Arman Process Journal (APJ)

Abstract Background and Objectives: Website clicks that redirect Android phone users to malicious ‎websites with fake virus warnings or phishing attacks are increasing exponentially. Although a ‎Uniform Resource Locator (URL) blacklist is considered as a suitable countermeasure for such ‎attacks, it is difficult to efficiently identify malicious websites. To the best of our knowledge, no ‎research has focused on detecting attacks that redirect Android phone users to malicious ‎websites. Therefore, we propose a redirection detection method that focuses on the URL bar ‎change interval of the Android-based Google Chrome browser.‎
Methods: The proposed method, which can be easily installed as an Android application, uses ‎the Android Accessibility Service to detect unwanted redirects to malicious websites without ‎collecting information about these websites in advance. This paper describes the details of the ‎design, implementation, and evaluation results of the proposed application on a real Android ‎device. We set threshold values for the number of times the URL bar changes and the elapsed ‎time to detect redirects to malicious websites for the proposed method.‎
Finding: Based on the results, we investigated the causes of false positive detections of ‎redirects to safe websites and proposed solutions to manage them. We also present threshold ‎values that can minimize the false positive and negative rates, as well as the detection accuracy ‎of the proposed method based on these threshold values. In addition, we present evaluation ‎results based on access reports of real users participating in the WarpDrive project experiment, ‎which show that the proposed method minimizes false positives and successfully detects most ‎redirects to malicious websites.‎

Abstract Background and Objectives: Fault of power distribution networks is based on the ‎uncontorable factors. Rapid approache to identidtification and localization of power ‎network fault is ctritical to maintain system riable. While traditional approaches use ‎measurements from current and voltage transformers, this study proposes an ‎artificial intelligence-driven approach for enhanced fault detection and analysis in ‎power distribution networks. A custom-designed sensing prototype captured voltage ‎and current data under simulated fault conditions, including short-circuit and open-‎circuit faults. The presented approach includes fundamental variables, such as fault ‎type, sensor placement topology, and line distance, were rigorously controlled during ‎data acquisition.‎

Methods: This paper presentes two algorithms: an Artificial Neural Network (ANN) ‎and an Adaptive Neuro-Fuzzy Inference System (ANFIS). Both used algorithms have ‎many parmeters that rquire to be tune While the values of these parameters effect ‎on the performance, but the major target of this study is using of these algorithms. ‎Steps of algorithms are described in the paper. The redults of algorithms are showed ‎with the used data. Performance was validated under variable load conditions across ‎line distances of 200–800 meters. ‎

Finding: Simulation results demonstrate that the ANFIS classifier achieved superior ‎accuracy in fault classification (99.7%) and minimal distance estimation error (0.5%). ‎Both ANN and ANFIS delivered high precision in fault detection, localisation, and ‎classification, with ANFIS exhibiting significantly faster training convergence (1 ms). ‎Indeed ANFIS has more consistency. ‎

Cnclusion: The framework presents a robust, computationally efficient solution for ‎real-time fault management (modeling), recommending (analysis) the integration of ‎dedicated sensors by power distribution network utilities to enable targeted grid ‎interventions.‎