In order to address the problems of slow generation and poor image quality of digital reconstructed radiographs (DRR) in the alignment of preoperative 3D computed tomography (CT) images with intraoperative 2D X-ray images, a single-scale Retinex-based improved grey-scale image enhancement method is proposed. The proposed method is based on a single-scale Retinex improvement of grey-scale image enhancement and employs a CUDA-based GPU parallel light projection algorithm globally. A hierarchical alignment method based on a weighted histogram of gradient directions (WHGD) is proposed to address the problems of slow convergence and small capture range caused by simultaneous optimization of all pose parameters in the 2D/3D alignment algorithm. The WHGD is independent of the translation parameters to achieve spatial decoupling of the parameters, and an adaptive evolutionary optimization strategy of the covariance matrix is introduced to ensure correct convergence of all the positional parameters while avoiding local optima. The experimental results show that the method is 41.42% faster and 34.53% more accurate than similar alignment methods, meeting the requirements for accuracy and speed in clinical settings.

Concerns about the risk of catastrophic accidents have prompted governments and industries to develop new methods for identifying and evaluating potential hazards. The most promising strategy involves assembling a collection of quantitative risk assessment techniques (QRA). The use of (QRA) is rapidly spreading across industries, having been adapted primarily from probabilistic risk assessment approaches developed in other industries. The Netherlands Organization (TNO) developed the (QRA) for the external safety of industrial plants against fire and explosion hazards. Escalation of primary events that trigger accidental scenarios may have a significant impact on industrial risk, increasing the overall expected frequency of single scenarios and resulting in extremely severe damages involving multiple plant units simultaneously. The present study applied a methodology developed for quantifying the risk of liquefied natural gas (LNG) containment loss. To begin, an industrial facility is separated into modules based on its structural characteristics. Following that, the relevant fire and explosion scenarios are identified, along with their frequency of occurrence. Recently developed equipment damage probability models were used to determine the probability of the final scenario occurring. SAFETI software was used to model and calculate risks. Finally, the individual risks (thermal and overpressure exceedance curves) are calculated, as well as the societal risk (FN curve). The findings demonstrate the critical importance of quantitative risk assessment in identifying critical equipment and addressing prevention and protection measures.

Intelligent networks are the most common form of cyber-physical networks, which provide a strong connection between cyber communications and physical networks. As smart grid applications and technologies are developed and put into use, cyber security is becoming a serious problem. Therefore, it is crucial to research how cyber-attacks affect the frequency relay device of smart grids. This study investigates how cyber-attacks that increase latency in communications infrastructure affect system dependability. These were finished utilizing information gathered from a STATCOM or SVC that was linked to the grid. This paper presents two new approaches based on nonlinear controllers (NL) and PI controllers to minimize the negative impacts of cyber-attacks on the mentioned relay, as well as a novel detection and mitigation methodology for the FACTS based on the voltage threshold. There are case studies that examine the effects of fixed communication delays on transient angles and voltage stability just in electricity networks. Two methods of cyber-attacks were reviewed, and their impacts were demonstrated using the MATLAB Simulink-implemented Kigali national grid (KNG). According to simulation studies, certain communication delays resulting from cyber-attacks might lead the network to become unsustainable. Suggestions are made to improve electrical security in the event of cyber-attacks, damage, and delays in future power system grids against potential cyber-attacks.

The process of making changes to software after it has been delivered to the client is known as maintainability. Maintainability deals with new or changed client requirements. Service-oriented architecture (SOA) is a method for developing applications that helps services work on different environments. SOA works on patterns of distributed systems that help different applications communicate with each other using different protocols. To assess the maintainability of service-oriented architecture, different factors are required. Some of these factors are analyzability, changeability, stability, and testability. Modification is the process of upgrading the software functionality. After modification of service-oriented architecture, the module will go to the testing phase. The evaluation and verification of whether a software product or application performs as intended is known as testing. The testing phase is a combination of various stages, such as individual module testing and testing after collaborations between them. This testing stage is time-consuming in the maintenance process. The term “outlier" refers to a module in software systems that deviates significantly from the rest of the module. It represents the collection of data, variables, and methods. For instance, the program might have been coded mistakenly or an investigation might not have been run accurately. To detect the outlier module, test cases are needed. A methodology is proposed to reduce the predefined test cases. K-means clustering is the best approach to calculate the number of test cases, but the outlier is not automatically determined. In this paper, a hybrid clustering approach is applied to detect the outlier. This clustering method is used in software testing to count the number of comments in various software and in medical science to diagnose the disease of Covid patients. The experimental outcomes show that our strategy achieves better results.

Existing fault tolerance approaches in the cloud are broadly based on replication and checkpointing. Each of these approaches has its advantages and limitations. This paper presents an adaptable fault tolerance method for determining which of the two approaches will be appropriate for the successful execution of a task in the given cloud conditions. The proposed method classifies the failure risk of host machines available for task execution based on their failure history. Subsequently, fuzzy logic is used to determine the appropriate fault tolerance approach by considering a host's failure risk, user-defined task's priority, and level of resource redundancy. Setting a task’s priority provides a user with control to solicit a desired fault tolerance level while the availability of resources reflects a cloud provider’s capability to offer fault tolerance. Simulation experiments have verified that the proactive selection of a fault-tolerance method increases the number of tasks that complete successfully.

A wide variety of Application Areas for Machine Learning & Diagnostic Imaging are supported by machine learning. Nevertheless, using this approach carelessly, especially for medical purposes, may result in poor results. As a result, one needs to be conscious of potential hazards and related obstacles in machine learning stages such as pre-processing, training, and testing. This necessitates embedding domain-specific information into to the training process, which would be incredibly vital and plays an important role in many applications. This article introduces a technological solution for using this information in machine developing learning algorithms for biological uses, such as detecting breast cancer. The most prevalent cancer in women worldwide is breast cancer, which also has a high mortality rate. This study's goal is to suggest a method for looking at the use of various machine learning (ML)-based approaches in biomedicine for earlier skin cancer detection and diagnosis. For this purpose, a new prediction model is proposed based on a machine learning technique to achieve the aim of accurate classification of breast cancer. The experiments have been carried out in a Jupyter framework on breast cancer data of WDBC Dataset. These experimented outcomes of tests tell us the proposed prediction model achieved better outcomes by increasing the state-of-the-art machine learning techniques' accuracy, precision, recall, and f-measure. The comparative analysis revealed that the suggested model outperforms other cutting-edge machine learning methods.

Due to the increasing demand for energy, the current approach of obtaining energy from fossil fuels is insufficient, resulting in significant environmental destruction. As a result, switching to unconventional energy sources is being given more consideration. Due to the global transition to renewable energy sources, distributed generation is now used to produce electricity regionally. MATLAB/Simulink is used for the simulation-based integrated renewable energy system model. The hybrid microgrid is made up of resistive loads, Nickel Metal Hydride (NiMH) battery storage, and renewable generators like solar and wind. The created system functions as an entirely carbon-free microgrid. The solar PV generator is connected to the hybrid microgrid using Buck converter, whilst the wind generator is connected with Wind Maximum Power Point Tracking (MPPT). Bidirectional Converter (Buck-Boost) is used to link the battery to the microgrid, allowing for both charging and discharging in order to balance supply and demand. Depending on the availability of renewable power generators, electricity is transferred from the DC bus to the loads and between the loads (including dump load) and batteries. To assess the efficacy of the suggested technique two scenarios were examined.

Traffic accidents are a significant health and economic issue on a global scale and have been the main focus of traffic psychology research. Utilizing differences among drivers has been a key strategy to anticipate eventual accident involvement. A popular tool for identifying and evaluating unusual driving behavior is the Driver Behavior Questionnaire (DBQ). Despite the popularity of the self-report method, the DBQ's use in underdeveloped countries like India has not been tried. The DBQ measures what are referred to as aberrant driving behaviors and is based on Reason's error theory. The foreseeability of road accidents is one of its primary intended purposes. Although several studies have explored this and shown some success, it is important to notice one aspect of DBQ reports: practically all of them have used self-reported accidents as the dependent variable. The aim of this study is to analyze the relationship between aberrant driving behavior and traffic offences by using DBQ to evaluate the factors that influence aberrant driving behavior. Exploratory and confirmatory factor analyses provided evidence in favor of the initial factor structure. Overall, the results demonstrated that the cross-cultural DBQ is a useful and reliable tool for assessing driving behavior in India. The results offer helpful knowledge on the factors that affect driving ability and behavior, which will help India reduce traffic jams and accidents on the roads.