Weapon Violence Dataset 2.0: A synthetic dataset for violence detection.

In the current era, satisfying the appetite of data hungry models is becoming an increasingly challenging task. This challenge is particularly magnified in research areas characterised by sensitivity, where the quest for genuine data proves to be elusive. The study of violence serves as a poignant example, entailing ethical considerations and compounded by the scarcity of authentic, real-world data that is predominantly accessible only to law enforcement agencies. Existing datasets in this field often resort to using content from movies or open-source video platforms like YouTube, further emphasising the scarcity of authentic data. To address this, our dataset aims to pioneer a new approach by creating the first synthetic virtual dataset for violence detection, named the Weapon Violence Dataset (WVD). The dataset is generated by creating virtual violence scenarios inside the photo-realistic video game namely: Grand Theft Auto-V (GTA-V). This dataset includes carefully selected video clips of person-to-person fights captured from a frontal view, featuring various weapons-both hot and cold across different times of the day. Specifically, WVD contains three categories: Hot violence and Cold violence (representing the violence category) as well as No violence (constituting the control class). The dataset is designed and created in a way that will enable the research community to train deep models on such synthetic data with the ability to increase the data corpus if the needs arise. The dataset is publicly available on Kaggle and comprises normal RGB and optic flow videos.

Progressive Observation of Covid-19 Vaccination Effects on Skin-Cellular Structures by Use of Intelligent Laser Speckle Classification (ILSC) Technique.

The recent pandemic showed that the current global research strategies on vaccine development in an emergency period necessitates more optimized supplementary techniques to observe instant progressive vaccines' subtle effects on human metabolisms to make better and speedy evolutionary health assessments. To fill this gap, we have followed a multi-disciplinary approach exploiting AI, laser-optics, and specific imaging methods. The proposed technique can make progressive observations on Covid-19 Astra Zeneca vaccination effects on skin cellular network by use of the well-established technique-Intelligent Laser Speckle Classification (ILSC), as Covid-19 is a skin-affecting systemic disease. The method also managed to distinguish between three different subject groups via their laser speckle skin image samplings, grouped as early-vaccinated, late-vaccinated and non-vaccinated participants. The results have proven that the ILSC technique, in association with the parametrically optimised Bayesian network, can classify hidden skin changes of vaccinated and non-vaccinated individuals up to 90% accuracy and is also capable of detecting instant progressive developments pertaining to skin cellular properties. The proposed method has also proven that the continuous Covid-19 vaccine effect on the sub-skin layers can be observable by high frequency and speedy non-invasive data collection in real-time with high reliability.

Vehicular Sensor Networks: Applications, Advances and Challenges.

Vehicular sensor networks (VSN) provide a new paradigm for transportation technology and demonstrate massive potential to improve the transportation environment due to the unlimited power supply of the vehicles and resulting minimum energy constraints. This special issue is focused on the recent developments within the vehicular networks and vehicular sensor networks domain. The papers included in this Special Issue (SI) provide useful insights to the implementation, modelling, and integration of novel technologies, including blockchain, named data networking, and 5G, to name a few, within vehicular networks and VSN.

Man-In-The-Middle Attacks in Vehicular Ad-Hoc Networks: Evaluating the Impact of Attackers' Strategies.

Vehicular Ad-Hoc Network (VANET), a vital component of Intelligent Transportation Systems (ITS) technology, relies on communication between dynamically connected vehicles and static Road Side Units (RSU) to offer various applications (e.g., collision avoidance alerts, steep-curve warnings and infotainment). VANET has a massive potential to improve traffic efficiency, and road safety by exchanging critical information between nodes (vehicles and RSU), thus reducing the likelihood of traffic accidents. However, this communication between nodes is subject to a variety of attacks, such as Man-In-The-Middle (MITM) attacks which represent a major risk in VANET. It happens when a malicious node intercepts or tampers with messages exchanged between legitimate nodes. In this paper, we studied the impact on network performance of different strategies which attackers can adopt to launch MITM attacks in VANET, such as fleet or random strategies. In particular, we focus on three goals of MITM attacks-message delayed, message dropped and message tampered. The simulation results indicate that these attacks have a severe influence on the legitimate nodes in VANET as the network experience high number of compromised messages, high end-to-end delays and preeminent packet losses.

Spatio-Temporal Rich Model-Based Video Steganalysis on Cross Sections of Motion Vector Planes.

A rich model-based motion vector (MV) steganalysis benefiting from both temporal and spatial correlations of MVs is proposed in this paper. The proposed steganalysis method has a substantially superior detection accuracy than the previous methods, even the targeted ones. The improvement in detection accuracy lies in several novel approaches introduced in this paper. First, it is shown that there is a strong correlation, not only spatially but also temporally, among neighbouring MVs for longer distances. Therefore, temporal MV dependency alongside the spatial dependency is utilized for rigorous MV steganalysis. Second, unlike the filters previously used, which were heuristically designed against a specific MV steganography, a diverse set of many filters, which can capture aberrations introduced by various MV steganography methods is used. The variety and also the number of the filter kernels are substantially more than that of used in the previous ones. Besides that, filters up to fifth order are employed whereas the previous methods use at most second order filters. As a result of these, the proposed system captures various decorrelations in a wide spatio-temporal range and provides a better cover model. The proposed method is tested against the most prominent MV steganalysis and steganography methods. To the best knowledge of the authors, the experiments section has the most comprehensive tests in MV steganalysis field, including five stego and seven steganalysis methods. Test results show that the proposed method yields around 20% detection accuracy increase in low payloads and 5% in higher payloads.