No abstract

Pulmonary nodule is one of the lung diseases and its early diagnosis and treatment are essential to cure the patient. This paper introduces a deep learning framework to support the automated detection of lung nodules in computed tomography (CT) images. The proposed framework employs VGG-SegNet supported nodule mining and pre-trained DL-based classification to support automated lung nodule detection. The classification of lung CT images is implemented using the attained deep features, and then these features are serially concatenated with the handcrafted features, such as the Grey Level Co-Occurrence Matrix (GLCM), Local-Binary-Pattern (LBP) and Pyramid Histogram of Oriented Gradients (PHOG) to enhance the disease detection accuracy. The images used for experiments are collected from the LIDC-IDRI and Lung-PET-CT-Dx datasets. The experimental results attained show that the VGG19 architecture with concatenated deep and handcrafted features can achieve an accuracy of 97.83% with the SVM-RBF classifier.

No abstract

Abstract-Vehicle Routing Problem (VRP) is a NP-Complete and a multi-objective problem. The problem involves optimizing a fleet of vehicles that are to serve a number of customers from a central depot. Each vehicle has limited capacity and each customer has a certain demand. Genetic Algorithm (GA) maintains a population of solutions by means of a crossover and mutation operators. For crossover and mutation best cost route crossover techniques and swap mutation procedure is used respectively. In this paper, we focus on two objectives of VRP i.e. number of vehicles and total cost (distance). The proposed Multi Objective Genetic Algorithm (MOGA) finds optimum solutions effectively.Index Terms-Vehicle routing problem, genetic algorithm, multi-objective optimization, pareto ranking procedure, bestcost route crossover (BCRC).

Abstract

Paradigm need to shifts from cloud computing to intercloud for disaster recoveries, which can outbreak anytime and anywhere. Natural disaster treatment includes radically high voluminous impatient job request demanding immediate attention. Under the disequilibrium circumstance, intercloud is more practical and functional option. There are need of protocols like quality of services, service level agreement and disaster recovery pacts to be discussed and clarified during the initial setup to fast track the distress scenario. Orchestration of resources in large scale distributed system having muli-objective optimization of resources, minimum energy consumption, maximum throughput, load balancing, minimum carbon footprint altogether is quite challenging. Intercloud where resources of different clouds are in align, plays crucial role in resource mapping. The objective of this paper is to improvise and fast track the mapping procedures in cloud platform and addressing impatient job requests in balanced and efficient manner. Genetic algorithm based resource allocation is proposed using pareto optimal mapping of resources to keep high utilization rate of processors, high througput and low carbon footprint.  Decision variables include utilization of processors, throughput, locality cost and real time deadline. Simulation results of load balancer using first in first out and genetic algorithm are compared under similar circumstances.

Feminism is an existential struggle to assert one's individuality-it stands for gender equality, independence and empowerment to women. The concept of feminism examines and analyzes gender identity, by way of targeting women's autonomous self-identity. If we enter into the world of cyberspace we find technology is opening up the possibility for female emancipation. Over just two decades, the Internet has worked a thorough revolution and is considered to be a great equalizer; yet, access to it is not uniformly shared. This paper explores what Internet along with the cyberspace signifies to women and how they employ the cyberspace for their personal schedule from a socio-anthropological perspective. Cyber feminism is basically involved with countering the recognized and accepted domination of men in the employment and advancement of information and communication technology (ICT) and cyberspace. The image of technology needs to change to incorporate a female view.

In the computer vision applications such as security surveillance and robotics, pedestrian identification shows much attention in the last decade. This is usually achieved by human biometrics. Besides human biometrics, sometimes it is required to identify pedestrians at a distance. This could be accomplished based on a fact of different whole-body appearances. The real-time pedestrian identification is a challenging task due to several factors such as illumination effects, noise, change in viewpoint, and video resolution. The more recent, the deep neural network (DNN) shows a massive performance for various real-world applications. In this article, we present a real-time architecture for pedestrian identification using motion-controlled DNN. In the proposed architecture, the motion vectors are calculating using optical flow and then utilized in the next step, named features extraction. Two types of features, such as HOG and DNN, are computing. The pre-trained VGG19 CNN model is employing and trained through transfer learning. The deep learning features are extracted from two layers-fully connected layers 7 and 8. Also, we proposed a feature selection method named Bayesian modeling along with LSVM. The best selected features of both HOG and DNN are finally fused in one matrix for final identification. The multi-class support vector machine classifier is used for final identification. The videos are recording in the real-time environment for the experimental process and achieve an average accuracy of 98.62%. Overall, identification accuracy shows the effectiveness of the proposed approach.