Physics-Informed Machine Learning for Lifetime Prediction of Multi-layer Ceramic Capacitors

Machine learning in predicting mechanical behavior of additively manufactured parts

Autism spectrum disorder (ASD) is a diverse neurodevelopmental condition with a significant genetic basis. Machine learning (ML) and deep learning (DL) models are emerging as powerful tools for identifying potential ASD risk genes and biomarkers to improve diagnostic accuracy. This narrative systematic review synthesizes evidence on the use of ML and DL models for ASD prediction and diagnosis, focusing on studies that utilized genetic variants and biomarkers. We conducted a systematic search across six databases [Web of Science, PubMed, Science Direct, Semantic Scholar, Institute of Electrical and Electronics Engineers (IEEE Xplore), and Association for Computing Machinery Digital Library (ACM-DL)] for articles published between 2009 and 2024, yielding 483 initial records. Multiple inclusion criteria were applied, and only peer-reviewed articles that used artificial intelligence, ML, or DL to predict ASD based on genetic biomarkers were included. After deduplication and applying inclusion and exclusion criteria, 14 studies were included in this review. These studies focused on genetic variants based on whole-genome sequencing, whole-exome sequencing, RNA sequencing, single-nucleus RNA sequencing, mRNA expression, long non-coding RNA, or single nucleotide polymorphism data. Our findings indicate that various ML models achieved robust performance, while DL architectures such as DeepASDPred outperformed ML models, with an accuracy of 93.8%. Most of the studies used datasets such as the Simons Foundation Autism Research Initiative (SFARI), the Simons Simplex Collection (SSC), the Autism Genetic Resource Exchange (AGRE), Atlas of the Developing Human Brain (BrainSpan), and the Simons Foundation Powering Autism Research for Knowledge (SPARK). The reviewed studies demonstrate that ML can help identify genetic risk factors and biomarkers that contribute to ASD. However, challenges remain, including data heterogeneity, small sample sizes, and the need for greater model interpretability. Addressing these challenges is crucial for translating ML models into clinically useful tools. In conclusion, DL substantially enhances ASD prediction, leveraging genetic data to identify novel candidate genes and support biological discovery of cell type-specific gene expression and roles of non-coding mutations in ASD.

Material innovation plays a very important role in technological progress and industrial development. Traditional experimental exploration and numerical simulation often require considerable time and resources. A new approach is urgently needed to accelerate the discovery and exploration of new materials. Machine learning can greatly reduce computational costs, shorten the development cycle, and improve computational accuracy. It has become one of the most promising research approaches in the process of novel material screening and material property prediction. In recent years, machine learning has been widely used in many fields of research, such as superconductivity, thermoelectrics, photovoltaics, catalysis, and high-entropy alloys. In this review, the basic principles of machine learning are briefly outlined. Several commonly used algorithms in machine learning models and their primary applications are then introduced. The research progress of machine learning in predicting material properties and guiding material synthesis is discussed. Finally, a future outlook on machine learning in the materials science field is presented.

IntroductionThe prediction of postherpetic neuralgia (PHN) is of great clinical significance. PHN prediction based on machine learning have received extensive attention in recent years. This study aims to conduct a comprehensive evaluation of machine learning in PHN prediction and provide guidance for the future models.MethodThe system retrieved the relevant literatures published in the PubMed, Web of Science, Embase and Cochrane Library databases from the establishment of the database to May 2025. Literature screening and data extraction were conducted in accordance with the PRISMA guidelines. According to the heterogeneity, the fixed-effect or the random-effect model was selected for data synthesis. The potential sources of heterogeneity were further explored through subgroup analysis, sensitivity tests and meta-regression. Funnel plots and Deeks’ tests were used to evaluate the possible publication biases.ResultThe main meta-analysis included 41 models from 14 studies. The results showed that machine learning demonstrated excellent performance in predicting PHN (sensitivity: 0.81, 95% confidence interval (CI): 0.74–0.86; specificity: 0.84, 95% CI: 0.79–0.88; area under the curve: 0.90, 95% CI: 0.87–0.92). Meta-regression analysis indicates that the source of the data set, model selection, and the choice of predictors are the main reasons leading to heterogeneity. Subgroup analysis showed that the training set model outperformed the validation set model. Logistic regression and other machine learning had varying strengths and weaknesses. Serum data or omics analysis did not significantly enhance model performance.ConclusionMachine learning represents a promising approach for the prediction of PHN. However, most of the existing models face issues like lack of external validation, overfitting, and insufficient reporting standardization. This has raised doubts about whether the current PHN prediction models can still maintain a high prediction accuracy when extended to external data. To improve future models, we recommend conducting strict external validation, clearly reporting cutoff values (balanced, positive, and negative), and adhering to international predictive model reporting standards. When applicable, ensemble learning and pain trajectory analyses should also be considered.Systematic review registrationThis study was registered in the Prospective Register of Systematic Reviews (PROSPERO; CRD420251054364).

Accurate crop yield prediction is paramount in agriculture to improve decision-making and resource allocation. It is a key part of precision agriculture, a sustainable farming approach that uses data and technology to improve crop yields while reducing environmental impact. Machine learning techniques have been extensively researched to enhance the accuracy of yield prediction. Athorough comprehension of the available literature on this topic is imperative. This study aims to categorize research, map relevant literature, and evaluate the progress made in yield prediction with machine learning over the last 13 years using bibliometric techniques. It analyzed the Scopus database for articles using search keywords "Yield Prediction," "Yield Estimation," and "Yield Forecasting" with "Machine Learning." It located 1177 pertinent articles, confirming the significance of machine learning in yield prediction. The Biblioshiny package analyzes the aggregated Scopus database, identifying current trends, challenges, and future research directions. The insights gained from this study can advance agricultural practices and contribute to sustainability efforts. Outcome: The study highlights the crucial role of machine learning in predicting crop yield accurately by using the Scopus database for finding articles, and the biblioshiny package of R is used to identify the current trends, challenges, and future research directions, which has the potential to transform precision agriculture by increasing crop yield and minimizing environmental impact.

A common problem in the world is crime, and predicting crime rates is an important element in providing and predicting crime rates is an important effective crime prevention and resource management. This paper examines the use of machine learning in prediction of crime rates in order to prevent crime and allocate resources more efficiently. This study uses dataset of crime statistics and demographic information for specific regions and applies various machine learning algorithms such as K-Nearest Neighbor, Support Vector Machine and Decision tree to classify given region as high, medium, and low crime rate region. Each algorithm is evaluated based on metrics such as accuracy, precision and recall. This study provides insight of machine learning potential in predicting crime and suggests future research options in this field. Ultimately, these findings could have important implications for crime prevention and resource allocation. Therefore, helping policy makers and law enforcement to accurately, efficiently forecast and reduce crime rate. Crime rates can change over time due to changes in social, economic, or political factors, and machine learning algorithms can adapt to these changes and make more accurate predictions. However, there are also potential ethical issues associated with using machine learning to predict crime rates. In addition, privacy and traceability issues may arise when models use sensitive data such as personal information or criminal records. This is a risk of bias or discrimination if the data used to train the model is not representative of the general population. The research emphasizes the value of interdisciplinary cooperation between data scientists and law enforcement agencies and shows the potential of machine learning in crime prediction.

Purpose: Within the current literature, the writer’s objective in this literature review is to examine the integration of the analysis of sentiment with the measurement of Emotional Intelligence (EI) utilizing explainable machine learning in predicting the development of children. The current research on the measurement of EI, sentiment analysis, and the utilization of machine learning in child development prediction is focused on in this research study. Methodology: The reviewed studies were released between 1990 and 2021 and focused on the intersection of EI assessment, sentiment analysis, and explainable AI in child development research. Relevant peer-reviewed articles were systematically gathered from databases such as IEEE, Wiley, ScienceDirect, MDPI, and others to identify relevant and credible literature. Various machine learning and deep learning methods were predominantly used in the studies to analyze emotional and cognitive growth in children based on sentiment and behavioral data. Findings/Result: Recent advancements in sentiment analysis and machine learning have significantly contributed to understanding children's developmental potential. However, existing studies reveal research gaps in integrating EI assessment with sentiment analysis through explainable AI models. In any current approaches, although lack transparency, interpretability, and flexibility, both of which are essential for accurately predicting developmental outcomes. Additionally, although deep learning models improve prediction accuracy, they frequently have interpretability issues, which makes it difficult to use them practically in developmental psychology. Originality: In order to develop a systematic framework for further research, this review synthesizes findings from a variety of studies that are accessible through internet sources It highlights the potential of integrating EI assessment with sentiment analysis and explainable machine learning, aiming to bridge existing research gaps and provide a foundation for further exploration. Paper Type: Literature Review.

This paper explores the applications of machine learning in the prediction of anemia, highlighting its potential to revolutionize clinical diagnosis and management. Anemia, a prevalent condition affecting millions globally, is often underdiagnosed due to traditional diagnostic methods that rely on clinical judgment and standard laboratory tests. Machine learning techniques provide innovative solutions by analyzing complex datasets that incorporate questionnaire, clinical features, demographic information, and laboratory results, thereby enhancing the accuracy of anemia predictions. This paper examines decision trees, random forests, support x'ector machines, and neural networks. emphasizing their efficacy in identifying patterns and risk factors associated with anemia. Obstacles such as data quality, feature selection, and model interpretability continue to hinder clinical adoption. The review identifies future research directions aimed at improving model generalizability and interpretability, ensuring that these technologies can be effectively integrated into healthcare practice. This paper advocates for the systematic adoption of machine learning methodologies in anemia management, positing that such innovations are crucial for advancing public health and optimizing resource allocation in clinical settings.

Comparison of machine learning and human prediction to identify trauma patients in need of hemorrhage control resuscitation (ShockMatrix study): a prospective observational study

Accurate PM2.5 and visibility predictions are essential for effective air quality management in central and eastern China. This study seeks to enhance the regional air quality numerical prediction system (RMAPS‐Chem) by integrating machine learning techniques and a dynamic ensemble algorithm to improve the accuracy of hourly PM2.5 and visibility forecasts across 309 cities in mainland China. Results demonstrate that machine learning methods significantly improve the accuracy of PM2.5 and visibility forecasts. For a 24‐hr lead time, the root mean square error (RMSE) is reduced by an average of 19% for PM2.5 and 30.2% for visibility, while the temporal correlation coefficient (TCC) increases by an average of 4.2% and 22.1%, respectively. Furthermore, we introduce a new ensemble forecasting algorithm, RCHEM‐AI, which capitalizes on dynamic RMSE and TCC weights based on machine learning predictions. RCHEM‐AI outperforms both RMAPS‐Chem and all individual machine learning members, reducing the average RMSE of PM2.5 (visibility) by 33.3% (39.3%) and increasing the average TCC by 16.4% (39.6%). Although the performance of machine learning and ensemble predictions declines with longer forecast time, the improvement in forecast accuracy remains substantial throughout the 1–10 days forecast period. By integrating RMAPS‐Chem, machine learning, and ensemble algorithms, this research provides a powerful tool for earlier and more accurate haze pollution predictions, thereby supporting more effective air pollution control and informed scientific decision‐making.

A prediction of the number of patients with conjunctivitis plays an important role in providing adequate treatment at the hospital, but such accurate predictive model currently does not exist. The current study sought to use machine learning (ML) prediction based on past patient for conjunctivitis and several air pollutants. The optimal machine learning prediction model was selected to predict conjunctivitis-related number patients. The average daily air pollutants concentrations (CO, O3, NO2, SO2, PM10, PM2.5) and weather data (highest and lowest temperature) were collected. Data were randomly divided into training dataset and test dataset, and normalized mean square error (NMSE) was calculated by 10 fold cross validation, comparing between the ability of seven ML methods to predict the number of patients due to conjunctivitis (Lasso penalized linear model, Decision tree, Boosting regression, Bagging regression, Random forest, Support vector, and Neural network). According to the accuracy of impact prediction, the important air and weather factors that affect conjunctivitis were identified. A total of 84,977 cases to treat conjunctivitis were obtained from the ophthalmology center of the Affiliated Hospital of Hangzhou Normal University. For all patients together, the NMSE of the different methods were as follows: Lasso penalized linear regression: 0.755, Decision tree: 0.710, Boosting regression: 0.616, Bagging regression: 0.615, Random forest: 0.392, Support vectors: 0.688, and Neural network: 0.476. Further analyses, stratified by gender and age at diagnosis, supported Random forest as being superior to others ML methods. The main factors affecting conjunctivitis were: O3, NO2, SO2 and air temperature. Machine learning algorithm can predict the number of patients due to conjunctivitis, among which, the Random forest algorithm had the highest accuracy. Machine learning algorithm could provide accurate information for hospitals dealing with conjunctivitis caused by air factors.

with the intensification of market competition and the complexity of consumer behavior, enterprises are faced with the challenge of how to accurately identify potential customers and improve user conversion rate. This paper aims to study the application of machine learning in consumer behavior prediction and precision marketing. Four models, namely support vector machine (SVM), extreme gradient boosting (XGBoost), categorical boosting (CatBoost), and backpropagation artificial neural network (BPANN), are mainly used to predict consumers' purchase intention, and the performance of these models in different scenarios is verified through experiments. The results show that CatBoost and XGBoost have the best prediction results when dealing with complex features and large-scale data, F1 scores are 0.93 and 0.92 respectively, and CatBoost's ROC AUC reaches the highest value of 0.985. while SVM has an advantage in accuracy rate, but slightly underperformance when dealing with large-scale data. Through feature importance analysis, we identify the significant impact of page views, residence time and other features on purchasing behavior. Based on the model prediction results, this paper proposes the specific application of optimization marketing strategies such as recommendation system, dynamic pricing and personalized advertising. Future research could improve the predictive power of the model by introducing more kinds of unstructured data, such as consumer reviews, images, videos, and social media data. In addition, the use of deep learning models, such as Transformers or Self-Attention Mechanisms, can better capture complex patterns in long time series data.

There is growing interest in canine behavioral research specifically for working dogs. Here we take advantage of a dataset of a Transportation Safety Administration olfactory detection cohort of 628 Labrador Retrievers to perform Machine Learning (ML) prediction and classification studies of behavioral traits and environmental effects. Data were available for four time points over a 12 month foster period after which dogs were accepted into a training program or eliminated. Three supervised ML algorithms had robust performance in correctly predicting which dogs would be accepted into the training program, but poor performance in distinguishing those that were eliminated (~ 25% of the cohort). The 12 month testing time point yielded the best ability to distinguish accepted and eliminated dogs (AUC = 0.68). Classification studies using Principal Components Analysis and Recursive Feature Elimination using Cross-Validation revealed the importance of olfaction and possession-related traits for an airport terminal search and retrieve test, and possession, confidence, and initiative traits for an environmental test. Our findings suggest which tests, environments, behavioral traits, and time course are most important for olfactory detection dog selection. We discuss how this approach can guide further research that encompasses cognitive and emotional, and social and environmental effects.

The applications of nanomaterials in various fields have led to an urgent need for rapid assessment of the biosafety of nanomaterials. The time-consuming, laborious, and expensive biological experiments are difficult to meet the needs of rapid and comprehensive evaluation of nanotoxicity. Based on a large number of existing toxicity data of nanomaterials, machine learning has played an import role in predicting nanotoxicity. This chapter briefly describes the nanotoxicology and the application of machine learning in predicting the toxicity of nanomaterials such as carbon nanomaterials, metal and metal oxide nanomaterials, and some emerging nanomaterials. We also propose prospects for future development of machine learning in prediction of nanotoxicology.

Abnormal pressure and wellbore instability are the main challenges during drilling in shale gas reservoirs. Traditionally, the pre-drill predictions of pore pressure and wellbore stability are executed manually by geomechanics engineers. The procedures are usually complicated and take time, the results also highly depend on the executor's expertise. All these make pore pressure and wellbore stability prediction far from ideal and automatic. In this study, we utilized machine learning methods to perform prediction in a simpler manner. The digital models were trained with existing well data, geology data and drilling data, and were correlated with spacing coordinates, that contains geological structure information. The models on formation materials properties are trained and learnt with patterns recognition; the pore pressure, earth stresses and wellbore stability are trained with physics-based hybrid algorithm. The trained models are then used to predict pore pressure and mud weight window at any point in subsurface or along any planned well trajectory, to identify drilling risks and recommend solutions. This approach was applied and validated in a deep shale gas field in Sichuan basin, China. In this field, the main shale gas reservoirs are overpressured and severe drilling complexities were encountered in drilling. Horizonal development wells are planned to drill to enhance production. This requires pre-drill pore pressure and wellbore stability prediction. Due to multiple abnormal pressure mechanisms and subsurface complexity, manual methodology is usually time-consuming, and the results are not consistent with different executors. With the developed new machine learning method, the digital models were trained with eleven geology surfaces and well data from eight existing wells. The trained model was used to predict pore pressure and mud weight window, including formation collapse pressure, mud loss pressure and breakdown pressure. The machine learning prediction of planned horizontal well Y14H and well Y15H were then compared against manual results calculated by geomechanics experts. The digital results matched well with manual results. The actual drilling results of well Y15H also confirmed the accuracy of the machine learning method. In well Y15H drilling, there were no drilling complexities and hole enlargements as using mud weight optimized with machine learning prediction. After well completed, the results showed that the pore pressure difference was only 0.5% between downhole measurement, 53.1MPa, and machine learning prediction, 52.8MPa. The minimum horizontal stress difference was about 5% between machine learning prediction, 72.88MPa, and downhole measurement, 76.76MPa. This field study confirmed the accuracy, effectiveness, and efficiency of machine learning method.