Graph embedding improves fMRI classification and reveals brain region differences in ASD.
problem Difficult to embed informative brain fMRI representations due to high dimensionality and low SNR.
method Modelled fMRI as a graph, used GNN to learn from graph data, incorporated mutual information loss (Infomax).
result Infomax graph embedding improves classification performance and reveals separable nodal representations of ASD and HC groups.
The goal of the present study is to identify autism using machine learning techniques and resting-state brain imaging data, leveraging the temporal variability of the functional connections (FC) as the only information. We estimated and compared the FC variability across brain regions between typical, healthy subjects …
Machine learning improves ASD diagnosis accuracy.
problem Early detection and treatment of ASD.
method Machine learning, specifically SMO-SVM and Relief Attributes.
result SMO-SVM classifier outperforms other algorithms in ASD detection.
Deep learning aids in autism diagnosis and rehabilitation using neuroimaging data.
problem Challenges in automated detection and rehabilitation of ASD using neuroimaging data.
method Deep learning techniques applied to neuroimaging data for ASD diagnosis and rehabilitation.
result Deep learning improves accuracy in ASD diagnosis and rehabilitation.
Autism Spectrum Disorder (ASD) is a developmental disorder that often impairs a child's normal development of the brain. According to CDC, it is estimated that 1 in 6 children in the US suffer from development disorders, and 1 in 68 children in the US suffer from ASD. This condition has a negative impact on a person's …
Deep-learning model detects ASD from MRI data with high accuracy.
problem Challenges in diagnosing ASD due to subjective behavioral assessments and informant biases.
method Integrates deep-learning and SVM techniques to classify ASD brain scans.
result Highly accurate classification of ASD brain scans from neurotypical scans.
The article provides conditions for unobstructedness of ASD manifolds.
problem Understanding the local structure of moduli spaces of ASD conformal structures.
method Conformally invariant conditions for ASD manifolds of positive Yamabe type.
result ASD manifolds of positive Yamabe type are unobstructed.
Machine learning for ASD diagnosis using morphological MRI networks.
problem Challenging to diagnose ASD using MRI due to heterogeneity and incomplete network neuroscience.
method Crowdsourced Kaggle competition to develop and benchmark ML pipelines.
result First-ranked team achieved 70% accuracy, 72.5% sensitivity, and 67.5% specificity.
DCASE 2022 Task 2 tackles domain shifts in ASD for machine condition monitoring.
problem Domain shifts change acoustic characteristics, affecting ASD performance.
method Domain generalization techniques to detect anomalies across unknown domains.
result Two types of domain generalization techniques were identified and analyzed.
We study a moduli space of ASD connections over S3×R. We consider not only finite energy ASD connections but also infinite energy ones. So the moduli space is infinite dimensional in general. We study the (local) mean dimension of this infinite dimensional moduli space. We show the upper bound on the …
We present an approach to model time series data from resting state fMRI for autism spectrum disorder (ASD) severity classification. We propose to adopt kernel machines and employ graph kernels that define a kernel dot product between two graphs. This enables us to take advantage of spatio-temporal information to captu…
Autism spectrum condition (ASC) or autism spectrum disorder (ASD) is primarily identified with the help of behavioral indications encompassing social, sensory and motor characteristics. Although categorized, recurring motor actions are measured during diagnosis, quantifiable measures that ascertain kinematic physiognom…
We study an infinite dimensional ASD moduli space over the cylinder. Our main result is the formula of its local mean dimension. A key ingredient of the argument is the notion of non-degenerate ASD connections. We develop its deformation theory and show that there exist sufficiently many non-degenerate ASD connections …
Game teaches ASD teenagers to imitate gestures.
problem Improving social interactions of ASD teenagers.
method Adapted robot-based imitation game with machine learning for pose detection.
result Preliminary results show game can elicit expected responses.
Extends ASD connection existence to 4-manifolds with cylindrical ends.
problem Existence of ASD connections on 4-manifolds with specific ends.
method Extends gluing theorems to cylindrical ends, using mASD connections.
result Establishes existence of ASD connections on 4-manifolds with cylindrical ends.
In this paper we announce a gluing theorem for conformal structures with anti-self-dual (ASD) Weyl tensor that applies in geometrical situations that are more general than those considered by previous authors. By adapting a method proposed by Floer, sufficient conditions are given for the existence of ASD conformal str…
The paper defines ASD connections and constructs families over a 5D Heisenberg group.
problem Defining and constructing ASD connections over a 5D Heisenberg group.
method Geometric approach using twistor spaces and Atiyah-Ward ansätz.
result Construction of families of ASD connections and their relation to vector bundles.
Mental disorders such as Autism Spectrum Disorders (ASD) are heterogeneous disorders that are notoriously difficult to diagnose, especially in children. The current psychiatric diagnostic process is based purely on the behavioural observation of symptomology (DSM-5/ICD-10) and may be prone to over-prescribing of drugs …
Game aims to improve social interactions for teenagers with ASD.
problem Improving social interactions for teenagers with ASD.
method Presentation of game structure, skeleton detection, and imitation learning methods.
result Game structure and support tools for skeleton detection and imitation learning presented.
We prove a sharp lower bound on the curvatures of non-flat ASD connections over the cylinder.
Anti-self-dual (ASD) connections for a compact smooth four manifold arise as critical values for the Yang-Mills action functional. Nahm transform is a nice correspondence between a vector bundle with ASD connections and a vector bundle with ASD connections over Picard torus associated to X. In this talk we propose a no…
We give new and rather general gluing theorems for anti-self-dual (ASD) conformal structures, following the method suggested by Floer. The main result is a gluing theorem for pairs of conformally ASD manifolds `joined' across a common piece (union of connected components) of their boundaries. This theorem genuinely ope…
Objective. The paper investigates the presence of autism using the functional brain connectivity measures derived from electro-encephalogram (EEG) of children during face perception tasks. Approach. Phase synchronized patterns from 128-channel EEG signals are obtained for typical children and children with autism spect…
Deep learning classifies autism vs controls with high accuracy using large fMRI dataset.
problem Classification difficulty of autism vs typically developing controls with fMRI data.
method Ensemble CNN model trained on 43,858 fMRI datapoints, employing class-balancing and visualization methods.
result Deep learning models achieve AUROCs of 0.6774, 0.7680, and 0.9222 for ASD vs TD, gender, and task vs rest classifications.
PR-GNN identifies salient brain regions for ASD biomarkers.
problem Identifying brain regions associated with neurological disorders.
method Pooling Regularized Graph Neural Network (PR-GNN) with novel salient region selection.
result PR-GNN outperforms baseline methods in ASD classification accuracy.
Gluing instantons on 4-manifolds with group action.
problem Gluing invariant ASD connections on 4-manifolds with group action.
method Equivariant gluing theory for instanton moduli spaces.
result Construction of Γ-invariant ASD connections on connected sums. An Alexander self-dual complex gives rise to a compactification of M0,n, called ASD compactification, which is a smooth algebraic variety. ASD compactifications include (but are not exhausted by) the polygon spaces, or the moduli spaces of flexible polygons. We present an explicit description of the Chow rings of …
Study identifies key brain regions and model architectures for ASD diagnosis.
problem Subjective and time-consuming ASD diagnosis by clinicians.
method Comparative analysis of model architectures and atlas granularities.
result High-performing models use 2-4 hidden layers and 16-64 neurons per layer, and cerebellum is predictive of ASD.
Finding the biomarkers associated with ASD is helpful for understanding the underlying roots of the disorder and can lead to earlier diagnosis and more targeted treatment. A promising approach to identify biomarkers is using Graph Neural Networks (GNNs), which can be used to analyze graph structured data, i.e. brain ne…
ASD algorithm maximizes model estimates by adaptively labeling points.
problem Maximizing model estimates through adaptive labeling of points in a sequential decision-making problem.
method Formulated a general information-directed sampling (IDS) algorithm with theoretical guarantees for linear, graph, and low-rank models.
result IDS algorithm outperforms in both simulation and real-data experiments for discovering chemical reaction conditions.
Study G2-instantons on 7-sphere from 4-sphere instantons.
problem Deformation theory of G2-instantons on 7-sphere. method Analysis of pullback from 4-sphere instantons and identification of deformation spaces.
result Existence of a smooth, complete family of 15-dimensional G2-instantons. Paper discusses ASD challenge for machine condition monitoring.
problem Detecting unknown anomalous sounds without labeled data.
method Design and evaluation of a large-scale ASD dataset, novel approaches.
result Several novel approaches developed, evaluation results analyzed.
DCASE 2021 ASD task tackles domain-shifted anomalous sound detection.
problem Detecting unknown anomalous sounds under domain-shifted conditions.
method Ensemble of outlier exposure and inlier modeling detectors, feature learning from machine identification.
result Two types of remarkable approaches were adopted by top teams.
Discovering imaging biomarkers for autism spectrum disorder (ASD) is critical to help explain ASD and predict or monitor treatment outcomes. Toward this end, deep learning classifiers have recently been used for identifying ASD from functional magnetic resonance imaging (fMRI) with higher accuracy than traditional lear…
Study compares ML and DL methods for autism classification.
problem Classifying autism from healthy individuals using rs-fMRI data.
method Developed classification frameworks for rs-fMRI connectivity patterns.
result Best model achieved 71% accuracy on multisite ABIDE I data.
This paper develops a local analogue of the ADHM construction, which characterises ASD instantons defined over smooth bounded domains inside Euclidean R4 diffeomorphic to the 4-ball, in terms of infinite dimensional Hilbert spaces and bounded Hermitian linear operators satisfying an analogue of the ADHM equ…
Automated video conferencing system improves user experience with ASD and VC.
problem Improve remote video conferencing experience through automated speaker detection and virtual cinematography.
method Uses 4K wide-FOV camera, depth camera, and microphone array to extract features and train machine learning models for ASD and VC.
result System performs within 0.3 MOS of an expert cinematographer, as rated by users.
While the prevalence of Autism Spectrum Disorder (ASD) is increasing, research continues in an effort to identify common etiological and pathophysiological bases. In this regard, modern machine learning and network science pave the way for a better understanding of the neuropathology and the development of diagnosis ai…
We review aspects of twistor theory, its aims and achievements spanning thelast five decades. In the twistor approach, space--time is secondary with events being derived objects that correspond to compact holomorphic curves in a complex three--fold -- the twistor space. After giving an elementary construction of this s…
The Centers for Disease Control and Prevention (CDC) coordinates a labor-intensive process to measure the prevalence of autism spectrum disorder (ASD) among children in the United States. Random forests methods have shown promise in speeding up this process, but they lag behind human classification accuracy by about 5%…
The study finds a positive lower bound for the extra field in Yang-Mills equations on closed 4-manifolds.
problem Analyzing the boundedness of solutions to complex Yang-Mills equations on 4-manifolds.
method Investigates the analytical properties of solutions under specific conditions on a closed Riemannian four-manifold.
result Establishes a positive lower bound for the extra field when the metric is 'good' and the connection is an approximate ASD connection.
We study the following question: Let (X,g) be a compact Gauduchon surface, (E,h) be a differentiable rank r vector bundle on X, D be a fixed holomorphic structure on D:=det(E) and a be the Chern connection of the pair (D,det(h)). Does the complex space structure on ${\mathcal{M}}…
We give a correspondence between toric 3-Sasaki 7-manifolds S and certain toric Sasaki-Einstein 5-manifolds M. These 5-manifolds are all diffeomorphic to k#(S^2\times S^3), where k=2b_2(S)+1, and are given by a pencil of Sasaki embeddings of M in S and are given concretely by the zero set of a component of the 3-Sasaki…
Study on instantons over product manifolds with a codimension-4 form.
problem Characterize dimension reduction for moduli spaces of generalized ASD instantons.
method Integrability results for families of connections, topological criteria, and explicit descriptions of moduli spaces.
result Complete characterization of dimension reduction for moduli spaces of generalized ASD instantons.
In this article, we study the Kapustin-Witten equations on a closed, simply-connected, four-dimensional manifold which were introduced by Kapustin and Witten. We use the Taubes' compactness theorem in arXiv:1307.6447v4 to prove that if (A,φ) is a smooth solution of Kapustin-Witten equations and the connection A is …
Framework predicts clinical severity from rs-fMRI data using network optimization.
problem Predicting clinical severity from rs-fMRI data.
method Joint network optimization framework combining sparse subnetworks and linear regression.
result Framework outperforms standard methods and identifies clinically relevant ASD networks.
We make some comments on noncommutative U(N)-instantons on Rθ4. We elaborate on the equations for the ASD-connection for free modules. Further we make some remarks on the computation of the topological index of ADHM instantons.
Formulae prove equivalence of two invariants on specific 4-manifolds.
problem Equivalence of two invariants on homology S1imesS3. method Surgery and excision formulas for Furuta-Ohta invariant λFO. result Computes λFO of certain families of manifolds.