Proceedings Article10.1109/ICNC.2007.540
Parameter Selection for Sub-hyper-sphere Support Vector Machine
Peng Chen,Tao Wen +1 more
- 24 Aug 2007
- Vol. 1, pp 628-631
5
TL;DR: A new GA-based parameter selection method is presented to get better generalization accuracy in sub-hyper-sphere support vector machines when dealing with multi-class classification problem.
read more
Abstract: Sub-hyper-sphere support vector machines (SVMs) are proposed for solving the classification of the intersections of hyper-spheres when dealing with multi-class classification problem. Since the Gaussian kernel parameter influences the overlap position of the hyper-spheres, the resulting minimum bounding sphere-based classifier must be chosen optimally. This paper presents a new GA-based parameter selection method to get better generalization accuracy. Experimental results show the proposed approach is feasible and efficient.
read more
Chat with Paper
AI Agents for this Paper
Find similar papers on Google Scholar, PubMed and Arxiv
Write a critical review of this paper
Analyze citations of this paper to find unaddressed research gaps
Citations
Patent
Cognitive distributed network
Aaron K. Baughman,Thomas B. Harrison,Brian M. O'Connell,Herbert D. Pearthree +3 more
- 10 Apr 2014
TL;DR: In this paper, the authors present an approach for answering an inquiry of a cognitive distributed network, which is based on the natural language of the inquiry and a classification for the inquiry based on natural language.
41
Patent
Hyperparameter and network topology selection in network demand forecasting
Aaron K. Baughman,Brian M. O'Connell,Michael Perlitz,Stefan A. G. Van Der Stockt +3 more
- 08 Apr 2014
TL;DR: In this article, the authors proposed an approach for optimizing network demand forecasting models and network topology using hyperparameter selection, which includes defining a pool of features that are usable in models that predict demand of network resources.
18
Patent
Forecasting computer resources demand
Aaron K. Baughman,Richard J. Bogdany,Richard A. Locke,Brian M. O'Connell +3 more
- 04 Apr 2014
TL;DR: In this paper, the authors present an approach for forecasting demand that includes a method that includes receiving one or more variables associated with an event and then generating a model to forecast future demand based on the one or multiple variables.
17
Patent
Network demand forecasting
Aaron K. Baughman,James R. Kozloski,Brian M. O'Connell +2 more
- 04 Apr 2014
TL;DR: In this paper, the authors present an approach for predicting demand spikes and cyclic demand for web-related content based on generating multiple models and inputting information into the model, and the approach further includes generating a total predicted demand curve by combining the predicted demand spike with predicted cyclical demand.
16
Patent
Dynamic network monitoring
Aaron K. Baughman,Richard A. Locke,Brian M. O'Connell,Brian J. Snitzer +3 more
- 24 May 2016
TL;DR: In this paper, an approach for monitoring performance in a networked environment is presented. But, the approach is limited to monitoring the performance of a first host running a virtual machine.
12
References
A Genetic Algorithm for Function Optimization: A Matlab Implementation
Christopher R. Houck
- 01 Jan 2001
TL;DR: The genetic algorithm using a oat representation is found to be superior to both a binary genetic algorithm and simulated annealing in terms of e ciency and quality of solution.
1.3K
•Proceedings Article
Extracting support data for a given task
Bernhard Schölkopf,Chris Burges,Vladimir Vapnik +2 more
- 20 Aug 1995
TL;DR: It is observed that three different types of handwritten digit classifiers construct their decision surface from strongly overlapping small subsets of the data base, which opens up the possibility of compressing data bases significantly by disposing of theData which is not important for the solution of a given task.
Sphere-structured support vector machines for multi-class pattern recognition
Meilin Zhu,Yue Wang,Shi-Fu Chen,Xiangdong Liu +3 more
- 26 May 2003
TL;DR: This paper provides a new algorithm called sphere-structured SVMs to solve the multi-class problem of support vector machines, and shows the algorithm in detail and analyzes its characteristics.
43