Bayesian Search Research Articles

Efficient ensemble uncertainty estimation in Gaussian processes regression

Abstract Reliable uncertainty measures are required when using data-based machine learning interatomic potentials (MLIPs) for atomistic simulations. In this work, we propose for sparse Gaussian process regression (GPR) type MLIPs a stochastic uncertainty measure akin to the query-by-committee approach often used in conjunction with neural network based MLIPs. The uncertainty measure is coined ‘label noise’ ensemble uncertainty as it emerges from adding noise to the energy labels in the training data. We find that this method of calculating an ensemble uncertainty is as well calibrated as the one obtained from the closed-form expression for the posterior variance when the sparse GPR is treated as a projected process. Comparing the two methods, our proposed ensemble uncertainty is, however, faster to evaluate than the closed-form expression. Finally, we demonstrate that the proposed uncertainty measure acts better to support a Bayesian search for optimal structure of Au20 clusters.

CBAM VGG16: An efficient driver distraction classification using CBAM embedded VGG16 architecture

Driver monitoring systems (DMS) are crucial in autonomous driving systems (ADS) when users are concerned about driver/vehicle safety. In DMS, the significant influencing factor of driver/vehicle safety is the classification of driver distractions or activities. The driver’s distractions or activities convey meaningful information to the ADS, enhancing the driver/ vehicle safety in real-time vehicle driving. The classification of driver distraction or activity is challenging due to the unpredictable nature of human driving. This paper proposes a convolutional block attention module embedded in Visual Geometry Group (CBAM VGG16) deep learning architecture to improve the classification performance of driver distractions. The proposed CBAM VGG16 architecture is the hybrid network of the CBAM layer with conventional VGG16 network layers. Adding a CBAM layer into a traditional VGG16 architecture enhances the model’s feature extraction capacity and improves the driver distraction classification results. To validate the significant performance of our proposed CBAM VGG16 architecture, we tested our model on the American University in Cairo (AUC) distracted driver dataset version 2 (AUCD2) for cameras 1 and 2 images. Our experiment results show that the proposed CBAM VGG16 architecture achieved 98.65% classification accuracy for camera 1 and 97.85% for camera 2 AUCD2 datasets. The CBAM VGG16 architecture also compared the driver distraction classification performance with DenseNet121, Xception, MoblieNetV2, InceptionV3, and VGG16 architectures based on the proposed model’s accuracy, loss, precision, F1 score, recall, and confusion matrix. The drivers’ distraction classification results indicate that the proposed CBAM VGG16 has 3.7% classification improvements for AUCD2 camera 1 images and 5% for camera 2 images compared to the conventional VGG16 deep learning classification model. We also tested our proposed architecture with different hyperparameter values and estimated the optimal values for best driver distraction classification. The significance of data augmentation techniques for the data diversity performance of the CBAM VGG16 model is also validated in terms of overfitting scenarios. The Grad-CAM visualization of our proposed CBAM VGG16 architecture is also considered in our study, and the results show that VGG16 architecture without CBAM layers is less attentive to the essential parts of the driver distraction images. Furthermore, we tested the effective classification performance of our proposed CBAM VGG16 architecture with the number of model parameters, model size, various input image resolutions, cross-validation, Bayesian search optimization and different CBAM layers. The results indicate that CBAM layers in our proposed architecture enhance the classification performance of conventional VGG16 architecture and outperform the state-of-the-art deep learning architectures.

Analyzing risk influencing factors of ship collision accidents: A data-driven Bayesian network model integrating physical knowledge

The interaction and propagation effects among risk-influencing factors (RIFs) often lead to maritime accidents. Therefore, to support maritime risk management in decision-making, it is imperative to conduct a quantitative risk assessment (QRA) of these accidents, which requires a methodology capable of capturing causal relationships in limited cases. To achieve this goal, this study proposes a data-driven Bayesian network (BN) model that integrates physical knowledge with the QRA. Based on the collected data, a combination of domain knowledge, structure learning, and parameter learning is employed to construct the model. In the data-driven phase, three structural learning algorithms including Bayesian search (BS), Greedy thick thinning (GTT), and Peter-Clark (PC) algorithms, were used in combination with the expectation maximization algorithm of parameter learning. Then, using four indices calculated by the confusion matrix, the most fitting algorithm for structure learning was chosen, and the confusion matrix was obtained by five-fold cross-validation. Finally, network propagation impact (NPI) is introduced to prioritize RIFs. Preventive measures and emergency plans are formulated based on the network resilience metric (NRM) and network vulnerability metric (NVM). This approach leverages the objectivity of a data-driven BN and integrates domain expertise to enhance model validity. A case study of collisions was conducted to demonstrate the applicability of the model. The data were sourced from 327 collision accident reports provided by the China Maritime Safety Administration, and the PC algorithm was chosen. Findings indicate that the “Management system”, “Supervision”, and “Crew training” RIFs are prioritized for preventive measures, whereas “Communication” receives more resources for emergency handling. The results suggest the formulation of risk management strategies for practitioners to improve maritime safety.

An international relations quantitative evaluation model (IRQEM) based on an integrated method.

International relations (IR) have great uncertainty and instability. Bad IR or conflicts will bring about heavy economic losses and widespread social unrest domestically and internationally. The accurate prediction for bilateral relations can support decision making for timely responses, which will be used to find ways to maintain development in the complex international situation. An international relations quantitative evaluation model (IRQEM) is proposed by integrating a variety of research models and methods like the interpretative structural modeling method (ISM), Bayesian network (BN) model, the Bayesian search (BS), and the expectation-maximization (EM) algorithm, which is novel for IR research. Factors from several different fields are identified as BN nodes. Each node is assigned different state values. The hierarchical structure of these BN nodes is obtained by ISM. The data collection of 192 cases is used to construct the BN model by GeNIe 4.0. The IRQEM can be used to evaluate the influence of emergencies on IR. The critical factors of IR also can be explored through our proposed model. Results show that the prediction of bilateral relations under emergencies can be realized by updating the indicator set when emergencies occur. The capability to anticipate threats of IR changes is advanced by optimizing the reporting information of IR forecasting through a combination of qualitative and quantitative methods, charts, and texts. Relevant analysis results can provide support for national security decision making.

Hepatitis Identification using Backward Elimination and Extreme Gradient Boosting Methods

Background: Hepatitis is a contagious inflammatory disease of the liver and is a public health problem because it is easily transmitted. The main factors causing hepatitis are viral infections, disease complications, alcohol, autoimmune diseases, and drug effects. Some hepatitis variants such as B, C, and D can also cause liver cancer if left untreated. Objective: This research aims to determine the effect of Backward Elimination feature selection on the performance of hepatitis disease identification compared to cases where Backward Elimination is not applied. Methods: XGBoost classification, capable of handling machine learning problems, was utilized. Additionally, Backward Elimination was used as a featured selection to increase accuracy by reducing the number of less important features in the data classification process. Results: The results for training XGBoost model with Backward Elimination, and applying Random Search for hyperparameter optimization, achieved an accuracy of 98.958% at 0.64 seconds. This performance was better than using Bayesian search, which produced the same accuracy of 98.958% but required a longer training time of 0.70 seconds. Conclusion: The use of features obtained from Backward Elimination process as well as the use of feature average values for missing value treatment, produced an accuracy of 98.958%.the precision in training XGBoost model with hyperparameter Bayesian search achieved accuracy, recall, and F1 score of 98.934%, 98.934%, and 98.934%, respectively. Consequently, the use of Backward Elimination in XGBoost model led to faster training, improved accuracy, and decreased overfitting. Keywords: Hepatitis, Backward Elimination, XGBoost, Bayesian Search, Random Search

Comparing hyperparameter tuning methods in machine learning based urban building energy modeling: A study in Chicago

In recent years, many studies have applied machine learning (ML) in urban building energy models (UBEMs) to understand building energy issues in cities. However, previous studies had limited in-depth discussions on hyperparameter tuning, an essential aspect of model training. To address this gap, this study examines the impact of different hyperparameter tuning strategies on the development of ML-based UBEMs, specifically for residential buildings in Chicago. Utilizing a comprehensive dataset that encompasses building, urban, household, and energy management factors, and annual electricity usage across 2,078 residential block groups in Chicago for the year 2010, this study employs five widely used supervised machine learning (SML) algorithms. Through three experiments, the study found that gradient boosting decision trees models generally outperform others. However, hyperparameter tuning can significantly enhance the performance of all tested SML models. The comparison of three search methods, grid search, random search, and Bayesian search, revealed that they have similar tuning performance, but random search stands out for its effectiveness, speed, and flexibility. Moreover, the study demonstrates that the suggested search space for hyperparameters yields better results compared to the commonly used search space in most cases. Interestingly, altering the search budget appeared to have minimal impact on the tuning effectiveness. Employing repeated cross-validation methods helped mitigate the issues associated with random data splits in the training process, leading to more reliable tuning outcomes. Further investigations into the scalability of training datasets and the evaluation of models using alternative accuracy metrics and considerations of model inductive bias provided additional insights. These findings informed recommendations regarding hyperparameter tuning strategies, optimal sample sizes, and model evaluation techniques. Overall, this research contributes to a deeper understanding of the role of hyperparameter tuning in the development of ML-based UBEMs, offering valuable insights for energy-efficient urban planning and policymaking toward sustainable city development.

A framework to characterize, model, and optimize water-energy systems: case study of a novel HDH system

The rapid development in water-energy systems calls for advanced modeling and optimization tools to improve the technologies throughputs and minimize their energy consumption. While having a wide footprint in multiple research areas, Artificial Intelligence applications in water-energy systems are still in early stages. There is a need for generalized models to fully characterize parametric relationships, optimize technologies' performance, and have the flexibility to apply to different complex and non-linear systems. This article describes a digital twin framework that can be used for that purpose. This framework provides fundamental understanding of the process as in process-driven models alongside with the accuracy and usability of data-driven methods. The framework's structure focused on modeling and optimization aspects of digital twin models. As a part of developing a novel humidification-dehumidification desalination technology, this framework was used to model energy consumption based on 16 different operational parameters and was accurate to within 1 % of the data. Pairwise parameters sensitivities were identified by the framework for two case studies involving the whole cycle operation and a critical subsystem of the technology. Moreover, the framework was used to optimize the technology performance through data-efficient Bayesian search methods. Different search realms were used in this process. The framework was able to identify minimum and maximum energy consumption regions by sampling only 25 data points out of possible 5157 cases.

Reliable prediction of difficult airway for tracheal intubation from patient preoperative photographs by machine learning methods

BackgroundEstimating the risk of a difficult tracheal intubation should help clinicians in better anaesthesia planning, to maximize patient safety. Routine bedside screenings suffer from low sensitivity. ObjectiveTo develop and evaluate machine learning (ML) and deep learning (DL) algorithms for the reliable prediction of intubation risk, using information about airway morphology. MethodsObservational, prospective cohort study enrolling n=623 patients who underwent tracheal intubation: 53/623 difficult cases (prevalence 8.51%).First, we used our previously validated deep convolutional neural network (DCNN) to extract 2D image coordinates for 27 + 13 relevant anatomical landmarks in two preoperative photos (frontal and lateral views). Here we propose a method to determine the 3D pose of the camera with respect to the patient and to obtain the 3D world coordinates of these landmarks. Then we compute a novel set of dM=59 morphological features (distances, areas, angles and ratios), engineered with our anaesthesiologists to characterize each individual's airway anatomy towards prediction.Subsequently, here we propose four ad hoc ML pipelines for difficult intubation prognosis, each with four stages: feature scaling, imputation, resampling for imbalanced learning, and binary classification (Logistic Regression, Support Vector Machines, Random Forests and eXtreme Gradient Boosting). These compound ML pipelines were fed with the dM=59 morphological features, alongside dD=7 demographic variables. Here we trained them with automatic hyperparameter tuning (Bayesian search) and probability calibration (Platt scaling). In addition, we developed an ad hoc multi-input DCNN to estimate the intubation risk directly from each pair of photographs, i.e. without any intermediate morphological description.Performance was evaluated using optimal Bayesian decision theory. It was compared against experts' judgement and against state-of-the-art methods (three clinical formulae, four ML, four DL models). ResultsOur four ad hoc ML pipelines with engineered morphological features achieved similar discrimination capabilities: median AUCs between 0.746 and 0.766. They significantly outperformed both expert judgement and all state-of-the-art methods (highest AUC at 0.716). Conversely, our multi-input DCNN yielded low performance due to overfitting. This same behaviour occurred for the state-of-the-art DL algorithms. Overall, the best method was our XGB pipeline, with the fewest false negatives at the optimal Bayesian decision threshold. ConclusionsWe proposed and validated ML models to assist clinicians in anaesthesia planning, providing a reliable calibrated estimate of airway intubation risk, which outperformed expert assessments and state-of-the-art methods. Our novel set of engineered features succeeded in providing informative descriptions for prognosis.

The NANOGrav 12.5 yr Data Set: Search for Gravitational Wave Memory

We present the results of a Bayesian search for gravitational wave (GW) memory in the NANOGrav 12.5 yr data set. We find no convincing evidence for any gravitational wave memory signals in this data set. We find a Bayes factor of 2.8 in favor of a model that includes a memory signal and common spatially uncorrelated red noise (CURN) compared to a model including only a CURN. However, further investigation shows that a disproportionate amount of support for the memory signal comes from three dubious pulsars. Using a more flexible red-noise model in these pulsars reduces the Bayes factor to 1.3. Having found no compelling evidence, we go on to place upper limits on the strain amplitude of GW memory events as a function of sky location and event epoch. These upper limits are computed using a signal model that assumes the existence of a common, spatially uncorrelated red noise in addition to a GW memory signal. The median strain upper limit as a function of sky position is approximately 3.3 × 10−14. We also find that there are some differences in the upper limits as a function of sky position centered around PSR J0613−0200. This suggests that this pulsar has some excess noise that can be confounded with GW memory. Finally, the upper limits as a function of burst epoch continue to improve at later epochs. This improvement is attributable to the continued growth of the pulsar timing array.

Unraveling atherosclerotic cardiovascular disease risk factors through conditional probability analysis with Bayesian networks: insights from the AZAR cohort study

This study aimed at modelling the underlying predictor of ASCVD through the Bayesian network (BN). Data for the AZAR Cohort Study, which evaluated 500 healthcare providers in Iran, was collected through examinations, and blood samples. Two BNs were used to explore a suitable causal model for analysing the underlying predictor of ASCVD; Bayesian search through an algorithmic approach and knowledge-based BNs. Results showed significant differences in ASCVD risk factors across background variables’ levels. The diagnostic indices showed better performance for the knowledge-based BN (Area under ROC curve (AUC) = 0.78, Accuracy = 76.6, Sensitivity = 62.5, Negative predictive value (NPV) = 96.0, Negative Likelihood Ratio (LR−) = 0.48) compared to Bayesian search (AUC = 0.76, Accuracy = 72.4, Sensitivity = 17.5, NPV = 93.2, LR− = 0.83). In addition, we decided on knowledge-based BN because of the interpretability of the relationships. Based on this BN, being male (conditional probability = 63.7), age over 45 (36.3), overweight (51.5), Mets (23.8), diabetes (8.3), smoking (10.6), hypertension (12.1), high T-C (28.5), high LDL-C (23.9), FBS (12.1), and TG (25.9) levels were associated with higher ASCVD risk. Low and normal HDL-C levels also had higher ASCVD risk (35.3 and 37.4), while high HDL-C levels had lower risk (27.3). In conclusion, BN demonstrated that ASCVD was significantly associated with certain risk factors including being older and overweight male, having a history of Mets, diabetes, hypertension, having high levels of T-C, LDL-C, FBS, and TG, but Low and normal HDL-C and being a smoker. The study may provide valuable insights for developing effective prevention strategies for ASCVD in Iran.

Navigating the nuances: comparative analysis and hyperparameter optimisation of neural architectures on contrast-enhanced MRI for liver and liver tumour segmentation

In medical imaging, accurate segmentation is crucial to improving diagnosis, treatment, or both. However, navigating the multitude of available architectures for automatic segmentation can be overwhelming, making it challenging to determine the appropriate type of architecture and tune the most crucial parameters during dataset optimisation. To address this problem, we examined and refined seven distinct architectures for segmenting the liver, as well as liver tumours, with a restricted training collection of 60 3D contrast-enhanced magnetic resonance images (CE-MRI) from the ATLAS dataset. Included in these architectures are convolutional neural networks (CNNs), transformers, and hybrid CNN/transformer architectures. Bayesian search techniques were used for hyperparameter tuning to hasten convergence to the optimal parameter mixes while also minimising the number of trained models. It was unexpected that hybrid models, which typically exhibit superior performance on larger datasets, would exhibit comparable performance to CNNs. The optimisation of parameters contributed to better segmentations, resulting in an average increase of 1.7% and 5.0% in liver and tumour segmentation Dice coefficients, respectively. In conclusion, the findings of this study indicate that hybrid CNN/transformer architectures may serve as a practical substitute for CNNs even in small datasets. This underscores the significance of hyperparameter optimisation.

Prediction of transient NOX emission from a non-road diesel engine using a model combining Bayesian search and Population-based training

Due to the rising environmental concerns, particularly air quality, the emission regulations for non-road mobile machinery are becoming increasingly strict. Real-time emission prediction from diesel engines is significant for emission control and regional pollution estimation. This study aims to develop a machine learning model and optimize its hyperparameters by using a hyperparameter optimization method to NOX emission. Firstly, we collected NOX emission data from test under the non-road transient test cycle (NRTC) and built a significant dataset to choose a best model. Then, the model was trained by dataset and the hyperparameters were automatically optimized by combining Bayesian and Population based training. The accuracy of the optimized was indicated by an R2 value of 0.9784 with the 8 input features. The relative error in the cycle level was 1.3%. Lastly, the quality of NOX emissions during the cycle and the effect of each parameter on NOX emissions were analyzed. The results show that the model is able to predict the real-time concentration changes of NOX more accurately. It can provide a reference for the research and development of emission control technology for non-road mobile machinery.

Optimizing aspect-based sentiment analysis using sentence embedding transformer, bayesian search clustering, and sparse attention mechanism

The aspect-based sentiment analysis of hotel reviews represents a critical yet underexplored area of research. Such reviews encompass a range of expressions that extend beyond simple positive, negative, or neutral sentiments, delving into specific aspects discussed within the review. For instance, a statement like 'the location is comfortable, the food is good, but unfortunately, the service is bad' encapsulates multiple aspects, including location, food, and service. Existing research in Aspect-Based Sentiment Analysis (ABSA) frequently employs word embedding techniques for feature extraction, utilizing both Term and Transformer models. This study introduces an innovative approach by transitioning from word to sentence embedding, employing the SBERT transformer model for this transformation. This study further innovates label creation and topic modeling by integrating Bayesian search clustering with Inverse Document Frequency (IDF) calculations. This approach enables the identification of relevant topics, categorizing IDF scores based on occurrence frequencies. Scores ranging between 4–6 are marked as having low value but high informative potential, making them suitable candidates for label-specific datasets, particularly those without pre-existing labels. Additionally, this study incorporates the BigBird model to enhance this classification methodology. Applying this comprehensive framework to hotel review datasets, the result of the ABSA evaluation achieved an impressive accuracy score of 99%, indicating the efficacy of the proposed methodology in this nuanced field.

Machine Learning model based on the Light Gradient Boosting Machine to predict the probability of default in customers of the Credit Card portfolio

Bank loans are a widely used means of payment in recent times, more and more people are accessing products such as credit cards, loans, etc. Banks have implemented classic prediction models, the vast majority based on logistic regression since it allows great interpretability for the business and the effect of the model variables. The purpose of this research is to perform a predictive analysis on the probability of customer default in the credit card portfolio using a risk score. The dataset used is the so-called default of credit card clients Data Set from the UCI Machine Learning DB, the approach is quantitative and the methodology is descriptive analytics, techniques based on gradient boosters will be used to make the prediction, among the trained algorithms We have Logistic Regression with WOE, CatBoost, As a result, the light gradient enhancement machine (LightGBM) tuned with a Bayesian search was obtained, obtaining a GINI of 57.4, which improves by +6 points to the Logistic Regression with Woe and by +3p to XgBoost and CatBoost. Finally, obtaining the Gain and Shapley values made up for the lack of interpretability of the variables, allowing better decision making when evaluating clients. Likewise, as future work, it is intended to add unstructured variables that allow the Model's indicators to be improved.

An Ensemble Machine Learning Model Using Gradient Boosting Identifies Patients with Disease Progression in Newly Diagnosed Multiple Myeloma

Introduction: In many cases, treatment decisions for multiple myeloma patients must be made in the absence of high quality randomized controlled clinical trials. As a result, many clinicians lean on prognostic models to drive treatment selection. The most widely used of these models incorporate a limited number of patient related factors that reflect tumor burden, cytogenetic features, or gene expression profiling. These prediction scores are derived from regression models that incorporate these variables at the time of diagnosis. They do not account for variables that change dynamically over time, do not explore the relationship between treatment selection and progression, and imperfectly predict survival outcomes. We designed a prognostic model based on an ensemble machine learning platform to predict progression in NDMM using Extreme Gradient Boosting Machine (XGBoost) combined with accelerated failure time modeling for survival analysis. Methods: We utilized a large retrospective data set containing treatment and response information for 1127 patients with newly diagnosed multiple myeloma (NDMM) treated at the Cleveland Clinic Foundation between 2000 and 2023. Following data preprocessing based on data completeness, 953 patient records were included in our training, testing, and cross validation datasets. For the purposes of our analysis, the initial dataset was randomly split into training (70%), testing (15%) and validation (15%) subsets at the patient level. We also defined the lower and upper bounds for each subset, which is critical due to the right-censored nature of survival data. Hyperparameters for XGBoost were optimized using Bayesian search, minimizing the negative log-likelihood. A random forest method was applied for the imputation of missing data (MissForest). We then trained the XGBoost model using GPU acceleration for enhanced computational efficiency. Finally, a log-rank test on predicted survival times was used to test the model's performance on patients with and without known progression. Results: Our preprocessed data set had 953 patients with a mean age at disease onset of 65 years and a slight male predominance (55%). Approximately 27% of patients harbored high cytogenetic risk disease and 3.5% of the cohort presented with extramedullary disease a diagnosis. At a median follow up of 35 months, 47% of patients had experienced disease progression or death. Induction therapy included an immunomodulatory drug in 40% of patients and proteasome inhibitors in 22%. Frontline autologous stem cell transplantation followed induction in 28% of patients. Median progression free survival in the overall data set was 44 months. These features were consistent across the randomly assigned training, testing, and validation cohorts. Following data preprocessing, 34 independent clinical and genomic variables including selection of first line treatment were assessed as model inputs each available record. Under optimized parameters, the model was trained with a maximum tree depth = 7 and a learning rate ~ 0.22 for the desired output of progression free survival (PFS). We then queried PFS for both the training and validation sets and divided patients into those known to have progressed and those without a progression event. Survival analysis was undertaken using predicted PFS values for patients known to have progressed and those who remained progression free. For the validation data set, our model successfully discerned between progressed and non-progressed cases (log-rank test statistic = 22.07, p < 0.005) (Figure 1). Discussion: We present a machine learning approach based on regularized gradient boosting that accurately discerns between patients who experience progression and those who remain progression free at a median ~35 months of follow-up in a large retrospective data set in patients presenting with NDMM. Further elaboration of our model will allow for the incorporation of large amounts data to predict survival outcomes on the basis of dynamic variables such as depth of response and treatment selection. With the ability to parse outcomes among multiple myeloma patients at high resolution, future clinicians and clinical trialists may be able to overcome limitations in trial design and patient-level therapy selection for both newly diagnosed and relapsed patients.

ChatGPT Research Group for Optimizing the Crystallinity of MOFs and COFs.

We leveraged the power of ChatGPT and Bayesian optimization in the development of a multi-AI-driven system, backed by seven large language model-based assistants and equipped with machine learning algorithms, that seamlessly orchestrates a multitude of research aspects in a chemistry laboratory (termed the ChatGPT Research Group). Our approach accelerated the discovery of optimal microwave synthesis conditions, enhancing the crystallinity of MOF-321, MOF-322, and COF-323 and achieving the desired porosity and water capacity. In this system, human researchers gained assistance from these diverse AI collaborators, each with a unique role within the laboratory environment, spanning strategy planning, literature search, coding, robotic operation, labware design, safety inspection, and data analysis. Such a comprehensive approach enables a single researcher working in concert with AI to achieve productivity levels analogous to those of an entire traditional scientific team. Furthermore, by reducing human biases in screening experimental conditions and deftly balancing the exploration and exploitation of synthesis parameters, our Bayesian search approach precisely zeroed in on optimal synthesis conditions from a pool of 6 million within a significantly shortened time scale. This work serves as a compelling proof of concept for an AI-driven revolution in the chemistry laboratory, painting a future where AI becomes an efficient collaborator, liberating us from routine tasks to focus on pushing the boundaries of innovation.

Shape characterization and depth recognition of metal cracks based on laser infrared thermography and machine learning

Due to the operation of modern industrial equipment under high pressure, high speed and high load conditions, cracks inevitably appear on the surfaces of metal components. Crack detection on metal surfaces is increasingly becoming a focal point in the field of non-destructive testing. In order to locate and quantitatively analyze surface cracks on metallic materials as early as possible to reduce the cost in industrial production, this paper achieves rapid localization of surface cracks by establishing a line laser thermography scanning system. An unsupervised edge detection algorithm of principal component analysis combined with K-means (PK) is proposed to achieve accurate crack edge detection by combining with a point-pulse laser thermography system. The accuracy of the PK algorithm is confirmed by comparison with other edge detection algorithms. After that, accurate identification of crack depth is achieved by selecting temperature features through particle swarm optimization algorithm and optimizing hyper-parameters of support vector machine and k-nearest neighbor through Bayesian search method. The experiments show that the best recall and accuracy of PK for crack detection are 82.9% and 86.2%, respectively; Combining the particle swarm optimization algorithm with the BS method, the mean square error of SVR and KNN for crack depth recognition is 0.092 and 0.089, respectively.

Search for scalar induced gravitational waves in the international pulsar timing array data release 2 and NANOgrav 12.5 years datasets

We perform a Bayesian search in the latest Pulsar Timing Array (PTA) datasets for a stochastic gravitational wave (GW) background sourced by curvature perturbations at scales 10^5105 Mpc^{-1}\lesssim−1≲ k\lesssim 10^8≲108 Mpc^{-1}−1. These re-enter the Hubble horizon at temperatures around and below the QCD crossover phase transition in the early Universe. We include a stochastic background of astrophysical origin in our search and properly account for constraints on the curvature power spectrum from the overproduction of primordial black holes (PBHs). We find that the International PTA Data Release 2 significantly favors the astrophysical model for its reported common-spectrum process, over the curvature-induced background. On the other hand, the two interpretations fit the NANOgrav 12.5 years dataset equally well. We then set new upper limits on the amplitude of the curvature power spectrum at small scales. These are independent from, and competitive with, indirect astrophysical bounds from the abundance of PBH dark matter. Upcoming PTA data releases will provide the strongest probe of the curvature power spectrum around the QCD epoch.

Untargeted Bayesian search of anisotropic gravitational-wave backgrounds through the analytical marginalization of the posterior

Untargeted Bayesian search of anisotropic gravitational-wave backgrounds through the analytical marginalization of the posterior

Using Bandit Algorithms to Maximize SARS-CoV-2 Case-Finding: Evaluation and Feasibility Study.

The Flexible Adaptive Algorithmic Surveillance Testing (FAAST) program represents an innovative approach for improving the detection of new cases of infectious disease; it is deployed here to screen and diagnose SARS-CoV-2. With the advent of treatment for COVID-19, finding individuals infected with SARS-CoV-2 is an urgent clinical and public health priority. While these kinds of Bayesian search algorithms are used widely in other settings (eg, to find downed aircraft, in submarine recovery, and to aid in oil exploration), this is the first time that Bayesian adaptive approaches have been used for active disease surveillance in the field. This study's objective was to evaluate a Bayesian search algorithm to target hotspots of SARS-CoV-2 transmission in the community with the goal of detecting the most cases over time across multiple locations in Columbus, Ohio, from August to October 2021. The algorithm used to direct pop-up SARS-CoV-2 testing for this project is based on Thompson sampling, in which the aim is to maximize the average number of new cases of SARS-CoV-2 diagnosed among a set of testing locations based on sampling from prior probability distributions for each testing site. An academic-governmental partnership between Yale University, The Ohio State University, Wake Forest University, the Ohio Department of Health, the Ohio National Guard, and the Columbus Metropolitan Libraries conducted a study of bandit algorithms to maximize the detection of new cases of SARS-CoV-2 in this Ohio city in 2021. The initiative established pop-up COVID-19 testing sites at 13 Columbus locations, including library branches, recreational and community centers, movie theaters, homeless shelters, family services centers, and community event sites. Our team conducted between 0 and 56 tests at the 16 testing events, with an overall average of 25.3 tests conducted per event and a moving average that increased over time. Small incentives-including gift cards and take-home rapid antigen tests-were offered to those who approached the pop-up sites to encourage their participation. Over time, as expected, the Bayesian search algorithm directed testing efforts to locations with higher yields of new diagnoses. Surprisingly, the use of the algorithm also maximized the identification of cases among minority residents of underserved communities, particularly African Americans, with the pool of participants overrepresenting these people relative to the demographic profile of the local zip code in which testing sites were located. This study demonstrated that a pop-up testing strategy using a bandit algorithm can be feasibly deployed in an urban setting during a pandemic. It is the first real-world use of these kinds of algorithms for disease surveillance and represents a key step in evaluating the effectiveness of their use in maximizing the detection of undiagnosed cases of SARS-CoV-2 and other infections, such as HIV.