What is claimed is:
1. A method of processing data relating to a plurality of examples using a data classifier arranged to classify input data into one of a number of classes, and a rule inducer, comprising the steps of:
(i) inputting a series of inputs to the data classifier so as to obtain a series of corresponding outputs;
(ii) inputting said series of outputs and at least some of said series of inputs to the rule inducer so as to obtain a series of rules which describe relationships between the series of inputs to the data classifier and the series of corresponding outputs from the data classifier.
2. A method as claimed in claim 1 wherein the data classifier is unsupervised.
3. A method as claimed in claim 1 wherein the data classifier comprises a neural network.
4. A method as claimed in claim 1 wherein the data classifier comprises a Bayesian classifier.
5. A method as claimed in claim 1 wherein said step (ii) comprises combining each input with its corresponding output so as to create a second series of inputs; and inputting the second series of inputs to the rule inducer.
6. A method as claimed in claim 1 wherein an input to the data classifier comprises an example comprising a series of attribute values and a corresponding output comprises an indication of which of the number of possible classes the example is a member of.
7. A method as claimed in claim 1 which further comprises the step of transforming the series of rules into a format such that the formatted rules can be used as a data classifier.
8. A method as claimed in claim 1 which further comprises the step of:
incorporating the rules in to a case-based reasoning system such that in use the case-based reasoning system can be used as a data classifier.
9. A computer system for processing data relating to a communications network comprising:
a data classifier arranged to classify input data into one of a number of classes;
a rule inducer;
a first input arranged to accept a series of inputs to the data classifier;
a first output arranged to provide a series of corresponding outputs from the data classifier;
a second input arranged to accept said series of outputs and at least some of said series of inputs to the rule generator; and
a second output arranged to output from the rule generator a set of rules which describe relationships between the series of inputs to the data classifier and the series of corresponding outputs from the data classifier.
10. A method of processing data relating to a communications network using a rule extractor and a neural network data classifier comprising the steps of:
(i) inputting a series of training data inputs to the neural network and training the neural network using this series of training data so as to obtain a series of output values corresponding to the training data inputs;
(ii) inputting information about the configuration of the trained neural network to the rule extractor so as to obtain a series of rules which describe relationships between the series of training data inputs and the series of output values.
11. A method as claimed in claim 10 wherein the information about the configuration of the trained neural network comprises information about a set of weighted connections between units in the neural network.
12. A computer system for processing data relating to a telecommunications network comprising:
(i) a rule extractor;
(ii) a neural network data classifier;
(iii) a first input arranged to accept a series of training data inputs to the neural network;
(iv) a processor arranged to train the neural network using the series of training data inputs so as to produce a series of output values corresponding to the training data inputs; and
(v) a second input arranged to accept information about the configuration of the trained neural network to the rule extractor so as to produce a series of rules which describe relationships between the series of training data inputs and the series of output values.
13. A method as claimed in claim 1 wherein the data relates to a communications network.
14. A method as claimed in claim 1 wherein the data relates to a telecommunications network.
15. A method as claimed in claim 1 wherein the data classifier is arranged to classify input data into one of a number of classes according to whether an input is anomalous or not.
16. A method as claimed in claim 10 wherein the trained neural network is arranged to classify the training data inputs according to whether an input is anomalous or not.
The claims below are in addition to those above.
All refrences to claim(s) which appear below refer to the numbering after this setence.
1. A device for cell transplantation comprising:
a biocompatible frame configured to be inserted into tissue;
at least one slit passing through the frame, wherein the at least one slit is sized and configured to allow vascular perfusion through the at least one slit; and
a fluidic channel located within the frame and comprising a semipermeable surface region configured to retain cells while allowing certain dissolved molecules to diffuse between the fluidic channel and the at least one slit.
2. The device of claim 1, further comprising at least one inletoutlet port in fluid communication with the fluidic channel.
3. The device of claim 2, wherein the at least one inletoutlet port is configured to be sealed.
4. The device of claim 1, wherein the fluidic channel is configured to retain islet cells.
5. The device of claim 1, wherein the frame is formed from a plurality of layers bonded together.
6. The device of claim 1, wherein the frame is monolithic.
7. The device of claim 1, wherein the frame is a hydrogel.
8. The device of claim 1, wherein the frame is formed from a material selected from the group consisting of alginate, polydimethylacrylamide (PDMA), polydimethylsiloxane (PDMS), polyacrylonitrile (PAN) or polymethylmethacrylate (PMMA).
9. The device of claim 1, further comprising a plurality of slits.
10. The device of claim 1, further comprising a plurality of fluidic channels.
11. The device of claim 1, wherein the semipermeable surface region of the fluidic channel comprises dialysis tubing.
12. The device of claim 1, wherein the biocompatible frame is hollow and at least partially defines the fluidic channel.
13. The device of claim 1, wherein the fluidic channel is serpentine.
14. The device of claim 1, further comprising an oxygen sensitive dye incorporated into the device.
15. The device of claim 14, wherein the oxygen sensitive dye has a fluorescence lifetime based on oxygen levels.
16. The device of claim 1, wherein one or more agents promoting vascularization are incorporated into the device.
17. The device of claim 16, wherein the one or more agents promoting vascularization are autologous blood, fibrin purified from donor mice, VEGF, or other growth factors.
18. A method for making an transplantation device for islet transplantation comprising:
fabricating a bottom layer having at least one slit;
fabricating an inner layer having a fluidic channel comprising a semipermeable surface region and an injection port;
fabricating a top layer having at least one slit, the at least one slit of the top layer configured to substantially align with the at least one slit on the bottom layer; and
bonding the layers together to sandwich the inner layer between the top and bottom layers thereby enclosing the fluidic channel, wherein the fluidic channel is positioned to allow diffusion communication between the fluidic channel and the slits.
19. The method of claim 18, wherein the top and bottom layers comprising a plurality of slits.
20. A method for making a device for islet transplantation comprising:
preparing a dissolvable mold configured to form an implantable device comprising:
a biocompatible frame configured to be inserted into tissue;
at least one slit configured to pass at least partially through the frame, wherein the at least one slit is sized and configured to promote vascular perfusion; and
a fluidic channel configured to retain cells and located within the biocompatible frame, the fluidic channel being separated from the at least one slit and able to communicate with the at least one slit through diffusion;
adding a polymerizable material to the mold;
polymerizing the material to form the implantable device; and
dissolving the mold.
21. The method of claim 20, wherein polymerizing the material comprises polymerizing the material with UV light.
22. The method of claim 20, wherein dissolving the mold comprises submerging the mold in a dissolving solution.
23. The method of claim 22, wherein the dissolving solution is citrus oil.
24. A method for treating diabetes comprising:
implanting the device of claim 1 into a tissue of a diabetic patient;
equilibrating the device within the tissue for a period of time sufficient to allow vascularization of the at least one slit; and
injecting a suspension of islet cells into the fluidic channel, wherein the islet cells secrete insulin into the at least one vascularized slit in response to glucose levels in the at least one vascularized slit.