In practice, classical path optimization algorithms performs poorly when applied to an unknown environment, swarm intelligence algorithms need further improvement in agility and accuracy to avoid a moving object in dynamic environment, and reinforcement learning algorithm, a usual solution adopted in machine learning, may give rise to curse of dimensionality due to the complexity of scenario. In view of aforesaid practical problems, this paper proposes using MAXQ hierarchical reinforcement learning method to achieve dimensionality reduction by abstraction and combining leader-wingman approach with dynamic dead zone to model after cooperative formation and design triangular form. A novel algorithm based on MAXQ and simulated annealing is designed to solve unmanned aerial vehicle (UAV) path planning problem, which accomplishes grid method-based path planning simulation in 2D scenarios. A comparative analysis is performed on Q-Learning, ε-Q-Learning, standard MAXQ and SA-MAXQ algorithms in terms of their convergence, time consumption and search steps. Moreover, leader-wingman method is combined with dynamic dead zone in modelling triangular form for Multi-UAV collaborative formation. The experimental results indicate SA-MAXQ algorithm yields quicker astringence, lower volatility, better learning effect, less time consumed and optimized searched route.

Social media has become a daily routine in the lives of digitally connected populations. In order to be relevant and present in this vast medium, organizations have created brand pages to communicate, engage, and build relationships on social media. This study explores the performance of the big four American banks on Facebook and Instagram. Performance is calculated by analyzing the engagement of social media posts in a three-month period. The study identifies the bank that has generated the most engagement in the time period and identifies the top performing posts for each month. The big four bank performance on social media have not been analyzed in academic literature previously. Thus, this research adds to the growing knowledge in the area of social media analysis. Future research can be built upon the methods used in this study and applied to other industries. The study uncovers that Bank of America has the highest engagement on Facebook and Instagram and that posts that highlight corporate social responsibility, products, and are informative perform the best on both social media channels.

Text line segmentation is an important step for the document image understanding system. Day by day volume of document images is increasing as a result of digitization activities run by various organizations. These data comprise of old archive document images which are important to heritage. Understanding documents and extracting information from these varieties of documents is important and yet challenging. Document layout analysis, graphics detection, table detection, stamp detection, annotation understanding, segmentation, recognition etc. are the component of document understanding system. Segmentation plays a very important role in document image understanding systems as stable recognition engines can only recognize words, characters or symbols. The older printed documents or manuscripts generally contain various artifacts, noise, skew, annotations, merged components, etc. which makes information extraction difficult as segmentation does not perform well. We are considering the document images containing Indian scripts where upper/lower zone characters from different lines get merged and containing interfering lines due to less space between the lines. Moreover, these documents possess complex layout, noise, deformities, local skew etc. which makes line segmentation more challenging. The line segmentation output is fed into the word segmentation module and then to character segmentation or recognition engine. The wrong/merged line segments generate fallacious results/data for the word segmentation and recognition engine, thus reducing the overall performance of the document understanding system. It is required to develop robust line segmentation as the overall performance of system is very sensitive to the performance of line segmentation. In this paper, we are proposing the rule based line segmentation method, employing region growing, morphological image processing, and connected component analysis to handle merged line segmentation. The proposed technique is able to segment lines where nonlinear separation exists between the adjacent lines. Evaluation has been performed on 350 documents images taken from old books containing approx. 10k text lines. It is observed the proposed approach outperforms the traditional projection profile based approach for the documents containing merged lines.

The construction industry has a major role for the development of a country, but on the other hand the construction industry has always been a challenging industry to complete its projects by controlling its different dimensions. There are many dimensions that play a vital role for the successful completion of a construction project, but the most important is the golden triangle, also known as the triple constraints of project management, consists of time, cost and quality. This paper focuses on quality management system of a construction project in three ways 1) quality planning (2) quality control (3) quality assurance. Different indicators are used for the preparation of the questionnaire to check existing quality management system of construction projects. The survey reveals that most of the projects have improper and inefficient quality management system with respect to quality control and quality assurance and needs serious improvements. Some major recommendations for the improvement of existing quality management system have been proposed.

Several nations have systematically developed a number of programmes to reduce the amount of pollution emitted by fossil fuels during power generation. The main focus of economic emission dispatch (EED) strategy is to find the most suitable solution by balancing the cost and emissions for a microgrid(MG) network which satisfy the operational needs of the generators. The electricity network in rural areas needs a significant investment in terms of infrastructure. As a result, the economic benefits of deploying a microgrid powered by renewable energy sources(RES) are remarkable. In order to come up with the most efficient EED, a combination of the cost and emission functions is integrated. A PV-thermal-wind-based framework has been employed to address the real-time combined EED problem effectively in a microgrid network. This study introduces a multi-objective load dispatch problem(LDP) using hybrid Nature-inspired algorithms. The proposed hybrid Whale Cat Optimization (WCO) outperforms other four optimization approaches, such as PSO, GWO, and WOA, in a series of experiments by considering two fitness functions (Microgrid cost and emission).

IoT in Smart Grid has paved the way for the continuing need for digitalization in electric power. Smart Grid has made enormous improvements to the emergence in internet and networking technology but creates a huge protection and privacy gap for numerous SG components. Many developed countries contribute technology to the existing SG infrastructure, but as a developing nation, India continues to struggle to solve problems. This article discussed the smart grid's safety implications and primarily focuses on providing protections for consumer information created by the cloud storage of smart meters. Many papers have been reviewed to provide insight into cloud and data security. In this paper, a taxonomy of simulation/ testbeds along with datasets is presented. It can be deduced that no single solution can prevent cyber-attacks on the infrastructure, but artificial intelligence can help discourage future attacks.

This work focuses on modeling the maintenance of complex repairable systems (CRS) based on realistic models to highlight the effect of imperfect repairs (IR) on the future performance of the system while incorporating certain information concomitants of the system called covariates. The latter were considered, thanks to the Generalized Proportional Intensity Model (GPIM), for a history of reliability and maintenance of a turbocharger having operated for nearly nine years in the National oil and gas company (SONATRACH). The GPIM was compared with the Proportional Intensity Model (PIM) to show its flexibility to take, in addition to covariates, the effect of corrective and preventive maintenance actions. The estimation of the model parameters is ensured by the maximum likelihood approach (MLE) using the MATLAB programming language. The goodness of fit of the models can be ensured by the likelihood test (LR) using the results found by the maximum likelihood approach. The failure intensity functions of the two models consider the linear log law, based on the non-homogeneous Poisson process (NHPP), with the same covariates “programming of maintenance shutdowns”, “temperature” and “time between failures’’.

According to a study on vulnerabilities of network security, the novel-based signature, and anomaly-based approaches for Distributed Denial of Service (DDoS) attacks attempt to exploit the security flaws. Based on signature filtering criteria, the goal of this work is to develop an effective strategy for anomaly detection and mitigation of Distributed Denial of Service (DDoS) assaults. Most of today’s performance reduction of internet resources is based on Distributed Denial of Service (DDoS) assaults. Whenever we heard about a website being hacked, we assumed it was the result of a DDoS attack. The accessibility of the services or resources is normally reduced to a legitimate user by overloading the excessive traffic using a zombie distributed network which is due to DDoS assaults. Botnet refers to the widespread network of hacked hosts that carry out the attack. We designed a Non-Anomaly Evolutionary (NAE) Signature-based Model for a DDoS protection system using a signature and anomaly-based method that detects and mitigates assaults at their source, ensuring the network infrastructure's normal operation. According to the findings of the test, our approach took a total average mitigation time of 1.75 seconds with the total average Round Trip Time (RTT) of 0.481 milliseconds to detect DDoS attacks and to mitigate the same when compared to other existing novel signature-based models.