Machine Learning Approach Research Articles

Bacterial profile-based body fluid identification using a machine learning approach.

Identifying the origins of biological traces is critical for the reconstruction of crime scenes in forensic investigations. Traditional methods for body fluid identification rely on chemical, enzymatic, immunological, and spectroscopic techniques, which can be sample-consuming and depend on simple color-change reactions. However, these methods have limitations when residual samples are insufficient after DNA extraction. This study aimed to develop a method for body fluid identification by leveraging bacterial DNA profiling to overcome the limitations of the conventional approaches. Bacterial profiles were determined by sequencing the hypervariable region of the 16S rRNA gene,using DNA metabarcoding of evidence collected from criminal cases. Amplicon sequence variants (ASVs) were analyzed to identify significant microbial patterns in different body fluid samples. The bacterial profile-based method demonstrated high discriminatory power with a machine learning model trained using the naïve Bayes algorithm, achieving an accuracy of over 98% in classifying samples into one of four body fluid types: blood, saliva, vaginal secretion, and mixture traces of vaginal secretions and semen. Bacterial profiling enhances the accuracy and robustness of body fluid identification in forensic analysis, providing a valuable alternative to traditional methods by utilizing DNA and microbial community data despite the uncontrollable conditions. This approach offers significant improvements in the classification accuracy and practical applicability in forensic investigations.

Assessment of groundwater quality variation characteristics and influencing factors in an intensified agricultural area: An integrated hydrochemical and machine learning approach

The decline in groundwater quality in intensive agricultural areas in recent years, driven by environmental change and intensified human activity, poses a significant threat to agricultural production and public health, requiring attention and effective management. However, distinguishing the specific impacts of various factors on groundwater quality remains challenging, which hinders the effective management and prevention of groundwater pollution. This research integrates a hydrochemical analysis with the Entropy-weighted Water Quality Index, Self-Organizing Map (SOM) approach, and Boruta algorithm to investigate groundwater chemical variations and their influencing factors in the Sanjiang Plain, an important grain-producing region in China. The findings reveal that, compared to 2012, the deep groundwater quality has improved, while the shallow groundwater quality has markedly deteriorated. This decline in shallow groundwater quality is primarily attributable to human activities and is characterized by elevated levels of chloride, sulfate, and nitrate and a shift in the groundwater hydrochemical facies from an HCO3−Ca·Mg type to a mixed HCO3−Ca·Mg and SO4·Cl−Ca·Mg type. The SOM results suggested that land use type significantly affects shallow groundwater quality. Further analysis with the Boruta algorithm identified increased sewage and manure emissions from expanding livestock operations as well as enhanced pollutant leakage from the expansion of paddy fields as the primary contributors to the decline in shallow groundwater quality. These findings offer new insights into the mechanisms of groundwater quality changes in agriculturally intensive regions and provide a foundation for improved groundwater pollution management in the Sanjiang Plain and similar areas.

A Hybrid Quantum-Classical Model for Stock Price Prediction Using Quantum-Enhanced Long Short-Term Memory

The stock markets have become a popular topic within machine learning (ML) communities, with one particular application being stock price prediction. However, accurately predicting the stock market is a challenging task due to the various factors within financial markets. With the introduction of ML, prediction techniques have become more efficient but computationally demanding for classical computers. Given the rise of quantum computing (QC), which holds great promise for being exponentially faster than current classical computers, it is natural to explore ML within the QC domain. In this study, we leverage a hybrid quantum-classical ML approach to predict a company’s stock price. We integrate classical long short-term memory (LSTM) with QC, resulting in a new variant called QLSTM. We initially validate the proposed QLSTM model by leveraging an IBM quantum simulator running on a classical computer, after which we conduct predictions using an IBM real quantum computer. Thereafter, we evaluate the performance of our model using the root mean square error (RMSE) and prediction accuracy. Additionally, we perform a comparative analysis, evaluating the prediction performance of the QLSTM model against several other classical models. Further, we explore the impacts of hyperparameters on the QLSTM model to determine the best configuration. Our experimental results demonstrate that while the classical LSTM model achieved an RMSE of 0.0693 and a prediction accuracy of 0.8815, the QLSTM model exhibited superior performance, achieving values of 0.0602 and 0.9736, respectively. Furthermore, the QLSTM outperformed other classical models in both metrics.

Physics-Based Machine Learning Trains Hamiltonians and Decodes the Sequence-Conformation Relation in the Disordered Proteome.

Intrinsically disordered proteins and regions (IDPs) are involved in vital biological processes. To understand the IDP function, often controlled by conformation, we need to find the link between sequence and conformation. We decode this link by integrating theory, simulation, and machine learning (ML) where sequence-dependent electrostatics is modeled analytically while nonelectrostatic interaction is extracted from simulations for many sequences and subsequently trained using ML. The resulting Hamiltonian, combining physics-based electrostatics and machine-learned nonelectrostatics, accurately predicts sequence-specific global and local measures of conformations beyond the original observable used from the simulation. This is in contrast to traditional ML approaches that train and predict a specific observable, not a Hamiltonian. Our formalism reproduces experimental measurements, predicts multiple conformational features directly from sequence with high throughput that will give insights into IDP design and evolution, and illustrates the broad utility of using physics-based ML to train unknown parts of a Hamiltonian, rather than a specific observable, in combination with known physics.

Exploring the Impact of Artificial Intelligence on Healthcare Management: A Combined Systematic Review and Machine-Learning Approach

The integration of artificial intelligence (AI) in healthcare management marks a significant advance in technological innovation, promising transformative effects on healthcare processes, patient care, and the efficacy of emergency responses. The scientific novelty of the study lies in its integrated approach, combining systematic review and predictive algorithms to provide a comprehensive understanding of AI’s role in improving healthcare management across different contexts. Covering the period between 2019 and 2023, which includes the global challenges posed by the COVID-19 pandemic, this research investigates the operational, strategic, and emergency response implications of AI adoption in the healthcare sector. It further examines how the impact of AI varies across temporal and geographical contexts. The study addresses two main research objectives: to explore how AI influences healthcare management in operational, strategic, and emergency response domains, and to identify variations in the impact of AI on healthcare management based on temporal and geographical contexts. Utilizing an integrated approach, we compared various prediction algorithms, including logistic regression, and interpreted the results through SHAP (SHapley Additive exPlanations) analysis. The findings reveal five key thematic areas: AI’s role in enhancing quality assurance, resource management, technological innovation, security, and the healthcare response to the COVID-19 pandemic. The study highlights AI’s positive influence on operational efficiency and strategic decision making, while also identifying challenges related to data privacy, ethical considerations, and the need for ongoing technological integration. These insights provide opportunities for targeted interventions to optimize AI’s impact in current and future healthcare landscapes. In conclusion, this work contributes to a deeper understanding of the role of AI in healthcare management and provides insights for policymakers, healthcare professionals, and researchers, offering a roadmap for addressing both the opportunities and challenges posed by AI integration in the healthcare sector.

Prediction of holey graphyne-supported single atom catalyst for nitrogen reduction reaction by interpretable machine learning and first-principles calculations

The electrocatalytic nitrogen reduction reaction (NRR) with efficient and selective electrocatalysts has emerged as a promising alternative for sustainable ammonia synthesis. In this study, we designed a novel class of single-atom catalysts (SACs), denoted as TM@HGY, by embedding 3d, 4d, and 5d transition metals into synthesized holey graphyne (HGY), and investigated their potential for NRR using a combined approach of density functional theory (DFT) calculations and machine learning. Through stability assessments and a three-step screening strategy, Sc@HGY, V@HGY, and Mo@HGY were identified as promising NRR electrocatalysts. Notably, V@HGY exhibited an exceptionally low limiting potential of −0.16 V, which is superior to all the known NRR SACs supported by graphyne-family members. Machine learning (ML) analysis revealed that the Mendeleev number (Nm), group (G), and d-orbital radius (Rd) of the absorbed metal atom are the primary contributors to the structural stability and catalytic activity of these SACs, and clear strategies for optimizing catalyst design were further suggested based on their intrinsic relationships. This work reveals the significant potential of TM@HGY in NRR, providing powerful guidance for designing high-performance SACs in the field of sustainable ammonia synthesis.

Enhancing IoT Security in Vehicles: A Comprehensive Review of AI-Driven Solutions for Cyber-Threat Detection

Background: The Internet of Things (IoT) has improved many aspects that have impacted the industry and the people’s daily lives. To begin with, the IoT allows communication to be made across a wide range of devices, from household appliances to industrial machinery. This connectivity allows for a better integration of the pervasive computing, making devices “smart” and capable of interacting with each other and with the corresponding users in a sublime way. However, the widespread adoption of IoT devices has introduced some security challenges, because these devices usually run in environments that have limited resources. As IoT technology becomes more integrated into critical infrastructure and daily life, the need for stronger security measures will increase. These devices are exposed to a variety of cyber-attacks. This literature review synthesizes the current research of artificial intelligence (AI) technologies to improve IoT security. This review addresses key research questions, including: (1) What are the primary challenges and threats that IoT devices face?; (2) How can AI be used to improve IoT security?; (3) What AI techniques are currently being used for this purpose?; and (4) How does applying AI to IoT security differ from traditional methods? Methods: We included a total of 33 peer-reviewed studies published between 2020 and 2024, specifically in journal and conference papers written in English. Studies irrelevant to the use of AI for IoT security, duplicate studies, and articles without full-text access were excluded. The literature search was conducted using scientific databases, including MDPI, ScienceDirect, IEEE Xplore, and SpringerLink. Results were synthesized through a narrative synthesis approach, with the help of the Parsifal tool to organize and visualize key themes and trends. Results: We focus on the use of machine learning, deep learning, and federated learning, which are used for anomaly detection to identify and mitigate the security threats inherent to these devices. AI-driven technologies offer promising solutions for attack detection and predictive analysis, reducing the need for human intervention more significantly. This review acknowledges limitations such as the rapidly evolving nature of IoT technologies, the early-stage development or proprietary nature of many AI techniques, the variable performance of AI models in real-world applications, and potential biases in the search and selection of articles. The risk of bias in this systematic review is moderate. While the study selection and data collection processes are robust, the reliance on narrative synthesis and the limited exploration of potential biases in the selection process introduce some risk. Transparency in funding and conflict of interest reporting reduces bias in those areas. Discussion: The effectiveness of these AI-based approaches can vary depending on the performance of the model and the computational efficiency. In this article, we provide a comprehensive overview of existing AI models applied to IoT security, including machine learning (ML), deep learning (DL), and hybrid approaches. We also examine their role in enhancing the detection accuracy. Despite all the advances, challenges still remain in terms of data privacy and the scalability of AI solutions in IoT security. Conclusion: This review provides a comprehensive overview of ML applications to enhance IoT security. We also discuss and outline future directions, emphasizing the need for collaboration between interested parties and ongoing innovation to address the evolving threat landscape in IoT security.

Innovative machine learning for drilling fluid density prediction: a novel central force search-adaptive XGBoost in HPHT environments

Oil and gas industries are facing a special dilemma when it comes to high-pressure, high-temperature (HPHT) drilling as the accurate forecasting of the drilling fluid density (DFD) is a vital factor for safe and efficient operations. Complicated relationships and inconsistencies in HPHT situations are rarely mapped by current forecasting models, while their buggy performance and safety risks during drilling can be underestimated. In this research, we propose a novel machine learning (ML) approach to enhance the accuracy of DFD anticipation under HPHT conditions: central force search-adaptive extreme gradient boosting (CFS-XGB). This paper uses a dataset that has drilling variables together with the DFD for HPHT situations to examine the accuracy of the CFS-XGB model. Excluding the abnormalities of data or mistakes, the reliability of the original data is maintained by applying min–max normalization. After that, finding the important features with the help of the boosted principal component analysis (BPCA) approach to the normalized data will ensure a major improvement in the CFS-XGB methodology’s prediction efficacy. This research is experimented in the Python platform, and the performance of the proposed CFS-XGB method is analyzed in terms of MSE, R2, and AAPRE metrics. The suggested approach performs better than the current methods in forecasting the drilling fluid concentration in HPHT settings, according to the experimental data. This development in predictive modeling helps increase the productivity and safety of drilling operations, which will eventually help the oil and gas sector manage the challenges posed by HPHT drilling settings.

Biomechanical and machine learning approaches to automating the identification of musical styles and emotions through human motion analysis

This study explores the intricate relationship between biomechanical movements and musical expression, focusing on the identification of musical styles and emotions. Violin performance is characterized by complex interactions between physical actions—such as bowing techniques, finger placements, and posture—and the resulting acoustic output. Recent advances in motion capture technology and sound analysis have enabled a more objective examination of these processes. However, the current literature frequently addresses biomechanics and acoustic features in isolation, lacking an integrated understanding of how physical movements translate into specific musical expressions. Machine Learning (ML), particularly Long Short-Term Memory (LSTM) networks, provides a promising avenue for bridging this gap. LSTM models are adept at capturing temporal dependencies in sequential data, making them suitable for analyzing the dynamic nature of violin performance. In this work, they have proposed a comprehensive model that combines biomechanical analysis with Mel-spectrogram-based LSTM modeling to automate the identification of musical styles and emotions in violin performances. Using motion capture systems, Inertial Measurement Units (IMUs), and high-fidelity audio recordings, we collected synchronized biomechanical and acoustic data from violinists performing various musical excerpts. The LSTM model was trained on this dataset to learn the intricate connections between physical movements and the acoustic features of each performance. Key findings from the study demonstrate the effectiveness of this integrated approach. The LSTM model achieved a validation accuracy of 92.5% in classifying musical styles and emotions, with precision, recall, and F1-score reaching 94.3%, 92.6%, and 93.4%, respectively, by the 100th epoch. The analysis also revealed strong correlations between specific biomechanical parameters, such as shoulder joint angle and bowing velocity, and acoustic features, like sound intensity and vibrato amplitude.

How deep is your art: An experimental study on the limits of artistic understanding in a single-task, single-modality neural network.

Computational modeling of artwork meaning is complex and difficult. This is because art interpretation is multidimensional and highly subjective. This paper experimentally investigated the degree to which a state-of-the-art Deep Convolutional Neural Network (DCNN), a popular Machine Learning approach, can correctly distinguish modern conceptual art work into the galleries devised by art curators. Two hypotheses were proposed to state that the DCNN model uses Exhibited Properties for classification, like shape and color, but not Non-Exhibited Properties, such as historical context and artist intention. The two hypotheses were experimentally validated using a methodology designed for this purpose. VGG-11 DCNN pre-trained on ImageNet dataset and discriminatively fine-tuned was trained on handcrafted datasets designed from real-world conceptual photography galleries. Experimental results supported the two hypotheses showing that the DCNN model ignores Non-Exhibited Properties and uses only Exhibited Properties for artwork classification. This work points to current DCNN limitations, which should be addressed by future DNN models.

Classification of dynamical Lie algebras of 2-local spin systems on linear, circular and fully connected topologies

Much is understood about 1-dimensional spin chains in terms of entanglement properties, physical phases, and integrability. However, the Lie algebraic properties of the Hamiltonians describing these systems remain largely unexplored. In this work, we provide a classification of all Lie algebras generated by the terms of 2-local spin chain Hamiltonians, or so-called dynamical Lie algebras, on 1-dimensional linear and circular lattice structures. We find 17 unique dynamical Lie algebras. Our classification includes some well-known models such as the transverse-field Ising model and the Heisenberg chain, and we also find more exotic classes of Hamiltonians that appear new. In addition to the closed and open spin chains, we consider systems with a fully connected topology, which may be relevant for quantum machine learning approaches. We discuss the practical implications of our work in the context of variational quantum computing, quantum control and the spin chain literature.

Construction of a disease risk prediction model for postherpetic pruritus by machine learning

BackgroundPostherpetic itch (PHI) is an easily overlooked complication of herpes zoster that greatly affects patients' quality of life. Studies have shown that early intervention can reduce the occurrence of itch. The aim of this study was to develop and validate a predictive model through a machine learning approach to identify patients at risk of developing PHI among patients with herpes zoster, making PHI prevention a viable clinical option.MethodWe conducted a retrospective review of 488 hospitalized patients with herpes zoster at The First Affiliated Hospital of Zhejiang Chinese Medical University and classified according to whether they had PHI. Fifty indicators of these participants were collected as potential input features for the model. Features associated with PHI were identified for inclusion in the model using the least absolute shrinkage selection operator (LASSO). Divide all the data into five pieces, and then use each piece as a verification set and the others as a training set for training and verification, this process is repeated 100 times. Five models, logistic regression, random forest (RF), k-nearest neighbor, gradient boosting decision tree and neural network, were built in the training set using machine learning methods, and the performance of these models was evaluated in the test set.ResultsSeven non-zero characteristic variables from the Lasso regression results were selected for inclusion in the model, including age, moderate pain, time to recovery from rash, diabetes, severe pain, rash on the head and face, and basophil ratio. The RF model performs better than other models. On the test set, the AUC of the RF model is 0.84 [(95% confidence interval (CI): 0.80–0.88], an accuracy of 0.78 (95% CI: 0.69–0.86), a precision of 0.61 (95% CI: 0.45–0.77), a recall of 0.73 (95% CI: 0.58–0.89), and a specificity of 0.79 (95% CI: 0.70–0.89).ConclusionsIn this study, five machine learning methods were used to build postherpetic itch risk prediction models by analyzing historical case data, and the optimal model was selected through comparative analysis, with the random forest model being the top performing model.

Classification of EEG evoked in 2D and 3D virtual reality: traditional machine learning versus deep learning

Backgrounds. Virtual reality (VR) simulates real-life events and scenarios and is widely utilized in education, entertainment, and medicine. VR can be presented in two dimensions (2D) or three dimensions (3D), with 3D VR offering a more realistic and immersive experience. Previous research has shown that electroencephalogram (EEG) profiles induced by 3D VR differ from those of 2D VR in various aspects, including brain rhythm power, activation, and functional connectivity. However, studies focused on classifying EEG in 2D and 3D VR contexts remain limited.Methods. A 56-channel EEG was recorded while visual stimuli were presented in 2D and 3D VR. The recorded EEG signals were classified using two machine learning approaches: traditional machine learning and deep learning. In the traditional approach, features such as power spectral density (PSD) and common spatial patterns (CSP) were extracted, and three classifiers-support vector machines (SVM), K-nearest neighbors (KNN), and random forests (RF)-were used. For the deep learning approach, a specialized convolutional neural network, EEGNet, was employed. The classification performance of these methods was then compared.Results. In terms of accuracy, precision, recall, and F1-score, the deep learning method outperformed traditional machine learning approaches. Specifically, the classification accuracy using the EEGNet deep learning model reached up to 97.86%.Conclusions. EEGNet-based deep learning significantly outperforms conventional machine learning methods in classifying EEG signals induced by 2D and 3D VR. Given EEGNet's design for EEG-based brain-computer interfaces (BCI), this superior classification performance suggests that it can enhance the application of 3D VR in BCI systems.

Towards Achilles Tendon Injury Prevention in Athletes with Structural MRI Biomarkers: A Machine Learning Approach.

Recent advancements in artificial intelligence have proven their effectiveness in orthopaedic settings, especially in tasks like medical image analysis. This study compares human musculoskeletal radiologists to artificial intelligence in a novel, detailed, short, and cost-effective examination of Achilles tendon magnetic resonance images to uncover potential disparities in their reasoning approaches. Aiming to identify relationships between the structured assessment of the Achilles tendon and its function that could support injury prevention. We examined 72 athletes to investigate the link between Achilles tendon structure, as visualised in magnetic resonance images using a precise T2*-weighted gradient echo sequence with very short echo times, and its functional attributes. The acquired data were analysed using advanced artificial intelligence techniques and reviewed by radiologists. Additionally, we conducted statistical assessments to explore relationships with functional studies in four meaningful groups: dynamic strength, range of motion, muscle torque and stabilography. The results show notable linear or non-linear relationships between functional indicators and structural alterations (maximal obtained Spearman correlation coefficients ranged from 0.3 to 0.36 for radiological assessment and from 0.33 to 0.49 for artificial intelligence assessment, while maximal normalised mutual information ranged from 0.52 to 0.57 for radiological assessment and from 0.42 to 0.6 for artificial intelligence assessment). Moreover, when artificial intelligence-based magnetic resonance assessment was utilised as an input, the associations consistently proved more robust, or the count of significant relationships surpassed that derived from radiological assessment. Ultimately, utilising only structural parameters as inputs enabled us to explain up to 59% of the variance within specific functional groups. This analysis revealed that structural parameters influence four key functional aspects related to the Achilles tendon. Furthermore, we found that relying solely on subjective radiologist opinions limited our ability to reason effectively, in contrast to the structured artificial intelligence assessment. Cross-sectional studies.

A detailed analysis of game statistics of professional tennis players: An inferential and machine learning approach.

Tennis, a widely enjoyed sport, motivates athletes and coaches to optimize training for competitive success. This retrospective predictive study examines anthropometric features and statistics of 1990 tennis players in the 2022 season, using 20,040 data points retrospectively obtained from the ATP official source after the end of the season. These data were cross-verified with information from other sources before categorisation to address any discrepancies. Employing various analytical methods, the results emphasize the strategic importance of tournament participation and gameplay for financial gains and higher rankings. Prize money analysis reveals a significant disparity favoring top players. Multivariate Analysis of Variance highlights the need to consider multiple variables for understanding ATP rankings. Multinomial Logistic Regression identifies age, height, and specific service-related metrics as key determinants, with older and taller players more likely to secure top positions. Neural Network models exhibit potential in predicting ATP Rank outcomes, particularly for ATP Rank (500). Our results argue for the use of Artificial Intelligence (AI), specifically Neural Networks, in handling complex interactions and emphasize that AI is a supportive tool in decision-making, requiring careful consideration by experienced individuals. In summary, this study enhances our understanding of ATP ranking factors, providing actionable insights for coaches, players, and stakeholders in the tennis community.

Application of computational algorithms for single-cell RNA-seq and ATAC-seq in neurodegenerative diseases.

Recent advancements in single-cell technologies, including single-cell RNA sequencing (scRNA-seq) and Assay for Transposase-Accessible Chromatin using sequencing (scATAC-seq), have greatly improved our insight into the epigenomic landscapes across various biological contexts and diseases. This paper reviews key computational tools and machine learning approaches that integrate scRNA-seq and scATAC-seq data to facilitate the alignment of transcriptomic data with chromatin accessibility profiles. Applying these integrated single-cell technologies in neurodegenerative diseases, such as Alzheimer's disease and Parkinson's disease, reveals how changes in chromatin accessibility and gene expression can illuminate pathogenic mechanisms and identify potential therapeutic targets. Despite facing challenges like data sparsity and computational demands, ongoing enhancements in scATAC-seq and scRNA-seq technologies, along with better analytical methods, continue to expand their applications. These advancements promise to revolutionize our approach to medical research and clinical diagnostics, offering a comprehensive view of cellular function and disease pathology.

Examining wildfire dynamics using ECOSTRESS data with machine learning approaches: the case of South‐Eastern Australia's black summer

Wildfires are increasing in risk and prevalence. The most destructive wildfires in decades in Australia occurred in 2019–2020. However, there is still a challenge in developing effective models to understand the likelihood of wildfire spread (susceptibility) and pre‐fire vegetation conditions. The recent launch of NASA's ECOSTRESS presents an opportunity to monitor fire dynamics with a high resolution of 70 m by measuring ecosystem stress and drought conditions preceding wildfires. We incorporated ECOSTRESS data, vegetation indices, rainfall, and topographic data as independent variables and fire events as dependent variables into machine learning algorithms applied to the historic Australian wildfires of 2019–2020. With these data, we predicted over 90% of all wildfire occurrences 1 week ahead of these wildfire events. Our models identified vegetation conditions with a 3‐week time lag before wildfire events in the fourth week and predicted the probability of wildfire occurrences in the subsequent week (fifth week). ECOSTRESS water use efficiency (WUE) consistently emerged as the leading factor in all models predicting wildfires. Results suggest that the pre‐fire vegetation was affected by wildfires in areas with WUE above 2 g C kg−1 H₂O at 95% probability level. Additionally, the ECOSTRESS evaporative stress index and topographic slope were identified as significant contributors in predicting wildfire susceptibility. These results indicate a significant potential for ECOSTRESS data to predict and analyze wildfires and emphasize the crucial role of drought conditions in wildfire events, as evident from ECOSTRESS data. Our approaches developed in this study and outcome can help policymakers, fire managers, and city planners assess, manage, prepare, and mitigate wildfires in the future.

Optimized Machine Learning Algorithms for Predicting the Punching Shear Resistance of Flat Slabs with Transverse Reinforcement

In the calculation of reinforced concrete (RC) flat slabs with transverse reinforcement, punching shear resistance is one of the most critical factors. It is true that design provisions may be implemented, but they often result in significant biases and deviations from expectations. This study aims to present an optimized machine learning (ML) algorithm for estimating the punching shear resistance. Four machine learning (ML) algorithms (SVR, DT, RF, and XGBoost) with Bayesian optimization (BO) are presented in this paper to provide accurate predictions for flat slabs. The adoptability and optimization of the models are achieved through the analysis of a database of 337 test specimens with nine design parameters. Machine learning (ML) techniques are used to estimate punching shear resistance, which is compared with design provisions and equations relating to critical shear crack theory (CSCT). According to this study, Bayesian optimization is still capable of improving the performance of conventional machine learning algorithms, while the XGBoost-based model offers advanced capabilities. Predictions based on BO-XGBoost are in good agreement with actual values (MAE, RMSE, and R2 are 0.09 MN, 0.14 MN, and 0.92, respectively) in test set. Following a detailed explanation using Shapley additive explanation (SHAP), a high-performance ML approach is used to investigate the predictive results. With the proposed optimized algorithms, it is possible to determine the punching shear resistance of flat slabs with transverse reinforcement during the preliminary stages of the construction.

Predicting temporomandibular disorders in adults using interpretable machine learning methods: a model development and validation study

IntroductionTemporomandibular disorders (TMD) have a high prevalence and complex etiology. The purpose of this study was to apply a machine learning (ML) approach to identify risk factors for the occurrence of TMD in adults and to develop and validate an interpretable predictive model for the risk of TMD in adults.MethodsA total of 949 adults who underwent oral examinations were enrolled in our study. 5 different ML algorithms were used for model development and comparison, and feature selection was performed by feature importance ranking and feature decreasing methods. Several evaluation indexes, including the area under the receiver-operating-characteristic curve (AUC), were used to compare the predictive performance. The precision-recall curve (PR), calibration curve, and decision curve analysis (DCA) further assessed the accuracy and clinical utility of the model.ResultsThe performance of the random forest (RF) model was the best among the 5 ML models. An interpretable RF model was developed with 7 features (gender, malocclusion, unilateral chewing, chewing hard substances, grinding teeth, clenching teeth, and anxiety). The AUCs of the final model on the training set, internal validation set, and external test set were 0.892, 0.854, and 0.857, respectively. Calibration and DCA curves showed high accuracy and clinical applicability of the model.DiscussionAn efficient and interpretable TMD risk prediction model for adults was successfully developed using the ML method. The model not only has good predictive performance, but also enhances the clinical application value of the model through the SHAP method. This model can provide clinicians with a practical and efficient TMD risk assessment tool that can help them better predict and assess TMD risk in adults, supporting more efficient disease management and targeted medical interventions.

Water quality estimates using machine learning techniques in an experimental watershed

ABSTRACT Estimation of the water quality parameters is important to enhance time and cost-effectiveness to that of the conventional approach. This study is aimed to identify the best machine learning (ML) approach to predict concentrations of biochemical oxygen demand (BOD), nitrate, and phosphate. Four ML techniques including decision tree, random forest, gradient boosting, and XGBoost were compared to estimate the water quality parameters based on biophysical (i.e., population, basin area, river slope, water level, and stream flow) and physicochemical properties (i.e., conductivity, turbidity, pH, temperature, and dissolved oxygen) as input parameters. The data were split into training and test sets, and the model performances were evaluated using coefficient of determination (R2), Nash–Sutcliffe efficiency coefficient (NSE), and root mean squared error (RMSE). The mean squared error (MSE) was used as the optimization target. The robust fivefold cross-validation, along with hyperparameter tuning, achieved R2 values of 0.76, 0.67, and 0.71 for phosphate, nitrate, and BOD, and NSE values of 0.73, 0.67, and 0.66, respectively. XGBoost yielded the lowest RMSE across all parameters, showcasing superior performance when considering all metrics performed. In conclusion, ML techniques, particularly with a robust cross-validation technique and hyperparameter optimization, showed good results in water quality parameter prediction.