Sequential Selection Research Articles

Improving the Performance of Electrotactile Brain–Computer Interface Using Machine Learning Methods on Multi-Channel Features of Somatosensory Event-Related Potentials

Traditional tactile brain–computer interfaces (BCIs), particularly those based on steady-state somatosensory–evoked potentials, face challenges such as lower accuracy, reduced bit rates, and the need for spatially distant stimulation points. In contrast, using transient electrical stimuli offers a promising alternative for generating tactile BCI control signals: somatosensory event-related potentials (sERPs). This study aimed to optimize the performance of a novel electrotactile BCI by employing advanced feature extraction and machine learning techniques on sERP signals for the classification of users’ selective tactile attention. The experimental protocol involved ten healthy subjects performing a tactile attention task, with EEG signals recorded from five EEG channels over the sensory–motor cortex. We employed sequential forward selection (SFS) of features from temporal sERP waveforms of all EEG channels. We systematically tested classification performance using machine learning algorithms, including logistic regression, k-nearest neighbors, support vector machines, random forests, and artificial neural networks. We explored the effects of the number of stimuli required to obtain sERP features for classification and their influence on accuracy and information transfer rate. Our approach indicated significant improvements in classification accuracy compared to previous studies. We demonstrated that the number of stimuli for sERP generation can be reduced while increasing the information transfer rate without a statistically significant decrease in classification accuracy. In the case of the support vector machine classifier, we achieved a mean accuracy over 90% for 10 electrical stimuli, while for 6 stimuli, the accuracy decreased by less than 7%, and the information transfer rate increased by 60%. This research advances methods for tactile BCI control based on event-related potentials. This work is significant since tactile stimulation is an understudied modality for BCI control, and electrically induced sERPs are the least studied control signals in reactive BCIs. Exploring and optimizing the parameters of sERP elicitation, as well as feature extraction and classification methods, is crucial for addressing the accuracy versus speed trade-off in various assistive BCI applications where the tactile modality may have added value.

Comparison of different machine learning methods in river streamflow estimation using isovel contours and hydraulic variables

ABSTRACT This study evaluates several machine learning (ML) models for estimating streamflow in the Osage River, Missouri, USA, and the Severn River, UK, using hydraulic input variables. These input variables are the flow section area (A), wetted perimeter (Pw ), water surface width (W), and velocity parameter (U) derived from isovel contours. Before using these models, the influential variables are selected using the sequential feature selection (SFS) method to reduce model complexity while maintaining performance. The two most important input variables identified were A and U, reducing the number of inputs from four to two. The results showed that the river’s flow conditions affect the accuracy of ML models used for estimating streamflow. Linear models such as MLR and ANFIS perform better in steady flow conditions (Osage River). In contrast, decision tree-based and non-linear models such as SVR with a radial basis kernel function (SVR_RBF) are better for unsteady flow conditions (Severn River). The finding suggests simpler models outperform complex deep-learning approaches (such as LSTM) for estimating streamflow by hydraulic variables. By selecting appropriate and efficient ML models, hydrometer stations can significantly improve the accuracy of streamflow estimation, leading to more informed decision-making in water management.

An evolving machine-learning-based algorithm to early predict response to anti-CGRP monoclonal antibodies in patients with migraine.

The present study aimed to determine whether machine-learning (ML)-based models can predict 3-, 6, and 12-month responses to the monoclonal antibodies (mAbs) against the calcitonin gene-related peptide (CGRP) or its receptor (anti-CGRPmAbs) in patients with migraine using early predictors (up to one month) and to create an evolving prediction tool. In this prospective cohort study, data from patients with migraine who had received anti-CGRP mAbs for 12 months were collected. Demographic and monthly clinical variables were collected, including monthly headache days (MHDs), days with acute medication use, number of analgesics and Headache Impact Test-6. Response rates were categorized as <25%, 26-50%, 51-75% and >75% reduction in MHDs. ML models were trained using random forest algorithm and optimized to maximize the F1 score. ML model performance was also evaluated using standard evaluation metrics, including accuracy, precision and area under the receiver operating characteristic curve (AUC-ROC). Sequential backward feature selection was employed to identify the most relevant predictors for each model. Each model was given 11 baseline data inputs and month-based predictors for months 1, 3 and 6. Each model was then validated against an external test cohort of patients who had received anti-CGRP mAbs for 12 months. Three hundred thirty-six patients treated with anti-CGRP mAbs were included. The external cohort included 93 patients treated with anti-CGRP mAbs. We developed six models to predict 3- 6- and 12-month responses using early predictors. ML-based models yielded predictions with an accuracy score in the range 0.40-0.73 and an AUC-ROC score in the range 0.56-0.76 during internal testing and yielding predictions with an accuracy in the range 0.39-0.64 and an AUC-ROC score in the range 0.52-0.78 when tested against an external test cohort. Shapley Additive explanations summary plots were generated to interpret the contribution of each feature for each model. Based on these findings, a response prediction tool was developed. Each model was run through a backward feature selection to find the most relevant features for the models. The MHDs reduction of the previous data point tends to be the most relevant, while the migraine with aura indicator tends to be the least effective predictor. The response prediction tool utilizing evolving ML-based models holds promise in the early prediction of treatment outcomes for patients with migraine undergoing anti-CGRP mAbs treatment.

Systematic review of modelling techniques in carbon trading research in construction

Purpose Carbon emissions trading is an effective instrument in reducing greenhouse gas emissions. There is a notable scarcity of comprehensive reviews on the modelling techniques within carbon trading research in construction. Design/methodology/approach This paper reviews 68 relevant articles published in 19 peer-reviewed journals using systematic search. Scientometric analysis and content analysis are undertaken. Findings Generally, China was the largest contributor to carbon trading research using quantitative models (representing 36% of the total articles). From the results, the modelling techniques identified were multi-objective grasshopper optimisation algorithm; system dynamics; interpretive structural modelling; multi-agent-based model; decision-support model; multi-objective chaotic sine cosine algorithm; optimised backpropagation neural network; sequential panel selection method; Granger causality test; and impulse response analysis. Moreover, the advantages and disadvantages of these techniques were identified. System dynamics was recommended as the most suitable modelling technique for carbon trading in construction. Originality/value This study is significant, and through this review paper, practitioners can easily be more familiar with the significant modelling techniques, and this will motivate them to better understand their uses.

Blending Ensemble Learning Model for 12-Lead Electrocardiogram-Based Arrhythmia Classification

The increasing prevalence of heart diseases has driven the development of automated arrhythmia classification systems using machine learning and electrocardiograms (ECGs). This paper presents a novel ensemble learning method for classifying multiple arrhythmia types using 12-lead ECG signals through a blending technique. The framework employs a predetermined meta-model from foundation models, while the remaining models serve as potential base estimators, ranked by accuracy. Using sequential forward selection and meta-feature augmentation, the system determines an optimal base estimator set and creates a meta-dataset for the meta-model, which is optimized through grid search with k-fold cross-validation. Experiments conducted with seven diverse machine learning algorithms (Adaptive Boosting, Extreme Gradient Boosting, Decision Trees, k-Nearest Neighbors, Logistic Regression, Random Forest, and Support Vector Machine) demonstrate that the proposed blending solution, utilizing an LR meta-model with three optimal base models, achieves a superior classification accuracy of 96.48%, offering an effective tool for clinical decision support.

Exploring Early Complications in Paraumbilical Hernia Mesh Repair: A Rigorous Six-Month Prospective Study and In-Depth Analysis.

Introduction When an organ, such as the colon, pushes through the wall of the abdominal cavity, a hernia results. After femoral and inguinal hernias, umbilical hernias account for the third most common kind of abdominal hernia in adults precipitated by conditions such as obesity, ascites, and repeated pregnancies. A subtype of umbilical hernias called paraumbilical hernias is more likely to cause problems such as rupture, skin ulceration, and obstruction. Seroma, hematoma, and infection are the reported post-repair consequences but data regarding early complications is limited. High-quality data assessing early complications is necessary to improve mesh repair outcomes. Materials and methods This cross-sectional study was carried out in the Department of General Surgery at Medical Teaching Institute (MTI) Lady Reading Hospital, Peshawar over one year, from January to December 2022. A total of 167 patients were selected using simple random sequential selection. Patients aged 20-60 years of both genders who were diagnosed with paraumbilical hernia in the emergency department were included. To prevent bias, those with uncontrolled diabetes or existing complications from hernia were excluded. Following informed consent, data were gathered using pre-designed proformas. Patients underwent open mesh repair during each surgery, and they were monitored at one and three months following the procedure. Complications such as seroma, hematoma, and wound infection were documented. Data were analyzed using SPSS version 20 (IBM Corp., Armonk, NY) with chi-square tests for categorical variables and a significance level of p < 0.05. Results The study included a total of 167 patients, with a mean age of 42 years (SD ±8.77). The majority of patients (40%) ranged in age from 41 to 50 years old, with 33% aged 31 to 40. Gender distribution revealed that 63 (38%) of the patients were male and 104 (62%) were female. Early complications included 25 (15%) wound infections, 32 (19%) seromas, and 63 (38%) hematomas. The occurrence of wound infections, seromas, and hematomas did not differ significantly by age or gender (p > 0.05). Conclusion Early complications from paraumbilical hernia mesh repair include wound infections (15%), seromas (19%), and hematomas (38%). Postoperative monitoring is critical to reducing these complications.

Estimation of Malondialdehyde Content in Medicago truncatula under Salt Stress Based on Multi-Order Spectral Transformation Characteristics

Salt stress is a significant abiotic factor affecting the growth and development of alfalfa. Malondialdehyde (MDA) serves as a critical biomarker for assessing alfalfa’s salt tolerance. Traditional methods for measuring MDA are often time-consuming and labor-intensive. Recent advances in remote sensing technology have made non-destructive estimation of metabolites feasible, positioning the accurate estimation of MDA content in alfalfa as a key focus in intelligent breeding. To address the challenge of detecting subtle changes in MDA content, this study developed a partial least squares regression (PLSR) model specifically for Medicago truncatula. This study utilized leaf reflectance hyperspectral data across the visible near-infrared–shortwave infrared (VIR-NIR-SWIR) spectrum, applying multi-order spectral transformation methods, including continuous wavelet transform (CWT), fractional differential (FD), and multi-granularity spectral segmentation (MGSS). Feature selection techniques, such as sequential forward selection (SFS), Least-Squares Boosting (LSBoost), and feature selection using neighborhood component analysis for regression (FSRNCA), were employed to enhance the efficiency of the MDA estimation. The findings revealed that the optimal PLSR model for MDA estimation was achieved by integrating CWT features across orders 1–30 with the SFS method. This model demonstrated robust estimation capabilities under varying salt stress conditions, significantly outperforming the original spectral data (R2 = 0.654, RMSE = 22.567 vs. R2 = 0.242, RMSE = 33.411). A comparative analysis of feature selection methods confirmed that SFS was the most effective for estimating MDA content in alfalfa. These results provide valuable insights and methodologies for MDA estimation and evaluating salt tolerance in alfalfa.

Framework for Data‒Driven Fault Diagnosis of Numerical Spacecraft Propulsion Systems

The increasing complexity of deep space missions introduces significant challenges in maintaining spacecraft health, particularly in the propulsion systems, due to the inherent communication delays with Earth. This research proposes a novel framework for the autonomous, data-driven fault diagnosis of spacecraft propulsion systems. Leveraging data generated from a spacecraft propulsion system simulation model. The study addresses the limitations imposed by computational resources and sensor installation constraints through Sequential Forward Selection (SFS) for optimized sensor placement and feature selection. The framework's effectiveness is demonstrated through implementation on a microcomputer, showing promising results in terms of diagnostic accuracy and processing speed, thus highlighting its potential for onboard spacecraft application. This study not only advances the autonomous capabilities of spacecraft in deep space but also contributes to the broader field of Prognostics and Health Management (PHM) by providing a scalable, efficient approach to fault diagnosis in critical spacecraft systems. The proposed framework demonstrates a promising approach to optimizing diagnostic tasks for spacecraft systems. However, the trade-offs observed necessitate a careful consideration of task-specific requirements and the potential need for adjustments to maintain a high level of accuracy alongside computational efficiency.

Deep Learning-Enabled Dynamic Model for Nutrient Status Detection of Aquaponically Grown Plants

Developing models to assess the nutrient status of plants at various growth stages is challenging due to the dynamic nature of plant development. Hence, this study encoded spatiotemporal information of plants within a single time-series model to precisely assess the nutrient status of aquaponically cultivated lettuce. In particular, the long short-term memory (LSTM) and deep autoencoder (DAE) approaches were combined to classify aquaponically grown lettuce plants according to their nutrient status. The proposed approach was validated using extensive sequential hyperspectral reflectance measurements acquired from lettuce leaves at different growth stages across the growing season. A DAE was used to extract distinct features from each sequential spectral dataset time step. These features were used as input to an LSTM model to classify lettuce grown across a gradient of nutrient levels. The results demonstrated that the LSTM outperformed the convolutional neural network (CNN) and multi-class support vector machine (MCSVM) approaches. Also, features selected by the DAE showed better performance compared to features extracted using both genetic algorithms (GAs) and sequential forward selection (SFS). The hybridization of deep autoencoder and long short-term memory (DAE-LSTM) obtained the highest overall classification accuracy of 94%. The suggested methodology presents a pathway to automating the process of nutrient status diagnosis throughout the entire plant life cycle, with the LSTM technique poised to assume a pivotal role in forthcoming time-series analyses for precision agriculture.

Improving Clinical Decisions in IR: Interpretable Machine Learning Models for Predicting Ascites Improvement after Transjugular Intrahepatic Portosystemic Shunt Procedures

PurposeTo evaluate the potential of interpretable machine learning (ML) models to predict ascites improvement in patients undergoing transjugular intrahepatic portosystemic shunt (TIPS) placement for refractory ascites. Materials and MethodsIn this retrospective study, 218 patients with refractory ascites who underwent TIPS placement were analyzed. Data on 29 demographic, clinical, and procedural features were collected. Ascites improvement was defined as reduction in the need of paracentesis by 50% or more at the 1-month follow-up. Univariate statistical analysis was performed. Data were split into train and test sets. Feature selection was performed using a wrapper-based sequential feature selection algorithm. Two ML models were built using support vector machine (SVM) and CatBoost algorithms. Shapley additive explanations values were calculated to assess interpretability of ML models. Performance metrics were calculated using the test set. ResultsRefractory ascites improved in 168 (77%) patients. Higher sodium (Na; 136 mEq/L vs 134 mEq/L; P = .001) and albumin (2.91 g/dL vs 2.68 g/dL; P = .03) levels, lower creatinine levels (1.01 mg/dL vs 1.17 mg/dL; P = .04), and lower Model for End-stage Liver Disease (MELD) (13 vs 15; P = .01) and MELD-Na (15 vs 17.5, P = .002) scores were associated with significant improvement, whereas main portal vein puncture was associated with a lower improvement rate (P = .02). SVM and CatBoost models had accuracy ratios of 83% and 87%, with area under the curve values of 0.83 and 0.87, respectively. No statistically significant difference was found between performances of the models in DeLong test (P = .3). ConclusionsAccording to this study, ML models may have potential in patient selection for TIPS placement by predicting the improvement in refractory ascites.

Sequential Decision Making in Beach Volleyball-A Mixed-Method Approach.

Which opponent player to sequentially serve to in beach volleyball is crucial given the advantage of the attacking team. The sequential choice theory was tested in three studies by analyzing allocation strategies based on the hot hand belief. Study 1 showed strong belief in the hot hand of national coaches. In Study 2, we analyzed Tokyo Olympics data to explore how base rates and sequential selection rates varied in an elite sample. When base rates of players differed by 0.25, low-performing players were frequently selected. In an experiment with elite athletes, Study 3A demonstrated accurate base-rate-difference recognition but low base-rate-change recognition. Study 3B found that the hot hand is believed to be important but is not often detected. We conclude that players and coaches follow predictions of the sequential choice theory and believe in the hot hand, but do not have a shared understanding of how to use it.

Personalized prediction of immunotherapy response in lung cancer patients using advanced radiomics and deep learning

BackgroundLung cancer (LC) is a leading cause of cancer-related mortality, and immunotherapy (IO) has shown promise in treating advanced-stage LC. However, identifying patients likely to benefit from IO and monitoring treatment response remains challenging. This study aims to develop a predictive model for progression-free survival (PFS) in LC patients with IO based on clinical features and advanced imaging biomarkers.Materials and methodsA retrospective analysis was conducted on a cohort of 206 LC patients receiving IO treatment. Pre-treatment computed tomography images were used to extract advanced imaging biomarkers, including intratumoral and peritumoral-vasculature radiomics. Clinical features, including age, gene status, hematology, and staging, were also collected. Key radiomic and clinical features for predicting IO outcomes were identified using a two-step feature selection process, including univariate Cox regression and chi-squared test, followed by sequential forward selection. The DeepSurv model was constructed to predict PFS based on clinical and radiomic features. Model performance was evaluated using the area under the time-dependent receiver operating characteristic curve (AUC) and concordance index (C-index).ResultsCombining radiomics of intratumoral heterogeneity and peritumoral-vasculature with clinical features demonstrated a significant enhancement (p < 0.001) in predicting IO response. The proposed DeepSurv model exhibited a prediction performance with AUCs ranging from 0.76 to 0.80 and a C-index of 0.83. Furthermore, the predicted personalized PFS curves revealed a significant difference (p < 0.05) between patients with favorable and unfavorable prognoses.ConclusionsIntegrating intratumoral and peritumoral-vasculature radiomics with clinical features enabled the development of a predictive model for PFS in LC patients with IO. The proposed model’s capability to estimate individualized PFS probability and differentiate the prognosis status held promise to facilitate personalized medicine and improve patient outcomes in LC.

Information FOMO: The Unhealthy Fear of Missing Out on Information-A Method for Removing Misleading Data for Healthier Models.

Misleading or unnecessary data can have out-sized impacts on the health or accuracy of Machine Learning (ML) models. We present a Bayesian sequential selection method, akin to Bayesian experimental design, that identifies critically important information within a dataset while ignoring data that are either misleading or bring unnecessary complexity to the surrogate model of choice. Our method improves sample-wise error convergence and eliminates instances where more data lead to worse performance and instabilities of the surrogate model, often termed sample-wise "double descent". We find these instabilities are a result of the complexity of the underlying map and are linked to extreme events and heavy tails. Our approach has two key features. First, the selection algorithm dynamically couples the chosen model and data. Data is chosen based on its merits towards improving the selected model, rather than being compared strictly against other data. Second, a natural convergence of the method removes the need for dividing the data into training, testing, and validation sets. Instead, the selection metric inherently assesses testing and validation error through global statistics of the model. This ensures that key information is never wasted in testing or validation. The method is applied using both Gaussian process regression and deep neural network surrogate models.

Determinants of paratransit feeder service provision using AI-synthesized revealed preference data: a paratransit drivers’ perspective on PT reform using machine learning

ABSTRACT Although there is a wealth of research on passengers’ perception of public transport services and their willingness to use them, only a few have examined paratransit drivers’ intention to provide service. In this study, we have proposed using combined forward sequential feature selection with random forest classifier (FSFS-RFC) and Artificial Neural Network (ANN) to investigate the factors influencing drivers’ intention to provide feeder services to a dedicated bus lane system in Freetown. Focus group discussion was held with heads of various public transport unions, and a questionnaire survey was administered to a sample of 1124 paratransit drivers. The proposed FSFS-RFC and ANN algorithms revealed consistent results with schemes for fleet renewal, provision of coordinated paratransit feeder terminals, guaranteed hours of bus operation and increase in daily profit as the most significant determinants. The results imply that the algorithms can learn from AI-synthesized data on paratransit drivers’ operations for efficient planning.

Accelerating large-scale DEA computation using sequential categorization and dynamic reference set selection

Data envelopment analysis (DEA) is a well-known data-enabled analytic tool for evaluating relative efficiency of units with multiple inputs and multiple outputs. The DEA computation increases substantially in the presence of large samples. In this study, we first recall two lemmas to distinguish efficient units using arithmetic operations without solving linear programming (LP). Using the used lemmas, the total sample of units is partitioned into several sequential blocks, where units in the preceding blocks are relatively efficient to those in the subsequent blocks. A novel reference set selection procedure is then formulated. We implement the proposed approach into one of the fastest existing methods and demonstrate a significant improvement in elapsed time. We conduct simulation experiments and illustrate the outcomes across varying dimensions, cardinality, and density.

A Machine Learning-Based Wrapper Method for Feature Selection

This paper presents a two-stage feature selection scheme using machine learning techniques. In the first stage a wrapper method is adopted to select various combinations of subsets of features from the original dataset. The performance of the model is evaluated by three classifiers: K-Nearest Neighbor (KNN), Support Vector Machines (SVM), and Random Forest (RF). In the second and final stage, a sequential backward feature selection Method is applied. The proposed method is demonstrated on eighteen datasets and the average classification accuracy of eighteen datasets achieved is 89.81%, 87.55%, and 89.82% using the KNN, SVM, and RF classifiers, respectively with a maximum reduced size of the subset being ten only. Comparing the proposed method to eight other feature selection methods, the former achieves better classification accuracy in terms of selecting the most useful but a smaller number of features.

Enhancement of tool life using magneto-rheological fluid damping and tool wear prediction through deep learning model in milling

Undesirable vibrations generated during milling significantly intensify milling tool wear and reduces tool life. Hence it is imperative to employ the effective vibration control strategy during milling to optimize the overall effectiveness of the process. Thus, the present study incorporates the magneto-rheological fluid damping for vibration mitigation during the milling to enhance the life of a cutting tool under different operating conditions. Simultaneously, the data-driven modelling are employed to predict the tool wear using real-time multi-sensor machining data under different operating conditions. Accordingly, the real-time multi-sensor data was acquired at different operating conditions during normal and vibration-damped milling. Later, the extracted tine-domain features were selected using the sequential feature selection with Random Forest Regressor to obtain the most relevant time-domain features from multi-sensor data for improving the model performance. These selected features are then fed to the different deep-learning algorithms for tool wear prediction. Thus, Magneto-rheological fluid damping significantly reduces the vibrations and cutting forces in vibration-damped milling between 65 and 80% and improves the tool life by 18–21 % compared to normal milling under different operating conditions. Moreover, among the different deep learning algorithms, hybrid Encoder-Decoder Long short-term Memory is considered the optimal choice for tool wear prediction due to highest accuracy with coefficient of determinations (R2) ranging from 0.980 to 0.995 with the lowest mean squared error between 22 and 50 μm under varying operating conditions during normal and vibration-damped milling. Thus, it facilitates the significant enhancement in the tool life under different operating conditions, and robust data-driven model for the effective implementation of predictive maintenance approach.

Image Processing and Support Vector Machine (SVM) for Classifying Environmental Stress Symptoms of Pepper Seedlings Grown in a Plant Factory

Environmental factors such as temperature, humidity, light, and CO2 influence plant growth, and unfavorable environmental conditions cause stress in plants, producing symptoms in their early growth stages. The increasing importance of optimizing crop management strategies has led to a rising demand for the precise evaluation of stress symptoms during early plant growth. Advanced technologies are transforming plant health monitoring through enabling image-based stress analysis. Machine learning (ML) models can effectively identify the important features and morphological changes connected with various stress conditions through the use of large datasets acquired from high-resolution plant images. Therefore, the objective of this study was to develop a method for classifying the early-stage stress symptoms of pepper seedlings and enabling their identification and quantification using image processing and a support vector machine (SVM). Two-week-old pepper seedlings were grown under different temperatures (20, 25, and 30 °C), light intensity levels (50, 250, and 450 µmol m−2s−1), and day–night hours (8/16, 10/14, and 16/8) in five controlled plant growth chambers. Images of the seedling canopies were captured daily using a low-cost red, green, and blue (RGB) camera over a two-week period. Eighteen color features, nine texture features using the gray-level co-occurrence matrix (GLCM), and one morphological feature were extracted from each image. A two-way ANOVA and multiple mean comparison (Duncan) analysis were used to determine the statistical significance of the treatment effects. To reduce feature overlap, sequential feature selection (SFS) was applied, and a support vector machine (SVM) was used for stress classification. The SFS method was used to identify the optimal features for the classification model, leading to substantial increases in stress classification accuracy. The SVM model, using these selected features, achieved a classification accuracy of 82% without the SFS and 86% with the SFS. To address overfitting, 5- and 10-fold cross-validation were used, resulting in MAEs of 0.138 and 0.163 for the polynomial kernel, respectively. The SVM model, evaluated with the ROC curve and confusion matrix, achieved a classification accuracy of 85%. This classification approach enables real-time stress monitoring, allowing growers to optimize environmental conditions and enhance seedling growth. Future directions include integrating this system into automated cultivation environments to enable continuous, efficient stress monitoring and response, further improving crop management and productivity.

Emotion Recognition Through Analysis of Speech – A Review

The feature extraction is very important for emotion recognition through speech. There are several approaches when dealing with emotion recognition. In this paper, we present different feature extraction approaches as well as different models used to differentiate between a neutral speech versus an emotional speech sample. This research is instrumental for the digitization and preservation of cultural heritage, as it allows us to capture and analyze the emotional nuances in historical audio recordings, ensuring their accurate representation for future generations. We have selected two works consisting of a total of four different methods for emotion recognition. In the first paper by Jacob (2017), we look at Decision tree and Logistic Regression. Decision tree attains an 84.45% accuracy on the test class whereas logistic regression is able to achieve an accuracy of 66.85% after stepwise regression. These methods contribute to the digital archiving of cultural heritage by providing robust tools for analyzing and preserving the emotional content of spoken artifacts. In another paper by Bhatti et all. (2004), sequential forward selection (SFS) was used to create subsets from the given features and relevance of the subsets of features. General regression neural network was used to evaluate the accuracy which was found to be 80.69%. As a complementary purpose, modular neural network was performed with an accuracy of 83.31% with the same dataset. These techniques enhance our ability to maintain the integrity and emotional depth of cultural heritage recordings in digital archives.

Predictors of Medical and Dental Clinic Closure by Machine Learning Methods: Cross-Sectional Study Using Empirical Data.

Small clinics are important in providing health care in local communities. Accurately predicting their closure would help manage health care resource allocation. There have been few studies on the prediction of clinic closure using machine learning techniques. This study aims to test the feasibility of predicting the closure of medical and dental clinics (MCs and DCs, respectively) and investigate important factors associated with their closure using machine running techniques. The units of analysis were MCs and DCs. This study used health insurance administrative data. The participants of this study ran and closed clinics between January 1, 2020, and December 31, 2021. Using all closed clinics, closed and run clinics were selected at a ratio of 1:2 based on the locality of study participants using the propensity matching score of logistic regression. This study used 23 and 19 variables to predict the closure of MCs and DCs, respectively. Key variables were extracted using permutation importance and the sequential feature selection technique. Finally, this study used 5 and 6 variables of MCs and DCs, respectively, for model learning. Furthermore, four machine learning techniques were used: (1) logistic regression, (2) support vector machine, (3) random forest (RF), and (4) Extreme Gradient Boost. This study evaluated the modeling accuracy using the area under curve (AUC) method and presented important factors critically affecting closures. This study used SAS (version 9.4; SAS Institute Inc) and Python (version 3.7.9; Python Software Foundation). The best-fit model for the closure of MCs with cross-validation was the support vector machine (AUC 0.762, 95% CI 0.746-0.777; P<.001) followed by RF (AUC 0.736, 95% CI 0.720-0.752; P<.001). The best-fit model for DCs was Extreme Gradient Boost (AUC 0.700, 95% CI 0.675-0.725; P<.001) followed by RF (AUC 0.687, 95% CI 0.661-0.712; P<.001). The most significant factor associated with the closure of MCs was years of operation, followed by population growth, population, and percentage of medical specialties. In contrast, the main factor affecting the closure of DCs was the number of patients, followed by annual variation in the number of patients, year of operation, and percentage of dental specialists. This study showed that machine running methods are useful tools for predicting the closure of small medical facilities with a moderate level of accuracy. Essential factors affecting medical facility closure also differed between MCs and DCs. Developing good models would prevent unnecessary medical facility closures at the national level.