Localization of access points has become an important research problem due to the wide range of applications it addresses such as dismantling critical security threats caused by rogue access points or optimizing wireless coverage of access points within a service area. Existing proposed solutions have mostly relied on theoretical hypotheses or computer simulation to demonstrate the efficiency of their methods. The techniques that rely on estimating the distance using samples of the received signal strength usually assume prior knowledge of the signal propagation characteristics of the indoor environment in hand and tend to take a relatively large number of uniformly distributed random samples. This paper presents an efficient and practical collaborative approach to detect the location of an access point in an indoor environment without any prior knowledge of the environment. The proposed approach comprises a swarm of wirelessly connected mobile robots that collaboratively and autonomously collect a relatively small number of non-uniformly distributed random samples of the access point’s received signal strength. These samples are used to efficiently and accurately estimate the location of the access point. The experimental testing verified that the proposed approach can identify the location of the access point in an accurate and efficient manner.

Node clustering in wireless sensor networks helps in extending the network life time by reducing the nodes' communication energy and balancing their remaining energy. This paper presents a new genetic-based approach that improves the performance of the LEACH clustering protocol used in wireless sensor networks. The proposed approach utilizes the mobility feature of sensor nodes in order to reduce the communication distances between the cluster heads and the base station. In each round, new locations of the cluster heads are determined using a genetic algorithm. The simulation results demonstrate that the proposed approach outperforms LEACH in terms of network lifetime and average remaining energy.

In this paper, a new approach for detecting surviving humans in destructed environments using a simulated autonomous robot is proposed. The proposed system uses a passive infrared sensor (PIR) in order to detect the existence of living humans and a low-cost camera in order to acquire a snapshot of the scene as needed. Having detected a sign of a living human, the PIR sensor triggers the camera to acquire an image of the scene. The image is fed into a feed-forward neural network, trained to detect the existence of a human body or part of it within an obstructed environment. This approach requires a relatively small number of images to be acquired and processed during the rescue operation. This way, the real-time cost of image processing and data transmission is considerably reduced. The results of the conducted experiments demonstrated that this system has the potential to achieve high performance in detecting living humans in obstructed environments relatively quickly and cost-effectively. The detection accuracy of the system ranged between 79% and 91% depending on a number of factors such as the body position, the light intensity of the scene, and the relative color matching between the body and the surrounding environment.