Ibrahim Radwan

Deep learning has evolved from early perceptron models to modern foundation models through a series of breakthroughs that addressed fundamental limitations in representation learning, optimization, computational efficiency, and scalability. While numerous surveys review specific architectures, learning paradigms, or application domains, few examine the field from a historical and evolutionary perspective. This paper traces the evolution of deep learning by identifying the key discoveries that shaped its development, the bottlenecks that motivated each advance, and the innovations that enabled subsequent progress. Without an understanding of the historical motivations behind major breakthroughs, researchers may inadvertently revisit previously resolved challenges or overlook design principles that have shaped modern deep learning architectures. Understanding why particular architectures emerged and how they addressed existing limitations can help researchers avoid revisiting previously solved problems and make more informed design decisions for future models. Beginning with the origins of artificial neural networks and the introduction of backpropagation, we examine the resurgence of deep learning driven by large-scale datasets, GPU computing, and architectural innovations, followed by developments in convolutional, recurrent, attention-based, graph, generative, and foundation models. Rather than providing an exhaustive review, this paper focuses on the seminal methods that established new research directions and highlights representative applications in which these advances have been successfully adopted. By connecting major breakthroughs with the challenges they addressed, this survey equips new researchers with a principled understanding of deep learning’s evolution and a foundation for developing novel approaches to emerging problems.

The sustainability of low-power mobile sensors is severely challenged by their limited battery capacity, and while simultaneous wireless information and power transfer (SWIPT) is a promising solution, its efficiency suffers dramatically under the uncertainty inherent to mobile three-dimensional (3D) aerial-to-ground environments. This work addresses the critical need for robust and efficient SWIPT under dynamic uncertainty by proposing a novel sensing-assisted SWIPT framework based on a unique hybrid learning algorithm. Our approach first formulates a two-layer optimization problem that rigorously couples a sensing layer, characterized by the Posterior Cram´er-Rao Bound (PCRB), with a SWIPT resource allocation layer. For the sensing layer, the core novelty is a learning-based Kalman Filtering (KF) estimator that merges the interpretative stability of model-based filtering with the adaptive power of neural networks to learn complex, nonlinear mobility patterns. We then prove that minimizing the estimator’s unsupervised loss is mathematically equivalent to minimizing the PCRB, ensuring convergence to optimal sensing without ground-truth supervision. This high-fidelity state information drives a decision-making learning model that adaptively optimizes beamforming, transmit power, and power splitting for the SWIPT resource allocation layer, forming a closed-loop hybrid learning system that continuously reinforces sensing and SWIPT performance. Extensive simulations demonstrate that our framework significantly outperforms benchmark methods in sensing accuracy, communication rate, and energy harvesting, validating its effectiveness in dynamic mobile environments.

The rapid adoption of micromobility solutions, particularly two-wheeled vehicles like e-scooters and e-bikes, has created an urgent need for reliable autonomous riding (AR) technologies. While autonomous driving (AD) systems have matured significantly, AR presents unique challenges due to the inherent instability of two-wheeled platforms, limited size, limited power, and unpredictable environments, which pose very serious concerns about road users' safety. This review provides a comprehensive analysis of AR systems by systematically examining their core components, perception, planning, and control, through the lens of AD technologies. We identify critical gaps in current AR research, including a lack of comprehensive perception systems for various AR tasks, limited industry and government support for such developments, and insufficient attention from the research community. The review analyses the gaps of AR from the perspective of AD to highlight promising research directions, such as multimodal sensor techniques for lightweight platforms and edge deep learning architectures. By synthesising insights from AD research with the specific requirements of AR, this review aims to accelerate the development of safe, efficient, and scalable autonomous riding systems for future urban mobility.

Mobile edge computing (MEC) servers integrated with multi‐unmanned aerial vehicles (multi‐UAVs) present a new system the multi‐UAV‐assisted MEC system. This system relies on the mobility of the UAVs to reduce the transmission distance between the servers and mobile users, thereby enhancing service quality and minimizing the overall energy consumption. Achieving optimal UAV deployment and precise task scheduling is crucial for improved coverage and service quality in this system. This problem is framed as a nonconvex optimization problem known as joint task scheduling and deployment optimization. Recently, an optimization technique based on a dual‐layer framework: Upper layer optimization and lower layer optimization have been proposed to tackle this problem and achieved superior performance compared to the alternative methods. In this framework, the lower layer was responsible for task scheduling optimization, while the upper layer was designed to assist in optimizing UAV deployment and thus achieving improved coverage and enhanced task scheduling for mobile users, thereby minimizing the total energy consumption. However, further refinement of upper layer optimization is needed to improve the deployment process. In this study, the upper layer undergoes enhancement through key modifications: First, random selection of the solutions is replaced with sequential selection to maintain the unique characteristics of each individual throughout the optimization process, fostering both exploration and exploitation. Second, a selection of recently reported metaheuristic algorithms, such as spider wasp optimizer (SWO), generalized normal distribution optimization (GNDO), and gradient‐based optimizer (GBO), are adapted to optimize UAV deployments. Both improved upper layer and lower layer optimization led to the development of novel, more effective optimization approaches, including IToGBOTaS, IToGNDOTaS, and IToSWOTaS. These techniques are evaluated using nine instances with a variety of mobile tasks ranging from 100 to 900 to test their stability and then compared to different optimization techniques to measure their effectiveness. This comparison is based on several statistical information to determine the superiority and difference between their outcomes. The results reveal that IToGBOTaS and IToSWOTaS exhibit slightly superior performance compared to all other algorithms, showcasing their competitiveness and efficacy in addressing the optimization challenges of the multi‐UAV‐assisted MEC system.

Wave energy is a promising source of clean, sustainable, and carbon‐neutral energy. Many nations have developed wave energy deployment policies and maps based on recommendations from relevant organisations. However, there is a concern about predicting wave energy potential in a way that reflects each country’s unique characteristics. Selecting sustainable wave energy conversion technology (WECT) in resource‐rich sites is a crucial research direction. This study presents an all‐encompassing approach that allows consultants to articulate their opinions on the criteria and indicators influencing the selection of sustainable wave energy converters and potential sites for wave energy plants, as demonstrated by a case study in Egypt. To achieve optimal and sustainable WECT, it is essential to consider various sustainability criteria, including economic, environmental, social, technical, reliability, and availability factors, along with their subcriteria. This study proposes a multicriteria decision‐making (MCDM) framework within a spherical fuzzy context, addressing multiple dimensions. It employs the SF‐criteria importance through intercriteria correlation (SF‐CRITIC) technique to evaluate the primary criteria influencing the selection of wave energy converters and to assess the dimensions relevant to identifying suitable sites for wave energy plants. The SF‐multiattribute ideal–real comparative analysis (SF‐MAIRCA) evaluates selected wave energy converters and potential sites. The findings highlight that the technological criterion is most effective for determining potential converters and sites. The Pelamis converter emerges as the most suitable for installation. Additionally, sensitivity and comparison analyses affirm the stability and effectiveness of the proposed methodology and its results.

Detecting deceptive behaviour for surveillance and border protection is critical for a country’s security. With the advancement of technology in relation to sensors and artificial intelligence, recognising deceptive behaviour could be performed automatically. Following the success of affective computing in emotion recognition from verbal and nonverbal cues, we aim to apply a similar concept for deception detection. Recognising deceptive behaviour has been attempted; however, only a few studies have analysed this behaviour from gait and body movement. This research involves a multimodal approach for deception detection from gait, where we fuse features extracted from body movement behaviours from a video signal, acoustic features from walking steps from an audio signal, and the dynamics of walking movement using an accelerometer sensor. Using the video recording of walking from the Whodunnit deception dataset, which contains 49 subjects performing scenarios that elicit deceptive behaviour, we conduct multimodal two-category (guilty/not guilty) subject-independent classification. The classification results obtained reached an accuracy of up to 88% through feature fusion, with an average of 60% from both single and multimodal signals. Analysing body movement using single modality showed that the visual signal had the highest performance followed by the accelerometer and acoustic signals. Several fusion techniques were explored, including early, late, and hybrid fusion, where hybrid fusion not only achieved the highest classification results, but also increased the confidence of the results. Moreover, using a systematic framework for selecting the most distinguishing features of guilty gait behaviour, we were able to interpret the performance of our models. From these baseline results, we can conclude that pattern recognition techniques could help in characterising deceptive behaviour, where future work will focus on exploring the tuning and enhancement of the results and techniques.

Purpose: This study addresses the lack of objective player-based metrics in men's rugby league by introducing a comprehensive set of novel performance metrics designed to quantify a player's overall contribution to team success. Methods: Player match performance data were captured by Stats Perform for every National Rugby League season from 2018 until 2022; a total of five seasons. The dataset was divided into offensive and defensive variables and further split according to player position. Five machine learning algorithms (Principal Component Regression, Lasso Regression, Random Forest, Regression Tree, and Extreme Gradient Boost) were considered in the analysis, which ultimately generated Wins Created and Losses Created for offensive and defensive performance, respectively. These two metrics were combined to create a final metric of Net Wins Added. The validity of these player performance metrics against traditional objective and subjective measures of performance in rugby league were evaluated. Results: The metrics correctly predicted the winner of 80.9% of matches, as well as predicting the number of team wins per season with an RMSE of 1.9. The metrics displayed moderate agreement (Gwet AC1 = 0.505) when predicting team of the year award recipients. When predicting State of Origin selection, the metrics displayed moderate agreement for New South Wales (0.450) and substantial agreement for Queensland (0.652). Conclusion: The development and validation of these objective player performance metrics represent significant potential to enhance talent evaluation and player recruitment.