China
Africa
Explore chapters and articles related to this topic
Advances in Artificial Intelligence Applied to Heart Failure
Published in Kayvan Najarian, Delaram Kahrobaei, Enrique Domínguez, Reza Soroushmehr, Artificial Intelligence in Healthcare and Medicine, 2022
Jose M. García-Pinilla, Francisco Lopez Valverde
Artificial neural networks are a machine learning paradigm inspired by the neurons of biological nervous systems. It is a system of neuron links that collaborate with each other to produce an output stimulus. The connections have numerical weights that are adapted according to experience. In this way, neural networks adapt to an impulse and are capable of learning (Ripley, 2014).
Machine Learning Algorithms Used in Medical Field with a Case Study
Published in K. Gayathri Devi, Kishore Balasubramanian, Le Anh Ngoc, Machine Learning and Deep Learning Techniques for Medical Science, 2022
The commonly used artificial neural network algorithms are:Multilayer Perceptrons (MLP)PerceptronHopfield NetworkStochastic Gradient DescentRadial Basis Function Network (RBFN)Back-Propagation
Can’t the computer just take care of all of this?
Published in Thomas A. Gerds, Michael W. Kattan, Medical Risk Prediction, 2021
Thomas A. Gerds, Michael W. Kattan
The left panel of Figure 8.12 illustrates the model with its input layer (age, antral follicle count), a hidden layer with 5 neurons, and an outcome layer (ovarian hyperstimulation syndrome). The right panel of Figure 8.12 shows the predicted risk of ovarian hyperstimulation syndrome that individual patients would receive from this model. From a biological perspective, it makes sense to assume that increasing antral follicle count increases the risk of OHSS. However, for any given age, the change of risk shown in the right panel of Figure 8.12 is dropping to almost zero in between moderate/high-risk areas (indicated by the narrow white stripe). It seems that this reflects overfitting. The problem is not simply that an artificial neural network is prone to overfitting, but rather that this overfitting can be difficult to detect, i.e., when the predictor variable space is high dimensional and not 2-dimensional as in our example. Also, it may very well happen that an overfitting neural network (or other machine learning method) scores the best prediction performance on average (IPA, AUC) with a model that is biologically implausible.
Effective heart disease prediction with Grey-wolf with Firefly algorithm-differential evolution (GF-DE) for feature selection and weighted ANN classification
Published in Computer Methods in Biomechanics and Biomedical Engineering, 2022
HNN (heuristic optimisation-weight of artificial neural network) is a Meta heuristic model designed to increase the performance of ANN (artificial neural network). Artificial neural network technically induce the brain behaviour to improve a system which can manage difficult prediction problems. It is trained by BP (back propagation) algorithm method. The artificial neural network contains several neurons and utilized synaptic weights that connect neurons. Back propagation updates artificial neuron network weights based on calculated errors that found from the previous data based on ANN principles. Because of complexity and application of various steps that makes delay in learning rate with artificial neural network. Back propagation trains artificial neural networks by tuning changing of weights on each trained cycle, consequently the learning range increased slowly. Obviously, the remarkable time needs to train artificial neural network by back propagation algorithm and the importance of developing prediction accuracy of artificial neural networks that motivate to design new model for optimisation of performance in terms of time and accuracy.
Analysing the effect of robotic gait on lower extremity muscles and classification by using deep learning
Published in Computer Methods in Biomechanics and Biomedical Engineering, 2022
İsmail Çalıkuşu, Esma Uzunhisarcıklı, Uğur Fidan, Mehmet Bahadır Çetinkaya
Deep learning is an artificial intelligence technique used in data processing and decision-making that mimics the brain’s neural functioning by creating patterns. It includes networks that can learn from unstructured or unlabeled data in an unsupervised manner and it is classified in the machine learning cluster in artificial intelligence. in deep learning, the data are divided into classes and patterns according to the type of information by using neural networks such as in the human brain. Each layer of the neural network behaves as a filter that increases the probability of detecting and giving an accurate result (Şeker et al. 2017; Lang et al. 2019). The most important difficulty faced in deep learning is the training of the artificial neural network because it requires a large data set and too much computing power.
Practical foundations of machine learning for addiction research. Part I. Methods and techniques
Published in The American Journal of Drug and Alcohol Abuse, 2022
Pablo Cresta Morgado, Martín Carusso, Laura Alonso Alemany, Laura Acion
Among the most expressive models, artificial neural networks process the information from predictor variables with a combination of simpler, connected classifiers called artificial neurons. They may be connected through successive layers stacked on top of each other, thus becoming deep artificial networks (21). Each layer transforms the data and the last layer produces the prediction. During neural network model training, the model predicted values are compared with actual observations, obtaining a measurement of how near the prediction was from the observation. An optimization algorithm then carries out the learning process, adjusting how the data are transformed within each layer to reduce the error between prediction and observation, usually by slightly modifying the connections between artificial neurons (21). This whole process runs iteratively until obtaining the best performance. Neural networks can capture complex dependencies among variables. As a drawback, they are very prone to overfitting, even if they incorporate many methods to mitigate it. Moreover, it is usually hard to understand each predictor’s contribution to the outcome.