Fazlina Ahmat Ruslan

About

Fazlina Ahmat Ruslan is a researcher whose work spans the frontiers of artificial intelligence, robotics, and environmental monitoring. Her key research areas include particle filter algorithms for flood prediction, wireless robotic control systems, and deep learning for cybersecurity and computer vision. In her highly cited 2012 paper (22 citations), she pioneered the application of Sampling Importance Resampling (SIR) particle filters—a Monte Carlo method—to track and predict flood water levels using GIS databases, offering a robust solution for nonlinear dynamic systems. She further demonstrated her versatility with a 2019 study (18 citations) on a wireless hand gesture-controlled robotic arm using NRF24L01 transceivers, enabling intuitive, cable-free human-robot interaction. More recently, she has tackled pressing challenges in cybersecurity with a review on deep learning-based text CAPTCHA breaking (2023, 6 citations) and advanced object detection for industrial robotics, improving Mask R-CNN algorithms to handle partial occlusion and stacked objects with higher speed and accuracy (2023–2024). Her work bridges theoretical innovation and practical deployment, making significant contributions to flood disaster management, assistive robotics, and automated security systems.

Research Focus

Key Achievements

Top Papers

1. 1
   Parameters effect in Sampling Importance Resampling (SIR) particle filter prediction and tracking of flood water level performance

   22 citations · 2012
2. 2
   Wireless Hand Gesture Controlled Robotic Arm Via NRF24L01 Transceiver

   18 citations · 2019
3. 3
   A Review on Text-based CAPTCHA Breaking Based on Deep Learning Methods

   6 citations · 2023
4. 4
   PARTIAL OCCLUSION OBJECT DETECTION BASED ON IMPROVED MASK-RCNN

   3 citations · 2024
5. 5
   An Improved Mask R-CNN Algorithm for High Object Detection Speed and Accuracy

   3 citations · 2023

Key Collaborators

Contact & Links