Journal of King Saud University-Computer and Information Sciences最新文献

This study explores X’s (formerly Twitter’s) capacity to serve as a real-time barometer of public sentiment, contextualized within the transformative reforms of Saudi Arabia during 2016–2017. The objective was to decipher the populace’s response to these significant national changes by analyzing approximately 200 million tweets in native Arabic dialects, thereby aiming for an authentic portrayal of local sentiment. Our methodology entailed a dual-phase analysis: initial tweet examination to discern prevalent social behaviors, followed by stance detection to classify tweets according to their support, neutrality, or opposition to the divisive issues at hand. For sentiment extraction, we employed a sophisticated feature vector, integrating the $k$ most frequent words and stems. A comprehensive evaluation of various classifiers was conducted, including Support Vector Machine and several variants of $K$-nearest neighbors (K-NN), with a particular emphasis on their applicability to our dataset. Notably, the 9-NN classifier, and more specifically, the weighted K-NN approach, demonstrated remarkable performance, achieving an $F$-score of 72.45%. These insights not only shed light on the public’s reception to the Saudi reforms but also position Twitter as a viable, real-time alternative to traditional survey methods for capturing the nuances of public opinion, thereby offering valuable perspectives for policy formulation.

One of the crucial pre-processing stages in data mining and machine learning is feature selection, which is used to choose a subset of representative characteristics and decrease dimensions. By eliminating unnecessary and redundant features, feature selection can improve machine learning tasks’ accuracy. This work presents a novel multi-label classification (MLC) model utilizing a combination of stack regression (RR) and original label space transformation (IPLST) called RR-IPLST (original label space transformation-ridge regression). A novel embedded technique is implemented, utilizing competitive crowding optimizer (CSO) for multi-label feature selection. Particles are first created using this procedure, after which they are split into two equal groups and compete in pairs. The winners advance to the next iteration, while the losers pick up tips from the victors. At the conclusion of each iteration, the objective function for every particle is determined. A local search technique inspired by the gradient descent algorithm is used to find the local structure of the data, and half of the initial population is produced by the similarity between features and labels in order to boost the convergence rate. Ultimately, feature selection is carried out depending on the best particle. Six popular and sophisticated multi-label feature selection techniques are evaluated to see how well the suggested approach performs. According to the simulation results, the application of the suggested solution performs better than comparable techniques in terms of stability, accuracy, precision, convergence, error measurement, and other criteria that have been examined on various data sets. In 93.35% of cases, the test results demonstrate superiority over traditional algorithms.

The Internet of Things (IoT) provides a major contribution to the innovation of smart manufacturing and industrial automation. Due to IoT, network devices and intelligent machines exchange information through different types of Internet connection and processes are predominantly automated. This reduces significantly the need for more human intervention and supports high performance. Nevertheless, the utilization of IoT in industrial automation called Industrial IoT (IIoT) has several issues, including the management of applications and IIoT devices. Moreover, heterogeneous networks and tremendous devices deployed in the IIoT environment require flexible configuration and reconfiguration according to the change for ensuring dynamic performance. We argue that Software-Defined Networking (SDN) is one of the technologies that can be used to solve some of the previously mentioned issues. In this paper, we propose a survey for the implementation of SDN solutions in IIoT and discuss the pros and cons brought about by this synergy named “SDN-IIoT”. We explore the current articles on SDN-IIoT by considering different crucial domains such as flow installation techniques, fault tolerance, traffic routing optimization, resource management, energy efficiency, real-time, and network security. Furthermore, we analyze Artificial Intelligence (AI)/Machine Learning (ML) tasks to improve the performance of SDN-IIoT and the deployment of different technologies like Network Function Virtualization (NFV) and Time-Sensitive Networking (TSN) in SDN-IIoT. After observing the limitations of existing SDN-IIoT architectures, we propose an improved candidate architecture for SDN-IIoT based on a hierarchical distributed control plane. The new SDN-IIoT architecture contains AI, Industrial Backhaul Network (IBN), Dynamic Hash Table (DHT), AdaptFlow protocol, and edge/cloud storages. This paper selects the five most used SDN controllers by the literature review and identifies the features of each SDN controller. In the end, we provide open challenges and future research orientations in SDN-IIoT. We hope that this paper will be helpful for engineers, organizations, and researchers on the innovation of IIoT and SDN technologies.

Mobile data offloading is a highly promising approach in mobile networks that tackles network congestion at Base Stations (BSs) and greatly improves both the Quality of Service (QoS) and Quality of Experience (QoE) for users. It presents significant business opportunities for operators, particularly in light of the exponential growth in mobile data traffic and the ongoing digital transformation. To effectively uphold the desired levels of QoS and QoE in the elevation of escalating digitalization and the unprecedented surge in data traffic, this paper presents offloading through a diverse range of technologies such as data offloading through Small Cell Networks (SCNs), Wi-Fi offloading, Device-to-Device (D2D) offloading, and data offloading through Vehicular Ad-Hoc Networks (VANETs). The SCNs and Wi-Fi offloading involve migrating data traffic to the alternative infrastructure i.e. the small BS and the Wi-Fi Access Points (AP), respectively while D2D focuses on transferring data through the device without transversing the BSs. VANETs is the process of offloading data in vehicular scenarios that consist of Vehicle-to-Vehicle (V2V), Vehicle-to-Infrastructure (V2I), and Vehicle-to-Everything (V2X). Additionally, mobile data offloading from cellular BS is categorized into four main factors: energy consumption or energy awareness, economic considerations, user satisfaction, and network congestion. These factors play a crucial role in the ongoing adoption and implementation of mobile data offloading strategies. Different technologies utilize diverse techniques to tackle the challenge of offloading, aligning with their specific research objectives. This paper delves into the challenges and outlines future research directions in the field of mobile traffic offloading.

Deep learning (DL) is one of the most promising technological developments emerging in the fourth industrial revolution era for businesses to improve processes, increase efficiency, and reduce errors. Accordingly, hierarchical learning software selection is one of the most critical decision-making problems in integrating neural network applications into business models. However, selecting appropriate reinforcement learning software for integrating deep learning applications into enterprises’ business models takes much work for decision-makers. There are several reasons for this: first, practitioners’ limited knowledge and experience of DL makes it difficult for decision-makers to adapt this technology into their enterprises’ business model and significantly increases complex uncertainties. Secondly, according to the authors’ knowledge, no study in the literature addresses deep structured learning solutions with the help of MCDM approaches. Consequently, making inferences concerning criteria that should be considered in an evaluation process is impossible by considering the studies in the relevant literature. Considering these gaps, this study presents a novel decision-making approach developed by the authors. It involves the combination of two new decision-making approaches, MAXC (MAXimum of Criterion) and TODIFFA (the total differential of alternative), which were developed to solve current decision-making problems. When the most important advantages of this model are considered, it associates objective and subjective approaches and eliminates some critical limitations of these methodologies. Besides, it has an easily followable algorithm without the need for advanced mathematical knowledge for practitioners and provides highly stable and reliable results in solving complex decision-making problems. Another novelty of the study is that the criteria are determined with a long-term negotiation process that is part of comprehensive fieldwork with specialists. When the conclusions obtained using this model are briefly reviewed, the C2 “Data Availability and Quality” criterion is the most influential in selecting deep learning software. The C7 “Time Constraints” criterion follows the most influential factor. Remarkably, prior research has overlooked the correlation between the performance of Deep Learning (DL) platforms and the quality and accessibility of data. The findings of this study underscore the necessity for DL platform developers to devise solutions to enable DL platforms to operate effectively, notwithstanding the availability of clean, high-quality, and adequate data. Finally, the robustness check carried out to test the validity of the proposed model confirms the accuracy and robustness of the results obtained by implementing the suggested model.

With the advancements of IoT and blockchain, a novel era has emerged in the domain of smart building systems. At the same time, it also brings some problems and challenges. Most traditional solutions typically utilize the fully-replicated storage strategy that results in high storage costs, while recent solutions like coded blockchain may compromise query efficiency. Moreover, traditional reputation-based consensus schemes do not consider dynamic situations, limiting scalability. To handle these problems, we propose a novel hierarchical message aggregation scheme and a classified storage method under Reed–Solomon (RS) coding to minimize storage overhead while ensuring data recoverability and query performance. Additionally, we introduce a dynamic incentive reputation consensus mechanism to tackle scalability challenges such as preventing node monopolies, promoting new node integration, and enhancing fault tolerance. Through theoretical analysis and experimental simulation, the proposed scheme demonstrates a high degree of decentralization and scalability. Our scheme achieves a 20% reduction in the Gini coefficient compared to other approaches. Furthermore, our scheme can save $\frac{1}{9}$ of storage overhead compared to traditional solutions while maintaining high query performance.

Serverless computing is a new concept as cloud computing, which dynamically manages the networks and is applied in Serverless Wireless Sensor Networks (SWSN) to help the networks. These networks are becoming famous for monitoring various physical and environmental factors. Serverless computing also facilitates the networks by offering an extensive range of applications. Different applications have been designed for monitoring purposes where the sensor nodes sense the data and transmit it to the base station through single or multi-hop routing. However, existing routing protocols cannot manage the sensor nodes’ energy issues because of the complex routing processes and depleted their power before their time. Because of these limitations, the nodes close to BS continuously rely on the network for data forwarding. As a result, these nodes cause energy consumption and lead to a useless state. This paper proposes a serverless architecture and designs an Enhanced Centroid-based Energy Efficient Clustering (ECEEC) protocol for SWSN networks. The proposed serverless architecture provides automated scalability, cost-effective services, and stateless execution. In addition, the proposed protocol offers the cluster head selection and its rotation to maximize the energy efficiency in the network. Furthermore, gateway nodes are chosen in every cluster to overcome the load on the cluster head. Simulation results indicated the excellent performance of the proposed protocol as compared to the existing routing protocols concerning network lifetime and energy consumption. The proposed protocol shows better reliability with nodes failing at 650 rounds compared to 600 rounds, especially with 5 % and 10 % Cluster Heads. The proposed protocol exhibits superior energy efficiency consumption of SNs under varying CH percentages, indicating the protocol’s consistent performance across different scenarios.

Data aggregation involves the integration of relevant data generated across platforms and devices, leveraging the potential value of sensory data. However, in addition to security and efficiency, which are the basic requirements for data aggregation involving private data, how to achieve fault tolerance and interference of aggregation in real computing networks is imminent and is the main contribution of this paper. In this paper, we propose a secure aggregation framework involving multiple servers based on coding theory, which is not only robust to clients dropping out and tolerant to partial server withdrawal but also resistant to malicious computation by servers and forgery attacks by adversaries. In particular, the proposed protocol employs the Chinese Residual Theorem (CRT) to encode private data and constructs Lagrange interpolation polynomials to perform aggregation, which achieves lightweight privacy preservation while achieving robust, verifiable and secure aggregation goals.

RSA stands as a widely adopted method within asymmetric cryptography, commonly applied for digital signature validation and message encryption. The security of RSA relies on the challenge of integer factorization, a problem considered either computationally infeasible or highly intricate, especially when dealing with sufficiently large security parameters. Effective exploits of the integer factorization problem in RSA can allow an adversary to assume the identity of the key holder and decrypt such confidential messages. The keys employed in secure hardware are particularly significant due to the typically greater value of the information they safeguard, such as in the context of securing payment transactions. In general, RSA faces various attacks exploiting weaknesses in its key equations. This paper introduces a new vulnerability that enables the concurrent factorization of multiple RSA moduli. By working with pairs $(N_i,e_i)$ and a fixed value $y$ satisfying the Diophantine equation $e_i{x}_i^2-y^2\varphi \left(N_i\right)=z_i$, we successfully factorized these moduli simultaneously using the lattice basis reduction technique. Notably, our research expands the scope of RSA decryption exponents considered as insecure.

Flying ad hoc networks (FANETs) belong to the family of mobile ad hoc networks (MANETs). They have gained high popularity due to their extensive applications in various industries such as emergency management, military missions, and supervision. However, these networks face important challenges in guaranteeing reliable data transmission because of their dynamic nature and lack of infrastructure. In this paper, a new version of the greedy perimeter stateless routing scheme called GPSR+AODV is proposed in FANET. It combines two routing schemes, namely GPSR and AODV, and is a family member of geographic routing methods. In GPSR+AODV, each UAV consists of a certain hello broadcast period that is adjusted based on the prediction of its spatial coordinates in the future. Additionally, GPSR+AODV modifies the greedy forwarding process and restricts the search space for finding the next-hop node by obtaining a refined candidate set, calculated in the cylindrical coordinate system. Then, each UAV in the refined candidate set is evaluated under a fitness function, and the most suitable next-hop node with the maximum fitness is determined. This function is a combination of four criteria, namely relative velocity, energy level, buffer capacity, and distance to destination. When failing in the greedy forwarding process, GPSR+AODV changes the forwarding technique and uses an AODV-based perimeter forwarding technique to select the best next-hop node. Lastly, GPSR+AODV is implemented by the NS2 simulator, and the simulation results show a successful performance in terms of packet delivery rate, throughput, and delay compared to AGGR, AeroRP, and GPSR. However, the routing overhead in the proposed scheme is higher than that in AGGR.