In this final project it is done a simple prototype, not complex in order not to overload the packet network or the computational part, of a sensor network, which communicating through wireless body area network (WBAN) are able to characterize daily activities. The nodes used were the Adafruit HUZZAH32 from the company Adafruit, it’s a System on Chip, which incorporates a Wi-Fi module that has been used for the communication between devices.
Firstly, an analysis has been done of the available system. On the one hand, an analysis of the devices and on the other hand a study of one possible characterization from data already collected.
In a second phase, the software of the devices has been modified to create the sensor network and to communicate with each other. For this purpose, the Wi-Fi module of the devices was used, after which, once they were connected, a series of experiments were carried out for different scenarios. With these experiments it has been possible to set thresholds for the development of the final classification algorithm.
Finally, in a third phase, the different tests have been exposed according to the algorithm performed in the second phase.
The results obtained have shown that it is a valid algorithm for the characterization of activities. In addition, an accelerometer has been included to differentiate more activities.
Animals have long been part of the human experience, serving multiple purposes throughout history, from food to companionship. In recent years, the therapeutic potential that offers the use of animals to help people overcome illness and/or mental disorders has been increasingly recognized, leading to more healthcare facilities providing Animal-Assisted-Interventions (AAIs) to their patients.
The steadily increasing popularity of AAIs programs is supported by the fact that they deliver health benefits to the patients. A growing literature gathers testimonials of veterinarians, psychologists and other pet-therapy enthusiasts about the effectiveness of AAIs programs for humans. In contrast, very few researchers have focused on the possible ill effects that AAIs programs have on the animals themselves.
Nowadays, the present lines of research that are trying to determine both positive and negative effects on the physical and mental well-being of the animals involved in AAIs are divided in two groups:
Non-invasive methodologies based on the interpretation of the body language of the animals. For instance, a dog’s wagging tail may mean different things depending on the speed of the wag, and whether the full tail or just the tip is wagging. Besides, dogs also use a range of what the renowned dog trainer Turid Rugaas refers to as “calming signals” that they use to defuse stressful situations. For example, a dog may lick her nose, sniff the ground, yawn, turn away, or stare in response to a stressful situation. The main drawback of these methodologies is the subjectivity of the observer.
Invasive methodologies based on medical procedures such as blood extractions, faces analysis or saliva analysis in order to measure certain hormones levels that could have correlation with the stress that could be suffering the animals during the AAIs. Despite of the fact of the objectivity of the results, due to the nature of these procedures, these interventions by themselves could provoke stress in the animals.
Thus, the aim of this Master’s Thesis is to design and develop an electronic wearable device to collect physiological and behavioral variables in dogs participating in the AAIs in order to extract stress patterns in different scenarios and therefore determine objectively the effects of the AAIs in the animal welfare. The data gathered will be analyzed by ethologists than can evaluate what is happening in the process of interaction of the therapy dog with the rest of the actors. This way, conclusions related to the dog state in the different stages of therapy could be obtained, allowing the modification of the routines to increase the dog’s quality of life.
It is worth mentioning that this project is being carried out in collaboration with the Escuela Técnica de Ingenieros de Telecomunicación and the animals and society chair at the Universidad Rey Juan Carlos, which will be in charge of the visualization and interpretation, respectively, of the data acquired by the system to be developed in this Master’s Thesis.
To achieve this goal, this Master’s Thesis has focused on the development of the electronic wearable device that will monitor the therapy dog. This development has covered both the design and hardware implementation of the three printed circuit boards that make up the device, as well as the software implementation of the drivers needed to control each sensor individually in addition to the application architecture at the user level.
Both software implementations are based on two existing design patterns that provide modularity to the system in order to incorporate new sensors to the device. Finally, in order to validate the design and implementation phases at hardware and software level, functional tests of the system have been carried out which have allowed conclusions to be drawn on the development of this project as well as to propose future lines to improve its current state.