Description:
In this paper we propose a novel technique of using a hybrid evolutionary method, which uses a combination of genetic algorithm and matrix based solution methods such as QR factorization. The training of the model is based on a layer based hierarchical structure for the architecture and the weights for the Artificial Neural Network classifier. The architecture for the classifier is found using a binary search type procedure. The hierarchical structured algorithm (EALS-BT) is also a hybrid, because it combines the Genetic Algorithm based method with the Matrix based solution method for finding weights. A heuristic segmentation algorithm is initially used to over segment each word. Then the segmentation points are passed through the rule-based module to discard the incorrect segmentation points and include any missing segmentation points. Following the segmentation the contour is extracted between two correct segmentation points. The contour is passed through the feature extraction module that extracts the angular features, after which the EALS-BT algorithm finds the architecture and the weights for the classifier network. These recognized characters are grouped into words and passed to a variable length lexicon that retrieves words that have the highest confidence value. ACM Classification: I.4 (Image Processing and Computer Vision)
Description:
The paper presents a feature extraction technique for online handwriting recognition. The technique incorporates many characteristics of handwritten characters based on structural, directional and zoning information and combines them to create a single global feature vector. The technique is independent to character size and it can extract features from the raw data without resizing. Using the proposed technique and a Neural Network based classifier, many experiments were conducted on UNIPEN benchmark database. The recognition rates are 98.2% for digits, 91.2% for uppercase and 91.4% for lowercase.
Description:
Many previous efforts have utilized many different approaches for recognition in breast cancer detection using various ANN classifier-modelling techniques. Most of the previous work was concentred mostly on the classification of the damaged areas with the help of doctor’s suggestion. Doctors use to mark the suspicious areas area in the mammogram and the classifier only extract those marked areas and tries to classify it. An intelligent automatic diagnosis system can be very helpful for radiologist in diagnosing Breast cancer. In this research we are applying a local search gradient free clustering algorithm to find out the suspicious / damaged area. We compare our results with the doctor’s marking. Also it has been observed that, beyond a certain point, the inclusion of additional features leads to a worse rather than better performance. Moreover, the choice of features to represent the patterns affects several aspects of pattern recognition problems such as accuracy, required learning time and a necessary number of samples. A common problem with the multi-category feature classification is the conflict between the categories. None of the feasible solutions allow simultaneous optimal solution for all categories. In order to find an optimal solution the search space can be divided based on an individual category in each sub region and finally merging them through decision spport system. Combining the feature selection with the classifier has been a major challenge for the researchers. A similar technique employed in both the levels often worsens their performance. Some preliminary studies has revealed that while using traditional canonical GA has been a good choice for feature selection modules, however under perform for the classifier level module. An evolutionary based algorithm for the classifier level provides a much better solution for this purpose. In this paper we propose a hybrid canonical based feature extraction technique with a combination of evolutionary algorithm based classifier using a feed forward MLP model.
Description:
Many works in the area of hybrid neural learning algorithms combine global and local based method for artificial neural network. In this paper, we discuss some special properties of a hybrid neural learning algorithm that combines the GA based method with least square based methods such as QR factorization. We look at different types of learning properties of this new hybrid algorithm, such as time complexity, convergence property, and the stability of the algorithm.
Applying anatomical therapeutic chemical (ATC) and critical term ontologies to Australian drug safety data for association rules and adverse event signalling
Description:
We demonstrate the use of a visual data-mining tool for non-technical domain experts within organizations to facilitate the extraction of meaningful information and knowledge from in-house databases. The tool is mainly based on the basic notion of grouping association rules. Association rules are useful in discovering items that are frequently found together. However in many applications, rules with lower frequencies are often interesting for the user. Grouping of association rules is one way to overcome the rare item problem. However some groups of association rules are too large for ease of understanding. In this chapter we propose a method for clustering categorical data based on the conditional probabilities of association rules for data sets with large numbers of attributes. We argue that the proposed method provides non-technical users with a better understanding of discovered patterns in the data set.
Description:
The traditional method for estimation of the parameters of Hidden Markov Model (HMM) based acoustic modeling of speech uses the Expectation-Maximization (EM) algorithm. The EM algorithm is sensitive to initial values of HMM parameters and is likely to terminate at a local maximum of likelihood function resulting in non-optimized estimation for HMM and lower recognition accuracy. In this paper, to obtain better estimation for HMM and higher recognition accuracy, several candidate HMMs are created by applying EM on multiple initial models. The best HMM is chosen from the candidate HMMs which has highest value for likelihood function. Initial models are created by varying maximum frame number in the segmentation step of HMM initialization process. A binary search is applied while creating the initial models. The proposed method has been tested on TIMIT database. Experimental results show that our approach obtains improved values for likelihood function and improved recognition accuracy.
Description:
This paper reports on an experimental approach to nd a modularized articial neural network solution for the UCI letters recognition problem. Our experiments have been carried out in two parts. We investigate directed task decomposition using expert knowledge and clustering approaches to nd the subtasks for the modules of the network. We next investigate processes to combine the modules e ectively in a single decision process. After having found suitable modules through task decomposition we have found through further experimentation that when the modules are combined with decision tree supervision, their functional error is reduced signicantly to improve their combination through the decision process that has been implemented as a small multilayered perceptron. The experiments conclude with a modularized neural network design for this classication problem that has increased learning and generalization characteristics. The test results for this network are markedly better than a single or stand alone network that has a fully connected topology.
Description:
In this paper we investigate different variants for hybrid models using the Discrete Gradient method and an evolutionary strategy for determining the weights in a feed forward artificial neural network. The Discrete Gradient method has the advantage of being able to jump over many local minima and find very deep local minima. However, earlier research has shown that a good starting point for the discrete gradient method can improve the quality of the solution point. Evolutionary algorithms are best suited for global optimisation problems. Nevertheless they are cursed with longer training times and often unsuitable for real world application. For optimisation problems such as weight optimisation for ANNs in real world applications the dimensions are large and time complexity is critical. Hence the idea of a hybrid model can be a suitable option. In this paper we propose different fusion strategies for hybrid models combining the evolutionary strategy with the discrete gradient method to obtain an optimal solution much quicker. Three different fusion strategies are discussed: a linear hybrid model, an iterative hybrid model and a restricted local search hybrid model Comparative results on a range of standard datasets are provided for different fusion hybrid models.
Description:
In the last few years, there have been many works in the area of hybrid neural learning algorithms combining a global and local based method for training artificial neural networks. In this paper, we discuss various connection strategies that can be applied to a special kind of a hybrid neural learning algorithm group, one that combines a genetic algorithm-based method with various least square-based methods like QR factorization. The relative advantages and disadvantages of the different connection types are studied to find a suitable connection topology for combining the two different learning methods. The methodology also finds the optimum number of hidden neurons using a hierarchical combination methodology structure for weights and architecture. We have tested our proposed approach on XOR, 10 bit odd parity, and some other real-world benchmark data sets, such as the hand-writing character dataset from CEDAR, Breast cancer, and Heart Disease from the UCI machine learning repository.
Description:
Advances in machine intelligence have provided a whole new window of opportunities in medical research. Building a fully automated computer aided diagnostic system for digital mammograms is just one of them. Given some success with semi-automated systems earlier, a fully automated CAD system is just another step forward. A proper combination of a feature selection model and a classifier for those areas of a mammogram marked by radiologists has been very successful. However a fully automated system with only two modules is a time consuming process as the suspicious areas in a mammogram can be quite small when compared to the whole image. Thus an additional clustering process can help in reducing the time complexity of the overall process. In this paper we propose a fast clustering process to identify suspicious areas. Another novelty of this paper is a multi-category feature selection approach. The choice of features to represent the patterns affects several aspects of pattern recognition problems such as accuracy, required learning time and the required number of samples. In this paper we propose a hybrid canonical based feature extraction technique as a combination of an evolutionary algorithm based classifier with a feed forward MLP model.