Design and Performance Evaluation of Machine Learning-based Terahertz Metasurface Chemical Sensor.

This paper presents a terahertz metasurface based sensor design incorporating graphene and other plasmonic materials for highly sensitive detection of different chemicals. The proposed sensor employs the combination of multiple resonator designs - including circular and square ring resonators - to attain enhanced sensitivity among other performance parameters. Machine learning techniques like Random Forest regression, are employed to enhance the sensor design and predict its performance. The optimized sensor demonstrates excellent sensitivity of 417 GHzRIU-1 and a low detection limit of 0.264 RIU for ethanol and benzene detection. Furthermore, the integration of machine learning cuts down the simulation time and computational requirements by approximately 90% without compromising accuracy. The sensor's unique design and performance characteristics, including its high-quality factor of 14.476, position it as a promising candidate for environmental monitoring and chemical sensing applications. Moreover, it also demonstrates potential for 2-bit encoding applications through strategic modulation of graphene chemical potential values. On the other hand, it also shows prospects of 2-bit encoding applications via the modulation of graphene chemical. This work provides a major advancement to the terahertz sensing application by proposing new materials, structures, and methods in computation in order to develop a high-performance chemical sensor.

Optimization of Novel 2D Material Based SPR Biosensor Using Machine Learning.

Biosensors are needed for today's health monitoring system for detecting different biomolecules. Graphene is a monolayer material that can be utilized to sense biomolecules and design biosensors. We have proposed a Graphene-Gold-Silver hybrid structure design based on Zinc Oxide which gives sensitive performance to detect hemoglobin biomolecules. The advanced biosensor designed based on this hybrid structure shows the highest sensitivity of 1000 nm/RIU which is far better concerning similar structure previously analyzed. The graphene-gold-silver hybrid structure is presented for its possible reflectance results and electric field results. The E-field results match well with the reflectance results given by the sensitive hybrid structure. The sensing biomolecules are presented above the structure where a combination of graphene-gold-silver hybrid structure improves the sensitivity to a great extent. The optimized parameters are obtained by applying variations in the physical parameters of the design. The machine learning algorithm employed for reflectance prediction shows a high prediction accuracy and can be utilized for simulation resource reduction. The proposed biosensor can be used in real-time hemoglobin monitoring.

CANAttack: Assessing Vulnerabilities within Controller Area Network.

Current vehicles include electronic features that provide ease and convenience to drivers. These electronic features or nodes rely on in-vehicle communication protocols to ensure functionality. One of the most-widely adopted in-vehicle protocols on the market today is the Controller Area Network, popularly referred to as the CAN bus. The CAN bus is utilized in various modern, sophisticated vehicles. However, as the sophistication levels of vehicles continue to increase, we now see a high rise in attacks against them. These attacks range from simple to more-complex variants, which could have detrimental effects when carried out successfully. Therefore, there is a need to carry out an assessment of the security vulnerabilities that could be exploited within the CAN bus. In this research, we conducted a security vulnerability analysis on the CAN bus protocol by proposing an attack scenario on a CAN bus simulation that exploits the arbitration feature extensively. This feature determines which message is sent via the bus in the event that two or more nodes attempt to send a message at the same time. It achieves this by prioritizing messages with lower identifiers. Our analysis revealed that an attacker can spoof a message ID to gain high priority, continuously injecting messages with the spoofed ID. As a result, this prevents the transmission of legitimate messages, impacting the vehicle's operations. We identified significant risks in the CAN protocol, including spoofing, injection, and Denial of Service. Furthermore, we examined the latency of the CAN-enabled system under attack, finding that the compromised node (the attacker's device) consistently achieved the lowest latency due to message arbitration. This demonstrates the potential for an attacker to take control of the bus, injecting messages without contention, thereby disrupting the normal operations of the vehicle, which could potentially compromise safety.

Naïve Bayes classifier assisted automated detection of cerebral microbleeds in susceptibility-weighted imaging brain images.

Cerebral microbleeds (CMBs) in the brain are the essential indicators of critical brain disorders such as dementia and ischemic stroke. Generally, CMBs are detected manually by experts, which is an exhaustive task with limited productivity. Since CMBs have complex morphological nature, manual detection is prone to errors. This paper presents a machine learning-based automated CMB detection technique in the brain susceptibility-weighted imaging (SWI) scans based on statistical feature extraction and classification. The proposed method consists of three steps: (1) removal of the skull and extraction of the brain; (2) thresholding for the extraction of initial candidates; and (3) extracting features and applying classification models such as random forest and naïve Bayes classifiers for the detection of true positive CMBs. The proposed technique is validated on a dataset consisting of 20 subjects. The dataset is divided into training data that consist of 14 subjects with 104 microbleeds and testing data that consist of 6 subjects with 63 microbleeds. We were able to achieve 85.7% sensitivity using the random forest classifier with 4.2 false positives per CMB, and the naïve Bayes classifier achieved 90.5% sensitivity with 5.5 false positives per CMB. The proposed technique outperformed many state-of-the-art methods proposed in previous studies.

Staphylococcus aureus strains exhibit heterogenous tolerance to direct cold atmospheric plasma therapy.

The global clinical and socioeconomic impact of chronic wounds is substantial. The main difficulty that clinicians face during the treatment of chronic wounds is the risk of infection at the wound site. Infected wounds arise from an accumulation of microbial aggregates in the wound bed, leading to the formation of polymicrobial biofilms that can be largely resistant to antibiotic therapy. Therefore, it is essential for studies to identify novel therapeutics to alleviate biofilm infections. One innovative technique is the use of cold atmospheric plasma (CAP) which has been shown to possess promising antimicrobial and immunomodulatory properties. Here, different clinically relevant biofilm models will be treated with cold atmospheric plasma to assess its efficacy and killing effects. Biofilm viability was assessed using live dead qPCR, and morphological changes associated with CAP evaluated using scanning electron microscopy (SEM). Results indicated that CAP was effective against Candida albicans and Pseudomonas aeruginosa, both as mono-species biofilms and when grown in a triadic model system. CAP also significantly reduced viability in the nosocomial pathogen, Candida auris. Staphylococcus aureus Newman exhibited a level of tolerance to CAP therapy, both when grown alone or in the triadic model when grown alongside C. albicans and P. aeruginosa. However, this degree of tolerance exhibited by S. aureus was strain dependent. At a microscopic level, biofilm treatment led to subtle changes in morphology in the susceptible biofilms, with evidence of cellular deflation and shrinkage. Taken together, these results indicate a promising application of direct CAP therapy in combatting wound and skin-related biofilm infections, although biofilm composition may affect the treatment efficacy.

A Numerical Study of the Dynamics of Vector-Born Viral Plant Disorders Using a Hybrid Artificial Neural Network Approach.

Most plant viral infections are vector-borne. There is a latent period of disease inside the vector after obtaining the virus from the infected plant. Thus, after interacting with an infected vector, the plant demonstrates an incubation time before becoming diseased. This paper analyzes a mathematical model for persistent vector-borne viral plant disease dynamics. The backpropagated neural network based on the Levenberg-Marquardt algorithm (NN-BLMA) is used to study approximate solutions for fluctuations in natural plant mortality and vector mortality rates. A state-of-the-art numerical technique is utilized to generate reference data for obtaining surrogate solutions for multiple cases through NN-BLMA. Curve fitting, regression analysis, error histograms, and convergence analysis are used to assess accuracy of the calculated solutions. It is evident from our simulations that NN-BLMA is accurate and reliable.

On the Computational Study of a Fully Wetted Longitudinal Porous Heat Exchanger Using a Machine Learning Approach.

The present study concerns the modeling of the thermal behavior of a porous longitudinal fin under fully wetted conditions with linear, quadratic, and exponential thermal conductivities surrounded by environments that are convective, conductive, and radiative. Porous fins are widely used in various engineering and everyday life applications. The Darcy model was used to formulate the governing non-linear singular differential equation for the heat transfer phenomenon in the fin. The universal approximation power of multilayer perceptron artificial neural networks (ANN) was applied to establish a model of approximate solutions for the singular non-linear boundary value problem. The optimization strategy of a sports-inspired meta-heuristic paradigm, the Tiki-Taka algorithm (TTA) with sequential quadratic programming (SQP), was utilized to determine the thermal performance and the effective use of fins for diverse values of physical parameters, such as parameter for the moist porous medium, dimensionless ambient temperature, radiation coefficient, power index, in-homogeneity index, convection coefficient, and dimensionless temperature. The results of the designed ANN-TTA-SQP algorithm were validated by comparison with state-of-the-art techniques, including the whale optimization algorithm (WOA), cuckoo search algorithm (CSA), grey wolf optimization (GWO) algorithm, particle swarm optimization (PSO) algorithm, and machine learning algorithms. The percentage of absolute errors and the mean square error in the solutions of the proposed technique were found to lie between 10-4 to 10-5 and 10-8 to 10-10, respectively. A comprehensive study of graphs, statistics of the solutions, and errors demonstrated that the proposed scheme's results were accurate, stable, and reliable. It was concluded that the pace at which heat is transferred from the surface of the fin to the surrounding environment increases in proportion to the degree to which the wet porosity parameter is increased. At the same time, inverse behavior was observed for increase in the power index. The results obtained may support the structural design of thermally effective cooling methods for various electronic consumer devices.

Incremental Composition Process for the Construction of Component-Based Management Systems.

Cyber-physical systems (CPS) are composed of software and hardware components. Many such systems (e.g., IoT based systems) are created by composing existing systems together. Some of these systems are of critical nature, e.g., emergency or disaster management systems. In general, component-based development (CBD) is a useful approach for constructing systems by composing pre-built and tested components. However, for critical systems, a development method must provide ways to verify the partial system at different stages of the construction process. In this paper, for system architectures, we propose two styles: rigid architecture and flexible architecture. A system architecture composed of independent components by coordinating exogenous connectors is in flexible architecture style category. For CBD of critical systems, we select EX-MAN from flexible architecture style category. Moreover, we define incremental composition mechanism for this model to construct critical systems from a set of system requirements. Incremental composition is defined to offer preservation of system behaviour and correctness of partial architecture at each incremental step. To evaluate our proposed approach, a case study of weather monitoring system (part of a disaster management) system was built using our EX-MAN tool.

Incremental Construction for Scalable Component-Based Systems.

The availability of smart and intelligent sensors has changed the monitoring, control and maintenance of a conventional and advanced cyber-physical system used in public or private sectors of a society. For example, internet of things (IoT)-based health, agricultural and weather management systems. With the emergence of such sensors, along with the new ways to communicate or coordinate with them, we need to analyze and optimize the system construction processes. In this paper, to address the issue of scalability for bigger and complex systems based on sensors, we redefine an incremental construction process with an emphasis on behavior preservation and study the effectiveness of the use of software component models from the component-based development domain. In this paper, to deal with the issue of scalability, we investigate component-based development approaches with respect to our defined process and propose a taxonomy of component models with respect to component/system behavior. Moreover, based on the outcome of our analysis, we recommend the EX-MAN component model as the most suitable approach. We investigate incremental construction in the context of the three main categories of current component models, namely models where components are: (i) objects, (ii) architectural units and (iii) encapsulated components. Furthermore, to evaluate our defined process and selection of EX-MAN, we designed three examples of systems using our proposed process in EX-MAN component model.