Loading...
15 results
Search Results
Now showing 1 - 10 of 15
- Breast Skin Temperature Evaluation in Lactating and Non-lactating Women by Thermography: An Exploratory StudyPublication . Gouveia, Ana; Pires, Luís Carlos Carvalho; Garcia, Nuno; Barbosa, Ana; Jesus, Ana; Pombo, Nuno; Soares, Marta; Oliveira, J. Martinez deDuring pregnancy and lactation, woman breasts feel changes like blood flow increasement, associated with a higher breast temperature. We performed an exploratory study of the breast skin temperature of lactating and non-lactating women based on thermography, with a qualitative analysis of the temperature patterns and a quantitative evaluation of the differences. Frontal breast thermograms of four non-lactating young women and four women with well-established lactation were acquired and analyzed. Qualitative analysis of the images obtained show some evidence of the existence of a characteristic skin temperature pattern for lactating women. Quantitative differences between thermograms were also noticed, especially when considering dispersion metrics: lactating women present higher breast skin temperature gradients and amplitudes. Results obtained, especially based on central tendency metrics, should be interpreted with caution because some of the acquisition conditions for non-lactating women may lead to some bias on the results. Further investigation will be performed to quantify breast skin temperature gradient and be able to classify images based in the breast skin temperature pattern.
- Towards an accurate sleep apnea detection based on ECG signal: The quintessential of a wise feature selectionPublication . Pinho, André; Pombo, Nuno; Silva, Bruno M.C.; Bousson, K.; Garcia, Nuno M.A wise feature selection from minute-to-minute Electrocardiogram (ECG) signal is a challenging task for many reasons, but mostly because of the promise of the accurate detection of clinical disorders, such as the sleep apnea. In this study, the ECG signal was modeled in order to obtain the Heart Rate Variability (HRV) and the ECG-Derived Respiration (EDR). Selected features techniques were used for benchmark with different classifiers such as Artificial Neural Networks (ANN) and Support Vector Machine(SVM), among others. The results evidence that the best accuracy was 82.12%, with a sensitivity and specificity of 88.41% and 72.29%, respectively. In addition, experiments revealed that a wise feature selection may improve the system accuracy. Therefore, the proposed model revealed to be reliable and simpler alternative to classical solutions for the sleep apnea detection, for example the ones based on the Polysomnography.
- Implementing Mobile Games into Care Services - Service Models for Finnish and Chinese Elderly CarePublication . Merilampi, Sari; Koivisto, Antti; Leino, Mirka; Pombo, Nuno; Felizardo, Virginie; Lu, Jue; Poberznik, Anja; Virkki, JohannaThe purpose of this paper was to create service models for cognitively stimulating mobile games and incorporate them into Finnish and Chinese elderly care. The implementation involved the use of two different mobile games as part of the everyday lives of older adults in care homes in Finland (3 months) and China (6 months). Although a large number of publications examine serious games in elderly care, there are rather few publications related to the practical implementation within the elderly care processes. In general, rehabilitation orientated games should incorporate entertainment (motivation) and relevant therapeutic content (rehabilitation) in order to be effective. Regardless of the game design, successful implementation of the games in elderly care is paramount to benefit the end user. In this paper, two mobile games were investigated as a case study. To investigate the therapeutic content of the games, the game outcomes (game scores and time stamps) were automatically recorded to facilitate analysis of the participant’s progress during the trial. To investigate motivation, user feedback was collected through observation of the game trials and by interviewing the nursing staff and the participants (test group). The gaming service implementation was designed in collaboration with the nursing staff and researchers, according to an experimentation-driven approach, in which the service model ideas were tested by the professionals before piloting. In both countries, the players and the nursing staff found the games showed potential as self-managed rehabilitation tools. Other significant effects of gameplay were enhanced recreation and self-managed activity level. Despite cultural differences, the gaming experience was amazingly similar and improvements in game scores were also observed during the trial in both countries. The biggest difference between the pilots was the implementation process, which led to the development of two different service models that are reported in this paper. In Finland, the games were embedded into the care practices and the nursing staff were responsible for the piloting. In China, the games were independent of the care process and an external service provider (the researcher) managed the piloting. The findings imply that service design in different cultures should be carefully considered when implementing new digital services.
- Internet of Things Architectures, Technologies, Applications, Challenges, and Future Directions for Enhanced Living Environments and Healthcare Systems: A ReviewPublication . Marques, Gonçalo; Pitarma, R.; Garcia, Nuno M.; Pombo, NunoInternet of Things (IoT) is an evolution of the Internet and has been gaining increased attention from researchers in both academic and industrial environments. Successive technological enhancements make the development of intelligent systems with a high capacity for communication and data collection possible, providing several opportunities for numerous IoT applications, particularly healthcare systems. Despite all the advantages, there are still several open issues that represent the main challenges for IoT, e.g., accessibility, portability, interoperability, information security, and privacy. IoT provides important characteristics to healthcare systems, such as availability, mobility, and scalability, that o er an architectural basis for numerous high technological healthcare applications, such as real-time patient monitoring, environmental and indoor quality monitoring, and ubiquitous and pervasive information access that benefits health professionals and patients. The constant scientific innovations make it possible to develop IoT devices through countless services for sensing, data fusing, and logging capabilities that lead to several advancements for enhanced living environments (ELEs). This paper reviews the current state of the art on IoT architectures for ELEs and healthcare systems, with a focus on the technologies, applications, challenges, opportunities, open-source platforms, and operating systems. Furthermore, this document synthesizes the existing body of knowledge and identifies common threads and gaps that open up new significant and challenging future research directions.
- Approach for the Development of a Framework for the Identification of Activities of Daily Living Using Sensors in Mobile DevicesPublication . Pires, Ivan; Garcia, Nuno M.; Pombo, Nuno; Flórez-Revuelta, Francisco; Spinsante, SusannaSensors available on mobile devices allow the automatic identification of Activities of Daily Living (ADL). This paper describes an approach for the creation of a framework for the identification of ADL, taking into account several concepts, including data acquisition, data processing, data fusion, and pattern recognition. These concepts can be mapped onto different modules of the framework. The proposed framework should perform the identification of ADL without Internet connection, performing these tasks locally on the mobile device, taking in account the hardware and software limitations of these devices. The main purpose of this paper is to present a new approach for the creation of a framework for the recognition of ADL, analyzing the allowed sensors available in the mobile devices, and the existing methods available in the literature.
- Teaching in conditions of difficult knowledge transfer due to the state of emergency caused by the pandemicPublication . Mravik, Miloš; Šarac, Marko; Veinovic, Mladen; Pombo, NunoIntroduction/purpose: This paper presents the transformation of the current, classical approach to teaching. Online platforms enable students with and without disabilities to follow classes without hindrance during the lecture period. After the lecture, they are allowed to view video and presentation materials. The main advantage of this way of teaching is the possibility of attending classes from any location and from any device; it is only important to be connected to the Internet. Methods: Full integration with the already existing Faculty Information System has been performed. The paper describes a new approach to teaching and illustrates the expected benefits of online teaching. The platforms used in this integration are Microsoft Azure, Microsoft Office 365 Admin, Microsoft Teams, Microsoft Stream and Microsoft SharePoint. Results: The result of the test of work with students showed that by introducing a system for online teaching, we directly affect the improvement and quality of teaching. Conclusion: Considering all the results, it can be concluded that the transition to the online way of teaching allows end listeners a comprehensive transfer of knowledge as well as re-listening to the same. This model can be used for an unlimited number of users in all Institutions, regardless of whether the field of activity of these Institutions is of educational origin.
- Identification of activities of daily living through data fusion on motion and magnetic sensors embedded on mobile devicesPublication . Pires, Ivan; Garcia, Nuno M.; Pombo, Nuno; Flórez-Revuelta, Francisco; Spinsante, Susanna; Teixeira, Maria Cristina CanavarroSeveral types of sensors have been available in off‐the‐shelf mobile devices, including motion, magnetic, vision, acoustic, and location sensors. This paper focuses on the fusion of the data acquired from motion and magnetic sensors, i.e., accelerometer, gyroscope and magnetometer sensors, for the recognition of Activities of Daily Living (ADL). Based on pattern recognition techniques, the system developed in this study includes data acquisition, data processing, data fusion, and classification methods like Artificial Neural Networks (ANN). Multiple settings of the ANN were implemented and evaluated in which the best accuracy obtained, with Deep Neural Networks (DNN), was 89.51%. This novel approach applies L2 regularization and normalization techniques on the sensors’ data proved it suitability and reliability for the ADL recognition.
- Information technologies for pain managementPublication . Pombo, Nuno Gonçalo Coelho Costa; Araújo, Pedro José Guerra; Viana, Joaquim Manuel Vieira da SilvaMillions of people around the world suffer from pain, acute or chronic and this raises the importance of its screening, assessment and treatment. The importance of pain is attested by the fact that it is considered the fifth vital sign for indicating basic bodily functions, health and quality of life, together with the four other vital signs: blood pressure, body temperature, pulse rate and respiratory rate. However, while these four signals represent an objective physical parameter, the occurrence of pain expresses an emotional status that happens inside the mind of each individual and therefore, is highly subjective that makes difficult its management and evaluation. For this reason, the self-report of pain is considered the most accurate pain assessment method wherein patients should be asked to periodically rate their pain severity and related symptoms. Thus, in the last years computerised systems based on mobile and web technologies are becoming increasingly used to enable patients to report their pain which lead to the development of electronic pain diaries (ED). This approach may provide to health care professionals (HCP) and patients the ability to interact with the system anywhere and at anytime thoroughly changes the coordinates of time and place and offers invaluable opportunities to the healthcare delivery. However, most of these systems were designed to interact directly to patients without presence of a healthcare professional or without evidence of reliability and accuracy. In fact, the observation of the existing systems revealed lack of integration with mobile devices, limited use of web-based interfaces and reduced interaction with patients in terms of obtaining and viewing information. In addition, the reliability and accuracy of computerised systems for pain management are rarely proved or their effects on HCP and patients outcomes remain understudied. This thesis is focused on technology for pain management and aims to propose a monitoring system which includes ubiquitous interfaces specifically oriented to either patients or HCP using mobile devices and Internet so as to allow decisions based on the knowledge obtained from the analysis of the collected data. With the interoperability and cloud computing technologies in mind this system uses web services (WS) to manage data which are stored in a Personal Health Record (PHR). A Randomised Controlled Trial (RCT) was implemented so as to determine the effectiveness of the proposed computerised monitoring system. The six weeks RCT evidenced the advantages provided by the ubiquitous access to HCP and patients so as to they were able to interact with the system anywhere and at anytime using WS to send and receive data. In addition, the collected data were stored in a PHR which offers integrity and security as well as permanent on line accessibility to both patients and HCP. The study evidenced not only that the majority of participants recommend the system, but also that they recognize it suitability for pain management without the requirement of advanced skills or experienced users. Furthermore, the system enabled the definition and management of patient-oriented treatments with reduced therapist time. The study also revealed that the guidance of HCP at the beginning of the monitoring is crucial to patients' satisfaction and experience stemming from the usage of the system as evidenced by the high correlation between the recommendation of the application, and it suitability to improve pain management and to provide medical information. There were no significant differences regarding to improvements in the quality of pain treatment between intervention group and control group. Based on the data collected during the RCT a clinical decision support system (CDSS) was developed so as to offer capabilities of tailored alarms, reports, and clinical guidance. This CDSS, called Patient Oriented Method of Pain Evaluation System (POMPES), is based on the combination of several statistical models (one-way ANOVA, Kruskal-Wallis and Tukey-Kramer) with an imputation model based on linear regression. This system resulted in fully accuracy related to decisions suggested by the system compared with the medical diagnosis, and therefore, revealed it suitability to manage the pain. At last, based on the aerospace systems capability to deal with different complex data sources with varied complexities and accuracies, an innovative model was proposed. This model is characterized by a qualitative analysis stemming from the data fusion method combined with a quantitative model based on the comparison of the standard deviation together with the values of mathematical expectations. This model aimed to compare the effects of technological and pen-and-paper systems when applied to different dimension of pain, such as: pain intensity, anxiety, catastrophizing, depression, disability and interference. It was observed that pen-and-paper and technology produced equivalent effects in anxiety, depression, interference and pain intensity. On the contrary, technology evidenced favourable effects in terms of catastrophizing and disability. The proposed method revealed to be suitable, intelligible, easy to implement and low time and resources consuming. Further work is needed to evaluate the proposed system to follow up participants for longer periods of time which includes a complementary RCT encompassing patients with chronic pain symptoms. Finally, additional studies should be addressed to determine the economic effects not only to patients but also to the healthcare system.
- Improving Activity Recognition Accuracy in Ambient-Assisted Living Systems by Automated Feature EngineeringPublication . Zdravevski, Eftim; Lameski, Petre; Trajkovik, Vladimir; Kulakov, Andrea; Chorbev, Ivan; Goleva, Rossitza; Pombo, Nuno; Garcia, Nuno M.Ambient-assisted living (AAL) is promising to become a supplement of the current care models, providing enhanced living experience to people within context-aware homes and smart environments. Activity recognition based on sensory data in AAL systems is an important task because 1) it can be used for estimation of levels of physical activity, 2) it can lead to detecting changes of daily patterns that may indicate an emerging medical condition, or 3) it can be used for detection of accidents and emergencies. To be accepted, AAL systems must be affordable while providing reliable performance. These two factors hugely depend on optimizing the number of utilized sensors and extracting robust features from them. This paper proposes a generic feature engineering method for selecting robust features from a variety of sensors, which can be used for generating reliable classi cation models. From the originally recorded time series and some newly generated time series [i.e., magnitudes, rst derivatives, delta series, and fast Fourier transformation (FFT)-based series], a variety of time and frequency domain features are extracted. Then, using two-phase feature selection, the number of generated features is greatly reduced. Finally, different classi cation models are trained and evaluated on an independent test set. The proposed method was evaluated on ve publicly available data sets, and on all of them, it yielded better accuracy than when using hand-tailored features. The bene ts of the proposed systematic feature engineering method are quickly discovering good feature sets for any given task than manually nding ones suitable for a particular task, selecting a small feature set that outperforms manually determined features in both execution time and accuracy, and identi cation of relevant sensor types and body locations automatically. Ultimately, the proposed method could reduce the cost of AAL systems by facilitating execution of algorithms on devices with limited resources and by using as few sensors as possible.
- Keyed User Datagram Protocol: Concepts and Operation of an Almost Reliable Connectionless Transport ProtocolPublication . Garcia, Nuno M.; Gil, Fabio; Matos, Barbara; Yahaya, Coulibaly; Pombo, Nuno; Goleva, RossitzaDeparting from the well-known problem of the excessive overhead and latency of connection oriented protocols, this paper describes a new almost reliable connectionless protocol that uses user datagram protocol (UDP) segment format and is UDP compatible. The problem is presented and described, the motivation, the possible areas of interest and the concept and base operation modes for the protocol named keyed UDP are presented (here called KUDP). Also, discussed are some of the possible manners in which the KUDP can be used, addressing potential problems related with current networking technologies. As UDP is a connectionless protocol, and KUDP allows for some degree of detection of loss and re-ordering of segments received out-of-sequence, we also present a proposal for a stream reconstruction algorithm. This paper ends by mentioning some of the research issues that still need to be addressed.