In recent times, more and more social data is transmitted in different ways. Protecting the privacy of social network data has turn out to be an essential issue. Hypothetically, it is assumed that the attacker utilizes the similar information used by the genuine user. With the knowledge obtained from the users of social networks, attackers can easily attack the privacy of several victims. Thus, assuming the attacks or noise node with the similar environment information does not resemble the personalized privacy necessities, meanwhile, it loses the possibility to attain better utility by taking benefit of differences of users’ privacy necessities. The traditional research on privacy-protected data publishing can only deal with relational data and even cannot applied to the data of social networking. In this research work, K-anonymity is used for providing the security of the sensitive information from the attacker in the social network. K-anonymity provides security from attacker by making the graph and developing nodes degree. The clusters are made by grouping the similar degree into one group and the process is repeated until the noisy node is identified. For measuring the efficiency the parameters named as Average Path Length (APL) and information loss are measured. A reduction of 0.43% of the information loss is obtained.

No abstract

In this work, a radio over free-space optical communication (Ro-FSO) link has been examined considering quadrature amplitude modulation (64-QAM) based orthogonal frequency division multiplexing (OFDM) technique for a turbulence channel. The performance of the system has been investigated considering log normal and gamma-gamma atmospheric scintillation models under clear air, rain and fog weather conditions. Artificial neural network (ANN), k-nearest neighbour (KNN), and decision tree (DT) machine learning (ML) techniques have been applied for estimation of quality of received signal in terms of bit error rate BER. ANN model exhibits the highest value of R-squared (R2) of 0.9967 and lowest value of root mean square error (RMSE) of 0.0134 as compared to other ML techniques resulting in the best fit model.

No abstract

No abstract