In the last few decades, Deep Neural Networks (DNNs) has shown outstanding performance in speech recognition applications. We demonstrate that the improved accuracy obtained by Deep Convolutional Neural Network (DCNN) arose from their capacity to extract discriminative representations which are robust to various sources of variability in speech signals. By this study, we propose a new algorithm, named Scattering Transform-Deep Convolutional Neural Network CNN: ST-DCNN to identify normal and pathological voices. The effectiveness of advances in speech features have been proven to be the root for an efficient pathological voices classification. The proposed algorithm involved two stages: First, scatter wavelet features are extracted. Then, DCNN is used to classify the voices samples. We evaluated the robustness of the proposed system in silent environments. The experimental results indicates that it achieves better performance with scattering wavelet and DCNN with the clean data within 99.62 % of recognition rate.

Morphological shape of the optic nerve's disc and excavation presents an important feature in the identification of eyes' diseases such as glaucoma. Leading to the optic nerve head (ONH) destruction, this sickness is considered as the second leading cause of blindness worldwide and mainly in least developed countries. Since early detection is crucial to cure this disease, this paper describes a new decision-making system based on Artificial Neural Network (ANN) classifier. The suggested method has the advantage of taking into consideration both instrumental parameters (Cup-to-Disc Ratio, ISNT rule and eyes' asymmetry) and factor risks (age, gender, genetic history and origin). Experiments are performed on a real dataset of ophthalmologic images of normal and glaucomatous cases. The experimental results show high accuracy compared with some existing systems.

Lately, medical imaging has evolved as it represents an essential support for the patients' diagnosis and monitoring. Early recognition of diseases such as “Glaucoma” is fundamental to the assumption. Indeed, the earlier the treatment is instituted, the better the chances of success are. Since the shape of the optic nerve's excavation is the most important feature in its identification, correct detection techniques are necessary to highlight their forms. This paper presents a comparative study of different edge detection's methods applied on a set of ophthalmologic images of the optic nerve.