Product design involves the conceptualization and creation of products, where simulation workflows often require dynamic scheduling. Although deep reinforcement learning has shown competitive performance in addressing dynamic scheduling problems, they encounter challenges when dealing with multiple types of dynamic events in workflow scheduling. To this end, the paper introduces a novel meta-reinforcement learning-based dynamic scheduling algorithm (MDSA) to tackle multiple dynamic events. Four types of dynamic events are considered and modeled, including random insertion, loop execution, structural adjustments, and resource uncertainties. The Markov decision process is formulated for the workflow scheduling problem, defining the state, action, reward, and state transition. To capture time-sequential information, a context-aware discretized policy is introduced, and a meta-training algorithm is employed to extract common knowledge across various scheduling scenarios. The effectiveness of the proposed method is demonstrated through a case study in the semiconductor display industry. The simulation environments are constructed using industry-inspired synthetic data, with reference to deployment practices from BOE and task patterns derived from Alibaba cluster traces, to ensure practical relevance while maintaining experimental control. Experimental results indicate that the approach demonstrates strong generalization capabilities, especially in terms of its consistent performance across varying task data distribution and its robustness in adapting to multiple dynamic conditions, thereby enhancing its adaptability in practical applications.

In IoT-enabled smart infrastructure, accurate and real-time road damage detection is crucial for enhancing road safety and optimizing maintenance processes. However, detecting road damage in complex and dynamic environments presents significant challenges, such as varying lighting conditions, diverse damage types, and the need for fast processing to enable real-time decision-making. This study introduces an advanced approach utilizing the YOLOv9s-Fusion model to overcome these challenges. Leveraging the RDD2022 dataset, which comprises 1976 annotated images of road damage from China, we employ comprehensive data preprocessing to create optimal conditions for model training. The YOLOv9s-Fusion model integrates innovative features, including a Transformer-based auxiliary module and enhanced feature extraction layers, specifically designed to detect fine-grained damage patterns accurately. Experimental results demonstrate that the model outperforms existing approaches, achieving notable improvements in mean average precision (mAP) and F1-score. Ablation studies further validate the impact of our modifications, highlighting the model’s robustness in real-time detection across diverse conditions. This IoT-centric approach sets a new standard for autonomous road damage detection, significantly advancing vehicle navigation and smart infrastructure management capabilities.

Critical infrastructure is a collection of physical and cyber systems, which are essentially required to support the day-to-day operations of our daily life. In the critical infrastructure, the computing systems (i.e., Internet of Things (loT) devices) communicate through the Internet. Therefore, most of the time, critical infrastructures are targeted by hackers by launching some cyber-attack, i.e., ransomware. Hence we require some security mechanisms to protect the data and systems of critical infrastructures. This paper proposes a scheme for the detection, analysis and mitigation of ransomware attacks to protect Internet of Things (loT)-enabled critical infrastructure (in short, RADM-ICI). We also practically demonstrated RADM-ICI and computed essential performance parameters, i.e., accuracy and F1-score under different machine learning models. The conducted security analysis of RADM-ICI proved its excellent security for the ransom ware attacks. During the performance comparison of the proposed RADM-ICI and other similar competing existing schemes, it has been observed that the proposed RADM-ICI achieved better accuracy than the other existing competing schemes.

In this paper, we investigate the auxiliary vehicle positioning system and localization method for intelligent transportation systems, as a supplement to the Global Navigation Satellite System which is prone to large positioning deviations and even failures in occluded scenes such as urban canyons and tunnels. The time modulated antenna arrays are first introduced into the positioning system, avoiding mutual coupling between antennas and greatly reducing the hardware cost of the vehicle terminal. The auxiliary positioning framework for the smart vehicle is advocated in conjunction with existing radio frequency signals. To take full advantage of the multiple auxiliary sources around the road net, Doppler shifts embedded into the received signals are unearthed, and a smoothed block sparse reconstruction is developed for directly locating the vehicle, providing significant enhancements of degrees of freedom and the localization accuracy. Additionally, the proposed direct localization method is robust to multichannel gain and phase mismatch in practice, and the array perturbations can be estimated and compensated without any calibration source. Extensive simulation results corroborate that the proposed system and method achieves superior localization accuracy (approximately 0.22 m error at SNR of 10 dB), outperforming its state-of-the-art counterparts.

Vehicular Ad-Hoc Networks (VANETs), as the cru-cial support of Intelligent Transportation Systems (ITS), have received a great attention in recent years. Network traffic prediction is useful for network management and security in VANETs, such as network planning and anomaly detection. Due to the movement of nodes, the traffic flow in VANETs consists of a great number of irregular fluctuations, which is the main challenge for network traffic prediction. This paper proposes a novel algorithm, which combines Deep Q-Learning (DQN) and Generative Adversarial Networks (GAN) for network traffic prediction. We use DQN to carry out network traffic prediction, in which GAN is involved to represent Q-network. Meanwhile, the generative network can increase the number of samples to improve the prediction error. We evaluate the performance of our method by implementing it on two real network traffic data sets. Finally, we compare the two state-of-the-art competing methods with our method.

Intelligent Internet of Things (IIoT) is comprised of various wireless and wired networks for industrial applications, which makes it complex and heterogeneous.The openness of IIoT has led to the intractable problems of network security and management. Many network security and management functions rely on network traffic prediction techniques, such as anomaly detection and predictive network planning. Predicting IIoT network traffic is significantly difficult because its frequently updated topology and diversified services lead to irregular network traffic fluctuations. Motivated by these observations, we proposed a reinforcement learning-based mechanism in this article. We modeled the network traffic prediction problem as a Markov decision process, and then, predicted network traffic by Monte Carlo Q-learning. Furthermore, we addressed the real-time requirement of the proposed mechanism and we proposed a residual-based dictionary learning algorithm to improve the complexity of Monte Carlo Q-learning. Finally, the effectiveness of our mechanism was evaluated using the real network traffic.

Industrial Internet of Things (IIoT), as a common industrial application of Internet of Things, has been widely deployed in recent years. End-to-end network traffic is an essential information for many network security and management functions. This article investigates the issues of IIoT-oriented backbone network traffic prediction. Predicting the traffic of IIoT backbone networks is intractable because of the large number of prior network traffic information, which needs to consume expensive network resources for sampling. Motivated by that, we propose an effective prediction mechanism using multitask learning (MTL), which is a special paradigm of transfer learning. A deep learning architecture constructed by MTL and long short-term memory is designed. This deep architecture takes advantage of link loads as additional information to improve prediction accuracy. We provide a theoretical analysis for the MTL mechanism. The effectiveness is evaluated by implementing our mechanism on real network.

Recent developments of edge computing and content caching in wireless networks enable the Intelligent Transportation System (ITS) to provide high-quality services for vehicles. However, a variety of vehicular applications and time-varying network status make it challenging for ITS to allocate resources efficiently. Artificial intelligence algorithms, owning the cognitive capability for diverse and time-varying features of Internet of Connected Vehicles (IoCVs), enable an intent-based networking for ITS to tackle the above-mentioned challenges. In this paper, we develop an intent-based traffic control system by investigating Deep Reinforcement Learning (DRL) for 5G-envisioned IoCVs, which can dynamically orchestrate edge computing and content caching to improve the profits of Mobile Network Operator (MNO). By jointly analyzing MNO's revenue and users' quality of experience, we define a profit function to calculate the MNO's profits. After that, we formulate a joint optimization problem to maximize MNO's profits, and develop an intelligent traffic control scheme by investigating DRL, which can improve system profits of the MNO and allocate network resources effectively. Experimental results based on real traffic data demonstrate our designed system is efficient and well-performed.

Heterogeneity and convergence are two distinctive features for new generation networks like the Long Term Evolution-Advanced (LTE-A) system. LTE-A is now being deployed and is the way forward for high speed cellular services. LTE-A enhancements the four areas of capacity, coverage, inter-cells coordination, and cost. Improvements in these areas are based on using several technologies. Multiple-Input Multiple Output along with Orthogonal Frequency Division Multiple Access (MIMO/OFDMA) are two of the base technologies that are enablers. In addition, self-organizing and optimization (SON) technologies have been also developed to enable automatic configuration, optimization of network operations, including the 802.21 Media Independent Handover protocol (MIH), which is designed to optimize the vertical handover process. In this paper, we show the importance of inter-technologies and inter-entities cooperation, which can exploit heterogeneity as an enabler to improve the system capacity as well as the quality of service (QoS) for users. We present a new cooperative radio resource allocation scheme for LTE-A network to coordinate better the utilization of network's available radio resources. We adopted the MIH framework, in order to facilitate the exchange between heterogeneous network entities to insure self-configuration of radio resource management parameters. We worked on allocating the right PRB to the right user at the right time. We also analyze some existing solutions and evaluate our proposed scheme using simulation analysis. Simulation results illustrate the performance gains brought by the proposed optimization, especially for average throughput of macro-cell users comparing to their initial performance within two-tier LTE-A network.

Currently, Network Mobility (NEMO) Basic Support protocol enables the attachment of mobile networks to different points in the Internet. It permits session continuity for all nodes in the mobile network to be reachable as the network moves. While this standard is based on the MobileIPv6 standard, it inherits these disadvantages such as security vulnerabilities. To manage the problems of NEMO, many schemes combine it with a network-based approach such as Proxy Mobile IPv6 (PMIPv6). Despite the fact that this latter expedites the real deployment of IP mobility management; it suffers from lack of security. Therefore, we propose an Efficient and Secure Mutual Authentication Mechanism during initial attachment in NEMO-based Proxy Mobile IPv6 Networks called EMA-NEMO based PMIPv6 in order to provide mutual authentication between a mobile router and diameter server during initial attachment of the mobile router to a PMIPv6 domain. Moreover, we evaluate the performance of our scheme using the Automated Validation of Internet Security Protocols and Applications (AVISPA) software which has proved that authentication goals are achieved.

In order to improve all aspects of tourism in any country, it is vital to utilize all available state-of-the art computing and IT technologies and facilities. In this paper, we present our work in this regard as applied to Jordan. Our objective is to build a geographic information system (GIS) model for tourism industries (services) from one side and for officials and conservationist of the historic sites on the other side. This will encourage tourism by providing tourists with all the needed services such as: maps, routes, restaurants, hospitals, Web site with virtual reality models of different monuments and sites. Officials concerned with tourism industries including the private sector, will have an important role in improving and planning the future of their industries using GIS capabilities. Moreover, GIS will enable us to have up-to-date information, recommendation and orientation to tourists to guarantee their security in case of emergency which is a great concern to them. In our GIS creation we included tourism maps scale (1:50,00) and (1:10,000), Ikonos, and spot satellite images to allow maximum information. The GIS covered all cities which have important historical sites including: Amman, Jerash, Madaba, Aqaba and Petra. Existing and newly gathered data were used to enrich our GIS system in order to offer all kind of services to both planners and tourists. The created GIS system will enable the future usage of all modern location-based services. We present here and in depth study for accurate 3D modeling of each historic monument for conservation and registration purposes which was done by our group with international cooperation. Results will be included in the GIS system to enrich it and to allow inside visits to the great ancient history of the sites through a Web site.

Employing Geographic Information Systems (GIS) and Remote Sensing (RS) techniques is a very important issue these days as they aid planners and decision makers to make effective and correct deisions and designs. They allow the enginner to continuously monitor any change any intended plans to secure their success or rectification to meet the requirments.

Three-dimensional modeling is the true simulation of reality, especially if it is relatively accurate. On the other hand, using 3D modeling in GIS environment offers a flexible interactive system for providing the best visual interpretation, planning and decision making process. The 3D models are becoming one of the most efficient technologies for spatial data management and analysis. The objective is to demonstrate the usefulness of three-dimensional modeling, and explore the capabilities of current technologies. Through this, the corresponding required production workflow for building three- dimensional GIS Model of Al-Balqa Applied University (BAU) using new up-to-date digital camera technology and adding true texture mapping will be discussed

Our world is becoming more and more interested in virtual city modeling. This trend coincides with the need to better understand the spatially related problems and issues visually. With the increase types of information that can be linked spatially, and also, the increase size of population and buildings, better city planning to manage the third dimension is becoming a necessity. Meanwhile, 3D virtual city models do not have to be accurate but well representing the reality. Thus the paper is presenting a simple procedure to follow for a study area to show the effectiveness of such approach in 3D modeling for Cadastral, real estate evaluation purposes.

Location based services (LBSs) provide personalized services to the subscribers based on their current position using global navigation satellite system (GNSS), geographic information system (GIS) and wireless communication (WC) technologies. LBS offers modern world the tool for efficient management and continuous control. More and more people involve LBS in their industry and day to day life to better achieve their goals. The increasing demand for commercial LBS has driven scientists to focus on more accurate positioning solutions. It employs accurate, real-time positioning to connect users to points of interest and advises them of the current conditions such as traffic and weather conditions, or provides routing and tracking information using wireless devices. It is important to integrate the mobile computing technology and the GIS technology in order to meet the needs of LBS, which is considered one of the most promising applications of GIS. The location of the caller could be determined by other position determination techniques. these include cell-id, enhanced observed time difference (E-OTD), observed timed difference of arrival (OTDOA), wireless assisted GNSS (A-GNSS) and hybrid technologies (combining A- GNSS with other standard technologies). Cell-ID is used for positioning purposes, but it is not accurate. In the following we will present an introduction on the LBS, its combination with GIS and WC, and some of our recent related work.

This paper presents techniques to verify the identity of computer users using the keystroke dynamics of computer user's login string as characteristic patterns using pattern recognition and neural network techniques. This work is a continuation of our previous work where only interkey times were used as features for identifying computer users. In this work we used the key hold times for classification and then compared the performance with the former interkey time-based technique. Then we use the combined interkey and hold times for the identification process. We applied several neural network and pattern recognition algorithms for verifying computer users as they type their password phrases. It was found that hold times are more effective than interkey times and the best identification performance was achieved by using both time measurements. An identification accuracy of 100% was achieved when the combined hold and intekey time-based approach were considered as features using the fuzzy ARTMAP, radial basis function networks (RBFN), and learning vector quantization (LVQ) neural network paradigms. Other neural network and classical pattern algorithms such as backpropagation with a sigmoid transfer function (BP, Sigm), hybrid sum-of-products (HSOP), sum-of-products (SOP), potential function and Bayes' rule algorithms gave moderate performance.