oalib
Search Results: 1 - 10 of 100 matches for " "
All listed articles are free for downloading (OA Articles)
Page 1 /100
Display every page Item
Classification of Textual Documents Using Learning Vector Quantization  [PDF]
Muhammad Fahad Umer,M. Sikander Hayat Khiyal
Information Technology Journal , 2007,
Abstract: The classification of a large collection of texts into predefined set of classes is an enduring research problem. The comparative study of classification algorithms shows that there is a tradeoff between accuracy and complexity of the classification systems. This study evaluates the Learning Vector Quantization (LVQ) network for classifying text documents. In the LVQ method, each class is described by a relatively small number of codebook vectors. These codebook vectors are placed in the feature space such that the decision boundaries are approximated by the nearest neighbor rule. The LVQ require less training examples and are much faster than other classification methods. The experimental results show that the Learning Vector Quantization approach outperforms the k-NN, Rocchio, NB and Decision Tree classifiers and is comparable to SVMs.
Learning Rates of Support Vector Machine Classifiers with Data Dependent Hypothesis Spaces
Bao-Huai Sheng,Pei-Xin Ye
Journal of Computers , 2012, DOI: 10.4304/jcp.7.1.252-257
Abstract: We study the error performances of -norm Support Vector Machine classifiers based on reproducing kernel Hilbert spaces. We focus on two category problem and choose the data-dependent polynomial kernels as the Mercer kernel to improve the approximation error. We also provide the standard estimation of the sample error, and derive the explicit learning rate.
Convergence of distributed asynchronous learning vector quantization algorithms  [PDF]
Beno?t Patra
Statistics , 2010,
Abstract: Motivated by the problem of effectively executing clustering algorithms on very large data sets, we address a model for large scale distributed clustering methods. To this end, we briefly recall some standards on the quantization problem and some results on the almost sure convergence of the Competitive Learning Vector Quantization (CLVQ) procedure. A general model for linear distributed asynchronous algorithms well adapted to several parallel computing architectures is also discussed. Our approach brings together this scalable model and the CLVQ algorithm, and we call the resulting technique the Distributed Asynchronous Learning Vector Quantization algorithm (DALVQ). An in-depth analysis of the almost sure convergence of the DALVQ algorithm is performed. A striking result is that we prove that the multiple versions of the quantizers distributed among the processors in the parallel architecture asymptotically reach a consensus almost surely. Furthermore, we also show that these versions converge almost surely towards the same nearly optimal value for the quantization criterion.
Regularization in Relevance Learning Vector Quantization Using l one Norms  [PDF]
Martin Riedel,Marika K?stner,Fabrice Rossi,Thomas Villmann
Computer Science , 2013,
Abstract: We propose in this contribution a method for l one regularization in prototype based relevance learning vector quantization (LVQ) for sparse relevance profiles. Sparse relevance profiles in hyperspectral data analysis fade down those spectral bands which are not necessary for classification. In particular, we consider the sparsity in the relevance profile enforced by LASSO optimization. The latter one is obtained by a gradient learning scheme using a differentiable parametrized approximation of the $l_{1}$-norm, which has an upper error bound. We extend this regularization idea also to the matrix learning variant of LVQ as the natural generalization of relevance learning.
Learning Vector Quantization (LVQ) and k-Nearest Neighbor for Intrusion Classification  [cached]
Reyadh Shaker Naoum,Zainab Namh Al-Sultani
World of Computer Science and Information Technology Journal , 2012,
Abstract: Attacks on computer infrastructure are becoming an increasingly serious problem nowadays, and with the rapid expansion of computer networks during the past decade, computer security has become a crucial issue for protecting systems against threats, such as intrusions. Intrusion detection is an interesting approach that could be used to improve the security of network system. Different soft-computing based methods have been proposed in recent years for the development of intrusion detection systems. This paper presents a composition of Learning Vector Quantization artificial neural network and k-Nearest Neighbor approach to detect intrusion. A Supervised Learning Vector Quantization (LVQ) was trained for the intrusion detection system; it consists of two layers with two different transfer functions, competitive and linear. Competitive (hidden) and output layers contain a specific number of neurons which are the sub attack types and the main attack types respectively. k-Nearest Neighbor (kNN) as a machine learning algorithm was implemented using different distance measures and different k values, but the results demonstrates that using the first norm instead the second norm and using k=1 gave the best results among other possibilities. The experiments and evaluations of the proposed method have been performed using the NSL-KDD 99 intrusion detection dataset. Hybrid (LVQ_kNN) was able to classify the datasets into five classes at learning rate 0.09 using 23 hidden neurons with classification rate about 89%.
A Learning Vector Quantization Based Recognition Technique for Arabic Characters
Amer Al- Nassiri
Asian Journal of Information Technology , 2012,
Abstract: Artificial Neural Networks (ANN `s) have been successfully applied to optical character recognition (OCR) yielding excellent results. This paper describes improvements to a system that recognize Arabic character in a low and high resolution binary document images. A classical conventional algorithm that uses chain coding for the segmentation of words, while an Learning Vector Quantization (LVQ) network is used to identify the segmented Arabic characters. Performance advances reflected in the current system largely result from the introduction of ensembles Freeman Arabic Classification Tree (FACT) (Al-Nasssiri, 2001), as the base for LVQ recognizer. By using features produced by chain coding algorithm, FACT, and LVQ (as a classifier), we have obtained high recognition rate on printed Arabic character. Application of LVQ demonstrates the arbitrary of the method to significantly reduce the computational lost of the classification system and improves the recognition rate. On characters extracted from more than 40 test images (pages) scanned with various kinds of scanners with 300 and 600 dpi scanning resolution, in addition to various degree of noise, the current system attains a character recognition rate within 88- 92%.
SISTEM VERIFIKASI WAJAH MENGGUNAKAN JARINGAN SARAF TIRUAN LEARNING VECTOR QUANTIZATION  [cached]
Abdul Fadlil,Surya Yeki
Jurnal Informatika , 2012,
Abstract: Verifikasi wajah merupakan salah satu teknologi biometrika yang menjadi perhatian para peneliti. Banyak sekali sistem aplikasi yang berbasis kepada verifikasi wajah misalnya: akses pintu, akses mesin ATM, sistem presensi kehadiran, dll. Pada makalah ini akan dibahas perancangan dan pembuatan sistem verifikasi wajah manusia menggunakan metode ekstraksi menggunakan metode SPCA (Simple Principle Component Analysis) dan teknik klasifikasi jaringan saraf tiruan Learning Vector Quantization. Data citra wajah yang digunakan berasal dari 5 orang yang terdiri masing-masing sebanyak 10 citra wajah untuk proses pelatihan dan juga masing-masing sebanyak 10 wajah untuk proses pengujian. Hasil pengujian unjuk kerja sistem didapat nilai FRR rata-rata 0% dan FAR rata-rata = 1,55%.
Analysis of Flow Cytometry Data by Matrix Relevance Learning Vector Quantization  [PDF]
Michael Biehl, Kerstin Bunte, Petra Schneider
PLOS ONE , 2013, DOI: 10.1371/journal.pone.0059401
Abstract: Flow cytometry is a widely used technique for the analysis of cell populations in the study and diagnosis of human diseases. It yields large amounts of high-dimensional data, the analysis of which would clearly benefit from efficient computational approaches aiming at automated diagnosis and decision support. This article presents our analysis of flow cytometry data in the framework of the DREAM6/FlowCAP2 Molecular Classification of Acute Myeloid Leukemia (AML) Challenge, 2011. In the challenge, example data was provided for a set of 179 subjects, comprising healthy donors and 23 cases of AML. The participants were asked to provide predictions with respect to the condition of 180 patients in a test set. We extracted feature vectors from the data in terms of single marker statistics, including characteristic moments, median and interquartile range of the observed values. Subsequently, we applied Generalized Matrix Relevance Learning Vector Quantization (GMLVQ), a machine learning technique which extends standard LVQ by an adaptive distance measure. Our method achieved the best possible performance with respect to the diagnoses of test set patients. The extraction of features from the flow cytometry data is outlined in detail, the machine learning approach is discussed and classification results are presented. In addition, we illustrate how GMLVQ can provide deeper insight into the problem by allowing to infer the relevance of specific markers and features for the diagnosis.
Learning Mixtures of Linear Classifiers  [PDF]
Yuekai Sun,Stratis Ioannidis,Andrea Montanari
Computer Science , 2013,
Abstract: We consider a discriminative learning (regression) problem, whereby the regression function is a convex combination of k linear classifiers. Existing approaches are based on the EM algorithm, or similar techniques, without provable guarantees. We develop a simple method based on spectral techniques and a `mirroring' trick, that discovers the subspace spanned by the classifiers' parameter vectors. Under a probabilistic assumption on the feature vector distribution, we prove that this approach has nearly optimal statistical efficiency.
Workforce Assignment into Virtual Cells using Learning Vector Quantization (LVQ) Approach  [cached]
R.V. Murali
Research Journal of Applied Sciences, Engineering and Technology , 2012,
Abstract: In this study, an attempt has been made to apply Learning Vector Quantization (LVQ) approach, one of the network types of Artificial Neural Networks (ANN), into worker assignment problems for VCMS environment and analyze the network performance and effectiveness under different cell configurations and time periods. Worker assignment problems assume a crucial role in any type of manufacturing systems due to the fact that it is one of the major resource implicating factors. Its influence is much more significant in case of a dynamic production environment such as cell-based manufacturing systems. In this type production environment, product variety is changing very rapidly prompting the need to redesign the production facility quickly so as to accommodate agility. Virtual Cellular Manufacturing Systems (VCMS) have come into existence, replacing traditional Cellular Manufacturing Systems (CMS), to meet highly dynamic production conditions in terms of demand, production lots, processing times, product mix and production sequences. Traditional CMS involves formation of machine cells and part families based on the similarity characteristics in the product and process route. While cell formation phase has been dealt quite voluminously, researchers have started realizing, not long before, that workers’ role during implementation of this cell-based manufacturing systems has been a major dimension. The problem of worker assignment and flexibility in cell based manufacturing environments has been studied and analyzed in plenty and various heuristics/mathematical models are developed to achieve reduced labor costs, improved productivity and quality, effective utilization of workforce and providing adequate levels of labor flexibility. Application of ANN, adapted from the biological neural networks, is the recent development in this field exploiting its ability to work out mathematically-difficult-to-solve problems. Previous studies of the author have prompted that ANN technique is a useful approach for solving worker assignment problems while the present study expands the previous efforts through applying a unique class of ANN i.e., LVQ into worker assignment problems for VCMS environment. The results obtained in this study affirm that LVQ based approach is useful and effective under different cell configurations and time periods.
Page 1 /100
Display every page Item


Home
Copyright © 2008-2017 Open Access Library. All rights reserved.