To reach this objective, a method to build a representative database of examples has been developed, the right input (explanatory) and output (preparation process quality criteria) variables have been identified, then the learning model and its associated control parameters have been tuned.
Phylogenetic methods, for example, have been developed for inferring ancestral expression profiles or ancestral functions of homologs.
Specialized software tools like Genevestigator [ 4], the Botany Array Resource (BAR) [ 5], MapMan [ 6], ATTED-II [ 7, 8] or VirtualPlant [ 9] for example have been developed to answer such complex questions in plants.
20– 22 As an example, such a prediction model has been developed for estimating the long-term risk of VTE in general practice.
Microsoft, for example, has been developing software that takes advantage of the different times an acoustic wave arrives at each microphone in an array around the screen of a computer.
Then, three examples (which have been developed at the University of Bologna) are taken into account, namely a medium complexity 3-dof robotic gripper for autonomous tasks in IVA/EVA environments, an anthropomorphic gripper for tele-operated and autonomous operations, and finally a human-like robotic hand based on new design concepts (i.e. compliant mechanisms).
For example, questionnaires have been developed to sample people's thoughts after an upsetting event.
In genetics, for example, methods have been developed to identify chromosome locations subjected to strong recent selection, such as locations near the lactase gene that influence whether adults can digest milk.
For example, methods have been developed for mechanical modeling of breast deformations [12],[13] and simulation of steerable needle insertion for prostate therapy [14]-[16] [14]-[16]
