Search for: All records

Vehicle-to-Everything (V2X) communication enables vehicles to communicate with other vehicles and roadside infrastructure, enhancing traffic management and improving road safety. However, the open and decentralized nature of V2X networks exposes them to various security threats, especially misbehaviors, necessitating a robust Misbehavior Detection System (MBDS). While Machine Learning (ML) has proved effective in different anomaly detection applications, the existing ML-based MBDSs have shown limitations in generalizing due to the dynamic nature of V2X and insufficient and imbalanced training data. Moreover, they are known to be vulnerable to adversarial ML attacks. On the other hand, Generative Adversarial Networks (GAN) possess the potential to mitigate the aforementioned issues and improve detection performance by synthesizing unseen samples of minority classes and utilizing them during their model training. Therefore, we propose the first application of GAN to design an MBDS that detects any misbehavior and ensures robustness against adversarial perturbation. In this article, we present several key contributions. First, we propose an advanced threat model for stealthy V2X misbehavior where the attacker can transmit malicious data and mask it using adversarial attacks to avoid detection by ML-based MBDS. We formulate two categories of adversarial attacks against the anomaly-based MBDS. Later, in the pursuit of a generalized and robust GAN-based MBDS, we train and evaluate a diverse set of Wasserstein GAN (WGAN) models and presentVehicularGAN(VehiGAN), an ensemble of multiple top-performing WGANs, which transcends the limitations of individual models and improves detection performance. We present a physics-guided data preprocessing technique that generates effective features for ML-based MBDS. In the evaluation, we leverage the state-of-the-art V2X attack simulation tool VASP to create a comprehensive dataset of V2X messages with diverse misbehaviors. Evaluation results show that in 20 out of 35 misbehaviors,VehiGANoutperforms the baseline and exhibits comparable detection performance in other scenarios. Particularly,VehiGANexcels in detecting advanced misbehaviors that manipulate multiple fields in V2X messages simultaneously, replicating unique maneuvers. Moreover,VehiGANprovides approximately 92% improvement in false positive rate under powerful adaptive adversarial attacks, and possesses intrinsic robustness against other adversarial attacks that target the false negative rate. Finally, we make the data and code available for reproducibility and future benchmarking, available athttps://github.com/shahriar0651/VehiGAN. 

Small angle neutron scattering was employed to investigate the mechanism of copolymerization of metal-organic nanotubes. 

Colloids can be used either as model systems for directed assembly or as the necessary building blocks for making functional materials. Previous work primarily focused on assembling colloids under a single external field, where controlling particle−particle interactions is limited. This work presents results under a combination of electric and magnetic fields. When these two fields are orthogonally applied, we can independently tune the magnitude and direction of the dipolar attraction and repulsion between the particles. As a result, we obtain well-aligned, highly dense, but individually separated linear chains at intermediate particle concentrations. Both the inter- and intrachain spacings can be tuned by adjusting the particle concentration and relative strengths of both fields. At high particle concentrations and by tuning the electric field frequency, the individual microspheres can assemble into colloidal oligomers such as trimers, tetramers, heptamers, and nonamers in response to the electric field due to the synergy between dipolar and electrohydrodynamic interactions. These oligomers, in turn, serve as building blocks for making hierarchical structures with finer architectures upon superimposing a one-dimensional (1D) magnetic field. In addition to experiments, Monte Carlo (MC) simulations have been performed on colloids confined near the electrode, interacting through a Stockmayer-like potential. They faithfully reproduce key observations in the experiments. Our work demonstrates the potential of using orthogonal electric and magnetic fields to assemble diversified types of highly aligned structures for applications in high-strength composites, optical materials, or structured battery electrodes. 

This study aimed to estimate the prevalence of illegal kidney sales in Kalai Upazila, Bangladesh, using the Network Scale-Up Method (NSUM), an ego-centric network survey-based technique used to estimate the size of hidden populations. The study estimated the size of the kidney seller population, analysed the profiles of kidney sellers and kidney brokers and investigated the characteristics of villagers who are more likely to be connected to kidney sellers to identify possible biases of the NSUM estimate. The study found that the prevalence of kidney trafficking in Kalai Upazila was between 1.98% and 2.84%, which is consistent with the estimates provided by a local leader and reporters, but with much narrower bounds. The study also found that a large proportion of kidney sellers and brokers were men (over 70% and 90%, respectively) and relatively young (mean age of 33 and 39, respectively). Specific reasons for kidney sales included poverty (83%), loan payment (4%), drug addiction (2%) and gambling (2%). While most reported male sellers were farmers (56%) and female sellers were housewives (78%) in need of money, most reported brokers were characterised as rich, well-known individuals. 

Walking in real-world environments involves constant decision-making, e.g., when approaching a staircase, an individual decides whether to engage (climbing the stairs) or avoid. For the control of assistive robots (e.g., robotic lower-limb prostheses), recognizing such motion intent is an important but challenging task, primarily due to the lack of available information. This paper presents a novel vision-based method to recognize an individual’s motion intent when approaching a staircase before the potential transition of motion mode (walking to stair climbing) occurs. Leveraging the egocentric images from a head-mounted camera, the authors trained a YOLOv5 object detection model to detect staircases. Subsequently, an AdaBoost and gradient boost (GB) classifier was developed to recognize the individual’s intention of engaging or avoiding the upcoming stairway. This novel method has been demonstrated to provide reliable (97.69%) recognition at least 2 steps before the potential mode transition, which is expected to provide ample time for the controller mode transition in an assistive robot in real-world use. 

Measurement of prosthesis structural load, as an important way to quantify the interaction of the amputee user with the environment, may serve important purposes in the control of smart lower-limb prosthetic devices. However, the majority of existing force sensors used in protheses are developed based on strain measurement and thus may suffer from multiple issues such as weak signals and signal drifting. To address these limitations, this paper presents a novel Force-Moment Prosthesis Load Sensor (FM-PLS) to measure the axial force and bending moment in the structure of a lower-limb prosthesis. Unlike strain gauge-based force sensors, the FM-PLS is developed based on the magnetic sensing of small (millimeter-scale) deflection of an elastic element, and it may provide stronger signals that are more robust against interferences and drifting since such physical deflection is several orders of magnitude greater than the strain of a typical load-bearing structure. The design of the sensor incorporates uniquely curved supporting surfaces such that the measurement is sensitive to light load but the sensor structure is robust enough to withstand heavy load without damage. To validate the sensor performance, benchtop testing of the FM-PLS and walking experiments of a FM-PLS-embedded robotic lower-limb prosthesis were conducted. Benchtop testing results displayed good linearity and a good match to the numerical simulation results. Results from the prosthesis walking experiments showed that the sensor signals can be used to detect important gaits events such as heel strike and toe-off, facilitating the reliable motion control of lower-limb prostheses. 

Dementia is a brain disease which results in irreversible and progressive loss of cognition and motor activity. Despite global efforts, there is no simple and reliable diagnosis or treatment option. Current diagnosis involves indirect testing of commonly inaccessible biofluids and low-resolution brain imaging. We have developed a portable, wireless readout-based Graphene field-effect transistor (GFET) biosensor platform that can detect viruses, proteins, and small molecules with single-molecule sensitivity and specificity. We report the detection of three important amyloids, namely, Amyloid beta (Aβ), Tau (τ), and α-Synuclein (αS) using DNA aptamer nanoprobes. These amyloids were isolated, purified, and characterized from the autopsied brain tissues of Alzheimer’s Disease (AD) and Parkinson’s Disease (PD) patients. The limit of detection (LoD) of the sensor is 10 fM, 1–10 pM, 10–100 fM for Aβ, τ, and αS, respectively. Synthetic as well as autopsied brain-derived amyloids showed a statistically significant sensor response with respect to derived thresholds, confirming the ability to define diseased vs. nondiseased states. The detection of each amyloid was specific to their aptamers; Aβ, τ, and αS peptides when tested, respectively, with aptamers nonspecific to them showed statistically insignificant cross-reactivity. Thus, the aptamer-based GFET biosensor has high sensitivity and precision across a range of epidemiologically significant AD and PD variants. This portable diagnostic system would allow at-home and POC testing for neurodegenerative diseases globally.