Train Machine Learning Research Articles

Statistical analysis of microstructurally small fatigue crack growth in three-dimensional polycrystals based on high-fidelity numerical simulations

Microstructurally small cracks (MSCs) are sensitive to their local microstructural neighborhoods, resulting in highly variable 3D crack propagation within individual samples and among a population of samples. Statistically quantifying this complex spatiotemporal variability requires collecting and analyzing a large number of 3D MSC growth observations, which remains challenging due to experimental constraints that limit the availability of 3D observations of MSCs in the existing literature. We address this gap by leveraging virtual observations of MSC growth using a state-of-the-art, high-fidelity simulation framework to provide a statistical perspective on 3D MSC growth behavior. The MSC growth simulations were performed in 40 unique but statistically similar polycrystalline microstructures, and the data extracted from the virtual observations were collectively analyzed to quantify variability in geometric, microstructural, and micromechanical aspects of MSCs. Variability in tortuosity, crack surface crystallography, and MSC growth parameters (local crack extension and kink angle) were quantified statistically. The results show that 3D MSC surfaces do not necessarily propagate along {111} crystallographic planes despite crack traces on radial planes being closely aligned with {111} slip plane traces. Also, the 3D MSC surfaces exhibit increasingly tortuous propagation and spatially varying local crack growth rates (with variability as high as 59% among the population). Moreover, a correlation study revealed some of the highly influential microstructural and micromechanical features controlling MSC growth parameters. The quantified variability holds direct implications for advanced materials prognosis in engineering applications, and the identified features from the correlation study can be leveraged to train machine learning models for rapidly predicting MSC growth behavior in the future.

An optimization framework with dimensionality reduction using Markov Chain Monte Carlo and genetic algorithms for groundwater potential assessment

Limited samples and high-dimensional feature spaces often hinder the accuracy of machine learning (ML) models in regional groundwater potential assessment (GPA). This study proposes a novel framework, the GPA with Dimensionality Optimization (GPADO), that optimizes feature dimension reduction to enhance prediction performance. Taking the Jianghan Basin as an example, data on nine continuous variables and five categorical variables influencing the region's GPA were gathered, expanding the feature set to 37 through One-hot encoding for categorical variables. Three scenarios were devised to assess prediction outcomes following various dimensionality reduction approaches. Comparative analysis revealed that a hybrid dimension reduction method, incorporating both continuous and categorical variables, yielded the highest validation set accuracy. Consequently, genetic algorithm and Markov Chain Monte Carlo methods were employed to determine the optimal solution and uncertainties associated with four unknown parameters: the chosen dimension reduction method for continuous and categorical variables, and the number of dimensions retained. Results indicated that utilizing singular value decomposition to reduce categorical variables to three dimensions, coupled with principal component analysis reducing continuous variables to three dimensions, produced the highest model validation accuracy of 0.834 within the GPADO framework. This optimal configuration facilitated automated ML training, resulting in a final validation set accuracy of 0.851 and a test set accuracy of 0.836. The resulting model provided a more precise spatial distribution of groundwater potential and demonstrated the GPADO framework's effectiveness in improving GPA accuracy, particularly in data-scarce regions. The GPADO framework offers a valuable approach for enhancing GPA studies.

A cost modelling methodology based on machine learning for engineered-to-order products

Recent scientific studies are targeted at applying and assessing the effectiveness of Machine Learning (ML) approaches for cost estimation during the preliminary design phases. To train ML prediction models, comprehensive and structured datasets of historical data are required. This solution is inapplicable when such information is unavailable or sparse due to the lack of structured datasets. For engineered-to-order products, the number of historical records is often limited and strongly influenced by different purchasing or manufacturing strategies, thus requiring complex normalisation of such data.This method overcomes the above limitations by presenting an ML-based cost modelling methodology for the conceptual design that is applicable even when historical data are insufficient to train the prediction algorithms. The training dataset is generated through an analytical and automatic software tool for manufacturing cost estimation. Such a tool, starting from a 3D model of a product, can quickly and autonomously assess the related cost in different scenarios. An extensive and structured training dataset can be easily generated. The proposed methodology was based on CRISP-DM (Cross Industry Standard Process for Data Mining).Cost engineers of an Oil & Gas company used the method to develop parametric cost models for discs and spacers of an axial compressor. The solution guarantees lower error (7% vs 9%) and significant time-saving (minutes instead of hours) than estimations based on other approaches. Cost models are more comprehensive (capable of analysing different scenarios), explainable (not conceived as a black box), and self-learning (can be updated by extending the training dataset).

Generating Synthetic MR Spectroscopic Imaging Data with Generative Adversarial Networks to Train Machine Learning Models.

To develop a new method to generate synthetic MR spectroscopic imaging (MRSI) data for training machine learning models. This study targeted routine MRI examination protocols with single voxel spectroscopy (SVS). A novel model derived from pix2pix generative adversarial networks was proposed to generate synthetic MRSI data using MRI and SVS data as inputs. T1- and T2-weighted, SVS, and reference MRSI data were acquired from healthy brains with clinically available sequences. The proposed model was trained to generate synthetic MRSI data. Quantitative evaluation involved the calculation of the mean squared error (MSE) against the reference and metabolite ratio value. The effect of the location of and the number of the SVS data on the quality of the synthetic MRSI data was investigated using the MSE. The synthetic MRSI data generated from the proposed model were visually closer to the reference. The 95% confidence interval (CI) of the metabolite ratio value of synthetic MRSI data overlapped with the reference for seven of eight metabolite ratios. The MSEs tended to be lower in the same location than in different locations. The MSEs among groups of numbers of SVS data were not significantly different. A new method was developed to generate MRSI data by integrating MRI and SVS data. Our method can potentially increase the volume of MRSI data training for other machine learning models by adding SVS acquisition to routine MRI examinations.

Machine‐learning‐based demand forecasting against food waste: Life cycle environmental impacts and benefits of a bakery case study

AbstractRapid advancements in artificial intelligence (AI) are driving transformative changes in many areas, with significant environmental implications. Yet, environmental assessments for specific applications are scarce. This study presents an in‐depth life cycle assessment of “Foodforecast,” a machine learning (ML) cloud service designed to reduce food waste in bakeries by optimizing sales forecasting. It covers four impact categories: global warming, abiotic resource depletion, cumulative energy demand, and freshwater eutrophication. The assessment includes both the direct environmental impacts of the ML model and the underlying system hardware, as well as the indirect benefits of avoided bakery returns compared to traditional ordering methods, using real‐world case study data. In 2022, “Foodforecast” led to an average 30% reduction in bakery returns, primarily bread and rolls, according to sales reports. The associated environmental benefits significantly outweighed the system's direct impacts by one to three orders of magnitude across impact categories and return utilization scenarios. The study identifies support activities such as service maintenance during deployment as major direct impact factors, surpassing those from cloud compute for ML operations. Data processing and inference dominate the latter, while the much‐discussed ML training plays a minor role. The environmental consequences of AI are complex and dual sided. This case study demonstrates that AI might provide environmental benefits in certain contexts, yet results are constrained by methodological challenges and data uncertainties. There remains a need for further holistic LCAs across different ML applications to inform decision‐making processes and ultimately guide the responsible use of AI.

Estimation of water quality in Korattur Lake, Chennai, India, using Bayesian optimization and machine learning

Assessing water quality becomes imperative to facilitate informed decision-making concerning the availability and accessibility of water resources in Korattur Lake, Chennai, India, which has been adversely affected by human actions. Although numerous state-of-the-art studies have made significant advancements in water quality classification, conventional methods for training machine learning model parameters still require substantial human and material resources. Hence, this study employs stochastic gradient descent (SGD), adaptive boosting (AdaBoosting), Perceptron, and artificial neural network algorithms to classify water quality categories as these well-established methods, combined with Bayesian optimization for hyperparameter tuning, provide a robust framework to demonstrate significant performance enhancements in water quality classification. The input features for model training from 2010 to 2019 comprise water parameters such as pH, phosphate, total dissolved solids (TDS), turbidity, nitrate, iron, chlorides, sodium, and chemical oxygen demand (COD). Bayesian optimization is employed to dynamically tune the hyperparameters of different machine learning algorithms and select the optimal algorithms with the best performance. Comparing the performance of different algorithms, AdaBoosting exhibits the highest performance in water quality level classification, as indicated by its superior accuracy (100%), precision (100%), recall (100%), and F1 score (100%). The top four important factors for water quality level classification are COD (0.684), phosphate (0.119), iron (0.112), and TDS (0.084). Additionally, variations or changes in phosphate levels are likely to coincide with similar variations in TDS levels.

Gamified Crowdsourcing as a Novel Approach to Lung Ultrasound Data Set Labeling: Prospective Analysis.

Machine learning (ML) models can yield faster and more accurate medical diagnoses; however, developing ML models is limited by a lack of high-quality labeled training data. Crowdsourced labeling is a potential solution but can be constrained by concerns about label quality. This study aims to examine whether a gamified crowdsourcing platform with continuous performance assessment, user feedback, and performance-based incentives could produce expert-quality labels on medical imaging data. In this diagnostic comparison study, 2384 lung ultrasound clips were retrospectively collected from 203 emergency department patients. A total of 6 lung ultrasound experts classified 393 of these clips as having no B-lines, one or more discrete B-lines, or confluent B-lines to create 2 sets of reference standard data sets (195 training clips and 198 test clips). Sets were respectively used to (1) train users on a gamified crowdsourcing platform and (2) compare the concordance of the resulting crowd labels to the concordance of individual experts to reference standards. Crowd opinions were sourced from DiagnosUs (Centaur Labs) iOS app users over 8 days, filtered based on past performance, aggregated using majority rule, and analyzed for label concordance compared with a hold-out test set of expert-labeled clips. The primary outcome was comparing the labeling concordance of collated crowd opinions to trained experts in classifying B-lines on lung ultrasound clips. Our clinical data set included patients with a mean age of 60.0 (SD 19.0) years; 105 (51.7%) patients were female and 114 (56.1%) patients were White. Over the 195 training clips, the expert-consensus label distribution was 114 (58%) no B-lines, 56 (29%) discrete B-lines, and 25 (13%) confluent B-lines. Over the 198 test clips, expert-consensus label distribution was 138 (70%) no B-lines, 36 (18%) discrete B-lines, and 24 (12%) confluent B-lines. In total, 99,238 opinions were collected from 426 unique users. On a test set of 198 clips, the mean labeling concordance of individual experts relative to the reference standard was 85.0% (SE 2.0), compared with 87.9% crowdsourced label concordance (P=.15). When individual experts' opinions were compared with reference standard labels created by majority vote excluding their own opinion, crowd concordance was higher than the mean concordance of individual experts to reference standards (87.4% vs 80.8%, SE 1.6 for expert concordance; P<.001). Clips with discrete B-lines had the most disagreement from both the crowd consensus and individual experts with the expert consensus. Using randomly sampled subsets of crowd opinions, 7 quality-filtered opinions were sufficient to achieve near the maximum crowd concordance. Crowdsourced labels for B-line classification on lung ultrasound clips via a gamified approach achieved expert-level accuracy. This suggests a strategic role for gamified crowdsourcing in efficiently generating labeled image data sets for training ML systems.

A multiclass short-term lightning predictor for the Amazon region using ground-based meteorological data and artificial neural network

Lightning prediction is a complex task due to the intricate nature of this phenomenon. Various sectors of society, including aviation and civil defense, can benefit from accurate lightning occurrence information. Methodologies that can predict lightning occurrence are crucial to minimize the issues related to this phenomenon. In this work, we propose a novel approach using the machine learning model called Artificial Neural Network (ANN) to predict lightning occurrence one hour ahead. We use ground-based meteorological data from the National Institute of Meteorology (INMET) and the number of lightning per hour to feed the ANN model. We used a lightning dataset of six years of observation (2015–2020) from GLD360 to train, validate, and test machine learning algorithm models. A model was developed for each weather station. We use data from 24 stations distributed throughout the Brazilian Legal Amazon region. The multiclass predictor was based on three categories: no lightning, low-intensity, and high-intensity of lightning. We also developed a solution comprising two cascade ANN models, each performing binary prediction. The first predicts the occurrence or no occurrence of lightning, and the second predicts the intensity: low or high. The cascade approach showed superior performance compared to the regular approach.

Contrastive Self-supervised Learning for Neurodegenerative Disorder Classification.

Neurodegenerative diseases such as Alzheimer's disease (AD) or frontotemporal lobar degeneration (FTLD) involve specific loss of brain volume, detectable in vivo using T1-weighted MRI scans. Supervised machine learning approaches classifying neurodegenerative diseases require diagnostic-labels for each sample. However, it can be difficult to obtain expert labels for a large amount of data. Self-supervised learning (SSL) offers an alternative for training machine learning models without data-labels. We investigated if the SSL models can applied to distinguish between different neurodegenerative disorders in an interpretable manner. Our method comprises a feature extractor and a downstream classification head. A deep convolutional neural network trained in a contrastive self-supervised way serves as the feature extractor, learning latent representation, while the classifier head is a single-layer perceptron. We used N=2694 T1-weighted MRI scans from four data cohorts: two ADNI datasets, AIBL and FTLDNI, including cognitively normal controls (CN), cases with prodromal and clinical AD, as well as FTLD cases differentiated into its sub-types. Our results showed that the feature extractor trained in a self-supervised way provides generalizable and robust representations for the downstream classification. For AD vs. CN, our model achieves 82% balanced accuracy on the test subset and 80% on an independent holdout dataset. Similarly, the Behavioral variant of frontotemporal dementia (BV) vs. CN model attains an 88% balanced accuracy on the test subset. The average feature attribution heatmaps obtained by the Integrated Gradient method highlighted hallmark regions, i.e., temporal gray matter atrophy for AD, and insular atrophy for BV. In conclusion, our models perform comparably to state-of-the-art supervised deep learning approaches. This suggests that the SSL methodology can successfully make use of unannotated neuroimaging datasets as training data while remaining robust and interpretable.

Bayesian Networks for Prescreening in Depression: Algorithm Development and Validation.

Identifying individuals with depressive symptomatology (DS) promptly and effectively is of paramount importance for providing timely treatment. Machine learning models have shown promise in this area; however, studies often fall short in demonstrating the practical benefits of using these models and fail to provide tangible real-world applications. This study aims to establish a novel methodology for identifying individuals likely to exhibit DS, identify the most influential features in a more explainable way via probabilistic measures, and propose tools that can be used in real-world applications. The study used 3 data sets: PROACTIVE, the Brazilian National Health Survey (PesquisaNacionalde Saúde [PNS]) 2013, and PNS 2019, comprising sociodemographic and health-related features. A Bayesian network was used for feature selection. Selected features were then used to train machine learning models to predict DS, operationalized as a score of ≥10 on the 9-item Patient Health Questionnaire. The study also analyzed the impact of varying sensitivity rates on the reduction of screening interviews compared to a random approach. The methodology allows the users to make an informed trade-off among sensitivity, specificity, and a reduction in the number of interviews. At the thresholds of 0.444, 0.412, and 0.472, determined by maximizing the Youden index, the models achieved sensitivities of 0.717, 0.741, and 0.718, and specificities of 0.644, 0.737, and 0.766 for PROACTIVE, PNS 2013, and PNS 2019, respectively. The area under the receiver operating characteristic curve was 0.736, 0.801, and 0.809 for these 3 data sets, respectively. For the PROACTIVE data set, the most influential features identified were postural balance, shortness of breath, and how old people feel they are. In the PNS 2013 data set, the features were the ability to do usual activities, chest pain, sleep problems, and chronic back problems. The PNS 2019 data set shared 3 of the most influential features with the PNS 2013 data set. However, the difference was the replacement of chronic back problems with verbal abuse. It is important to note that the features contained in the PNS data sets differ from those found in the PROACTIVE data set. An empirical analysis demonstrated that using the proposed model led to a potential reduction in screening interviews of up to 52% while maintaining a sensitivity of 0.80. This study developed a novel methodology for identifying individuals with DS, demonstrating the utility of using Bayesian networks to identify the most significant features. Moreover, this approach has the potential to substantially reduce the number of screening interviews while maintaining high sensitivity, thereby facilitating improved early identification and intervention strategies for individuals experiencing DS.

Integrated multi-view modeling for reliable machine learning-intensive software engineering

Development of machine learning (ML) systems differs from traditional approaches. The probabilistic nature of ML leads to a more experimentative development approach, which often results in a disparity between the quality of ML models with other aspects such as business, safety, and the overall system architecture. Herein the Multi-view Modeling Framework for ML Systems (M3S) is proposed as a solution to this problem. M3S provides an analysis framework that integrates different views. It is supported by an integrated metamodel to ensure the connection and consistency between different models. To facilitate the experimentative nature of ML training, M3S provides an integrated platform between the modeling environment and the ML training pipeline. M3S is validated through a case study and a controlled experiment. M3S shows promise, but future research needs to confirm its generality.

Does synthetic data augmentation improve the performances of machine learning classifiers for identifying health problems in patient-nurse verbal communications in home healthcare settings?

Identifying health problems in audio-recorded patient-nurse communication is important to improve outcomes in home healthcare patients who have complex conditions with increased risks of hospital utilization. Training machine learning classifiers for identifying problems requires resource-intensive human annotation. To generate synthetic patient-nurse communication and to automatically annotate for common health problems encountered in home healthcare settings using GPT-4. We also examined whether augmenting real-world patient-nurse communication with synthetic data can improve the performance of machine learning to identify health problems. Secondary data analysis of patient-nurse verbal communication data in home healthcare settings. The data were collected from one of the largest home healthcare organizations in the United States. We used 23 audio recordings of patient-nurse communications from 15 patients. The audio recordings were transcribed verbatim and manually annotated for health problems (e.g., circulation, skin, pain) indicated in the Omaha System Classification scheme. Synthetic data of patient-nurse communication were generated using the in-context learning prompting method, enhanced by chain-of-thought prompting to improve the automatic annotation performance. Machine learning classifiers were applied to three training datasets: real-world communication, synthetic communication, and real-world communication augmented by synthetic communication. Average F1 scores improved from 0.62 to 0.63 after training data were augmented with synthetic communication. The largest increase was observed using the XGBoost classifier where F1 scores improved from 0.61 to 0.64 (about 5% improvement). When trained solely on either real-world communication or synthetic communication, the classifiers showed comparable F1 scores of 0.62-0.61, respectively. Integrating synthetic data improves machine learning classifiers' ability to identify health problems in home healthcare, with performance comparable to training on real-world data alone, highlighting the potential of synthetic data in healthcare analytics. This study demonstrates the clinical relevance of leveraging synthetic patient-nurse communication data to enhance machine learning classifier performances to identify health problems in home healthcare settings, which will contribute to more accurate and efficient problem identification and detection of home healthcare patients with complex health conditions.

Integrating Machine Learning and Feature Extraction for Islanding Detection in Grid-Connected Photovoltaic Systems: A Hybrid Intelligent Approacha

Introduction: In recent years, the integration of renewable energy sources, particularly Photovoltaic (PV) systems, into the grid has garnered considerable attention. However, the distributed nature of these grid-integrated PV systems has introduced challenges concerning grid faults and maintenance. Method: This paper aims to present a pioneering approach to augment the monitoring of gridintegrated PV systems by integrating intelligent methods, specifically machine learning and feature extraction techniques. The primary focus of this approach is on islanding detection, which involves promptly identifying grid faults or maintenance challenges and initiating the grid's transition to an isolated mode of operation. To accomplish this, an intelligent signaling method is employed, capitalizing on the capabilities of Distributed Generation (DG) networks. By recording critical signals such as voltage, current, and frequency at common coupling points, fault conditions can be accurately detected. Signals obtained from the grid are subjected to wavelet transformation to extract pertinent information that characterizes fault conditions. These extracted features are then utilized as inputs to machine learning methods, facilitating the proposal of intelligent islanding scenarios. To assess the efficacy of the proposed approach, simulations are conducted on a grid-connected PV system. The recorded signals are meticulously analyzed, and the extracted features are employed to train machine learning models. The performance of these models is evaluated based on their ability to detect fault conditions and initiate appropriate islanding scenarios accurately. Result: The results obtained demonstrate the immense potential of the proposed approach in bolstering the monitoring of grid-integrated PV systems. Conclusion: By synergizing machine learning techniques with feature extraction and intelligent signaling methods with the KNN-Confusion Matrix, all predicted labels match the true labels, resulting in a 100% accuracy. The detection of grid faults and maintenance challenges can be substantially improved, thereby fostering more efficient and dependable operation of these systems.

Detection of disease-specific signatures in B cell repertoires of lymphomas using machine learning.

The classification of B cell lymphomas-mainly based on light microscopy evaluation by a pathologist-requires many years of training. Since the B cell receptor (BCR) of the lymphoma clonotype and the microenvironmental immune architecture are important features discriminating different lymphoma subsets, we asked whether BCR repertoire next-generation sequencing (NGS) of lymphoma-infiltrated tissues in conjunction with machine learning algorithms could have diagnostic utility in the subclassification of these cancers. We trained a random forest and a linear classifier via logistic regression based on patterns of clonal distribution, VDJ gene usage and physico-chemical properties of the top-n most frequently represented clonotypes in the BCR repertoires of 620 paradigmatic lymphoma samples-nodular lymphocyte predominant B cell lymphoma (NLPBL), diffuse large B cell lymphoma (DLBCL) and chronic lymphocytic leukemia (CLL)-alongside with 291 control samples. With regard to DLBCL and CLL, the models demonstrated optimal performance when utilizing only the most prevalent clonotype for classification, while in NLPBL-that has a dominant background of non-malignant bystander cells-a broader array of clonotypes enhanced model accuracy. Surprisingly, the straightforward logistic regression model performed best in this seemingly complex classification problem, suggesting linear separability in our chosen dimensions. It achieved a weighted F1-score of 0.84 on a test cohort including 125 samples from all three lymphoma entities and 58 samples from healthy individuals. Together, we provide proof-of-concept that at least the 3 studied lymphoma entities can be differentiated from each other using BCR repertoire NGS on lymphoma-infiltrated tissues by a trained machine learning model.

A probabilistic approach to training machine learning models using noisy data

Machine learning (ML) models are increasingly popular in environmental and hydrologic modeling, but they typically contain uncertainties resulting from noisy data (erroneous or outlier data). This paper presents a novel probabilistic approach that combines ML and Markov Chain Monte Carlo simulation to (1) detect and underweight likely noisy data, (2) develop an approach capable of detecting noisy data during model deployment, and (3) interpret the reasons why a data point is deemed noisy to help heuristically distinguish between outliers and erroneous data. The new algorithm recognizes that there is no unique way to split the training data into noisy and clean data, and thus produces an ensemble of plausible splits. The algorithm successfully detected noisy data in synthetic benchmark problems with varying complexity and a real-world public supply water withdrawal dataset. The algorithm is generic and flexible, making it suitable for application across a broad range of hydrologic and environmental disciplines.

Concomitant Procedures, Black Race, Male Sex, and General Anesthesia Show Fair Predictive Value for Prolonged Rotator Cuff Repair Operative Time: Analysis of the National Quality Improvement Program Database Using Machine Learning

PurposeThe purpose of this study is to develop machine learning models using the American College of Surgeons National Quality Improvement Program (ACS-NSQIP) database to predict prolonged operative time (POT) for rotator cuff repair (RCR). Furthermore, this study aims to use the trained machine learning (ML) models, cross-referenced with traditional multivariate logistic regression (MLR), to determine the key perioperative variables that may predict POT for RCR. MethodsData were obtained from a large, national database (NSQIP) from 2021. Patients with unilateral RCR procedures were included. Demographic, preoperative, and operative variables were analyzed. A multivariable logistic regression (MLR) model and various other machine learning techniques, including random forest (RF) and artificial neural network (ANN), were compared using area under the curve (AUC), calibration, Brier score, and decision curve analysis. Feature importance was identified from the overall best-performing model. ResultsA total of 6,690 patients met inclusion criteria. The random forest (RF) ML model had the highest AUC upon internal validation (0.706) and the lowest Brier score (0.15), outperforming the other models. The RF model also demonstrated strong performance upon assessment of the calibration curves (Slope = 0.86, Intercept = 0.08) and decision curve analysis. The model identified concomitant procedure, specifically labral repair and biceps tenodesis, as the most important variable for determining POT, followed by age <30 years, Black or African American race, male sex, and general anesthesia. ConclusionsDespite the advanced machine learning models used in this study, the NSQIP dataset was only able to fairly predict POT following RCR. The RF model identified concomitant procedures, specifically labral repair and biceps tenodesis, as the most important variables for determining POT. Additionally, demographic factors such as age <30 years, Black race, and general anesthesia were significant predictors. While male sex was identified as important in the RF model, the MLR model indicated that its predictive value is primarily in conjunction with specific procedures like biceps tenodesis and subacromial decompression.

Quantifying inconsistencies in the Hamburg Sign Language Notation System

The advent of machine learning (ML) has significantly advanced the recognition and translation of sign languages, bridging communication gaps for hearing-impaired communities. At the heart of these technologies is data labeling, crucial for training ML algorithms on a huge amount of consistently labeled data to achieve models that generalize well. The adoption of language-agnostic annotations is essential to connect different sign languages, as single-language databases often provide limited lexicon examples, insufficient for training robust ML algorithms. This study critically examines the Hamburg Sign Language Notation System (HamNoSys), which describes the signer’s initial position and body movements, in contrary to the meanings of glosses. Despite HamNoSys’s utility in standardizing transcriptions across various sign languages, our investigation uncovers inconsistencies within HamNoSys that may negatively impact the development of accurate and reliable ML models. By analyzing HamNoSys labels across five sign languages, we identified a lack of standardized annotation procedures and the complexities within HamNoSys that introduce biases and errors. Our findings underscore the urgent need for unified, standardized data annotation guidelines to enhance the accuracy and efficiency of sign language recognition technologies. This research highlights the importance of addressing annotation challenges and advocates for a comprehensive, diversified database to improve the generalization of ML models.

SoK: Wildest Dreams: Reproducible Research in Privacy-preserving Neural Network Training

Machine Learning (ML), addresses a multitude of complex issues in multiple disciplines, including social sciences, finance, and medical research. ML models require substantial computing power and are only as powerful as the data utilized. Due to the high computational cost of ML methods, data scientists frequently use Machine Learning-as-a-Service (MLaaS) to outsource computation to external servers. However, when working with private information, like financial data or health records, outsourcing the computation might result in privacy issues. Recent advances in Privacy-Preserving Techniques (PPTs) have enabled ML training and inference over protected data through the use of Privacy-Preserving Machine Learning (PPML). However, these techniques are still at a preliminary stage and their application in real-world situations is demanding. In order to comprehend the discrepancy between theoretical research suggestions and actual applications, this work examines the past and present of PPML, focusing on Homomorphic Encryption (HE) and Secure Multi-party Computation (SMPC) applied to ML. This work primarily focuses on the ML model's training phase, where maintaining user data privacy is of utmost importance. We provide a solid theoretical background that eases the understanding of current approaches and their limitations. We also provide some preliminaries of SMPC, HE, and ML. In addition, we present a systemization of knowledge of the most recent PPML frameworks for model training and provide a comprehensive comparison in terms of the unique properties and performances on standard benchmarks. Also, we reproduce the results for some of the surveyed papers and examine at what level existing works in the field provide support for open science. We believe our work serves as a valuable contribution by raising awareness about the current gap between theoretical advancements and real-world applications in PPML, specifically regarding open-source availability, reproducibility, and usability.

Efficient Removal of Greenhouse Gases: Machine Learning-Assisted Exploration of Metal-Organic Framework Space.

Global warming is a crisis that humanity must face together. With greenhouse gases (GHGs) as the main factor causing global warming, the adoption of relevant processes to eliminate them is essential. With the advantages of high specific surface area, large pore volume, and tunable synthesis, metal-organic frameworks (MOFs) have attracted much attention in GHG storage, adsorption, separation, and catalysis. However, as the pool of MOFs expands rapidly with new syntheses and discoveries, finding a suitable MOF for a particular application is highly challenging. In this regard, high-throughput computational screening is considered the most effective research method for screening a large number of materials to discover high-performance target MOFs. Typically, high-throughput computational screening generates voluminous and multidimensional data, which is well suited for machine learning (ML) training to improve the screening efficiency and explore the relationships between the multidimensional data in depth. This Review summarizes the general process and common methods for using ML to screen MOFs in the field of GHG removal. It also addresses the challenges faced by ML in exploring the MOF space and potential directions for the future development of ML for MOF screening. This aims to enhance the understanding of the integration of ML and MOFs in various fields and broaden the application and development ideas of MOFs.

Deep Learning of a 200-Member Ensemble with a Limited Historical Training to Improve the Prediction of Extreme Precipitation Events

Abstract This study introduces a deep learning (DL) scheme to generate reliable and skillful probabilistic quantitative precipitation forecasts (PQPFs) in a postprocessing framework. Enhanced machine learning model architecture and training mechanisms are proposed to improve the reliability and skill of PQPFs while permitting computationally efficient model fitting using a short training dataset. The methodology is applied to postprocessing of 24-h accumulated PQPFs from an ensemble forecast system recently introduced by the Center for Western Weather and Water Extremes (CW3E) and for lead times from 1 to 6 days. The ensemble system was designed based on a high-resolution version of the Weather Research and Forecasting (WRF) Model, named West-WRF, to produce a 200-member ensemble in near–real time (NRT) over the western United States during the boreal cool seasons to support Forecast-Informdayed Reservoir Operations (FIRO) and studies of prediction of heavy-to-extreme events. Postprocessed PQPFs are compared with those from the raw West-WRF ensemble, the operational Global Ensemble Forecast System version 12 (GEFSv12), and the ensemble from the European Centre for Medium-Range Weather Forecasts (ECMWF). As an additional baseline, we provide PQPF verification metrics from a recently developed neural network postprocessing scheme. The results demonstrate that the skill of postprocessed forecasts significantly outperforms PQPFs and deterministic forecasts from raw ensembles and the recently developed algorithm. The resulting PQPFs broadly improve upon the reliability and skill of baselines in predicting heavy-to-extreme precipitation (e.g., &gt;75 mm) across all lead times while maintaining the spatial structure of the high-resolution raw ensemble.