Blog

TFG: development of a data model for the detection of presence of people in domestic enviroments
Posted on by rookie

This project aims to develop a presence detection model for domestic environments equipped
with IoT-based security systems. The model is based on the integration and analysis of data
provided by various Securitas Direct – Verisure devices, such as magnetic door and window
sensors, infrared-equipped cameras, and emerging technologies like WiFi Sensing.


Currently, the company has devices that collect real-time information, but it lacks a system
that combines this data to accurately detect human presence. The proposed model aggregates
all available data and determines whether there is presence in the environment based on
logical rules.


The work includes a preliminary study of Verisure’s technology and the state of the art, the
design, development, and deployment of the model, the preparation of a simulation
environment, the collection and processing of real data, and the analysis of results. Finally,
potential future developments, applications, and uses of the model are evaluated, along with
the ethical, social, economic, and environmental impacts of the project.
The project has been carried out within the Securitas Direct – Verisure research chair,
following a SCRUM methodology for its development.

The system integrated the following components:

Central Unit (CU)

Magnetic door and window sensors

Photodetector cameras equipped with PIR sensors and WiFi Sensing

Keypad

Remote keyfob

The final method consisted of a lightweight rule-based model developed in Python, embedded directly in the Central Unit. This model integrates data from the different sensors and WiFi Sensing, applying weighted logic and a sigmoid output function to generate a real-time confidence percentage of human presence.

Several visual interfaces were created to controll the model parameters, create simulated scenarios, or visualize the output of the model. The most relevant of these was developed to visualize the recorded data and model predictions. This interface displays the data collected from all sensors and the acumulated weight over time, which is reset whenever the front door is opened, as well as the correspondence between the model predictions and the actual presence of people.

The solution was validated both in simulation and with real data collected at the Cátedra Securitas Direct. The results demonstrated that the model accurately distinguished between presence and absence across different usage scenarios, such as entering, leaving, or moving inside the home. After refining corner cases, the system achieved an accuracy of approximately 86%, while maintaining very low resource usage (<3% RAM and <1% CPU).

This work provides a reliable presence detection model that strengthens the Verisure security ecosystem without additional hardware costs, preserves user privacy, and ensures efficient performance.

This project was carried out by Jorge Alejandro Estefanía Hidalgo and supervised by Belén Vega Castrillo.

Mesa redonda – Modificación de conductas como apoyo a las operaciones
Posted on by Octavio Nieto-Taladriz

Academia de las Ciencias y las Artes Militares – Sección de Prospectiva Tecnológica

El pasado 7 de mayo tuvo lugar una mesa redonda en la Academia de las Ciencias y las Artes Militares (ACAMI) organizada por nuestro compañero Octavio Nieto-Taladriz, de la que es Académico. Además de tener un formato presencial, la mesa redonda se retransmitió y el vídeo puede verse en el siguiente link.

Resumen

En la actualidad las operaciones multidominio están teniendo un fuerte auge, un gran impacto en las nuevas operaciones y hay una gran preocupación sobre cómo abordarlas, tanto bajo el punto de vista ofensivo como defensivo. Por otra parte, la sección de Prospectiva Tecnológica de la ACAMI pretende con esta mesa redonda sembrar la semilla de cual podría ser un aspecto futuro de especial relevancia como es el poder modelar el comportamiento humano y con ese conocimiento ser capaces de crear estrategias tanto de ataque como de defensa.

Con la amplia extensión de las redes sociales y su capacidad de influencias en los individuos se abre un nuevo mundo de modificación de conductas, como todos podemos ver está ocurriendo en los últimos años. Por otra parte, la existencia de herramientas de procesado de datos a gran escala y la realización de operaciones de inteligencia y control sobre ellos pueden permitir la elaboración de estrategias complejas de modificación de conductas individuales dentro de un colectivo. Un paso relevante es el paso desde la influencia sobre masas a la influencia dirigida y personalizada de elementos clave previamente definidos como críticos para una estrategia de acción.

Finalmente, hay un campo en el mundo de la psicología que tiene puntos en común con la radicalización de un individuo de especial interés para la creación de los diferentes relatos e informaciones a inyectar. Asimismo, y para la parte defensiva, el mundo de la psicología tiene mucho que aplicar para que puedan identificarse ataques como el planteado y poder tomar medidas preventivas. El concepto de “Guardaespaldas Virtual” toma sentido en un entorno como el que se plantea como forma de protección de los individuos frente a este tipo de ataques.

En esta mesa redonda se plantearán conceptos sobre este tema como punto de discusión para el posible desarrollo de estrategias y herramientas tanto ofensivas como defensivas en este campo de influencia sobre individuos.

Datos de la mesa redonda

Fecha: 7 de mayo – Hora: de 18:00 a 20:00 horas – Lugar: Sede de ACAMI

18:00 Palabras de bienvenida

GE R. D. Jaime Domínguez Buj – Presidente de la Academia de las Ciencias y las Artes Militares

18:10  Ponencia “La desinformación un instrumento clave en los conflictos actuales”

GB R. Dr. Miguel Ángel Ballesteros Martín – ACAMI

18:30   Ponencia “Así somos, así nos influyen”

Comandante Psicólogo Dña. Lucía Pery Pardo De Donlebún – EMAD

18:50 Ponencia “Caso práctico: Poniendo los huevos en la cesta”

Prof. Dr. Octavio Nieto-Taladriz García – Catedrático de Universidad en el Departamento de Ingeniería Electrónica de la E.T.S.I. de Telecomunicación – Universidad Politécnica de Madrid 

Prof. Dr. María Paz García Vera – Catedrática de Psicología Clínica en el Departamento de Personalidad, Evaluación y Psicología Clínica – Universidad Complutense de Madrid

19:30 PREGUNTAS

20:00 CLAUSURA

TFM: Design of a Communication System Through the Body
Posted on by rookie

The loss of a limb is a traumatic event for a human being, permanently altering the way they perform everyday tasks. Currently, most of these patients require a prosthesis for both aesthetic and functional reasons. Today, there are various types of prostheses, with robotic arms being the most commonly used for movement. These mechanical and/or electrical devices mimic human movements, controlled by the person. At present, the communication between the robotic arm and the user is established either through implants inside the body or via vulnerable communication methods.

The objective of this master’s thesis is to design a non-invasive communication system that uses the human body as a transmission medium. This approach is based on the innovative Human Body Communication (HBC) technology, which is part of Wireless Body Area Networks (WBAN). It is designed for wearable devices on the surface or inside the human body, specifically in the field of medicine. The goal is to transmit electrical or electromagnetic signals using the conductive properties of the human body.

To achieve this, an exhaustive study was conducted to understand how the human body behaves when a signal is transmitted at the selected frequency of 2.45 GHz. The signal will be transmitted through the patient’s forearm, which consists of multiple layers of materials with different dielectric properties. Therefore, computational simulations are necessary to analyze how the signal behaves.

This project is based on two experimental studies aimed at measuring propagation losses. The goal is to place the transmission and reception devices on the skin’s surface, using study [1] as a reference to calculate the signal losses through the multiple layers of the spleen. Additionally, the signal losses associated with transmission through the interior of the forearm, between the transmitter and receiver, were evaluated based on the data from study [2].

Once the system requirements were established, preliminary tests were conducted to validate the designed system. The results showed greater propagation losses than the theoretical estimates, prompting the project to focus on developing a functional prototype that is small, low-cost, and energy-efficient. The following image shows the completed system.

Finally, after testing the assembled system, it was determined that the selected insulator, RFSW-S-125-FR-PSA from Laird Technologies, is effective for communication through the air. However, aluminum yielded better results for communication through the body. On the other hand, the selected antenna was not ideal due to market limitations.

The results obtained suggest multiple areas for improvement and encourage further research to optimize the system.

References:

[1] Y. M. G. M. D. Zhi Ying Chen, «Propagation characteristics of electromagnetic wave on multiple tissue interfaces in wireless deep implant communication,» IET Microwaves, Antennas & Propagation, vol. 12, nº 13, pp. 2034-2040, 2018.

[2] C. G.-P. A. F.-L. A. V.-L. G. V. J. S. M. I. I. B. S. M. I. a. N. C. S. M. I. Ra´ul Ch´avez-Santiago, «Experimental Path Loss Models for In-Body Communications Within 2.36–2.5 GHz,» IEEE JOURNAL OF BIOMEDICAL AND HEALTH INFORMATICS, vol. 19, nº 3, pp. 930-937, 2015.

TFM: Design and implementation of a simulation environment for transcranial magnetic stimulation in human and mouse brains.
Posted on by rookie

The study of the human brain is currently a fundamental area of interest in science due to the complexity and diversity of functions performed by this organ. Although the brains of humans and mice differ in size and structure, they share numerous fundamental principles that allow scientists to extrapolate findings from rodent studies to humans. However, neuroscience research faces significant challenges due to the intrinsic complexity of nervous systems and the ethical and practical limitations associated with direct experiments on living organisms.

In this context, simulation environments have emerged as powerful tools for research. These environments allow for the modelling and detailed analysis of neural processes in a controlled setting without involving any living organisms. The ability to simulate brain activity when stimulated by external factors not only facilitates understanding of the brain’s response to these stimuli but also can accelerate the development of treatments for neurological diseases, such as cancer or stroke.

The main objective of this work is to develop a simulator capable of stimulating human and mouse brains using the transcranial magnetic stimulation method and quantifying the impact of various parameters in the simulation.

To achieve this objective, various brain simulators currently in use have been analysed, and one has been selected as the basis for the simulator. Additionally, the functioning of transcranial magnetic stimulation and the necessary instruments for carrying out this stimulation method have been studied. Furthermore, the modelling of the magnetic field generated by coils, both with and without a core, has been explored.

After gathering all this information, the simulator was completed, capable of simulating both human and mouse brains. Moreover, it allows for generating stimuli in the target brain with fully customized coils, as it is possible to model them by varying parameters such as height, radius, or number of turns. The intensity circulating through these coils can also be adjusted. Additionally, various commercial coils and stimulation systems consisting of multiple coils were successfully modelled.

Finally, various tests were conducted to verify that the modelling of the different coils was accurate and to measure different parameters. The parameters measured included the maximum radial electric field generated in the brain for each coil, the value of this electric field at different depths, the effect of the distance between the skull and the coil on the stimulation, and the field generated by the stimulation systems. Subsequently, all these tests were parametrized.

This project has developed and implemented a simulator capable of replicating brain stimulation in humans and mice through transcranial magnetic stimulation. The simulator allows customization of parameters such as coil position and number, distance from the skull, or stimulation intensity. After various tests, its accuracy has been confirmed, helping to reduce risks and improve personalized TMS treatments. Additionally, the inclusion of mouse models reduces the need for live experiments. The simulator offers applications in neuroscience research, therapy optimization, and the development of new clinical protocols.

Therefore, it can be confirmed that the proposed general objectives have been achieved and the technical feasibility of the project has been demonstrated.

All the code corresponding to the simulator is located in the following repository: https://github.com/rfparra/TFM

TFM: Diseño de un Sistema de Monitorización de Constantes Vitales de Roedores a Distancia
Posted on by rookie

The VISNE project, from the B105 Electronic Systems Lab at the ETSIT in collaboration with the Neuro-Computing and Neuro-Robotics group at the Complutense University, focuses on the development of a thalamic prosthesis to restore vision in humans. In its initial phases, this system will be tested on rodents, specifically mice, through behavioral tests in an operant conditioning chamber, also known as a Skinner box (as can be seen in the image below) .

However, the use of animals for medical research is one of the most controversial and debated topics in the modern scientific community. Therefore, ensuring the welfare of the animals has become a fundamental task, and to this end, the aim is to remotely monitor their vital signs.

In this master’s thesis, two techniques for monitoring mice were evaluated and tested: an infrared camera (MLX90640 from Melexis) for temperature measurement and an FMCW radar (AWR6843AOP from Texas Instruments) for tracking heart rate and respiration through thoracic variations. An electronic system was designed and implemented, consisting of two components: a proof-of-concept using both sensors and a prototype PCB that integrates the temperature monitoring system.

The proof of concept was integrated with a central interface within a Skinner box for mice. A user-friendly graphical interface was developed to display measurements from both sensors over time. A program was created using the infrared camera to detect the rodent’s warm body, positioning it at the central point to enable precise tracking and presence detection. The motion data collected could be used to estimate the rodent’s stress level during behavioral tests. Additionally, this program records temperature and movement data in text files for further analysis.

System tests demonstrated that the camera enabled continuous monitoring of the mouse’s body temperature, while the radar successfully measured heart rate in humans, with results closely aligning with those obtained through traditional methods. However, the radar measurements exhibited notable variability. Additionally, the system effectively measured the respiratory cycle and accurately detected presence.

The Printed Circuit Board (PCB) for the prototype temperature monitoring system was designed and manufactured with compact dimensions of 50 x 103 mm. It includes wireless connectivity and supports data storage on a microSD card. Additionally, the PCB is equipped with a micro-USB port for easy programming and powering of the system. All the TFM’s files are available in this repository: https://bitbucket.org/b105upm/tfm_rpeon/

The PCB has been successfully soldered, tested, and programmed. The embedded software enables data communication with a central node using the MQTT protocol, while the central server capture the data and displays thermal images on a web interface. All the embedded software of this system is located in this repository: https://bitbucket.org/b105upm/skinnerbox