RESUMO
The increasing prevalence of diet-related diseases calls for an improvement in nutritional advice. Personalized nutrition aims to solve this problem by adapting dietary and lifestyle guidelines to the unique circumstances of each individual. With the latest advances in technology and data science, researchers can now automatically collect and analyze large amounts of data from a variety of sources, including wearable and smart devices. By combining these diverse data, more comprehensive insights of the human body and its diseases can be achieved. However, there are still major challenges to overcome, including the need for more robust data and standardization of methodologies for better subject monitoring and assessment. Here, we present the AI4Food database (AI4FoodDB), which gathers data from a nutritional weight loss intervention monitoring 100 overweight and obese participants during 1 month. Data acquisition involved manual traditional approaches, novel digital methods and the collection of biological samples, obtaining: (i) biological samples at the beginning and the end of the intervention, (ii) anthropometric measurements every 2 weeks, (iii) lifestyle and nutritional questionnaires at two different time points and (iv) continuous digital measurements for 2 weeks. To the best of our knowledge, AI4FoodDB is the first public database that centralizes food images, wearable sensors, validated questionnaires and biological samples from the same intervention. AI4FoodDB thus has immense potential for fostering the advancement of automatic and novel artificial intelligence techniques in the field of personalized care. Moreover, the collected information will yield valuable insights into the relationships between different variables and health outcomes, allowing researchers to generate and test new hypotheses, identify novel biomarkers and digital endpoints, and explore how different lifestyle, biological and digital factors impact health. The aim of this article is to describe the datasets included in AI4FoodDB and to outline the potential that they hold for precision health research. Database URL https://github.com/AI4Food/AI4FoodDB.
Assuntos
Telemedicina , Dispositivos Eletrônicos Vestíveis , Humanos , Inteligência Artificial , Dieta , Estilo de VidaRESUMO
BACKGROUND: Mental fatigue is a common and potentially debilitating state that can affect individuals' health and quality of life. In some cases, its manifestation can precede or mask early signs of other serious mental or physiological conditions. Detecting and assessing mental fatigue can be challenging nowadays as it relies on self-evaluation and rating questionnaires, which are highly influenced by subjective bias. Introducing more objective, quantitative, and sensitive methods to characterize mental fatigue could be critical to improve its management and the understanding of its connection to other clinical conditions. OBJECTIVE: This paper aimed to study the feasibility of using keystroke biometrics for mental fatigue detection during natural typing. As typing involves multiple motor and cognitive processes that are affected by mental fatigue, our hypothesis was that the information captured in keystroke dynamics can offer an interesting mean to characterize users' mental fatigue in a real-world setting. METHODS: We apply domain transformation techniques to adapt and transform TypeNet, a state-of-the-art deep neural network, originally intended for user authentication, to generate a network optimized for the fatigue detection task. All experiments were conducted using 3 keystroke databases that comprise different contexts and data collection protocols. RESULTS: Our preliminary results showed area under the curve performances ranging between 72.2% and 80% for fatigue versus rested sample classification, which is aligned with previously published models on daily alertness and circadian cycles. This demonstrates the potential of our proposed system to characterize mental fatigue fluctuations via natural typing patterns. Finally, we studied the performance of an active detection approach that leverages the continuous nature of keystroke biometric patterns for the assessment of users' fatigue in real time. CONCLUSIONS: Our results suggest that the psychomotor patterns that characterize mental fatigue manifest during natural typing, which can be quantified via automated analysis of users' daily interaction with their device. These findings represent a step towards the development of a more objective, accessible, and transparent solution to monitor mental fatigue in a real-world environment.
RESUMO
Atrial fibrillation (AF) is an abnormal heart rhythm, asymptomatic in many cases, that causes several health problems and mortality in population. This retrospective study evaluates the ability of different AI-based models to predict future episodes of AF from electrocardiograms (ECGs) recorded during normal sinus rhythm. Patients are divided into two classes according to AF occurrence or sinus rhythm permanence along their several ECGs registry. In the constrained scenario of balancing the age distributions between classes, our best AI model predicts future episodes of AF with area under the curve (AUC) 0.79 (0.72-0.86). Multiple scenarios and age-sex-specific groups of patients are considered, achieving best performance of prediction for males older than 70 years. These results point out the importance of considering different demographic groups in the analysis of AF prediction, showing considerable performance gaps among them. In addition to the demographic analysis, we apply feature visualization techniques to identify the most important portions of the ECG signals in the task of AF prediction, improving this way the interpretability and understanding of the AI models. These results and the simplicity of recording ECGs during check-ups add feasibility to clinical applications of AI-based models.
Assuntos
Inteligência Artificial , Fibrilação Atrial/diagnóstico , Eletrocardiografia/métodos , Frequência Cardíaca , Sistema de Registros/estatística & dados numéricos , Adolescente , Adulto , Idoso , Idoso de 80 Anos ou mais , Área Sob a Curva , Fibrilação Atrial/diagnóstico por imagem , Demografia , Feminino , Seguimentos , Humanos , Masculino , Pessoa de Meia-Idade , Prognóstico , Estudos Retrospectivos , Fatores de Risco , Adulto JovemRESUMO
This work proposes a novel privacy-preserving neural network feature representation to suppress the sensitive information of a learned space while maintaining the utility of the data. The new international regulation for personal data protection forces data controllers to guarantee privacy and avoid discriminative hazards while managing sensitive data of users. In our approach, privacy and discrimination are related to each other. Instead of existing approaches aimed directly at fairness improvement, the proposed feature representation enforces the privacy of selected attributes. This way fairness is not the objective, but the result of a privacy-preserving learning method. This approach guarantees that sensitive information cannot be exploited by any agent who process the output of the model, ensuring both privacy and equality of opportunity. Our method is based on an adversarial regularizer that introduces a sensitive information removal function in the learning objective. The method is evaluated on three different primary tasks (identity, attractiveness, and smiling) and three publicly available benchmarks. In addition, we present a new face annotation dataset with balanced distribution between genders and ethnic origins. The experiments demonstrate that it is possible to improve the privacy and equality of opportunity while retaining competitive performance independently of the task.
Assuntos
Algoritmos , Privacidade , Segurança Computacional , Feminino , Humanos , Aprendizagem , Masculino , Redes Neurais de ComputaçãoRESUMO
Human footsteps can provide a unique behavioural pattern for robust biometric systems. We propose spatio-temporal footstep representations from floor-only sensor data in advanced computational models for automatic biometric verification. Our models deliver an artificial intelligence capable of effectively differentiating the fine-grained variability of footsteps between legitimate users (clients) and impostor users of the biometric system. The methodology is validated in the largest to date footstep database, containing nearly 20,000 footstep signals from more than 120 users. The database is organized by considering a large cohort of impostors and a small set of clients to verify the reliability of biometric systems. We provide experimental results in 3 critical data-driven security scenarios, according to the amount of footstep data made available for model training: at airports security checkpoints (smallest training set), workspace environments (medium training set) and home environments (largest training set). We report state-of-the-art footstep recognition rates with an optimal equal false acceptance and false rejection rate (equal error rate) of 0.7 percent an improvement ratio of 371 percent compared to previous state-of-the-art. We perform a feature analysis of deep residual neural networks showing effective clustering of client's footstep data and to provide insights of the feature learning process.
Assuntos
Identificação Biométrica/métodos , Aprendizado Profundo , Pé/fisiologia , Gravação em Vídeo/métodos , Bases de Dados Factuais , Humanos , Reconhecimento Automatizado de Padrão , PressãoRESUMO
This paper describes the design, acquisition process and baseline evaluation of the new e-BioSign database, which includes dynamic signature and handwriting information. Data is acquired from 5 different COTS devices: three Wacom devices (STU-500, STU-530 and DTU-1031) specifically designed to capture dynamic signatures and handwriting, and two general purpose tablets (Samsung Galaxy Note 10.1 and Samsung ATIV 7). For the two Samsung tablets, data is collected using both pen stylus and also the finger in order to study the performance of signature verification in a mobile scenario. Data was collected in two sessions for 65 subjects, and includes dynamic information of the signature, the full name and alpha numeric sequences. Skilled forgeries were also performed for signatures and full names. We also report a benchmark evaluation based on e-BioSign for person verification under three different real scenarios: 1) intra-device, 2) inter-device, and 3) mixed writing-tool. We have experimented the proposed benchmark using the main existing approaches for signature verification: feature- and time functions-based. As a result, new insights into the problem of signature biometrics in sensor-interoperable scenarios have been obtained, namely: the importance of specific methods for dealing with device interoperability, and the necessity of a deeper analysis on signatures acquired using the finger as the writing tool. This e-BioSign public database allows the research community to: 1) further analyse and develop signature verification systems in realistic scenarios, and 2) investigate towards a better understanding of the nature of the human handwriting when captured using electronic COTS devices in realistic conditions.
Assuntos
Benchmarking , Biometria , Bases de Dados Factuais , Escrita ManualRESUMO
This paper proposes a functional feature-based approach useful for real forensic caseworks, based on the shape, orientation and size of facial traits, which can be considered as a soft biometric approach. The motivation of this work is to provide a set of facial features, which can be understood by non-experts such as judges and support the work of forensic examiners who, in practice, carry out a thorough manual comparison of face images paying special attention to the similarities and differences in shape and size of various facial traits. This new approach constitutes a tool that automatically converts a set of facial landmarks to a set of features (shape and size) corresponding to facial regions of forensic value. These features are furthermore evaluated in a population to generate statistics to support forensic examiners. The proposed features can also be used as additional information that can improve the performance of traditional face recognition systems. These features follow the forensic methodology and are obtained in a continuous and discrete manner from raw images. A statistical analysis is also carried out to study the stability, discrimination power and correlation of the proposed facial features on two realistic databases: MORPH and ATVS Forensic DB. Finally, the performance of both continuous and discrete features is analyzed using different similarity measures. Experimental results show high discrimination power and good recognition performance, especially for continuous features. A final fusion of the best systems configurations achieves rank 10 match results of 100% for ATVS database and 75% for MORPH database demonstrating the benefits of using this information in practice.
Assuntos
Pontos de Referência Anatômicos , Identificação Biométrica , Face/anatomia & histologia , Bases de Dados Factuais , Ciências Forenses/métodos , HumanosRESUMO
This article presents an experimental analysis of the combination of different regions of the human face on various forensic scenarios to generate scientific knowledge useful for the forensic experts. Three scenarios of interest at different distances are considered comparing mugshot and CCTV face images using MORPH and SC face databases. One of the main findings is that inner facial regions combine better in mugshot and close CCTV scenarios and outer facial regions combine better in far CCTV scenarios. This means, that depending of the acquisition distance, the discriminative power of the facial regions change, having in some cases better performance than the full face. This effect can be exploited by considering the fusion of facial regions which results in a very significant improvement of the discriminative performance compared to just using the full face.
Assuntos
Face/anatomia & histologia , Reconhecimento Facial , Pontos de Referência Anatômicos , Ciências Forenses , Humanos , Fotografação , Análise de Componente Principal , Máquina de Vetores de Suporte , TelevisãoRESUMO
This paper reports an exhaustive analysis of the discriminative power of the different regions of the human face on various forensic scenarios. In practice, when forensic examiners compare two face images, they focus their attention not only on the overall similarity of the two faces. They carry out an exhaustive morphological comparison region by region (e.g., nose, mouth, eyebrows, etc.). In this scenario it is very important to know based on scientific methods to what extent each facial region can help in identifying a person. This knowledge obtained using quantitative and statical methods on given populations can then be used by the examiner to support or tune his observations. In order to generate such scientific knowledge useful for the expert, several methodologies are compared, such as manual and automatic facial landmarks extraction, different facial regions extractors, and various distances between the subject and the acquisition camera. Also, three scenarios of interest for forensics are considered comparing mugshot and Closed-Circuit TeleVision (CCTV) face images using MORPH and SCface databases. One of the findings is that depending of the acquisition distances, the discriminative power of the facial regions change, having in some cases better performance than the full face.
Assuntos
Identificação Biométrica/métodos , Face/anatomia & histologia , Bases de Dados como Assunto , Feminino , Humanos , Processamento de Imagem Assistida por Computador , Masculino , Fotografação , Gravação em VídeoRESUMO
Footstep recognition is a relatively new biometric which aims to discriminate people using walking characteristics extracted from floor-based sensors. This paper reports for the first time a comparative assessment of the spatiotemporal information contained in the footstep signals for person recognition. Experiments are carried out on the largest footstep database collected to date, with almost 20,000 valid footstep signals and more than 120 people. Results show very similar performance for both spatial and temporal approaches (5 to 15 percent EER depending on the experimental setup), and a significant improvement is achieved for their fusion (2.5 to 10 percent EER). The assessment protocol is focused on the influence of the quantity of data used in the reference models, which serves to simulate conditions of different potential applications such as smart homes or security access scenarios.