Use Of Support Vector Regression Research Articles

Urban Arterial Travel Time Prediction Using Support Vector Regression

Travel time is one of the most appropriate traffic measures that can be provided to road users for easy understanding and decision making. This paper presents a simple method to predict travel time on urban arterial roads. Travel time prediction methods include historical methods, model based methods, and data driven approaches. Of these, data driven approaches capture the uncertainty and non-linearity of traffic time series better and hence could be used for travel time prediction under Indian traffic conditions effectively. Among data driven approaches, support vector regression (SVR) models predict travel times with reasonable accuracy, especially when the amount of data is less or the variability in the data is high. However, studies on the use of SVR for travel time prediction under Indian traffic conditions are limited. In this paper, SVR technique was used to predict the travel time using data collected from Bluetooth sensors placed at specific locations on an urban arterial corridor in Chennai, India. The optimum number of inputs, appropriate kernel function, cost parameter and width of tolerance for the SVR model were determined. The results obtained show that the SVR performed better than an Artificial Neural Network model and moving average approach.

Residential buildings conceptual cost estimates with the use of support vector regression

Cost analyses, and the conceptual cost estimates among them, are of the key importance for the construction projects successes. Implementation of neural networks or machine learning methods provides broad possibilities for this specific type of cost. The aim of the paper is to present some results of the studies on the use of support vector regression as a machine learning tool for conceptual cost estimates of residential buildings. Results for three models based on support vector regression and radial basis kernel functions are introduced.

Efficient Prediction of Low-Visibility Events at Airports Using Machine-Learning Regression

We address the prediction of low-visibility events at airports using machine-learning regression. The proposed model successfully forecasts low-visibility events in terms of the runway visual range at the airport, with the use of support-vector regression, neural networks (multi-layer perceptrons and extreme-learning machines) and Gaussian-process algorithms. We assess the performance of these algorithms based on real data collected at the Valladolid airport, Spain. We also propose a study of the atmospheric variables measured at a nearby tower related to low-visibility atmospheric conditions, since they are considered as the inputs of the different regressors. A pre-processing procedure of these input variables with wavelet transforms is also described. The results show that the proposed machine-learning algorithms are able to predict low-visibility events well. The Gaussian process is the best algorithm among those analyzed, obtaining over 98% of the correct classification rate in low-visibility events when the runway visual range is $${>}$$ 1000 m, and about 80% under this threshold. The performance of all the machine-learning algorithms tested is clearly affected in extreme low-visibility conditions ( $${<}$$ 500 m). However, we show improved results of all the methods when data from a neighbouring meteorological tower are included, and also with a pre-processing scheme using a wavelet transform. Also presented are results of the algorithm performance in daytime and nighttime conditions, and for different prediction time horizons.

Use of Support Vector Regression Based on Mean Impact Value Model to Identify Active Compounds in a Combination of Curcuma longa L. and Glycyrrhiza extracts

A support vector regression based on the mean impact value (MIV) model was constructed to identify the bioactive compounds inhibiting proliferation of HeLa cells in a combination of turmeric (Curcuma longa L.) and liquorice (Glycyrrhiza) extracts. The quantitative chemical fingerprint from 50 batches of turmeric and liquorice extracts was established using high performance liquid chromatography hyphenated to an ultraviolet visible detector. Qualitative results were obtained using ultra performance liquid chromatography coupled with electrospray ionization quadrupole time-of-flight tandem mass spectrometry. A total of 46 peaks (peaks 1–15 from turmeric and 16–46 from liquorice) were selected as “common peaks” for analysis. The inhibitory effect of the combined extracts on HeLa cells was measured by MTT (3-(4,5-dimethylthiazol-2-yl)-2,5-diphenyltetrazolium bromide) assay. It was found that 15 compounds (peaks: 8, 12, 30, 24, 46, 11, 14, 9, 3, 1, 44, 18, 7, 45 and 43) possessing high absolute MIV exhibited a significant correlation with the cytotoxicity against HeLa cells; most of these have already been confirmed with potential cytotoxicity in previous research. The important potential application of the present model can be extended to help discover active compounds from complex herbal medicine prior to traditional bioassay-guided separation. It is considered that this could be a useful tool for re-developing herbal medicine based on the use of these active compounds.

Using genetic algorithms to improve support vector regression in the analysis of atomic spectra of lubricant oils

Purpose – The purpose of this paper is to assess the quality of commercial lubricant oils. A spectroscopic method was used in combination with multivariate regression techniques (ordinary multivariate multiple regression, principal components analysis, partial least squares, and support vector regression (SVR)). Design/methodology/approach – The rationale behind the use of SVR was the fuzzy characteristics of the signal and its inherent ability to find nonlinear, global solutions in highly complex dimensional input spaces. Thus, SVR allows extracting useful information from calibration samples that makes it possible to characterize physical-chemical properties of the lubricant oils. Findings – A dataset of 42 spectra measured from oil standards was studied to assess the concentration of copper into the oils and, thus, evaluate the wearing of the machinery. It was found that the use of SVR was very advantageous to get a regression model. Originality/value – The use of genetic algorithms coupled to SVR was considered in order to reduce the time needed to find the optimal parameters required to get a suitable prediction model.

Hourly Photovoltaics Power Output Prediction for Malaysia Using Support Vector Regression

Reliable solar energy forecasting enables grid operators to manage the grid better as PV penetration level increases. This research explores the use of support vector regression to forecast hourly power output from a grid-connected PV system in Malaysia. Data is obtained from a grid-connected PV system that is equipped with a weather monitoring station. Three parameters are used as input to the forecast model; global irradiance, tilted irradiance and ambient temperature. Results were compared against a persistence model. The SVR model manages to forecast hourly power production with satisfactory accuracy.

Wall parameters estimation based onsupport vector regression for through wall radar sensing

In through wall radar sensing, the wall parameters estimation (WPE) problem has been a topic that attracts a lot of attention since the wall parameters, i.e., the permittivity and the thickness, are of crucial importance to locate the targets and to produce a well-focused image, but they are usually unknown in practice. To solve this problem, in this paper, the support vector regression (SVR), a powerful tool for regression analysis, is introduced, and its performance on WPE, provided it is used it in the regular way, is investigated. Unfortunately, it is shown that the regular use of SVR cannot afford satisfactory estimation results since the sample data used in SVR, namely the received echoes from the walls, are seriously interfered with the echoes from the targets which are located near the walls. In view of this limitation, a novel SVR-based WPE approach that consists of three stages is proposed by this paper. In the first stage, three regression functions are trained by SVR, one of which will output the estimate of the permittivity in the second stage, and the others are designed to output two instrumental variables for estimating the thickness. In the third stage, the estimate of thickness will be achieved by minimizing a predefined cost function wherein the estimated permittivity and the outputted instrumental variables are involved. The better robustness and higher estimation accuracy of the proposed approach compared to the regular use of SVR are validated by the numerical experimental results using finite-difference time-domain simulations.

Surgical planning for horizontal strabismus using Support Vector Regression

Strabismus is a pathology which affects about 4% of the population, causing esthetic problems (reversible at any age) and irreversible sensory disorders, altering the vision mechanism. Many techniques can be applied to settle the muscular balance, thus eliminating strabismus. However, when the conservative treatment is not enough, the surgical treatment is adopted, applying recoils or resections to the ocular muscles affected. The factors involved in the surgical strategy in cases of strabismus are complex, demanding both theoretical knowledge and experience from the surgeon. So, the present work proposes a methodology based on Support Vector Regression to help the physician with decision related to horizontal strabismus surgeries. The efficiency of the method at the indication of the surgical plan was evaluated through the average difference between the values that it provided and the values indicated by the specialists. In the planning of medial rectus muscles surgeries, the average error was 0.5mm for recoil and 0.7 for resection. For lateral rectus muscles, the mean error was 0.6 for recoil and 0.8 for resection. The results are promising and prove the feasibility of the use of Support Vector Regression in the indication of strabismus surgeries.

Seasonal forecasting of tropical cyclone activity in the Australian and the South Pacific Ocean regions

AbstractThe Australian Bureau of Meteorology (Bureau) issues operational tropical cyclone (TC) seasonal forecasts for the Australian region (AR) and the South Pacific Ocean (SPO) and subregions therein. The forecasts are issued in October, ahead of the Southern Hemisphere TC season (November to April). Improvement of operational TC seasonal forecasts can lead to more accurate warnings for coastal communities to prepare for TC hazards. This study investigates the use of support vector regression (SVR) models, exploring new explanatory variables and non-linear relationships between them, the use of model averaging, and lastly the integration of forecast intervals based on a bias-corrected and accelerated non-parametric bootstrap. Hindcasting analyses show that the SVR model outperforms several benchmark methods. Analysis of the generated models shows that the Dipole Mode Index, 5VAR index and the Southern Oscillation Index are the most frequently selected as explanatory variables for TC seasonal forecasting in all regions. The usage of ENSOrelated covariates implies that definitions of regions and subregions may have to be updated to achieve optimal forecasting performance. Overall, the new SVR methodology is an improvement over the current linear discriminant analysis models and has the potential to increase accuracy of TC seasonal forecasts in the AR and SPO.

Forecasting Exchange Rates

Accurate forecasting for future events constitutes a fascinating challenge for theoretical and for applied researches. Foreign Exchange market (FOREX) is selected in this research to represent an example of financial systems with a complex behavior. Forecasting a financial time series can be a very hard task due to the inherent uncertainty nature of these systems. It seems very difficult to tell whether a series is stochastic or deterministic chaotic or some combination of these states. More generally, the extent to which a non-linear deterministic process retains its properties when corrupted by noise is also unclear. The noise can affect a system in different ways even though the equations of the system remain deterministic. Since a single reliable statistical test for chaoticity is not available, combining multiple tests is a crucial aspect, especially when one is dealing with limited and noisy data sets like in economic and financial time series. In this research, the authors propose an improved model for forecasting exchange rates based on chaos theory that involves phase space reconstruction from the observed time series and the use of support vector regression (SVR) for forecasting.Given the exchange rates of a currency pair as scalar observations, observed time series is first analyzed to verify the existence of underlying nonlinear dynamics governing its evolution over time. Then, the time series is embedded into a higher dimensional phase space using embedding parameters.In the selection process to find the optimal embedding parameters,a novel method based on the Differential Evolution (DE) geneticalgorithm(as a global optimization technique) was applied. The authors have compared forecasting accuracy of the proposed model against the ordinary use of support vector regression. The experimental results demonstrate that the proposed method, which is based on chaos theory and genetic algorithm,is comparable with the existing approaches.

Regional forecasts of photovoltaic power generation according to different data availability scenarios: a study of four methods

AbstractThe development of methods to forecast photovoltaic (PV) power generation regionally is of utmost importance to support the spread of such power systems in current power grids. The objective of this study is to propose and to evaluate methods to forecast regional PV power 1 day ahead of time and to compare their performances. Four forecast methods were regarded, of which two are new ones proposed in this study. Together, they characterize a set of forecast methods that can be applied in different scenarios regarding availability of data and infrastructure to make the forecasts. The forecast methods were based on the use of support vector regression and weather prediction data. Evaluations were performed for 1 year of hourly forecasts using data of 273 PV systems installed in two adjacent regions in Japan, Kanto, and Chubu. The results show the importance of selecting the proper forecast method regarding the region characteristics. For Chubu, the region with a variety of weather conditions, the forecast methods based on single systems' forecasts and the one based on stratified sampling provided the best results. In this case, the best annual normalized root mean square error (RMSE) and mean absolute error (MAE) were 0.25 and 0.15 kWh/kWhavg, respectively. For Kanto, with homogeneous weather conditions, the four methods performed similarly. In this case, the lowest annual forecast errors were 0.33 kWh/kWhavg for the normalized RMSE and 0.202 kWh/kWhavg for the normalized MAE. Copyright © 2014 John Wiley &amp; Sons, Ltd.

Operating Rules Derivation of Jinsha Reservoirs System with Parameter Calibrated Support Vector Regression

The reservoir optimal operation depends on not only specific characteristics of reservoirs and hydropower stations but also stochastic inflows. The key issue of actual hydropower operation is to make an approximate optimal decision triggered by limited inflow forecasts. To implement actual optimal operation of hydropower system with limited inflows forecast, this paper makes use of Support Vector Regression (SVR) to derive optimal operating rules. To improve the performance of SVR, parameters in SVR model are calibrated with grid search and cross validation techniques. The trained SVR model describes the complex nonlinear relationships between reservoir operation decisions and factors by considering both generalization and regression performance, which overcomes local optimization and over fitting deficits. Hybrid programming platform is further developed to implement system simulation. This SVR model along with simulation platform is applied to the largest hydropower base in China – Jinsha system. Three scenarios are developed for comparison: deterministic optimal operation, SVR based simulation with calibrated parameters, SVR based simulation with default parameters. Comprehensive evaluation indicates that, operating rules derived from SVR presents a reliable performance in system power generation and output processes with respect to ideal deterministic results, especially when the parameters are calibrated. Hybrid programming technique provides a feasible and compatible platform for future research.

Variable selection and uncertainty analysis of scale growth rate under pre-salt oil wells conditions using support vector regression

The formation of inorganic scale, particularly calcium carbonate (CaCO3), is a persistent and one of the most serious and costly problems in the oil and gas industries. This event may cause partial to complete plugging, block valves, tubing and flowlines, and then reduce the production rates. This article proposes the use of support vector regression to build a nonlinear mapping between a set of variables (surface cladding, material, temperature, pressure, brine composition, and fluid velocity) and the scale build-up. The support vector regression is fed with data gathered from laboratory tests carried out on coupons that simulate realistic downhole conditions encountered in oil well bores from the pre-salt fields in Brazil. The proposed failure prediction framework is comprehensive as it entails the stages of hyperparameter tuning, variable selection, and uncertainty analysis, which are addressed by a combination of particle swarm optimization and bootstrap with support vector regression. The obtained results suggest that the bootstrapped particle swarm optimization + support vector regression is a valuable tool that may be used to support condition-based maintenance-related decisions.

Detection of Total Phosphorus Concentrations of Turbid Inland Waters Using a Remote Sensing Method

Phosphorus (P) is widely known as a limiting nutrient of water eutrophication for inland freshwater ecosystems. Owing to the complexity of P chemistry, remote sensing detection of total phosphorus (TP) concentrations currently remains limited especially for optically complex turbid inland waters. To address this need, a new TP remote sensing algorithm is developed based on prior water optical classification and the use of support vector regression (SVR) machine. The in situ observed datasets, used in this study, were collected at specific times during 2009 ~ 2011, covering a total of 232 stations from eight cruises in Lakes Taihu, Chaohu, Dianchi, and Three Gorges reservoir of China. Three types of waters were first classified by using a recently developed NTD675 (Normalized Trough Depth of spectral reflectance at 675 nm) water classification method. Then, spectral regions sensitive specifically to each water type were explored and expressed via several band ratios and used for retrieval algorithm development. The established type-specific SVR algorithms yield relatively high predictive accuracies. Specifically, the mean absolute percentage errors (MAPE) produced with the independent validation samples were achieved at 32.7, 23.2, and 14.1 % for type 1, type 2, and type 3 waters, respectively. Such water type-specific SVR algorithms are more accurate for the classified waters than an aggregated SVR algorithm for the nonclassified water and also superior to commonly used statistical algorithms. Moreover, application of the developed algorithms with HJ1A/HSI image data demonstrates that the algorithms have a large potential for remote sensing estimation of TP concentrations in optically complex turbid inland waters.

Use of Support Vector Regression to Improve Computational Efficiency of Stochastic Time-Cost Trade-Off

AbstractStochastic time-cost trade-off has been a popular object of investigation in past decades because there are uncertain factors that can be considered when determining the appropriate trade-off between project completion time and cost. Previous studies, however, have implemented a double loop procedure, which performs optimization in the outer loop and simulation in the inner loop. The double loop procedure is ponderous because it requires an unacceptably long computation time (taking hours or days), even for a small to medium project. The present study proposes an integrated system that converts the double loop to single loops,thereby dramatically reducing computation time. This is done by incorporating a support vector regression model to obtain a decision function, which will be used to replace the time-consuming Monte Carlo simulation to evaluate the objective function values for individual solutions. With the objective function values, a multiobjective particle swarm optimization algorithm is d...

On-board state of health monitoring of lithium-ion batteries using incremental capacity analysis with support vector regression

Battery state of health (SOH) monitoring has become a crucial challenge in hybrid electric vehicles (HEVs) and all electric vehicles (EVs) research, as SOH significantly affects the overall vehicle performance and life cycle. In this paper, we focus on the identification of Li-ion battery capacity fading, as the loss of capacity and therefore the driving range is a primary concern for EV and plug-in HEV (PHEV). While most studies on battery capacity fading are based on laboratory measurement such as open circuit voltage (OCV) curve, few publications have focused on capacity loss monitoring during on-board operations. We propose a battery SOH monitoring scheme based on partially charging data. Through analysis of battery aging cycle data, a robust signature associated with battery aging is identified through incremental capacity analysis (ICA). Several algorithms to extract this signature are developed and evaluated for on-board SOH monitoring. The use of support vector regression (SVR) is shown to provide the most consistent identification results with moderate computational load. For battery cells tested, we show that the SVR model built upon the data from one single cell is able to predict the capacity fading of 7 other cells within 1% error bound.

Estimation of tensile strength of ductile iron friction welded joints using hybrid intelligent methods

A hybrid intelligent method for evaluation of near optimal settings of friction welding process parameters of ductile iron was presented. The optimization of welding parameters was carried out in automatic cycle with the use of support vector regression (SVR), genetic algorithm (GA) and imperialist competitive algorithm (ICA). The method suggested was used to determine welding process parameters by which the desired tensile strength was obtained in the friction welding of ductile iron. The highest tensile strength (TS) of 256.93 MPa was obtained using SVR plus GA method for the following friction welding parameters: heating force 40 kN, heating time 300 s and upsetting force 10.12 kN. The samples were welded by friction and subjected to the tensile strength test. The optimized values obtained by means of these hybrid techniques were compared with the experimental results. The application of hybrid intelligent methods allowed to increase the tensile strength joints from 211 to 258 MPa for the friction welder ZT–14 type.

Comparison and Analysis of Different Software Cost Estimation Methods

Software cost estimation is the process of predicting the effort required to develop a software system. The basic input for the software cost estimation is coding size and set of cost drivers, the output is Effort in terms of Person-Months (PM’s). Here, the use of support vector regression (SVR) has been proposed for the estimation of software project effort. We have used the COCOMO dataset and our results are compared to Intermediate COCOMO as well as to MOPSO model results for this dataset. It has been observed from the simulation that SVR outperforms other estimating techniques. This paper provides a comparative study on support vector regression (SVR), Intermediate COCOMO and Multiple Objective Particle Swarm Optimization (MOPSO) model for estimation of software project effort. We have analyzed in terms of accuracy and Error rate. Here, data mining tool Weka is used for simulation

A statistical fault detection and diagnosis method for centrifugal chillers based on exponentially-weighted moving average control charts and support vector regression

This paper presents a new fault detection and diagnosis (FDD) method for centrifugal chillers of building air-conditioning systems. Firstly, the Support Vector Regression (SVR) is adopted to develop the reference PI models. A new PI, namely the heat transfer efficiency of the sub-cooling section (ɛsc), is proposed to improve the FDD performance. Secondly, the Exponentially-Weighted Moving Average (EWMA) control charts are introduced to detect faults in a statistical way to improve the ratios of correctly detected points. Thirdly, when faults are detected, diagnosis follows which is based on a proposed FDD rule table. Six typical chiller component faults are concerned in this paper. This method is validated using the real-time experimental data from the ASHRAE RP-1043. Test results show that the combined use of SVR and EWMA can achieve the best performance. Results also show that significant improvements are achieved compared with a commonly used method using Multiple Linear Regression (MLR) and t-statistic.

Use of support vector regression in structural optimization: Application to vehicle crashworthiness design

Metamodel is widely used to deal with analysis and optimization of complex system. Structural optimization related to crashworthiness is of particular importance to automotive industry nowadays, which involves highly nonlinear characteristics with material and structural parameters. This paper presents two industrial cases using support vector regression (SVR) for vehicle crashworthiness design. The first application aims to improve roof crush resistance force, and the other is lightweight design of vehicle front end structure subject to frontal crash, where SVR is utilized to construct crashworthiness responses. The use of multiple instances of SVR with different kernel types and hyper-parameters simultaneously and select the best accurate one for subsequent optimization is proposed. The case studies present the successful use of SVR for structural crashworthiness design. It is also demonstrated that SVR is a promising alternative for approximating highly nonlinear crash problems, showing a successfully alternative for metamodel-based design optimization in practice.