| 0:00:01 | hello by |
|---|
| 0:00:02 | either supplementing from the university medical college crackle bolt |
|---|
| 0:00:07 | a little attention to the paper entitled in we should be the relationship to generalize |
|---|
| 0:00:12 | model based on artificial on it |
|---|
| 0:00:17 | if you should be able correlation i d c is classical approach it's a mathematical |
|---|
| 0:00:22 | model |
|---|
| 0:00:23 | designed to predict the in-vehicle measured from energy profile based on the in vitro measure |
|---|
| 0:00:30 | dissolution provide of that particular trial of interest |
|---|
| 0:00:34 | this formula is used by pharmaceutical industry for the costs at purposes |
|---|
| 0:00:39 | because once it is established it allows to reduce the demand of prospective buyers |
|---|
| 0:00:47 | this is the classical approach of i'm a satellite based on instructions of it |
|---|
| 0:00:54 | you have or is it linear problem were drug fraction of sort of be said |
|---|
| 0:01:00 | and via and independent variable dry fraction within b |
|---|
| 0:01:06 | for the last are you have the results ready for computations measured in the lower |
|---|
| 0:01:11 | bound for czech |
|---|
| 0:01:12 | for the for you don't have text is its measurement of this profile therefore you |
|---|
| 0:01:17 | need to create based on numerical approaches one of them the most commonly used it's |
|---|
| 0:01:23 | the deconvolution |
|---|
| 0:01:26 | and the deconvolution methods unfortunately in order to be precise and accurate demands an additional |
|---|
| 0:01:33 | in table five which is usually derived from the |
|---|
| 0:01:38 | intravenous restriction particular drug |
|---|
| 0:01:42 | this situation |
|---|
| 0:01:43 | it's not very comfortable for pharmaceutical industry goes |
|---|
| 0:01:47 | first it requires an additional by a slight and second us for certain cases |
|---|
| 0:01:55 | okay |
|---|
| 0:01:57 | i know administration is sometimes impostor |
|---|
| 0:02:01 | for particular so we would like to propose some solution distribution based on artificial neural |
|---|
| 0:02:07 | networks |
|---|
| 0:02:09 | computational intelligence tools |
|---|
| 0:02:11 | eight to create very complicated relationships |
|---|
| 0:02:15 | and therefore to provide direct relationship idea of our model without a deconvolution phase and |
|---|
| 0:02:23 | these obstacles |
|---|
| 0:02:26 | so that we shall do not show how we do |
|---|
| 0:02:29 | we put two into the input of the neural network to dissolution provide accompanied by |
|---|
| 0:02:35 | the chemical formula of the active pharmaceutical entreaty and icsi and encoded in so called |
|---|
| 0:02:43 | monocular descriptors |
|---|
| 0:02:45 | and also we introduce some parameters of the dissolution test |
|---|
| 0:02:52 | to the output in order to train the one that's work we put a presented |
|---|
| 0:02:57 | a corresponding from canada provides derived from each range |
|---|
| 0:03:02 | this is an example all the prediction power system an average prediction |
|---|
| 0:03:09 | we can see it's not it's not perfectly precise |
|---|
| 0:03:14 | it's still able to need a job of course of the of the kinetic profile |
|---|
| 0:03:19 | and it is also a able to predict the range of considerations |
|---|
| 0:03:27 | which is very important feature the small |
|---|
| 0:03:30 | for more details i would like to invite you to drive design development and their |
|---|
| 0:03:36 | actual |
|---|
| 0:03:37 | i we should have really thank you for that image |
|---|