Lilia Lazli

Hidden Neural Network for Complex Pattern Recognition: A Comparison Study with Multi- Neural Network Based Approach

When the feature space undergoes changes, owing to different operating and environmental conditions, multi-aspect classification is almost a necessity in order to maintain the performance of the pattern recognition system and improve robustness and reliability in decision making. This is an important issue being investigated in ANN research, in many cases, the problems can be solved more effectively by combining one or two other techniques rather than implementing ANN exclusively. New learning methods, especially multiple classifier systems, are now actively studied and applied in pattern recognition. So, the main goal of this paper is to propose two hybrid models and compare your performance in complex pattern recognition problem: speech recognition and biomedical diagnosis. This paper compare, the performance obtained with (1) Multi-network RBF/LVQ structure, we use involves Learning Vector Quantization (LVQ) as a competitive decision processor and Radial Basis Function (RBF) as a classifier. (2) Hybrid HMM/MLP model using a Multi Layer-Perceptron (MLP) to estimate the Hidden Markov Models (HMM) emission probabilities. For pre- classification, the k-means clustering algorithm is proposed to obtain optimum information for the biomedical and speech training data for the proposed hybrid models.

Hybrid HMM/ANN System Using Fuzzy Clustering for Speech and Medical Pattern Recognition

The main goal of this paper is to compare the performance which can be achieved by three different approaches analyzing their applications’ potentiality on real world paradigms. We compare the performance obtained with (1) Discrete Hidden Markov Models (HMM) (2) Hybrid HMM/MLP system using a Multi Layer-Perceptron (MLP) to estimate the HMM emission probabilities and using the K-means algorithm for pattern clustering (3) Hybrid HMM-MLP system using the Fuzzy C-Means (FCM) algorithm for fuzzy pattern clustering.Experimental results on Arabic speech vocabulary and biomedical signals show significant decreases in error rates for the hybrid HMM/MLP system based fuzzy clustering (application of FCM algorithm) in comparison to a baseline system.

Tissue segmentation by fuzzy clustering technique: case study on Alzheimer's disease

Segmentation of brain images especially into three main tissue types: Gray Matter (GM), Cerebrospinal Fluid (CSF), and White Matter (WM) has important role in computer aided neurosurgery and diagnosis. In imaging, physical phenomena and the acquisition system are responsible for noise and the Partial Volume Effect (PVE) respectively, which affect the uncertainty and the imprecision. To reduce the effect of these different imperfections, we propose a clustering approach that is based on a fuzzy- possibilistic segmentation process for the assessment of WM, GM and CSF volumes from Alzheimer’s brain images. The brain segmentation scheme which is illustrated in the study of Alzheimer’s disease using Alzheimer’s disease Neuroimaging Initiative (ADNI) and real images take in consideration the PVE and it is less sensitive to noise.

Brain Tissues Volumes Assessment by Fuzzy Genetic Optimization Based Possibilistic Clustering: Application to Alzheimer Patients Images

Cerebral images include several artifacts, such as partial volume effect which limit the diagnostic potential of brain imaging. So, the main objective of this paper is to reduce the effect of partial volume averaging on the boundaries of the ventricles. We thus proposed a fuzzy-genetic brain segmentation scheme for the assessment of white matter, gray matter and cerebrospinal fluid volumes from brain images of Alzheimer patients from a real database and from Alzheimers Disease Neuroimaging Initiative (ADNI) database. This clustering process based on Possibilistic algorithm which allows modeling the degree of relationship between each voxels and a given tissue; and based on fuzzy genetic initialization for the centers of clusters by a Fuzzy algorithm, and for which the result is optimized by genetic process. The visual results show a concordance between the ground truth segmentation and the hybrid algorithm results, which allows efficient tissue classification. The superiority was also proved with the quantitative results of the proposed method in comparison with the conventional algorithms.

Diagnosis of Auditory Pathologies with Hidden Markov Models

Since about twenty years, the otoneurology functional exploration possesses auditory tool to analyze objectively the state of the nervous conduction of additive pathway. In this paper, we present a new classification approach based on the Hidden Markov Models (HMM) which used to design a Computer aided medical diagnostic (CAMD) tool that asserts auditory pathologies based on Brain-stem Evoked Response Auditory based biomedical test, which provides an effective measure of the integrity of the auditory pathway. Case study, experimental results and comparison with a conventional neural networks models have been reported and discussed.