Search

Summary: Mobile Ad Hoc Network (MANETs) are indeed autonomous, fast‐deployable wireless networks that are ideal for communications in areas with limited radio infrastructure, outdoor events, military operations, and disaster relief. But the primary problem is with routing because of the nodes' mobility. This paper proposes a cluster‐based routing under energy prediction via deep learning techniques. Here, proposes a new model termed as Concatenation of Convolutional with Max‐Avg Pooling layer in Deep Convolutional Neural Network (CCMAP‐DCNN) for energy prediction, in which additional layers are inserted into the extant DCNN structure to ensure the effectiveness of energy prediction. As a result, clusters are created by grouping the nodes together. Constraints like energy, trust, distance, and latency are taken into account while choosing the cluster leader. For cluster head selection and optimal routing, proposes a new hybrid Namib Beetle Upgraded Jellyfish Search Optimization (NBUJSO) algorithm that utilizes the NBO strategy to the JSO algorithm making the selection process more optimal. The best route is then chosen by the optimum routing method, which takes into account variables like network quality and mobility to send data packets from source to destination as efficiently as possible. Finally, the data aggregation process is followed for eliminating the redundant transmission. [ABSTRACT FROM AUTHOR]

Summary: In millimeter wave (mmWave) massive multiple‐input‐multiple‐output (MIMO) systems, hybrid precoding plays a pivotal role in reducing complexity and cost while providing a good spectral efficiency. However, implementation of digital precoders with large number of antennas is difficult due to hardware constraints, while analog precoders offer confined performance. This leads to high computational complexity and cannot fully exploit the spatial information. Previous studies on hybrid precoding were based on exhaustive search solutions or greedy schemes, which result in higher complexity system performance. To face these challenges, this paper proposes deep hybrid precoding framework with phase quantization and residual dense network to design the matrix of analog and digital precoders. The proposed deep hybrid precoding technique consists of offline training stage and online deployment stage. In offline training stage, hybrid precoding is obtained assuming the approximate phase quantization. While in the online deployment stage, the matrix of analog precoding is calculated by exchanging approximate phase quantization with ideal phase and grouping the analog precoding vectors. In this paper, we also propose a deep reinforcement learning‐based hybrid precoding. It consists of a deep reinforcement learning with employing convolutional neural network and long short‐term memory (LSTM) methods. In our proposed frameworks, structures of proposed techniques are trained for maximum spectral efficiency. Our proposed techniques are compared with other precoding techniques. Results illustrate that the proposed techniques outperforms the other precoding techniques in terms of the spectral efficiency. [ABSTRACT FROM AUTHOR]

Summary: In the presence of noise in communication systems, constellation diagram points are scattered to the extent that may make the modulation classification a difficult task. With the plethora of applications of machine and deep learning, several communication systems have adopted machine and deep learning to solve some classical detection and classification problems. Casting the modulation order detection as a pattern classification of the constellation images opens the door for application of mature machine learning and image processing tools to solve the classification problem, efficiently. This paper presents a system based on a wavelet‐aided convolutional neural network (CNN) classifier to efficiently detect the modulation type and order in the presence of noise. The proposed system depends on a pretrained CNN setup, which is trained with a set of constellation diagrams for each modulation scheme and used after that for testing. In addition, discrete wavelet transform (DWT) is investigated to generate representative patterns from constellation diagrams to be used for the training and testing tasks as well. The wavelet approximation images and their corresponding wavelet sub‐bands across all predefined scales are used in the dataset. Several pretrained networks including AlexNet, VGG‐16, and VGG‐19 are used as classifiers for the modulation type from the DWTs for different constellation diagrams. Several simulation experiments are presented in this paper to compare different scenarios for modulation classification at different signal‐to‐noise ratios (SNRs). [ABSTRACT FROM AUTHOR]

Summary: The omnipresence of drones in the civilian air space has led to their malicious usage raising high alert security issues. In this paper, a deep learning approach to detect and identify drones and to determine their flight modes from the remotely sensed radio frequency (RF) signatures is presented. This work intends to detect the presence of drones using two‐class classification, the presence along with identification of their make using four‐class classification. And this is further extended to the determination of their flight modes using ten‐class classification. It employs the proposed architectures of prominent deep learning classifiers, namely, autoencoder (AE), long short‐term memory (LSTM), convolutional neural network (CNN), and CNN‐LSTM hybrid model. To procure the relevant information from 227 RF signatures having 100 fragments each, the seven significant temporal statistical features, namely, maxima, minima, mean, variance, skewness, kurtosis, and root mean square, are extracted. In a two‐class classification scenario, all considered classifiers perform near to idle, whereas in a four‐class classification scenario, CNN performs best, followed by AE, CNN‐LSTM, and LSTM, respectively. Moreover, in a ten‐class classification scenario, AE far outperforms CNN, followed by LSTM and CNN‐LSTM, respectively. The best performance in terms of accuracy and classification time confirms the feasibility of the proposed AE classifier for the three considered drone operations. [ABSTRACT FROM AUTHOR]

Summary: Data center networks (DCNs) are facing challenging control problems such as flow scheduling, congestion control, load balancing, and bandwidth allocation when dynamically handling heterogeneous mice and elephant flows. This paper focuses on the load balancing in DCNs as an online decision‐making problem with high complexity (NP‐hard problem). Traditional load balancing approaches are usually the heuristic algorithms relying on the operator's viewpoint and a short‐term knowledge of the traffic conditions and network environment. This paper proposes DeepRLB, a deep reinforcement learning (DRL)‐based load balancing approach for software‐defined networking‐based DCNs which exploits the deep deterministic policy gradient (DDPG) algorithm to adaptively learn the link‐weight values by observing the traffic flow characteristics. The actor and critic neural networks in the DDPG model have been designed based on two learning models: fully connected (DeepRLB‐Full) and convolutional (DeepRLB‐Conv). The output of the model is further used by the controller to determine the forwarding paths for traffic flows accordingly. We evaluated the performance of DeepRLB by comparing it with ECMP as well as a per‐packet load balancing algorithm in three different data center topologies under 30 heterogeneous traffic demand matrices. The obtained results showed that the DeepRLB algorithm outperforms the ECMP with respect to studied load balancing metrics considerably (DeepRLB‐Conv achieved the best performance). As a sample, DeepRLB‐Full and DeepRLB‐Conv were able to reach 19.14% and 24.46% reduction in the total number of over‐utilized and under‐utilized network links compared to ECMP, respectively. [ABSTRACT FROM AUTHOR]

Summary: Studying deep learning framework in massive cellular system to optimize its performance is a challenge task. In this paper, multi‐cell massive cellular system with device‐to‐device (D2D) communication is studied, where D2D pairs and cellular users can share different orthogonal pilots to overcome interference at the cellular base station (BS). We propose data and pilot power controls scheme based on deep learning framework using convolutional neural network (CNN) for cellular and D2D users. The main focus is to obtain the optimal data and pilot powers (i.e., cellular pilot power, pCellular Userpilot, cellular data power, pCellular User, D2D pilot power, pD2Dpilot, and D2D data power, pD2D) for maximum spectral efficiency (SE). SE optimization problem is formulated with the goal of obtaining optimal transmit powers. Also, comparison between the proposed scheme and the iterative power control schemes (i.e., weighted minimum mean square error [MMSE] technique, bisection technique, and technique‐based geometric mean per‐cell max–min fairness) is provided. Results show that the proposed scheme can increase the sum SE of multi‐cell massive cellular system with D2D communications. [ABSTRACT FROM AUTHOR]

Summary: Multiple‐input multiple‐output (MIMO) technology is much significant for achieving high data rates while considering the multiuser communication. For this purpose, the estimation of Channel State Information (CSI) is performed by the pilot. But, the estimated CSI cannot be applied for downlinks while processing an extremely high speed mobile data as it gets outdated because of the rapid channel variation. Estimating the channel in the MIMO systems is highly difficult on using non‐stationary channel characteristics under the high mobility environments. Channel estimation with received signal‐to‐noise ratio (SNR) feedback ensures an effective performance in the practical wireless MIMO systems. This paper plans to develop an intelligent deep learning strategy to solve the channel estimation problem in MIMO system. The main goal of the proposed model is to estimate the MIMO channel coefficients at a transmitter based on the received SNR feedback information from a receiver using the swarm intelligence‐based deep ensemble learning machine (SI‐DELM). For both the scenarios, the SI‐DELM is developed, in which the convolution neural network (NN) with three classifiers is used. Here, the fully connected layers of CNN are replaced by the NN, recurrent neural network (RNN), and deep neural network (DNN). In the SI‐DEL‐based channel estimation, the hyper parameter tuning is performed by the adaptive iteration assisted mixture ratio‐based cat swarm optimization (AIMR‐CSO) for minimizing the mean square error (MSE) and bit error rate (BER) of the estimated channel. Finally, by performing numerical simulations, the efficiency and better performance of the suggested model is revealed by conducting the comparison between proposed and conventional models. [ABSTRACT FROM AUTHOR]

Summary: Cognitive radio (CR) has become an interesting research field that attracts researchers due to its increasing spectrum efficiency. Therefore, spectrum sensing (SS) is the essential function of cognitive radio systems. This paper presents an efficient SS model based on convolutional neural networks (CNNs). We use the spectrogram images of the received signals as the input to the CNN and use various images for signal and noise at different low primary‐user (PU) signal‐to‐noise ratios (SNRs) to train the network model. The model extracts the main features from the spectrogram images to represent signals and noise. Hence, this model can efficiently discriminate between signal and noise at different SNRs. The detection performance of the suggested model is compared with those of the traditional one‐stage, two‐stage SS methods, and different previous CNN models. The obtained outcomes demonstrate that the suggested model increases the detection accuracy more than those of the previous one‐stage SS methods by 17% at low SNRs of −20 dB and more than the previous two‐stage SS methods by 8% at low SNRs of −20 dB. In addition, it is demonstrated that the suggested model offers shorter sensing times than those of the two‐stage and one‐stage SS methods in the orders of 16.3, 16.6, 1.1, and 1.5 ms at SNRs of −20, −15, −10 and −5 dB, respectively. Furthermore, the proposed model improves the detection accuracy better than the different previously compared CNN models by 28% and 19% at low SNRs of −20 and −15 dB, respectively. [ABSTRACT FROM AUTHOR]