English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Tools annual

Global: Zendy Free Plan

Global: Zendy Tools monthly

Global: Zendy Plus monthly

In the recent years, the user activities over online social networks (OSNs) have increased tremendously. A large number of users share information across the different social networking platforms. The information across the OSNs is easy to access, and thus, can be easily used by the fraudulent users for misleading the entire community. Such fraudulent users are termed anomalies. In this paper, a problem of cross-platform anomalies is considered, which possesses different behaviors by an individual with different users across the multiple OSNs. The variation in the behavior and activity makes it difficult to identify such anomalies. A solution to this problem is proposed on the basis of cognitive tokens, which provide an intelligent sensing model for anomalies detection (ISMA) by deliberately inducing faulty data to attract the anomalous users. A common login system for different OSNs is also suggested as a part of collaborative anomaly identification across different OSNs. A fair play point approach is used for the determination of anomalies. Both simulations and email-based real data sets are used to measure the performance of the proposed approach. Furthermore, as an example of implementation, a case study is presented for anomaly detection in Internet of Things. The proposed approach is able to provide the highest accuracy at the rate of 99.2%; this is 25.1% higher as compared with the SVM-RBF and sigmoid approach, and 22% higher than that of the k-nearest neighbor approach. Furthermore, the proposed ISMA also caused less error in detecting the anomalies, which were within the range of 0.1% to 2.8%. The error in identification is reduced up to 96.6% in comparison with the SVM and k-nearest neighbor approaches. The gains in comparative results validate the efficiency of the ISMA in identification and classification of anomalies in cross-platform OSNs.

ISMA: Intelligent Sensing Model for Anomalies Detection in Cross Platform OSNs With a Case Study on IoT