Acquisition of skin characteristics by Monte Carlo modeling and evolutionary setting of parameters.

BACKGROUND: In this paper, we present the intelligent system to characterize optically human skin; our proposal is a non-invasive way to obtain some parameters of the skin such as the concentration of hemoglobin, water percentages, and thickness of the layers of the skin. MATERIAL AND METHODS: To achieve the objective of this work, we used an experimental technique called diffuse reflectance spectrophotometry and numerical calculations, such as the Monte Carlo method and the evolutionary algorithm Evonorm. RESULTS: Five case studies were performed. In the first two cases with the Monte Carlo method, a simulated diffuse reflectance was obtained with proposed parameters in order to compare the parameters obtained by the evolutionary algorithm and the proposed parameters. In the rest of the cases, an experimental diffuse reflectance obtained from volunteers was used. CONCLUSIONS: Numerical modeling was presented to non-invasively detect some parameters of the skin such as hemoglobin concentration, water percentages, and the thickness of the epidermis, dermis, and hypodermis. It was proposed to use evolutionary algorithms for being robust methods for the optimization of complex problems with a reasonable computational cost.

Parameter estimation of a meal glucose-insulin model for TIDM patients from therapy historical data.

The effect of meal on blood glucose concentration is a key issue in diabetes mellitus because its estimation could be very useful in therapy decisions. In the case of type 1 diabetes mellitus (T1DM), the therapy based on automatic insulin delivery requires a closed-loop control system to maintain euglycaemia even in the postprandial state. Thus, the mathematical modelling of glucose metabolism is relevant to predict the metabolic state of a patient. Moreover, the eating habits are characteristic of each person, so it is of interest that the mathematical models of meal intake allow to personalise the glycaemic state of the patient using therapy historical data, that is, daily measurements of glucose and records of carbohydrate intake and insulin supply. Thus, here, a model of glucose metabolism that includes the effects of meal is analysed in order to establish criteria for data-based personalisation. The analysis includes the sensitivity and identifiability of the parameters, and the parameter estimation problem was resolved via two algorithms: particle swarm optimisation and evonorm. The results show that the mathematical model can be a useful tool to estimate the glycaemic status of a patient and personalise it according to her/his historical data.

Hybrid BCI approach to control an artificial tibio-femoral joint.

Brain-Computer Interfaces (BCIs) for disabled people should allow them to use their remaining functionalities as control possibilities. BCIs connect the brain with external devices to perform the volition or intent of movement, regardless if that individual is unable to perform the task due to body impairments. In this work we fuse electromyographic (EMG) with electroencephalographic (EEG) activity in a framework called "Hybrid-BCI" (hBCI) approach to control the movement of a simulated tibio-femoral joint. Two mathematical models of a tibio-femoral joint are used to emulate the kinematic and dynamic behavior of the knee. The interest is to reproduce different velocities of the human gait cycle. The EEG signals are used to classify the user intent, which are the velocity changes, meanwhile the superficial EMG signals are used to estimate the amplitude of such intent. A multi-level controller is used to solve the trajectory tracking problem involved. The lower level consists of an individual controller for each model, it solves the tracking of the desired trajectory even considering different velocities of the human gait cycle. The mid-level uses a combination of a logical operator and a finite state machine for the switching between models. Finally, the highest level consists in a support vector machine to classify the desired activity.