1 |
PREDICTION OF 28-DAY COMPRESSIVE STRENGTH OF CONCRETE USING RELEVANCE VECTOR MACHINES (RVM)Owusu Twumasi, Jones 01 May 2013 (has links)
Early and accurate prediction of the compressive strength of concrete is important in the construction industry. Modeling the compressive strength of concrete to obtain a balance and equality between prediction accuracy, time and uncertainty of the prediction is a very difficult task due to the highly nonlinear nature of concrete. For structural engineering purposes, the 28- day compressive strength is the most relevant parameter. In this study, an attempt has been made to predict the 28-day compressive strength of concrete using Relevance Vector Machine (RVM). An RVM belongs to the class of sparse kernel classifiers, which are powerful tools in classification and regression. It has a model of identical functional form to the popular and state-of-the-art `Support Vector Machine (SVM)'. The benefits of using RVM include automatic estimation of nuisance parameters, probabilistic prediction and the ability to model complex data with little information. A total of 425 different data of high performance mix designs were collected from the University of California, Irvine repository. The data used to predict the compressive strength consisted of nine components. The RVM model was trained and tested using 395 and 30 data sets respectively. The model's performance was assessed at the end of the training and testing period using four performance measures; coefficient of determination, root-mean-square error, percentage of relevance vectors and residual plots. All the performance measures confirmed the accuracy of the model. The results of the study suggested that RVM is an effective tool for predicting the 28- day compressive strength of concrete from its mix ingredients.
|
2 |
Using Relevance Vector Machines Approach for Prediction of Total Suspended Solids and Turbidity to Sustain Water Quality and Wildlife in Mud LakeBatt, Hussein Aly 01 May 2012 (has links)
Mud Lake is a wildlife refuge located in southeastern Idaho just north of Bear Lake that traps sediment from Bear River water flowing into Bear Lake.Very few water quality and sediment observations, if any, exist spatially in Mud Lake. Spatial patterns of sediment deposition may affect Mud Lake flows and habitat; prediction of those patterns should help refuge managers predict water quality constituents and spatial distribution of fine sediment.This will help sustain the purposes of Mud Lake as a habitat and migratory station for species.
The main objective of the research is the development of Multivariate Relevant Vector Machine (MVRVM) to predict suspended fine sediment and water quality constituents, and to provide an understanding for the practical problem of determining the amount of data required for the MVRVM. MVRVM isa statistical learning algorithm that is based on Bayes theory.It has been widely used to predict patterns in hydrological systems and other fields. This research represents the first known attempt to use a MVRVM approach to predict transport of very fine sediment andwater quality constituents in a complex natural system.
The results demonstrate the ability of the MVRVM to capture and predict the underlying patterns in data.Also careful construction of the experimental design for data collection can lead the Relevant Vectors (RVs is a subset of training observation which carries significant information that is used for prediction) to show locations of significant patterns.
The predictions of water quality constituents will be of potential value to US Fish and Wildlife refuge managers in making decisions for operation and management in the case of Mud Lake based on their objectives, and will lead the way for scientists to expand the use of the MVRVM for modeling of suspended fine sediment and water quality in complex natural systems.
|
3 |
Performance comparison of support vector machine and relevance vector machine classifiers for functional MRI dataPerez, Daniel Antonio 12 July 2010 (has links)
Multivariate pattern analysis (MVPA) of fMRI data has been growing in popularity due to its sensitivity to networks of brain activation. It is performed in a predictive modeling framework which is natural for implementing brain state prediction and real-time fMRI applications such as brain computer interfaces. Support vector machines (SVM) have been particularly popular for MVPA owing to their high prediction accuracy even with noisy datasets. Recent work has proposed the use of relevance vector machines (RVM) as an alternative to SVM. RVMs are particularly attractive in time sensitive applications such as real-time fMRI since they tend to perform classification faster than SVMs. Despite the use of both methods in fMRI research, little has been done to compare the performance of these two techniques. This study compares RVM to SVM in terms of time and accuracy to determine which is better suited to real-time applications.
|
4 |
Machine Learning for Market Prediction : Soft Margin Classifiers for Predicting the Sign of Return on Financial AssetsAbo Al Ahad, George, Salami, Abbas January 2018 (has links)
Forecasting procedures have found applications in a wide variety of areas within finance and have further shown to be one of the most challenging areas of finance. Having an immense variety of economic data, stakeholders aim to understand the current and future state of the market. Since it is hard for a human to make sense out of large amounts of data, different modeling techniques have been applied to extract useful information from financial databases, where machine learning techniques are among the most recent modeling techniques. Binary classifiers such as Support Vector Machines (SVMs) have to some extent been used for this purpose where extensions of the algorithm have been developed with increased prediction performance as the main goal. The objective of this study has been to develop a process for improving the performance when predicting the sign of return of financial time series with soft margin classifiers. An analysis regarding the algorithms is presented in this study followed by a description of the methodology that has been utilized. The developed process containing some of the presented soft margin classifiers, and other aspects of kernel methods such as Multiple Kernel Learning have shown pleasant results over the long term, in which the capability of capturing different market conditions have been shown to improve with the incorporation of different models and kernels, instead of only a single one. However, the results are mostly congruent with earlier studies in this field. Furthermore, two research questions have been answered where the complexity regarding the kernel functions that are used by the SVM have been studied and the robustness of the process as a whole. Complexity refers to achieving more complex feature maps through combining kernels by either adding, multiplying or functionally transforming them. It is not concluded that an increased complexity leads to a consistent improvement, however, the combined kernel function is superior during some of the periods of the time series used in this thesis for the individual models. The robustness has been investigated for different signal-to-noise ratio where it has been observed that windows with previously poor performance are more exposed to noise impact.
|
Page generated in 0.1046 seconds