Object location in indoor environments is challenging when there is no physical contact, a field of view, reflective materials, and an excess of obstacles. Several works propose using Radio Frequency Identification technology (RFID) and machine learning methods to develop location systems in those situations. However, using an object as a target class slows learning and prediction in large-scale environments. To circumvent such problems, we proposed a location system that uses hierarchical classification. We divided the environment into regions to reduce the classifier’s training and the number of predicted classes. To define the regions, we used clustering techniques, indicating which clustering technique achieves the best performance in the proposed scenario. The main contribution of this work is a high-precision location system for large-scale environments. The results showed the proposed system’s implantation in a real environment with 400 target objects with 5 cm of location precision. The accuracy for region detection is 99.36%, while for identifying the object is 99.94%. Additionally, with the proposed hierarchical approach, we showed a reduction of 38.16% and 58.39% in processing time and classifier model size.

The technological paradigm of the Internet of Things has attracted the attention of the market, industry, and scientific community. The possibility of integrating wireless sensor network (WSN) devices to the Internet has prompted the Internet Engineering Task Force (IETF) to specify new standards and protocols, such as the Routing Protocol for Low-Power and Lossy Networks (RPL), designed to find stable routing paths via links that have considerable losses. Among the routing metrics, the expected transmission count (ETX) is notable because its implementation in RPL helps choosing reliable paths. However, the rapid exhaustion of battery energy at bottleneck nodes remains a problem. In this context, this study introduces the network interface average power metric (NIAP), a new metric based on the estimated average power consumption of the network interface, which contributes not only to the choice of reliable paths but also to load balancing and lifetime increasing of a wireless sensor network. The results of several experiments conducted in a simulated environment demonstrate that NIAP is a promising alternative to ETX due to its simple implementation without modifications of the RPL standard.

A link state routing approach makes available detailed information about the connectivity and the topology found in a network. The OLSR (optimized link state routing) protocol is an optimization of the classical link state algorithm tailored to the requirements of a mobile wireless LAN. OLSR introduces an interesting concept, multipoint relays (MPRs), to mitigate the message overhead during the flooding process. The heuristic for MPR selection limits their number in the network and ensures that the overhead is as low as possible. However, there is no guarantee that OLSR finds the optimal path in terms of QoS requirements. Moreover, in QoS routing, if the same heuristic used in the standard OLSR protocol for MPR selection is applied, the good quality links may be hidden to other nodes in the network. We introduce two algorithms for MPR selection based on QoS measurements. Analysis, numerical evaluation and simulations are presented. We show that the QOLSR protocol with the second proposed algorithm for MPR selection (QOLSR/spl I.bar/MPR2) finds optimal widest paths on the known partial network topology and presents the best performance.

A quality-of-service (QoS) routing protocol is developed for mobile ad hoc networks. We perform the proposed QoS-based routing in the optimized link state routing (OLSR) protocol, introducing a more appropriate metric than the hop distance. In our simulations the QoS routing protocol produces better performance comparing with the best-effort OLSR protocol.