Abstract:This paper presents a deep learning-based framework for enhancing radar systems in the presence of interference, leveraging Reconfigurable Intelligent Surfaces (RIS). The proposed technique uses a modified MUSIC algorithm to estimate the angles of the target and interference. The core of the method is a deep learning model that optimizes the RIS configuration to reduce the impact of interference while maintaining accurate angle estimates. The model consists of a multi-layer perceptron (MLP) that takes estimated angles as inputs and outputs the configuration of the RIS. A specially designed loss function ensures that the interference is properly suppressed and the target remains detectable. To further enhance performance, a convolution technique is introduced to create a notch at the interference angle, ensuring better separation between the target and interference. Additionally, the method is extended to work over multiple subcarriers, improving robustness and performance in practical scenarios. Simulation results show that the technique enhances the signal-to-interference-plus-noise ratio (SINR) and provides accurate localization estimates, demonstrating its potential for radar systems in complex environments.
Abstract:This paper introduces a method to reduce interference in OFDM radar systems through the use of reconfigurable intelligent surfaces (RIS). The method involves adjusting the RIS elements to diminish interference effects and improve the clarity of the desired signal. A neural network framework is established to optimize the configurations of the RIS, aiming to lower the power from unwanted sources while enhancing the target signal. The network produces settings that focus on maximizing the signal at the intended angle. Utilizing a convolution-based approach, we illustrate the effective tuning of RIS elements for interference mitigation and the creation of nulls in the direction of interference, resulting in a better signal-to-interference-and-noise ratio (SINR). Simulations confirm the effectiveness of the proposed method in a radar context, demonstrating its capability to enhance target detection while reducing interference.
Abstract:Traffic flows are set of packets transferring between a client and a server with the same set of source and destination IP and port numbers. Traffic classification is referred to as the task of categorizing traffic flows into application-aware classes such as chats, streaming, VoIP, etc. Classification can be used for several purposes including policy enforcement and control or QoS management. In this paper, we introduce a novel end-to-end traffic classification method to distinguish between traffic classes including VPN traffic. Classification of VPN traffic is not trivial using traditional classification approaches due to its encrypted nature. We utilize two well-known neural networks, namely multi-layer perceptron and recurrent neural network focused on two metrics: class scores and distance from the center of the classes. Such approaches combined extraction, selection, and classification functionality into a single end-to-end system to systematically learn the non-linear relationship between input and predicted performance. Therefore, we could distinguish VPN traffics from Non-VPN traffics by rejecting the unrelated features of the VPN class. Moreover, obtain the application of Non-VPN traffics at the same time. The approach is evaluated using the general traffic dataset ISCX VPN-nonVPN and the acquired real dataset. The results of the analysis demonstrate that our proposed model fulfills the realistic project's criterion for precision.