• Corpus ID: 245669001

Classifying Autism from Crowdsourced Semi-Structured Speech Recordings: A Machine Learning Approach

  title={Classifying Autism from Crowdsourced Semi-Structured Speech Recordings: A Machine Learning Approach},
  author={Nathan Chi and Peter Yigitcan Washington and Aaron Kline and Arman Husic and Cathy Hou and Chloe He and Kaitlyn Dunlap and Dennis Paul Wall},
Background: Autism spectrum disorder (ASD) is a neurodevelopmental disorder which results in altered behavior, social development, and communication patterns. In past years, autism prevalence has tripled, with 1 in 54 children now affected. Given that traditional diagnosis is a lengthy, labor-intensive process which requires the work of trained physicians, significant attention has been given to developing systems that automatically diagnose and screen for autism. Objective: Prosody… 

Figures and Tables from this paper

An Exploration of Active Learning for Affective Digital Phenotyping

This work simulates an active learning process for crowdsourcing many labels and finds that prioritizing frames using the entropy of the crowdsourced label distribution results in lower categorical cross-entropy loss compared to random frame selection.

Context-responsive ASL Recommendation for Parent-Child Interaction

The design and development of an initial working prototype of TIPS are described and preliminary results of the system’s efficiency regarding system latency and accuracy for ASL recommendation and visualization are described.



Automatic Detection of Autism Spectrum Disorder in Children Using Acoustic and Text Features from Brief Natural Conversations

The goal of this project is to develop an automatic detection system for ASD that relies on very brief, generic, and natural conversations, which can eventually be used for ASD prescreening and triage in realworld settings such as doctor’s offices and schools.

Mobile detection of autism through machine learning on home video: A development and prospective validation study

The hypothesis that feature tagging of home videos for machine learning classification of autism can yield accurate outcomes in short time frames is supported, using mobile devices.

Deep-Learning-Based Detection of Infants with Autism Spectrum Disorder Using Auto-Encoder Feature Representation

A pre-trained feature extraction auto-encoder model and a joint optimization scheme are introduced which can achieve robustness for widely distributed and unrefined data using a deep-learning-based method for the detection of autism that utilizes various models.

Detecting Developmental Delay and Autism Through Machine Learning Models Using Home Videos of Bangladeshi Children: Development and Validation Study

These results show promise for using a mobile video-based and machine learning–directed approach for early and remote detection of autism in Bangladeshi children and identify the population-level burden of developmental disabilities and impairments.

Child vocalization composition as discriminant information for automatic autism detection

It is discovered that child vocalization composition contains rich discriminant information for autism detection, and it is believed that this new tool can serve a significant role in childhood autism screening, especially in regards to population-based or universal screening.

The Performance of Emotion Classifiers for Children With Parent-Reported Autism: Quantitative Feasibility Study

Commercial emotion classifiers available off-the-shelf to the general public through Microsoft, Amazon, Google, and Sighthound are well-suited to the pediatric population and could be used for developing mobile therapies targeting aspects of social communication and interaction, perhaps accelerating innovation in this space.

Leveraging video data from a digital smartphone autism therapy to train an emotion detection classifier

Autism spectrum disorder (ASD) is a neurodevelopmental disorder affecting one in 40 children in the United States and is associated with impaired social interactions, restricted interests, and

Feature replacement methods enable reliable home video analysis for machine learning detection of autism

The results show that general and dynamic feature replacement methods achieve a higher performance than classic univariate and multivariate methods, supporting the hypothesis that algorithmic management can maintain the fidelity of video-based diagnostics in the face of missing values and variable video quality.

Feature Selection and Dimension Reduction of Social Autism Data

This work performed item-level question selection on answers to the Social Responsiveness Scale, Second Edition to determine whether ASD can be distinguished from non-ASD using a similarly small subset of questions, and evaluated the performance of an MLP classifier trained on the low-dimension representations of the SRS.