T. Karthikeyan^1,*, M. Govindarajan¹, V. Vijayakumar²

Intelligent Automation & Soft Computing, Vol.37, No.2, pp. 1483-1498, 2023, DOI:10.32604/iasc.2023.037606 - 21 June 2023

Abstract Frauds don’t follow any recurring patterns. They require the use of unsupervised learning since their behaviour is continually changing. Fraudsters have access to the most recent technology, which gives them the ability to defraud people through online transactions. Fraudsters make assumptions about consumers’ routine behaviour, and fraud develops swiftly. Unsupervised learning must be used by fraud detection systems to recognize online payments since some fraudsters start out using online channels before moving on to other techniques. Building a deep convolutional neural network model to identify anomalies from conventional competitive swarm optimization patterns with a focus… More >

C. Nandagopal^1,*, P. Siva Kumar², R. Rajalakshmi³, S. Anandamurugan⁴

Intelligent Automation & Soft Computing, Vol.36, No.1, pp. 113-126, 2023, DOI:10.32604/iasc.2023.031103 - 29 September 2022

Abstract Vehicle Ad hoc Networks (VANETs) have high mobility and a randomized connection structure, resulting in extremely dynamic behavior. Several challenges, such as frequent connection failures, sustainability, multi-hop data transfer, and data loss, affect the effectiveness of Transmission Control Protocols (TCP) on such wireless ad hoc networks. To avoid the problem, in this paper, mobility-aware zone-based routing in VANET is proposed. To achieve this concept, in this paper hybrid optimization algorithm is presented. The hybrid algorithm is a combination of Ant colony optimization (ACO) and artificial bee colony optimization (ABC). The proposed hybrid algorithm is designed for… More >

Purvashi Baynath, Sunjiv Soyjaudah, Maleika Heenaye-Mamode Khan

Intelligent Automation & Soft Computing, Vol.25, No.4, pp. 651-661, 2019, DOI:10.31209/2018.100000060

Abstract The goal of this paper is (i) adopt fusion of features (ii) determine the best method of feature selection technique among ant Colony optimisation, artificial bee colony optimisation and genetic algorithm. The experimental results reported that ant colony Optimisation is a promising techniques as feature selection on Keystroke Dynamics as it outperforms in terms of recognition rate for our inbuilt database where the distance between the keys has been considered for the password derivation with recognition rate 97.85%. Finally the results have shown that a small improvement is obtained by fused features, which suggest that More >