Evaluation of innovation on in vivo - In vitro correlation of gastric retenting drug delivery system for Chinese materia medica / 中草药

The recent study on gastric retenting drug delivery system (GRDDS) used in Chinese medicinal formule has been summaried and overviewed in this paper. The key problems about the development of GRDDS have been explored, the influence about absence of the system for in vivo-in vitro correlation (IVIVC) analyzed, especially the evaluation on IVIVC model discussed, and the possible approach that artificial neural networks (ANN) are applied in GRDDS for Chinese medicinal formule has been put forward. The processing technology, evaluation of IVIVC, and the advantage, characteristic, and problems of the application of ANN have been studied in order to provide the reference for innovating research of Chinese medicinal formule.

Estimación de velocidad del movimiento de mano usando redes neuronales artificiales y mediciones electromiográfíca / Hand movements speed estimation by means of artificial neural networks and electromiographical measurements

En este artículo se presenta el desarrollo de un algoritmo para la estimación de la velocidad de los movimientos básicos de la mano usando redes neuronales artificiales a partir del sensado de la actividad electromiográfica del antebrazo. Parala implementación de dicho algoritmo fue necesario adaptar un modelo funcional de laboratorio para la medición de la velocidad, usando procesado digital de imágenes, presentando un error bajo en la medición de velocidad. Asimismo, para la estimación de velocidad a partir del análisis de la sEMG (señal electromiográfica superficial) se escogió una red NARX (nonlinear autoregressive network with exogenous inputs) como resultado de la comparación de diversas topologías de redes neuronales dinámicas. Losresultados mostrados evidencian una aproximación adecuada en la estimación de velocidad, que sirve como punto de comparación al usarse metodologías diferentes para obtener los perfiles de velocidad.

In this paper an algorithm for estimating the speed of the basic hand movements using artificial neural networksbased on recorded electromyographic activity at the forearm is presented. To implement this algorithm it was necessary to adapt amodel for measuring the speed, using digital image processing, which presented a low error rate measurement. Likewise, for speedestimation, a NARX network (network nonlinear autoregressive with exogenous inputs) was chosen after comparing differentdynamic neural network topologies. The results shown demonstrated a suitable approach to the estimation of speed, which servesas a comparison to the different methodologies used to obtain the velocity profiles.

Research on classification method of burn scar hypertrophy by using support vector machine / 医疗卫生装备

This paper introduces a new method which can judge the degree of burn scar hypertrophy by analyzing chroma of the burn scar. Its technical schedule is as follows: Firstly, the image of the burn scar is captured by using a digital camera. Then the chroma emendation is performed by using an Artificial Neural Network(ANN). At last, the chroma of burn scar is analyzed and the classification of burn scar hypertrophy is given by using a Support Vector Machine(SVM). Compared with clinical evaluation, the result deduced from this method is proved to be effective.