Search

Skin cancer is an uncontrolled development of abnormal skin cells potentially due to excessive exposure to sun, history of sunburns, less melanin, Precancerous skin lesions, moles, etc. This occur when unrepaired DNA damages the cells of the skin. It is one of the diseases that are viewed on its quick evolution and the most common type of cancer that endangers life. Researchers have implemented several machine learning and deep learning techniques for classification of skin cancer. In this research paper, different cancer categories are classified using significant attributes. We have used International Skin Imaging Collaboration (ISIC) dataset for classification purposes. This dermoscopic attributes dataset includes 1000 images and 10016 instances, seven categories, 5 features and 2 Meta attributes. We implemented K-Nearest Neighbor, Logistic Regression, Convolutional Neural Network, Naïve Bayes, and Decision Tree for classification and compared their performance. In order to implement classification algorithm, we used Orange which is an open-source machine learning, data mining, and data visualization toolkit. The models are evaluated based on matrices that include Accuracy, C. Automation, F1 score, Precision, Recall, and AUC. Furthermore, frequency of features is visualized using graphical method and the ROC analysis is also performed for the classifiers. It is observed that CNN technique provided the highest accuracy of 89% and the mentioned results are the highest results of classification with the state of the art techniques. For future, the improved and recent dataset and ensemble modelling techniques based on deep learning can used to enhance classification results. The research can also be extended for other cancer types using CNN.

Software-Defined Networking (SDN) technology significantly simplifies network management tasks. It enables complex network configuration and controlling easy through a programmable and flexible interface. It opens a new horizon for network application development and innovation. Contrarily, complicated traditional IP networks are very difficult to manage and troubleshoot. They are error-prone and it is difficult to introduce new features and development of a new set of policies. In traditional networks, data and control planes are bundled in the firmware of the device whereas in SDN they are abstracted from one another. In this research work, a comparative study has been conducted between traditional networks and SDN. A comparative study is performed on the basis of various aspects such as architecture, layers, protocols, security, simulators, and vendors. This article also describes various SDN controllers and communication between the controllers with upper and lower layers with the help of API’s. Moreover, it also presents the architecture and communication protocols in the SDN.

The aim of this research article and survey is to acknowledge the modern term of bullying, and develop better understanding of it by accessing all facts and causes of this problem. The effects of cyberbullying are directly proportional to effects of face to face bullying. Cyberbullying is negativity and aggressive behaviors that is often generated in a person's mind, it's traumatically effecting the psyches of adolescents and adults too. It also negatively effects the development of children, their academic performance, physical and mental health. Cyberbullying is a worldwide problem and many countries are experiencing its consequences. Cyberbullying has various impacts, and causes on one's health, so many services are provided by service providers such as physicians, nurses, parents and social workers. The objective is to educate parents, society and adults about symptoms of cyberbullying in victim as well as prevention and controlling over this problem. This paper includes consequences of cyberbullying on both victim's and bully's psyches. A survey has been conducted and its results are also included in this paper which shows the awareness rates, online bullying percentages and also other related factors that arises from cyberbullying.

Software development process provides detailed guideline for development testing and maintenance of software products. It deals with the risks associated withsoftware development and a road map to manage its complexities. In other words, software development processes are considered as optimized solution specific to any particular software product development. There are many software process models available in literature. This research performs a non-parametric comparison between formal process model, agile process model and agent based process model to aid software community in developing quality software product.