2023/2

Browse

Now showing 1 - 5 of 11

Machine Learning Based Classification of IoT Traffic
(Společnost pro radioelektronické inženýrství, 2023-06) Velichkovska, B.; Cholakoska, A.; Atanasovski, V.
With the rapid expansion and widespread adoption of the Internet of Things (IoT), maintaining secure connections among active devices can be challenging. Since IoT devices are limited in power and storage, they cannot perform complex tasks, which makes them vulnerable to different types of attacks. Given the volume of data generated daily, detecting anomalous behavior can be demanding. However, machine learning (ML) algorithms have proven successful in extracting complex patterns from big data, which has led to active applications in IoT. In this paper, we perform a comprehensive analysis, including 4 ML algorithms and 3 neural networks (NNs), and propose a pipeline which analyzes the influence data reduction (loss) has on the performance of these algorithms. We use random undersampling as a data reduction technique, which simulates reduced network traffic data. The pipeline investigates several degrees of data loss. The results show that models trained on the original data distribution obtain accuracy that verges on 100%. XGBoost performs best from the classic ML algorithms. From the deep learning models, the 2-layered NN provides excellent results and has sufficient depth for practical application. On the other hand, when the models are trained on the undersampled data, there is a decrease in performance, most notably in the case of NNs. The most prominent change is seen in the 4-layered NN, where the model trained on the original dataset detects attacks with a success of 93.53%, whereas the model trained on the maximally reduced data has a success of only 39.39%.
Optimization of the Crest Factor for Complex-Valued Multisine Signals
(Společnost pro radioelektronické inženýrství, 2023-06) Cseppento, B.; Retzler, A.; Kollar, Z.
Multisine signals are commonly used in the measurement of dynamic systems and wireless channels. For optimal measurements with a high dynamic range, a low Crest Factor (CF) excitation signal is required. In this paper, a modified approach to optimize the crest factor for complex-valued multisine signals is presented. The approach uses a nonlinear optimization method where the real and imaginary parts can also be optimized for low CF. Furthermore, extensions of the real-valued multisine CF optimization methods are presented for complex-valued cases. The proposed methods are validated and compared using simulations. Based on the results it is shown that the novel approach can lead to more optimal signal design and lower CF compared to other techniques for complex-valued multisine signals.
Radar-Based Human Motion Recognition by Using Vital Signs with ECA-CNN
(Společnost pro radioelektronické inženýrství, 2023-06) Chen, K.; Gu, M.; Chen, Z.
Radar technologies reserve a large latent capacity in dealing with human motion recognition (HMR). For the problem that it is challenging to quickly and accurately classify various complex motions, an HMR algorithm combing the attention mechanism and convolution neural network (ECA-CNN) using vital signs is proposed. Firstly, the original radar signal is obtained from human chest wall displacement. Chirp-Z Transform (CZT) algorithm is adopted to refine and amplify the narrow band spectrum region of interest in the global spectrum of the signal, and accurate information on the specific band is extracted. Secondly, six time-domain features were extracted for the neural network. Finally, an ECA-CNN is designed to improve classification accuracy, with a small size, fast speed, and high accuracy of 98%. This method can improve the classification accuracy and efficiency of the network to a large extent. Besides, the size of this network is 100 kb, which is convenient to integrate into the embedded devices.
Ambient Backscatter Communication Based Cooperative Relaying for Heterogeneous Cognitive Radio Networks
(Společnost pro radioelektronické inženýrství, 2023-06) Onay, M. Y.; Ertug, O.
In this paper, a new network model is proposed to improve the performance of the secondary channel in cognitive radio networks (CRNs) based ambient backscatter communication systems. This model is considered as a cooperative system with multi-secondary transmitter (ST) and multi-relay. The ST backscatters data to both the secondary receiver (SR) and relay. Also it harvests energy from the signal emitted by the primary transmitter (PT) during the busy period. The relay activated by the ST user forwards the information from ST to SR. During the idle period, the PT broadcast is interrupted and ST also performs active data transmission using the energy it has harvested. We aim to maximize the number of data transmitted to the SR. Therefore, how long the ST will perform backscattering, energy harvesting and active data transmission is a problem to be solved. In such cooperative systems with multiple users, the solution of the problem becomes more complex. Therefore, the system model has been mathematically modeled and transformed into an optimization problem, considering that users are transmitting data using time division multiple access (TDMA) and non-orthogonal multiple access (NOMA) techniques. Numerical results showed that higher data rates were achieved in NOMA. Additionally, It has been seen that the proposed model performs better when compared to the existing approaches in the literature, where the ST can only harvest energy and transmit data actively or only transmit data with ambient backscatter communication.
Sparsity Adaptive Compressive Sensing based Two-stage Channel Estimation Algorithm for Massive MIMO-OFDM Systems
(Společnost pro radioelektronické inženýrství, 2023-06) Ge, L. J.; Wang, Z. C.; Qian, L.; Wei, P.
Massive multi-input multioutput (MIMO) coupled with orthogonal frequency division multiplexing (OFDM) has been utilized extensively in wireless communication systems to investigate spatial diversity. However, the increasing need for channel estimate pilots greatly increases spectrum consumption and signal overhead in massive MIMO-OFDM systems. This paper proposes a two-stage channel estimation algorithm based on sparsity adaptive compressive sensing (CS) to address this issue. To estimate the channel state information (CSI) for pilot locations in Stage 1, we provide a geometry mean-based block orthogonal matching pursuit (GBMP) method. By calculating the geometric mean of the energy in the support set of the channel response, the GBMP method, when compared to conventional CS methods, can drastically reduce the number of iterations and effectively increase the convergence rate of channel reconstruction. Stage 2 involves estimating the CSI for nonpilot locations using a time-frequency correlation interpolation method, which can increase the accuracy of the channel estimation and is dependent on the estimated results from Stage 1. According to the simulation results, the proposed two-stage channel estimation algorithm greatly reduces the running time with little error performance degradation when compared to traditional channel estimating algorithms.

Browse

Recent Submissions