<!DOCTYPE html>
<html>
<head>
<meta http-equiv="content-type" content="text/html; charset=UTF-8">
</head>
<body>
<p><br>
</p>
<p>**************************************************************************<br>
<span style=""> [Please accept our apologies if you receive
multiple copies of this CFP]</span><br>
**************************************************************************<br>
<br>
4th IEEE Workshop on Pervasive and Resource-constrained Artificial
Intelligence (PeRConAI)<br>
co-located with IEEE PerCom 2025, March 17-21, 2025, Washington
DC, USA<br>
<br>
Website: <a
href="https://urldefense.com/v3/__http://perconai.iit.cnr.it__;!!D9dNQwwGXtA!QWOqdtRbbS04WTruHR9bBpceE5iCrIJmUEw3q_PXt2ohUb521g4z1EZw4o82NqTzwG9lvtNpDE7ug8Q_2JTauSRHZQ5znRhWG0qnhw$"
target="_blank">http://perconai.iit.cnr.it</a><br>
Email contact for info: <a
href="https://urldefense.com/v3/__https://mailto:perconai@iit.cnr.it__;!!D9dNQwwGXtA!QWOqdtRbbS04WTruHR9bBpceE5iCrIJmUEw3q_PXt2ohUb521g4z1EZw4o82NqTzwG9lvtNpDE7ug8Q_2JTauSRHZQ5znRhL-tLekw$"
target="_blank">perconai@iit.cnr.it</a><br>
<br>
This year’s PeRConAI enjoys the joint technical co-sponsorship of
the SONATA (<a href="https://sonata.cttc.es" target="_blank"
class="moz-txt-link-freetext">https://sonata.cttc.es</a>)
project.<br>
<br>
Important dates <br>
---------------<br>
* Paper submission deadline: November 17th, 2024 <br>
* Paper notification: January 8th, 2025<br>
<br>
Call for Papers<br>
---------------<br>
PeRConAI will focus on solutions that contribute to advancing
truly pervasive and liquid AI, enabling edge devices, regardless
of their available resources, to accomplish training and inference
under full, weak, or no supervision.<br>
<br>
The increasing pervasiveness of edge devices and the high
availability, velocity, and volatility of data generated and
collected at the edge of the internet are pushing towards a
paradigm shift in the design of AI-based systems. AI systems are
moving the execution of both training and inference tasks from
powerful and remote data centers where all data is available in a
centralized fashion to more pervasive and
distributed/decentralized systems at the edge of the internet,
working in proximity to where data is physically generated and/or
collected. <br>
The design of edge AI systems must leverage the collaboration of
several heterogeneous devices working in a highly dynamic context
both in terms of processing capabilities and connectivity. Beyond
resource limitations, data locally collected or generated by
devices might statistically differ from one device to another,
even if collected by the same application or belonging to the same
phenomenon. Finally, human intervention in the AI process is still
predominant, especially in its initial phases, e.g., data
preparation, labeling, and pre-processing, thus limiting the
necessary speed up to make AI truly pervasive. <br>
<br>
Topics of interest<br>
------------------<br>
The PeRConAI workshop aims to foster the development and
circulation of new ideas and research directions on pervasive and
resource-constrained AI/ML, bringing together practitioners and
researchers working on the intersection between pervasive
computing and machine learning.<br>
The PeRConAI workshop solicits contributions on, but not limited
to, the following topics:<br>
<br>
** Foundations of Advanced Machine learning algorithms and methods
for pervasive systems subject to resource limitations addressing
the following open challenges:<br>
<br>
- Distributed/decentralized Machine Learning for
resource-constrained devices (e.g., resource-efficient federated
learning);<br>
- Lightweight ML models for on-device training/inference in
pervasive computing (e.g., GRU, ELM, MHN, etc.);<br>
- Sustainable AI through new, brain- and bio-inspired ML
algorithms exploiting energy-efficient hardware, e.g., FPGA,
Neuromorphic HW;<br>
- Compression of deep learning models for real-time inference<br>
- Privacy-preserving distributed/decentralized learning in
pervasive and resource-constrained scenarios;<br>
- Trustworthiness of distributed/decentralized learning systems in
pervasive and resource-constrained scenarios;<br>
- Semi-supervised and self-supervised learning systems in
pervasive and resource-constrained scenarios;<br>
- Learning with imbalanced data in pervasive and
resource-constrained scenarios;<br>
- Continual learning in pervasive and resource-constrained
scenarios;<br>
Over-the-air computing for distributed/decentralized learning
systems in pervasive and resource-constrained scenarios.<br>
<br>
** Applications of Advanced Machine learning algorithms, methods,
and approaches for pervasive computing under resource limitations
applied to the following application domains:<br>
<br>
- Health and well-being applications (e.g., activity recognition,
health monitoring).<br>
- Anomaly/Novelty detection (e.g., Industry 4.0, intrusion
detection, privacy, and security).<br>
- Audio signal processing (e.g., sound event detection, speech
recognition/processing).<br>
- Video stream processing on resource-constrained devices.<br>
- Natural Language Processing and Information Retrieval (e.g.,
conversational applications running on resource-constrained,
mobile, or<br>
edge devices).<br>
- Intersection between mobile computing with ML/DL on
resource-constrained devices.<br>
- Any other real-world applications and case studies where the
pervasiveness of resource-constrained devices is central for
knowledge extraction.<br>
<br>
Submissions Guidelines<br>
----------------------<br>
All papers must be at most 6 pages of technical content, typeset
in double-column IEEE format using 10pt fonts on US letter paper,
with all fonts embedded. In PeRConAI, the peer-review process will
be single-blind. <br>
Submissions must be made via EasyChair. The IEEE LaTeX and
Microsoft Word templates and related information can be found on
the IEEE Computer Society website.<br>
<br>
PeRConAI will be held in conjunction with IEEE PerCom 2025 (<a
href="https://urldefense.com/v3/__https://www.percom.org__;!!D9dNQwwGXtA!QWOqdtRbbS04WTruHR9bBpceE5iCrIJmUEw3q_PXt2ohUb521g4z1EZw4o82NqTzwG9lvtNpDE7ug8Q_2JTauSRHZQ5znRi3ZhRAbw$"
target="_blank">https://www.percom.org</a>). All accepted papers
will be included in the Percom workshop proceedings and indexed in
the IEEEXplore digital library. At least one author must register
for the conference in full and present the paper during the
workshop.<br>
<br>
Steps:<br>
1- Follow the submission link: <a
href="https://urldefense.com/v3/__https://easychair.org/my/conference?conf=percom2025__;!!D9dNQwwGXtA!QWOqdtRbbS04WTruHR9bBpceE5iCrIJmUEw3q_PXt2ohUb521g4z1EZw4o82NqTzwG9lvtNpDE7ug8Q_2JTauSRHZQ5znRirKlVB7g$"
target="_blank">https://easychair.org/my/conference?conf=percom2025</a><br>
2- Select PeRConAI (4th Workshop on Pervasive and
Resource-Constrained AI)<br>
3- Fill in the form and upload the paper in PDF format. <br>
<br>
<br>
Organizing Committee<br>
--------------------<br>
Prof. Plamen Angelov, Lancaster University, UK<br>
Prof. Mario Luca Bernardi, University of Sannio, IT<br>
Dr. Paolo Dini, CTTC, ES<br>
Dr. Franco Maria Nardini, ISTI-CNR, IT<br>
Prof. Riccardo Pecori, eCampus University, IT and IMEM-CNR, IT<br>
Dr. Lorenzo Valerio, IIT-CNR, IT</p>
<p></p>
<div class="moz-signature">-- <br>
<font face="Calibri">
</font>
<p><font face="Calibri"><span style="font-size: 10pt;"><strong>Paolo
Dini</strong> <br>
Researcher (R4)<br>
<span style="font-size: 1pt;"><strong> </strong>
<span style="font-size: 10pt;">Sustainable Artificial
Intelligence (SAI) research unit<br>
Centre Tecnològic de Telecomunicacions de Catalunya
(CTTC)<br>
Av. Carl Friedrich Gauss, 7 - Building B4<br>
08860 - Castelldefels<br>
Tel.: +34 93 645 29 00</span></span></span></font></p>
<table>
<tbody>
<tr>
</tr>
</tbody>
</table>
<font face="Calibri">
</font>
<table>
<tbody>
<tr>
<td>
<p><span style="font-size: 8pt;"><u>DATA PROTECTION
INFORMATION. Data controller: CENTRE TECNOLOGIC DE
TELECOMUNICACIONS DE CATALUNYA (G62616586):</u></span></p>
</td>
</tr>
<tr>
<td>
<p><span style="font-size: 8pt;">We inform you that your
identification data and the data contained in the
emails and attached files can be incorporated into our
databases,
in order to maintain professional and / or commercial
relationships, and that it will be preserved
throughout the relationship.
According to the current regulations, you can exercise
your right to access, rectification, erasure,
restriction of processing, to portability and to
object by sending an email to <a class="moz-txt-link-abbreviated" href="mailto:dpo@cttc.cat">dpo@cttc.cat</a>. <br>
This message and any attached document, where
appropriate, may be confidential and intended for the
original recipient only.<br>
</span></p>
</td>
</tr>
<tr>
<td><br>
</td>
</tr>
<tr>
<td>
<p><span style="font-size: 8pt;">L'informem que les seves
dades identificatives i les compreses als correus
electrònics i fitxers adjunts poden ser incorporades a
les nostres bases de dades amb la finalitat de
mantenir relacions professionals i/o comercials i, que
seran conservades mentre es mantingui aquesta relació.
Si ho desitja, pot exercir el seu dret d'accés,
rectificació, supressió, limitació del tractament,
portabilitat i objecció enviant un correu electrònic a
<a class="moz-txt-link-abbreviated" href="mailto:dpo@cttc.cat">dpo@cttc.cat</a>. <br>
Aquest missatge i qualsevol document adjunt, en el seu
cas, pot ser confidencial i destinat únicament a la
persona o entitat a qui s'hagi enviat.
<br>
</span></p>
</td>
</tr>
<tr>
<td>
<p><span style="font-size: 7pt;"><font color="green">Before
printing this e-mail or attachments, be sure it is
necessary. It is in our hands to protect the
environment.</font><br>
</span></p>
</td>
</tr>
</tbody>
</table>
</div>
</body>
</html>