The convergence of urban informatics and vehicle intelligence has given rise to smart connected vehicles, which have immense potential as edge computing platforms for various applications. However, harnessing the full efficiency of these platforms presents challenges due to the diverse resource requirements, capabilities, and vehicle types, as well as unpredictable vehicle movements. To address these obstacles, a novel task offloading framework based on digital twin (DT) technology has been proposed for the Internet of Vehicles (IoV). This DT-based framework capitalizes on historical data and workload predictions to optimize the utilization of edge devices. It streamlines the offloading process by enabling tasks to be accepted and processed by the source vehicle without relying on external devices. The proposed system is designed to learn and forecast vehicle mobility patterns and computation waiting times, facilitating efficient allocation of computing resources at edge locations. Consequently, this approach enhances the quality of service by ensuring swift and effective task processing, irrespective of the vehicles’ unpredictable movements. The proposed approach is compared with a deep sequential model based on reinforcement learning, collaborative multiaccess edge computing (MEC), and energy-efficient MEC via reinforcement learning model. Our method demonstrates an improvement in task execution and overall offloading performance compared to these techniques during peak vehicle arrival rates. Likewise, substantial enhancements are observed in other benchmark parameters.

Collaborative Intrusion Detection System (CIDS) protect large networks against distributed attacks. However, a CIDS is vulnerable to insider attacks that decrease the mutual trust among the CIDS nodes. Most existing trust management approaches rely on a central authority, trusted third parties or network peers for managing trust. The current techniques are prone to high false positives and vulnerable to various reputation attacks. For instance, device attestation manages trust among CIDS nodes by verifying the integrity of a node’s hardware and software configuration. However, it lacks real-time monitoring of the dynamic state, limiting its effectiveness against ongoing attacks and malware. Therefore, incorporating the system’s dynamic state in the trust framework is crucial, but it causes false positives requiring corrective mechanisms. To address these challenges, this paper proposes a blockchain-based integrated trust management framework for CIDS, incorporating the device’s genome attestation, the system’s dynamic parameters, and a false positive resilient reputation mechanism. By storing the reputation scores on the blockchain, the framework alleviates the need for a third party for trust management and thus mitigates attacks applicable to reputation-based systems. The paper performs a comprehensive security and performance analysis of the proposed framework to gauge its efficiency and study the effects of a penalty on a node’s reputation during the recovery and rally phases. We also study the impact of false positives on the reputation of a node. The results show that Hyperledger Fabric offers lower transaction latency and low CPU utilization compared to Ethereum Blockchain.

RNA sequence properties prediction is significant for understanding RNA function and its potential applications in medicine and biotechnology. In this study, we developed a novel Gated Recurrent Unit (GRU) deep learning model to predict mRNA vaccine degradation with improved accuracy over traditional machine learning methods and previously reported deep learning approaches. A notable contribution of our approach is the innovative method of feature engineering that accounts for dependencies between nucleotides by shifting the feature values. Our proposed GRU model outperformed XGBoost, Random Forest, and LightGBM models. The GRU Network showed a Mean Columnwise Root Mean Squared Error (MCRMSE) of 0.275 and 0.389 for the public and the private sets, respectively. Despite some limitations, our model provides a strong foundation for future work to refine and expand the capabilities of RNA sequence property prediction. The results of this study have significant implications for RNA research, potentially leading to advancements in understanding RNA function and the development of RNA-targeting therapeutics and diagnostic tools.

Smart vehicles are equipped with onboard computing units designed to run in-vehicle applications. However, due to limited computing power, the onboard units are unable to execute compute-intensive tasks and those that require near real-time processing. Therefore tasks are offloaded to nearby fog/edge devices that have more powerful processors. However, the fog devices are static, placed at fixed locations such as intersections, and have a limited communication range. Therefore, they can only facilitate vehicles in their immediate vicinity and only limited areas of the city can be covered to provide services on demand. In this article, we propose an unmanned aerial vehicle (UAV)-based computing framework design termed Skywalker to provide computing in regions where there are no static fog units thereby extending coverage. Skywalker’s contributions are threefold: 1) it allows for load-aware UAV placement and provisions a swarm of UAVs to fly to areas experiencing a gap in service where the size of the swarm is proportional to the demand; 2) it implements multiple scheduling algorithms that the UAVs swarm employs to divide up the task processing responsibility for individual UAVs within the swarm; and 3) a zone-based delivery mechanism is being proposed to facilitate the return of completed tasks, either through direct delivery or relay-based methods. The choice between these options depends on the distance covered by the requesting vehicle from the UAV swarm. The efficiency of the framework is compared with existing techniques and it is found that it can greatly extend coverage during peak traffic hours while providing low communication delay and consuming minimum energy.

Abstract Social bots are automated social media accounts governed by software and controlled by humans at the backend. Some bots have good purposes, such as automatically posting information about news and even to provide help during emergencies. Nevertheless, bots have also been used for malicious purposes, such as for posting fake news or rumour spreading or manipulating political campaigns. There are existing mechanisms that allow for detection and removal of malicious bots automatically. However, the bot landscape changes as the bot creators use more sophisticated methods to avoid being detected. Therefore, new mechanisms for discerning between legitimate and bot accounts are much needed. Over the past few years, a few review studies contributed to the social media bot detection research by presenting a comprehensive survey on various detection methods including cutting-edge solutions like machine learning (ML)/deep learning (DL) techniques. This paper, to the best of our knowledge, is the first one to only highlight the DL techniques and compare the motivation/effectiveness of these techniques among themselves and over other methods, especially the traditional ML ones. We present here a refined taxonomy of the features used in DL studies and details about the associated pre-processing strategies required to make suitable training data for a DL model. We summarize the gaps addressed by the review papers that mentioned about DL/ML studies to provide future directions in this field. Overall, DL techniques turn out to be computation and time efficient techniques for social bot detection with better or compatible performance as traditional ML techniques.

The rapid evolution in social bots have required efficient solutions to detect them in real-time. In fact, obtaining labeled stream datasets that contains variety of bots is essential for this classification task. Despite that, it is one of the challenging issues for this problem. Accordingly, finding appropriate techniques to label unlabeled data is vital to enhance bot detection. In this paper, we investigate two labeling techniques for semi-supervised learning to evaluate different performances for bot detection. We examine self-training and co-training. Our results show that self-training with maximum confidence outperformed by achieving a score of 0.856 for F1 measure and 0.84 for AUC. Random Forest classifier in both techniques performed better compared to other classifiers. In co-training, using single view approach with random forest classifier using less features achieved slightly better compared to single view with more features. Using multi-view of features in co-training in general achieved similar results for different splits.

In recent times, machine learning and deep learning algorithms have contributed to the advances in audio and speech recognition. Despite the progress, there is limited emphasis on the classification of cantillation audio using deep learning. This paper introduces a dataset containing two labeled styles of cantillation from six reciters. Deep learning architectures including convolutional neural networks (CNN) and deep artificial neural networks (ANN) were used to classify the recitation styles using various spectrogram features. Moreover, the classification of the six reciters was also performed using deep learning. The best performance was achieved using a CNN model and Mel spectrograms resulting in an F1-score of 0.99 on the test set for classifying recitation style and an F1-score of 1.00 on the test set for classifying reciters. The results obtained in this work outperform the existing works in the literature. The paper also discusses the impact of various audio features and deep learning algorithms that apply to audio genre and speaker identification tasks.

Many IT labs require virtualization technology as students need to learn several software tools and operating systems. In an online setting, students sometimes are expected to fill the role of an IT lab architect by installing, configuring, deploying lab tasks on their personal computers, and deciding the virtualization technology needed. This can be intimidating and time-consuming for many students. Further, students often use traditional virtualization technology that is neither needed nor justified costing students significant time, effort, and computing resources. Existing studies discuss virtualization technology appropriateness in the context of industrial applications. This study, however, explores potential virtualization technologies that can be utilized in an academic setting by means of case studies that reflect our experience in transforming the labs of one of our courses. This study assesses virtualization technology suitability in online academic labs in terms of networking, setup time, feasibility, storage, and performance.

Cloud services are widely used to virtualize the management and actuation of the real-world the Internet of Things (IoT). Due to the increasing privacy concerns regarding querying untrusted cloud servers, query anonymity has become a critical issue to all the stakeholders which are related to assessment of the dependability and security of the IoT system. The paper presents our study on the problem of query receiver-anonymity in the cloud-based IoT system, where the trade-off between the offered query-anonymity and the incurred communication is considered. The paper will investigate whether the accepted worst-case communication cost is sufficient to achieve a specific query anonymity or not. By way of extensive theoretical analysis, it shows that the bounds of worst-case communication cost is quadratically increased as the offered level of anonymity is increased, and they are quadratic in the network diameter for the opposite range. Extensive simulation is conducted to verify the analytical assertions.

We address query-anonymity, the property that the destination of a client's query is indistinguishable from other potential destinations, in the context of wireless sensor networks. Prior work has established that this is an important issue, and has also pointed out that there appears to be a natural trade-off between query-anonymity and communication-cost. We explore what we call the limits of this trade-off: what is the communication-cost that is sufficient to achieve a certain query-anonymity, and what is the communication-cost that we must necessarily incur to achieve a certain query-anonymity? Towards this, we point out that two notions of query-anonymity that prior work in this context proposes are not meaningful. We propose an unconditional notion of query-anonymity that we argue has intuitive appeal. We then establish the limits of the trade-off. In particular, we show that in wireless sensor networks whose topology is a square grid and are source-routed, the necessary and sufficient communication-cost for query-anonymity asymptotically smaller than n, where n is the number of nodes in the network, is dependent on n only, and the necessary and sufficient communication-cost for query-anonymity larger than n is dependent on the desired query-anonymity only. We then generalize to topologies that are arbitrary connected undirected graphs, an exercise that involves a novel approach based on a spanning tree for the graph. We show that the diameter of the graph is the inflection point in the trade-off. We discuss extensions of our results to other settings, such as those in which routes are not necessarily shortest-paths. We also validate our analytical insights empirically, via simulations in Tossim, a de facto standard approach for wireless sensor networks. In summary, our work establishes sound and interesting theoretical results for query-anonymity in wireless sensor networks, and validates them empirically.

The advances in the wireless technology, represented by the improved computational capabilities of third generation (3G) and fourth generation (4G) wireless devices and the wider bandwidth wireless networks, make it possible to support a variety of security-sensitive applications such as m-banking and m-commerce. This, however, requires increasingly robust End-to-End security solutions.The contribution of this paper is twofold. First, it presents a design and an implementation of a light weight application-level security solution for handheld devices in wireless LAN. Second, it analyzes the impact of the processing power, time, and memory on the performance of two of the widely known encryption algorithms—RC4 and AES—used by the lightweight handheld devices in the wireless network environment.The work in this paper uses pure Java components to provide end-to-end client authentication and data confidentiality and integrity between wireless J2ME-based clients and J2ME-based servers.