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

Article history: Received: 08 October, 2020 Accepted: 25 December, 2020 Online: 30 December, 2020 Android Operating system (OS) has been used much more than all other mobile phone’s OS turning android OS to a major point of attack. Android Application installation serves as a major avenue through which attacks can be perpetrated. Permissions must be first granted by the users seeking to install these third-party applications. Some permissions can be subtle escaping the attentions of the users. Some of these permissions can have adverse effects like spying on the users, unauthorized retrieval and transference of the data and so on. This calls for the need of a heuristic method for the identification and detection of malware. In this discourse, testing of classification algorithms including Random forest, Naïve Bayes, Random Tree, BayesNet, Decision Table, Multi-layer perceptron (MLP), Bagging, Sequential Minimal Optimization (SMO)/Support-Vector Machine (SVM), KStar and IBK (also known as K Nearest Neighbours classifier (KNN)) was carried out to decide which algorithm performs best in android malware detection. Two dataset was used in this study and were gotten from figshare. They were trained and tested in the Waikato Environment for Knowledge Analysis (WEKA). The performance metrics used are Root Mean Square Error (RMSE), Accuracy, Receiver Operating Curve (ROC), False positive rate, F-measure, Precision and recall. It was discovered that the best performance with an accuracy of 99.4% was the multi-layer perceptron on the first dataset. Random Forest has the best performance with accuracy, 98.9% on the second dataset. The implication of this is that MLP or random forest can be used to detect android application malwares.

An Evaluation of some Machine Learning Algorithms for the detection of Android Applications Malware