Lung abnormalities are highly risky conditions in humans. The early diagnosis of lung abnormalities is essential to reduce the risk by enabling quick and efficient treatment. This research work aims to propose a Deep-Learning (DL) framework to examine lung pneumonia and the cancer. This work proposes two different DL practices to evaluate the considered problem: (i) The initial DL method, named a modified AlexNet (MAN), is implemented to classify chest X-Ray images into normal and pneumonia class. In the MAN, the classification is implemented using with Support Vector Machine (SVM), and its performance is compared against Softmax. Further, its performance is validated with other pre-trained DL techniques, such as AlexNet, VGG16, VGG19 and ResNet50. (ii) The second DL work implements a fusion of handcrafted and learned features in the MAN to improve the classification accuracy during lung cancer assessment. This work employs serial fusion and Principal Component Analysis (PCA) based features selection to enhance the feature vector. The performance of this DL structure is tested by the benchmark lung cancer CT images of LIDC-IDRI and superior classification accuracy of >97.27% is achieved.

No abstract

No abstract

No abstract

No abstract

Social group optimization (SGO), a populationbased optimization technique is proposed in this paper. It is inspired from the concept of social behavior of human toward solving a complex problem. The concept and the mathematical formulation of SGO algorithm is explained in this paper with a flowchart. To judge the effectiveness of SGO, extensive experiments have been conducted on number of different unconstrained benchmark functions as well as standard numerical benchmark functions taken from the IEEE Congress on Evolutionary Computation 2005 competition. Performance comparisons are made between state-of-theart optimization techniques, like GA, PSO, DE, ABC and its variants, and the recently developed TLBO. The investigational outcomes show that the proposed social group optimization outperforms all the investigated optimization techniques in computational costs and also provides optimal solutions for most of the functions considered in our work. The proposed technique is found to be very simple and straightforward to implement as well. It is believed that SGO will supplement the group of effective and efficient optimization techniques in the population-based category and give researchers wide scope to choose this in their respective applications.

No abstract

No abstract