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 an

The paper present design of a control structure that enables integration of a Kinematic neural controller for trajectory tracking of a nonholonomic differential two wheeled mobile robot, then  proposes a Kinematic neural controller to direct a National Instrument mobile robot (NI Mobile Robot). The controller is to make the actual velocity of the wheeled mobile robot close the required velocity by guarantees that the trajectory tracking mean squire error converges at minimum tracking error. The proposed tracking control system consists of two layers; The first layer is a multi-layer perceptron neural network system that controls the mobile robot to track the required path , The second layer is an optimization layer ,which is impleme

Cancer is in general not a result of an abnormality of a single gene but a consequence of changes in many genes, it is therefore of great importance to understand the roles of different oncogenic and tumor suppressor pathways in tumorigenesis. In recent years, there have been many computational models developed to study the genetic alterations of different pathways in the evolutionary process of cancer. However, most of the methods are knowledge-based enrichment analyses and inflexible to analyze user-defined pathways or gene sets. In this paper, we develop a nonparametric and data-driven approach to testing for the dynamic changes of pathways over the cancer progression. Our method is based on an expansion and refinement of the pathway bei

The multi-focus image fusion method can fuse more than one focused image to generate a single image with more accurate description. The purpose of image fusion is to generate one image by combining information from many source images of the same scene. In this paper, a multi-focus image fusion method is proposed with a hybrid pixel level obtained in the spatial and transform domains. The proposed method is implemented on multi-focus source images in YCbCr color space. As the first step two-level stationary wavelet transform was applied on the Y channel of two source images. The fused Y channel is implemented by using many fusion rule techniques. The Cb and Cr channels of the source images are fused using principal component analysis (PCA).

Digital image manipulation has become increasingly prevalent due to the widespread availability of sophisticated image editing tools. In copy-move forgery, a portion of an image is copied and pasted into another area within the same image. The proposed methodology begins with extracting the image's Local Binary Pattern (LBP) algorithm features. Two main statistical functions, Stander Deviation (STD) and Angler Second Moment (ASM), are computed for each LBP feature, capturing additional statistical information about the local textures. Next, a multi-level LBP feature selection is applied to select the most relevant features. This process involves performing LBP computation at multiple scales or levels, capturing textures at different