Autism Spectrum Disorder Prediction Using Machine Learning | Chapter 14 | Leading the Charge: A Guide to Management, Entrepreneurship and Technology in the Dynamic Business Landscape Edition 1

Autism Spectrum Disorder (ASD) is a complex neurodevelopmental condition characterized by challenges in social interaction, communication, and restricted repetitive behaviors. Early diagnosis and intervention significantly improve outcomes for individuals with ASD. In this paper, we propose a machine learning approach using an Artificial Neural Network (ANN) classifier to predict ASD based on a set of relevant features extracted from clinical assessments and behavioral observations. The ANN model is trained on a large dataset of individuals with and without ASD, incorporating features such as demographic information, medical history, and behavioral characteristics. Moreover, its web-based deployment ensures broader accessibility, facilitating early interventions and support. These advanced models can identify subtle patterns that may not be detectable through traditional clinical assessments alone.

 

Author (s) Details

 

Umesh R
Department of Information Technology, Velammal College of Engineering and Technology, Madurai, India.

 

Shanjay S
Department of Information Technology, Velammal College of Engineering and Technology, Madurai, India.

 

Sathish Kumar K S
Department of Information Technology, Velammal College of Engineering and Technology, Madurai, India.

 

Please see the book here:- https://doi.org/10.9734/bpi/mono/978-93-48859-98-3/CH14

Determination of Appropriate Drone Flight Altitude for Horse Behavioural Observation | Chapter 10 | Research Aspects in Agriculture and Veterinary Science Vol. 4

 Drone technology has advanced recently, and their safety and operability have greatly improved, resulting in increased use in animal research. Drones of varying sizes and capabilities are commercially available and quite easy to purchase. This study used drone technology to watch horse behaviour and validate the proper horse–drone distance for airborne behavioural observations, demonstrating drone application in livestock management. The Phantom 4 Pro drone was used to record 11 horses between September and October 2017. To explore the horses' reactions to the drones and watch their behaviour, four flight altitudes were evaluated (60, 50, 40, and 30 m); the recording time at each altitude was 5 minutes. At whatever flight altitude, none of the horses demonstrated avoidance behaviour, and the observer was able to distinguish between any two horses. Foraging, moving, standing, recumbency, avoidance, and other actions were recorded. The most prevalent behaviour observed both personally and in the drone videos was foraging. All behavioural data from direct and drone video observations at all altitudes had substantial correlation coefficients (p 0.01). These findings suggest that both direct and recorded drone video observations may accurately detect horse behaviour. Finally, drones can be valuable for observing and documenting horse behaviour.

Author(S) Details

Tomoko Saitoh
Field Center of Animal Science and Agriculture, Obihiro University of Agriculture and Veterinary Medicine, Obihiro, 080-8555, Hokkaido, Japan.

Moyu Kobayashi
Field Center of Animal Science and Agriculture, Obihiro University of Agriculture and Veterinary Medicine, Obihiro, 080-8555, Hokkaido, Japan.

View Book:- https://stm.bookpi.org/RAAVS-V4/article/view/4852