Machine Model Research Articles

MKELM based multi-classification model for foreign accent identification

The automatic identification of foreign accents can play a crucial role in various speech systems, including speaker identification, e-learning, telephone banking, and more. Additionally, it can greatly enhance the robustness of Automatic Speech Recognition (ASR) systems. Non-native accents in speech signals are characterized by distinct pronunciations, prosody, and voice characteristics of the speaker. However, automatically identifying foreign accents poses significant challenges, particularly in the context of multi-class modeling. Multi-classification models face difficulties in achieving high performance and dealing with computational challenges when confronted with multi-dimensional and unbalanced datasets, such as those with more than two accents. Furthermore, the choice of features remains a bottleneck problem for Foreign Accent Identification (FAID), further hindering performance in these tasks. Consequently, the accuracy of current systems is typically low. To address these challenges, this paper proposes a framework based on the Multi-Kernel Extreme Learning Machine (MKELM) model for the multi-classification of FAID. The MKELM model utilizes a novel weighted scheme to classify various non-native English accents, including Arabic, Chinese, Korean, French, and Spanish. The model first combines Mel-frequency cepstral coefficients (MFCCs) and prosodic features as input, trains pairwise binary classifiers independently, and subsequently employs a weighting scheme to distinguish between classes and identify accents. Through experiments, the proposed model achieves an accuracy rate of 84.72% using a paired weighting scheme. In contrast, the accuracy rate drops to 66.5% when employing the traditional non-weighted multi-classification scheme. A comparison with other models demonstrates the significant advantages of the proposed model in FAID multi-class classification, showcasing improved accuracy, reduced computational complexity (requiring fewer computations, faster learning rates, and shorter training time), and enhanced stability compared to state-of-the-art classification methods.

A novel sand cat swarm optimization algorithm-based SVM for diagnosis imaging genomics in Alzheimer's disease.

In recent years, brain imaging genomics has advanced significantly in revealing underlying pathological mechanisms of Alzheimer's disease (AD) and providing early diagnosis. In this paper, we present a framework for diagnosing AD that integrates magnetic resonance imaging (fMRI) genetic preprocessing, feature selection, and a support vector machine (SVM) model. In particular, a novel sand cat swarm optimization (SCSO) algorithm, named SS-SCSO, which integrates the spiral search strategy and alert mechanism from the sparrow search algorithm, is proposed to optimize the SVM parameters. The optimization efficacy of the SS-SCSO algorithm is evaluated using CEC2017 benchmark functions, with results compared with other metaheuristic algorithms (MAs). The proposed SS-SCSO-SVM framework has been effectively employed to classify different stages of cognitive impairment in Alzheimer's Disease using imaging genetic datasets from the Alzheimer's Disease Neuroimaging Initiative. It has demonstrated excellent classification accuracies for four typical cases, including AD, early mild cognitive impairment, late mild cognitive impairment, and healthy control. Furthermore, experiment results indicate that the SS-SCSO-SVM algorithm has a stronger exploration capability for diagnosing AD compared to other well-established MAs and machine learning techniques.

Optimasi Support Vector Machine (SVM) Menggunakan Naive Bayes dan Decision Tree untuk Klasifikasi Tema Tugas Akhir Mahasiswa Sistem Informasi

-The School of Informatics and Computer Management (STMIK) Abulyatama faces challenges in classifying student thesis topics. The current manual classification process is inefficient and ineffective. Therefore, the implementation of data mining techniques is needed to manage this data, specifically to automate the classification process. This study aims to optimize the Support Vector Machine (SVM) model by integrating Naive Bayes and Decision Tree algorithms to improve the accuracy of thesis topic classification. Based on the analysis, it can be concluded that both SVM and K-Means can be utilized by decision-makers to categorize thesis topics as a decision support system. Naive Bayes and Decision Tree were shown to optimize SVM and enhance its accuracy. Naive Bayes achieved the highest accuracy at 82.50%, while Decision Tree recorded an accuracy of 62.50%, making Naive Bayes the most suitable model for thesis classification.

A Real-World Study on the Short-Term Efficacy of Amlodipine in Treating Hypertension Among Inpatients.

Hospitalized hypertensive patients rely on blood pressure medication, yet there is limited research on the sole use of amlodipine, despite its proven efficacy in protecting target organs and reducing mortality. This study aims to identify key indicators influencing the efficacy of amlodipine, thereby enhancing treatment outcomes. In this multicenter retrospective study, 870 hospitalized patients with primary hypertension exclusively received amlodipine for the first 5 days after admission, and their medical records contained comprehensive blood pressure records. They were categorized into success (n=479) and failure (n=391) groups based on average blood pressure control efficacy. Predictive models were constructed using six machine learning algorithms. Evaluation metrics encompassed the area under the curve (AUC), accuracy, sensitivity, specificity, positive predictive value (PPV), and negative predictive value (NPV). SHapley Additive exPlanations (SHAP) analysis assessed feature contributions to efficacy. All six machine learning models demonstrated superior predictive performance. Following variable reduction, the model predicting amlodipine efficacy was reconstructed using these algorithms, with the light gradient boosting machine (LightGBM) model achieving the highest overall performance (AUC = 0.803). Notably, amlodipine showed enhanced efficacy in patients with low platelet distribution width (PDW) values, as well as high hematocrit (HCT) and thrombin time (TT) values. This study utilized machine learning to predict amlodipine's effectiveness in hypertension treatment, pinpointing key factors: HCT, PDW, and TT levels. Lower PDW, along with higher HCT and TT, correlated with enhanced treatment outcomes. This facilitates personalized treatment, particularly for hospitalized hypertensive patients undergoing amlodipine monotherapy.

Machine Learning Predicts Patients With New-onset Diabetes at Risk of Pancreatic Cancer.

New-onset diabetes represent a high-risk cohort to screen for pancreatic cancer. Develop a machine model to predict pancreatic cancer among patients with new-onset diabetes. A retrospective cohort of patients with new-onset diabetes was assembled from multiple health care networks in the United States. An XGBoost machine learning model was designed from a portion of this cohort (the training set) and tested on the remaining part of the cohort (the test set). Shapley values were used to explain the XGBoost's model features. Model performance was compared with 2 contemporary models designed to predict pancreatic cancer among patients with new-onset diabetes. In the test set, the XGBoost model had an area under the curve of 0.80 (0.76 to 0.85) compared with 0.63 and 0.68 for other models. Using cutoffs based on the Youden index, the sensitivity of the XGBoost model was 75%, the specificity was 70%, the accuracy was 70%, the positive predictive value was 1.2%, and the negative predictive value was >99%. The XGBoost model obtained a positive predictive value of at least 2.5% with a sensitivity of 38%. The XGBoost model was the only model that detected at least 50% of patients with cancer one year after the onset of diabetes. All 3 models had similar features that predicted pancreatic cancer, including older age, weight loss, and the rapid destabilization of glucose homeostasis. Machine learning models isolate a high-risk cohort from those with new-onset diabetes at risk for pancreatic cancer.

Combining Hyperspectral Techniques and Genome-Wide Association Studies to Predict Peanut Seed Vigor and Explore Associated Genetic Loci.

Seed vigor significantly affects peanut breeding and agricultural yield by influencing seed germination and seedling growth and development. Traditional vigor testing methods are inadequate for modern high-throughput assays. Although hyperspectral technology shows potential for monitoring various crop traits, its application in predicting peanut seed vigor is still limited. This study developed and validated a method that combines hyperspectral technology with genome-wide association studies (GWAS) to achieve high-throughput detection of seed vigor and identify related functional genes. Hyperspectral phenotyping data and physiological indices from different peanut seed populations were used as input data to construct models using machine learning regression algorithms to accurately monitor changes in vigor. Model-predicted phenotypic data from 191 peanut varieties were used in GWAS, gene-based association studies, and haplotype analyses to screen for functional genes. Real-time fluorescence quantitative PCR (qPCR) was used to analyze the expression of functional genes in three high-vigor and three low-vigor germplasms. The results indicated that the random forest and support vector machine models provided effective phenotypic data. We identified Arahy.VMLN7L and Arahy.7XWF6F, with Arahy.VMLN7L negatively regulating seed vigor and Arahy.7XWF6F positively regulating it, suggesting distinct regulatory mechanisms. This study confirms that GWAS based on hyperspectral phenotyping reveals genetic relationships in seed vigor levels, offering novel insights and directions for future peanut breeding, accelerating genetic improvements, and boosting agricultural yields. This approach can be extended to monitor and explore germplasms and other key variables in various crops.

Using enhanced Variational Modal Decomposition and Dung Beetle Optimization Algorithm optimization-kernel Extreme Learning Machine model to forecast short-term wind power

With the widespread use of clean energy, the forecasting of wind power has become increasingly significant. Extracting time series from sophisticated wind power data and thus improving the prediction accuracy of wind power generation has become the key to short-term forecasting. This paper proposes a Kernel Extreme Learning Machine (KELM) prediction model based on Crested Porcupine Optimizer (CPO), Variational Modal Decomposition (VMD) with Improved Dung Beetle Optimization Algorithm (QHDBO). Firstly, by analyzing the correlation between the variables in the wind power data, the CPO algorithm is used to optimize the modal decomposition number and the penalty parameter of the VMD and extract the time-series information of the wind power series, and smooth it to obtain a number of sub-sequences with strong regularity. Then, the KELM prediction model is constructed for different subsequences, and the kernel parameters and regularization coefficients of KELM are optimized using the QHDBO algorithm. Finally, the predicted values of different subsequences are reconstructed to obtain the final prediction results. The simulation results show that the CVMD-QHDBO-KELM model can effectively improve the wind power prediction performance, and the MAPE values are all below 9 %, and most of the RE values are below 10 %.

Application Value of the Automated Machine Learning Model Based on Modified Computed Tomography Severity Index Combined With Serological Indicators in the Early Prediction of Severe Acute Pancreatitis.

Machine learning (ML) algorithms are widely applied in building models of medicine due to their powerful studying and generalizing ability. To assess the value of the Modified Computed Tomography Severity Index (MCTSI) combined with serological indicators for early prediction of severe acute pancreatitis (SAP) by automated ML (AutoML). The clinical data, of the patients with acute pancreatitis (AP) hospitalized in Hospital 1 and hospital 2 from January 2017 to December 2021, were retrospectively analyzed. Serological indicators within 24 hours of admission were collected. MCTSI score was completed by noncontrast computed tomography within 24 hours of admission. Data from the hospital 1 were adopted for training, and data from the hospital 2 were adopted for external validation. The diagnosis of AP and SAP was based on the 2012 revised Atlanta classification of AP. Models were built using traditional logistic regression and AutoML analysis with 4 types of algorithms. The performance of models was evaluated by the receiver operating characteristic curve, the calibration curve, and the decision curve analysis based on logistic regression and decision curve analysis, feature importance, SHapley Additive exPlanation Plot, and Local Interpretable Model Agnostic Explanation based on AutoML. A total of 499 patients were used to develop the models in the training data set. An independent data set of 201 patients was used to test the models. The model developed by the Deep Neural Net (DL) outperformed other models with an area under the receiver operating characteristic curve (areas under the curve) of 0.907 in the test set. Furthermore, among these AutoML models, the DL and gradient boosting machine models achieved the highest sensitivity values, both exceeding 0.800. The AutoML model based on the MCTSI score combined with serological indicators has good predictive value for SAP in the early stage.

Intelligent risk identification for drilling lost circulation incidents using data-driven machine learning

In drilling operations, lost circulation (LC) poses a significant challenge, potentially leading to severe accidents such as overflow or blowouts if not accurately identified and controlled. This study introduces a method for identifying LC risk severity using data-driven machine learning and statistical algorithms, specifically demonstrated in the Ying-Qiong Basin of the South China Sea. The method begins with variance filtering to eliminate invalid data, followed by the application of the Pearson correlation coefficient to remove redundant data. This process results in the selection of 12 logging parameters out of the initial 38. Combined with indirect judgments of LC severity based on relevant prior knowledge, the data is labeled to construct the original dataset. A feature extraction and optimization method is proposed, which employs sliding time windows to extract 21 features. These features are then selected and optimized using a random forest algorithm to construct the optimal feature set. To enhance the controllability of the Extreme Learning Machine (ELM) model, the sparrow search algorithm is integrated. Additionally, several fitness functions are introduced for both regression and classification models, resulting in the development of the improved ELM (IELM) model. The dataset is split into training and test sets, and the performance of the IELM model is compared to that of the standard ELM and BP neural network models. The results indicate that the IELM model outperforms the other two, achieving an impressive test F1 score of 97.22 % for accurately identifying LC severity. Moreover, the model trained using the optimal feature set demonstrates higher accuracy and faster convergence. The proposed feature extraction and optimization method effectively increases the amount of information contained in the data, thereby enhancing the model's performance.

Determination of soluble solids content in loquat using near-infrared spectroscopy coupled with broad learning system and hybrid wavelength selection strategy

Soluble solids content (SSC) serves as a crucial metric in assessing loquat quality. To achieve fast, non-destructive, and accurate detection of SSC, the combination of near-infrared (NIR) spectroscopy and broad learning system (BLS) model was developed in this study. Meanwhile, the influence of six spectral preprocessing methods and six wavelength selection algorithms on SSC prediction was explored, and the performance of the BLS model was compared with the widely used partial least squares regression (PLSR) and least squares support vector machine (LS-SVM) models. The results showed that Savitzky-Golay smoothing combined with standard normal transformation (SG-SNV) offered the optimal pretreatment, and the hybrid method, namely interval variable iterative space shrinking analysis and successive projections algorithm (iVISSA-SPA), emerged as the most effective wavelength selection method. The BLS model outperformed both PLSR and LS-SVM models. Specifically, the BLS model based on the iVISSA-SPA method achieved the optimal SSC prediction results, with RP2 = 0.8646, RMSEP = 0.5104, and RPD = 2.7481. Therefore, NIR spectroscopy coupled with the BLS model and hybrid wavelength selection strategy could rapidly, non-destructively and accurately detect the SSC of loquat, providing a viable alternative for SSC prediction in fruit.

Predicting borrower default risk using support vector machine AI models

Precise prediction on the likelihood of borrower default is pivotal for credit institution and decision makers to mitigate the loss of capital and rationalize decision process. This article reviewed the Effects of Support Vector Machine (SVM) models with radial basis function (RBF) kernel in predicting the mortality rate of borrowers. By integrating with a dataset of approximately 100,000 borrowers profile harvested through historical loan performance, we set up the SVM model, and employed a feature-distribution method utilizing grid search and cross-validation technique to fine-tune the predictive model of SVM. Results indicated that the model accomplished an excellent performance with accuracy of 92%, precision of 89%, the recall and F1-score of 85% and 87%, respectively, alongside an Area Under the Curve -Receiver Operating Characteristic (AUC-ROC value of 0.95). It was evinced that the model performed substantially better than traditional logistic regression and decision trees in discriminating defaulter from non-defaulter. The outcome informs that an in-depth process should be implemented on data preprocessing, featureselection, and parameter tuning to achieve a robust predictive model for credit risk assessment. The article concludes the potentials of AI based on the resort to artificial technology in revolutionising the risk assessment scheme within the financial industry.

Implementation Of The Support Vector Machine Method In Predicting Student Graduation

Student graduation is an important indicator of the quality of education at a higher education institution. A high graduation rate not only indicates success in the learning process but also has a positive impact on the reputation of the institution. Conversely, a low graduation rate can be a signal of problems that require special attention. Various factors, both academic and non-academic, influence higher education institutions in ensuring timely student graduation. Therefore, we need a method that can accurately predict student graduation to carry out early intervention. This study aims to apply the support vector machine method in predicting student graduation. We chose this method due to its capacity to classify complex data. We use historical student data, such as Semester Achievement Index scores, as input variables to build a prediction model. We evaluate the model using precision, recall, and f1-score metrics. According to the study's findings, the support vector machine model's accuracy level is 71.20%. This method is good at predicting students who graduate with a precision of 95%, recall of 72%, and f1-score of 82%. However, the model's performance in predicting students who failed was less than satisfactory, with a precision of only 17%, a recall of 62%, and an f1-score of 26%. The imbalance in data between passed and failed students contributed to this result. The Support Vector Machine method effectively predicts student graduation for the majority class (passed), but requires special handling of the data imbalance to enhance the accuracy of predictions for the minority class (failed). Universities expect to use the results of this study to carry out early intervention and increase student graduation rates.

Design and implementation of efficient distributed deep learning model inference architecture on serverless computation

Although the distributed algorithm and architecture have been widely used in the development of traditional large-scale machine model reasoning tasks, but it is unavoidable about the source waste caused by synchronization between learners and participants. However, serverless computing is charged based on usage, which makes it a popular alternative for model inference. This article mainly proposes the architecture and algorithm that can be used for the inference task of the distributed deep learning model and adopts coarse-grained parallelization strategy to solve the problem of high communication cost between Serverless platform functions. The paper tested the performance of the model on the deep learning model and found that the model reasoning based on the Serverless platform can better cope with the requirements and changes, and ensure the stability of the system. It is worth noting that both the data owner and the model owner can benefit from the process of carrying out the machine learning model inference task, but existing solutions cannot satisfied with them privacy requirements, which is a problem needs to think about in the field of machine learning inference tasksbased on the Serverless platform in the future.

Artificial intelligence to predict pre-clinical dental student academic performance based on pre-university results: A preliminary study.

Admission into dental school involves selecting applicants for successful completion of the course. This study aimed to predict the academic performance of Kulliyyah of Dentistry, International Islamic University Malaysia pre-clinical dental students based on admission results using artificial intelligence machine learning (ML) models, and Pearsoncorrelation coefficient (PCC). ML algorithms logistic regression (LR), decision tree (DT), random forest (RF), and support vector machine (SVM) models were applied. Academic performance prediction in pre-clinical years was made using three input parameters: age during admission, pre-university Cumulative Grade Point Average (CGPA), and total matriculation semester. PCC was deployed to identify the correlation between pre-university CGPA and dental school grades. The proposed models' classification accuracy ranged from 29% to 57%, ranked from highest to lowest as follows: RF, SVM, DT, and LR. Pre-university CGPA was shown to be predictive of dental students' academic performance; however, alone they did not yield optimal outcomes. RF was the most precise algorithm for predicting grades A, B, and C, followed by LR, DT, and SVM. In forecasting failure, LR predicted three grades with the highest recall, SVM predicted two grades, and DT predicted one. RF performance was insignificant. The findings demonstrated the application of ML algorithms and PCC to predict dental students' academic performance. However, it was limited by several factors. Each algorithm has unique performance qualities, and trade-offs between different performance metrics may be necessary. No definitive model stood out as the best algorithm for predicting student academic success in this study.

Modelling the rapid detection of Carbapenemase-resistant Klebsiella pneumoniae based on machine learning and matrix-assisted laser desorption/ionization time-of-flight mass spectrometry

In this study, 80 carbapenem-resistant Klebsiella pneumoniae (CR-KP) and 160 carbapenem-susceptible Klebsiella pneumoniae (CS-KP) strains detected in the clinic were selected and their matrix-assisted laser desorption/ionization time-of-flight mass spectrometry (MALDI-TOF MS) peaks were collected. K-means clustering was performed on the MS peak data to obtain the best "feature peaks", and four different machine learning models were built to compare the area under the ROC curve, specificity, sensitivity, test set score, and ten-fold cross-validation score of the models. By adjusting the model parameters, the test efficacy of the model is increased on the basis of reducing model overfitting. The area under the ROC curve of the Random Forest, Support Vector Machine, Logistic Regression, and Xgboost models used in this study are 0.99, 0.97, 0.96, and 0.97, respectively; the model scores on the test set are 0.94, 0.91, 0.90, and 0.93, respectively; and the results of the ten-fold cross-validation are 0.84, 0.81, 0.81, and 0.85, respectively. Based on the machine learning algorithms and MALDI-TOF MS assay data can realize rapid detection of CR-KP, shorten the in-laboratory reporting time, and provide fast and reliable identification results of CR-KP and CS-KP.

Identification and characterization of immunogenic cell death-related molecular clusters in rheumatoid arthritis

Background: This study is to analyze the potential mechanisms of immunogenic cell death genes (ICDs) in rheumatoid arthritis (RA) using bioinformatics methods and identify potential biomarkers. Method: We utilized the GSE93777 dataset to systematically evaluate the differential expression and immune characteristics of ICDs in RA patients. Thus, molecular clusters related to ICD, immune cell infiltration, and biological characteristics were explored. Weighted gene co-expression network analysis (WGCNA) was then performed to identify cluster-specific differentially expressed genes. Subsequently, we employed a Support Vector Machine (SVM) machine learning model for prediction analysis, with validation conducted using the external dataset GSE15573. Results: A total of 52 differentially expressed ICDs were identified between healthy individuals and RA patients. Compared to healthy individuals, RA patients exhibited high infiltration of T cells CD4 memory activated, T cells gamma delta, Monocytes, and Neutrophils. The ICD subtypes in RA patients displayed significant heterogeneity in terms of immunity. Specifically, Cluster 2 demonstrated elevated immune scores and relatively high levels of immune infiltration. Gene Ontology (GO) and Kyoto Encyclopedia of Genes and Genomes (KEGG) pathway analyses revealed that cluster-specific differentially expressed genes in Cluster 2 were closely associated with amino acid and glucose metabolism and degradation, as well as the biosynthesis of N-glycosylation. For the diagnosis of RA, the SVM machine model demonstrated optimal performance with relatively low residual and high area under the curve (AUC=0.998) and was validated using an external validation dataset (GSE15573, AUC=0.700). Analysis of the column chart model indicated that CKS2, NDUFB1, CHCHD1, MAGOH, and MAP7D1 could be used as diagnostic markers for RA diseases. Conclusion: This study systematically elucidates the complex relationship between ICD and RA disease and establishes a promising predictive model to evaluate the risk of ICD subtypes and pathological outcomes in RA patients.

Effect of Using Alkoxy - Silane (ethoxy silane) Coupling Agent to Enhance the Mechanical Properties of Bio-Composites

This research work investigated the effect of alkoxy silane (ethoxy silane) on the mechanical properties of polyethylene/ dried powdered pine apple peels composite. The pine apple peels was washed in distilled water, sun dried for about eight hours and later oven dried at a temperature of 60oC for about three hours. The dried pine apple peels was pulverized and sieved using a mechanical sieve arranged in descending order of fineness. The alkoxy-silane (ethoxy-silane) coupling agent (2%) was first hydrolyzed in ethanol to deliver the alkoxy functional silane to the interior of the pineapple peels and ion-free water at room temperature for 6 hours. This was followed by addition of the dried powdered pineapple peels into the hydrolyzed coupling agent solution in a reactor at a temperature of about 80 ◦C for 20 minutes. The formed product was oven dried at 110 ◦C for 3 hours and pulverized using a locally made grinding machine and sieved using a set of sieves arranged in descending order of fineness in accordance with BS1377:1990 standard as was reported by Rajan et al., (2007) to obtain pineapple peels coated with the coupling agent (150mμ). The recycled polyethylene waste was washed using distilled water, sun-dried and shredded in a shredding machine. The pineapple peels powder coated with alkoxy silane and the shredded recycled polyethylene waste were blended using a two-roll rheo-mixer at 50°C and a rotor speed of 60 rpm. The percentage of the powdered pineapple peels coated with coupling agent in the recycled polyethylene matrix was varied from 10% to 40% to produce four different compositions. A hydraulic pressing machine was used to compress the produced composites for about ten minutes applying a pressure of about 25 tons at 130°C. The produced composite samples were allowed to cool to room temperature under sustained pressure before being removed from the hydraulic press for various mechanical tests. The impact tests were performed according to ASTM D256 standard using Impact testing machine model EXT94064/6705CE, 300 J. Flexural test was performed using Universal Testing Machine model TUE-C-100, according to ASTM D790. The hardness tests were performed according to ASTM D785 standard using Rockwell Scale K hardness testing machine. The results showed that maximum flexural strength of 10.8MPa and 384Hv were recorded at 40wt.% reinforcement. The developed composite can be used applications where moderate strength will be required.

Co-seismic landslides susceptibility evaluation of Bayesian random forest considering InSAR deformation: a case study of the Luding Ms6.8 earthquake

Strong earthquakes can frequently trigger a large number of co-seismic landslides. Obtaining an accurate susceptibility map of co-seismic landslides is crucial for post-disaster rescue and reconstruction efforts. In this study, the pre-seismic average annual surface deformation rate of the study area was obtained using Small Baseline Subset Interferometric Synthetic Aperture Radar (SBAS-InSAR) technology. Furthermore, the landslide hazards prior to the earthquake in multiple locations within the study area were analyzed. Subsequently, the deformation data was combined with 11 evaluation factors, including the distance to the fault and the Peak Ground Acceleration (PGA), to model the susceptibility of landslides. We constructed four models to evaluate the susceptibility of landslides in the study area: the Bayesian optimization random forest (BO-RF) model, the random forest model (RF), the logistic regression model (LR), and the support vector machine model (SVM). The BO-RF model outperformed the other models, achieving an AUC value of 0.984, an accuracy of 0.952, a precision of 0.953, a recall of 0.952, and an F1 score of 0.953. Furthermore, incorporating pre-seismic deformation features in the evaluation of co-seismic landslide susceptibility can effectively improve the reliability of model predictions, as compared to the evaluation model results without incorporating deformation factors. The obtained research results provide valuable data support for the rescue and management of disaster-stricken areas.

Machine Learning in Medical Triage: A Predictive Model for Emergency Department Disposition

The study explores the application of automated machine learning (AutoML) using the MIMIC-IV-ED database to enhance decision-making in emergency department (ED) triage. We developed a predictive model that utilizes triage data to forecast hospital admissions, aiming to support medical staff by providing an advanced decision-support system. The model, powered by H2O.ai’s AutoML platform, was trained on approximately 280,000 preprocessed records from the Beth Israel Deaconess Medical Center collected between 2011 and 2019. The selected Gradient Boosting Machine (GBM) model demonstrated an AUC ROC of 0.8256, indicating its efficacy in predicting patient dispositions. Key variables such as acuity and waiting hours were identified as significant predictors, emphasizing the model’s capability to integrate critical triage metrics into its predictions. However, challenges related to the complexity and heterogeneity of medical data, privacy concerns, and the need for model interpretability were addressed through the incorporation of Explainable AI (XAI) techniques. These techniques ensure the transparency of the predictive processes, fostering trust and facilitating ethical AI use in clinical settings. Future work will focus on external validation and expanding the model to include a broader array of variables from diverse healthcare environments, enhancing the model’s utility and applicability in global emergency care contexts.

Interpretable machine learning boosting the discovery of targeted organometallic compounds with optimal bandgap

Organometallic compounds (OMCs) have attracted tremendous attention in various fields, such as photovoltaic cell and high-k dielectric application, due to their beneficial properties. Despite their potential, the progression of OMCs into industrial applications is hindered by the limited databases available for their properties and the absence of efficient surrogate models. To address this, in this study, optimally selected feature-based surrogate models for predicting the electronic properties of OMCs are constructed via various multiscale features and extensive database. To this end, high-throughput calculation was performed to obtain electronic properties of more than 18k materials generally known as organometallics, augmenting around 12k organic materials obtained from the public open data set, OMDB-GAP1. For generating features closely related to OMCs, descriptors encapsulating the information ranging local to global, also other widely-used composition-, structure-based features (more than 3.5k in total) were employed. Among these descriptors, we identified 48 critical features that elucidates the physicochemical underpinnings of OMCs’ properties, suggesting their impact on the properties of OMCs. The light gradient boosting machine model achieved high-accuracy predictions across the entire database with just 1 % of the total descriptors, sufficiently compared to the entire sets (decreased of around 0.01 by R2 score and 0.01 eV by MAE). Furthermore, the efficacy of active learning process was demonstrated to find OMCs with optimal properties rapidly. As a result, expected improvement outperforms other methods by identifying 69 % of the target materials only searching 46 % of the total search space. Our constructed platform with a high-throughput calculated database can pave the way for the rapid screening of OMCs for the targeted industrial application, and suggest a comprehensive grasp of the intrinsic properties of OMCs and related compounds.