TFG: Development of an Artificial Intelligent system based on low-resource Edge Computing for autonomous vehicles applications

Nowadays, there are plenty of IoT devices which make our everyday life easier thanks to their intelligent tasks: data capture, process automation… However, the increase of these devices is turning out to be somehow risky in terms of latency or bandwidth. That is the reason why some alternatives that may solve these problems are being searched, and one of them is Edge Computing technologies.

Edge Computing devices are those who are able to process the information captured without connecting to the network. Due to that, the latency and bandwidth issues that may occur can be significantly reduced, allowing the radio spectrum to decrease its saturation as well as improving the latency and consumption performance.

In this project, the main goal is to create a system that is able to develop and execute Artificial Intelligence algorithms designed for autonomous driving and assistance to the driver, always taking care of Edge Computing philosophy. In order to do that, we have used Google Coral, a hardware platform that perfectly adapts to our needs, allowing us to develop all the Edge Computing algorithms as well as offering appropriate consumption and processing characteristics.

Finally, we have tested our system in a real situation, evaluating the quality of the results as well as the resources used (latency, bandwidth…) and the advantages and disadvantages in relation to the existing technologies is this area. After these experiments, we have concluded that the quality of our Edge Computing system is enough to carry out the tasks it has been designed for. Also, all the resources used have been optimized in relation to Cloud Computing alternatives, turning this project into a faster, more effcient and economic alternative.

TFM: Design and implementation of an intelligent system for eldercare support

The number of elderly people in Spain is in a constant process of growth. It is frequent that in this age range problems appear that do not allow people to live their daily lives in a totally independent way. The health care system has limited resources to solve these problems, and the families of these people are having problems reconciling their work and family life.

The motivation for this Master’s Thesis has been to design a solution for people in this situation. In order to do this, a study of the technological solutions present on the market has been carried out first to obtain a list of functionalities that help to deal with the problem. Then, an architecture has been designed that allows the incorporation of these functionalities. Finally, a proof of concept for one of them has been implemented.

The designed architecture is composed of three elements. The terminal is placed at the patient’s home, and provides the patient with different utilities. The web client allows the caregiver to access the different functionalities that arise from monitoring the patient from the terminal. The server is responsible for managing communications between the terminal and the client, as well as managing access to the architecture’s resources, such as the database.

To implement the proof of concept, the utility that has been chosen is the dispensing of medicines. On the patient side, the terminal will alert you when it is time to take the medication, making it accessible at that time. The dispenser has a sensor on the lid that allows you to know when the medication has been accessed, allowing you to monitor your medication intake.

On the caregiver’s side, the status of the intake can be checked through a web client. Once the caregiver has logged into the application, he or she can access the associated terminal and check whether the programmed intakes have been taken in the time interval defined for them, or whether they have been forgotten. On the other hand, the web client also allows the caregiver to schedule the intakes from the terminal.

TFG: Implementation and evaluation of ANNs in microcontroller-based systems

Nowadays, artificial neural networks (ANNs) are computational models that, while they have solved many different problems, they require a large amount of memory to execute those solutions. Therefore, their implementation is more common in systems with high-performance capabilities, such as data centers or servers. However, there is an increasing interest in developing these solutions on devices with fewer resources, such as personal computers, mobile devices, and microcontrollers.  This situation has led to the proliferation of multiple techniques and tools to reduce the requirements of these models and allow their implementation on those platforms.

The main objective of this project is the evaluation of a tool for the implementation of artificial neural networks in microcontroller-based systems. For this purpose, a practical use case has been defined.

To achieve this objective, the classification of types of tremors in Parkinson’s patients was chosen as the practical use case. In addition, the Arduino Nano 33 BLE Sense has been also chosen as the microcontroller-based platform to implement the solutions of the practical use case.

Later, a dataset has been generated with real measurements from a sensor on that platform. With this dataset various experiments have been carried out to determine how the different structures of artificial neural networks deal with the chosen use case.

Then, based on those experiments, some appropriate ANNs for classifying types of tremors have been designed, trained, and evaluated in a system with graphics and tensor processing units and in a microcontroller-based system.

Finally, based on the results obtained, the trade-offs between classification accuracy, memory footprint and inference latency involved in the implementation of ANNs solutions in microcontroller-based systems have been determined. In addition, a discussion of the strengths and weaknesses of the selected tool for the implementation of artificial neural networks in microcontroller-based systems has been presented.

Gated Recurrent Unit Neural Networks for Automatic Modulation Classification With Resource-Constrained End-Devices

The article “Gated Recurrent Unit Neural Networks for Automatic Modulation Classification With Resource-Constrained End-Devices” by our lab member Ramiro Utrilla has just been published in the IEEE Access, a high-impact open-access journal.

This work has been carried out in collaboration with researchers from the CONNECT – Centre for Future Networks and Communications in Dublin (Ireland), where Ramiro carried out a research stay of 3 months.

In this article, they focus on the Automatic Modulation Classification (AMC). AMC is essential to carry out multiple CR techniques, such as dynamic spectrum access, link adaptation and interference detection, aimed at improving communications throughput and reliability and, in turn, spectral efficiency. In recent years, multiple Deep Learning (DL) techniques have been proposed to address the AMC problem. These DL techniques have demonstrated better generalization, scalability and robustness capabilities compared to previous solutions. However, most of these techniques require high processing and storage capabilities that limit their applicability to energy- and computation-constrained end-devices.

In this work, they propose a new gated recurrent unit neural network solution for AMC that has been specifically designed for resource-constrained IoT devices.

The proposed GRU network model for AMC.

They trained and tested their solution with over-the-air measurements of real radio signals, which were acquired with the MIGOU platform.

Dataset generation scenario set up.

Comparison of signals recorded at (a) 1 and (b) 6 meters. The signals in the bottom row are the normalized version of those in the top row.

Their results show that the proposed solution has a memory footprint of 73.5 kBytes, 51.74% less than the reference model, and achieves a classification accuracy of 92.4%.

Increasing the training set can lead to improvements in the performance of a model without increasing its complexity. These improvements allow developers to reduce the complexity of the model and, therefore, the device resources it requires. However, longer training processes can lead to fitting and gradient problems. These tradeoffs should be explored when developing neural network-based solutions for resource-constrained end-devices.

Research visit at UC Berkeley

Our lab member Alba Rozas has recently completed a PhD research visit at the Berkeley Wireless Research Center (BWRC), part of the University of California at Berkeley, under the supervision of renowned Profesor Jan Rabaey. This group carries out world-leading research in the fields of radio communications and wireless electronics, with a particular recent interest in Body Area Networks and the Human Intranet.

World Map with location pins for every BWRC member

The main research line of Alba’s PhD is focused on QoS-aware and energy efficient routing strategies for WSNs. This 5-month stay took place within the last stage of her PhD, and its main goal was the study and research of over-the-body communication aspects and the Human Intranet paradigm. These fields have unique characteristics that differentiate them from traditional WSNs, presenting new challenges and opportunities. Thus, in this research stay, Alba has focused on applying the core ideas of her PhD to the field of body area networks. As a result of the work carried out during the visit, she has ultimately developed an energy-efficient and QoS-aware strategy for on-body wireless communication, based on dynamic human activity detection.

In addition to this main research objective, the stay has also strengthened the already existing working relationship between BWRC and B105. Both labs are already collaborating in the development of health-related solutions and systems, initiated by Alvaro Araujo‘s two research visits at BWRC.

Visita del CIDAT

Como podrán apreciar los lectores frecuentes de nuestro blog, las lineas de investigación de nuestro grupo abordan temáticas muy diversas. La que trataremos en este artículo está orientada mejorar la percepción espacial por medios no visuales. Para ello, utilizamos una red de dispositivos “wearables” que generan estímulos hápticos y acústicos de acuerdo a teorías recientes en materia de sustitución sensorial.

El objetivo principal es que una persona con discapacidad visual grave o ceguera tenga menos dificultades a la hora de desplazarse por la ciudad, en interiores, etc. Nuestro primer prototipo, Virtually Enhanced Senses (VES), virtualiza las características más importantes de un escenario real desde una perspectiva de orientación y movilidad, y proporciona la información al usuario de forma intuitiva.

Recientemente hemos tenido la suerte de contar con personal del CIDAT para la evaluación y posterior perfeccionamiento del prototipo. Durante las reuniones y demostraciones de la tecnología, los usuarios finales pudieron experimentar de primera mano el sistema tanto en escenarios virtuales como reales.

Desde aquí queríamos agradecer a nuestros invitados por su tiempo, esfuerzo e ilusión, esperando vernos de nuevo en un futuro próximo.

A Methodology for Choosing Time Synchronization Strategies for Wireless IoT Networks

This summer we have published a new article about time synchronization for wireless sensor networks, applied to the field of IoT, in Sensors Open Access Journal. This journal has these statistics:

  • 2018 Impact Factor: 3.031
  • 5-year Impact Factor: 3.302
  • JCR category rank: 15/61 (Q1) in ‘Instruments & Instrumentation’

This article belongs to the Special Issue Topology Control and Protocols in Sensor Network and IoT Applications.

This article has a direct relationship with the thesis of our colleague Francisco Tirado-Andrés. This thesis investigates a methodology, and associated tools, to make it easier for all researchers to choose time synchronization protocols for specific WSNs.

For more information about this article please visit MDPI webpage.

TFG: Design and implementation of a wearable system for livestock

Today, the use of monitoring systems is widespread in society. However, it is not common to see them in animals.

This end-of-grade work aims to design and implement a wearable system for cows, horses, sheep and goats. Thus, the farmer can know the state of the animals and their location. Taking into account the signs and characteristics that occur in this type of animals in situations of interest, the system has several sensors: a microphone, a temperature and humidity sensor, a gyroscope, an accelerometer, an air quality sensor, a gas sensor to detect diseases and a GPS.

Thanks to the information of these sensors it is possible to know when the animal is sick, has problems walking or even the period of heat of the females and later the time of delivery.

Finally, all data is sent to the farmer to make decisions on the farm, improving the welfare of the animal and increasing its productivity.

For the development of the system, the complete hardware design and implementation was carried out, in addition to the realization of a hardware abstraction layer (HAL) for all sensors.


This final project focuses on the field of robotics aimed at developing automated prostheses, helping to recover part of the lost mobility of people who need it. More specifically, it will focus on analysing and designing a wirelessly controlled robotic arm, which will serve as the basis for future projects at the B105 Electronic Systems Lab.

To this end, a preliminary study was carried out of the technologies currently used to develop a robotic arm, extracting which components can be used to carry out the movement and control of the arm, what considerations must be taken into account to design the different parts that make it up and what prototypes currently exist, extracting their characteristics to try to find a way to improve them.

Once the previous study had been done, the design of the arm was carried out, where the way to control it, the type of wireless communication, the motorization to be used and how it is fed were chosen. After this, we have chosen the components that best suit to meet the specifications requested, the modeling program has been used to design the parts, the materials used to build them, and the type of manufacture used to make them. It has been concluded that the parts must be manufactured by 3D printing, that Bluetooth will be used as technology for wireless communication, and servomotors to motorize the system.

Afterwards, the connection has been made, the design of the pieces by means of a 3D modeling program and the subsequent manufacture of part of them by means of 3D printing. A mobile application has also been developed to control several servomotors and check the wireless connection between the arm and the mobile, in addition to having created several integration files on the board to check the operation of the components.

Then different tests have been carried out, using the software created, where different components have been connected, and it has been checked whether they work correctly or not.

In the end a complete functionality has not been achieved, but a partial functionality has been achieved where it has been possible to connect by means of Bluetooth the mobile and the arm, to move two servomotors, with which two fingers have been moved, and the battery has been controlled by means of a series of leds. Several problems have also been found with regard to the power supply of the servomotors and the reception of data sent by the board that controls the servomotors to the mobile.

TFM: Development of a vehicle monitoring system based on NB-IoT technology

Nowadays, several European cities are looking for ways to regulate their internal traffic due to the high concentration rates of pollutants present because of vehicles. These concentrations cause hundreds of thousands of premature deaths in Europe per year, so it is beginning to be considered as a risk factor for its citizens. In most of the cities that implement some type of restriction, the regulation of this traffic is carried out by establishing a fixed low emission zone controlled by cameras.

In this context, the aim of this work is to provide an alternative to the conditions for access to these restricted zones, which are generally based on the Euro standard met by each vehicle. Thus, a device has been developed that connects to the vehicles by means of the OBD II standard, obtains its geolocation and transmits the acquired data using the NB-IoT technology. The purpose of these data is to obtain an estimate of the emissions produced by vehicles individually and based on actual traffic data, with which to regulate the access to the restricted zone. To this end, the COPERT emissions estimator has been incorporated based on speed data with a half-second time interval. This provides an opportunity to create fairer driving conditions based on the particular emissions of each vehicle within the restricted zones. In addition, it allows the creation of dynamic zones that can be a palliative for the border effect that could occur with a fixed zone. With this change of perspective, we can restrict more or less the traffic depending on the pollution situation in the city. Another improvement is the regulation of other pollutants like carbon monoxide or methane.

The developed system is powered by the vehicle battery, uses OBD II through the CAN bus or the ISO 9141 to communicate with the vehicle and obtains the location using a multi-constellation. A PCB has been designed that integrates three modules that carry out the tasks of communicating with the vehicle, transmitting the data to a central server and establishing of the geolocation of the vehicle; as well as a microcontroller in charge of the coordination between these elements and communicating with the user through commands.

A vehicle ECU simulator has been developed in order to debug the system and check that the data obtained are related to the expected values without the need to be permanently connected to a real vehicle during development. The objective was to create a simple simulator that would implement CAN bus communication and could respond to requests from an OBD II port.

Several tests have been carried out with the developed system on board a vehicle during a real journey. Their results allow us to see a distribution consistent with what was expected in terms of the concentration of pollutants emitted. Thus, we have empirically proven that the concentration of pollutants increases on narrow and slow roads and decreases on wider roads. From these tests the correct functioning of the final system and, therefore, the fulfilment of the objectives are confirmed. The result of a test made with a Euro 6 diesel car can be seen in the following picture, where we can see the NOx estimated emissions.