Loading...
Search for:
patterns-classification
0.011 seconds
Semipolynomial kernel optimization based on the fisher method
, Article IEEE International Workshop on Machine Learning for Signal Processing, 18 September 2011 through 21 September 2011 ; September , 2011 , Page(s): 1 - 6 ; 9781457716232 (ISBN) ; Sadeghipoor, Z ; Manzuri, M. T ; Sharif University of Technology
Abstract
Kernel based methods are significantly important in the pattern classification problem, especially when different classes are not linearly separable. In this paper, we propose a new kernel, which is the modified version of the polynomial kernel. The free parameter (d) of the proposed kernel considerably affects the error rate of the classifier. Thus, we present a new algorithm based on the Fisher criterion to find the optimum value of d. Simulation results show that using the proposed kernel for classification leads to satisfactory results. In our simulation in most cases the proposed method outperforms the classification using the polynomial kernel
Application of Semi-Supervised Learning in Image Processing
, M.Sc. Thesis Sharif University of Technology ; Rabiee, Hamidreza (Supervisor)
Abstract
In recent years, the emergence of semi-supervised learning methods has broadened the scope of machine learning, especially for pattern classification. Besides obviating the need for experts to label the data, efficient use of unlabeled data causes a significant improvement in supervised learning methods in many applications. With the advent of statistical learning theory in the late 80's, and the emergence of the concept of regularization, kernel learning has always been in deep concentration. In recent years, semi-supervised kernel learning, which is a combination of the two above-mentioned viewpoints, has been considered greatly.
Large number of dimensions of the input data along with...
Large number of dimensions of the input data along with...
Semi-Supervised Kernel Learning for Pattern Classification
, Ph.D. Dissertation Sharif University of Technology ; Rabiee, Hamid Reza (Supervisor)
Abstract
Supervised kernel learning has been the focus of research in recent years. Although these methods are developed based on rigorous frameworks, they fail to improve the classification accuracy in real world applications. In order to find the origin of this problem, it should be noted that the kernel function represents a prior knowledge on the labeling function. Similar to other learning problem, learning this prior knowledge needs another prior knowledge. In supervised kernel learning, only naive assumptions can be used as the prior knowledge. These include minimizing the ℓ1 and ℓ2 norms of the kernel parameters.
As an alternative approach, in Semi-Supervised Learning (SSL), unlabeled...
As an alternative approach, in Semi-Supervised Learning (SSL), unlabeled...
Intrusion detection in computer networks using tabu search based Fuzzy system
, Article 2008 7th IEEE International Conference on Cybernetic Intelligent Systems, CIS 2008, London, 9 September 2008 through 10 September 2008 ; March , 2008 ; 9781424429141 (ISBN) ; Habibi, J ; Saadi, H ; Sharif University of Technology
2008
Abstract
The process of scanning the events occurring in a computer system or network and analyzing them for warning of intrusions is known as intrusion detection system (IDS). This paper presents a new intrusion detection system based on tabu search based fuzzy system. Here, we use tabu search algorithm to effectively explore and exploit the large state space associated with intrusion detection as a complicated classification problem. Experiments were performed on KDD-Cup99 data set which has information about intrusive and normal behaviors on computer networks. Results show that the proposed method obtains notable accuracy and lower cost in comparison with several renowned algorithms
Classification of wide variety range of power quality disturbances based on two dimensional wavelet transformation
, Article PEDSTC 2010 - 1st Power Electronics and Drive Systems and Technologies Conference, 17 February 2010 through 18 February 2010, Tehran ; 2010 , Pages 398-405 ; 9781424459728 (ISBN) ; Mokhtari, H ; Sharif University of Technology
2010
Abstract
Identification of voltage and current disturbances is an important task in power system monitoring and protection. In this paper, a new algorithm for online characterization of a wide range of voltage disturbances based on two dimensional wavelet transformation is proposed. This algorithm is more complicated than algorithms based on one dimensional wavelet transformation, but it's more precise and is useful for steady state disturbances, transients with slow variations and transients with rapid changes. After each five cycles, a matrix is formed based on the last fourteen cycles, in a way that the voltage signal in one cycle forms one row of the matrix. Then, the resulted image is decomposed...
Using a memristor crossbar structure to implement a novel adaptive real-time fuzzy modeling algorithm
, Article Fuzzy Sets and Systems ; Volume 307 , 2017 , Pages 115-128 ; 01650114 (ISSN) ; Bagheri Shouraki, S ; Merrikh Bayat, F ; Gholami, M ; Sharif University of Technology
Elsevier B.V
2017
Abstract
Fuzzy techniques can be used for accurate and high-speed modeling as well as for the control of complex systems, but various challenging problems are usually encountered during their actual implementation. For example, the variable parameters need to be optimized iteratively during the training phase, where this process is inspired by crisp domain algorithms. However, in recent years, memristor-based structures have emerged as another promising method for implementing neural network structures and fuzzy algorithms. In this study, we propose a novel adaptive and real-time fuzzy modeling algorithm, which employs the active learning method concept to mimic the functionality of the brain's right...