Academic literature on the topic 'Flexible regression models'

This article focuses on flexible Bayes regression of epidemiologic data involving pregnancy outcomes. It first provides an overview of finite mixture models and nonparametric Bayes methods before discussing some of the possibilities focusing on gestational age at delivery, DDE and age data from the Longnecker et al. (2001) study. More specifically, it examines how risk of premature delivery is impacted by maternal exposure to the pesticide DDT. The results showcase the use of Bayesian analysis in epidemiological studies that collect continuous health outcomes data, and in which the scientific and clinical interest typically focuses on the relationships between exposures and risks of an abnormal response, corresponding to an observation in the tails of the distribution. The article also highlights the limitations of current standard approaches that can be overcome by means of Bayesian analysis using density regression, mixtures and nonparametric models, as developed and applied in this pregnancy outcome study.

AbstractThe variety of the artificial intelligence and machine learning methods are applied for data analysis in various areas, including the data-rich healthcare domain. However, aiming to improve health care efficiency and use the captured information to improve treatment methods is often hampered by poor quality of medical data collections, as high percent of health data are unstructured and preserved in different systems and formats. In addition, it is not always agreed which methods of artificial intelligence and machine learning perform better in different problem areas, and which computer tools could make their application more convenient and flexible. The chapter provides essential characteristics of methods, traditionally applied in statistics, such as regression analysis, as well as their advanced modifications of logit, probit models, K-means, and Neural networks. The performance of the methods, their analytical power and relevance to the healthcare application domain is illustrated by brief experimental computations for investigation of stroke patient database with the help of several readily available software tools, such as MS Excel, Statistica, Matlab, Google BigQuery ML.

The prediction of medical waste generation is an important task in hospital waste management. This article uses Relevance Vector Machine (RVM), Multivariate Adaptive Regression Spline (MARS) and Minimax Probability Machine Regression (MPMR) for prediction of rate of medical waste generation. Type of hospital, Capacity and Bed Occupancy has been used as inputs of RVM, MARS and MPMR. RVM is a probabilistic bayesian learning framework. MARS builds flexible model by using piecewise linear regressions. MPMR maximizes the minimum probability that future predicted outputs of the regression model will be within some bound of the true regression function. MARS, RVM and MPMR have been used as regression techniques. The results show that the developed RVM, MPMR and MARS give excellent models for determination of rate of medical waste generation.

Tree-based models are popular among regression methods to predict continuous variables. Also, Generalized Linear Models (GLMs) are pretty standard in many statistical applications and provide a generalization to many of the most commonly applied statistical procedures. However, in most regression tree methods, there is only one theoretical model associated for prediction in the final nodes, like multiple linear regression, logistic regressions, polynomial models, Poisson models, among others. We, therefore, propose a new tree method in which we estimate a GLM in each leaf node of the estimated tree including variable selection, new hyperparameters optimization, and tree pruning. Our method, called Generalized linear tree (GLT), has shown to be competitive compared to other well-known regression methods in real datasets, with the advantages and estimation flexibility provided by GLMs.

Abstract In this work, a previously proposed finite element is applied in conjunction with a modal approach to predict the lateral buckling resistance of the tensile armors in flexible pipes. The finite element represents the mechanical behavior of tensile armors settled on elastic foundations, which model the frictional interaction between these armors and the surrounding layers. This FE modal approach is used to evaluate the buckling response of 44 different tensile armors considering 15 different friction coefficients between layers. The responses obtained formed a dataset employed in symbolic regression analyses that led to an analytical formulation capable of adequately reproducing the numerical results with minimum computational effort. The results obtained with this analytical formulation are compared to those from other numerical models and experimental measurements showing good agreement and evidencing the potential of the proposed formulation.

This paper discusses the compensation of tool paths for machining flexible parts. Despite various research published on the topic, machining in practice nowadays remains limited to tool path planning based on only the geometric models of the parts and tools. This is mainly because that tool path compensation methods usually require accurate physical information of the systems and rely on analytical or finite element simulations, which are often not available to the end-users. In regards to this problem, this paper presents data-oriented nonparametric learning methods that require solely the geometric measurements of the trial machined contour(s). The physical parameters of the parts and tools as well as simulations of the machining process are not required. Two algorithms are developed based on Gaussian Process Regression and Artificial Neural Network respectively. Experimental tests are conducted. A plan of further improving the results using an auxiliary real-time vision sensor is also discussed.

The hydrostatic collapse strength of a flexible pipe is largely dependent on the ability of its carcass and pressure armor to resist radial loading and, therefore, its prediction involves an adequate modeling of these layers. Hence, initially, this work proposes a set of equations to estimate equivalent thicknesses and physical properties for these layers, which allows their modeling as equivalent orthotropic cylinders. These equations are obtained by simulating several two-point static ring tests with a three-dimensional finite element (FE) model based on beam elements and using these results to form datasets that are analyzed with a symbolic regression (SR) tool. The results of these analyses are the closed-form equations that best fit the provided datasets. After that, these equations are used in conjunction with a three-dimensional shell FE model and a previously presented analytical model to study the dry and wet hydrostatic collapse mechanisms of a flexible pipe. The predictions of these models agreed quite well with the collapse pressures obtained in experimental tests thus indicating that the use of the equivalent approach is promising.

Advanced diesel engine architectures employing flexible valve trains enable emissions reductions and fuel economy improvements. Flexibility in the valve train allows engine designers to optimize the gas exchange process in a manner similar to how common rail fuel injection systems enable optimization of the fuel injection process. Modulating valve timings directly impacts the volumetric efficiency of the engine. In fact, the control authority of valve timing modulation over volumetric efficiency is three times larger than that due to any other engine actuator. Traditional empirical or regression-based models for volumetric efficiency, while suitable for conventional valve trains, are therefore challenged by flexible valve trains. The added complexity and additional empirical data needed for wide valve timing ranges limit the usefulness of these methods. A physically-based volumetric efficiency model was developed to address these challenges. The model captures the major physical processes occurring over the intake stroke, and is applicable to both conventional and flexible valve trains. The model inputs include temperature and pressure in the intake and exhaust manifolds, intake and exhaust valve timings, bore, stoke, connecting rod length, engine speed and effective compression ratio, ECR. The model is physically-based, requires no regression tuning parameters, is generalizable to other engine platforms, and has been experimentally validated using an advanced multi-cylinder diesel engine equipped with a flexible variable intake valve actuation system. Experimental data was collected over a wide range of the operating space of the engine and augmented with air handling actuator and intake valve timing sweeps to maximize the range of conditions used to thoroughly experimentally validate the model for a total of 217 total operating conditions. The physical model developed differs from previous physical modeling work through the novel application of ECR, incorporation of no tuning parameters and extensive validation on unique engine test bed with flexible intake valve actuation.

Abstract Reservoir characterization requires accurate prediction of multiple petrophysical properties such as bulk density (or acoustic impedance), porosity, and permeability. However, it remains a big challenge in heterogeneous reservoirs due to significant diagenetic impacts including dissolution, dolomitization, cementation, and fracturing. Most well logs lack the resolution to obtain rock properties in detail in a heterogenous formation. Therefore, it is pertinent to integrate core images into the prediction workflow. This study presents a new approach to solve the problem of obtaining the high-resolution multiple petrophysical properties, by combining machine learning (ML) algorithms and computer vision (CV) techniques. The methodology can be used to automate the process of core data analysis with a minimum number of plugs, thus reducing human effort and cost and improving accuracy. The workflow consists of conditioning and extracting features from core images, correlating well logs and core analysis with those features to build ML models, and applying the models on new cores for petrophysical properties predictions. The core images are preprocessed and analyzed using color models and texture recognition, to extract image characteristics and core textures. The image features are then aggregated into a profile in depth, resampled and aligned with well logs and core analysis. The ML regression models, including classification and regression trees (CART) and deep neural network (DNN), are trained and validated from the filtered training samples of relevant features and target petrophysical properties. The models are then tested on a blind test dataset to evaluate the prediction performance, to predict target petrophysical properties of grain density, porosity and permeability. The profile of histograms of each target property are computed to analyze the data distribution. The feature vectors are extracted from CV analysis of core images and gamma ray logs. The importance of each feature is generated by CART model to individual target, which may be used to reduce model complexity of future model building. The model performances are evaluated and compared on each target. We achieved reasonably good correlation and accuracy on the models, for example, porosity R2=49.7% and RMSE=2.4 p.u., and logarithmic permeability R2=57.8% and RMSE=0.53. The field case demonstrates that inclusion of core image attributes can improve petrophysical regression in heterogenous reservoirs. It can be extended to a multi-well setting to generate vertical distribution of petrophysical properties which can be integrated into reservoir modeling and characterization. Machine leaning algorithms can help automate the workflow and be flexible to be adjusted to take various inputs for prediction.

The physics-of-failure (POF) modeling approach is a proven and powerful method to predict the reliability of mechanical components and systems. Most of POF models have been originally developed based upon empirical data from a wide range of applications (e.g. fracture mechanics approach to the fatigue life). Available curve fitting methods such as least square for example, calculate the best estimate of parameters by minimizing the distance function. Such point estimate approaches, basically overlook the other possibilities for the parameters and fail to incorporate the real uncertainty of empirical data into the process. The other important issue with traditional methods is when new data points become available. In such conditions, the best estimate methods need to be recalculated using the new and old data sets all together. But the original data sets, used to develop POF models may be no longer available to be combined with new data in a point estimate framework. In this research, for efficient uncertainty management in POF models, a powerful Bayesian framework is proposed. Bayesian approach provides many practical features such as a fair coverage of uncertainty and the updating concept that provide a powerful means for knowledge management, meaning that the Bayesian models allow the available information to be stored in a probability density format over the model parameters. These distributions may be considered as prior to be updated in the light of new data when they become available. At the first part of this article a brief review of classical and probabilistic approach to regression is presented. In this part the accuracy of traditional normal distribution assumption for error is examined and a new flexible likelihood function is proposed. The Bayesian approach to regression and its bonds with classical and probabilistic methods are explained next. In Bayesian section we shall discuss how the likelihood functions introduced in probabilistic approach, can be combined with prior information using the conditional probability concept. In order to highlight the advantages, the Bayesian approach is further clarified with case studies in which the result of calculation is compared with other traditional methods such as least square and maximum likelihood estimation (MLE) method. In this research, the mathematical complexity of Bayesian inference equations was overcome utilizing Markov Chain Monte Carlo simulation technique.

In developed electricity markets, the deregulation boosted competition among companies participating in the electricity market. Therefore, the enhanced reliability and availability of gas turbine systems is an industry obligation. Not only providing the available power with minimum operation and maintenance costs, but also guaranteeing high efficiency are additional requisites and efficiency loss of the power plants leads to a loss of money for the electricity generation companies. Multivariate Adaptive Regression Spline (MARS) is a modern methodology of statistical learning, data mining and estimation theory that is significant in both regression and classification is a form of flexible non-parametric regression analysis capable of modeling complex data. In this study, single shaft, 6MW class industrial gas turbines located at various sites have been monitored. The performance monitoring of a gas turbine consisted of hourly measurements of various input variables over an extended period of time. Using such measurements, predictive models for gas turbine heat rate and the gas turbine axial compressor discharge pressure values have been generated. The measured values have been compared with the values obtained as a result of the MARS models. The MARS-based models are obtained with the combination of gas turbine performance input and target variables and the complementary meteorological data. The results are presented, discussed, and conclusions are drawn for modern energy and cost efficient gas turbine and power plant maintenance management as the outcomes of this study.

A multistage system that consists of multiple stages for sequential operations to finish products is widely employed in modern manufacturing systems. Due to the characteristics of multistage systems, the product quality not only depends on operations in current stage but is also affected by operations in upstream stages. Most existing studies use Stream of Variation models to analyze error propagation and interactions among multiple stages in discrete manufacturing systems such as machining shops and assembly systems. In this paper, a multistage model based on the “Stream of Variation” concept is developed to investigate the tension propagation in a flexible material roll-to-roll manufacturing system. This modeling method uses a physical model coupled with a data-driven model to correlate the roller operation performance and product quality characteristics. Torque equilibrium analysis and Hooke’s law are employed for physical model and the censored regression model is used to explore unknown structures/parameters. A web unwinding process demonstrates the feasibility and prediction performance of the proposed model. The result shows that the proposed multistage model can serve as a virtual metrology method to increase system visibility, enhance health management capability and eventually improve product quality.

Telecommuting, the practice of working remotely at home, increased significantly (25% to 35%) early in the COVID-19 pandemic. This shift represented a major societal change that reshaped the family, work, and social lives of many Californians. These changes also raise important questions about what factors influenced telecommuting before, during, and after COVID-19, and to what extent changes in telecommuting have influenced transportation patterns across commute modes, employment, land use, and environment. The research team conducted state-level telecommuting surveys using a crowd-sourced platform (i.e., Amazon Mechanical Turk) to obtain valid samples across California (n=1,985) and conducted state-level interviews among stakeholders (n=28) across ten major industries in California. The study leveraged secondary datasets and developed regression and time-series models. Our surveys found that, compared to pre-pandemic levels, more people had a dedicated workspace at home and had received adequate training and support for telecommuting, became more flexible to choose their own schedules, and had improved their working performance—but felt isolated and found it difficult to separate home and work life. Our interviews suggested that telecommuting policies were not commonly designed and implemented until COVID-19. Additionally, regression analyses showed that telecommuting practices have been influenced by COVID-19 related policies, public risk perception, home prices, broadband rates, and government employment. This study reveals advantages and disadvantages of telecommuting and unveils the complex relationships among the COVID-19 outbreak, transportation systems, employment, land use, and emissions as well as public risk perception and economic factors. The study informs statewide and regional policies to adapt to the new patterns of telecommuting.

The objectives of this project were to develop nondestructive methods for detection of internal properties and firmness of fruits and vegetables. One method was based on a soft piezoelectric film transducer developed in the Technion, for analysis of fruit response to low-energy excitation. The second method was a dot-matrix piezoelectric transducer of North Carolina State University, developed for contact-pressure analysis of fruit during impact. Two research teams, one in Israel and the other in North Carolina, coordinated their research effort according to the specific objectives of the project, to develop and apply the two complementary methods for quality control of agricultural commodities. In Israel: An improved firmness testing system was developed and tested with tropical fruits. The new system included an instrumented fruit-bed of three flexible piezoelectric sensors and miniature electromagnetic hammers, which served as fruit support and low-energy excitation device, respectively. Resonant frequencies were detected for determination of firmness index. Two new acoustic parameters were developed for evaluation of fruit firmness and maturity: a dumping-ratio and a centeroid of the frequency response. Experiments were performed with avocado and mango fruits. The internal damping ratio, which may indicate fruit ripeness, increased monotonically with time, while resonant frequencies and firmness indices decreased with time. Fruit samples were tested daily by destructive penetration test. A fairy high correlation was found in tropical fruits between the penetration force and the new acoustic parameters; a lower correlation was found between this parameter and the conventional firmness index. Improved table-top firmness testing units, Firmalon, with data-logging system and on-line data analysis capacity have been built. The new device was used for the full-scale experiments in the next two years, ahead of the original program and BARD timetable. Close cooperation was initiated with local industry for development of both off-line and on-line sorting and quality control of more agricultural commodities. Firmalon units were produced and operated in major packaging houses in Israel, Belgium and Washington State, on mango and avocado, apples, pears, tomatoes, melons and some other fruits, to gain field experience with the new method. The accumulated experimental data from all these activities is still analyzed, to improve firmness sorting criteria and shelf-life predicting curves for the different fruits. The test program in commercial CA storage facilities in Washington State included seven apple varieties: Fuji, Braeburn, Gala, Granny Smith, Jonagold, Red Delicious, Golden Delicious, and D'Anjou pear variety. FI master-curves could be developed for the Braeburn, Gala, Granny Smith and Jonagold apples. These fruits showed a steady ripening process during the test period. Yet, more work should be conducted to reduce scattering of the data and to determine the confidence limits of the method. Nearly constant FI in Red Delicious and the fluctuations of FI in the Fuji apples should be re-examined. Three sets of experiment were performed with Flandria tomatoes. Despite the complex structure of the tomatoes, the acoustic method could be used for firmness evaluation and to follow the ripening evolution with time. Close agreement was achieved between the auction expert evaluation and that of the nondestructive acoustic test, where firmness index of 4.0 and more indicated grade-A tomatoes. More work is performed to refine the sorting algorithm and to develop a general ripening scale for automatic grading of tomatoes for the fresh fruit market. Galia melons were tested in Israel, in simulated export conditions. It was concluded that the Firmalon is capable of detecting the ripening of melons nondestructively, and sorted out the defective fruits from the export shipment. The cooperation with local industry resulted in development of automatic on-line prototype of the acoustic sensor, that may be incorporated with the export quality control system for melons. More interesting is the development of the remote firmness sensing method for sealed CA cool-rooms, where most of the full-year fruit yield in stored for off-season consumption. Hundreds of ripening monitor systems have been installed in major fruit storage facilities, and being evaluated now by the consumers. If successful, the new method may cause a major change in long-term fruit storage technology. More uses of the acoustic test method have been considered, for monitoring fruit maturity and harvest time, testing fruit samples or each individual fruit when entering the storage facilities, packaging house and auction, and in the supermarket. This approach may result in a full line of equipment for nondestructive quality control of fruits and vegetables, from the orchard or the greenhouse, through the entire sorting, grading and storage process, up to the consumer table. The developed technology offers a tool to determine the maturity of the fruits nondestructively by monitoring their acoustic response to mechanical impulse on the tree. A special device was built and preliminary tested in mango fruit. More development is needed to develop a portable, hand operated sensing method for this purpose. In North Carolina: Analysis method based on an Auto-Regressive (AR) model was developed for detecting the first resonance of fruit from their response to mechanical impulse. The algorithm included a routine that detects the first resonant frequency from as many sensors as possible. Experiments on Red Delicious apples were performed and their firmness was determined. The AR method allowed the detection of the first resonance. The method could be fast enough to be utilized in a real time sorting machine. Yet, further study is needed to look for improvement of the search algorithm of the methods. An impact contact-pressure measurement system and Neural Network (NN) identification method were developed to investigate the relationships between surface pressure distributions on selected fruits and their respective internal textural qualities. A piezoelectric dot-matrix pressure transducer was developed for the purpose of acquiring time-sampled pressure profiles during impact. The acquired data was transferred into a personal computer and accurate visualization of animated data were presented. Preliminary test with 10 apples has been performed. Measurement were made by the contact-pressure transducer in two different positions. Complementary measurements were made on the same apples by using the Firmalon and Magness Taylor (MT) testers. Three-layer neural network was designed. 2/3 of the contact-pressure data were used as training input data and corresponding MT data as training target data. The remaining data were used as NN checking data. Six samples randomly chosen from the ten measured samples and their corresponding Firmalon values were used as the NN training and target data, respectively. The remaining four samples' data were input to the NN. The NN results consistent with the Firmness Tester values. So, if more training data would be obtained, the output should be more accurate. In addition, the Firmness Tester values do not consistent with MT firmness tester values. The NN method developed in this study appears to be a useful tool to emulate the MT Firmness test results without destroying the apple samples. To get more accurate estimation of MT firmness a much larger training data set is required. When the larger sensitive area of the pressure sensor being developed in this project becomes available, the entire contact 'shape' will provide additional information and the neural network results would be more accurate. It has been shown that the impact information can be utilized in the determination of internal quality factors of fruit. Until now,