Automatic Extraction and Detection of Characteristic Movement Patterns in Children with ADHD Based on a Convolutional Neural Network (CNN) and Acceleration Images
Attention deficit and hyperactivity disorder (ADHD) is a neurodevelopmental disorder, which is characterized by inattention, hyperactivity and impulsive behaviors. In particular, children have difficulty keeping still exhibiting increased fine and gross motor activity. This paper focuses on analyzin...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2018-11-01
|
| Series: | Sensors |
| Subjects: | |
| Online Access: | https://www.mdpi.com/1424-8220/18/11/3924 |
| _version_ | 1811185125352800256 |
|---|---|
| author | Mario Muñoz-Organero Lauren Powell Ben Heller Val Harpin Jack Parker |
| author_facet | Mario Muñoz-Organero Lauren Powell Ben Heller Val Harpin Jack Parker |
| author_sort | Mario Muñoz-Organero |
| collection | DOAJ |
| description | Attention deficit and hyperactivity disorder (ADHD) is a neurodevelopmental disorder, which is characterized by inattention, hyperactivity and impulsive behaviors. In particular, children have difficulty keeping still exhibiting increased fine and gross motor activity. This paper focuses on analyzing the data obtained from two tri-axial accelerometers (one on the wrist of the dominant arm and the other on the ankle of the dominant leg) worn during school hours by a group of 22 children (11 children with ADHD and 11 paired controls). Five of the 11 ADHD diagnosed children were not on medication during the study. The children were not explicitly instructed to perform any particular activity but followed a normal session at school alternating classes of little or moderate physical activity with intermediate breaks of more prominent physical activity. The tri-axial acceleration signals were converted into 2D acceleration images and a Convolutional Neural Network (CNN) was trained to recognize the differences between non-medicated ADHD children and their paired controls. The results show that there were statistically significant differences in the way the two groups moved for the wrist accelerometer (<i>t</i>-test <i>p</i>-value <0.05). For the ankle accelerometer statistical significance was only achieved between data from the non-medicated children in the experimental group and the control group. Using a Convolutional Neural Network (CNN) to automatically extract embedded acceleration patterns and provide an objective measure to help in the diagnosis of ADHD, an accuracy of 0.875 for the wrist sensor and an accuracy of 0.9375 for the ankle sensor was achieved. |
| first_indexed | 2024-04-11T13:24:06Z |
| format | Article |
| id | doaj.art-f41bb0c0bd034087b20010a2c270272e |
| institution | Directory Open Access Journal |
| issn | 1424-8220 |
| language | English |
| last_indexed | 2024-04-11T13:24:06Z |
| publishDate | 2018-11-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Sensors |
| spelling | doaj.art-f41bb0c0bd034087b20010a2c270272e2022-12-22T04:22:07ZengMDPI AGSensors1424-82202018-11-011811392410.3390/s18113924s18113924Automatic Extraction and Detection of Characteristic Movement Patterns in Children with ADHD Based on a Convolutional Neural Network (CNN) and Acceleration ImagesMario Muñoz-Organero0Lauren Powell1Ben Heller2Val Harpin3Jack Parker4Telematics Engineering Department, Universidad Carlos III de Madrid, Av. Universidad, 30, 28911 Leganes, SpainSchool of Health and Related Research, University of Sheffield, Regent Court, 30, Sheffield S1 4DA, UKCentre for Sports Engineering Research, Sheffield Hallam University, Sheffield S10 2LW, UKRyegate Children’s Centre, Sheffield S10 5GA, UKSchool of Health and Related Research, University of Sheffield, Regent Court, 30, Sheffield S1 4DA, UKAttention deficit and hyperactivity disorder (ADHD) is a neurodevelopmental disorder, which is characterized by inattention, hyperactivity and impulsive behaviors. In particular, children have difficulty keeping still exhibiting increased fine and gross motor activity. This paper focuses on analyzing the data obtained from two tri-axial accelerometers (one on the wrist of the dominant arm and the other on the ankle of the dominant leg) worn during school hours by a group of 22 children (11 children with ADHD and 11 paired controls). Five of the 11 ADHD diagnosed children were not on medication during the study. The children were not explicitly instructed to perform any particular activity but followed a normal session at school alternating classes of little or moderate physical activity with intermediate breaks of more prominent physical activity. The tri-axial acceleration signals were converted into 2D acceleration images and a Convolutional Neural Network (CNN) was trained to recognize the differences between non-medicated ADHD children and their paired controls. The results show that there were statistically significant differences in the way the two groups moved for the wrist accelerometer (<i>t</i>-test <i>p</i>-value <0.05). For the ankle accelerometer statistical significance was only achieved between data from the non-medicated children in the experimental group and the control group. Using a Convolutional Neural Network (CNN) to automatically extract embedded acceleration patterns and provide an objective measure to help in the diagnosis of ADHD, an accuracy of 0.875 for the wrist sensor and an accuracy of 0.9375 for the ankle sensor was achieved.https://www.mdpi.com/1424-8220/18/11/3924ADHDtri-axial accelerometersdeep learningconvolutional neural networks (CNN) |
| spellingShingle | Mario Muñoz-Organero Lauren Powell Ben Heller Val Harpin Jack Parker Automatic Extraction and Detection of Characteristic Movement Patterns in Children with ADHD Based on a Convolutional Neural Network (CNN) and Acceleration Images Sensors ADHD tri-axial accelerometers deep learning convolutional neural networks (CNN) |
| title | Automatic Extraction and Detection of Characteristic Movement Patterns in Children with ADHD Based on a Convolutional Neural Network (CNN) and Acceleration Images |
| title_full | Automatic Extraction and Detection of Characteristic Movement Patterns in Children with ADHD Based on a Convolutional Neural Network (CNN) and Acceleration Images |
| title_fullStr | Automatic Extraction and Detection of Characteristic Movement Patterns in Children with ADHD Based on a Convolutional Neural Network (CNN) and Acceleration Images |
| title_full_unstemmed | Automatic Extraction and Detection of Characteristic Movement Patterns in Children with ADHD Based on a Convolutional Neural Network (CNN) and Acceleration Images |
| title_short | Automatic Extraction and Detection of Characteristic Movement Patterns in Children with ADHD Based on a Convolutional Neural Network (CNN) and Acceleration Images |
| title_sort | automatic extraction and detection of characteristic movement patterns in children with adhd based on a convolutional neural network cnn and acceleration images |
| topic | ADHD tri-axial accelerometers deep learning convolutional neural networks (CNN) |
| url | https://www.mdpi.com/1424-8220/18/11/3924 |
| work_keys_str_mv | AT mariomunozorganero automaticextractionanddetectionofcharacteristicmovementpatternsinchildrenwithadhdbasedonaconvolutionalneuralnetworkcnnandaccelerationimages AT laurenpowell automaticextractionanddetectionofcharacteristicmovementpatternsinchildrenwithadhdbasedonaconvolutionalneuralnetworkcnnandaccelerationimages AT benheller automaticextractionanddetectionofcharacteristicmovementpatternsinchildrenwithadhdbasedonaconvolutionalneuralnetworkcnnandaccelerationimages AT valharpin automaticextractionanddetectionofcharacteristicmovementpatternsinchildrenwithadhdbasedonaconvolutionalneuralnetworkcnnandaccelerationimages AT jackparker automaticextractionanddetectionofcharacteristicmovementpatternsinchildrenwithadhdbasedonaconvolutionalneuralnetworkcnnandaccelerationimages |