Ventricular arrhythmia detection is a critical yet challenging task in cardiac healthcare due to the rarity of abnormal episodes and the high inter-patient variability in cardiac signals. These challenges are further exacerbated in implantable cardioverter-defibrillators, which operate under stringent memory and computational constraints. In this paper, we analyze inter- and intra-patient variability using dimensionality reduction and divergence metrics, and leverage these observations to formulate ventricular arrhythmia detection as a deployment-aligned one-class meta-learning problem. Accordingly, we adopt a one-class formulation of model-agnostic meta-learning (OC-MAML) with a clinically grounded task design that reflects real-world deployment conditions. Specifically, patient-disjoint support and query sets are used to simulate realistic distribution shifts and inter-patient variability. By training primarily on normal intracardiac electrogram segments, the OC-MAML-based framework learns a task-agnostic initialization that rapidly adapts to new patients using only a few normal samples, thereby substantially reducing dependence on labeled arrhythmic data. Compared to conventionalvanillamodel-agnostic meta-learning (MAML), our proposed OC-MAML-based framework achieves a relative improvement of +14.1% in sensitivity, +2.5% in balanced accuracy, and +4.1% inF1-score, while reducing adaptation time by 5× and maintaining comparable memory efficiency. These results underscore the framework’s potential for scalable, nearly label-free deployment in edge-based cardiac monitoring systems. The code for the proposed framework is publicly available at https://github.com/jaradat/VAD-OC-MAML.

FALCON is a lattice-based post-quantum cryptographic (PQC) digital signature standard known for its compact signatures and resistance to quantum attacks. Since its recent standardization, its hardware implementation remains an open challenge, particularly for key generation, which is significantly more complex than the simple and well-studied signature verification process. In this paper, targeting edge devices with constrained resources, we present an energy-efficient and area-optimized NTT/INTT architecture tailored to the specific requirements of FALCON key generation. By leveraging NTT-friendly primes and reducing the size of the multipliers in the Montgomery reduction algorithm — optimized for ASIC implementation — our design minimizes hardware complexity, achieving the lowest power and area consumption compared to state-of-the-art Montgomery reduction implementations. The proposed hardware architecture features a processing element array, distributed SRAMs, and ROMs, with three levels of reconfigurability, supporting both NTT and INTT operations. Designed using the Global Foundries’ 22 nm FD-SOI process, an Application-Specific Integrated Circuit (ASIC) is estimated to occupy 0.04 mm 2 and consume 18.2 mW at 1 GHz. The proposed processor achieves 700 times greater energy efficiency and performs computations 200 times faster than software implementations on the ARM Cortex-M4. It also achieves the lowest area–time product and highest energy efficiency among state-of-the-art NTT/INTT hardware accelerators. By carefully balancing power consumption and computational speed, this design offers an efficient solution for deploying FALCON key generation on devices with limited resources.

Deep neural networks (DNNs) are indispensable in various artificial intelligence (AI) applications. However, their inherent complexity presents significant challenges, particularly when deploying them on resource-constrained devices. To overcome these hurdles, academia and industry are actively seeking ways to accelerate and optimize DNN implementations. A significant area of research revolves around discovering more effective methods to represent the enormous data volumes processed by DNNs. Traditional number systems (NSs) have proven nonoptimal for this task, prompting extensive exploration into alternative and bespoke systems for DNNs. This survey aims to comprehensively discuss various NSs utilized to efficiently represent DNN data. These systems are categorized mainly based on their impact on DNN performance and hardware implementation. This survey offers an overview of these categorized NSs and delves into different subsystems within each, outlining their effect on DNN performance and hardware design. Furthermore, these systems are compared quantitatively and qualitatively concerning their expected quantization error, memory utilization, and computational requirements. This survey also emphasizes the challenges linked with each system and the diverse proposed solutions to address them. Insights into the utilization of these NSs for sophisticated DNNs are also presented in this survey. Readers will acquire a deeper understanding of the importance of efficient NSs for DNNs, explore commonly used systems, comprehend the tradeoffs between these systems, delve into design considerations influencing their impact on DNN performance, and discover recent trends and potential research avenues in this field.

Balancing traffic among cellular networks is very challenging due to many factors. Nevertheless, the explosive growth of mobile data traffic necessitates addressing this problem. Due to the problem complexity, data-driven self-optimized load balancing techniques are leading contenders. In this work, we propose a comprehensive deep reinforcement learning (RL) framework for steering the cell individual offset (CIO) as a means for mobility load management. The state of the LTE network is represented via a subset of key performance indicators (KPIs), all of which are readily available to network operators. We provide a diverse set of reward functions to satisfy the operators' needs. For a small number of cells, we propose using a deep Q-learning technique. We then introduce various enhancements to the vanilla deep Q-learning to reduce bias and generalization errors. Next, we propose the use of actor-critic RL methods, including Deep Deterministic Policy Gradient (DDPG) and twin delayed deep deterministic policy gradient (TD3) schemes, for optimizing CIOs for a large number of cells. We provide extensive simulation results to assess the efficacy of our methods. Our results show substantial improvements in terms of downlink throughput and non-blocked users at the expense of negligible channel quality degradation.

Wireless networks have been going through tremendous proliferation recently. As a result, a continuous configuration and management are necessary to sustain a balanced performance while facing such continued growth and endless changes. A self-managed network is required to replace manual management, which is costly, time-consuming, and error-prone. In this paper, we propose a machine-learning-based cellular network management system. The proposed system aims to enhance the network stability and adaptability to temporal changes (e.g., load imbalances across cells). The presented approach is a deep reinforcement learning scheme that enables a network manager to learn a policy that maximizes the network average sum throughput while trying to minimize the consumed energy and the number of blocked users. In addition to controlling the transmitted power and the cell individual offset, MIMO can be switched ON and OFF to control the consumed energy without affecting the quality of service. This results in a hybrid action space, i.e., our action vector has some binary actions as well as continuous actions. We present a novel algorithm to deal with this hybrid action space. Our results reveal that our proposed algorithm is flexible, efficient, and reliable. We report significant performance gains compared to some baselines (without self-management) and previously proposed algorithms.

Cellular networks' congestion has been one of the most common problems in cellular networks due to the huge increase in network load resulted from enhancing communication quality as well as increasing the number of users. Since mobile users are not uniformly distributed in the network, the need for load balancing as a cellular networks' self-optimization technique has increased recently. Then, the congestion problem can be handled by evenly distributing the network load among the network resources. Lots of research has been dedicated to developing load balancing models for cellular networks. Most of these models rely on adjusting the Cell Individual Offset (CIO) parameters which are designed for self-optimization techniques in cellular networks. In this paper, a new deep reinforcement learning-based load balancing approach is proposed as a solution for the LTE Downlink congestion problem. This approach does not rely only on adapting the CIO parameters, but it rather has two degrees of control; the first one is adjusting the CIO parameters, and the second is adjusting the eNodeBs' transmission power. The proposed model uses Double Deep Q-Network (DDQN) to learn how to adjust these parameters so that a better load distribution in the overall network is achieved. Simulation results prove the effectiveness of the proposed approach by improving the network overall throughput by up to 21.4% and 6.5% compared to the base-line scheme and the scheme that only adapts CIOs, respectively.

We consider the problem of jointly optimizing the transmission power and cell individual offsets (CIOs) in the downlink of cellular networks using reinforcement learning. To that end, we reformulate the problem as a Markov decision process (MDP). We abstract the cellular network as a state, which comprises of carefully selected key performance indicators (KPIs). We present a novel reward function, namely, the penalized throughput, to reflect the tradeoff between the total throughput of the network and the number of covered users. We employ the twin deep delayed deterministic policy gradient (TD3) technique to learn how to maximize the proposed reward function through the interaction with the cellular network. We assess the proposed technique by simulating an actual cellular network, whose parameters and base station placement are derived from a 4G network operator, using NS-3 and SUMO simulators. Our results show the following: 1) optimizing one of the controls is significantly inferior to jointly optimizing both controls; 2) our proposed technique achieves 18.4% throughput gain compared with the baseline of fixed transmission power and zero CIOs; 3) there is a tradeoff between the total throughput of the network and the number of covered users.

Scalability and the highly dynamic topology of Vehicular Ad Hoc Networks (VANETs) are the biggest challenges that slow the roll-out of such a promising technology. Adopting an effective VANET clustering algorithm can tackle these issues in addition to benefiting routing, security and media access management. In this paper, we propose a general-purpose resilient double-head clustering (DHC) algorithm for VANET. Our proposed approach is a mobility-based clustering algorithm that exploits the most relevant mobility metrics such as vehicle speed, position, and direction, in addition to other metrics related to the communication link quality such as the link expiration time (LET) and the signal-to-noise ratio (SNR). The proposed algorithm has enhanced performance and stability features, especially during the cluster maintenance phase, through a set of procedures developed to achieve these objectives. An extensive evaluation methodology is followed to validate DHC and compare its performance with another algorithm using different existing and newly proposed evaluation metrics. These metrics are analyzed under various mobility scenarios, vehicle densities, and radio channel models such as log-normal shadowing and two-ray ground loss with and without Nakagami-m fading model. The proposed algorithm DHC has proven its ability to be more stable and efficient under different simulation scenarios.