Nowadays, people are starting to have much interest in investing in the stock market and cryptocurrencies to profit. However, at the beginning of 2022, many fraudulent investments, such as illegal trading robots, are persuaded by big profits. People cause a significant loss when trading with the wrong strategies and decisions. Therefore, we need a system that can help simulate trading using technical indicator analysis and machine learning decision trees. Tests carry on several JCI stocks and cryptocurrencies. The simulation result data display as table data and graphs. As a result, the benefits obtained from trading simulations with machine learning decision trees are more than using only technical indicators.
Cluster Head (CH) selection is a crucial process in clustered Wireless Sensor Networks (WSNs) because it directly affects energy balance and network lifetime. However, CH selection is an NP-hard optimization problem, and many metaheuristic-based methods suffer from limited search diversity and premature convergence, leading to uneven energy dissipation. This paper formulates CH selection as a multi-criteria energy-aware optimization problem and proposes an Enhanced Secretary Bird Optimization Algorithm (ESBOA). The proposed ESBOA improves the original Secretary Bird Optimization Algorithm by integrating logistic chaotic map-based population initialization to enhance early-stage exploration and an iterative local search mechanism to strengthen solution refinement in later iterations. A multi-criteria fitness function considering residual energy, distance to the base station, and node degree explicitly guides the optimization toward energy-efficient clustering. The proposed method is implemented in a Python 3.11.9-based simulation framework using a first-order radio energy model and evaluated against standard SBOA, Crested Porcupine Optimization (CPO), and Dung Beetle Optimization (DBO). Simulation results demonstrate that ESBOA preserves more alive nodes, maintains higher residual energy, delivers more cumulative packets to the base station, and extends network lifetime, achieving approximately 3–13% improvement in last node death (LND) compared with the standard SBOA.
1 October 2025 in Bulletin of Electrical Engineering and Informatics
In robotic operation, an autonomous operation for a mobile robot is needed to operate smoothly, hence, a control system is needed. Numerous architectures for robotics control systems have been put forth. Regretfully, creating a control system architecture is very challenging and occasionally results in inaccuracy in control. An alternative to conventional mobile robot control has emerged to address this issue: behavior-based control system architectures. This paper addresses the behavior of an autonomous mobile robot (AMR) control system in an outdoor rescue operation. The AMR behavior will be governed by the neural network methods, which are a computational intelligence to generate a dependable control algorithm. The architecture is used to coordinate behavior, especially to localize the victims, and for speed control to find the victim location with fast timing. In localization parameters to find the victim in the disaster area, this neural network adaptive model has the smallest error, which is 3.27, compared with other models such as free space model 43.46, and empirical model 4.735. While in robot speed parameter has a low error value, which is 1.47. With this small error, we can conclude that the neural network adaptive behaviour control architecture model for rescue mobile robot operation has been successfully developed.