The ubiquity of smartphones and the growth of computing resources, such as connectivity, processing, portability, and power of sensing, have greatly changed people’s lives. Today, many smartphones contain a variety of powerful sensors, including motion, location, network, and direction sensors. Motion or inertial sensors (e.g., accelerometer), specifically, have been widely used to recognize users’ physical activities. This has opened doors for many different and interesting applications in several areas, such as health and transportation. In this perspective, this work provides a comprehensive, state of the art review of the current situation of human activity recognition (HAR) solutions in the context of inertial sensors in smartphones. This article begins by discussing the concepts of human activities along with the complete historical events, focused on smartphones, which shows the evolution of the area in the last two decades. Next, we present a detailed description of the HAR methodology, focusing on the presentation of the steps of HAR solutions in the context of inertial sensors. For each step, we cite the main references that use the best implementation practices suggested by the scientific community. Finally, we present the main results about HAR solutions from the perspective of the inertial sensors embedded in smartphones.

No abstract

The miniaturization of hardware components has lead to the development of Wireless Sensor Networks (WSN) and networked-applications over them. Meanwhile, middleware systems have also been proposed in order to both facilitating the development of these applications and providing common application services. The development of middleware for sensor networks, however, places new challenges to middleware developers due to the low availability of resources and processing capacity of the sensor nodes. In this context, this paper presents a middleware for WSN named Mires. Mires incorporates characteristics of message-oriented middleware by allowing applications communicate in a publish/subscribe way. In order to illustrate the proposed middleware, we implement an aggregation middleware service for an environment-monitoring application.

No abstract

The fulfillment of this Thesis would not have been possible without the contribution of a large number of persons. The first persons I am deeply indebted to are my wife Livia Soraya and my children"s Gabriel, Bruna and Luísa. While they did not contribute to this Thesis directly, but I would like to thank them for their support and love. I would also like to thank my parents, Clarice and José Ribamar, for their important support. I owe a big thank-you to my Thesis advisor, Djamel Sadok, who offered the opportunity to join his research team a few years ago. I must say that at that time, I was not really imagining the kind of experience I was about to embark on. I appreciated very much Djamel"s very pragmatic approach to networking. Djamel is also an inexhaustible source of networking references. Through his enthusiasm and unlimited support (time, ideas and experience), he helped me to complete this Thesis. In addition to that, this work contains the fruits of many and lengthy discussions regarding the present contributions with Djamel. My sincere thanks also go to Professor Judith Kelner for giving me as well as to my family a great deal of support when we moved to Recife. She was instrumental in my participation in the GPRT group. I learned a lot from her valuable experience. I am also thankful for the excellent example she has provided as a successful researcher and Professor. The third person I would like to thank is my Thesis co-advisor Eduardo Souto. Souto has been a great friend from Manaus, where we worked together in the University"s Data Processing Center (CPD). He was key to my decision for choosing Recife as the place to do my Doctorate studies. I learned a lot from the references he pointed me to and from the many discussions we had. We collaborated on a lot of problems, especially about the design of the OADS Miner.

No abstract

Smartphones have emerged as a revolutionary technology for monitoring everyday life, and they have played an important role in Human Activity Recognition (HAR) due to its ubiquity. The sensors embedded in these devices allows recognizing human behaviors using machine learning techniques. However, not all solutions are feasible for implementation in smartphones, mainly because of its high computational cost. In this context, the proposed method, called HAR-SR, introduces information theory quantifiers as new features extracted from sensors data to create simple activity classification models, increasing in this way the efficiency in terms of computational cost. Three public databases (SHOAIB, UCI, WISDM) are used in the evaluation process. The results have shown that HAR-SR can classify activities with 93% accuracy when using a leave-one-subject-out cross-validation procedure (LOSO).

No abstract