Search

The Arabic language role in actual global affairs entails sophisticated natural language processing techniques, especially in text classification. This paper presents Tasneef as a novel hybrid approach to tackle computational challenges by reducing memory usage and runtime overhead for actual Arabic text classification (ATC). Tasneef integrates distance-based meta-features (DBMFs) representation with word embeddings. This integration is useful because using a single text representation technique can be limiting in capturing the essential range of features necessary for effective classification, especially in complex languages like Arabic. By addressing the intricacies arising from the high dimensionality and sparsity inherent in Term Frequency-Inverse Document Frequency (TF-IDF) representation, the utilization of DBMFs is shown to offer a promising solution. The DBMFs rely on document labels and statistical features to establish meaningful distance relationships between documents, thereby facilitating effective reduction. Furthermore, word embeddings encapsulate semantic attributes. Empirical assessments reveal a significant reduction of two orders of magnitude in both memory usage and runtime. This reduction translates to memory savings ranging from 158x to 361x and runtime reductions from 120x to 524x across three popular datasets; maintaining comparable MicroF1 and MacroF1 values, while notably reducing learning time. Moreover, Tasneef outperforms ten state-of-the-art deep learning models and seven dimension reduction methods in accuracy, with enhancements ranging from 0.3% to 39.6%; and F-Measure, with improvements from 4.6% to 26.8%, across four additional datasets. These findings highlight Tasneef as a promising solution for diverse ATC applications in real-world scenarios, offering concise and rapid classification with reduced computational learning costs.

Autonomous Driving (AD) has evolved significantly since its beginnings in the 1980s, with continuous advancements driven by both industry and academia. Traditional AD systems break down the driving task into smaller modules—such as perception, localization, planning, and control– and optimizes them independently. In contrast, end-to-end models use neural networks to map sensory inputs directly to vehicle controls, optimizing the entire driving process as a single task. Recent advancements in deep learning have driven increased interest in end-to-end models, which is the central focus of this review. In this survey, we discuss how CARLA-based state-of-the-art implementations address various issues encountered in end-to-end autonomous driving through various model inputs, outputs, architectures, and training paradigms. To provide a comprehensive overview, we additionally include a concise summary of these methods in a single large table. Finally, we present evaluations and discussions of the methods, and suggest future avenues to tackle current challenges faced by end-to-end models.

Automatic detection of laryngeal disorders via voice analysis allows for early diagnosis. However, the effectiveness of AI-based detection methods is often limited, mainly due to insufficient training data subject to confidentiality constraints, as well as the wide range of pathologies, which hinders accurate detection. To address these issues, an automatic voice disorder detection (AVDD) system is proposed, employing an innovative AI-based feature extraction approach to improve detection performance. The approach, termed MFCC-CBN, employs Mel-frequency cepstral coefficients (MFCC) with a convolutional bottleneck network (CBN). It also integrates a diverse feature set, such as measurements related to the fundamental frequency (F0) perturbation, features specific to the glottal source, and conventional MFCC features. The proposed approach is validated through comprehensive experiments on the public database of the Príncipe de Asturias University Hospital (HUPA), which contains recordings of sustained vowels. The method is tested using various classifiers, including Support Vector Machine (SVM), Random Forest (RF), and eXtreme Gradient Boosting (XGBoost). The obtained results show that our method provides a high detection rate and maintains stable performance regardless of the classifier used, which reveals its good generalization. A 5-fold cross-validation technique is adopted for the performance evaluation of the AVDD system. The optimal feature configuration surpasses state-of-the-art results, achieving a classification accuracy of 88.79% and an F1-score of 0.88.

The accurate speech recognition of the Holy Quran is crucial for maintaining the traditional recitation styles and pronunciations, which helps in preserving the authenticity of the Quranic teachings and ensuring their accurate transmission across generations. Though the application of freshly developed models to spoken and written Arabic and non-Arabic speech recognition has yielded highly accurate results, research on Holy Quran is still in its early levels. Indeed, speech recognition of the Holy Quran presents several challenges, including language complexity and the absence of a comprehensive dataset. This research aims to improve the accuracy of speech recognition models for the recital of the Holy Quran. A new dataset called comprehensive Quranic dataset version 1 (CQDV1) is created to serves the HQSR field. The dataset is publicly available for use by other researchers and includes recitations of the entire Quran (114 sura, recited by 35 reciters), based on Hafs from Asim narrative.The study explores the development of a speech recognition model for the accurate recital of the Holy Quran. The model combines a connectionist temporal classification (CTC)/attention loss function with a Bidirectional Long Short-Term Memory with projections (BLSTMP) architecture and a token-based recurrent neural network language model (RNNLM) using CQDV1 dataset. The results achieved were a token error rate (TER) of 6.4%, a word error rate (WER) of 10.4%, and a sentence error rate (SER) of 55.3% with $\lambda =0.2$ .

In recent years, there has been a significant increase in the development of autonomous vehicles. One critical task for ensuring their safety and dependability, is obstacle avoidance in challenging weather conditions. However, no studies have explored the use of data augmentation to generate training data for Deep learning (DL) models aimed at navigating obstacles in extreme weather conditions. This study makes a substantial contribution to the field of autonomous vehicle obstacle avoidance by introducing an innovative approach that utilizes a Generative Adversarial Network (GAN) model for data augmentation, with the objective of enhancing the accuracy of DL models. The use of a GAN model to generate a training dataset and integrate images depicting challenging weather conditions has been pivotal in enhancing the accuracy of the DL models. The extensive training dataset, consisting of 64,336 images, was created using three cameras installed in VSim-AV, an autonomous vehicle simulator, thereby ensuring a diverse and comprehensive dataset for training purposes. Three DL models (ResNet50, ResNet101, and VGG16 transfer learning) were trained on this dataset both before and after applying the data augmentation techniques. The performance of the augmented models was evaluated in a real-time environment using the autonomous mode of the VSim-AV simulator. The testing phase resulted in the highest accuracy rate of 97.2% when employing Resnet101 following the implementation of GAN. It was observed that the autonomous car could navigate without any collisions, showcasing a remarkable reaction time of 0.105 seconds, thus affirming the effectiveness of the approach. The comparison between the original and augmented datasets demonstrate the originality and value of this study, showcasing its significant contribution to the advancement of autonomous vehicle obstacle avoidance technology. This paper makes significant advances to the field of autonomous vehicle navigation by exploiting Generative Adversarial Networks (GANs) to improve obstacle avoidance capabilities in severe weather conditions, hence increasing safety and dependability in real-world applications.

Vehicular visible light communication (VVLC) has emerged as a promising field of research, garnering considerable attention from scientists and researchers. VVLC offers a potential solution to enable connectivity and communication between travelling vehicles along the road by using their existing headlights (HLs) and taillights (TLs) as wireless transmitters and integrating photodetectors (PDs) within the car front or car-back as wireless receivers. However, VVLC encounters more challenges than indoor VLC, particularly in vehicle-to-vehicle (V2V) communication, where vehicle mobility disrupts the establishment of direct communication links. To address this, we propose a multi-hop relay system wherein intermediate vehicles act as wireless relays to maintain a line-of-sight (LoS) link. In this paper, we investigate the performance of a bidirectional multi-hop relay V2V-VLC system that operates in both the forward and backward directions. Based on realistic ray tracing channel models, we derive a closed-form expression for the full bidirectional communication range. We also analyze how the transceiver’s parameters and the number of relays affect the system performance. Our results show that the proposed bidirectional multi-hop relay system can extend the direct transmission range by more than 19 m with only a hop relay.

Since the outbreak of the COVID-19 crisis, the transition to remote education presented several challenges to educational institutions. Unlike face-to-face classes where educators can modify and keep track of the lessons and content according to the students’ observed emotions and participation, such activities are difficult to complete in online learning environments. To address this issue, we propose here a novel and comprehensive framework that leverages advanced computer vision and analysis techniques to detect students’ emotions during online learning and assess their state of mind regarding the taught content. Our framework is composed of three modules. The first module uses a novel lightweight machine learning method, called convolutional neural network-random forest (CNN-RF), to efficiently detect the students’ basic emotions, e.g., sad, happy, etc., during the online course. Our approach surpasses existing benchmarks in terms of accuracy (over 71%) on the FER-2013 dataset, while being less complex (i.e., using a smaller number of parameters). The second module consists of mapping the basic emotions to an education-aware state of mind, e.g., interest, boredom, distraction, etc. Unlike the few works that proposed simplistic mapping, we propose here a Plutchik wheel’s inspired mapping system, which is more precise and reflects better the relationship between combinations of basic emotions and the resulting education-aware state of mind. Thus, our understanding of the students’ cognitive and affective experiences during online learning can be enhanced. The third module is a visualization dashboard that offers clear and intuitive real-time representations of basic emotions and states of mind. This tool provides educators with invaluable insights into students’ emotional dynamics, enabling them to identify learning difficulties with high precision and make informed recommendations for improvements in course content and online teaching methods. In summary, the proposed framework presents a novel and powerful tool that addresses the challenges related to online learning. By accurately detecting the students’ emotions, assessing their states of mind, and providing real-time visualization, our approach represents a significant advancement toward the optimization of online education, which is critically needed in rural and remote areas of the globe.

Satellite images play a crucial role in ecology as they provide rich information about the Earth’s surface. The deep analysis of satellite images presents a vast challenge due to the sheer size of the data that needs to be managed. Sophisticated storage solutions are required to handle the ever-increasing velocity of incoming data and to deal with potential latency or data loss. Storage balancing ensures efficient allocation and distribution of storage capacity across a system, which involves monitoring, analyzing, and adjusting how data is stored to optimize performance, minimize downtime, and maximize cost savings. Additionally, storage balancing helps avoid data bottlenecks by automatically redistributing data across multiple resources. While many solutions have been proposed to balance storage, no polynomial solution is available. This paper addresses the issue of transmitting a considerable amount of satellite images across the network to various storage supports. The challenge is to find an effective way to schedule these satellite images to the storage supports that lead to equitable results in distribution. Many heuristics and enhancement methods are proposed to solve this problem. The effectiveness of the algorithms presented in this paper was tested and analyzed through extensive testing. The experimental study shows that the proposed heuristics outperform those developed in the literature. Indeed, in 73.8% of cases, the best-proposed algorithm, the best iterative-selection satellite images algorithm ( $BIS$ ), reached the best solution compared to the best algorithm in the literature and the other proposed algorithms. The $BIS$ algorithm obtained an average gap of 0.147 in an average running time of 1.0654 s.

In this paper, a high-gain circularly polarized (CP) hexagonal antenna array is proposed for RF energy-harvesting applications. The hexagonal antenna array is intended to operate at the frequency of 5.8 GHz. It is composed of 6 multilayer substrate CP antennas excited by an X-shaped aperture-coupling feed structure. A frequency selective surface (FSS) was added to further improve the gain, resulting in a maximum gain of 12.7 dBi per element. The main advantage of the proposed hexagonal antenna array is the ability to cover 360 degrees in the azimuth plane with a high gain in all directions without the use of any additional circuitry, allowing the effective absorption of ambient RF energy. A prototype was fabricated and measured, and a good agreement with the simulation results is achieved. In addition, a rectifier is used to convert RF energy absorbed by the antenna into DC energy at the frequency of 5.8 GHz. The measured RF-to-DC conversion efficiency of 44.5% and a DC output voltage of 423 mV at −10 dBm are observed. The performance of the rectenna array with one and six rectifiers has been demonstrated. With the use of a DC combiner, the total RF to DC efficiency of the array is 67.75%, with a DC output voltage of 1.115 V from −10 dBm has been recorded. Due to the immunity to misalignment of the CP antenna, the proposed rectenna array is very suitable for wireless power transfer (WPT).

The concept of smart cities is to enhance the life quality of residents and provide efficient services by integrating advanced information and communication technologies, autonomous robots, Internet of Things (IoT) devices, etc. Unmanned Aerial Vehicles (UAVs) are a class of autonomous flying mobile robots that bring a lot of benefits to smart cities due to their mobility, accessibility, autonomy, and many other advantages. Their integration allows for accomplishing hard and complex tasks that humans or other entities are not able to complete. In most applications, multiple connected UAVs are required to build a network under which missions are completed and tasks are shared. This network can be established by finding the optimal UAV placement that meets some requirements such as user coverage, UAV connectivity, energy, and load distribution. In this paper, we present a hybrid algorithm, called IMRFO-TS, based on the hybridization of Improved Manta Ray Foraging Optimization (IMRFO) with the Tabu Search (TS) algorithm for solving the UAV placement problem in a smart city. First, the tangential control strategy is incorporated into the original MRFO algorithm to enhance its convergence speed and explore the search space effectively. Second, The TS algorithm is hybridized with the IMRFO algorithm to increase the exploitation capability of IMRFO and improve the best solution (placement quality) obtained after each iteration. The performance of the proposed IMRFO-TS algorithm is validated using 52 benchmarks considering the fitness value, coverage, connectivity, energy consumption, and load distribution parameters. Compared to eight well-known optimization meta-heuristics such as the original MRFO, TS algorithm, Bat Algorithm (BA), Firefly Algorithm (FA), Grey Wolf Optimization (GWO), Sine Cosine Algorithm (SCA), Whale Optimization Algorithm (WOA), and Reptile Search Algorithm (RSA), the results of the experiments revealed the significant superiority of the proposed IMRFO-TS algorithm by obtaining promising solutions (optimal positions of UAVs) in the majority of the cases.

Vehicular Visible light communication (VLC) technology has recently attracted much interest from researchers and scientists. This technology enables connectivity between vehicles and infrastructures along the road by using vehicles’ headlights and taillights as wireless transmitters. The reliability of vehicle-to-vehicle (V2V) VLC systems is affected by several factors, such as car mobility, optics system design, and visibility conditions, where the first two have the most impact on the VLC system performance. This paper, therefore, focuses on the relative positions of the cars and the design of the optics, especially on the receiving end, which has been proposed with the use of a polar detector instead of the rectangular detectors commonly used in the literature. We investigate the achievable gain compared to the conventional detector for different vehicle locations, utilizing a professional optical system design and ray tracing approach. Then, to improve the performance, we introduce the utilization of an imaging receiver by integrating the polar detector with different optical commercial lens combinations, such as Fresnel and Aspherical lenses. To further improve the V2V system performance, we propose a novel optical lens combination design by integrating double-convex lens with half-Plano-concave lens, which allows the correction of more optical aberrations, such as chromatic and spherical aberration. Utilizing the non-sequential ray tracing tools, we designed these VLC systems and perform a realistic channel modeling study considering the typical 3D CAD models of vehicles and roads as well as the possibility of horizontal and vertical movement between the vehicles. Based on the channel impulse responses (CIRs) obtained from the ray tracing simulations, we analyzed the performance of V2V VLC systems with all lens combinations at different vehicle positions on the road. We further investigated the impact of different system parameters on the overall V2V system performance, such as receiver diameter and bandwidth. The obtained results demonstrated that with a carefully chosen system and lens parameters, the proposed system design of lens combination provides an enhancement of up to 7 dB in total received power compared to the case without a lens. Our results also revealed that the proposed system design outperforms the benchmark ones for all lateral displacements and longitudinal distances.

Mobility is a critical element for understanding human contact networks. In many studies, the researchers use random processes to model human mobility. However, people do not move randomly in their environment. Their interactions do not depend only on spatial constraints but on their temporal, social, economic, and cultural activities. The topological structure of the physical and/or proximity contact networks depends, therefore, entirely on the mobility patterns. This paper performs an extensive comparative analysis of real-world temporal contact networks and synthetic networks based on influential mobility models. Results show that the various topological properties of most of the synthetic datasets depart from those observed in real-world contact networks because the randomness of some mobility parameters tends to move away from human contact properties. However, it appears that data generated using Spatio-Temporal Parametric Stepping (STEPS) mobility model reveals similarities with real temporal contact networks such as heavy-tailed distribution of contact duration, frequency of pairs of contacts, and the bursty phenomenon. These results pave the way for further improvement of mobility models to generate meaningful artificial contact networks.

Massive Multiple Input Multiple Output (MIMO) system has gathered lately a huge interest from researchers and it has been known as a backbone technology for the 5th generation because it can greatly improve the capacity of wireless communication and it can potentially provide energy efficiency and security. Before ensuring the full advantages, massive MIMO system has to overcome many challenges. One of them is to accurate an exact estimation of the Channel Impulse response (CIR) between each transmit-receive antenna pair. The other problem arises when implementing such a system in presence of High Power Amplifiers (HPA) which imposes a nonlinear distortion on the transmitted signals. This paper proposes contributions in three key areas. Firstly, we investigate the nonlinear effects of memoryless HPA, which is modeled using Saleh model, by deriving its Bit Error Rate expression (BER) in massive MIMO Orthogonal Frequency Division Multiplexing (OFDM) system. Secondly, we highlight the necessity of providing the accurate channel characteristics by estimating it using Compressive Sensing (CS) techniques. Moreover, we propose also a CS compensation algorithm based on Orthogonal Matching Pursuit (OMP) to mitigate the nonlinear distortion in the receiver. The proposed CS-based compensation technique has been compared to the Neural Network (NN) pre and post compensation technique and it has shown a good performance not only in terms of BER but also in terms of complexity.

Due to the ever-stringent regulatory standards and financial pressure imposed by governments worldwide, public universities are striving to produce and deliver high quality knowledge by leveraging various organizational and technological tools. Despite their prominence and proliferation, research information management systems (RIMS) cover only the research management life-cycle of the institution and thereby presume that the scholars are actively engaged in research and are committed to feeding the system with accurate research data, which may not be the case at public universities. In this paper, we propose to leverage Axiomatic Design and Research Information Systems to support the entire research production life-cycle. The architecture of the proposed system is described in terms of a set of software modules, which may be incorporated into an open-source or a commercial Current Research Information System (CRIS). This will extend the CRIS functionality to cover the research production life-cycle in addition to the research management life-cycle making it well suited for developing research capacity at public universities.

Wireless Mesh Networks (WMNs) have rapid real developments during the last decade due to their simple implementation at low cost, easy network maintenance, and reliable service coverage. Despite these properties, the nodes placement of such networks imposes an important research issue for network operators and influences strongly the WMNs performance. This challenging issue is known to be an NP-hard problem, and solving it using approximate optimization algorithms (i.e. heuristic and meta-heuristic) is essential. This motivates our attempts to present an application of the Coyote Optimization Algorithm (COA) to solve the mesh routers placement problem in WMNs in this work. Experiments are conducted on several scenarios under different settings, taking into account two important metrics such as network connectivity and user coverage. Simulation results demonstrate the effectiveness and merits of COA in finding optimal mesh routers locations when compared to other optimization algorithms such as Firefly Algorithm (FA), Particle Swarm Optimization (PSO), Whale Optimization Algorithm (WOA), Genetic Algorithm (GA), Bat Algorithm (BA), African Vulture Optimization Algorithm (AVOA), Aquila Optimizer (AO), Bald Eagle Search optimization (BES), Coronavirus herd immunity optimizer (CHIO), and Salp Swarm Algorithm (SSA).

The Internet of Things (IoT) is a heterogeneous environment that connects billions of devices. Thus, it is a significantly high-value target for attackers and suffers from several threats, especially impersonation attacks during the session. Moreover, the denial of service attack (DoS) threatens IoT environments, as it affects the availability and energy of communicating devices. Continuous authentication solves session hijacking since it checks user legitimacy during the session. Several continuous authentication schemes were proposed to authenticate users to IoT devices, while few works addressed device-to-device authentication. Therefore, it is essential to authenticate devices because if one device gets compromised, then the whole system is at risk. Continuous authentication between devices differs from user-to-device authentication since it cannot rely on biometrics and passwords. This research proposes a fast and secure device-to-device continuous authentication protocol that relies on devices’ features (token, battery, and location), and mitigates DoS attacks using shadow IDs and emergency keys. Moreover, it takes the sensor movement into account while preserving privacy. To evaluate the robustness and validate the security of the proposed protocol, we conducted informal and formal analyses using Scyther. In addition, we tested its performance to establish computation costs relative to the system counterparts. The results show the protocol is robust against security threats, incurring reasonable computational costs.

Since outdoor events are gradually allowed within the current pandemic situation, a close monitoring of the crowd activity is needed to avoid undesired contact and disease transmission. In this context, unmanned aerial vehicles (UAVs) can be occasionally used to watch these activities, to ensure that health measures are applied, and to trigger alerts when an anomaly is detected. Consequently, we propose in this paper a complete UAV framework for intelligent monitoring of post COVID-19 outdoor activities. Specifically, we propose a three-step approach. In the first, captured images are analyzed using machine learning to detect and locate individuals. The second step consists of a novel coordinates mapping approach to evaluate distances among individuals and cluster them, while the third step provides an energy-efficient and reliable UAV trajectory to further inspect clusters for restrictions violation. Obtained results provide important insights towards the efficient design of the framework: 1) Efficient detection of individuals depends on the angle from which the images were captured, 2) coordinates mapping is very sensitive to estimate errors in individuals’ bounding boxes, and 3) UAV trajectory design algorithm 2-Opt is recommended for practical real-time deployments due to its low-complexity and near-optimal performance.

Grasshopper Optimization Algorithm (GOA) is a recent swarm intelligence algorithm inspired by the foraging and swarming behavior of grasshoppers in nature. The GOA algorithm has been successfully applied to solve various optimization problems in several domains and demonstrated its merits in the literature. This paper proposes a comprehensive review of GOA based on more than 120 scientific articles published by leading publishers: IEEE, Springer, Elsevier, IET, Hindawi, and others. It provides the GOA variants, including multi-objective and hybrid variants. It also discusses the main applications of GOA in various fields such as scheduling, economic dispatch, feature selection, load frequency control, distributed generation, wind energy system, and other engineering problems. Finally, the paper provides some possible future research directions in this area.

Aggregation is a vital behavior when performing complex tasks in most of the swarm systems, such as swarm robotics systems. In this paper, three new aggregation methods, namely the distance-angular, the distance-cosine, and the distance-Minkowski k-nearest neighbor (k-NN) have been introduced. These aggregation methods are mainly built on well-known metrics: the cosine, angular, and Minkowski distance functions, which are used here to compute distances among robots' neighbors. Relying on these methods, each robot identifies its k-nearest neighborhood set that will interact with. Then, in order to achieve the aggregation, the interactions sensing capabilities among the set members are modeled using a virtual viscoelastic mesh. Analysis of the results obtained from the ARGoS simulator shows a significant improvement in the swarm aggregation performance compared to the conventional distance-weighted k-NN aggregation method. Also, the aggregation performance of the methods is reported to be robust to partially faulty robots and accurate under noisy sensors.