ESALAB. Artículos

Singular Spectrum Analysis for Source Separation in Drone-Based Audio Recording

Fri, 01 Jan 2021 00:00:00 GMT

[EN]The usage of drones is increasingly spreading into new fields of application, ranging from agriculture to security. One of these new applications is sound recording in areas of difficult access. The challenge that arises when using drones for this purpose is that the sound of the recorded sources must be separated from the noise produced by the drone. The intensity of the noise emitted by the drone depends on several factors such as engine power, propeller rotation speed, or propeller type. Noise reduction is thus one of the greatest challenges for the next generations of unmanned aerial vehicles (UAVs) and unmanned aerial systems (UAS). Even though some advances have been made on that matter, drones still produce a considerable noise. In this article, we approach the problem of removing drone noise from single-channel audio recordings using blind source separation (BSS) techniques, and in particular, the singular spectrum analysis algorithm (SSA). Furthermore, we propose an optimization of this algorithm with a spatial complexity of O(nt), which is significantly lower than the naive implementation which has a spatial complexity of O(tk2) (where n is the number of sounds to be recovered, t is the signal length and k is the window size). The best value for each parameter (window length and number of components used to reconstruct the source) is selected by testing a wide range of values on different noise-sound ratios. Our system can greatly reduce the noise produced by the drone on said recordings. On average, after the recording has been processed by our method, the noise is reduced by 1.41 decibels

A Platform for Swimming Pool Detection and Legal Verification Using a Multi-Agent System and Remote Image Sensing.

Sun, 01 Jan 2023 00:00:00 GMT

[EN]Spain is the second country in Europe with the most swimming pools. However, the legal literature estimates that 20% of swimming pools are not declared or irregular.The administration has a corps of people who manually analyze satellite or drone images to detect illegal or irregular structures. This method is costly in terms of effort and time, and it is also a method based on the subjectivity of the person carrying it out. This proposal aims to design a platform that allows the automatic detection of irregular pools. Using geographic information tools (GIS) based on orthophotography, combined with advanced machine learning techniques for object detection, allows this work. Furthermore, using a multi-agent architecture allows the system to be modular, with the possibility of the different parts of the system working together, balancing the workload. The proposed system has been validated by testing it in different towns in Spain. The system has shown promisin results in performing this task, with an F1-Score of 97.1%.

A Multiagent Platform for promoting physical activity and learning through interactive educational games using the depth camera recognition system

Wed, 03 Jan 2024 00:00:00 GMT

[EN]Physical activity is one of the most important elements in the motor and cognitive development of school and high school students. As has been demonstrated in different studies, physical exercise improves students’ intellectual performance while positively influencing their health. In this work an educational tool based on the Kinect sensorization system capable of interacting with students in a proactive and dynamic way has been designed. Through the use of a projector and a set of balls, students interact with various games and activities. The Kinect system detects the movement and position of the balls thrown by the students and generates a response to the game or activity performed. Thanks to the flexibility and ease of use of the designed tool, it is possible to easily develop new games or activities adapted to each subject. In this way, teachers are provided with a new didactic tool to promote the knowledge of a certain area through games and physical activity of the students. In order to validate the system, a case study has been carried out in a school with real students. The results obtained are very promising.

A multi-agent system approach for balance disorder treatment: integrating computer vision and gamification

Mon, 01 Jan 2024 00:00:00 GMT

[ENG]This study introduces a pioneering approach for treating balance disorders, integrating advanced computer vision and engaging gamification techniques within a multi-agent system framework. Balancing disorders significantly impair quality of life, manifesting through symptoms like dizziness and muscle weakness. Addressing this, we developed a platform that employs depth imaging and real-time pose estimation to accurately capture and analyze patient movements, enabling personalized and adaptive rehabilitation exercises. The multi-agent system architecture ensures seamless communication and coordination, facilitating the delivery of tailored exercises that cater to the evolving needs of patients, either in person or remotely. Key to our approach is the use of gamification, which transforms rehabilitation exercises into interactive virtual activities, significantly enhancing patient engagement and motivation. Preliminary results demonstrate the platform's efficacy in improving balance, highlighting its potential as a versatile tool for balance disorder treatment. This research advances the technological frontier in balance disorder rehabilitation and offers a blueprint for future telehealth and patient-centric care innovations.

A novel multiagent system for cervical motor control evaluation and individualized therapy: integrating gamification and portable solutions

Mon, 01 Jan 2024 00:00:00 GMT

[EN] The study focused on designing a portable, objective device for assessing and addressing Cervical Motor Control (CMC) impairments. This device is based on a proposed architecture that employs advanced technology to evaluate and enhance patients’ CMC. During a pilot study with 10 participants, the device’s feasibility and usability were verified, including an initial assessment using the Head Relocation Test and a 12-session intervention over 4 weeks. The architecture of the proposed system is responsible for gathering pertinent data concerning patients’ cervical motor control. It employs advanced algorithms to process this data and objectively assess CMC function. Furthermore, the system tailors the therapy to each patient’s individual needs. Preliminary results indicate that the device and the proposed architecture positively impact assessment test performance accuracy. While additional validation tests are required to confirm their effectiveness, this device emerges as a promising and valuable alternative for assessing and treating patients with CMC impairments. Its focus on advanced technology and personalized adaptation aligns with previous research in telerehabilitation and classroom physical activity promotion.

RespiraConNosotros: a viable home-based telerehabilitation system for respiratory patients

Fri, 01 Jan 2021 00:00:00 GMT

Currently, there are more than 1.55 million cases of SARS-CoV-2 infection in Spain. Of these, it is estimated that around 45% will present respiratory complications, which represents approximately 620,000 patients who will need respiratory rehabilitation. The health system has no resources for this huge quantity of patients after the hospital discharge to finish the complete recovery and avoid the chronicity of the symptoms. We propose an application named RespiraConNosotros. The application has been created and designed to guide users in performing respiratory rehabilitation exercises, especially for COVID-19 patients, and it also facilitates patient–physiotherapist contact via chat or video calling to help patients. It is accessible for all users and on all devices. All exercises would be guided and supervised by a specialized physiotherapist who suggests, adapts, and guides the exercise according to the function level of each patient. Data obtained was satisfactory; all patients pointed out the easy access, the intuitive format, and the advantage of communicating with an expert. Concerning functional assessment, all participants improved their score on the Borg scale after performing the intervention with the application.This platform would help respiratory patients to make rehabilitation treatments to recover their pulmonary function and to decrease or eliminate the possible complications they have. It never substitutes any prescribed treatment. In conclusion, RespiraConNosotros is a simple, viable, and safe alternative for the improvement and maintenance of respiratory capacity and patient’s functionality affected by COVID-19. It could be used as a complement to face-to-face treatment when the situation allows it.

Reliability and validity of the spanish version of the memorial symptom assessment scale in oncology patients

Thu, 01 Dec 2016 00:00:00 GMT

Context Memorial Symptom Assessment Scale (MSAS) is a multidimensional tool developed to evaluate frequency, severity, and distress of common symptoms present in cancer patients. Objective To translate the original English version of MSAS and prove the reliability and validity of the Spanish version. Methods MSAS scale was translated into Spanish and administered to 246 cancer patients aged between 18 and 85 years. They attended the Day Hospital to receive chemotherapy. European Organization for Research and Treatment of Cancer Quality of Life Questionnaire–Core 30 and Rotterdam Symptom Checklist were used to test criterion validity. Results TOTAL MSAS, Physical Symptom Subscale (PHYS), Psychological Symptom Subscale (PSYCH), and Global Distress Index (GDI) reported high internal consistency: 0.891, 0.801, 0.825, 0.813, respectively. Exploratory factor analysis identified two-factors structure and confirmatory factor analysis showed good adjustment rates. The emotional functioning subscale of European Organization for Research and Treatment of Cancer Quality of Life Questionnaire–Core 30 highly correlated with PSYCH (r = −0.868; P < 0.001) and GDI (r = −0.810; P < 0.001), whereas social functioning subscale correlated with PSYCH (r = −0.704; P < 0.001) and GDI (r = −0.624; P < 0.001). The PHYS of Rotterdam Symptom Checklist correlated with PHYS (r = 0.876; P < 0.001) and the PSYCH with PSYCH (r = 0.872; P < 0.001). Conclusion The Spanish version of MSAS was determined to be a valid and reliable scale in cancer patients.