Go To AIH-HSP Data Types

1 Definition 2 Functional Requirements 3 Syntax 4 Semantics 5    Conformance Testing 6     Performance Assessment

1 Definition

The Request to a Health Front End to provide its trained NN Model or the Response from the Health Front End.

2 Functional Requirements

The Federated Learn Request includes

  1. Health Front End ID
  2. ID of NN Model before it is subjected to Machine Learning.(Pre-Learn)

The Federated Learn Response includes

  1. NN Model after it has been subjected to Machine Learning (Post-Learn).

3 Syntax

https://schemas.mpai.community/AIH1/V1.0/data/FederatedLearn.json

4 Semantics

Label Description
Header Federated Learn Header – Standard “AIH-FDL-Vx.y”
MInstanceID Identifier of M-Instance.
FederatedLearnID Identifier of Federated Learn.
FederatedLearnTime Time of Federated Learn.
FederatedLearn Data in Federated Learn.
– Request If Request
  – HFEID ID Of Health Front End
  – PreLearnNNModelID ID of NN Model downloaded from the MPAI Store.
– Response If Response
  – PostLearnNNModel NN Model after Machine Learning.
DataXMData Information about this Federated Learn Instance.
DescrMetadata Descriptive Metadata

5     Conformance Testing

A Data instance Conforms with Federated Learn (AIH-FDL) if:

  1.  Its JSON Object validates against its JSON Schema.
  2. Any included  JSON Object validates against its JSON Schema.
  3. All Data in the JSON Object:
    1. Have the specified Data Types.
    2. Conform with the Qualifiers signaled in their JSON Schemas.

6     Performance Assessment

Go To AIH-HSP Data Types