A combination of artificial intelligence (AI) and robotics is giving hope to people suffering from neurotrauma.A new study was published in a journal frontier Shows how AI-powered soft robotic gloves can help patients with neuromuscular disorders relearn how to play the piano.
“So far, other soft robotic actuators have been used to play the piano. ,” write the researchers at Florida Atlantic University, Boise State University, and the University of Florida College. medicine.
Neurotrauma, an injury to the brain and/or spinal cord, is a global health problem. According to the World Health Organization (WHO), an estimated 69 million people worldwide suffer from traumatic brain injury (TBI) each year. According to the World Stroke Organization (WSO), there are an estimated 12.2 million new strokes worldwide, and one in four women aged 25 and over will experience a stroke in their lifetime. Worldwide, the WSO estimates that 101 million people live with the aftereffects of stroke, a number that has nearly doubled over the past 30 years.
The researchers equipped a soft robotic exoskeleton with piezoresistive sensor arrays with 16 taxels on five fingertips.
Piezoresistive sensors measure pressure with high accuracy. Its name reflects the piezoresistive effect, which is the change in electrical resistance when stress or strain is mechanically applied. TActile piXEL is a sensor that can recognize contact pressure by calculating how much force is applied to the area.
The researchers created 10 variations of “Mary Had a Little Lamb” (1 correct, 9 incorrect rhythmically) and used the collected data to run Random Forest (RF), K-Nearest Neighbor (KNN), and artificial neural network (ANN) algorithms. From the five sensors on your fingertips.
The Random Forest Algorithm (also known as Random Decision Forest) is a type of user-friendly machine learning algorithm that uses supervised machine learning. Supervised machine learning in artificial intelligence refers to the technique of using labeled input data to train an algorithm to predict or classify data. These algorithms are widely used for classification and regression tasks. Rather than using a single decision tree, the random forest algorithm consists of many individual decision trees working together as an ensemble, hence the name “forest”. A class prediction from each decision tree is made and the one with the majority of votes is the final output.
The K nearest neighbors algorithm is also a popular supervised machine learning algorithm often used for classification and regression problems. Rather than performing computations, this basic algorithm stores all available cases and performs classification based on similarity. This algorithm is also considered a nonparametric method because it makes no assumptions about the data distribution. The algorithm looks at the nearest annotated data point, or nearest neighbor data point, to classify a data point, hence the name of the algorithm.
Artificial neural networks, also known as neural nets or neural networks, are machine learning algorithms with an architecture inspired by the biological brain. An artificial neural network consists of an input layer, one or more hidden layers, and an output layer. Each layer contains multiple interconnected artificial neurons called nodes with associated weights and thresholds.
When a node is activated over a specified threshold, data is passed to the next layer of the network. Artificial neural networks can quickly classify data and are often used for search, speech recognition, and image recognition.
A subset of machine learning, deep learning is an artificial neural network with at least three layers. The more layers, the deeper the network. Machine learning (ML) is a subset of artificial intelligence in which algorithms are not hardcoded. Instead, in machine learning, algorithms learn from training data to find patterns and make predictions.
Scientists can use the pattern recognition capabilities of AI machine learning to “feel” the difference between correct and incorrect versions of piano songs. The research team found that the AI algorithm that produced the highest accuracy was an artificial neural network algorithm, with a classification accuracy of over 97% for him, plus or minus 2% when played by his 25-year-old male in a healthy subject. Reported. When no human subject played, the ANN algorithm itself allowed him to perform classification with an accuracy of 94.6% ± 1.26%.
“These findings highlight the potential of smart exoskeletons to help people with disabilities relearn dexterous tasks such as playing musical instruments,” the scientists concluded.
Copyright © 2023 Kami Rosso All rights reserved.
