Keynotes
Prof. Dr. GIANCARLO STORTI GAJANI
Politecnico di Milano, Italy
He received the Dr. Ing degree in electronic engineering and the Ph. D. degree in electronic systems from Politecnico di Milano in 1986, and 1991 respectively. Since 1992 he is Assistant Professor and since 2002 Associate Professor of Circuit Theory in the same University. His research interests have initially focused on the development of architectures for signal processing (in particular, for audio and music applications) and neural networks. More recently, his research interests include non linear circuits and machine learning methods applied to power engineering. He is a senior member of IEEE and the author of more than 90 papers in international Journals and Conferences.
Title: Artificial Intelligence in Power Systems and Electric Mobility
Abstract:
The changing nature of power systems alongside the increasing presence of electric vehicles,
which presents both challenges and opportunities, makes the availability of
tools capable of prediction of the utmost importance.
AI and ML applications improve power systems' ability to predict outcomes,
allowing for better electricity demand, price, and generation forecasts,
which is needed to balance supply with demand and avoid blackouts.
While vital for lowering emissions, the incorporation of renewable energy
creates stability issues that ML can solve through better forecasting
and optimized dispatch and storage.
The expansion of EV charging infrastructure impacts grid stability,
potentially causing voltage fluctuations and overloading, which calls
for intelligent management systems.
The aggregator model presented, which uses RL to optimize charging and
reduce grid overloads, is one such system.
When Optimal Power Flow (OPF) is addressed with AI and RL, it allows
for the lowest operational costs while maintaining system security,
which is critical for efficient grid operation.
Microgrid control in Renewable Energy Communities (RECs) benefits from
Model Predictive Control (MPC) models that are enhanced with
LSTM-based predictors.
This optimizes resource management and promotes renewable energy use.
Finally, AI's adaptability enables dynamic stability control and adjustments
to changing grid conditions, assuring better energy management and dispatch.
Dr. DENIZ GENCAGA
Antalya Bilim University, Türkiye
Deniz Gencağa is a current member of the engineering faculty at the Antalya Bilim University in Antalya, Turkey. He received the Ph.D. degree in electrical and electronics engineering from Boğaziçi University in 2007. Same year, he joined State University of New York at Albany, as a postdoctoral researcher. Between 2009 and 2011, he was a research associate at the NOAA Center for Earth System Sciences & Remote Sensing Technologies Center of the City University of New York, USA. Until 2017, he took roles in inter-disciplinary projects at universities, including the University of Texas Department of Space Sciences and Carnegie Mellon University. Until 2016, he was the chair of IEEE Pittsburgh signal processing and control systems societies. Since 2017, he has been an Assistant Professor at the electrical and electronic engineering department of the Antalya Bilim University. He is a member of the editorial board of Entropy, inventor in three US patents, recipient of NATO research fellowship, general chair of the first ECEA and one of the organizers of MaxEnt 2007. His research interests include statistical signal processing, Bayesian inference, uncertainty modeling and causality.
Title: Uncovering Causal Dynamics in AI with Transfer Entropy
Abstract:
Causality analysis is increasingly acknowledged as essential for developing robust, interpretable, and reliable artificial intelligence (AI) systems. Unlike conventional machine learning approaches that emphasize pattern recognition and correlations, causal analysis enables AI to discern true cause-and-effect relationships rather than mere statistical associations. This enhances decision-making, especially in dynamic or changing data environments.
This talk highlights Transfer Entropy, an information-theoretic method for uncovering causal interactions from data. Transfer entropy measures the directional flow of information between variables, making it particularly effective for identifying causality in complex, high-dimensional systems. In AI, it allows systems to move beyond surface-level correlations and capture deeper causal dynamics within data. Its model-independent framework makes it suitable for handling nonlinearities and non-Gaussian distributions, common in neural networks and multi-agent environments.
Practical applications include improving AI model explainability and robustness, analyzing information flow in deep learning architectures, and supporting causally grounded decision-making in domains such as healthcare, finance, and autonomous systems.
Dr. Rita Singh
Carnegie Mellon University, USA
Dr. Rita Singh is a Research Professor at the Language Technologies Institute, School of Computer Science at Carnegie Mellon University (CMU) and a visiting Research Professor at the University of Pittsburgh in USA. She is the Director of the Center for Voice Intelligence and Security at CMU, and ISCA Distinguished Lecturer. Her academic career spans over two decades of research on a wide range of topics in speech and audio processing, multimedia forensics and cyber forensics with pioneering contributions in developing the science of profiling humans from their voice, a sub-area of Artificial Intelligence and Voice Forensics. She has extensive patents and publications in these areas. Her current work is focused on creating multimedia AI systems with a wide range of capabilities including human profiling, and AGI systems accelerated by quantum computing. The technology pioneered by her group has led to three world firsts: In September 2018, her team created the world’s first live voice-based profiling system, demonstrated live at the World Economic Forum in Tianjin, China. In 2019 her group also created the world’s first instance of human voice – that of the artist Rembrandt – generated based on evidence from his facial self-portraits. In 2020, her team built the technology that demonstrated and enabled the detection of Covid-19 from voice. At CMU, she teaches multiple graduate level courses including Computational Forensics and AI, Generative AI, Multimedia Processing, Quantum Computing, Quantum Cryptography and Quantum Machine Learning. She is the author of the book “Profiling Humans from their Voice,” published in June 2019 by Springer-Nature, Singapore.
Title: Human Voice as a Biometric: Can Generative AI Systems Really Emulate It
(Part of 2025 ISCA Distinguished Lecture Series)
Abstract: The human voice is unique. A conservative calculation (explained in this talk) easily shows that the chances of two people having the same voice are less than one in a trillion. This places the human voice alongside DNA and fingerprints as a powerful biometric. In some ways, it is more potent than the latter because it not only carries unique identifying characteristics of the speaker but also carries information about the speaker at the time of speaking. Over the past decade, Artificial Intelligence systems have become increasingly capable of emulating the human voice. However, many questions arise in this context: Is their capability limited in any way? Is our evaluation thereof biased by our auditory perception? Can generative AI systems really emulate the information embedded in the human voice? Are they on a trajectory to threaten its use as a biometric entity in real life applications? What are the implications of that? In this talk we will ponder all of these issues. At a high level, we will briefly discuss how generative AI systems and audio foundation models work, and analyze their current and future capabilities, extrapolating all the way to quantum-accelerated AI systems.
ACDSA
International Conference on Artificial Intelligence,
Computer, Data Sciences and Applications
Contact
ECER EventsWorld Wide Commercial Building, No:72
Al Hilal, D Ring Road, Doha, Qatar +974 72021173 info@acdsa.org