Results and Challenges of Artificial Neural Networks Used for Decision-Making and Control in Medical Applications

Abstract

The aim of this paper is to present several approaches by which technology can assist medical decision-making. This is an essential, but also a difficult activity, which implies a large number of medical and technical aspects. But, more important, it involves humans: on the one hand, the patient, who has a medical problem and who requires the best solution; on the other hand, the physician, who should be able to provide, in any circumstances, a decision or a prediction regarding the current and the future medical status of the patient. The technology, in general, and particularly the Artificial Intelligence (AI) tools could help both of them, and it is assisted by appropriate theory regarding modeling tools. One of the most powerful mechanisms that can be used in this field is the Artificial Neural Networks (ANNs). This paper presents some of the results obtained by the Process Control group of the Politehnica University Timisoara, Romania, in the field of ANNs applied to modeling, prediction and decision-making related to medical systems. An Iterative Learning Control-based approach to batch training a feedforward ANN architecture is given. The paper includes authors’ concerns in this domain and emphasizes that these intelligent models, even if they are artificial, are able to make decisions, being useful tools for prevention, early detection and personalized healthcare.

Neural network‐based learning and estimation of battery state‐of‐charge : A comparison study between direct and indirect methodology

“…Machine learning has been deeply entrenched in industrial control. [18][19][20][21] Therein, NN, developed as SOC estimators, have been studied extensively in the literature, including back-propagation neural networks (BP-NN), 22,23 radial basis function neural networks (RBFNN). 24,25 In the NN model for SOC estimation, a large mass of known input data and expected output data obtained from the battery charging and discharging experiments is required to train the network, thereby self-learning the network parameters and extracting the fitting relationship.…”

Evaluation of Criteria for the Implementation of High-Performance Computing (HPC) in Danube Region Countries Using Fuzzy PIPRECIA Method

“…Availability of commercial HPC infrastructure (where you have to pay for using it) C 3 Availability of skilled human resources C 4 Degree to which universities equip students with the necessary knowledge to work in HPC C 5 Availability of competitive public funding (e.g., direct public funding, grants, awards, baseline funding) C 6 Availability of private funding for R&D related to HPC C 7 Degree of awareness about HPC benefits C 8 Degree of science-industry cooperation related to HPC C 9 Degree of industry-public authorities' cooperation related to HPC C 10 Degree of science-public authorities' cooperation related to HPC C 11 HPC prioritization in legislative documents and strategies…”

A Center Manifold Theory-Based Approach to the Stability Analysis of State Feedback Takagi-Sugeno-Kang Fuzzy Control Systems

“…3 give an indication on the system stability. The regulation and tracking performance of the fuzzy control system were not analyzed; however, the optimal tuning can be carried out in this context, with the results that can be quite different for this application and other challenging ones as well [103][104][105][106][107][108]. Starting with the authors' application of the center manifold theory to Mamdani fuzzy control systems, this paper suggests its application to state feedback Takagi-Sugeno-Kang fuzzy control systems as well.…”