The growing use of Wireless Sensor Networks (WSNs) in Internet of Things (IoT) applications requires innovation in energy-efficient and secure communication protocols to improve network functionality and lifetime. Legacy routing protocols struggle to achieve an equilibrium between energy usage, security, and information accuracy, resulting in excessive node failure rates and transmission errors. Compared to previous methods, this candidate RK-EFCRP is the first to combine a rank-based dynamic key update protocol with the hierarchy clustering hierarchical structure of the hybrid RK-tree, and can comprehensively optimize both routing and cryptography security, within the same lightweight structure. To solve these problems, this paper presents an enhanced Rank-Based Key Management for Energy-Efficient Cluster-Based Routing Protocol (RK-EFCRP) which implements a new hierarchical clustering method with Adaptive Cluster Head (CH) selection and a novel rank-based key assignment scheme to enhance the system’s stability, security, and energy efficiency. The effectiveness of RK-EFCRP is compared with the last mile safety routing for low power WSN (Safety-RPL) protocol, Hybrid Blockchain Enabled Energy Efficient Routing (HBEER), Secure and Energy Efficient Hierarchical Routing (SEHR), and Secure and Energy Aware Multi-Hop Hierarchical Routing (SEAMHR) protocol using energy efficiency, security strength, latency, and packet delivery ratio (PDR), and overall network lifetime as key performance indicators (KPIs). Experimental results demonstrate that RK-EFCRP significantly reduces energy consumption to 6.13 J, outperforming other protocols like SEAMHR (11.20 J). Additionally, RK- EFCRP enhances security strength to 97.5%, surpassing SEAMHR (85%) and HBEER (78%) as well. Moreover, unlike existing protocols that operate between 1.5 and 2.3 ms, RK-EFCRP reduces latency to 0.12 ms. The protocol has an improved PDR of 97.8%, surpassing Safety-RPL (91.5%) and the other models. Lastly, network lifetime is improved and extended to 3200 rounds compared to SEAMHR's (2100 rounds). From these results, it is evident that RK-EFCRP optimizes the balance of energy efficiency, security, and data reliability makes RK-EFCRP performing well for WSN based IoT applications. Rank based key allocation along with dynamic CH selection provides effective solutions to security holes and cuts down failure transmission while boosting overall network performance. This research facilitates the next steps towards intelligent and secure WSN based IoT systems with flexible and robust network structures.

The application of the Smart Grids with Artificial intelligence - AI has transformed the sector of management and demand forecasting dramatically. The objective of such research is to develop AI based prospective energy management system which involves advanced tool as LSTM for demand forecasting. The figure of merit stressed over the research in the literature has been data preprocessing, feature selection and classification techniques performed for improving the model performance. In order to provide an evidence of the success of this method in analyzing real time energy data, this is a case study of the use of Scikit Learn library. So, removing missing value, normalising the data, feature selection with RFE, classification with GBM. With the help of AI technology, the results suggest better accuracy of prediction and scalability, and is thus deemed a future of smart grid management.

Recently soft computing techniques and artificial intelligent techniques such as fuzzy logic Artificial Neural Network are widely used for variety of systems, namely, controller architecture, pattern learning, navigation etc. This paper describes an alternative hardware solution realized on FPGAs for autonomous mobile robot to avoid obstacles and plan path to reach the target. Pipelined based Artificial Neural Network based controller architecture is proposed using FPGA. The proposed ANN algorithm is able to perform the task for unstructured environment and diverse environments. Simulation and hardware implementation has been done by using Xilinx ISE simulator targeted on Virtex-IV kit. Experimental study shows that proposed approach obtains 357.5 MHz clock frequency which shows improved performance when compared with state-of-art techniques. Similarly, proposed approach shows a significant performance improvement in terms of power consumption.

Mobile robots are extensively used in numerous applications now a day's. Navigation of mobile robot is primary issue in robotic research field. For mobile robots to be effective, they must respond quickly and robustly, perform useful tasks in a multifaceted, dynamic, known and unknown environment. The aim of mobile robot navigation is to provide shortest and safest path while avoiding obstacles with the help of navigation technique such as neural network. MATLAB tool is used for the simulation and validation of algorithm. The Neural Networks are then implemented on a FPGA. Simulation and hardware implementation has been done by using Xilinx ISE simulator targeted on Virtex-IV kit. Experimental study shows that proposed approach obtains 357.5 MHz clock frequency which shows better performance when compared with state-of-art techniques.

Unmanned aerial vehicles (UAVs) are increasingly employed in diverse applications such as military operations, delivery services, traffic and architectural monitoring, and aerial surveillance. These drones often encounter challenges in navigating complex and dynamic environments, including irregular object shapes, occlusions, and varying contrasts with backgrounds. To overcome these obstacles, this study presents a novel hybrid approach that integrates Top-Down Attention with a Siamese Sparrow Neural Network (TDA-SSNN) for efficient and data-driven drone navigation. The methodology begins with sourcing input images from publicly available datasets, including those from Udacity's project. To enhance image quality, the Robust Generalized Maximum Blake-Zisserman Total Correntropy (RMB-ZTC) adaptive filter is employed for preprocessing. Feature selection is performed using a novel Gorilla Troops Optimizer with Artificial Hummingbird Optimization (GTO-AMO). For automatic drone navigation, the TDA-SSNN is utilized, enhanced by an advanced Sparrow Search Algorithm to optimize the performance of the Top-Down Attention-based Siamese Neural Network. The proposed approach achieves a remarkable accuracy of 99.6%.

Integration of solar energy management through the innovative use of explainable artificial intelligence (XAI) is changing the way solar power is utilized. This chapter is dedicated to explaining how XAI can be applied to solar energy systems to enhance their effectiveness, substantive, and options. Thus, in this chapter, the authors reveal how XAI can enhance the efficiency of overall solar energy management, such as the right time for investment in solar energy projects, energy prediction, and its tracking. Here in this study, different scenarios are illustrated along with its practical implementation in order to explicate the benefits of the XAI, which include the elevated confidence level of the users, cost efficiency, and the reliability of the model. In addition, the chapter presents problems with the use of XAI for solar energy, concerning data issues and integration issues and how these issues can be addressed.