Inquiry (E-Journal - Faculty of Business and Administration, International University of Sarajevo)
Not a member yet
209 research outputs found
Sort by
Authorship Categorization With Neural Network
Get PDFThis paper explores the use of neural networks in author classification. Also exploring the effect of stylometry is another aim of the research. Choosing the algorithm and descriptors are important issues in the research. In this paper methods for the multi-topic machine learning of an authorship attribution classifier were investigated using texts from novels as the data set. Artificial neural network is proposed to classify the texts of authors using a set of lexical descriptors and feed-forward neural network using back propagation. The result shows that Turkish authors Peyami Safa, Orhan Pamuk and Mustafa Necati Sepetcioglu’s two novels are successfully classified
Automatic Segmentation of Human Chromosomes
Get PDFThis paper is concerned with automatic segmentation of high resolution digitized metaphases. Firstly using a thresholding technique, a binary image of the cell picture is obtained. This binary image contains the addresses of darker pixels of the gray image of the colored cell picture. Several thousand of random points are assigned from among these addresses, and then using a distance condition, typically 50 pixels, and the number of centers is reduced to near 100. These points are search centers for chromosome segmentation. Algorithm first searches eight pixels surrounding the center. Picks the coordinates of the pixels darker than the gray level 0.9, then passes to one of the pixels recently recorded as dark enough, and repeat the same procedure to the neighbors which are not visited before. If none of the new neighbors are not darker than 0.9, search reaches at the boundaries of the chromosome, and ends. Then we call the pixels of the chromosomes in the colored image from the addresses in the binary counterparts to finish segmentation
Extracting Gray Level Profiles of Human Chromosomes by Curve Fitting
Get PDFIn this paper, a unified algorithm for extracting gray level profiles of Human chromosomes is presented. It is a unified approach since we do not discriminate chromosomes as straight and bended. This is a very helpful procedure which extends the domain of success of most of the previously reported algorithms to highly curved chromosomes. The gray image of the chromosome is thresholded at the gray level 0.9, and the matrix of gray image is transformed into a list of pixel coordinates whose gray level is less than 0.9. To the list of two dimensional points, the most appropriate smooth curve is fitted. Then this smooth curve subdivided into n arcs of equal lengths, and straight lines are drawn that are normal to the curve at the end points of the subdivision. The points of the list are classified into n bins according to their distance to these n straight lines. The average of gray levels of each bin gives the gray levels at the points of the gray level profile of the chromosome. It is seen that the gray level profiles of the bended chromosomes have a high similarity with the straight counterparts
Parallelization of genetic algorithms using Hadoop Map/Reduce
Get PDFIn this paper we present parallel implementation of genetic algorithm using map/reduce programming paradigm. Hadoop implementation of map/reduce library is used for this purpose. We compare our implementation with implementation presented in [1]. These two implementations are compared in solving One Max (Bit counting) problem. The comparison criteria between implementations are fitness convergence, quality of final solution, algorithm scalability, and cloud resource utilization. Our model for parallelization of genetic algorithm shows better performances and fitness convergence than model presented in [1], but our model has lower quality of solution because of species problem
Teaching Neural Networks to Detect the Authors of Texts Using Lexical Descriptors
Get PDFThis paper proposes a means of using an artificial neural network to distinguish the authors of paragraphs. Once the network has been trained, its hidden layer activations are recorded as a representation of the average number of words and average characters of words in a paragraphs of an author. This stored information can then be used to identify the texts written by authors. This computational task is solved by dividing it into a number of computationally simple tasks and then combining the solutions to those tasks. Computational simplicity is achieved by distributing the learning task among a number of experts, which in turn divides the input space into a set of subspaces. The combination of these experts is said to constitute a committee machine. Basically, it fuses knowledge acquired by experts to arrive at an overall decision that is supposedly superior to that attainable by anyone of them acting alone. By this, we succeeded to distinguish the paragraphs authored by Ivo Andrić, from the ones authored by Mehmed Meša Selimović
Teaching Neural Networks to Classify the Authors of Texts
Get PDFA lot of research has been done on author classification using various methodologies. One of them is using artificial neural networks. It is common that the number of descriptors used for author classification exceeds two. In this paper we propose a means of using artificial neural network to classify the authors of texts using only two descriptors: the number of words in a paragraph and a number of characters per word in a paragraph. The approach taken uses committee machines based on ensemble averaging. The basic idea is to solve the complex computational task by dividing it into a number of computationally simple tasks and then combining the solution of these tasks. The high performance achieved is because the committee is much better than the single best constituent in the isolation. Our results show that with the above approach we succeeded to correctly classify the works of Leo Tolstoy and George Orwell
Constrained Optimization with Evolutionary Algorithms: A Comprehensive Review
Get PDFGlobal optimization is an essential part of any kind of system. Various algorithms have been proposed that try to imitate the learning and problem solving abilities of the nature up to certain level. The main idea of all nature-inspired algorithms is to generate an interconnected network of individuals, a population. Although most of unconstrained optimization problems can be easily handled with Evolutionary Algorithms (EA), constrained optimization problems (COPs) are very complex. In this paper, a comprehensive literature review will be presented which summarizes the constraint handling techniques for COP
Classification of chromosomes using nearest neighbor classifier
Get PDFThis paper addresses automated classification of human chromosomes using k nearest neighbor classifier. k nearest neighbor classifier classifies objects according to the closest training sample in the feature space. Various distance functions can be used in computation of how close the object is to the training sample. In this work various different distance functions are used to compare the performance of each. It was found that Euclidean distance function produces the best results
Application of Ensemble Machines of Neural Networks to Chromosome Classification
Get PDFThis work presents approaches to the automatic classification of metaphase chromosomes using several perceptron neural network techniques on neural networks function as committee machines. To represent the banding patterns, only chromosome gray level profiles are exploited. The other inputs to the ensemble machines of the network are the chromosome size and centromeric index. It is shown that, without much effort, the classification performances of the four networks are found to be similar to the ones of a well-developed parametric classifier. Four parallel networks trained for the four different aspects of the data set, the gray level profile vector, Fourier coefficients of gray level profiles, 3D data of chromosome length – centromeric index – total gray levels, and 4D data obtained by the addition of average gray levels. Then the classification results of differently trained neural networks (i.e., experts), are combined by the use of a genuine ensemble-averaging to produce an overall output by the combiner. We discuss the flexibility of the classifier developed, its potential for development, and how it may be improved to suit the current needs in karyotyping
Three Variable Cancer Angiogenesis models
Get PDFIn this paper we present several mathematical models of tumor growth and angiogenesis expressed by systems of ODE’ s encoding the most essential observations and assumptions about the complex hierarchical interactive processes of tumor neo-vascularization (angiogenesis). The simplest modeling option presented merely captures the three independent variables mentioned earlier-tumor size N, total vessel volume V and the amount of protein P. We modify this model assuming that the protein is additionally consumed by growing vessels and obtain a model with protein consumption. Next models with time-delays are introduced. To make our models more realistic, two more compartments representing more complex vascularity and protein effects are introduced