A three-stage learning algorithm for deep multilayer perceptron (DMLP) with effective weight initialisation based on sparse auto-encoder is proposed in this paper, which aims to overcome difficulties in training deep neural networks with limited training data in high-dimensional feature space. At the first stage, unsupervised learning is adopted using sparse auto-encoder to obtain the initial weights of the feature extraction layers of the DMLP. At the second stage, error back-propagation is used to train the DMLP by fixing the weights obtained at the first stage for its feature extraction layers. At the third stage, all the weights of the DMLP obtained at the second stage are refined by error back-propagation. Network structures and values of learning parameters are determined through cross-validation, and test datasets unseen in the cross-validation are used to evaluate the performance of the DMLP trained using the three-stage learning algorithm. Experimental results show that the proposed method is effective in combating overfitting in training deep neural networks.
Different ANN architectures of MLP have been trained by BP and used to analyze Landsat TM images. Two different approaches have been applied for training: an ordinary approach (for one hidden layer M-H1-L & two hidden layers M-H1-H2-L) and one-against-all strategy (for one hidden layer (M-H1-1)xL, & two hidden layers (M-H1-H2-1)xL). Classification accuracy up to 90% has been achieved using one-against-all strategy with two hidden layers architecture. The performance of one-against-all approach is slightly better than the ordinary approach
Information from 54 Magnetic Resonance Imaging (MRI) brain tumor images (27 benign and 27 malignant) were collected and subjected to multilayer perceptron artificial neural network available on the well know software of IBM SPSS 17 (Statistical Package for the Social Sciences). After many attempts, automatic architecture was decided to be adopted in this research work. Thirteen shape and statistical characteristics of images were considered. The neural network revealed an 89.1 % of correct classification for the training sample and 100 % of correct classification for the test sample. The normalized importance of the considered characteristics showed that kurtosis accounted for 100 % which means that this variable has a substantial effect
... Show MoreEarly detection of brain tumors is critical for enhancing treatment options and extending patient survival. Magnetic resonance imaging (MRI) scanning gives more detailed information, such as greater contrast and clarity than any other scanning method. Manually dividing brain tumors from many MRI images collected in clinical practice for cancer diagnosis is a tough and time-consuming task. Tumors and MRI scans of the brain can be discovered using algorithms and machine learning technologies, making the process easier for doctors because MRI images can appear healthy when the person may have a tumor or be malignant. Recently, deep learning techniques based on deep convolutional neural networks have been used to analyze med
... Show MoreDetection of early clinical keratoconus (KCN) is a challenging task, even for expert clinicians. In this study, we propose a deep learning (DL) model to address this challenge. We first used Xception and InceptionResNetV2 DL architectures to extract features from three different corneal maps collected from 1371 eyes examined in an eye clinic in Egypt. We then fused features using Xception and InceptionResNetV2 to detect subclinical forms of KCN more accurately and robustly. We obtained an area under the receiver operating characteristic curves (AUC) of 0.99 and an accuracy range of 97–100% to distinguish normal eyes from eyes with subclinical and established KCN. We further validated the model based on an independent dataset with
... Show MoreThis paper presents a hybrid energy resources (HER) system consisting of solar PV, storage, and utility grid. It is a challenge in real time to extract maximum power point (MPP) from the PV solar under variations of the irradiance strength. This work addresses challenges in identifying global MPP, dynamic algorithm behavior, tracking speed, adaptability to changing conditions, and accuracy. Shallow Neural Networks using the deep learning NARMA-L2 controller have been proposed. It is modeled to predict the reference voltage under different irradiance. The dynamic PV solar and nonlinearity have been trained to track the maximum power drawn from the PV solar systems in real time.
Moreover, the proposed controller i
... Show MoreWith the rapid development of smart devices, people's lives have become easier, especially for visually disabled or special-needs people. The new achievements in the fields of machine learning and deep learning let people identify and recognise the surrounding environment. In this study, the efficiency and high performance of deep learning architecture are used to build an image classification system in both indoor and outdoor environments. The proposed methodology starts with collecting two datasets (indoor and outdoor) from different separate datasets. In the second step, the collected dataset is split into training, validation, and test sets. The pre-trained GoogleNet and MobileNet-V2 models are trained using the indoor and outdoor se
... Show More