Linear Regressor Research Articles

Earthquake Early Warning System for Structural Drift Prediction Using Machine Learning and Linear Regressors

In this work, we explored the feasibility of predicting the structural drift from the first seconds of P-wave signals for On-site Earthquake Early Warning (EEW) applications. To this purpose, we investigated the performance of both linear least square regression (LSR) and four non-linear machine learning (ML) models: Random Forest, Gradient Boosting, Support Vector Machines and K-Nearest Neighbors. Furthermore, we also explore the applicability of the models calibrated for a region to another one. The LSR and ML models are calibrated and validated using a dataset of ∼6,000 waveforms recorded within 34 Japanese structures with three different type of construction (steel, reinforced concrete, and steel-reinforced concrete), and a smaller one of data recorded at US buildings (69 buildings, 240 waveforms). As EEW information, we considered three P-wave parameters (the peak displacement, Pd, the integral of squared velocity, IV2, and displacement, ID2) using three time-windows (i.e., 1, 2, and 3 s), for a total of nine features to predict the drift ratio as structural response. The Japanese dataset is used to calibrate the LSR and ML models and to study their capability to predict the structural drift. We explored different subsets of the Japanese dataset (i.e., one building, one single type of construction, the entire dataset. We found that the variability of both ground motion and buildings response can affect the drift predictions robustness. In particular, the predictions accuracy worsens with the complexity of the dataset in terms of building and event variability. Our results show that ML techniques perform always better than LSR models, likely due to the complex connections between features and the natural non-linearity of the data. Furthermore, we show that by implementing a residuals analysis, the main sources of drift variability can be identified. Finally, the models trained on the Japanese dataset are applied the US dataset. In our application, we found that the exporting EEW models worsen the prediction variability, but also that by including correction terms as function of the magnitude can strongly mitigate such problem. In other words, our results show that the drift for US buildings can be predicted by minor tweaks to models.

Earthquake Early Warning System for Structural Drift Prediction Using Machine Learning and Linear Regressors

Earthquake Early Warning System for Structural Drift Prediction Using Machine Learning and Linear Regressors

Gait Phases Blended Control for Enhancing Transparency on Lower-Limb Exoskeletons

A major challenge in the design and control of exoskeletons is the preservation of the user.s natural behavior when interacting with these machines. From this point of view, one of the most important features is the transparency of the exoskeleton. An ideally transparent exoskeleton follows the user's movements without interaction forces. This is the goal of many control algorithms proposed in the literature. Traditional algorithms are based on finite state machines and are affected by assistive torque discontinuity problems in the transitions between phases. State-of-the-art methods approach this problem by imposing a smooth transition that does not account for variable walking speed. In this work, the authors propose an innovative control algorithm for a lower-limb exoskeleton. The proposed control aims at solving the torque discontinuity problem, without requiring a smooth transitions strategy. The proposed control algorithm continuously blends the output of two independent single stance dynamic models, by weighting the contribution of each stance model to the total assistance based on the gait phase. A linear regressor is used to produce the weights, and it requires a brief user-specific calibration. Results showed a significant reduction of interaction forces, and a longer stride length when compared to two finite-state-machine-based controls at two speeds on the treadmill and one self-selected-speed in an overground walk.

Prediction and Analysis of Gold Prices using Ensemble Machine Learning Algorithms

In this article, we used historical time series data up to the current day gold price. In this study of predicting gold price, we consider few correlating factors like silver price, copper price, standard, and poor’s 500 value, dollar-rupee exchange rate, Dow Jones Industrial Average Value. Considering the prices of every correlating factor and gold price data where dates ranging from 2008 January to 2021 February. Few algorithms of machine learning are used to analyze the time-series data are Random Forest Regression, Support Vector Regressor, Linear Regressor, ExtraTrees Regressor and Gradient boosting Regression. While seeing the results the Extra Tree Regressor algorithm gives the predicted value of gold prices more accurately.

Analyzing the performance of segmented trajectory reconstruction of lower limb movements from EEG signals with combinations of electrodes, gaps, and delays

ObjectiveBrain–machine interfaces have performed continuous trajectory reconstruction of limb movements from brain signals relying on multiple linear regression. Most reported approaches deal with the reconstruction of the entire motion trajectory using a single regression and choosing its parameters arbitrarily. This study proposes the reconstruction of trajectories dividing them on phases and proposing a regression for each phase. The parameters for each regressor were selected according to their influence in the performance of the trajectory reconstruction. MethodsIsotonic flexions and extensions of the hip and knee were segmented in phases and a linear regressor was proposed for each phase. The number of electrodes, gaps, and delays of these regressors were selected using an exhaustive comprehensive search to improve the correlation coefficient, normalized root mean square error, and signal-to-noise ratio of the reconstructed trajectory. ResultsThe most frequent electrodes in the trajectory reconstructions between subjects with good performance were electrodes Fz, C3, C4, Cz, P3, P4, and Pz. The combination of a delay of 3 s with 9 gaps gave better performances in general. ConclusionsIn this study it was appreciated that the electrodes that mainly contribute to the trajectory reconstruction are located around the mid-scalp. Also, it was appreciated that the information of movement in the electrical activity is located around 3 s before the movement. SignificanceThe set of parameters obtained could be helpful to define a limited numbers of electrodes. The delay and number of data samples could also be helpful to establish better experimental setups.

Learning To Scale Mixed-Integer Programs

Many practical applications require the solution of numerically challenging linear programs (LPs) and mixed integer programs (MIPs). Scaling is a widely used preconditioning technique that aims at reducing the error propagation of the involved linear systems, thereby improving the numerical behavior of the dual simplex algorithm and, consequently, LP-based branch-and-bound. A reliable scaling method often makes the difference whether these problems can be solved correctly or not. In this paper, we investigate the use of machine learning to choose at the beginning of the solution process between two common scaling methods: Standard scaling and Curtis-Reid scaling. The latter often, but not always, leads to a more robust solution process, but may suffer from longer solution times. Rather than training for overall solution time, we propose to use the attention level of a MIP solution process as a learning label. We evaluate the predictive power of a random forest approach and a linear regressor that learns the (square-root of the) difference in attention level. It turns out that the resulting classification not only reduces various types of numerical errors by large margins, but it also improves the performance of the dual simplex algorithm. The learned model has been implemented within the FICO Xpress MIP solver and it is used by default since release 8.9, May 2020, to determine the scaling algorithm Xpress applies before solving an LP or a MIP.

Machine learning regression and classification algorithms utilised for strength prediction of OPC/by-product materials improved soils

In this study, stand-alone machine (ML) models (Bayesian regressor (BLR), least square linear regressor (REG), artificial neural networks (ANN), and logistic regression (LR)), tree-ensemble ML models (boosted decision tree (BDT), random decision forest (RDF) decision jungle (DJ)) and meta-ensemble ML models (voting (VE) and stacking (SE)) are applied to predict the strength of different soils improved by part-substitution of OPC with PFA and GGBS in various combinations and proportions. Multiclass elements of these proposed ML models are also deployed to provide analysis across multiple cross-validation methods. Results of regression analysis indicated higher statistical variance of OPC-substituted predictor variables compared to soils improved by OPC alone when using both stand-alone and tree-based algorithms. On average, the REG model produced strength predictions with higher accuracy (RMSE of 0.39 and R2 of 0.86) compared to ANN (RMSE of 0.44 and R2 of 0.82), but with comparatively lower accuracy compared to tree-based models (average RMSE of 0.33 and R2 of 0.90) and meta-ensemble models (average RMSE of 0.06 and R2 of 0.91). For ML classification, multiclass neural network algorithm (mANN) produced higher accuracy (0.78), precision (0.67) and rate of recall (0.67) compared to tree-based models but fell short to meta-ensemble models (average accuracy of 0.80, precision of 0.70 and recall of 0.71). Diagnostic tests across different validation methods indicated better performance of the VE model compared to its SE ML counterpart when adopting the train-validation split technique. Overall, the ensemble methods were more versatile on regression and multiclass classification problems because they aggregated multiple learners to provide robust predictions.

Prediction of Phakic Intraocular Lens Vault Using Machine Learning of Anterior Segment Optical Coherence Tomography Metrics

To compare the achieved vault using the conventional manufacturer's nomogram and the predicted vault using machine learning, in a large cohort of eyes undergoing posterior chamber phakic intraocular lens (EVO implantable collamer lens [ICL]; STAAR Surgical) implantation. Reliability and validity assessment and comparison. Our study comprised a total of 1,745 eyes of 1,745 consecutive patients (mean age ± standard deviation, 26.2 ± 6.8 years) undergoing ICL implantation. At 1 month postoperatively, we quantitatively measured the actual vault, and compared it with the predicted vault using machine leaning of anterior segment optical coherence tomography metrics. All machine learning methods, such as support vector regressor (SVR), gradient boost regressor (GBR), random forest regressor (RFR), and linear regressor (LR), showed significantly less mean absolute error and higher percentages of eyes within 50-200 µm of the targeted ICL vault than the conventional nomogram (P < .001). The RFR provided the lowest mean absolute errors and the highest percentages of eyes within 50 to 200 µm, followed by the GBR, the LR, and the SVR (P < .01). Machine learning of the preoperative anterior segment optical coherence tomography metrics, especially the RFR, provided significantly higher predictability of the ICL vault than the conventional manufacturer's nomogram, suggesting that it will become an aid for predicting the ICL vault and subsequently selecting the proper ICL size in daily practice.

Machine learning-assisted production data analysis in liquid-rich Duvernay Formation

The production of gas and oil from the unconventional tight and shale reservoirs is the outcome through a series of cooperative efforts of drilling, completion, and production operations. This study aims to optimize these operations to enhance the well productivity and oil recovery, and ultimately to reduce the development footprint on the level of individual wells. More specifically, a comprehensive data set is collected and analyzed for the Duvernay reservoir, including geology, drilling, completion, production operations, and production data. A customized stacked model is created to train production models with an extreme gradient boosting regressor as the base model and linear regressor as the meta model. The models achieve robust predictive ability with a determination coefficient of up to 0.80. The Shapley values reveal that the producing time, condensate/gas ratio, and the completion section length are the most important features to the early time production. The Bayesian optimization method is adopted to optimize the production using the trained models. This study shows the potential of the machine learning approach to model oil and gas production and provides insights for optimizing production in the tight and shale reservoirs.

Time-capturing Dynamic Graph Embedding for Temporal Linkage Evolution

Dynamic graph embedding learns representation vectors for vertices and edges in a graph that evolves over time. We aim to capture and embed the evolution of vertices' temporal connectivity. Existing work studies the vertices' dynamic connection changes but neglects the time it takes for edges to evolve, failing to embed temporal linkage information into the evolution of the graph. To capture vertices' temporal linkage evolution, we model dynamic graphs as a sequence of snapshot graphs, appending the respective timespans of edges (ToE). We co-train a linear regressor to embed ToE while inferring a common latent space for all snapshot graphs by a matrix-factorization-based model to embed vertices' dynamic connection changes. Vertices' temporal linkage evolution is captured as their moving trajectories within the common latent representation space. Our embedding algorithm converges quickly with our proposed training methods, which is very time efficient and scalable. Extensive evaluations on several datasets show that our model can achieve significant performance improvements, i.e. 22.98% on average across all datasets, over the state-of-the-art baselines in the tasks of vertex classification, static and time-aware link prediction, and ToE prediction.

Development of a Machine Learning based model for Damage Detection, Localization and Quantification to extend Structure Life

Structural Health Monitoring (SHM) has been researched for a long time and continues to be an active area of research. Initial work on SHM involved identification of hand-crafted features and predictive models relied on statistical methods. The recent improvements in computing capabilities, coupled with better integration of sensor data, has led to the emergence of more effective techniques in terms of scalability and predictive power. Machine learning offers a solution through automatic feature extraction algorithms, and scalable and noise robust models. Convolutional Neural Networks (CNN) have been used as state-of-art classifiers for images as well as for text. This paper proposes the use of the monitored structure’s transmissibility functions for the structure under observation, which can be fed into a novel composite architecture consisting of Deep CNN followed by multivariate linear regressors to detect, localize, and quantify the damage extent in a system. The proposed method was tested on the Los Alamos’ Eight degree-of-freedom (DOF) structure, and the Structural Beam Data from Laboratory of Mechanical Vibrations and Rotor Dynamics, University of Chile. This study on damage localization and quantification can be leveraged to comment on the safety and soundness of the structure under inspection and can help in making more informed inferences. It is expected that, in general, this will lead to extended structure life, which not only improves the resource utilization in terms of structure maintenance and its longevity but also decreases the carbon footprint and capital expenditure.

Parametric Identification Method for an Absorption Air Conditioning Parabolic Trough Collector Solar Plant

In this work is established a parametric identification method for an absorption air conditioning solar plant. A scaled thermal plant, consisting of a thermal capacitor and a flow line that acts as a capacitor and thermal energy radiator is used. As the mathematical model of the scaled plant is structurally identical to that of the solar plant the first is used to determine the methodology that can be used later for the identification of the PTC solar plant. Parametric identification is a necessary step that allows to determine the unknown parameters of the mathematical model of any solar/thermal plant. This model then can be used to analyze the plant characteristics and design an appropriate control algorithm. Although the system model is nonlinear it can be expressed in the form of a linear regressor in the parameters. This permits to use the least squares method as the identification method. The method is applied to the thermal plant to identify the useful form that the covariance matrix and excitation signals should have to ensure that when applied to the solar plant its unknown parameters can be properly estimated. Once the solar plant parameters are properly estimated model can be used to analyze and simulate the operation of the absorption air conditioning system.

Prediction study on critical temperature (C) of different atomic numbers superconductors (both gaseous/solid elements) using machine learning techniques

Superconductors has been comprehensively studied as huge research effort taking into consideration of actuality that its invention ruins a theme of passionate discuss once its discovery completed. The standard behind this paper is the study about explaining as well as scrutinizing how different regression methods are used for predicting the superconducting critical temperature Tc from Superconductors database collected from Kaggle dataset source. Mainly, regression models such as linear Regressor, decision tree Regressor, Lasso Lars Regressor, Bayesian Ridge Regressor, XGB Regressor, and Huber Regressor have been studied to forecast critical temperature in superconductor materials.

Comparison of Machine Learning Methods in Stochastic Skin Optical Model Inversion

In this study, we compare six different machine learning methods in the inversion of a stochastic model for light propagation in layered media, and use the inverse models to estimate four parameters of the skin from the simulated data: melanin concentration, hemoglobin volume fraction, and thicknesses of epidermis and dermis. The aim of this study is to determine the best methods for stochastic model inversion in order to improve current methods in skin related cancer diagnostics and in the future develop a non-invasive way to measure the physical parameters of the skin based partially on the results of the study. Of the compared methods, which are convolutional neural network, multi-layer perceptron, lasso, stochastic gradient descent, and linear support vector machine regressors, we find the convolutional neural network to be the most accurate in the inversion task.

Adaptive control systems with linear regressor and parameter identification algorithm applied to a magnetic levitation system

Conventional regulators or controllers are used regularly in control engineering, however, there are limitations to their use. In this document we develop the essential mathematical concepts and expressions in the study of adaptive control techniques. To do this, we will initially make a brief deduction of the equations that are identified in a linear regressor control system, and also for the case of the parameter identification algorithm. Next, we will apply this control technique in a non-linear state space system for a magnetic levitation system, allowing us to conclude, among other things, that this technique makes the control more robust.

Comparative Analysis of Regression Learning Methods for Estimation of Energy Performance of Residential Structures

Energy efficiency is a top priority for private and commercial buildings. This study evaluates the performance of six regression learning methods, including Linear Regressor, MLP Regressor, RBF Regressor, SVM Regressor, Gaussian Processes, and ANFIS Regressor to predict the heating and cooling loads of residential buildings. 768 buildings were considered and analyzed based on the influential parameters, such as relative density, surface area, wall area, roof area, overall height, orientation, glazing area, and glazing area distribution for predicting heating load and cooling load. Three statistical criteria such as correlation coefficient (R), mean absolute error (MAE) and root mean square error (RMSE) were used to assess the potential of the regression methods used in this study. The best estimation results were obtained with the ANFIS regression model, with R of 0.998, MAE of 0.46 and RMSE of 0.68 for HL; and with R of 0.990, MAE of 1.26 and RMSE of 1.60 for CL.

Reservoir trophic state confounds flow-ecology relationships in regulated streams

Cultural eutrophication and river regulation have been identified as two of the most pressing threats to global freshwater biodiversity. However, we know little about their combined ecological effects, raising questions over biomonitoring practices that typically consider such stressors in isolation. To address this inconsistency, we examined a decade-long dataset of macroinvertebrate samples and environmental data collected downstream of three reservoirs spanning a broad gradient of trophic states, from mesotrophic to hypereutrophic. We analysed the responses of routine macroinvertebrate biomonitoring indices and community composition to antecedent flow, temperature and water quality, including parameters associated with eutrophication (total phosphorous, nitrate, nitrite, ammonia, chlorophyll a). Multi-model comparisons of linear regressor combinations, variation partitioning and distance-based redundancy analyses all revealed shifts in the relative significance of flow and water quality predictors across the trophic state gradient. At the mesotrophic site biomonitoring indices and community composition were most sensitive to seasonal flow variability– particularly high-flow conditions– whereas in the hypereutrophic system stronger associations with nutrient concentrations emerged, notably nitrite and nitrate. Patterns at the eutrophic site were broadly intermediate between these, with significant biotic responses to antecedent flows mediated by water quality. Based on these results we suggest that nutrient regimes should be regarded as an integral component of environmental flows science. We therefore call on practitioners to look beyond the stressor-specific indices widely used to assess ecological status in rivers to consider the interactive effects of flow and water quality.

A comparative study of human facial age estimation: handcrafted features vs. deep features

In recent times, the topic of human facial age estimation attracted much attention. This is due to its ability to improve biometrics systems. Recently, several applications that are based on the demographic attributes estimation have been developed. These include law enforcement, re-identification in videos, planed marketing, intelligent advertising, social media, and human-computer interaction. The main contributions of the paper are as follows. Firstly, it extends some handcrafted models that are based on the Pyramid Multi Level (PML) face representation. Secondly, it evaluates the performance of two different kinds of features that are handcrafted and deep features. It compares handcrafted and deep features in terms of accuracy and computational complexity. The proposed scheme of study includes the following three main steps: 1) face preprocessing; 2) feature extraction (two different kinds of features are studied: handcrafted and deep features); 3) feeding the obtained features to a linear regressor. In addition, we investigate the strengths and weaknesses of handcrafted and deep features when used in facial age estimation. Experiments are run on three public databases (FG-NET, PAL and FACES). These experiments show that both handcrafted and deep features are effective for facial age estimation.

Localizing confined epileptic foci in patients with an unclear focus or presumed multifocality using a component-based EEG-fMRI method.

Precise localization of epileptic foci is an unavoidable prerequisite in epilepsy surgery. Simultaneous EEG-fMRI recording has recently created new horizons to locate foci in patients with epilepsy and, in comparison with single-modality methods, has yielded more promising results although it is still subject to limitations such as lack of access to information between interictal events. This study assesses its potential added value in the presurgical evaluation of patients with complex source localization. Adult candidates considered ineligible for surgery on account of an unclear focus and/or presumed multifocality on the basis of EEG underwent EEG-fMRI. Adopting a component-based approach, this study attempts to identify the neural behavior of the epileptic generators and detect the components-of-interest which will later be used as input in the GLM model, substituting the classical linear regressor. Twenty-eightsets interictal epileptiform discharges (IED) from nine patients were analyzed. In eight patients, at least one BOLD response was significant, positive and topographically related to the IEDs. These patients were rejected for surgery because of an unclear focus in four, presumed multifocality in three, and a combination of the two conditions in two. Component-based EEG-fMRI improved localization in five out of six patients with unclear foci. In patients with presumed multifocality, component-based EEG-fMRI advocated one of the foci in five patients and confirmed multifocality in one of thepatients. In seven patients, component-based EEG-fMRI opened new prospects for surgery and in two of these patients, intracranial EEG supported the EEG-fMRI results. In these complex cases, component-based EEG-fMRI either improved source localization or corroborated a negative decision regarding surgical candidacy. As supported by the statistical findings, the developed EEG-fMRI method leads to a more realistic estimation of localization compared to the conventional EEG-fMRI approach, making it a tool of high value in pre-surgical evaluation of patients with refractory epilepsy. To ensure proper implementation, we have included guidelines for the application of component-based EEG-fMRI in clinical practice.

A Comparative Analysis for Air Quality Estimation from Traffic and Meteorological Data

Air pollution in urban regions remains a crucial subject of study, given its implications on health and environment, where much effort is often put into monitoring pollutants and producing accurate trend estimates over time, employing expensive tools and sensors. In this work, we study the problem of air quality estimation in the urban area of Milan (IT), proposing different machine learning approaches that combine meteorological and transit-related features to produce affordable estimates without introducing sensor measurements into the computation. We investigated different configurations employing machine and deep learning models, namely a linear regressor, an Artificial Neural Network using Bayesian regularization, a Random Forest regressor and a Long Short Term Memory network. Our experiments show that affordable estimation results over the pollutants can be achieved even with simpler linear models, therefore suggesting that reasonably accurate Air Quality Index (AQI) measurements can be obtained without the need for expensive equipment.