A5001268306- Network Security and Intrusion Detection
- Remote-Sensing Image Classification
- Anomaly Detection Techniques and Applications
- Remote Sensing and Land Use
- Advanced Image Fusion Techniques
- Software-Defined Networks and 5G
- Image Retrieval and Classification Techniques
- Internet Traffic Analysis and Secure E-voting
- Advanced Image and Video Retrieval Techniques
- Advanced Vision and Imaging
- Advanced Malware Detection Techniques
- Network Traffic and Congestion Control
- Remote Sensing in Agriculture
- Infrared Target Detection Methodologies
- Image Processing Techniques and Applications
- Software System Performance and Reliability
- Vehicular Ad Hoc Networks (VANETs)
National University of Sciences and Technology
2014-2021
Intelligent Transportation Systems (ITS), especially Autonomous Vehicles (AVs), are vulnerable to security and safety issues that threaten the lives of people. Unlike manual vehicles, communications computing components AVs can be compromised using advanced hacking techniques, thus barring from effective use in our routine lives. Once vehicles connected Internet, called Internet (IoVs), it would exploited by cyber-attacks, like denial service, sniffing, distributed spoofing replay attacks....
This paper presents techniques for segmentation and change classification using logistic regression. The research was conducted on SPOT 5 multispectral multitemporal images covering the 2010 floods in Pakistan. Segmentation performed to extract built up area (BUA) from satellite detection find damaged BUA. classified into three categories based extent of damage. results were validated statistical measures like precision, recall, dice coefficient available ground truth. compared found...
Summary Software‐defined networking (SDN) is a new architecture that decouples both the control and management planes from data plane of forwarding devices. Control are implemented at logically centralized entity called controller. Despite numerous advantages, SDN more prone to logical errors like loops, black holes, network reachability problems, access list (ACL) policies violation. In existing approaches, requirements specified by different administrators using ACL policies. allows...
Morphological profiles are one of the highly effective tools for image classification when structural information is critical. profiles, however create high dimensional feature space and increase complexity classifier. In this paper we have quantitatively evaluated fact that accuracy each profile dependent on size shape structuring element. We propose a scheme which uses morphological with adaptive relate element used producing discrete wavelet transform image. The adapts to frequency...
Network performance monitoring holds a pivotal role in improving the overall network performance. It is essential to monitor traffic statistics at Internet eXchange Points (IXPs) optimize flows. The existing system either lacks usability or programmability. We present Software Defined Networking (SDN) enabled and OpenFlow (OF) compatible (SDX-Manager) improve programmability of IXP simultaneously. proposed integrates traditional IXP-Manager with SDN controller Grafana better visualize...
Image fusion merges the complementary information of different sensors and wavelengths. Images from multiple such as visible infrared (IR) are particular interest in many applications. We present here a multi-stage image scheme for multi-sensor images. At first stage, proposed method segments into homogeneous regions generates segmentation maps. second maps combined by an adaptive weight adjustment procedure. The third stage fuses input images via genetic algorithm based multi-objective...