Browsing by Subject "Pipelines"

Now showing 1 - 2 of 2
  • Thumbnail Image
    Item
    3D Facial Matching by Spiral Convolutional Metric Learning and a Biometric Fusion-Net of Demographic Properties
    (IEEE, 2021) Mahdi, Soha Sadat; Nauwelaers, Nele; Joris, Philip; Bouritsas, Giorgos; Gong, Shunwang; Bokhnyak, Sergiy; Walsh, Susan; Shriver, Mark D.; Bronstein, Michael; Claes, Peter; Biology, School of Science
    Face recognition is a widely accepted biometric verification tool, as the face contains a lot of information about the identity of a person. In this study, a 2-step neural-based pipeline is presented for matching 3D facial shape to multiple DNA-related properties (sex, age, BMI and genomic background). The first step consists of a triplet loss-based metric learner that compresses facial shape into a lower dimensional embedding while preserving information about the property of interest. Most studies in the field of metric learning have only focused on 2D Euclidean data. In this work, geometric deep learning is employed to learn directly from 3D facial meshes. To this end, spiral convolutions are used along with a novel mesh-sampling scheme that retains uniformly sampled 3D points at different levels of resolution. The second step is a multi-biometric fusion by a fully connected neural network. The network takes an ensemble of embeddings and property labels as input and returns genuine and imposter scores. Since embeddings are accepted as an input, there is no need to train classifiers for the different properties and available data can be used more efficiently. Results obtained by a to-fold cross-validation for biometric verification show that combining multiple properties leads to stronger biometric systems. Furthermore, the proposed neural-based pipeline outperforms a linear baseline, which consists of principal component analysis, followed by classification with linear support vector machines and a Naïve Bayes-based score-fuser.
  • Thumbnail Image
    Item
    Remote Assessment of ADHD Symptoms Based on Mobile Game Performance in Children with ADHD: A Proof of Concept
    (IEEE, 2023-07) Song, Jeong-Heon; Kim, Byeongil; Kim, Seon-Chil; Toom, Niharika; Kaur, Charanjit; Rodriguez, Gabriela Marie; Hord, Melissa Kay; Jung, Hee-Tae; Psychiatry, School of Medicine
    The use of game-based digital medicine is gaining increasing interest in helping children with ADHD to improve their attention outside the clinical setting. In this process, it is important to continue monitoring children’s responses to the use of digital medicine. In this work, we introduce novel digital markers and an analytic pipeline to estimate ADHD-related symptomatic levels during the self-administration of attention games. The digital markers, capturing the children’s characteristics of attention and inattention spans, were extracted and translated into clinically-accepted measures of ADHD symptoms, specifically the ADHD-Rating Scale (ADHD-RS) and Child Behavior Checklist (CBCL). To validate the feasibility of our approach, we collected game-specific performance data from 15 children with ADHD, which was used to train machine learning-based regression models to estimate their corresponding ADHD-RS and CBCL scores. Our experiment results showed mean absolute errors of 5.14 and 4.05 points between the actual and estimated ADHD-RS and CBCL scores respectively. This study enables new clinical and research opportunities for accurate longitudinal assessment of symptomatic levels of ADHD via an interactive means of playing mobile games.