Topical Track: Artificial Intelligence and Machine Learning

Track ID: Topi-04

 

Description

As the number of interconnected devices continues to grow exponentially, leveraging AI and ML algorithms becomes imperative for extracting valuable insights from vast amounts of IoT data. By leveraging AI and ML algorithms, IoT devices can gather and analyze vast amounts of data in real time, enabling intelligent decision-making and automation. AI/ML models can identify patterns, predict outcomes, and make informed recommendations, enhancing the efficiency and performance of IoT systems. Moreover, by uncovering hidden patterns and correlations, these technologies enable businesses to make data-driven decisions, optimize operations, and create personalized experiences for users.

The topics which the “Artificial Intelligence and Machine Learning for IoT Track” Presentations, Panels, and Working Group discussions will cover include:

• "Federated Learning for Secure and Privacy-Preserving IoT Systems": Explore techniques that leverage federated learning to train AI/ML models on distributed IoT devices while ensuring data privacy and security.
• "Edge Intelligence in IoT: Real-Time Decision-Making at the Edge": Discover advancements in edge intelligence, enabling IoT devices to process data locally, make intelligent decisions in real-time, and reduce reliance on cloud infrastructure.
• "Deep Reinforcement Learning for IoT Resource Management": Investigate how deep reinforcement learning algorithms can optimize resource allocation and management in dynamic IoT environments, enhancing efficiency and scalability.
• "Explainable AI for Trustworthy IoT Applications": Delve into explainable AI approaches that provide interpretable insights into the decision-making process of AI models in IoT scenarios, fostering trust and transparency.
• "Predictive Maintenance in Industrial IoT: Leveraging AI/ML for Enhanced Reliability": Explore the application of AI and ML techniques in predicting and preventing equipment failures in industrial IoT settings, optimizing maintenance schedules, and minimizing downtime.
• "AI-Driven Security in IoT: Detecting and Mitigating Cyber Threats": Discuss the integration of AI and ML algorithms for real-time detection and mitigation of cyber threats, ensuring robust security measures for IoT ecosystems.
• "Machine Learning for Energy Optimization in Smart Grids": Investigate the use of machine learning algorithms to optimize energy consumption, demand response, and renewable energy integration in smart grid systems, enabling efficient and sustainable energy management.

 

Sessions

Session 1: Federated Learning within IoT. This session delves into the profound implications of Federated Learning within the Internet of Things (IoT) domain. With a focus on collaborative machine learning models trained on distributed IoT devices, the session uncovers the revolutionary potential of this decentralized approach in eliminating the necessity for centralized data collection. By examining the practical applications of Federated Learning within IoT, comprehensive insights will be gained into its transformative impact on the landscape of intelligent IoT systems.

 

Session 2: AI-Enabled IoT Resource Management. This session delves into the convergence of Artificial Intelligence (AI) and the Internet of Things (IoT) to enable efficient resource management in IoT ecosystems. The session will explore how machine learning and optimization algorithms, can be leveraged to dynamically allocate resources, optimize energy consumption, and enhance overall system performance.

 

Session 3: AI-Driven Security in IoT. This session delves into the critical domain of AI-driven security within the context of the Internet of Things (IoT). Exploring the integration of Artificial Intelligence (AI) techniques and methodologies, experts will showcase the latest advancements in securing IoT ecosystems against emerging threats. Attendees will gain insights into how AI-driven solutions, including anomaly detection, behavioral analysis, and predictive modeling, can fortify IoT devices, networks, and applications against malicious activities and vulnerabilities. Additionally, discussions will revolve around the challenges and future directions of AI-driven security in IoT, offering a platform for scholarly discourse and fostering a deeper understanding of safeguarding the ever-expanding IoT landscape.

 

Session 4: Explainable AI for Trustworthy IoT Applications. This session focuses on the imperative aspect of Explainable Artificial Intelligence (AI) within the realm of Internet of Things (IoT) applications to foster user trust and confidence. By elucidating the underlying mechanisms and interpretability of AI models, this session will explore how Explainable AI techniques can bridge the gap between complex AI algorithms and end-users, ensuring transparency, accountability, and comprehensibility.

 

Session 5: Predictive Maintenance in IIoT: Leveraging AI/ML for Enhanced Reliability. This session delves into the realm of Predictive Maintenance in Industrial Internet of Things (IIoT) ecosystems, focusing on the utilization of Artificial Intelligence (AI) and Machine Learning (ML) techniques to achieve heightened reliability and efficiency. The session will describe the latest advancements in predictive maintenance methodologies, real-time monitoring, and anomaly detection in IIoT systems.

 

Chairs

Mário Antunes: Universidade de Aveiro, Portugal

Mário Antunes serves as an Assistant Professor at the University of Aveiro. In 2018, he successfully completed his doctoral program in computer science at MAPi, where he distinguished himself as a finalist in three prestigious international competitions: the ERCIM Cor Baayen Young Researcher Award 2019, the Altice International Innovation Award 2019, and the "Melhor Tese de Doutoramento em STI - 2019." His primary research interests revolve around Knowledge Extraction and Context Storage in IoT Scenarios, employing cutting-edge techniques such as Machine Learning and Big Data repositories.

 

 

 

 

Flavio Cirillo: NEC Labs, Germany

Dr. Flavio Cirillo is a Senior Research Scientist of the Data Ecosystem and Standard research team at NEC Laboratories Europe, Heidelberg, Germany. His research topics include AI/ML applied to IoT, and IoT analytics platforms focusing on cloud-edge, federation, data usage control aspects. The main application scenario is Smart Cities. He has worked on many IoT related European research projects. He has obtained a PhD in Information Technology and Electric Engineering at the University of Naples Federico II (Italy).