Towards Integrating Machine Learning Models into Mobile Apps using AppCraft

TY - CONF

T1 - Towards Integrating Machine Learning Models into Mobile Apps using AppCraft

AU - Alwakeel, Lyan

AU - Lano, Kevin

AU - Alfraihi, Hessa

N1 - Publisher Copyright: © 2023 Copyright for this paper by its authors. Use permitted under Creative Commons License Attribution 4.0 International (CC BY 4.0).

PY - 2023

Y1 - 2023

N2 - Mobile apps increasingly incorporate machine learning (ML) to enhance their services. However, integrating ML models locally with mobile apps can be challenging. Each ML model has specific designs that accept certain types of input and produce specific outputs. Model-driven engineering (MDE) and low-code solutions can specify the integration process in a high-level language, alleviating this issue. In this paper, we incorporate our framework, AppCraft, with the ML process to generate code for Android and iOS mobile apps with all the necessary components to load the model, process the input data, and display the output results in a user-friendly way. This enhancement contributes to designing and automating the integration of ML engineering processes with mobile apps.

AB - Mobile apps increasingly incorporate machine learning (ML) to enhance their services. However, integrating ML models locally with mobile apps can be challenging. Each ML model has specific designs that accept certain types of input and produce specific outputs. Model-driven engineering (MDE) and low-code solutions can specify the integration process in a high-level language, alleviating this issue. In this paper, we incorporate our framework, AppCraft, with the ML process to generate code for Android and iOS mobile apps with all the necessary components to load the model, process the input data, and display the output results in a user-friendly way. This enhancement contributes to designing and automating the integration of ML engineering processes with mobile apps.

KW - Android

KW - iOS

KW - Low-code

KW - Machine Learning Engineering

KW - Mobile App

KW - Model-Driven Engineering

UR - http://www.scopus.com/inward/record.url?scp=85183907588&partnerID=8YFLogxK

M3 - Paper

AN - SCOPUS:85183907588

T2 - 2023 Software Technologies: Applications and Foundations Workshops, STAF-WS 2023; 15th Transformation Tool Contest, TTC 2023, 3rd International Workshop on MDE for Smart IoT Systems, MeSS 2023 and Agile Model-driven Engineering Workshop, AgileMDE 2023

Y2 - 18 July 2023 through 21 July 2023

ER -