Search

Cooperative communications is a core research area in wireless vehicular networks (WVNs), thanks to its capability to provide a certain degree of fading mitigation and to improve spectral efficiency. In a cooperative scenario, the intercept probability of the system can be reduced by optimizing the relay selection scheme in order to select the optimal relay from a set of available relays for data transmission. However, due to the mobility of WVNs, the best relay is often selected in practice based on outdated channel state information (CSI), which in turn affects the overall system performance. Therefore, there is a need for a robust relay selection scheme (RSS) that guarantees a satisfactory overall achievable performance in the presence of an outdated CSI. Motivated by this and considering the advantageous features of autoregressive moving average (ARMA), the proposed contribution models a cooperative vehicular communication scenario with relay selection as a Markov decision process (MDP) and proposes two deep Q-networks (DQNs), namely DQN-RSS and DQN-RSS-ARMA. In the proposed framework, two deep reinforcement learning (RL)-based RSS are trained based on the intercept probability, aiming to select the optimal vehicular relay from a set of multiple relays. We then compare the proposed RSS with the conventional methods and evaluate the performance of the network from the security point of view. Simulation results show that DQN-RSS and DQN-RSS-ARMA perform better than conventional approaches, as they reduce intercept probability by approximately 15% and 30%, respectively, compared to the standard ARMA approach.

Deep learning networks achieve high accuracy for many classification tasks in computer vision and natural language processing. As these models are usually over-parameterized, the computations and memory required are unsuitable for power-constrained devices. One effective technique to reduce this burden is through low-bit quantization. However, the introduced quantization error causes a drop in the classification accuracy and requires design rethinking. To benefit from the hardware-friendly power-of-two (POT) and additive POT quantization, we explore various gradient estimation methods and propose quantization error-aware gradient estimation that manoeuvres weight update to be as close to the projection steps as possible. The clipping or scaling coefficients of the quantization scheme are learned jointly with the model parameters to minimize quantization error. We also apply per-channel quantization on POT and additive POT quantized models to minimize the accuracy degradation due to the rigid resolution property of POT quantization. We show that comparable accuracy can be achieved when using the proposed gradient estimation for POT quantization, even at ultra-low bit precision.

The highly dynamic nature of cognitive radio (CR) systems and their stringent latency requirements pose a significant challenge in the realization of efficient intelligent transport systems (ITS). In this paper, we investigate relay selection and opportunistic spectrum access in conjunction with blockchain technology in a secure manner. Specifically, we propose a cross-layer method for secure relay selection, where secondary relays (SRs) are granted access to available spectrum bands based on the balance of their respective virtual wallets. These virtual wallets, which are built based on the SRs' secrecy capacity and their behavior in the network, are the predominant factors that allow SRs to participate in an auction model. To quantify the trustworthiness of the SRs, we formulate a mathematical framework to evaluate the trust value of each SR, which is then leveraged for rewarding or penalizing the SR. Also, we develop an offline blockchain framework to store the information of participating relays and make it available for future operations, to detect reputable and non-reputable relays in the presence of multiple eavesdroppers. The stored reputations of the participating relays are used to develop a self-learning algorithm to exclude the non-reputable relays from the selection group. Finally, we present thorough numerical results to demonstrate the superiority of the proposed system in terms of security, credibility, and integrity.

Visible light communication (VLC) has been introduced as a key enabler for high-data rate wireless services in future wireless communication networks. In addition to this, it was also demonstrated recently that non-orthogonal multiple access (NOMA) can further improve the spectral efficiency of multi-user VLC systems. In this context and owing to the significantly promising potential of artificial intelligence in wireless communications, the present contribution proposes a deep Q-learning (DQL) framework that aims to optimize the performance of an indoor NOMA-VLC downlink network. In particular, we formulate a joint power allocation and LED transmission angle tuning optimization problem, in order to maximize the average sum rate and the average energy efficiency. The obtained results demonstrate that our algorithm offers a noticeable performance enhancement into the NOMA-VLC systems in terms of average sum rate and average energy efficiency, while maintaining the minimum convergence time, particularly for higher number of users. Furthermore, considering a realistic downlink VLC network setup, the simulation results have shown that our algorithm outperforms the genetic algorithm (GA) and the differential evolution (DE) algorithm in terms of average sum rate, and offers considerably less run-time complexity.

Deep Neural Networks (DNNs) are computationally and memory intensive, which present a big challenge for hardware, especially for resource-constrained devices such as Internet-of-Things (IoT) nodes. This paper introduces a new method to improve DNNs performance by fusing approximate computing with data reuse techniques for image recognition applications. First, starting from the pre-trained network, then the DNNs weights are approximated based on the linear and quadratic approximation methods during the retraining phase to reduce the DNN model size and number of arithmetic operations. Then, the DNNs weights are replaced with the linear/quadratic coefficients to execute the inference so that different DNNs weights can be computed using the same coefficients. That leads to a repetition of the weights, which enables the reuse of the DNN sub-computations (computational reuse) and leverages the same data (data reuse) to reduce DNNs computations memory accesses, and improve energy efficiency, albeit at the cost of increased training time. Complete analysis for MNIST, Fashion MNIST, CIFAR 10, CIFAR 100, and tiny ImageNet datasets is presented for image recognition, where different DNN models are used, including LeNet, ResNet, AlexNet, and VGG16. Our results show that the linear approximation achieves $1211.3\times $ , $21.8\times $ , $700\times $ , and $19.3\times $ on LeNet-5 MNIST, LeNet Fashion MNIST, VGG16 and ResNet-20. respectively, with small accuracy loss. Compared to the state-of-the-art Row Stationary (RS) method, the proposed architecture saved 54% of the total number of adders and multipliers needed. Overall, the proposed approach is suitable for IoT edge devices as it reduces computing complexity, memory size, and memory access with a small impact on accuracy.

Recent advances in artificial intelligence (AI) and continuous monitoring of patients using wearable devices have enhanced the accuracy of diagnosing various arrhythmias, from the captured Electrocardiogram (ECG) signals. Achieving high accuracy when using Deep Neural Network (DNN) for ECG classification is accomplished at the cost of compute and memory intensive operations, thus limiting its deployment to devices with high computing capabilities, and makes it unsuitable for wearable edge devices. To facilitate the deployment of deep neural networks on wearable mobile edge devices with limited resources, a lightweight Convolution Neural Network (CNN) model based on the ShuffleNet architecture is proposed and implemented as a solution in this paper. A sliding window of variable stride is used to increase the number of under-represented classes in the database. Moreover, a novel encoding scheme is employed for labelling and training test set samples, allowing the model to detect multiple classes in one ECG segment. A loss function (Focal loss) that proved to be effective when applied for DNN training on an imbalanced dataset was also explored in this work. The proposed model outperformed traditional CNN with 9x less trainable parameters and improved the F1-score by 2%.

Inter-cell interference (ICI) and inter-user interference (IUI) constitute a major issue towards achieving the optimum spectral efficiency (SE) and energy efficiency (EE) performance in multi-cell visible light communication (VLC) networks. Hence, advanced multiple access techniques need to be leveraged in order to improve the provided service to the users of such interfering networks. To this end, the present contribution proposes the integration of coordinated beamforming (CB) with rate-splitting multiple access (RSMA) in multi-cell VLC systems. Specifically, we consider the design of beamformers for the common and private streams in a coordinated manner between different attocells, which is shown to provide efficient mitigation of the incurred interference. Additionally, the formulated optimization problem aims to minimize the sum of the mean squared error across all attocells in order to jointly determine the optimum receive filters and coordinated transmit beamformers for RSMA streams. In this context, we illustrate through extensive computer simulations, which are carried out in a realistic setup that assumes noisy channel state information acquisition, the distinct flexibility and robustness of CB-based RSMA in mitigating the incurred interference. Finally, the offered results demonstrate the superiority of CB-based RSMA in terms of achievable SE and EE performance in multi-cell VLC networks compared to the conventional CB-based space division multiple access counterpart.

Visible light communication (VLC) has been recognized as a promising technology for handling the continuously increasing quality of service and connectivity requirements in modern wireless communications, particularly in indoor scenarios. In this context, the present work considers the integration of two distinct modulation schemes, namely spatial modulation (SM) with space time block codes (STBCs), aiming at improving the overall VLC system reliability. Based on this and in order to further enhance the achievable transmission data rate, we integrate quasi-orthogonal STBC (QOSTBC) with SM, since relaxing the orthogonality condition of OSTBC ultimately provides a higher coding rate. Then, we generalize the developed results to any number of active light-emitting diodes (LEDs) and any $M$-ary pulse amplitude modulation size. Furthermore, we derive a tight and tractable upper bound for the corresponding bit error rate (BER) by considering a simple two-step decoding procedure to detect the indices of the transmitting LEDs and then decode the signal domain symbols. Notably, the obtained results demonstrate that QOSTBC with SM enhances the achievable BER compared to SM with repetition coding (RC-SM). Finally, we compare STBC-SM with both multiple active SM (MASM) and RC-SM in terms of the achievable BER and overall data rate, which further justifies the usefulness of the proposed scheme.

We propose an enhanced spatial modulation (SM)-based scheme for indoor visible light communication systems. This scheme enhances the achievable throughput of conventional SM schemes by transmitting higher order complex modulation symbol, which is decomposed into three different parts. These parts carry the amplitude, phase, and quadrant components of the complex symbol, which are then represented by unipolar pulse amplitude modulation (PAM) symbols. Superposition coding is exploited to allocate a fraction of the total power to each part before they are all multiplexed and transmitted simultaneously, exploiting the entire available bandwidth. At the receiver, a two-step decoding process is proposed to decode the active light emitting diode index before the complex symbol is retrieved. It is shown that at higher spectral efficiency values, the proposed modulation scheme outperforms conventional SM schemes with PAM symbols in terms of average symbol error rate (ASER), and hence, enhancing the system throughput. Furthermore, since the performance of the proposed modulation scheme is sensitive to the power allocation factors, we formulated an ASER optimization problem and propose a sub-optimal solution using successive convex programming (SCP). Notably, the proposed algorithm converges after only few iterations, whilst the performance with the optimized power allocation coefficients outperforms both random and fixed power allocation.

This paper proposes an efficient encryption technique based on Dynamic and Secure Substitution Box (DS2B) design suitable for IoT and resource-constrained platforms. The DS2B has the advantages of simple structure and good encryption performance. A different number of strong S-boxes could be generated with minor variations in the DS2B parameters. Performance analyses of the DS2B, including differential/linear cryptanalysis, bijective, nonlinearity, strict avalanche criterion (SAC), and bit independence criterion (BIC) have been presented where high $nonlinearity$ , and low differential uniformity are achieved. Besides, a comparison with recent S-boxes is introduced which shows the robustness of the DS2B. To verify the DS2B, a speech encryption engine was realized on FPGA. Various security analyses were evaluated including the National Institute of Standards & Technology (NIST) statistical test suite, number of samples changes rate NSCR, mean square error (MSE), correlation, histogram, and spectrogram. In this work, the silence periods are encrypted in a way that makes them much harder to detect using the DS2B. The proposed encryption scheme achieved a throughput of 9.87 G bit/s, which is higher than previous work. A Xilinx Nexys 4 FPGA evaluation board was used for implementing and verifying the design.

Convolutional Neural Networks (CNNs) revolutionized computer vision and reached the state-of-the-art performance for image processing, object recognition, and video classification. Even though CNN inference is notoriously compute-intensive, as convolutions account for >90% of the total operation tasks, the ability to tradeoff between accuracy, performance, power, and latency to meet target application makes it an open research topic. This paper proposes the Spatial Locality Input Data (SLID) method for computational reuse during the inference stage for a pre-trained network. The method exploits input data spatial locality via skipping partial processing of the multiply-and-accumulate (MAC) operations for adjacent data and equating its value to previously computed ones. SLID improves the throughput of resource-constrained devices (Internet-of-Things, edge devices) and accelerates computations during the inference phase by reducing the number of MAC operations. Such approximate computing schema does not require a similarity quantification step nor any modification for the training stage. The computational data reuse was evaluated on three well-known distinctive CNN structures and data sets with alternating layer selections: LeNet, CIFAR-10, and AlexNet. The computational data reuse method saves up to 34.9%, 49.84%, and 31.5% of MAC operations while reducing the accuracy by 8%, 3.7%, and 5.0% for the three models mentioned earlier, respectively. Besides, the proposed method saves on memory access by eliminating data fetching of skipped inputs. Furthermore, filter size, strides, and padding on the accuracy and savings of operations are analyzed. SLID is the first work to exploit the input spatial locality for savings on CNN convolution operations with minimal accuracy loss and without memory or computational overhead. This makes it a great option to support intelligence at the edge.

Binary convolutional neural networks (BCNN) have been proposed in the literature for resource-constrained IoTs nodes and mobile computing devices. Such computing platforms have strict constraints on the power budget, system performance, processing and memory capabilities. Nonetheless, the platforms are still required to efficiently perform classification and matching tasks needed in various applications. The memristor device has shown promising results when utilized for in-memory computing architectures, due to its ability to perform storage and computation using the same physical element. This is in addition to their nonlinear dynamic characteristics that can be used for various applications. Emulating the memristor operation through FPGAs implementation provides flexibility for rapid prototyping and exploration of the design space. In this paper, a FPGA-based memristor emulator circuit is implemented using a multi-bit XNOR gate as the main block for binary convolution which is followed by a memristor-based pooling layer. The BCNN layer is realized by bitwise XNOR-cell followed by wide NOR gate. The implementation has been successfully synthesized and verified using Xilinx Nexys4 FPGA with less than 1% utilization and 144.9 MHz frequency of operation. In order to test the functionality of the proposed cores, a digital implementation for the circuit was realized and verified experimentally. The experimental results show similar performance when compared to software simulation.

The increased proliferation of connected devices requires a development of innovative technologies for the next generation of wireless systems. One of the key challenges, however, is the spectrum scarcity, owing to the unprecedented broadband penetration rate in recent years. Based on this, visible light communication (VLC) has recently emerged as an effective potential solution for enabling high-speed short-range communications. Yet, despite their undoubted advantageous features, VLC systems suffer from several limitations which constraint their capabilities. As a result, several multiple access (MA) techniques, such as space-division multiple access (SDMA) and non-orthogonal multiple access (NOMA), have been considered in VLC networks as an effective approach, among others, to circumvent these limitations. However, despite their achievable multiplexing gain, their overall performance is still limited compared to the overall potential of this technology. Motivated by this, the presented article offers two contributions: firstly, we provide an overview of the key MA technologies used in VLC systems and then we introduce rate-splitting multiple access (RSMA), and discuss its capabilities and potentials in VLC systems. Secondly, through realistic system modeling and simulations of an RSMA-based two-user scenario, we illustrate the flexibility of RSMA as well as its superiority in terms of the achievable weighted sum rate over NOMA and SDMA in the context of VLC. Finally, we discuss technical challenges, open issues, and research directions, along with the offered results and insights that are expected to be useful towards the effective practical realization of RSMA in VLC configurations.

Memristor characteristics such as nonlinear dynamics, state retention and accumulation are useful for many applications. FPGA implementation of memristor-based systems and algorithms provides fast development and verification platform. In this work, we first propose a versatile digital memristor emulator that exhibits either continuous or discrete behaviors, similar to valence change memories (VCM) and the electrochemical metallization memories. Secondly, the proposed memristor emulator is used to design a chaotic generator circuit utilizing the memristor's nonlinearity. Finally, the chaotic system is used to design a speech encryption engine to demonstrate its capabilities. The memristor emulator, chaotic generator, and the encryption system were implemented on Nexys 4 Artix-7 FPGA XC7A100T. The implementation results show an efficiency in throughput and hardware resources utilization compared to the previous works. In addition, the encryption system results show good performance against several perceptual, statistical attacks in addition to resistance to security attacks tests including differential attacks, NIST tests, key space analysis, mean square error (MSE), correlation, histogram and spectrogram.

A Machine Learning (ML)-based Intrusion Detection and Prevention System (IDPS) requires a large amount of labeled up-to-date training data to effectively detect intrusions and generalize well to novel attacks. However, the labeling of data is costly and becomes infeasible when dealing with big data, such as those generated by Internet of Things applications. To this effect, building an ML model that learns from non-labeled or partially labeled data is of critical importance. This paper proposes a Semi-supervised Multi-Layered Clustering ((SMLC)) model for the detection and prevention of network intrusion. SMLC has the capability to learn from partially labeled data while achieving a detection performance comparable to that of supervised ML-based IDPS. The performance of SMLC is compared with that of a well-known semi-supervised model (tri-training) and of supervised ensemble ML models, namely RandomForest, Bagging, and AdaboostM1 on two benchmark network-intrusion datasets, NSL and Kyoto 2006+. Experimental results show that SMLC is superior to tri-training, providing a comparable detection accuracy with 20% less labeled instances of training data. Furthermore, our results demonstrate that our scheme has a detection accuracy comparable to that of the supervised ensemble models. Keywords: Semi-supervised intrusion detection, Machine learning, Classification, Ensembles, Big data

We develop an analytical framework to characterize the effect of impulsive noise on the performance of relay-assisted simultaneous wireless information and power transfer (SWIPT) systems. We derive novel closed-form expressions for the pairwise error probability considering two variants based on the availability of channel state information (CSI), namely, blind relaying and CSI-assisted relaying. We further consider two energy harvesting (EH) techniques, i.e., instantaneous EH (IEH) and average EH (AEH). Capitalizing on the derived analytical results, we present a detailed numerical investigation of the diversity order for the underlying scenarios under the impulsive noise assumption. For the case when two relays and the availability of a direct link, it is demonstrated that the considered SWIPT system with blind AEH-relaying is able to achieve an asymptotic diversity order of less than 3, which is equal to the diversity order achieved by CSI-assisted IEH-relaying. This result suggests that, by employing the blind AEH relaying, the power consumption of the network can be reduced, due to eliminating the need of CSI estimation. This can be achieved without any performance loss. Our results further show that placing the relays close to the source can significantly mitigate the detrimental effects of impulsive noise. Extensive Monte Carlo simulation results are presented to validate the accuracy of the proposed analytical framework.

Continuous monitoring of vital signs, such as respiration and heartbeat, plays a crucial role in early detection and even prediction of conditions that may affect the wellbeing of the patient. Sensing vital signs can be categorized into: contact-based techniques and contactless based techniques. Conventional clinical methods of detecting these vital signs require the use of contact sensors, which may not be practical for long duration monitoring and less convenient for repeatable measurements. On the other hand, wireless vital signs detection using radars has the distinct advantage of not requiring the attachment of electrodes to the subject’s body and hence not constraining the movement of the person and eliminating the possibility of skin irritation. In addition, it removes the need for wires and limitation of access to patients, especially for children and the elderly. This paper presents a thorough review on the traditional methods of monitoring cardio-pulmonary rates as well as the potential of replacing these systems with radar-based techniques. The paper also highlights the challenges that radar-based vital signs monitoring methods need to overcome to gain acceptance in the healthcare field. A proof-of-concept of a radar-based vital sign detection system is presented together with promising measurement results.