Browsing by Author "MICHAEL, KISANGIRI"

Now showing 1 - 2 of 2

Classifying Swahili Smishing Attacks for Mobile Money Users: A Machine-Learning Approach
(IEEE Access, 2022-08-11) MAMBINA, IDDI; NDIBWILE, JEMA; MICHAEL, KISANGIRI
Due to the massive adoption of mobile money in Sub-Saharan countries, the global transaction value of mobile money exceeded $2 billion in 2021. Projections show transaction values will exceed $3 billion by the end of 2022, and Sub-Saharan Africa contributes half of the daily transactions. SMS (Short Message Service) phishing cost corporations and individuals millions of dollars annually. Spammers use Smishing (SMS Phishing) messages to trick a mobile money user into sending electronic cash to an unintended mobile wallet. Though Smishing is an incarnation of phishing, they differ in the information available and attack strategy. As a result, detecting Smishing becomes difficult. Numerous models and techniques to detect Smishing attacks have been introduced for high-resource languages, yet few target low-resource languages such as Swahili. This study proposes a machine-learning based model to classify Swahili Smishing text messages targeting mobile money users. Experimental results show a hybrid model of Extratree classifier feature selection and Random Forest using TFIDF (Term Frequency Inverse Document Frequency) vectorization yields the best model with an accuracy score of 99.86%. Results are measured against a baseline Multinomial Naïve-Bayes model. In addition, comparison with a set of other classic classifiers is also done. The model returns the lowest false positive and false negative of 2 and 4, respectively, with a Log-Loss of 0.04. A Swahili dataset with 32259 messages is used for performance evaluation.
Improved Resource Allocation Model for Reducing Interference Among Secondary Users in TV White Space for Broadband Services
(IEEE Access, 2022-11-11) MWAIMU, MARCO; MAJHAM, MIKE; RONOH, KENNEDY; MICHAEL, KISANGIRI; SINDE, RAMADHANI
In recent years, the Television White Space has attracted the interest of many researchers due to its propagation characteristics obtainable between 470MHz and 790MHz spectrum bands. However, aggre- gate interference increase when secondary users in wireless network increase. Aggregate interference on the side of Primary Users has been extensively scrutinized. Therefore, resource allocation (power and spectrum) is crucial when designing the Television White Space network to avoid interferences from Secondary Users to Primary Users and among Secondary Users themselves. This study proposes a resource allocation model that uses joint power and spectrum hybrid Particle Swarm Optimization, Firefly, and Genetic algorithm for reducing the aggregate interference among Secondary Users. The algorithm is integrated with the admission control algorithm so that; there is a possibility of removing some of the Secondary Users in the network whenever the Signal to Noise Ratio threshold for Secondary and Primary Users is not met. We considered an infeasible system whereby all Secondary and Primary Users may not be supported simultaneously. Metrics such as Primary User Signal-to-noise ratio, sum throughput, and secondary user signal-to-noise ratio less than the threshold used to compare the performance of the proposed algorithm and the results show that PSOFAGA with effective link gain ratio admission control has the best performance compared to particle swarm optimization, genetic algorithm, firefly algorithm, and PSOFAGA algorithm