested to be substituted by the much easier measurement with elevated xO2. This conclusion, alongside the methodology, holds potential for application in other flame types and help reduce the experimental efforts for model updating.

Comparison Study Using Arima and Ann Models for Forecasting Sugarcane Yield

Sugarcane is the largest crop in the world in terms of production. We use sugarcane and its byproducts more and more frequently in our daily lives, which elevates it to the status of a unique crop. As a result, the assessment of sugarcane production is critical since it has a direct impact on a wide range of lives. The yield of sugarcane is predicted using ARIMA and ANN models in this study. The models are based on sugarcane yield data collected over a period of 56 years (1951-2017). Root Mean Square Error (RMSE) and Mean Absolute Percentage Error (MAPE) have been used to analyze and compare the performance of different models to obtain the best-fit model. The results show that the RMSE and MAPE values of the ANN model are lower than those of the ARIMA model and that the ANN model matches best to this data set.

2.5D transfer deep learning model for segmentation of contrast-enhancing lesions on brain magnetic resonance imaging of multiple sclerosis and neuromyelitis optica spectrum disorder.

Multiple sclerosis (MS) and neuromyelitis optica spectrum disorder (NMOSD) are the two mimic autoimmune diseases of the central nervous system, which are rare in East Asia. Quantitative detection of contrast-enhancing lesions (CELs) on contrast-enhancing T1-weighted magnetic resonance (MR) images is of great significance for assessing the disease activity of MS and NMOSD. However, it is challenging to develop automatic segmentation algorithms due to the lack of data. In this work, we present an automatic segmentation model of CELs based on Fully Convolutional with Attention DenseNet (FCA-DenseNet) and transfer learning strategy to address the challenge of CEL quantification in small-scale datasets. A transfer learning approach was employed in this study, whereby pretraining was conducted using 77 MS subjects from the open access datasets (MICCAI 2016, MICCAI 2017, ISBI 2015) for white matter hyperintensity segmentation, followed by fine-tuning using 24 MS and NMOSD subjects from the local dataset for CEL segmentation. The proposed FCA-DenseNet combined the Fully Convolutional DenseNet and Convolutional Block Attention Module in order to improve the learning capability. A 2.5D data slicing strategy was used to process complex 3D MR images. U-Net, ResUNet, TransUNet, and Attention-UNet are used as comparison models to FCA-DenseNet. Dice similarity coefficient (DSC), positive predictive value (PPV), true positive rate (TPR), and volume difference (VD) are used as evaluation metrics to evaluate the performances of different models. FCA-DenseNet outperforms all other models in terms of all evaluation metrics, with a DSC of 0.661±0.187, PPV of 0.719±0.201, TPR of 0.680±0.254, and VD of 0.388±0.334. Transfer learning strategy has achieved success in building segmentation models on a small-scale local dataset where traditional deep learning approaches fail to train effectively. The improved FCA-DenseNet, combined with transfer learning strategy and 2.5D data slicing strategy, has successfully addressed the challenges in constructing deep learning models on small-scale datasets, making it conducive to clinical quantification of brain CELs and diagnosis of MS and NMOSD.

Machine learning tools for peptide bioactivity evaluation – Implications for cell culture media optimization and the broader cultivated meat industry

Although bioactive peptides have traditionally been studied for their health-promoting qualities in the context of nutrition and medicine, the past twenty years have seen a steady increase in their application to cell culture media optimization. Complex natural sources of bioactive peptides, such as hydrolysates, offer a sustainable and cost-effective means of promoting cellular growth, making them an essential component of scaling-up cultivated meat production. However, the sheer diversity of hydrolysates makes product selection difficult, highlighting the need for functional characterization. Traditional wet-lab techniques for isolating and estimating peptide bioactivity cannot keep pace with peptide identification using high-throughput tools such as mass spectrometry, requiring the development and use of machine learning-based classifiers.This review provides a comprehensive list of available software tools to evaluate peptide bioactivity, classified and compared based on the algorithm, training set, functionality, and limitations of the underlying models. We curated independent test sets to compare the predictive performance of different models based on specific bioactivity classification relevant to promoting cell culture growth: antioxidant and anti-inflammatory. A comprehensive screening of all bioactivity classifiers revealed that while there are approximately fifty tools to elucidate antimicrobial activity and sixteen that predict anti-inflammatory activity, fewer tools are available for other functionalities related to cell growth — five that predict antioxidant activity and two for growth factor and/or cell signaling prediction. A thorough evaluation of the available tools revealed significant issues with sensitivity, specificity, and overall accuracy. Despite the overall interest in estimating peptide bioactivity, our work highlights key gaps in the broader adoption of existing software for the specific application of cell culture media optimization in the context of cultivated meat and beyond.

Comparison of XGBoost and LSTM Models for Stock Price Prediction

Along with the development of technology, machine learning would take up a higher role in analyzing categories. Among those categories, predicting stock price meets the needs of most peopleor most people who trade stocks. By referring to the predicting model, stock traders can decide whether they should trade in or trade out to make a profit in the stock market. Therefore, it is necessary to testify which model can make the prediction with higher accuracy. To analyze this problem, this article examines the performance of different models under different size of datasets. This paper compared XGBoost and LSTM model by collecting stock price data that are 3 years, 6 years, and 9 years ago from the year 2023. Then analyze the close price of stock prices those models. By comparing the figures and calculated rmse value in each year and each model, the impact of different dataset sizes on each model would be revealed. This paper discovered that XGBoost model has greater accuracy under large-size dataset overall, but LSTM can predict more accurate stock price under small-size dataset.

YOLO_MRC: A fast and lightweight model for real-time detection and individual counting of Tephritidae pests

Tephritidae pests severely affect the quality and safety of various melons, fruits and vegetable crops. However, many agricultural managers lack an adequate understanding of the level of pest occurrence, resulting in the misuse of pesticides, which ultimately leads to environmental pollution and economic loss. Therefore, real-time detection and counting of Tephritidae pests are important for timely pest spotting and control. This work helps quickly determine the distribution and abundance of pests in the current environment, thus providing data on pest conditions for agricultural management to optimize pesticide use. Nevertheless, the fast speed, high accuracy, and lightweight performance of real-time detection and counting are difficult to balance. To address this problem, based on the YOLOv8n model, this paper takes Bactrocera cucurbitae pests as the detection target and proposes a fast and lightweight real-time detection and individual counting model for Tephritidae pests, named YOLO_MRC. This paper introduces three key improvements: (1) Constructing a new module called Multicat into the neck network increases the focus on the detection target by incorporating an attention mechanism; (2) Reducing the original three detection heads to two and then adjusting their sizes to decrease the number of parameters in the network model; (3) Devising a novel module, C2flite, to enhance the deep feature extraction capability of the backbone network. According to the above points, this paper conducts ablation experiments to compare the performances of different models. Experiments showed that the Multicat module significantly offsets the large increase in GFLOPs and processing time caused by reducing the detection head and can further reduce the number of parameters and improve the accuracy when combined with the C2flite module. On our Bactrocera cucurbitae pest dataset, the mAP@0.5 of the YOLO_MRC model reached 99.3%. Simultaneously, as the number of parameters decreases by 63.68%, GFLOPs is reduced by 19.75%, and the processing time is shortened by 5%. To ensure the validity of the model, YOLO_MRC is compared with four excellent detection models by using manual counting results as the benchmark. YOLO_MRC achieves an average pest counting accuracy of 94%, demonstrating superior performance in terms of model size and processing time. To further explore the performance of YOLO_MRC in multiclass insect detection tasks, we choose the public dataset Pest_24_640 for comparison with four state-of-the-art models. YOLO_MRC achieves a 3.6 ms processing time and 70.4% accuracy with only a 2.4 MB model size, which demonstrates the potential of YOLO_MRC in multiclass pest detection.

A Comparative Study of the Performance of Machine Learning Models on a Tax Dataset of Yemen to Detect Levels of Tax Evasion

The performance of a classification model in machine learning is affected by many factors, such as the type of machine learning technology used. Accuracy varies from method to method. This paper presents a comparison between the performance of different models in terms of the machine learning technique used (e.g. KNN, NB, SVM, DT, RF, MLP). Based on the data provided by the Tax Authority of Yemen, which is related to the commercial and industrial profits tax, which consists of 760 attributes, after the preprocessing of data. The dataset partition technique used k-fold validation. The paper shows that the e Naïve Bayes (NB) classifier gave the highest result in accuracy and other measures. Then KNN, SVM, and RF gave the same results in accuracy 99.87%, but in SVM, KNN the results were also the same in the rest measures, while in RF models the rest measures were 97.91%,99.95%, and 98.91% in Recall, Precision and F-score in order. MLP gave 98.42 in accuracy with 66.62%, 64.21%, and 64.40 in the recall, Precision, and F-score, then DT gave 97.76% in accuracy with 57.006% ,99.24% and 72.41% in the recall, precision, and F-score.

18F-FDG PET/CT-based deep learning radiomics predicts 5-years disease-free survival after failure to achieve pathologic complete response to neoadjuvant chemotherapy in breast cancer

BackgroundThis study aimed to assess whether a combined model incorporating radiomic and depth features extracted from PET/CT can predict disease-free survival (DFS) in patients who failed to achieve pathologic complete response (pCR) after neoadjuvant chemotherapy.ResultsThis study retrospectively included one hundred and five non-pCR patients. After a median follow-up of 71 months, 15 and 7 patients experienced recurrence and death, respectively. The primary tumor volume underwent feature extraction, yielding a total of 3644 radiomic features and 4096 depth features. The modeling procedure employed Cox regression for feature selection and utilized Cox proportional-hazards models to make predictions on DFS. Time-dependent receiver operating characteristic (ROC) curves and the area under the ROC curve (AUC) were utilized to evaluate and compare the predictive performance of different models. 2 clinical features (RCB, cT), 4 radiomic features, and 7 depth features were significant predictors of DFS and were included to develop models. The integrated model incorporating RCB, cT, and radiomic and depth features extracted from PET/CT images exhibited the highest accuracy for predicting 5-year DFS in the training (AUC 0.943) and the validation cohort (AUC 0.938).ConclusionThe integrated model combining radiomic and depth features extracted from PET/CT images can accurately predict 5-year DFS in non-pCR patients. It can help identify patients with a high risk of recurrence and strengthen adjuvant therapy to improve survival.

OP134 Mapping The Health Of The Nation Outcomes Scale To The EQ-5D Using The Pharmacotherapy Monitoring And Outcome Survey

IntroductionIn clinical practice, health outcomes relevant for economic evaluations, such as health-related quality of life (i.e., utilities), are not always available. However, algorithms can be developed to map available outcome measures to utilities. In the Netherlands, the Health of the Nations Outcomes Scores (HoNOS) is a physician-reported, disease-specific outcome measure frequently used for patients with severe mental illness for which no mapping algorithms for utilities currently exist. The aim of this study was to develop an algorithm to map responses on the HoNOS to EQ-5D utilities for use in economic evaluations.MethodsA dataset was obtained from the Pharmacotherapy Monitoring and Outcome Survey cohort study containing data from patients with psychotic disorders. The dataset contains EQ-5D-3L domain and HoNOS scores, the age and sex of patients, and additional demographics. Correlation between the EQ-5D-3L and HoNOS was evaluated. To derive mapping functions, least absolute shrinkage and selection operator (LASSO) regression and random forest algorithms were applied with various predictor variables using a machine learning approach, whereby data were split into separate training and test sets. Cross-validation was then used to compare the performance of different models using R-squared and the root mean square error (RMSE).ResultsA total of 2,111 patients were included in the study. Spearman’s correlation coefficients indicated a weak to moderate negative correlation of -0.31. Based on model performance metrics, LASSO models outperformed random forest models on the training set, where the model including all individual HoNOS items and the age and sex of patients showed the best overall performance with an RMSE of 0.237 and an R-squared of 0.218. When applied to the test set, this resulted in an R-squared of 0.233 and a mean absolute error of 0.177.ConclusionsThe HoNOS can be mapped onto EQ-5D-3L utilities with moderate predictive accuracy. The reported mapping algorithm may be sufficient to predict overall population utility scores for use in health economic evaluations but lacks accuracy for individual patient predictions.

Modeling the Differences between Ultra-Rapid and Final Orbit Products of GPS Satellites Using Machine-Learning Approaches

The International GNSS Service analysis centers provide orbit products of GPS satellites with weekly, daily, and sub-daily latency. The most frequent ultra-rapid products, which include 24 h of orbits derived from observations and 24 h of orbit predictions, are vital for real-time applications. However, the predicted part of the ultra-rapid orbits is less accurate than the estimated part and has deviations of several decimeters with respect to the final products. In this study, we investigate the potential of applying machine-learning (ML) and deep-learning (DL) algorithms to further enhance physics-based orbit predictions. We employed multiple ML/DL algorithms and comprehensively compared the performances of different models. Since the prediction errors of the physics-based propagators accumulate with time and have sequential characteristics, specific sequential modeling algorithms, such as Long Short-Term Memory (LSTM), show superiority. Our approach shows promising results with average improvements of 47% in 3D RMS within the 24-hour prediction interval of the ultra-rapid products. In the end, we applied the orbit predictions improved by LSTM to kinematic precise point positioning and demonstrated the benefits of LSTM-improved orbit predictions for positioning applications. The accuracy of the station coordinates estimated based on these products is improved by 16% on average compared to those using ultra-rapid orbit predictions.

Machine learning-based assessment of hygrothermal aging performance in CFRP-aluminum alloy adhesive bonded structures

ABSTRACT Adhesive bonding is an effective technique for connecting fiber reinforced composites (FRPs) and plays a crucial role in determining load transfer capability and overall structural safety. However, long-term exposure to temperature and moisture can degrade adhesive joints, highlighting the significant importance of accurately predicting their durability when designing reliable adhesive structures. This study aims to address the industry’s demand and academic interest by proposing a convenient and accurate prediction method to evaluate the durability of adhesive structures subject to complex stresses. Laboratory accelerated aging experiments were conducted on butt joints (experiencing pure normal stress) and shear joints (experiencing pure shear stress). Quasi-static tensile tests and adhesive FTIR tests were performed to establish a dataset of adhesive functional group absorbance and failure strength under single stress conditions. To compare and assess the predictive performance of different models for aging behaviors, Artificial Neural Network (ANN), Support Vector Regression (SVR) and Random Forest (RF) models were selected. The model hyperparameters were further optimized using the Genetic Algorithm (GA). The results demonstrated that the ANN model exhibited superior correlation and accuracy compared to the SVR, and RF. The characteristic importance analysis revealed that the hydrolysis and post-curing of adhesives were the primary factors affecting joint performance under hygrothermal environments. By incorporating environmental degradation factors and defining initial failure criteria, the CZM constitutive model was modified and a predictive method was established for assessing the hygrothermal aging behavior of CFRP/aluminum alloy bonding structures. This method effectively eliminates the effect the intricate aging process (e.g. aging time, aging conditions) and establishes a direct correlation between the molecular structure of adhesive and the macroscopic mechanical properties of the bonded joint, which serves as a valuable reference and guidance for the safety design of automotive composite material bonding structures throughout their entire lifespan.

Data-driven prediction of ship fuel oil consumption based on machine learning models considering meteorological factors

To improve the energy efficiency of ships and reduce greenhouse gas (GHG) emissions, the implementation of energy-efficient operation measures is particularly important. Driven by this, this study was dedicated to improving the accuracy of ship fuel oil consumption (FOC) prediction and laying the foundation for optimizing energy-efficient operations. Firstly, we combined voyage reports and meteorological data and constructed six datasets containing different features. These features comprise navigation-related features encompassing sailing speed, displacement and trim, as well as meteorological features encompassing wind, wave, sea current, sea water salinity and sea water temperature. Secondly, we conducted experiments with 14 popular ML models on the datasets and compared the prediction performance of different models by a new scoring system. Finally, we explored the advantages and disadvantages of each dataset based on the model performance scoring results and analyzed the effects of related meteorological factors on FOC during navigation. The key findings of the proposed work were that extra trees (ET), random forest (RF), XGBoost, and LightGBM had good fitting and generalization performance. Set5, the dataset containing the most complete meteorological data, achieved the best prediction results. In particular, it had an R2 (test) of 0.9317 on the ET model, which was 1.97% higher than the R2 (test) of the dataset using only voyage reports. The conclusions can assist shipping companies in constructing a ship FOC prediction framework and developing ship fuel-saving strategies.

Assessing model prediction performance for the expected cumulative number of recurrent events.

In a recurrent event setting, we introduce a new score designed to evaluate the prediction ability, for a given model, of the expected cumulative number of recurrent events. This score can be seen as an extension of the Brier Score for single time to event data but works for recurrent events with or without a terminal event. Theoretical results are provided that show that under standard assumptions in a recurrent event context, our score can be asymptotically decomposed as the sum of the theoretical mean squared error between the model and the true expected cumulative number of recurrent events and an inseparability term that does not depend on the model. This decomposition is further illustrated on simulations studies. It is also shown that this score should be used in comparison with a reference model, such as a nonparametric estimator that does not include the covariates. Finally, the score is applied for the prediction of hospitalisations on a dataset of patients suffering from atrial fibrillation and a comparison of the prediction performances of different models, such as the Cox model, the Aalen Model or the Ghosh and Lin model, is investigated.

Incremental forecaster using C–C algorithm to phase space reconstruction and broad learning network for short-term wind speed prediction

Wind power gains more and more attention from all over the world as a clean and renewable energy resource, and accurate prediction of wind speed has become a hot issue. This paper presents a novel incremental forecaster based on phase space reconstruction and broad learning network (BLN) for short-term prediction. First, time delay and embedding dimension which take an essential part in phase space reconstruction are determined by the C–C algorithm. Then, these optimal parameters are input to the BLN trained incrementally. Afterward, forecasting values are given by the output layer of BLN. Data collected from a wind farm is adopted for verifying the efficacy of this proposed model. Furthermore, five commonly used assessment indicators are applied to evaluate predictive performance of different models. Results show that the proposed model has the smallest prediction error, which performs better than the other models at one-step to three-step ahead forecasting, and this strength is attributed to address the problem of local optimum. Furthermore, the proposed model consumes less training time than the other models. Therefore, the proposed model tends to be promising for wind speed prediction of the big data era.

Elazığ İli için Meterolojik Ölçüm Verileri Kullanılarak Rüzgar Hızı Tahmini

As a result of the increasing energy demand and growing environmental concerns, the global significance of renewable energy resources is steadily rising. Wind energy has been increasingly gaining importance in electricity generation in recent years. The accurate prediction of wind speed is crucial for the safe operation of wind turbines. In this study, wind speed prediction performance of different models was examined using data obtained from various regions in the Elazığ province. LSTM, random forest, and XGBoost models were employed in the study. The dataset was decomposed into seasonal and trend components using the STL method, and seasonal components were determined using Fourier transformation. The results indicate that different models perform better in different regions. According to the findings, XGBoost and random forest models exhibit the lowest RMSE and MSE values in Elazığ, Keban, and Sivrice regions, indicating better predictions for these models in these areas.

Multi-ontology embeddings approach on human-aligned multi-ontologies representation for gene-disease associations prediction

ObjectivesKnowledge graphs and ontologies in the biomedical domain provide rich contextual knowledge for a variety of challenges. Employing that for knowledge-driven NLP tasks such as gene-disease association prediction represents a promising way to increase the predictive power of a model. MethodsWe investigated the power of infusing the embedding of two aligned ontologies as prior knowledge to the NLP models. We evaluated the performance of different models on some large-scale gene-disease association datasets and compared it with a model without incorporating contextualized knowledge (BERT). ResultsThe experiments demonstrated that the knowledge-infused model slightly outperforms BERT by creating a small number of bridges. Thus, indicating that incorporating cross-references across ontologies can enhance the performance of base models without the need for more complex and costly training. However, further research is needed to explore the generalizability of the model. We expected that adding more bridges would bring further improvement based on the trend we observed in the experiments. In addition, the use of state-of-the-art knowledge graph embedding methods on a joint graph from connecting OGG and DOID with bridges also yielded promising results. ConclusionOur work shows that allowing language models to leverage structured knowledge from ontologies does come with clear advantages in the performance. Besides, the annotation stage brought out in this paper is constrained in reasonable complexity.

Mineral resource assessment through geostatistical analysis in a phosphate deposit

Purpose. The selection of an appropriate variographic model is crucial in geostatistics to obtain accurate estimates of mineral reserves. The aim of this work is to develop a reserve estimation tool using a geostatistical approach. Methodology. The geostatistical approach is based on selecting the most representative variographic models for the studied variables. The model selection is done by applying a cross-validation procedure leave-one-out (LOOCV). LOOCV is a resampling technique used in statistical analysis and machine learning to estimate the generalization error of a model and compare the performance of different models. The studied variables are then estimated using ordinary kriging. Findings. The application of the proposed approach has resulted in satisfactory results in terms of dispersion of grades and thicknesses of mineralized layers in a phosphate deposit. To evaluate the quality of the adjustment models obtained, efficiency factors such as Nash-Sutcliffe, and RMSE (Root Mean Square Error), were employed. These factors provide quantitative measures of the agreement between the observed and predicted values. The NSE (Nash-Sutcliffe efficiency) and RMSE (root mean square error) values of 0.572 and 6.599, respectively, indicate a better fit and greater accuracy of the adjustment models. The accuracy and efficiency criteria of the studied variables have acceptable values, with a mean square error (MSE) of 1.54 · 10-7. Originality. The combination of the least squares and LOOCV methods in the geostatistical analysis leads to improved estimation precision, greater reliability in representing the spatial variability of the parameters, and enhanced confidence in the validity of the adjustment models. Practical value. The development of a computer code for this geostatistical approach provides a practical tool for decision-makers to use in the management and exploitation of mining sites. Overall, this study has contributed to the advancement of geostatistical techniques and their application in the mining industry.

Arabic Toxic Tweet Classification: Leveraging the AraBERT Model

Social media platforms have become the primary means of communication and information sharing, facilitating interactive exchanges among users. Unfortunately, these platforms also witness the dissemination of inappropriate and toxic content, including hate speech and insults. While significant efforts have been made to classify toxic content in the English language, the same level of attention has not been given to Arabic texts. This study addresses this gap by constructing a standardized Arabic dataset specifically designed for toxic tweet classification. The dataset is annotated automatically using Google’s Perspective API and the expertise of three native Arabic speakers and linguists. To evaluate the performance of different models, we conduct a series of experiments using seven models: long short-term memory (LSTM), bidirectional LSTM, a convolutional neural network, a gated recurrent unit (GRU), bidirectional GRU, multilingual bidirectional encoder representations from transformers, and AraBERT. Additionally, we employ word embedding techniques. Our experimental findings demonstrate that the fine-tuned AraBERT model surpasses the performance of other models, achieving an impressive accuracy of 0.9960. Notably, this accuracy value outperforms similar approaches reported in recent literature. This study represents a significant advancement in Arabic toxic tweet classification, shedding light on the importance of addressing toxicity in social media platforms while considering diverse languages and cultures.