Search

Urban traffic congestion is difficult for modern urban management due to Rapid City expansion, outdated traffic control methods, inadequate road design and construction, and rising car ownership. The literature provides a detailed Internet of Things (IoT) based Intelligent Transportation System (ITS) architecture, focusing on the application, network, and perception levels. The application layer processes traffic data and supports various ITS. Through sensors and communication networks, the perception layer collects real-time traffic data, while the network layer ensures reliable and secure data transfer. The design delves into vehicular communication network protocol architecture, with a focus on Mobile Ad-hoc Networks (MANETs). In the context of Vehicle Ad-hoc Networks (VANETs), it covers security issues, the transport layer, the Physical and Media access control (PHY/MAC) layer, and routing protocols. The paper explores the integration of mobile models with network simulation tools, outlining two methods: the Mobile Fusion Model and the Mobile Embedded Model. In conclusion, a simulation study utilizing the Optimized Network Engineering Tool (OPNET) Modeler platform is presented, this study evaluates Destination Sequenced Distance Vector (DSDV) Protocol, and Optimized Link State Routing (OLSR) Protocol about packet loss performance, network load, and Vehicle-to-Vehicle (V2V) communication networks. [ABSTRACT FROM AUTHOR]

Zinc oxide (ZnO) nanoparticles (NP) are generating substantial attention across multiple areas due to the distinctive Structural and Molecular Features. Predicting and understanding these properties is crucial for designing effective applications in areas such as catalysis, sensors, and biomedical devices. Nanotechnology has emerged as a pivotal field, particularly in materials science, where the unique properties of NP are harnessed for various applications. Understanding and predicting the physical properties of NP, such as those in ZnO, is crucial for optimizing their performance. For the classification approach, we introduced a novel method, Bat based Random Forest (B-RF) to enhance the accuracy and efficiency of predicting major physical properties of ZnO NP. In this research, we utilize a relevant dataset encompassing various physical properties of ZnO NP. The model is fine-tuned to achieve optimal performance. The proposed Random Forest-based classification approach demonstrates superior predictive performance compared to traditional methods. Our model attains high accuracy and reliability in predicting diverse physical properties of ZnO NP. By the end of the study, our suggested approach outperforms other methods in terms of Accuracy (92.8%), Sensitivity (90.8%), and Specificity (93.9%). This can contribute to improve the overall performance and functioning of the existing model in a better way. [ABSTRACT FROM AUTHOR]

Identifying and quantifying unexpected events in non-equilibrium systems is critical work that is necessary for systems managers to make well-informed decisions, particularly when forecasting rare and extreme events. In this paper neural networks are integrated to increase the predictive capacity of information theory. Two information theory techniques, “Information Length (IL) and Information Flow (IF)”, are being examined for their sensitivity to rapid changes. To simulate the first occurrence of extreme and rare events, we utilize a nonautonomous Kramer model to introduce a perturbation. we introduced a Dynamic Osprey Long Short-Term Memory (DOLSTM) for predicting rare and extreme events in non-equilibrium systems. Our results show that IL performs better than IF in accurately forecasting unexpected occurrences when combined with a neural network. This study highlights a novel integration between information theory & neural networks, giving an effective strategy for forecasting rare & extreme events in non-equilibrium environments. An effective methodology for identifying and forecasting the behavior of dynamic systems is established by combining information-length diagnostics with neural network predictions, especially in situations involving rare and extreme events. This novel method illustrates that the theory of information and neural networks can be used to provide robust predictions for dynamic systems, when encountering rare and extreme events. [ABSTRACT FROM AUTHOR]

Metal dichalcogenides are a kind of chemical substance that consists of a metal atom paired with chalcogen elements such as selenium and sulphur. These materials have distinctive electrical and optical characteristics, making them fascinating for a variety of applications, including electronics and optoelectronics. Growth examination of metal dichalcogenide thin films entails analyzing their controlled deposition and crystallization. Understanding growth processes, substrate interactions and controlling parameters like as temperature and precursor concentration are critical for producing high-quality films with the appropriate characteristics, establishing the way for developments in nanotechnology and device manufacturing. Throughout this research, we employed the Machine learning (ML) enabled Reflection High-Energy Electron Diffraction (RHEED) analytical approach to examine the development of two-dimensional (2D thin layers of dichalcogenides (ReSe2) made of transition metals on graphene substrates using Molecular Beam Epitaxy (MBE). Independent Component Analysis (ICA) and the Fuzzy C-Means approach were implemented to determine different patterns and represent the pattern growths. To decrease the original dataset's dimensionality, we employed 20 Independent Components (ICs) and each RHEED image was distributed to the closest centroid, which resulted in the dataset being clustered using Fuzzy C-Means. [ABSTRACT FROM AUTHOR]

The nanocomposite filtration membranes have emerged as potential water purification and separation technologies. However, reliable estimation of foulant rejection and permeate flux remains difficult due to the complicated interaction of many components. Traditional modeling techniques fail to capture the complex dynamics at work. In this paper, we provide a Refined Support Vector Machine (RSVM) strategy to solve this issue and increase the performance of nanocomposite filtration membranes. To normalize the features, the data are pre-processed using min-max normalization. Data features like foulant rejection rates, permeate flux values, membrane features, and experimental setup are displayed. Furthermore, the proposed RSVM to determine the best input factors for the effectiveness of each nanocomposite membrane. Due to the strong resilience of RSVM and the great generalization ability of the ML model, the obtained results demonstrated that the RSVM model's prediction efficiency (R2 = 0.995) outperformed the mathematical model in terms of prediction performance. To conduct training, validation and testing for this work, we employed statistical data including 764 samples of the input variables (five) and output variables (two). The RSVM approach provides a dependable and effective way to forecast membrane fouling and water filtration by predicting foulant rejection and permeate flux. [ABSTRACT FROM AUTHOR]

The arbitrarily formed golden cluster systems were created in the gas state which has strong Resistive Switching (RS) behavior around ambient temperatures and makes these attractive candidates for the creation of electronics geared toward neuron categorization along with information analysis. The cluster-assembled nanotechnology coatings that are fully linked have an irregular shape that includes neuromorphic crystallographic flaws, interactions and frontiers of grains, highlighting the complex interaction among electromagnetic in mechanical elements. In this analysis, we conduct a thorough investigation of the electroforming procedure that is utilized in the creation of film that was the cluster assembled. The present research sheds light regarding the electroforming procedure's substantial influence on the complex relations among nanopores and the mesoscale layer formations and underlying neurological properties of resistance switches activities that ensure. The findings provide insight into a methodical oversight of electroforming operation and reveal its function in building distinct patterns at various sizes in films of cluster assembled. The discovery not only improves our understanding of the intricate relationships among architectural and electrical parts but it provides opportunities for designing neurological structures that are randomly constructed and customized over multiple information-handling applications. [ABSTRACT FROM AUTHOR]

Metallic films, which are thin layers of metal deposited on surfaces, have a wide range of uses in many sectors. Metallic films are usually produced by sputtering or chemical vapor deposition and serve an important role in electronics, optics and coatings. Their fundamental conductivity, reflective qualities and adaptability makes important for the development of innovative materials and systems. Investigations are conducted on the rigidity, optical reflecting power, temperature conductivity and power mobility of metallic films. These attributes are affected by layer thickness, composition and deposition processes. Understanding the complexities of these physical features is critical for modifying metallic films to particular applications, which drives technological and material science innovation. In this research, the physical characteristics of metallic films, which are thinner than 20 – 200 nm were evaluated. The suggested methods for determining the Cu, and Al films temperature-dependent coefficients of resistance, thermal conductivity properties, particular heat and thermal diffusivity. The rapid amount of heating that is observed in a brief period allows the thermal characteristics of the metallic layer to be primarily evaluated without impacting the substrate. [ABSTRACT FROM AUTHOR]