Human activity recognition by inertial signals obtained from a smartphone

Human Activity Recognition (HAR) is an emerging research field with the aim to identify the actions carried out by a person given a set of observations and the surrounding environment. The wide growth in this research field inside the scientific community is mainly explained by the high number of applications that are arising in the last years. A great part of the most promising applications are related to the healthcare field, where it is possible to track the mobility of patients with motor dysfunction as also the physical activity in patients with cardiovascular risk. Until a few years ago, by using distinct kind of sensors, a patient follow-up was possible. However, far from being a long-term solution and with the smartphone irruption, that monitoring can be achieved in a non-invasive way by using the embedded smartphone���s sensors. For these reasons this Final Degree Project arises with the main target to evaluate new feature extraction techniques in order to carry out an activity and user recognition, and also an activity segmentation. The recognition is done thanks to the inertial signals integration obtained by two widespread sensors in the greater part of smartphones: accelerometer and gyroscope. In particular, six different activities are evaluated walking, walking-upstairs, walking-downstairs, sitting, standing and lying. Furthermore, a segmentation task is carried out taking into account the activities performed by thirty users. This can be done by using Hidden Markov Models and also a set of tools tested satisfactory in speech recognition: HTK (Hidden Markov Model Toolkit).

Human activity recognition by inertial signals obtained from a smartphone

El Reconocimiento de Actividades Humanas es un ��rea de investigaci��n emergente, cuyo objetivo principal es identificar las acciones realizadas por un sujeto analizando las se��ales obtenidas a partir de unos sensores. El r��pido crecimiento de este ��rea de investigaci��n dentro de la comunidad cient��fica se explica, en parte, por el elevado n��mero de aplicaciones que est��n surgiendo en los ��ltimos a��os. Gran parte de las aplicaciones m��s prometedoras se encuentran en el campo de la salud, donde se puede hacer un seguimiento del nivel de movilidad de pacientes con trastornos motores, as�� como monitorizar el nivel de actividad f��sica en pacientes con riesgo cardiovascular. Hasta hace unos a��os, mediante el uso de distintos tipos de sensores se pod��a hacer un seguimiento del paciente. Sin embargo, lejos de ser una soluci��n a largo plazo y gracias a la irrupci��n del tel��fono inteligente, este seguimiento se puede hacer de una manera menos invasiva, haciendo uso de la gran variedad de sensores integrados en este tipo de dispositivos. En este contexto nace este Trabajo de Fin de Grado, cuyo principal objetivo es evaluar nuevas t��cnicas de extracci��n de caracter��sticas para llevar a cabo un reconocimiento de actividades y usuarios as�� como una segmentaci��n de aquellas. Este reconocimiento se hace posible mediante la integraci��n de se��ales inerciales obtenidas por dos sensores presentes en la gran mayor��a de tel��fonos inteligentes: aceler��metro y gir��scopo. Concretamente, se eval��an seis tipos de actividades realizadas por treinta usuarios: andar, subir escaleras, bajar escaleras, estar sentado, estar de pie y estar tumbado. Adem��s y de forma paralela, se realiza una segmentaci��n temporal de los distintos tipos de actividades realizadas por dichos usuarios. Todo ello se llevar�� a cabo haciendo uso de los Modelos Ocultos de Markov, as�� como de un conjunto de herramientas probadas satisfactoriamente en reconocimiento del habla: HTK (Hidden Markov Model Toolkit).

Modelado de sistemas de inteligencia ambiental para el entrenamiento de las cualidades f��sicas

En un ejercicio no extenuante la frecuencia card��aca (FC) guarda una relaci��n lineal con el consumo m��ximo de ox��geno (V O2max) y se suele usar como uno de los par��metros de referencia para cuantificar la capacidad del sistema cardiovascular. Normalmente la frecuencia card��aca puede remplazar el porcentaje de V O2max en las prescripciones b��sicas de ejercicio para la mejora de la resistencia aer��bica. Para obtener los mejores resultados en la mejora de la resistencia aer��bica, el entrenamiento de los individuos se debe hacer a una frecuencia card��aca suficientemente alta, para que el trabajo sea de predominio din��mico con la fosforilaci��n oxidativa como fuente energ��tica primaria, pero no tan elevada que pueda suponer un riesgo de infarto de miocardio para el sujeto que se est�� entrenando. Los programas de entrenamiento de base m��nima y de base ��ptima, con ejercicios de estiramientos para prevenir lesiones, son algunos de los programas m��s adecuados para el entrenamiento de la resistencia aer��bica porque maximizan los beneficios y minimizan los riesgos para el sistema cardiovascular durante las sesiones de entrenamiento. En esta tesis, se ha definido un modelo funcional para sistemas de inteligencia ambiental capaz de monitorizar, evaluar y entrenar las cualidades f��sicas que ha sido validado cuando la cualidad f��sica es la resistencia aer��bica. El modelo se ha implementado en una aplicaci��n Android utilizando la camiseta inteligente ���GOW running��� de la empresa Weartech. El sistema se ha comparado en el Laboratorio de Fisiolog��a del Esfuerzo (LFE) de la Universidad Polit��cnica de Madrid (UPM) durante la realizaci��n de pruebas de esfuerzo. Adem��s se ha evaluado un sistema de guiado con voz para los entrenamientos de base m��nima y de base ��ptima. Tambi��n el desarrollo del software ha sido validado. Con el uso de cuestionarios sobre las experiencias de los usuarios utilizando la aplicaci��n se ha evaluado el atractivo de la misma. Por otro lado se ha definido una nueva metodolog��a y nuevos tipos de cuestionarios dise��ados para evaluar la utilidad que los usuarios asignan al uso de un sistema de guiado por voz. Los resultados obtenidos confirman la validez del modelo. Se ha obtenido una alta concordancia entre las medidas de FC hecha por la aplicaci��n Android y el LFE. Tambi��n ha resultado que los m��todos de estimaci��n del VO2max de los dos sistemas pueden ser intercambiables. Todos los usuarios que utilizaron el sistema de guiado por voz para entrenamientos de 10 base m��nima y de base ��ptimas de la resistencia aer��bica consiguieron llevar a cabo las sesiones de entrenamientos con un 95% de ��xito considerando unos m��rgenes de error de un 10% de la frecuencia card��aca m��xima te��rica. La aplicaci��n fue atractiva para los usuarios y hubo tambi��n una aceptaci��n del sistema de guiado por voz. Se ha obtenido una evaluaci��n psicol��gica positiva de la satisfacci��n de los usuarios que interactuaron con el sistema. En conclusi��n, se ha demostrado que es posible desarrollar sistemas de Inteligencia Ambiental en dispositivos m��viles para la mejora de la salud. El modelo definido en la tesis es el primero modelo funcional te��rico de referencia para el desarrollo de este tipo de aplicaciones. Posteriores estudios se realizar��n con el objetivo de extender dicho modelo para las dem��s cualidades f��sicas que suponen modelos fisiol��gicos m��s complejos como por ejemplo la flexibilidad. Abstract In a non-strenuous exercise, the heart rate (HR) shows a linear relationship with the maximum volume of oxygen consumption (V O2max) and serves as an indicator of performance of the cardiovascular system. The heart rate replaces the %V O2max in exercise program prescription to improve aerobic endurance. In order to achieve an optimal effect during endurance training, the athlete needs to work out at a heart rate high enough to trigger the aerobic metabolism, while avoiding the high heart rates that bring along significant risks of myocardial infarction. The minimal and optimal base training programs, followed by stretching exercises to prevent injuries, are adequate programs to maximize benefits and minimize health risks for the cardiovascular system during single session training. In this thesis, we have defined an ambient intelligence system functional model that monitors, evaluates and trains physical qualities, and it has been validated for aerobic endurance. It is based on the Android System and the ���GOW Running��� smart shirt. The system has been evaluated during functional assessment stress testing of aerobic endurance in the Stress Physiology Laboratory (SPL) of the Technical University of Madrid (UPM). Furthermore, a voice system, designed to guide the user through minimal and optimal base training programs, has been evaluated. Also the software development has been evaluated. By means of user experience questionnaires, we have rated the attractiveness of the android application. Moreover, we have defined a methodology and a new kind of questionnaires in order to assess the user experience with the audio exercise guide system. The results obtained confirm the model. We have a high similarity between HR measurements made of our system and the one used by SPL. We have also a high correlation between the VO2max estimations of our system and the SPL system. All users, that tried the voice guidance system for minimal and optimal base training programs, were able to perform the 95% of the training session with an error lower than the 10% of theoretical maximum heart rate. The application appeared attractive to the users, and it has also been proven that the voice guidance system was useful. As result we obtained a positive evaluation of the users' satisfaction while they interacted with the system. In conclusion, it has been demonstrated that is possible to develop mobile Ambient Intelligence applications for the improvement of healthy lifestyle. AmIRTEM model is the first theoretical reference functional model for the design of this kind of applications. Further studies will be realized in order to extend the AmIRTEM model to other physical qualities whose physiological models are more complex than the aerobic endurance.

Analyzing Business Models for Mobile Augmented Reality

Nowadays, a wide offer of mobile augmented reality (mAR) applications is available at the market, and the user base of mobile AR-capable devices -smartphones- is rapidly increasing. Nevertheless, likewise to what happens in other mobile segments, business models to put mAR in value are not clearly defined yet. In this paper, we focus on sketching the big picture of the commercial offer of mAR applications, in order to inspire a posterior analysis of business models that may successfully support the evolution of mAR. We have gathered more than 400 mAR applications from Android Market, and analyzed the offer as a whole, taking into account some technology aspects, pricing schemes and user adoption factors. Results show, for example, that application providers are not expecting to generate revenues per direct download, although they are producing high-quality applications, well rated by the users.

Soluci��n Abierta de Barrido y Pulsaci��n en Dispositivos M��viles Accesible para Personas con DFiscapacidad F��sica

Este trabajo de investigaci��n tiene como objetivo esencial ofrecer una soluci��n de accesibilidad a los dispositivos m��viles t��ctiles para personas con discapacidad f��sica con afecci��n en los miembros superiores. El dise��o, desarrollo y validaci��n de la soluci��n detallada est�� basado en una plataforma abierta y de bajo coste como Android que, mediante la interconexi��n de conmutadores comerciales y el uso de un sistema de barrido con realimentaci��n por voz sintetizada, permite al usuario acceder a todas las funciones b��sicas de la telefon��a m��vil. El an��lisis de los requisitos de usuario es un eje central de este trabajo para lo cual se ha contado con la participaci��n de la Asociaci��n de Lesionados Medulares y Grandes Discapacitados F��sicos (ASPAYM), de la Asociaci��n de Padres de Alumnos Minusv��lidos (APAM) y del Centro de Referencia Estatal de Atenci��n al Da��o Cerebral (CEADAC). El sistema resultante preserva las expectativas de autonom��a personal y privacidad demandadas.

Redes y servicios ubicuos para Internet de las Cosas en dispositivos llevables

En las ��ltimas d��cadas se han producido importantes avances tecnol��gicos, lo que ha producido un crecimiento importante de las Redes Inal��mbricas de Sensores (RIS), conocidas en ingl��s como Wireless Sensor Networks (WSN). Estas redes est��n formadas por un conjunto de peque��os nodos o tambi��n, conocidos como motas, compuestos por diversos tipos de sensores. Las Redes Inal��mbricas de Sensores pueden resultar muy ��tiles en entornos donde el despliegue de redes cableadas, formadas por ordenadores, encaminadores u otros dispositivos de red no sea posible. Sin embargo, este tipo de redes presentan una serie de carencias o problemas que dificultan, en ocasiones, su implementaci��n y despliegue. Este Proyecto Fin de Carrera tiene como principales objetivos: dise��ar e implementar un agente que haga uso de la tecnolog��a Bluetooth para que se pueda comunicar tanto con la arquitectura orientada a servicios, v��a radio, como con el m��dulo Bioharness para obtener par��metros fisiol��gicos; ofrecer una serie de servicios simples a la Red Inal��mbrica de Sensores; dise��ar un algoritmo para un sistema de alarmas; realizar e implementar una pasarela entre protocolos que usen el est��ndar IEEE802.15.4 (ZigBee) y el est��ndar IEEE802.15.1 de la Tecnolog��a Bluetooth. Por ��ltimo, implementar una aplicaci��n Android para el reloj WiMM y que este pueda recibir alarmas en tiempo real a trav��s del la Interfaz Bluetooth. Para lograr estos objetivos, en primer lugar realizaremos un estudio del Estado del Arte de las Redes Inal��mbricas de Sensores, con el fin de estudiar su arquitectura, el est��ndar Bluetooth y los dispositivos Bluetooth que se han utilizado en este Proyecto. Seguidamente, describiremos detalladamente el firmware iWRAP versi��n 4, centr��ndonos en sus modos de operaci��n, comandos AT y posibles errores que puedan ocurrir. A continuaci��n, se describir�� la arquitectura y la especificaci��n nSOM, para adentrarnos en la arquitectura orientada a servicios. Por ��ltimo, ejecutaremos la fase de validaci��n del sistema y se analizar��n los resultados obtenidos durante la fase de pruebas. ABSTRACT In last decades there have been significant advances in technology, which has resulted in important growth of Wireless Sensor Networks (WSN). These networks consist of a small set of nodes, also known as spots; equipped with various types of sensors. Wireless Sensor Networks can be very useful in environments where deployment of wired networks, formed by computers, routers or other network devices is not possible. However, these networks have a number of shortcomings or challenges to, sometimes, their implementation and deployment. The main objectives of this Final Project are to design and implement an agent that makes use of Bluetooth technology so you can communicate with both the service-oriented architecture, via radio, as with Bioharness module for physiological parameters; offer simple services to Wireless Sensor Network, designing an algorithm for an alarm system, make and implement a gateway between protocols using the standard IEEE802.15.4 (ZigBee) and IEEE802.15.1 standard Bluetooth Technology. Finally, implement an Android application for WiMM watch that can receive real-time alerts through the Bluetooth interface. In order to achieve these objectives, firstly we are going to carry out a study of the State of the Art in Wireless Sensor Network, where we study the architecture, the Bluetooth standard and Bluetooth devices that have been used in this project. Then, we will describe in detail the iWRAP firmware version 4, focusing on their operation modes, AT commands and errors that may occur. Therefore, we will describe the architecture and specification nSOM, to enter into the service-oriented architecture. Finally, we will execute the phase of validation of the system in a real application scenario, analyzing the results obtained during the testing phase.

Dise��o y fabricaci��n de dispositivos basados en cristal l��quido polim��rico

Esta tesis se centra en el estudio y desarrollo de dispositivos de aplicaci��n basados en cristal l��quido polim��rico. Las propiedades de los cristales l��quidos los hacen interesantes para su uso en el desarrollo de dispositivos de seguridad para autenticaci��n de productos y marcas, y detecci��n y prevenci��n de falsificaciones. Asimismo, pueden ser muy ��tiles para fabricar dispositivos basados en CLs dispersos en pol��mero, los cuales tienen a su vez m��ltiples aplicaciones. La orientaci��n de las mol��culas de cristal l��quido y la birrefringencia son las dos caracter��sticas principales que afectan a las propiedades de estos dispositivos. Un dispositivo de cristal l��quido est��ndar consiste en un s��ndwich formado por dos sustratos de vidrio transparente, dotados con electrodo de ITO (Indium Tin Oxide) en su superficie interna, que confinan el cristal l��quido en su interior. En la primera parte de esta tesis se describen las caracter��sticas m��s importantes que describen una c��lula de cristal l��quido. Esta introducci��n b��sica en necesaria para la correcta comprensi��n de los cap��tulos posteriores en los que se detalla el desarrollo concreto de los dispositivos desarrollados en la investigaci��n llevada a cabo. Por ejemplo, en el caso de los dispositivos de seguridad se han eliminado los sustratos de vidrio (en la ��ltima fase de su desarrollo) para conseguir dispositivos flexibles. En la segunda parte de la tesis se incluye la descripci��n completa de los dispositivos fabricados, as�� como de los protocolos de fabricaci��n seguidos y dise��ados espec��ficamente para ello. Tambi��n se detallan en esta parte los resultados obtenidos, as�� como las propiedades ��pticas y electro��pticas en cada caso, y el/los equipos de caracterizaci��n utilizados. Utilizando cristal l��quido nem��tico y colorante dicroico, se han desarrollado dispositivos que contienen m��ltiples im��genes latentes en cada cara del mismo. Utilizando distintas t��cnicas de alineamiento se consigue crear cualquier tipo de motivo latente, ya sean s��mbolos sencillos, figuras, logotipos o incluso im��genes con escala de gris. Cuanto m��s complejo es el dispositivo, mayor es la dificultad para reproducirlo en una eventual falsificaci��n. Para visualizar e identificar los motivos es necesario emplear luz polarizada, por ejemplo, con la ayuda de un sencillo polarizador lineal. Dependiendo de si el polarizador est�� colocado delante del dispositivo o detr��s del ��l, se mostrar��n las im��genes generadas en una u otra cara. Este efecto es posible gracias al colorante dicroico a��adido al CL, a la orientaci��n inducida sobre las mol��culas, y a la estructura de twist utilizada en los dispositivos. En realidad, para ver el efecto de los dispositivos no es necesario el uso de un polarizador, basta con el reflejo de una superficie diel��trica (percialmente polarizado), o la luz emitida por la pantalla de dispositivos de consumo comunes como un televisor LCD, un monitor de ordenador o un ���smartphone���. Por otro lado, utilizando una mezcla entre un CL nem��tico polim��rico y un CL nem��tico no polim��rico es posible fabricar dispositivos LCPC (Liquid Crystal Polymer Composite) con propiedades electro��pticas muy interesantes, que funcionan a tensiones de conmutaci��n bajas. El CL polim��rico conforma una estructura de red en el interior del s��ndwich que mantiene confinado al CL nem��tico en peque��os microdominios. Se han fabricado dispositivos LCPC con conmutaci��n inversa utilizando tanto alineamiento homog��neo como homeotr��pico. Debido a que tanto la estructura de CL polim��rico como el CL nem��tico que rellena los microdominios est��n orientados en una misma direcci��n de alineamiento preinducida, la luz dispersada por el dispositivo se encuentra polarizada. La direcci��n de polarizaci��n coincide con la direcci��n de alineamiento. La innovaci��n aportada por esta investigaci��n: un nuevo dispositivo LCPC inverso de respuesta ultrar��pida y polarizada basado en la mezcla de dos CL nem��ticos y, un dispositivo de seguridad y autenticaci��n, patentado internacionalmente, basado en CL nem��ticos dopados con colorante dicroico. Abstract This thesis is centered on the availability to use polymerizable liquid crystals to develop non-display application LC devices. Liquid crystal properties make them useful for the development of security devices in applications of authentication and detection of fakes, and also to achieve polymer dispersed LC devices to be used for different applications that will be studied here. Induced orientation of liquid crystal molecules and birefringence are the two main properties used in these devices. A standard liquid crystal device is a sandwich consisting of two parallel glass substrates carrying a thin transparent ITO (Indium���Tin���Oxide) electrode on their inner surfaces with the liquid crystal in the middle. The first part of this thesis will describe the most important parameters describing a liquid crystal cell. This basis is necessary for the understanding of later chapters where models of the liquid crystal devices will be discussed and developed. In the case of security devices the standard structure of an LC device has been modified by eliminating the glass substrates in order to achieve plastic and flexible devices. The second part of the thesis includes a detailed description of the devices achieved and the manufacturing protocols that have been developed ad-hoc. The optical and electrooptical properties and the characterization equipment are described here as well. Employing nematic liquid crystal and dichroic colorants, we have developed devices that show, with the aid of a polarizer, multiple images on each side of the device. By different alignment techniques it is possible to create any kind of symbols, drawings or motifs with a grayscale; the more complex the created device is, the more difficult is to fake it. To identify the motifs it is necessary to use polarized light. Depending on whether the polarizer is located in front of the LC cell or behind it, different motifs from one or the other substrate are shown. The effect arises from the dopant color dye added to the liquid crystal, the induced orientation and the twist structure. In practice, a grazing reflection on a dielectric surface is polarized enough to see the effect. Any LC flat panel display (LCD TV, computer, mobile phone) can obviously be used as backlight as well. On the other hand, by using a mixture of polymerizable and non-polymerizable nematics liquid crystals it is also possible to achieve LCPC (Liquid Crystal Polymer Composite) devices that show really interesting electrooptical characteristics using low switching voltages. Polymerizable LC creates a hollow structure inside the sandwich glass cell that keep nematics liquid crystal confined creating microdomains. Homogeneous and homeotropic alignments have been used to develop inverse switching mode LCPCs. Due to the double LC oriented structure, the outgoing scattered light from these devices is already polarized. The polarization axis coincides with LC molecules director, the alignment direction promoted. The novelties derived from the investigation presented here, new ultrafast inverse LCPC with polarized outgoing scattered light based on oriented nematic LC mixture, and an internationally patented security and authentication device based on nematics (doped with dichroic dye) oriented polymerizable LC.

Towards a fuzzy-based multi-classifier selection module for activity recognition applications

Performing activity recognition using the information provided by the different sensors embedded in a smartphone face limitations due to the capabilities of those devices when the computations are carried out in the terminal. In this work a fuzzy inference module is implemented in order to decide which classifier is the most appropriate to be used at a specific moment regarding the application requirements and the device context characterized by its battery level, available memory and CPU load. The set of classifiers that is considered is composed of Decision Tables and Trees that have been trained using different number of sensors and features. In addition, some classifiers perform activity recognition regardless of the on-body device position and others rely on the previous recognition of that position to use a classifier that is trained with measurements gathered with the mobile placed on that specific position. The modules implemented show that an evaluation of the classifiers allows sorting them so the fuzzy inference module can choose periodically the one that best suits the device context and application requirements.

Integrated luminescent chemical microsensors based on GaN LEDs for security applications using smartphones

Development of PCB-integrateable microsensors for monitoring chemical species is a goal in areas such as lab-on-a-chip analytical devices, diagnostics medicine and electronics for hand-held instruments where the device size is a major issue. Cellular phones have pervaded the world inhabitants and their usefulness has dramatically increased with the introduction of smartphones due to a combination of amazing processing power in a confined space, geolocalization and manifold telecommunication features. Therefore, a number of physical and chemical sensors that add value to the terminal for health monitoring, personal safety (at home, at work) and, eventually, national security have started to be developed, capitalizing also on the huge number of circulating cell phones. The chemical sensor-enabled ���super��� smartphone provides a unique (bio)sensing platform for monitoring airborne or waterborne hazardous chemicals or microorganisms for both single user and crowdsourcing security applications. Some of the latest ones are illustrated by a few examples. Moreover, we have recently achieved for the first time (covalent) functionalization of p- and n-GaN semiconductor surfaces with tuneable luminescent indicator dyes of the Ru-polypyridyl family, as a key step in the development of innovative microsensors for smartphone applications. Chemical ���sensoring��� of GaN-based blue LED chips with those indicators has also been achieved by plasma treatment of their surface, and the micrometer-sized devices have been tested to monitor O2 in the gas phase to show their full functionality. Novel strategies to enhance the sensor sensitivity such as changing the length and nature of the siloxane buffer layer are discussed in this paper.

Architecture for Text Sign Localization and Recognition

This paper describes a low complexity strategy for detecting and recognizing text signs automatically. Traditional approaches use large image algorithms for detecting the text sign, followed by the application of an Optical Character Recognition (OCR) algorithm in the previously identified areas. This paper proposes a new architecture that applies the OCR to a whole lightly treated image and then carries out the text detection process of the OCR output. The strategy presented in this paper significantly reduces the processing time required for text localization in an image, while guaranteeing a high recognition rate. This strategy will facilitate the incorporation of video processing-based applications into the automatic detection of text sign similar to that of a smartphone. These applications will increase the autonomy of visually impaired people in their daily life.

Mars: a personalised mobile activity recognition system

Mobile activity recognition focuses on inferring the current activities of a mobile user by leveraging the sensory data that is available on today���s smart phones. The state of the art in mobile activity recognition uses traditional classification learning techniques. Thus, the learning process typically involves: i) collection of labelled sensory data that is transferred and collated in a centralised repository; ii) model building where the classification model is trained and tested using the collected data; iii) a model deployment stage where the learnt model is deployed on-board a mobile device for identifying activities based on new sensory data. In this paper, we demonstrate the Mobile Activity Recognition System (MARS) where for the first time the model is built and continuously updated on-board the mobile device itself using data stream mining. The advantages of the on-board approach are that it allows model personalisation and increased privacy as the data is not sent to any external site. Furthermore, when the user or its activity profile changes MARS enables promptly adaptation. MARS has been implemented on the Android platform to demonstrate that it can achieve accurate mobile activity recognition. Moreover, we can show in practise that MARS quickly adapts to user profile changes while at the same time being scalable and efficient in terms of consumption of the device resources.

An Internet of Things approach for managing smart services provided by wearable devices.

The Internet of Things (IoT) is growing at a fast pace with new devices getting connected all the time. A new emerging group of these devices are the wearable devices, and Wireless Sensor Networks are a good way to integrate them in the IoT concept and bring new experiences to the daily life activities. In this paper we present an everyday life application involving a WSN as the base of a novel context-awareness sports scenario where physiological parameters are measured and sent to the WSN by wearable devices. Applications with several hardware components introduce the problem of heterogeneity in the network. In order to integrate different hardware platforms and to introduce a service-oriented semantic middleware solution into a single application, we propose the use of an Enterprise Service Bus (ESB) as a bridge for guaranteeing interoperability and integration of the different environments, thus introducing a semantic added value needed in the world of IoT-based systems. This approach places all the data acquired (e.g., via Internet data access) at application developers disposal, opening the system to new user applications. The user can then access the data through a wide variety of devices (smartphones, tablets, computers) and Operating Systems (Android, iOS, Windows, Linux, etc.).

System supporting public transport based on geolocation

El prop��sito de este proyecto de fin de Grado es el estudio y desarrollo de una aplicaci��n basada en Android que proporcionar�� soporte y atenci��n a los servicios de transporte p��blico existentes en Cracovia, Polonia. La principal funcionalidad del sistema ser�� consultar la posici��n de un determinado autob��s o tranv��a y mostrar su ubicaci��n con exactitud. Para lograr esto, necesitaremos tres fases de desarrollo. En primer lugar, deberemos implementar un sistema que obtenga las coordenadas geogr��ficas de los veh��culos de transporte p��blico en cada instante. A continuaci��n, tendremos que registrar todos estos datos y almacenarlos en una base de datos en un servidor web. Por ��ltimo, desarrollaremos un sistema cliente que realice consultas a tiempo real sobre estos datos almacenados, obteniendo la posici��n para una l��nea determinada y mostrando su ubicaci��n con un marcador en el mapa. Para hacer el seguimiento de los veh��culos, ser��a necesario tener acceso a una API p��blica que nos proporcionase la posici��n registrada por los GPS que integran cada uno de ellos. Como esta API no existe actualmente para los servicios de autob��s, y para los tranv��as es de uso meramente privado, desarrollaremos una segunda aplicaci��n en Android que har�� las funciones del lado servidor. En ella podremos elegir mediante una simple interfaz el n��mero de l��nea y un c��digo espec��fico que identificar�� a cada veh��culo en particular (e.g. podemos tener 6 tranv��as recorriendo la red al mismo tiempo para la l��nea 24). Esta aplicaci��n obtendr�� las coordenadas geogr��ficas del tel��fono m��vil, lo cual incluye latitud, longitud y orientaci��n a trav��s del proveedor GPS. De este modo, podremos realizar una simulaci��n de como el sistema funcionar�� a tiempo real utilizando la aplicaci��n servidora desde dentro de un tranv��a o autob��s y, al mismo tiempo, utilizando la aplicaci��n cliente haciendo peticiones para mostrar la informaci��n de dicho tranv��a. El cliente, adem��s, podr�� consultar la ruta de cualquier l��nea sin necesidad de tener acceso a Internet. Almacenaremos las rutas y paradas de cada l��nea en la memoria del tel��fono m��vil utilizando ficheros XML debido al poco espacio que ocupan y a lo ��til que resulta poder consultar un trayecto en cualquier momento, independientemente del acceso a la red. El usuario tambi��n podr�� consultar las tablas de horarios oficiales para cada l��nea. Aunque en este caso si ser�� necesaria una conexi��n a Internet debido a que se realizar�� a trav��s de la web oficial de MPK. Para almacenar todas las coordenadas de cada veh��culo en cada instante necesitaremos crear una base de datos en un servidor. Esto se resolver�� mediante el uso de MYSQL y PHP. Se enviar��n peticiones de tipo GET y POST a los servicios PHP que se encargar��n de traducir y realizar la consulta correspondiente a la base de datos MYSQL. Por ��ltimo, gracias a todos los datos recogidos relativos a la posici��n de los veh��culos de transporte p��blico, podremos realizar algunas tareas de an��lisis. Comparando la hora exacta a la que los veh��culos pasaron por cada parada y la hora a la que deber��an haber pasado seg��n los horarios oficiales, podremos descubrir fallos en estos. Seremos capaces de determinar si es un error puntual debido a factores externos (atascos, aver��as,���) o si por el contrario, es algo que ocurre muy a menudo y se deber��a corregir el horario oficial. ABSTRACT The aim of this final Project (for University) is to develop an Android application thatwill provide support and feedback to the public transport services in Krakow. The main functionality of the system will be to track the position of a desired bus or tram line, and display its position on the map. To achieve this, we will need 3 stages: the first one will be to implement a system that sends the geographical position of the public transport vehicles, the second one will be to collect this data in a web server, and the last one will be to get the last location registered for the desired line and display it on the map. For tracking the vehicles, we would need to have access to a public API that should be connected with each bus/tram GPS. As this doesn���t exist in Krakow or at least is not available for public use, we will develop a second android application that will do the server side job. We will be able to choose in a simple interface the line number and a code letter to identify each vehicle (e.g. we can have 6 trams that belong to the line number 24 working at the same time). It will take the current mobile geolocation; this includes getting latitude, longitude and bearing from the GPS provider. Thus, we will be able to make a simulation of how the system works in real time by using the server app inside a tram and at the same time, using the client app and making requests to display the information of that tram. The client will also be able to check the path of the desired line without internet access. We will store the path and stops for each line locally in the phone memory using xml files due to the few requirements of available space it needs and the usefulness of checking a path when needed. This app will also offer the functionality of checking the timetable for the line, but in this case, it will link to the official Mpk website, so Internet access will be required. For storing all the coordinates for each vehicle at every moment we will need to create a database on a server. We have decided that the easiest way is to use Mysql and PHP for the deployment of the service. We will send GET and POST requests to the php files and those files will make the according queries to our database. Finally, based on all the collected data, we will be able to get some information about errors in the system of public transport timetables. We will check at what time a line was in each specific stop and compare it with the official timetable to find mistakes of time. We will determine if it is something that happens occasionally and related to external factors (e.g. traffic jams, breakdowns���) or if on the other hand, it is something that happens very often and the public transport timetables should be looked over and corrected.

Distributed Web Interface for Real-Time Spatial Audio Reproduction System

SSR es el acr��nimo de SoundScape Renderer (tool for real-time spatial audio reproduction providing a variety of rendering algorithms), es un programa escrito en su mayor��a en C++. El programa permite al usuario escuchar tanto sonidos grabados con anterioridad como sonidos en directo. El sonido o los sonidos se oir��n, desde el punto de vista del oyente, como si el sonido se produjese en el punto que el programa decida, lo interesante de este proyecto es que el sonido podr�� cambiar de lugar, moverse, etc. Todo en tiempo real. Esto se consigue sin modificar el sonido al grabarlo pero s�� al emitirlo, el programa calcula las variaciones necesarias para que al emitir el sonido al oyente le llegue como si el sonido realmente se generase en un punto del espacio o lo m��s parecido posible. La sensaci��n de movimiento no deja de ser el punto anterior cambiando de lugar. La idea era crear una aplicaci��n web basada en Canvas de HTML5 que se comunicar�� con esta interfaz de usuario remota. As�� se solucionar��an todos los problemas de compatibilidad ya que cualquier dispositivo con posibilidad de visualizar p��ginas web podr��a correr una aplicaci��n basada en est��ndares web, por ejemplo un sistema con Windows o un m��vil con navegador. El protocolo deb��a de ser WebSocket porque es un protocolo HTML5 y ofrece las ���garant��as��� de latencia que una aplicaci��n con necesidades de informaci��n en tiempo real requiere. Nos permite una comunicaci��n full-d��plex as��ncrona sin mucho payload que es justo lo que se ven��a a evitar al no usar polling normal de HTML. El problema que surgi�� fue que la interfaz de usuario de red que ten��a el programa no era compatible con WebSocket debido a un handshacking inicial y obligatorio que realiza el protocolo, por lo que se necesitaba otra interfaz de red. Se decidi�� entonces cambiar a JSON como formato para el intercambio de mensajes. Al final el proyecto comprende no s��lo la aplicaci��n web basada en Canvas sino tambi��n un servidor funcional y la definici��n de una nueva interfaz de usuario de red con su protocolo a��adido. ABSTRACT. This project aims to become a part of the SSR tool to extend its capabilities in the field of the access. SSR is an acronym for SoundScape Renderer, is a program mostly written in C++ that allows you to hear already recorded or live sound with a variety of sound equipment as if the sound came from a desired place in the space. Like the web-page of the SSR says surely better explained: ���The SoundScape Renderer (SSR) is a tool for real-time spatial audio reproduction providing a variety of rendering algorithms.��� The application can be used with a graphical interface written in Qt but has also a network interface for external applications to use it. This network interface communicates using XML messages. A good example of it is the Android client. This Android client is already working. In order to use the application should be run it by loading an audio source and the wanted environment so that the renderer knows what to do. In that moment the server binds and anyone can use the network interface. Since the network interface is documented everyone can make an application to interact with this network interface. So the application can have as many user interfaces as wanted. The part that is developed in this project has nothing to do neither with audio rendering nor even with the reproduction of the spatial audio. The part that is developed here is about the interface used in the SSR application. As it can be deduced from the title: ���Distributed Web Interface for Real-Time Spatial Audio Reproduction System���, this work aims only to offer the interface via web for the SSR (���Real-Time Spatial Audio Reproduction System���). The idea is not to make a new graphical interface for SSR but to allow more types of interfaces and communication. To accomplish the objective of allowing more graphical interfaces this project is going to use a new network interface. By now the SSR application is using only XML for data interchange but this new network interface support JSON. This project comprehends the server that launch the application, the user interface and the new network interface. It is done with these modules in order to allow creating new user interfaces that can communicate with the server or new servers that can communicate with the user interface by defining a complete network interface for data interchange.

Sistema de informaci��n geogr��fica Campus Sur UPM

El proyecto que he realizado ha consistido en la creaci��n de un sistema de informaci��n geogr��fica para el Campus Sur UPM, que puede servir de referencia para su implantaci��n en cualquier otro campus universitario. Esta idea surge de la necesidad por parte de los usuarios de un campus de disponer de una herramienta que les permita consultar la informaci��n de los distintos lugares y servicios del campus, haciendo especial hincapi�� en su localizaci��n geogr��fica. Para ello ha sido necesario estudiar las tecnolog��as actuales que permiten implementar un sistema de informaci��n geogr��fica, dando lugar al sistema propuesto, que consiste en un conjunto de medios inform��ticos (hardware y software), que van a permitir al personal del campus obtener la informaci��n y localizaci��n de los elementos del campus desde su m��vil. Tras realizar un an��lisis de los requisitos y funcionalidades que deb��a tener el sistema, el proyecto ha consistido en el dise��o e implementaci��n de dicho sistema. La informaci��n a consultar estar�� almacenada y disponible para su consulta en un equipo servidor accesible para el personal del campus. Para ello, durante la realizaci��n del proyecto, ha sido necesario crear un modelo de datos basado en el campus y cargar los datos geogr��ficos de utilidad en una base de datos. Todo esto ha sido realizado mediante el producto software Smallword Core 4.2. Adem��s, ha sido tambi��n necesario desplegar un software servidor que permita a los usuarios consultar dichos datos desde sus m��viles v��a WIFI o Internet, el producto utilizado para este fin ha sido Smallworld Geospatial Server 4.2. Para la realizaci��n de las consultas se han utilizado los servicios WMS(Web Map Service) y WFS(Web Feature Service) definidos por el OGC(Open Geospatial Consortium). Estos servicios est��n adaptados para la consulta de informaci��n geogr��fica. El sistema tambi��n est�� compuesto por una aplicaci��n para dispositivos m��viles con sistema operativo Android, que permite a los usuarios del sistema consultar y visualizar la informaci��n geogr��fica del campus. Dicha aplicaci��n ha sido dise��ada y programada a lo largo de la realizaci��n del proyecto. Para la realizaci��n de este proyecto tambi��n ha sido necesario un estudio del presupuesto que supondr��a una implantaci��n real del sistema y el mantenimiento que implicar��a tener el sistema actualizado. Por ��ltimo, el proyecto incluye una breve descripci��n de las tecnolog��as futuras que podr��an mejorar las funcionalidades del sistema: la realidad aumentada y el posicionamiento en el interior de edificios. ABSTRACT. The project I've done has been to create a geographic information system for the Campus Sur UPM, which can serve as a reference for implementation in any other college campus. This idea arises from the need for the campus users to have a tool that allows them to view information from different places and services, with particular emphasis on their geographical location. It has been necessary to study the current technologies that allow implementing a geographic information system, leading to the proposed system, which consists of a set of computer resources (hardware and software) that will allow campus users to obtain information and location of campus components from their mobile phones. Following an analysis of the requirements and functionalities that the system should have, the project involved the design and implementation of the system . The information will be stored and available on a computer server accessible to campus users. Accordingly, during the project, it was necessary to create a data model based on campus data and load this data in a database. All this has been done by Smallword Core 4.2 software product. In addition, it has also been necessary to deploy a server software that allows users to query the data from their phones via WIFI or Internet, the product used for this purpose has been Smallworld Geospatial Server 4.2 . To carry out the consultations have used the services WMS (Web Map Service) and WFS (Web Feature Service) defined by the OGC (Open Geospatial Consortium). These services are tailored to the geographic information retrieval. The system also consists of an application for mobile devices with Android operating system, which allows users to query and display geographic information related to the campus. This application has been designed and programmed over the project. For the realization of this project has also been necessary to study the budget that would be a real system implementation and the maintenance that would have the system updated. Finally, the project includes a brief description of future technologies that could improve the system's functionality: augmented reality and positioning inside the buildings.