Power system transfer learning to identify event types with or without event labels

We propose a novel unsupervised transfer learning framework that utilises unlabelled auxiliary data to quantify and select the most relevant transferrable knowledge for recognising a target object class from the background given very limited training target samples. Unlike existing transfer learning techniques, our method does not assume that auxiliary data are labelled, nor the relationships between target and auxiliary classes are known a priori. Our unsupervised transfer learning is formulated by a novel kernel adaptation transfer (KAT) learning framework, which aims to (a) extract general knowledge about how more structured objects are visually distinctive from cluttered background regardless object class, and (b) more importantly, perform selective transfer of knowledge extracted from the auxiliary data to minimise negative knowledge transfer suffered by existing methods. The effectiveness and efficiency of the proposed approach is demonstrated by performing one-class object recognition (object vs. background) task using the Caltech256 dataset.

Transfer learning techniques try to transfer knowledge from previous tasks to a new target task with either fewer training data or less training than traditional machine learning techniques. Since transfer learning cares more about relatedness between tasks and their domains, it is useful for handling massive data, which are not labeled, to overcome distribution and feature space gaps, respectively. In this paper, we propose a new task selection algorithm in an unsupervised transfer learning domain, called as Task Selection Machine (TSM). It goes with a key technical problem, i.e., feature mapping for heterogeneous feature spaces. An extended feature method is applied to feature mapping algorithm. Also, TSM training algorithm, which is main contribution for this paper, relies on feature mapping. Meanwhile, the proposed TSM finally meets the unsupervised transfer learning requirements and solves the unsupervised multi-task transfer learning issues conversely.

Data is one of the most important limiting factors of deep machine learning (ML) model in drilling applications. Though a big size of historical data can be available, high-quality cleaned and labeled data is usually limited. In this case study, we show that with limited labeled data, physics-based data augmentation combined with unsupervised learning significantly improves both stability and accuracy in bit wear ML model. It provides a pathway to overcome labeled data shortage and field data quality limitations. Labeled bit wear data is usually limited because only the final bit dull state can be labeled using dull photos for the entire drilling distance. To overcome this difficulty, an encoder-decoder unsupervised ML framework based on Bi-directional LSTM architecture is first applied to the data of entire drilling distance to extract and maximize data learnings. Then, a physics-based wear estimator is implemented in the learned latent space to augment labeled wear dataset, guided by true wear labels and offset-well data. Weighting factor in loss function is applied to optimize augmented and true datasets in final supervised learning step. The proposed real-time bit wear model is built on a combination of physics-based data augmentation and unsupervised data learning method. The model is applied on multiple field bit runs. Results show that by implementing the unsupervised data learnings only, the prediction accuracy is improved by 30% compared to the baseline ML model. By combining physics-based augmentation, the accuracy is further improved by 10%. More importantly, adding physics-based data augmentation significantly reduces prediction variance and unphysical wear outputs, therefore improving prediction stability by more than 30%. It should be noted that the prediction stability of AI/ML model is crucial in real-time application and decision making. The results show physics-based data augmentation not only increases the size of label dataset and prevents model overfitting, but also applies physics-based guidance to the ML model effectively. It is learned weighting factor plays a crucial role in balancing loss contributions from true wear labels and physics-based labels. While low weighting factor of physics-based labels diminishes the augmented data, high weighting factor disrespects the true wear labels leading to a high prediction bias. Overall, the bit wear model study shows physic-based data augmentation combined with unsupervised data learning can effectively improve model accuracy, stability, and overcome labeled data shortage difficulty. The proposed paper shows a case study for the bit wear ML model using a combination of physics-based data augmentation and unsupervised data learning. While labeled data is one of the major challenges of ML models in many drilling applications, this study provides a pathway to improve both accuracy and stability of deep ML models with limited labeled data.

This paper proposes a predictive techno-economic analysis in terms of voltage stability and cost using regression-based machine learning (ML) models and effectiveness of the analysis is validated. Predictive analysis of a power system is proposed to address the need for faster and accurate analyses that would aid in the operation and control of modern power system. Several methods of analyses including metaheuristic optimization algorithms, artificial intelligence techniques and machine learning algorithms are being developed and used. Predictive ML models for two modified IEEE 14-bus and IEEE-30 bus systems, integrated with renewable energy sources (solar and wind) and reactive power compensative device (STATCOM) are proposed and developed with features that include hour of the day, solar irradiation, wind velocity, dynamic grid price and system load. An hour-wise input database for the model development is generated from monthly average data and hour-wise daily curves with normally distributed standard deviations. The data feasibility tests and output database generation is performed using MATLAB. Linear and higher order polynomial regression models are developed for the 8760hr database using Python 3.0 in JupyterLab and a best-fit predictive ML model is identified by analysing the coefficients of determination. The voltage stability and cost predictive ML models were tested for a 24hr input profile. The results obtained and the comparison with the expected values are furnished. Prediction of the outputs for the test data validate the accuracy of the developed model.

Transfer learning enables prediction of steel corrosion in concrete under natural environments

Nowadays, the increasing energy demand, development of smart grids, and the combination of different energy systems have led to the complexity of power systems. On the other hand, ever-expanding energy consumption, development of industry and technology systems, and high penetration of solar and wind energies have made electricity networks operate in more complex and uncertain conditions. Therefore, analysis of traditional power and energy systems requires physical modeling and extensive numerical computation. To analyze these systems’ behavior, advanced metering and condition monitoring devices and systems are utilized, which generate huge amounts of data. Assessment of these data is approximately impossible by conventional methods and requires powerful data mining procedures. Machine learning, deep learning, and a variety of regression, classification, and clustering algorithms are powerful tools to use in these issues. These procedures can be utilized for load/demand forecasting, demand response evaluation, defect/fault detection in electrical equipment, power system analysis and control, cybersecurity, and renewable energy generation prediction. Understanding the structure and functioning of each learning method is therefore one of the most important issues in the application of them to solve power system problems. In this chapter, we will introduce and discuss selected methods of data mining based on their learning, structure, formulation, mode of operation, and application in power systems. Literature on machine learning and deep learning procedures, train and test process of networked methods, and, finally, applications of each procedure are presented in this chapter.

Systematic Review of Machine Learning in Diagnosis of Myeloproliferative Neoplasia

There has been significant research into reject inference, with several statistical methods and machine learning techniques having been employed to infer the possible repayment behavior of rejected credit applicants. This study proposes a novel three-stage reject inference learning framework using unsupervised transfer learning and three-way decision theory that integrates: (1) the rejected credit sample selection using three-way decision theory, (2) higher-level representations to transfer learning from both accepted and selected rejected credit samples; and (3) credit scoring using the reconstructed accepted credit samples. This method was found to both perform well for reject inference and handle negative transfer learning problems. The numerical results were validated on Chinese credit data, the results from which demonstrated the superiority of the proposed reject inference method for credit risk management applications.

Currently, numerous machine learning (ML) techniques are being applied in the field of renewable energy (RE). These techniques may not perform well if they do not have enough training data. Additionally, the main assumption in most of the ML algorithms is that the training and testing data are from the same feature space and have similar distributions. However, in many practical applications, this assumption is false. Recently, transfer learning (TL) has been introduced as a promising machine-learning framework to mitigate these issues by preparing extra-domain data so that knowledge may be transferred across domains. This learning technique improves performance and avoids the resource expensive collection and labeling of domain-centric datasets; furthermore, it saves computing resources that are needed for re-training new ML models from scratch. Lately, TL has drawn the attention of researchers in the field of RE in terms of forecasting and fault diagnosis tasks. Owing to the rapid progress of this technique, a comprehensive survey of the related advances in RE is needed to show the critical issues that have been solved and the challenges that remain unsolved. To the best of our knowledge, few or no comprehensive surveys have reviewed the applications of TL in the RE field, especially those pertaining to forecasting solar and wind power, load forecasting, and predicting failures in power systems. This survey fills this gap in RE classification and forecasting problems, and helps researchers and practitioners better understand the state of the art technology in the field while identifying areas for more focused study. In addition, this survey identifies the main issues and challenges of using TL for REs, and concludes with a discussion of future perspectives.

Nowadays, the increment of energy demand in the world as well as the development of smart grids and the combination of different types of energy systems have led to the complexity of power systems. On the other hand, ever-expanding energy consumption, development of industry and technology systems, and high penetration of renewable energies have made electricity networks operating in more complex and uncertain conditions. Also, consumers and especially users of sensitive load tend to have access to a reliable and sustainable power supply. Therefore, power producers need a variety of long- and short-term planning methodologies for attaining to sustainable investment, production, and operation. Analysis of traditional power and energy systems requires physical modeling and extensive numerical computation. To analyze the behavior of these systems, advanced metering, and condition monitoring devices and systems are utilized, which generate a huge amount of data. Evaluation of these data is approximately impossible by conventional or numerical methods, and it requires powerful data mining procedures. Regression, classification, and clustering applications of machine learning and deep learning methods are powerful tools to use for dealing with such issues. These procedures can be utilized for load/demand forecasting, renewable energy generation forecasting, demand response evaluation, and power system analysis. Understanding the problem and functioning of each learning methods is, therefore, one of the most important issues in the application of such approaches to solve power system problems. Accordingly, in this chapter, the authors will introduce and discuss selected applications of machine learning and deep learning based on their learning, structure, mode of operation, and application in the load forecasting of power systems. Literature review on machine learning and deep learning applications in load forecasting will be presented in this chapter.

Assessing the quality of groundwater, a primary source of water in many sectors, is of paramount importance. To this end, modeling the geospatial distribution of chemical contaminants in groundwater can be of great utility. Machine learning (ML) models are being increasingly used to overcome the shortcomings of conventional predictive techniques. We report here a systematic review of the nature and utility of various supervised and unsupervised ML models during the past two decades of machine learning groundwater hazard mapping (MLGHM). We identified and reviewed 284 relevant MLGHM journal articles that met our inclusion criteria. Firstly, trend analysis showed (i) an exponential increase in the number of MLGHM studies published between 2004 and 2025, with geographical distribution outlining Iran, India, the US, and China as the countries with the most extensively studied areas; (ii) nitrate as the most studied target, and groundwater chemicals as the most frequently considered category of predictive variables; (iii) that tree-based ML was the most popular model for feature selection; (iv) that supervised ML was far more favored than unsupervised ML (94% vs. 6% of models) with tree-based category—mostly random forest (RF)—as the most popular supervised ML. Secondly, compiling accuracy-based comparisons of ML models from the explored literature revealed that RF, deep learning, and ensembles (mostly meta-model ensembles and boosting ensembles) were frequently reported as the most accurate models. Thirdly, a critical evaluation of MLGHM models in terms of predictive accuracy, along with several other factors such as models’ computational efficiency and predictive power—which have often been overlooked in earlier review studies—resulted in considering the relative merits of commonly used MLGHM models. Accordingly, a flowchart was designed by integrating several MLGHM key criteria (i.e., accuracy, transparency, training speed, number of hyperparameters, intended scale of modeling, and required user’s expertise) to assist in informed model selection, recognising that the weighting of criteria for model selection may vary from problem to problem. Lastly, potential challenges that may arise during different stages of MLGHM efforts are discussed along with ideas for optimizing MLGHM models.

<p>Earthquake Early Warning System (EEW) is a technology that calculates earthquake parameter using P-wave that arrives earlier and warns the expected damage area before the arrival of destructive S wave. Therefore, many countries are operating EEW to mitigate damage from earthquake shaking. Especially an on-site EEW is drawn attention as it can reduce blind zones due to using only a single or minimum station. In the on-site EEW, it is important to quickly predict the seismic intensity, which indicates the degree of ground damage, response of structures and ground shaking felt by people at a given location, rather than information on the magnitude or distance of the earthquake.</p><p>In this study, we suggest a machine learning (ML) model that can directly estimate the seismic intensity scale from initial P-waveforms of three-component acceleration data measured at a single station. We used 1D-Convolutional Neural Networks (1D-CNN), which have been shown good performance in signal processing of speech and medical data which are similar to earthquake signals. K-Net and KiK-net datasets, recorded at stations in Japan, were used for training the ML model. Since the amount of data is enough and all of data are labeled with Japan Meteorological Agency Seismic Intensity Scale (I<sub>JMA</sub>), the datasets were used as training data in this study. The developed model produced fast and accurate results using only the three-component acceleration field data at a single station.</p><p>In order to test applicability of the trained model to the new dataset acquired from other regions, the trained model was applied to the STEAD data which were recorded at stations distributed globally. When the trained model was applied to STEAD data directly, the prediction results were worse than those of K-Net and KiK-net data. The reason is that the characteristics of the ground and waveforms are different depending on the region. Therefore, to solve this problem, transfer learning was applied, and only the parameters of a fully connected layer of pretrained ML model were fine-tuned using small number of both labeled target dataset and training dataset used for pretraining. Moreover, by considering the imbalance problem of the training data for transfer learning, it was able to obtain better prediction results. Ultimately, this study shows the pretrained model with a specific region dataset can provide reasonable prediction of seismic intensity to new dataset acquired from other regions using transfer learning.</p>

Machine learning (ML) models provide more choices to patients with diabetes mellitus (DM) to more properly manage blood glucose (BG) levels. However, because of numerous types of ML algorithms, choosing an appropriate model is vitally important. In a systematic review and network meta-analysis, this study aimed to comprehensively assess the performance of ML models in predicting BG levels. In addition, we assessed ML models used to detect and predict adverse BG (hypoglycemia) events by calculating pooled estimates of sensitivity and specificity. PubMed, Embase, Web of Science, and Institute of Electrical and Electronics Engineers Explore databases were systematically searched for studies on predicting BG levels and predicting or detecting adverse BG events using ML models, from inception to November 2022. Studies that assessed the performance of different ML models in predicting or detecting BG levels or adverse BG events of patients with DM were included. Studies with no derivation or performance metrics of ML models were excluded. The Quality Assessment of Diagnostic Accuracy Studies tool was applied to assess the quality of included studies. Primary outcomes were the relative ranking of ML models for predicting BG levels in different prediction horizons (PHs) and pooled estimates of the sensitivity and specificity of ML models in detecting or predicting adverse BG events. In total, 46 eligible studies were included for meta-analysis. Regarding ML models for predicting BG levels, the means of the absolute root mean square error (RMSE) in a PH of 15, 30, 45, and 60 minutes were 18.88 (SD 19.71), 21.40 (SD 12.56), 21.27 (SD 5.17), and 30.01 (SD 7.23) mg/dL, respectively. The neural network model (NNM) showed the highest relative performance in different PHs. Furthermore, the pooled estimates of the positive likelihood ratio and the negative likelihood ratio of ML models were 8.3 (95% CI 5.7-12.0) and 0.31 (95% CI 0.22-0.44), respectively, for predicting hypoglycemia and 2.4 (95% CI 1.6-3.7) and 0.37 (95% CI 0.29-0.46), respectively, for detecting hypoglycemia. Statistically significant high heterogeneity was detected in all subgroups, with different sources of heterogeneity. For predicting precise BG levels, the RMSE increases with a rise in the PH, and the NNM shows the highest relative performance among all the ML models. Meanwhile, current ML models have sufficient ability to predict adverse BG events, while their ability to detect adverse BG events needs to be enhanced. PROSPERO CRD42022375250; https://www.crd.york.ac.uk/prospero/display_record.php?RecordID=375250.

Systematic literature review of machine learning based software development effort estimation models

This study focuses on using various machine learning (ML) models to evaluate the shear behaviors of ultra-high-performance concrete (UHPC) beams reinforced with glass fiber-reinforced polymer (GFRP) bars. The main objective of the study is to predict the shear strength of UHPC beams reinforced with GFRP bars using ML models. We use four different ML models: support vector machine (SVM), artificial neural network (ANN), random forest (R.F.), and extreme gradient boosting (XGBoost). The experimental database used in the study is acquired from various literature sources and comprises 54 test observations with 11 input features. These input features are likely parameters related to the composition, geometry, and properties of the UHPC beams and GFRP bars. To ensure the ML models' generalizability and scalability, random search methods are utilized to tune the hyperparameters of the algorithms. This tuning process helps improve the performance of the models when predicting the shear strength. The study uses the ACI318M-14 and Eurocode 2 standard building codes to predict the shear capacity behavior of GFRP bars-reinforced UHPC I-shaped beams. The ML models' predictions are compared to the results obtained from these building code standards. According to the findings, the XGBoost model demonstrates the highest predictive test performance among the investigated ML models. The study employs the SHAP (SHapley Additive exPlanations) analysis to assess the significance of each input parameter in the ML models' predictive capabilities. A Taylor diagram is used to statistically compare the accuracy of the ML models. This study concludes that ML models, particularly XGBoost, can effectively predict the shear capacity behavior of GFRP bars-reinforced UHPC I-shaped beams.