Training <i>v</i>-Support Vector Regression: Theory and Algorithms

Chang, Chia‐Jung; Lin, Chih-Jen

doi:10.1162/089976602760128081

Cited by 282 publications

(144 citation statements)

References 11 publications

Supporting

Mentioning

140

Contrasting

Unclassified

Order By: Relevance

“…ν-SVR is used in this study since it requires less tuning and fewer number of parameters than ɛ-SVR. It also automatically minimizes the loss function and has been shown to support more meaningful data interpretation [41,42]; this premise is validated by results from this research.…”

Section: Theorysupporting

confidence: 62%

Support vector regression for anomaly detection from measurement histories

Kromanis

Kripakaran

2013

Advanced Engineering Informatics

View full text Add to dashboard Cite

Section: Theorysupporting

confidence: 62%

Support vector regression for anomaly detection from measurement histories

Kromanis

Kripakaran

2013

Advanced Engineering Informatics

View full text Add to dashboard Cite

“…In such there is no necessity to map the data to a higher dimensional space as the non-linear mapping here does not improve the model performance, while significantly affects the requirements for computing power and time [47]. This assumption was confirmed by Bray and Han who tested the performance of different kernels in the LIBSVM toolkit for runoff modeling [48] and identified nu-SVR with the linear kernel as an optimal configuration in terms of learning capabilities.…”

Section: Model Setup and Learningmentioning

confidence: 83%

Applicability of a Nu-Support Vector Regression Model for the Completion of Missing Data in Hydrological Time Series

Langhammer

Česák

2016

Water

View full text Add to dashboard Cite

This paper analyzes the potential of a nu-support vector regression (nu-SVR) model for the reconstruction of missing data of hydrological time series from a sensor network. Sensor networks are currently experiencing rapid growth of applications in experimental research and monitoring and provide an opportunity to study the dynamics of hydrological processes in previously ungauged or remote areas. Due to physical vulnerability or limited maintenance, networks are prone to data outages, which can devaluate the unique data sources. This paper analyzes the potential of a nu-SVR model to simulate water levels in a network of sensors in four nested experimental catchments in a mid-latitude montane environment. The model was applied to a range of typical runoff situations, including a single event storm, multi-peak flood event, snowmelt, rain on snow and a low flow period. The simulations based on daily values proved the high efficiency of the nu-SVR modeling approach to simulate the hydrological processes in a network of monitoring stations. The model proved its ability to reliably reconstruct and simulate typical runoff situations, including complex events, such as rain on snow or flooding from recurrent regional rain. The worst model performance was observed at low flow periods and for single peak flows, especially in the high-altitude catchments.

show abstract

“…The two variants -SVR [8] and ν-SVR [9], [10] were evaluated. The free model parameters and ν for the respective algorithms, and C as the regularization parameter in both approaches, were experimentally chosen.…”

Section: Applied Machine Learning Methodsmentioning

confidence: 99%

Generalization of optimal motion trajectories for bipedal walking

Werner

Trautmann

Lee

et al. 2015

2015 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)

View full text Add to dashboard Cite

Abstract-Control of robot locomotion profits from the use of pre-planned trajectories. This paper presents a way to generalize globally optimal and dynamically consistent trajectories for cyclic bipedal walking. A small task-space consisting of stride-length and step time is mapped to spline parameters which fully define the optimal joint space motion. The paper presents the impact of different machine learning algorithms for velocity and torque optimal trajectories with respect to optimality and feasibility. To demonstrate the usefulness of the trajectories, a control approach is presented that allows general walking including transitions between points in the task-space. I. IntroductionAs many aspects of robotics technology improve, robots cover more tasks such as manipulating objects in complex environments. Often designed with humans in mind, these environments feature challenges like stairs or uneven terrain. It is therefore desirable that robots have matching abilities when it comes to locomotion in these environments. This motivates the use of legged locomotion for our robotic platforms.However, legged locomotion comes with rather complex kinematics and dynamics which still provide plenty of challenges for planning and control. All approaches create a mapping between the task of moving the robot somewhere and a suitable trajectory which deals with the full complexity of the robot. Models of varying complexity [1] are used to create this mapping. Creating a trajectory using a model that contains all degrees of freedom and takes into account the systems limitations is however not feasible when the solution should be created on-line, taking into account the task and the environment.The approach developed in this work, first presented in [2], provides this mapping from the task-space to the trajectory. For this it uses a combined approach of trajectory planning using non-linear optimization and generalization of these results by current machine learning methods. The optimization allows exploitation of the dynamics of the system by using strong models. This paper contains an analysis of the performance of a set of machine learning algorithms in providing this mapping for a successful execution of the task.

show abstract

Training v-Support Vector Regression: Theory and Algorithms

Cited by 282 publications

References 11 publications

Support vector regression for anomaly detection from measurement histories

Support vector regression for anomaly detection from measurement histories

Applicability of a Nu-Support Vector Regression Model for the Completion of Missing Data in Hydrological Time Series

Generalization of optimal motion trajectories for bipedal walking

Contact Info

Product

Resources

About