Multiple Adaptive Regression Splines Research Articles

Modeling of kappa factor using multivariate adaptive regression splines: application to the western Türkiye ground motion dataset

The recent seismic activity on Türkiye’s west coast, especially in the Aegean Sea region, shows that this region requires further attention. The region has significant seismic hazards because of its location in an active tectonic regime of North–South extension with multiple basin structures on soft soil deposits. Recently, despite being 70 km from the earthquake source, the Samos event (with a moment magnitude of 7.0 on October 30, 2020) caused significant localized damage and collapse in the Izmir city center due to a combination of basin effects and structural susceptibility. Despite this activity, research on site characterization and site response modeling, such as local velocity models and kappa estimates, remains sparse in this region. Kappa values display regional characteristics, necessitating the use of local kappa estimations from previous earthquake data in region–specific applications. Kappa estimates are multivariate and incorporate several characteristics such as magnitude and distance. In this study, we assess and predict the trend in mean kappa values using three–component strong–ground motion data from accelerometer sites with known VS30 values throughout western Türkiye. Multiple linear regression (MLR) and multivariate adaptive regression splines (MARS) were used to build the prediction models. The effects of epicentral distance Repi, magnitude Mw, and site class (VS30) were investigated, and the contributions of each parameter were examined using a large dataset containing recent seismic activity. The models were evaluated using well–known statistical accuracy criteria for kappa assessment. In all performance measures, the MARS model outperforms the MLR model across the selected sites.

Experimental investigation and application of soft computing models for predicting flow energy loss in arc-shaped constrictions

Abstract This investigation focuses on flow energy, a crucial parameter in the design of water structures such as channels. The research endeavors to explore the relative energy loss (ΔEAB/EA) in a constricted flow path of varying widths, employing Support Vector Machine (SVM), Artificial Neural Network (ANN), Gene Expression Programming (GEP), Multiple Adaptive Regression Splines (MARS), M5 and Random Forest (RF) models. Experiments span a Froude number range from 2.85 to 8.85. The experimental findings indicate that the ΔEAB/EA exceeds that observed in a classical hydraulic jump with constriction section. Within the SVM model, the linear kernel emerges as the best predictor of ΔEAB/EA, outperforming polynomial, radial basis function (RBF), and sigmoid kernels. In addition, in the ANN model, the MLP network was more accurate compared to the RBF network. The results indicate that the relationship proposed by the MARS model can play a significant role resulting in high accuracy compared to the non-linear regression relationship in predicting the target parameter. Upon comprehensive evaluation, the ANN method emerges as the most promising among the candidates, yielding superior performance compared to the other models. The testing phase results for the ANN-MLP are noteworthy, with R = 0.997, average RE% = 0.63%, RMSE = 0.0069, BIAS = −0.0004, DR = 0.999, SI = 0.0098 and KGE = 0.995.

Modeling of Monthly Rainfall–Runoff Using Various Machine Learning Techniques in Wadi Ouahrane Basin, Algeria

Rainfall–runoff modeling has been the core of hydrological research studies for decades. To comprehend this phenomenon, many machine learning algorithms have been widely used. Nevertheless, a thorough comparison of machine learning algorithms and the effect of pre-processing on their performance is still lacking in the literature. Therefore, the major objective of this research is to simulate rainfall runoff using nine standalone and hybrid machine learning models. The conventional models include artificial neural networks, least squares support vector machines (LSSVMs), K-nearest neighbor (KNN), M5 model trees, random forests, multiple adaptive regression splines, and multivariate nonlinear regression. In contrast, the hybrid models comprise LSSVM and KNN coupled with a gorilla troop optimizer (GTO). Moreover, the present study introduces a new combination of the feature selection method, principal component analysis (PCA), and empirical mode decomposition (EMD). Mean absolute error (MAE), root mean squared error (RMSE), relative RMSE (RRMSE), person correlation coefficient (R), Nash–Sutcliffe efficiency (NSE), and Kling Gupta efficiency (KGE) metrics are used for assessing the performance of the developed models. The proposed models are applied to rainfall and runoff data collected in the Wadi Ouahrane basin, Algeria. According to the results, the KNN–GTO model exhibits the best performance (MAE = 0.1640, RMSE = 0.4741, RRMSE = 0.2979, R = 0.9607, NSE = 0.9088, and KGE = 0.7141). These statistical criteria outperform other developed models by 80%, 70%, 72%, 77%, 112%, and 136%, respectively. The LSSVM model provides the worst results without pre-processing the data. Moreover, the findings indicate that using feature selection, PCA, and EMD significantly improves the accuracy of rainfall–runoff modeling.

Supporting Decision Making for Building Decarbonization: Developing Surrogate Models for Multi-Criteria Building Retrofitting Analysis

Decarbonizing buildings is crucial in addressing pressing climate change issues. Buildings significantly contribute to global greenhouse gas emissions, and reducing their carbon footprint is essential to achieving sustainable and low-carbon cities. Retrofitting buildings to become more energy efficient constitutes a solution. However, building energy retrofits are complex processes that require a significant number of simulations to investigate the possible options, which limits comprehensive investigations that become infeasible to carry out. Surrogate models can be vital in addressing computational inefficiencies by emulating physics-based models and predicting building performance. However, there is a limited focus on investigating feature engineering and selection methods and their effect on the model’s performance and optimization. Feature selection methods are considered effective with interpretable models such as multi-variate linear regression (MVLR) and multiple adaptive regression splines (MARS) for achieving stable prediction stability. This study proposes a modelling framework to create, optimize, and improve the performance of surrogate predictive models for energy consumption, carbon emissions, and the associated cost of building energy retrofit processes. The investigated feature selection methods are wrapper and embedded methods such as backward-stepwise feature selection (BSFS), recursive feature elimination (RFE), and Elastic Net embedded regularization in order to provide insights into the model’s behavior and optimize the model’s performance. The most accurate surrogate models developed achieved a mean absolute percentage error (MAPE) of 0.2–1.8% compared to the used test data. In addition, when calculated for a million samples, all developed surrogate models reduced the computational time by one-thousand-fold compared to physics-based models. The study’s findings pave the way towards low-computational accurate models that can comprehensively predict building performance in near real-time, ultimately leading to identifying decarbonization measures at scale.

Performance evaluation of machine learning algorithms to assess soil erosion in Mediterranean farmland: A case‐study in Syria

AbstractThe development of new techniques, such as machine learning (ML), can provide better insight into the processes and drivers of soil erosion and runoff. However, the performance of these techniques to assess soil erosion in agricultural landscapes is poorly understood. The aim of this study was to evaluate the performance of four machine learning algorithms, generalized linear model (GLM), Random Forest (RF), elastic net regression (EN) and multiple adaptive regression splines (MARS), in predicting soil erosion and runoff in Syria. Soil erosion and runoff were measured on three experimental plots (2.25 m × 1.50 m × 0.50 m, 0.10 m depth in the soil), combined with three different slopes and land use types: RS (8%, olive), SS (12%, citrus), KS (20%, pomegranate). Both erosion and runoff were determined after rainfall events of >10 mm between October 2019 and April 2020. Based on 24 effective rainfall events, the average soil erosion was 0.18 ± 0.14 kg m−2 per event in KS, 0.14 ± 0.11 kg m−2 per event in SS, and 0.12 ± 0.10 kg/m2 per event in RS. Regression analysis indicated strong relationship between the rainfalls and the runoff, the highest connection was recorded in the KS plot (r2 = 0.85; p < 0.05 n = 24). The analysis of covariance indicated that only the runoff had a significant impact on soil erosion (p = 0.02) with a medium effect (ε2p = 0.26). However, the impacts of rainfall events and slope categories on soil erosion were limited (ε2p < 0.01) and not significant (p > 0.05). ML techniques were usually efficient in the prediction, the RF and MARS models were the most accurate: RF had the strongest correlation with the measured values (r = 0.85) with a low estimation error (0.06 kg m−2), but MARS's standard deviation (SD) was closer to the recorded values' SD. GLM and EN were the weakest predictor models. Modeled values of the slightest slope (8%) had the worst accuracies, and the predictions of the 12% slope were the best in all models. This study provides important insights into the usefulness of machine learning techniques and algorithms in predicting the rate of soil erosion and runoff in agricultural dominated landscapes. We highlighted that the RF and MARS algorithms were better predictors of soil erosion and runoff in the coastal region of Syria.

Assessment of soil CO2 and NO fluxes in a semi-arid region using machine learning approaches

Agricultural lands are sources and sinks of greenhouse gases (GHGs). The identification of the main drivers affecting GHGs is crucial for planning sustainable agronomic practices and mitigating global warming potential. The main aim of this research was to evaluate the impact of environmental drivers (soil temperature and water-filled pore space, WFPS) and crop residue rates on CO2, NO, and NOx fluxes under conventional tillage (CT) and no-tillage (NT) systems. The accuracy of Random Forest Regression (RFR), Multiple Adaptive Regression Splines (MARS), and General Linear Models (GLM) in predicting CO2, NO, and NOx fluxes were also assessed.In both CT and NT systems, CO2, NO, and NOx fluxes decreased with increasing WFPS. Increasing temperature resulted in higher CO2 emissions and lower NO and NOx emissions. Higher residue rates resulted in significant increases in CO2 emission, whereas the NO and NOx emissions increased by decreasing the ratio of residue. For CO2 prediction, the RFR provided the largest R2 with the observed data. For NO–N and NOx-N prediction, RFR was the most efficient algorithm, but NO–N can be predicted with better accuracy. The output of this research highlights the importance of agronomic practices for climate mitigation, along with the possibility of using RFR to predict GHGs fluxes.

Prediction of Retention Time and Collision Cross Section (CCSH+, CCSH-, and CCSNa+) of Emerging Contaminants Using Multiple Adaptive Regression Splines.

Ultra-high performance liquid chromatography coupled to ion mobility separation and high-resolution mass spectrometry instruments have proven very valuable for screening of emerging contaminants in the aquatic environment. However, when applying suspect or nontarget approaches (i.e., when no reference standards are available), there is no information on retention time (RT) and collision cross-section (CCS) values to facilitate identification. In silico prediction tools of RT and CCS can therefore be of great utility to decrease the number of candidates to investigate. In this work, Multiple Adaptive Regression Splines (MARS) were evaluated for the prediction of both RT and CCS. MARS prediction models were developed and validated using a database of 477 protonated molecules, 169 deprotonated molecules, and 249 sodium adducts. Multivariate and univariate models were evaluated showing a better fit for univariate models to the experimental data. The RT model (R2 = 0.855) showed a deviation between predicted and experimental data of ±2.32 min (95% confidence intervals). The deviation observed for CCS data of protonated molecules using the CCSH model (R2 = 0.966) was ±4.05% with 95% confidence intervals. The CCSH model was also tested for the prediction of deprotonated molecules, resulting in deviations below ±5.86% for the 95% of the cases. Finally, a third model was developed for sodium adducts (CCSNa, R2 = 0.954) with deviation below ±5.25% for 95% of the cases. The developed models have been incorporated in an open-access and user-friendly online platform which represents a great advantage for third-party research laboratories for predicting both RT and CCS data.

River sensing: the inclusion of red band in predicting reach-scale types using machine learning algorithms

ABSTRACT This study aims to predict channel unit types (CUTs) by combining remotely sensed data with morphological variables using machine learning algorithms (random forest, support vector machines, multiple adaptive regression splines, extreme gradient boosting and adaptive boosting) within the Upper Ogun River Basin, Southwestern Nigeria. In achieving the aim of this study, we identified the most important variable(s) in CUT discrimination using the random forest – recursive feature elimination (RF-RFE). A total of 249 cross-sections across 83 reaches were sampled during the fieldwork. Landsat 8 and Sentinel-1 bands were retrieved for days the fieldwork was carried and mosaiced using the Google Earth Engine platform. The RF-RFE identified five top variables (accuracy: 0.79 ± 0.14; kappa: 0.39) discriminating the CUT as dimensionless stream power, slope, width, wetted perimeter and Band 4. In essence, there is much hope in the use of remote sensing in CUT mapping at the reach scale.

An Integrated Statistical-Machine Learning Approach for Runoff Prediction

Nowadays, great attention has been attributed to the study of runoff and its fluctuation over space and time. There is a crucial need for a good soil and water management system to overcome the challenges of water scarcity and other natural adverse events like floods and landslides, among others. Rainfall–runoff (R-R) modeling is an appropriate approach for runoff prediction, making it possible to take preventive measures to avoid damage caused by natural hazards such as floods. In the present study, several data-driven models, namely, multiple linear regression (MLR), multiple adaptive regression splines (MARS), support vector machine (SVM), and random forest (RF), were used for rainfall–runoff prediction of the Gola watershed, located in the south-eastern part of the Uttarakhand. The rainfall–runoff model analysis was conducted using daily rainfall and runoff data for 12 years (2009 to 2020) of the Gola watershed. The first 80% of the complete data was used to train the model, and the remaining 20% was used for the testing period. The performance of the models was evaluated based on the coefficient of determination (R2), root mean square error (RMSE), Nash–Sutcliffe efficiency (NSE), and percent bias (PBAIS) indices. In addition to the numerical comparison, the models were evaluated. Their performances were evaluated based on graphical plotting, i.e., time-series line diagram, scatter plot, violin plot, relative error plot, and Taylor diagram (TD). The comparison results revealed that the four heuristic methods gave higher accuracy than the MLR model. Among the machine learning models, the RF (RMSE (m3/s), R2, NSE, and PBIAS (%) = 6.31, 0.96, 0.94, and −0.20 during the training period, respectively, and 5.53, 0.95, 0.92, and −0.20 during the testing period, respectively) surpassed the MARS, SVM, and the MLR models in forecasting daily runoff for all cases studied. The RF model outperformed in all four models’ training and testing periods. It can be summarized that the RF model is best-in-class and delivers a strong potential for the runoff prediction of the Gola watershed.

Comparison of machine learning and dynamic models for predicting actual vapour pressure when psychrometric data are unavailable

• Machine learning models for predicting e a without psychrometric data were developed. • Machine learning models were compared with recently proposed dynamic empirical model. • The machine learning models using T mean and T min as inputs were superior to those using only T mean or T min . • The XGBoost model using T mean and T min offered the best accuracy in various climate zones. • We recommend global XGBoost model when there are no historical data except for hyper-arid regions. Information of actual vapour pressure ( e a ) is frequently required in many disciplines. However, psychrometric data required to calculate e a are often not readily available. Hence, it is of great importance to develop models to estimate e a when psychrometric data are unavailable. Here, five machine learning models were developed for estimating e a , viz. extreme gradient boosting (XGBoost), extreme learning machine (ELM), kernel-based nonlinear extension of Arps decline (KNEA), multiple adaptive regression splines (MARS), and support vector machine (SVM) models. Their performance was also compared to a dynamic model proposed recently, which estimates e a by adjusting dew point temperature from minimum temperature ( T min ) with dynamic correction factor. Three input combinations using only temperature data (i.e. T min and mean temperature ( T mean )) were considered in the machine learning models. The meteorological data collected from 1,188 stations across six climate zones were used to develop and assess the models. The overall results revealed that the dynamic and machine learning models offered satisfactory e a estimates spanning from hyper arid to humid climates. However, the accuracy of the dynamic model was lower than all machine learning algorithms using either only T min or combinations of T mean and T min in all climate zones. The machine learning models using T mean and T min were superior to those using only T mean or T min . There were comparable performances among the ELM, KNEA, MARS, and SVM models with various input variables; however, the XGBoost model incorporating T mean and T min produced the best accuracy. The computational demand was least for the ELM model, followed by the XGBoost model. Considering the accuracy and computational demand, the XGBoost model is recommended for predicting daily and monthly e a from hyper arid to humid climates when historical data are prior known. When there are no historical data, we recommend using the global XGBoost model incorporating T mean , T min , and aridity index for estimating daily and monthly e a from arid to humid regions, and using the dynamic model in hyper-arid regions.

Prediction Model of Compressive Strength of Fly Ash-Slag Concrete Based on Multiple Adaptive Regression Splines

Accurate prediction of compressive strength of concrete is one of the key issues in the concrete industry. In this paper, a prediction method of fly ash-slag concrete compressive strength based on multiple adaptive regression splines (MARS) is proposed, and the model analysis process is determined by analyzing the principle of this algorithm. Based on the Concrete Compressive Strength dataset of UCI, the MARS model for compressive strength prediction was constructed with cement content, blast furnace slag powder content, fly ash content, water content, reducing agent content, coarse aggregate content, fine aggregate content and age as independent variables. The prediction results of artificial neural network (BP), random forest (RF), support vector machine (SVM), extreme learning machine (ELM), and multiple nonlinear regression (MnLR) were compared and analyzed, and the prediction accuracy and model stability of MARS and RF models had obvious advantages, and the comprehensive performance of MARS model was slightly better than that of RF model. Finally, the explicit expression of the MARS model for compressive strength is given, which provides an effective method to achieve the prediction of compressive strength of fly ash-slag concrete.

Nation-scale reference evapotranspiration estimation by using deep learning and classical machine learning models in China

Accurately estimating the reference evapotranspiration (ET0) is a basic requirement for precision irrigation and the correct planning of regional water resources. This study aimed to investigate the spatiotemporal variations in ET0 in China and to improve the accuracy of ET0 calculations on different spatiotemporal scales. Meteorological data collected at 100 stations in China during 1961 to 2019 were used to calculate ET0 with the Penman–Monteith model, and the temporal and spatial patterns in ET0-PM were analyzed with the Mann–Kendall nonparametric trend test method. Three machine learning models comprising convolutional neural network (CNN), extreme learning machine (ELM), and multiple adaptive regression splines (MARS), and seven empirical models calibrated with mind evolutionary algorithm (MEA) were compared to assess their suitability for calculating ET0 on different spatiotemporal scales in China. The results showed that the annual mean ET0-PM value (413.29–2772.35 mm) in China gradually increased from north to south and from west to east. ET0 exhibited an upward trend in the temperate continental zone (TCZ) and mountain plateau zone (MPZ) but a downward trend in the temperate monsoon zone (TMZ) and subtropical monsoon region (SMZ). By comparing the global performance indicators (GPI), the machine learning models generally performed better than the empirical models at different spatiotemporal scales. And CNN was the best model for calculating ET0 in terms of the model accuracy and stability. On the daily scale, MARS performed well in MPZ, whereas ELM performed well in TMZ and TCZ. On the monthly scale, MARS performed well in TMZ, whereas ELM performed well in SMZ and MPZ. At the annual scale, the accuracy of ELM was higher than that of MARS.

Geometry optimization and pressure analysis of a proton exchange membrane fuel cell stack

For proton exchange membrane fuel cells (PEMFCs), the distribution of reactant streams in the reactor is critical to their efficiency. This study aims to investigate the optimal design of the inlet/outlet flow channel in the fuel cell stack with different geometric dimensions of the tube and intermediate zones (IZ). The tube-to-IZ length ratio, the IZ width, and the tube diameter are adjusted to optimize the geometric dimensions for the highest pressure uniformity. Four different methods, including the Taguchi method, analysis of variance (ANOVA), neural network (NN), and multiple adaptive regression splines (MARS), are used in the analyses. The results indicate the tube diameter is the most impactive one among the three factors to improve the pressure uniformity. The analysis suggests that the optimal geometric design is the tube-to-IZ length ratio of 9, the IZ width of 14 mm, and the tube diameter of 9 mm with the pressure uniformity of 0.529. The relative errors of the predicted pressure uniformity values by NN and MARS under the optimal design are 1.62% and 3.89%, respectively. This reveals that NN and MARS can accurately predict the pressure uniformity, and are promising tools for the design of PEMFCs.

Do we need different machine learning algorithms for QSAR modeling? A comprehensive assessment of 16 machine learning algorithms on 14 QSAR data sets.

Although a wide variety of machine learning (ML) algorithms have been utilized to learn quantitative structure-activity relationships (QSARs), there is no agreed single best algorithm for QSAR learning. Therefore, a comprehensive understanding of the performance characteristics of popular ML algorithms used in QSAR learning is highly desirable. In this study, five linear algorithms [linear function Gaussian process regression (linear-GPR), linear function support vector machine (linear-SVM), partial least squares regression (PLSR), multiple linear regression (MLR) and principal component regression (PCR)], three analogizers [radial basis function support vector machine (rbf-SVM), K-nearest neighbor (KNN) and radial basis function Gaussian process regression (rbf-GPR)], six symbolists [extreme gradient boosting (XGBoost), Cubist, random forest (RF), multiple adaptive regression splines (MARS), gradient boosting machine (GBM), and classification and regression tree (CART)] and two connectionists [principal component analysis artificial neural network (pca-ANN) and deep neural network (DNN)] were employed to learn the regression-based QSAR models for 14 public data sets comprising nine physicochemical properties and five toxicity endpoints. The results show that rbf-SVM, rbf-GPR, XGBoost and DNN generally illustrate better performances than the other algorithms. The overall performances of different algorithms can be ranked from the best to the worst as follows: rbf-SVM > XGBoost > rbf-GPR > Cubist > GBM > DNN > RF > pca-ANN > MARS > linear-GPR ≈ KNN > linear-SVM ≈ PLSR > CART ≈ PCR ≈ MLR. In terms of prediction accuracy and computational efficiency, SVM and XGBoost are recommended to the regression learning for small data sets, and XGBoost is an excellent choice for large data sets. We then investigated the performances of the ensemble models by integrating the predictions of multiple ML algorithms. The results illustrate that the ensembles of two or three algorithms in different categories can indeed improve the predictions of the best individual ML algorithms.

Downscaling daily air-temperature measurements in the Netherlands

High-resolution, regularly gridded air-temperature maps are frequently used in climatology, hydrology, and ecology. Within the Netherlands, 34 official automatic weather stations (AWSs) are operated by the National Met Service according to World Meteorological Organization (WMO) standards. Although the measurements are of high quality, the spatial density of the AWSs is not sufficient to reconstruct the temperature on a 1-km-resolution grid. Therefore, a new methodology for daily temperature reconstruction from 1990 to 2017 is proposed, using linear regression and multiple adaptive regression splines. The daily 34 AWS measurements are interpolated using eight different predictors: diurnal temperature range, population density, elevation, albedo, solar irradiance, roughness, precipitation, and vegetation index. Results are cross-validated for the AWS locations and compared with independent citizen weather observations. The RMSE of the reference method ordinary kriging amounts to 2.6 °C whereas using the new methods the RMSE drops below 1.0 °C. Especially for cities, a substantial improvement of the predictions is found. Independent predictions are on average 0.3 °C less biased than ordinary kriging at 40 high-quality citizen measurement sites. With this new method, we have improved the representation of local temperature variations within the Netherlands. The temperature maps presented here can have applications in urban heat island studies, local trend analysis, and model evaluation.

An Approach for the Retrieval of Land Surface Temperature from the Industrial Area Using Landsat-8 Thermal Infrared Sensors

The thermal imagine provides data with synoptic coverage for investigating thermal information from hot sources for detecting, mapping energy loss from the industrial area. This study attempts to retrieved heat loss from the industrial area using Landsat-8 TIRS experimented at an industrial area of Pasir Gudang, Peninsular Malaysia, the main objective is to investigate the sensitivity of Landsat-8 TIR for detecting industrial thermal energy within the various range of targets of different temperatures. An estimated heat map with absolute surface temperature values is the final output. Apart of the pre-processing of Landsat-8 TIRS data, data are processed for the retrieval of land surface temperature, then subjected to a downscaling process to final 30 x 30 m pixels, hence enable to merge with all Landsat-8 bands for visualization and validation of results. The split window algorithm (SWA) is used for the temperature retrieval from band 10 and 11, with other driven parameters. The Multiple Adaptive Regression Splines (MARS) model for spatial downscaling was adopted in this study. The generated thermal energy map was then validated over selected targets in the field and compared to corresponding downscaled MODIS LST product (MODIS11A2). TIR bands applied with SWA generated 13.7°C temperature dynamic range from 22.35˜51.36° C in comparison with MODIS LST product values range from 27.17 ˜ 37.65°C). Results indicated good agreement between the generated thermal energy map with the in-situ validations (RMSE=0.43 °C). It is therefore concluded that derived Land surface temperature map derived is suitable for study industrial thermal environment at 1:50,000 ˜ 100,000 scales, adequately to be used for environmental impact assessment.

Application of Soft Computing Models with Input Vectors of Snow Cover Area in Addition to Hydro-Climatic Data to Predict the Sediment Loads

The accurate estimate of sediment load is important for management of the river ecosystem, designing of water infrastructures, and planning of reservoir operations. The direct measurement of sediment is the most credible method to estimate the sediments. However, this requires a lot of time and resources. Because of these two constraints, most often, it is not possible to continuously measure the daily sediments for most of the gauging sites. Nowadays, data-based sediment prediction models are famous for bridging the data gaps in the estimation of sediment loads. In data-driven sediment predictions models, the selection of input vectors is critical in determining the best structure of models for the accurate estimation of sediment yields. In this study, time series inputs of snow cover area, basin effective rainfall, mean basin average temperature, and mean basin evapotranspiration in addition to the flows were assessed for the prediction of sediment loads. The input vectors were assessed with artificial neural network (ANN), adaptive neuro-fuzzy logic inference system with grid partition (ANFIS-GP), adaptive neuro-fuzzy logic inference system with subtractive clustering (ANFIS-SC), adaptive neuro-fuzzy logic inference system with fuzzy c-means clustering (ANFIS-FCM), multiple adaptive regression splines (MARS), and sediment rating curve (SRC) models for the Gilgit River, the tributary of the Indus River in Pakistan. The comparison of different input vectors showed improvements in the prediction of sediments by using the snow cover area in addition to flows, effective rainfall, temperature, and evapotranspiration. Overall, the ANN model performed better than all other models. However, as regards sediment load peak time series, the sediment loads predicted using the ANN, ANFIS-FCM, and MARS models were found to be closer to the measured sediment loads. The ANFIS-FCM performed better in the estimation of peak sediment yields with a relative accuracy of 81.31% in comparison to the ANN and MARS models with 80.17% and 80.16% of relative accuracies, respectively. The developed multiple linear regression equation of all models show an R2 value of 0.85 and 0.74 during the training and testing period, respectively.

Pathological Gait Detection Based on Multiple Regression Models Using Unobtrusive Sensing Technology

Analysis of human gait to detect walking abnormality has recently gained growing interest. It carries profound impact in medical diagnosis and rehabilitation engineering. In this study we have explored different regression modeling techniques to detect pathological gait. Inexpensive Microsoft Kinect (V2) sensor was used for data acquisition. Comparative analysis was performed between logistic regression, SVM and multiple adaptive regression splines (MARS) models. Kinematic time series, extracted from different lower limb joints, were fed into the models and used to detect the abnormal pattern. Feature vectors were constructed from 6 joint angles (hip, knee and ankle angles of both sides) and merged on the range of multiple time instance for greater accuracy. An attempt was also made to investigate the statistical significance of the feature vectors. MARS model was found to be comparatively better than others with 88.3% of detection accuracy.

Escape Velocity backed avalanche predictor- Neural evidence from Nifty

The concept of escape velocity has been extended from physics to stochastic finance and used as an avalanche predictor. Escape velocity being an extreme event serves as a perfect proxy of this stochastic finance event. This study identifies the propensity of the capital market to explode on rare occasions, which could be termed as avalanche. The frequency of such movement (both up and down) may not be high; however, the amplitude will be significantly high. The underlying for the study is Nifty, bellwether Indian bourse. Escape velocity has been calculated for Nifty on a daily basis for 17 years and prediction modelling has been constructed applying artificial neural networks (ANN) and multiple adaptive regression splines (MARS) simultaneously. Results indicate queer coupling of US events and Nifty apart from the evident behavioural traces. This research work is aimed at providing an implicit form of avalanche predictor from a distinctly different reference point.

Development of toolkits for detecting dental caries and caries experience among children using self-report and parent report.

To develop child- and parent-reported toolkits for active caries and caries experience in children and adolescents, ages 8-17. A sample of 398 child/parent dyads recruited from 12 dental practices in Los Angeles County completed a computer-assisted survey that assessed oral health perceptions. In addition, children received a dental examination that identified the presence or absence of active caries and caries experience. A Multiple Adaptive Regression Splines model was used to identify a subset of survey items associated with active caries and caries experience. The splines and coefficients were refined by generalized cross-validation. Sensitivity and specificity for both dependent variables were evaluated. Eleven child self-reported items were identified that had sensitivity of 0.82 and specificity of 0.45 relative to active caries. Twelve parent-reported items had a sensitivity of 0.86 and specificity of 0.50. Seven child self-reported items had a sensitivity of 0.86 and specificity of 0.34, and 11 parent-reported items had a sensitivity of 0.86 and specificity of 0.47 for caries experience. The survey items identified here are useful in distinguishing children with and without active caries and with and without caries experience. This research presents a path towards using children's and their parents' reports about oral health to screen for clinically determined caries and caries exposure. The items identified in this study can be useful when clinical information is unavailable.