Lung cancer is the world's leading cause of cancer death. The convolutional neural network (CNN) has been proved able to classify between malignant and benign tissues on CT scan images. In this paper, a deep neural network is designed based on GoogleNet, a pre-trained CNN. To reduce the computing cost and avoid overfitting in network learning, the densely connected architecture of the proposed network was sparsified, with 60 % of all neurons deployed on dropout layers. The performance of the proposed network was verified through a simulation on a pre-processed CT scan image dataset: The Lung Image Database Consortium (LIDC) dataset, and compared with that of several pre-trained CNNs, namely, AlexNet, GoogleNet and ResNet50. The results show that our network achieved better classification accuracy than the contrastive networks.

In this paper, presented a Gender classification through Support Vector Machine (SVM) and Scaled Conjugate Gradient Back Propagation Neural Network (SCGBPNN) from face images using Local Binary Patterns. To achieve better classification performance, need to be applied pre-processing technique first and then extracted the features on facial images from Local Binary Pattern Histogram (LBPH) method. These extracted features were stored into a vector called feature vector. Later, the feature vector is inputted to Polynomial SVM and SCG Back Propagation Neural Network classification methods along with labelled target vector. The performance of the both classifiers is measured by the labelled AT&T face database and Nottingham Scan Database.