RESUMO
Land-use land-cover (LULC) change contributes to major ecological impacts, particularly in areas undergoing land abandonment, inducing modifications on habitat structure and species distributions. Alternative land-use policies are potential solutions to alleviate the negative impacts of contemporary tendencies of LULC change on biodiversity. This work analyzes these tendencies in the Montesinho Natural Park (Portugal), an area representative of European abandoned mountain rural areas. We built ecological niche models for 226 species of vertebrates (amphibians, reptiles, birds, and mammals) and vascular plants, using a consensus modelling approach available in the R package 'biomod2'. We projected the models to contemporary (2018) and future (2050) LULC scenarios, under four scenarios aiming to secure relevant ecosystem services and biodiversity conservation for 2050: an afforestation and a rewilding scenario, focused on climate-smart management strategies, and a farmland and an agroforestry recovery scenario, based on re-establishing human traditional activities. We quantified the influences of these scenarios on biodiversity through species habitat suitability changes for 2018-2050. We analyzed how these management strategies could influence indices of functional diversity (functional richness, functional evenness and functional dispersion) within the park. Habitat suitability changes revealed complementary patterns among scenarios. Afforestation and rewilding scenarios benefited more species adapted to habitats with low human influence, such as forests and open woodlands. The highest functional richness and dispersion was predicted for rewilding scenarios, which could improve landscape restoration and provide opportunities for the expansion and recolonization of forest areas by native species. The recovery of traditional farming and agroforestry activities results in the lowest values of functional richness, but these strategies contribute to complex landscape matrices with diversified habitats and resources. Moreover, this strategy could offer opportunities for fire suppression and increase landscape fire resistance. An integrative approach reconciling rewilding initiatives with the recovery of extensive agricultural and agroforestry activities is potentially an harmonious strategy for supporting the provision of ecosystem services while securing biodiversity conservation and functional diversity within the natural park.
Assuntos
Biodiversidade , Conservação dos Recursos Naturais , Ecossistema , Fazendas , Animais , Florestas , ClimaRESUMO
Background: The special area of conservation Montesinho/Nogueira (SAC-MN) is a key area for biodiversity conservation in the Iberian Peninsula. Covering an area of approximately 1081 km² in the northeast of Portugal mainland, the SAC-MN is home to a wide range of species, including several endemic and endangered species and priority habitats. Despite its ecological significance and importance for conservation, there is a lack of publicly available biodiversity data, which urges the need to create a comprehensive and up-to-date biodiversity dataset for the SAC-MN. New information: To bridge the knowledge gap on biodiversity in SAC-MN, we undertook a thorough data collection process, including species occurrence records and conservation status information at regional (Portugal) and European levels, from multiple sources. We collected and compiled this information for five major taxonomic groups (amphibians, birds, flora - vascular plants, mammals and reptiles) in SAC-MN, resulting in a total of 31,871 records with 1,312 documented species. In addition, we developed an easy-to-navigate web-based geographic information system (Web GIS). In this article, we present an in-depth report on the process of compiling and preparing data, as well as the development and design of our Web GIS to increase awareness and enhance understanding of the importance of preserving biodiversity in SAC-MN.
RESUMO
Worldwide, cardiovascular diseases are some of the primary causes of death; yet the early detection and diagnosis of such diseases have the potential to save many lives. Technological means of detection are becoming increasingly essential and numerous techniques have been created for this purpose, such as forecasting. Of these techniques, the time series forecasting technique seeks to predict future events. The long-term time series forecasting of physiological data could assist medical professionals in predicting and treating patients based on very early diagnosis. This article presents a model that utilizes a deep learning technique to predict long-term ECG signals. The forecasting model can learn signals' nonlinearity, nonstationarity, and complexity based on a long short-term memory architecture. However, this is not a trivial task as the correct forecasting of a signal that closely resembles the original complex signal's structure and behavior while minimizing any differences in amplitude continues to pose challenges. To achieve this goal, we used a dataset available on the Physio net database, called MIT-BIH, with 48 ECG recordings of 30 min each. The developed model starts with pre-processing to reduce interference in the original signals, then applies a deep learning algorithm, based on a long short-term memory (LTSM) neural network with two hidden layers. Next, we applied the root mean square error (RMSE) and mean absolute error (MAE) metrics to evaluate the performance of the model and obtained an average RMSE of 0.0070±0.0028 and an average MAE of 0.0522±0.0098 across all simulations. The results indicate that the proposed LSTM model is a promising technique for ECG forecasting, considering the trends of the changes in the original data series, most notably in R-peak amplitude. Given the model's accuracy and the features of the physiological signals, the system could be used to improve existing predictive healthcare systems for cardiovascular monitoring.
RESUMO
This paper presents a dataset related to the performance of the Ten Meter Walking Test, a test to allow locomotor capacity in different research and clinical settings. One of the most important parameters to measure is the gait speed during a path of ten meters. The data available in this dataset consists of accelerometer, magnetometer, and gyroscope data acquired with a mobile device in a waistband. The experiments were performed two times by 109 individuals (30 males and 79 females) in different senior residences in the Fundão municipality (Portugal). The dataset includes 208 samples because the sensors reported some failures. The acquisition of the sensors data allows the creation of a technological method for the automatic measurement of features related to the Ten Meter Walk Test, promoting patient independence in measuring their physical health status.
RESUMO
Ultrasound (US) imaging is used in the diagnosis and monitoring of COVID-19 and breast cancer. The presence of Speckle Noise (SN) is a downside to its usage since it decreases lesion conspicuity. Filters can be used to remove SN, but they involve time-consuming computation and parameter tuning. Several researchers have been developing complex Deep Learning (DL) models (150,000-500,000 parameters) for the removal of simulated added SN, without focusing on the real-world application of removing naturally occurring SN from original US images. Here, a simpler (<30,000 parameters) Convolutional Neural Network Autoencoder (CNN-AE) to remove SN from US images of the breast and lung is proposed. In order to do so, simulated SN was added to such US images, considering four different noise levels (σ = 0.05, 0.1, 0.2, 0.5). The original US images (N = 1227, breast + lung) were given as targets, while the noised US images served as the input. The Structural Similarity Index Measure (SSIM) and Peak Signal-to-Noise Ratio (PSNR) were used to compare the output of the CNN-AE and of the Median and Lee filters with the original US images. The CNN-AE outperformed the use of these classic filters for every noise level. To see how well the model removed naturally occurring SN from the original US images and to test its real-world applicability, a CNN model that differentiates malignant from benign breast lesions was developed. Several inputs were used to train the model (original, CNN-AE denoised, filter denoised, and noised US images). The use of the original US images resulted in the highest Matthews Correlation Coefficient (MCC) and accuracy values, while for sensitivity and negative predicted values, the CNN-AE-denoised US images (for higher σ values) achieved the best results. Our results demonstrate that the application of a simpler DL model for SN removal results in fewer misclassifications of malignant breast lesions in comparison to the use of original US images and the application of the Median filter. This shows that the use of a less-complex model and the focus on clinical practice applicability are relevant and should be considered in future studies.
RESUMO
Magnetic Resonance Imaging (MRI) typically comes at the cost of small spatial coverage, high expenses and long scan times. Accelerating MRI acquisition by taking less measurements yields the potential to relax these inherent forfeits. Recent breakthroughs in the field of Machine Learning have shown high-resolution (HR) images could be recovered from low-resolution (LR) signals via super-resolution (SR). In particular, a novel class of neural networks named Generative Adversarial Networks (GAN) has manifested an alternative way of conceiving models capable of generating data. GANs can learn to infer details based on some prior information, subsequently recovering missing data. Accordingly, they manifest huge potential in MRI reconstruction and acceleration tasks. This paper conducts a review on GAN-based SR methods, exhibiting the immersive ability of GANs on upscaling MRIs by a scale factor of ×4 while at the same time maintaining trustworthy and high-frequency details. Despite quantitative results suggesting SRResCycGAN outperforms other popular deep learning methods in recovering ×4 downgraded images, qualitative results show Beby-GAN holds the best perceptual quality and proves GAN-based methods hold the capacity to reduce medical costs, distress patients and even enable new MRI applications where it is currently too slow or expensive.
Assuntos
Aprendizado de Máquina , Imageamento por Ressonância Magnética , Humanos , Redes Neurais de ComputaçãoRESUMO
Studying changes in temperature is fundamental for understanding its interactions with the environment and biodiversity. However, studies in mountainous areas are few, due to their complex formation and the difficulty of obtaining local data. We analysed changes in temperature over time in Montesinho Natural Park (MNP) (Bragança, Portugal), an important conservation area due to its high level of biodiversity. Specifically, we aimed to analyse: i) whether temperature increased in MNP over time, ii) what environmental factors influence the Land Surface Temperature (LST), and iii) whether vegetation is related to changes in temperature. We used annual summer and winter mean data acquired from the Moderate-Resolution Imaging Spectroradiometer (MODIS) datasets/products (e.g. LST, gathered at four different times: 11am, 1pm, 10pm and 2am, Enhance vegetation index - EVI, and Evapotranspiration - ET), available on the cloud-based platform Google Earth Engine between 2003 and 2021). We analysed the dynamics of the temporal trend patterns between the LST and local thermal data (from a weather station) by correlations; the trends in LST over time with the Mann-Kendall trend test; and the stability of hot spots and cold spots of LST with Local Statistics of Spatial Association (LISA) tests. The temporal trend patterns between LST and Air Temperature (Tair) data were very similar (ρ > 0.7). The temperature in the MNP remained stable over time during summer but increased during winter nights. The biophysical indices were strongly correlated with the summer LST at 11am and 1pm. The LISA results identified hot and cold zones that remained stable over time. The remote-sensed data proved to be efficient in measuring changes in temperature over time.
RESUMO
Physical issues started to receive more attention due to the sedentary lifestyle prevalent in modern culture. The Ten Meter Walk Test allows measuring the person's capacity to walk along 10 m and analyzing the advancement of various medical procedures for ailments, including stroke. This systematic review is related to the use of mobile or wearable devices to measure physical parameters while administering the Ten Meter Walk Test for the analysis of the performance of the test. We applied the PRISMA methodology for searching the papers related to the Ten Meter Walk Test. Natural Language Processing (NLP) algorithms were used to automate the screening process. Various papers published in two decades from multiple scientific databases, including IEEE Xplore, Elsevier, Springer, EMBASE, SCOPUS, Multidisciplinary Digital Publishing Institute (MDPI), and PubMed Central were analyzed, focusing on various diseases, devices, features, and methods. The study reveals that chronometer and accelerometer sensors measuring spatiotemporal features are the most pertinent in the Gait characterization of most diseases. Likewise, all studies emphasized the close relation between the quality of the sensor's data obtained and the system's ultimate accuracy. In other words, calibration procedures are needed because of the body part where the sensor is worn and the type of sensor. In addition, using ambient sensors providing kinematic and kinetic features in conjunction with wearable sensors and consistently acquiring walking signals can enhance the system's performance. The most common weaknesses in the analyzed studies are the sample size and the unavailability of continuous monitoring devices for measuring the Ten Meter Walk Test.
RESUMO
[This corrects the article DOI: 10.1016/j.dib.2022.108874.].
RESUMO
Breast cancer was the most diagnosed cancer around the world in 2020. Screening programs, based on mammography, aim to achieve early diagnosis which is of extreme importance when it comes to cancer. There are several flaws associated with mammography, with one of the most important being tissue overlapping that can result in both lesion masking and fake-lesion appearance. To overcome this, digital breast tomosynthesis takes images (slices) at different angles that are later reconstructed into a 3D image. Having in mind that the slices are planar images where tissue overlapping does not occur, the goal of the work done here was to develop a deep learning model that could, based on the said slices, classify lesions as benign or malignant. The developed model was based on the work done by Muduli et. al, with a slight change in the fully connected layers and in the regularization done. In total, 77 DBT volumes-39 benign and 38 malignant-were available. From each volume, nine slices were taken, one where the lesion was most visible and four above/below. To increase the quantity and the variability of the data, common data augmentation techniques (rotation, translation, mirroring) were applied to the original images three times. Therefore, 2772 images were used for training. Data augmentation techniques were then applied two more times-one set used for validation and one set used for testing. Our model achieved, on the testing set, an accuracy of 93.2% while the values of sensitivity, specificity, precision, F1-score, and Cohen's kappa were 92%, 94%, 94%, 94%, and 0.86, respectively. Given these results, the work done here suggests that the use of single-slice DBT can compare to state-of-the-art studies and gives a hint that with more data, better augmentation techniques and the use of transfer learning might overcome the use of mammograms in this type of studies.
Assuntos
Neoplasias da Mama , Mamografia , Humanos , Feminino , Mamografia/métodos , Neoplasias da Mama/diagnóstico por imagem , Redes Neurais de Computação , Imageamento Tridimensional/métodos , Interpretação de Imagem Radiográfica Assistida por Computador/métodosRESUMO
The prevalence of cardiovascular diseases is increasing around the world. However, the technology is evolving and can be monitored with low-cost sensors anywhere at any time. This subject is being researched, and different methods can automatically identify these diseases, helping patients and healthcare professionals with the treatments. This paper presents a systematic review of disease identification, classification, and recognition with ECG sensors. The review was focused on studies published between 2017 and 2022 in different scientific databases, including PubMed Central, Springer, Elsevier, Multidisciplinary Digital Publishing Institute (MDPI), IEEE Xplore, and Frontiers. It results in the quantitative and qualitative analysis of 103 scientific papers. The study demonstrated that different datasets are available online with data related to various diseases. Several ML/DP-based models were identified in the research, where Convolutional Neural Network and Support Vector Machine were the most applied algorithms. This review can allow us to identify the techniques that can be used in a system that promotes the patient's autonomy.
RESUMO
It is increasingly possible to acquire Electrocardiographic data with featured low-cost devices. The proposed dataset will help map different signals for various diseases related to Electrocardiography data. The dataset presented in this paper is related to the acquisition of electrocardiography data during the standing up and seated positions. The data was collected from 219 individuals (112 men, 106 women, and one other) in different environments, but they are in the Covilhã municipality. The dataset includes the 219 recordings and corresponds to the sensors' recordings of a 30 s sitting and a 30 s standing test, which checks to approximately 1 min for each one. This dataset includes 3.7 h (approximately) of recordings for further analysis with data processing techniques and machine learning methods. It will be helpful for the complementary creation of a robust method for identifying the characteristics of individuals related to Electrocardiography signals.
RESUMO
Nowadays, individuals have very stressful lifestyles, affecting their nutritional habits. In the early stages of life, teenagers begin to exhibit bad habits and inadequate nutrition. Likewise, other people with dementia, Alzheimer's disease, or other conditions may not take food or medicine regularly. Therefore, the ability to monitor could be beneficial for them and for the doctors that can analyze the patterns of eating habits and their correlation with overall health. Many sensors help accurately detect food intake episodes, including electrogastrography, cameras, microphones, and inertial sensors. Accurate detection may provide better control to enable healthy nutrition habits. This paper presents a systematic review of the use of technology for food intake detection, focusing on the different sensors and methodologies used. The search was performed with a Natural Language Processing (NLP) framework that helps screen irrelevant studies while following the PRISMA methodology. It automatically searched and filtered the research studies in different databases, including PubMed, Springer, ACM, IEEE Xplore, MDPI, and Elsevier. Then, the manual analysis selected 30 papers based on the results of the framework for further analysis, which support the interest in using sensors for food intake detection and nutrition assessment. The mainly used sensors are cameras, inertial, and acoustic sensors that handle the recognition of food intake episodes with artificial intelligence techniques. This research identifies the most used sensors and data processing methodologies to detect food intake.
Assuntos
Inteligência Artificial , Avaliação Nutricional , Adolescente , Ingestão de Alimentos , Comportamento Alimentar , Alimentos , HumanosRESUMO
Breast cancer was the most diagnosed cancer in 2020. Several thousand women continue to die from this disease. A better and earlier diagnosis may be of great importance to improving prognosis, and that is where Artificial Intelligence (AI) could play a major role. This paper surveys different applications of AI in Breast Imaging. First, traditional Machine Learning and Deep Learning methods that can detect the presence of a lesion and classify it into benign/malignant-which could be important to diminish reading time and improve accuracy-are analyzed. Following that, researches in the field of breast cancer risk prediction using mammograms-which may be able to allow screening programs customization both on periodicity and modality-are reviewed. The subsequent section analyzes different applications of augmentation techniques that allow to surpass the lack of labeled data. Finally, still concerning the absence of big datasets with labeled data, the last section studies Self-Supervised learning, where AI models are able to learn a representation of the input by themselves. This review gives a general view of what AI can give in the field of Breast Imaging, discussing not only its potential but also the challenges that still have to be overcome.
RESUMO
Rehabilitation aims to increase the independence and physical function after injury, surgery, or other trauma, so that patients can recover to their previous ability as much as possible. To be able to measure the degree of recovery and impact of the treatment, various functional performance tests are used. The Eight Hop Test is a hop exercise that is directly linked to the rehabilitation of people suffering from tendon and ligament injuries on the lower limb. This paper presents a systematic review on the use of sensors for measuring functional movements during the execution of the Eight Hop Test, focusing primarily on the use of sensors, related diseases, and different methods implemented. Firstly, an automated search was performed on the publication databases: PubMed, Springer, ACM, IEEE Xplore, MDPI, and Elsevier. Secondly, the publications related to the Eight-Hop Test and sensors were filtered according to several search criteria and 15 papers were finally selected to be analyzed in detail. Our analysis found that the Eight Hop Test measurements can be performed with motion, force, and imaging sensors.
Assuntos
Lesões do Ligamento Cruzado Anterior , Teste de Esforço , Exercício Físico , Teste de Esforço/métodos , Humanos , Extremidade Inferior , Movimento , Desempenho Físico FuncionalRESUMO
The dataset presented in this paper presents a dataset related to three motionless activities, including driving, watching TV, and sleeping. During these activities, the mobile device may be positioned in different locations, including the pants pockets, in a wristband, over the bedside table, on a table, inside the car, or on other furniture, for the acquisition of accelerometer, magnetometer, gyroscope, GPS, and microphone data. The data was collected by 25 individuals (15 men and 10 women) in different environments in Covilhã and Fundão municipalities (Portugal). The dataset includes the sensors' captures related to a minimum of 2000 captures for each motionless activity, which corresponds to 2.8 h (approximately) for each one. This dataset includes 8.4 h (approximately) of captures for further analysis with data processing techniques, and machine learning methods. It will be useful for the complementary creation of a robust method for the identification of these type of activities.
Assuntos
Atividades Cotidianas , Aprendizado de Máquina , Acelerometria , Condução de Veículo , Humanos , Movimento , PortugalRESUMO
Medicine is heading towards personalized care based on individual situations and conditions. With smartphones and increasingly miniaturized wearable devices, the sensors available on these devices can perform long-term continuous monitoring of several user health-related parameters, making them a powerful tool for a new medicine approach for these patients. Our proposed system, described in this article, aims to develop innovative solutions based on artificial intelligence techniques to empower patients with cardiovascular disease. These solutions will realize a novel 5P (Predictive, Preventive, Participatory, Personalized, and Precision) medicine approach by providing patients with personalized plans for treatment and increasing their ability for self-monitoring. Such capabilities will be derived by learning algorithms from physiological data and behavioral information, collected using wearables and smart devices worn by patients with health conditions. Further, developing an innovative system of smart algorithms will also focus on providing monitoring techniques, predicting extreme events, generating alarms with varying health parameters, and offering opportunities to maintain active engagement of patients in the healthcare process by promoting the adoption of healthy behaviors and well-being outcomes. The multiple features of this future system will increase the quality of life for cardiovascular diseases patients and provide seamless contact with a healthcare professional.
Assuntos
Inteligência Artificial , Dispositivos Eletrônicos Vestíveis , Atenção à Saúde , Humanos , Qualidade de Vida , SmartphoneRESUMO
Healthcare treatments might benefit from advances in artificial intelligence and technological equipment such as smartphones and smartwatches. The presence of cameras in these devices with increasingly robust and precise pattern recognition techniques can facilitate the estimation of the wound area and other telemedicine measurements. Currently, telemedicine is vital to the maintenance of the quality of the treatments remotely. This study proposes a method for measuring the wound area with mobile devices. The proposed approach relies on a multi-step process consisting of image capture, conversion to grayscale, blurring, application of a threshold with segmentation, identification of the wound part, dilation and erosion of the detected wound section, identification of accurate data related to the image, and measurement of the wound area. The proposed method was implemented with the OpenCV framework. Thus, it is a solution for healthcare systems by which to investigate and treat people with skin-related diseases. The proof-of-concept was performed with a static dataset of camera images on a desktop computer. After we validated the approach's feasibility, we implemented the method in a mobile application that allows for communication between patients, caregivers, and healthcare professionals.
Assuntos
Aplicativos Móveis , Telemedicina , Inteligência Artificial , Atenção à Saúde , Humanos , SmartphoneRESUMO
BACKGROUND AND AIM: Hypoglycaemia prediction play an important role in diabetes management being able to reduce the number of dangerous situations. Thus, it is relevant to present a systematic review on the currently available prediction algorithms and models for hypoglycaemia (or hypoglycemia in US English) prediction. METHODS: This study aims to systematically review the literature on data-based algorithms and models using diabetics real data for hypoglycaemia prediction. Five electronic databases were screened for studies published from January 2014 to June 2020: ScienceDirect, IEEE Xplore, ACM Digital Library, SCOPUS, and PubMed. RESULTS: Sixty-three eligible studies were retrieved that met the inclusion criteria. The review identifies the current trend in this topic: most of the studies perform short-term predictions (82.5%). Also, the review pinpoints the inputs and shows that information fusion is relevant for hypoglycaemia prediction. Regarding data-based models (80.9%) and hybrid models (19.1%) different predictive techniques are used: Artificial neural network (22.2%), ensemble learning (27.0%), supervised learning (20.6%), statistic/probabilistic (7.9%), autoregressive (7.9%), evolutionary (6.4%), deep learning (4.8%) and adaptative filter (3.2%). Artificial Neural networks and hybrid models show better results. CONCLUSIONS: The data-based models for blood glucose and hypoglycaemia prediction should be able to provide a good balance between the applicability and performance, integrating complementary data from different sources or from different models. This review identifies trends and possible opportunities for research in this topic.