TCSE logo 
 Sigsoft logo
Sustainability badge
Sun 27 Apr 2025 10:10 - 10:30 at 215 - Welcoming + Information models session Chair(s): Rodrigo Morales

The availability of pre-trained models (PTMs) has enabled faster deployment of machine learning across applications by reducing the need for extensive training. Techniques like quantization and distillation have further expanded PTM applicability to resource-constrained IoT hardware. Given the many PTM options for any given task, engineers often find it too costly to evaluate each model’s suitability. Approaches such as LogME, LEEP, and ModelSpider help streamline model selection by estimating task relevance without exhaustive tuning. However, these methods largely leave hardware constraints as future work—a significant limitation in IoT settings. In this paper, we identify the limitations of current model recommendation approaches regarding hardware constraints and introduce a novel, hardware-aware method for PTM selection. We also propose a research agenda to guide the development of effective, hardware-conscious model recommendation systems for IoT applications.

Sun 27 Apr

Displayed time zone: Eastern Time (US & Canada) change

09:00 - 10:30
Welcoming + Information models sessionSERP4IoT at 215
Chair(s): Rodrigo Morales Concordia University
09:00
20m
Day opening
Opening
SERP4IoT

09:20
25m
Talk
An Interoperable Ontology-based Information Model for Better Integration of Building Physics and IoT Data Analytics Models
SERP4IoT
Jose Manuel Broto CIMNE, Jordi Cipriano CIMNE, Gerard Mor CIMNE, Oriol Gavalda Concordia University, Shahin Masoumi-Verki Concordia University, Ursula Eicker Concordia University
09:45
25m
Talk
A Conceptual Model for Trustworthiness in Intelligent IoT Systems
SERP4IoT
Romina Spalazzese Malmö University, Martina De Sanctis Gran Sasso Science Institute, Andreas Jacobsson Malmö University, Fahed Alkhabbas Malmo University, Paul Davidsson Malmö University
10:10
20m
Talk
Recommending Pre-Trained Models for IoT Devices
SERP4IoT
Parth Vinod Patil Purdue University, Wenxin Jiang Purdue University, Huiyun Peng Purdue University, Daniel Lugo Purdue University, Kelechi G. Kalu Purdue University, Josh LeBlanc Purdue University, Lawrence Smith Purdue University, Hyeonwoo Heo Purdue University, Nathanael Aou Purdue University, James C. Davis Purdue University
Pre-print
:
:
:
: