Wireless sensor networks (WSNs) have great attention and applications in many fields in the recent years. One of the main challenges in using the WSNs is their energy consumptions. Although, many methods have been developed to overcome this problem, there are still some limitations facing the WSNs in this manner. In this paper, the proposed system introduces a new system that uses genetic algorithm (GA) for optimizing the node deployment, their locations and dividing the sensor nodes into two modes of operation that can minimize the energy consumption of the WSN. Suggested system has been applied for a simulated WSN used in the radiation discovering sites as a case of study. Its obtained results have proved its success to be applied in the practical sites.

The main goal of this research is to develop a novel optimum neuro-fuzzy system for diagnosis the complex and dynamic systems. .It has used the Particle Swarm Optimization (PSO) technique for training the Adaptive Neuro Fuzzy Inference System (ANFIS) off-line. The proposed system has applied for diagnosis the faults of two complex Photovoltaic (PV) systems. They are used to feed the power for lighting and pumps in a synchrotron building inside a radiation centre and the power for a house in a rural village. Its achieved results are compared with three ANFIS' diagnostic systems. They are: traditional neuro-fuzzy diagnostic systems, optimized ANFIS with genetic algorithm, optimized ANFIS with gradient descendent technique. The suggested system has proved its good performance to be applied for diagnose the complex dynamic systems.

No abstract