Watch Again | IEEE WIE UKI Ambassadors’ Scheme Early Career Talk 11 – An Inspirational and Empowering Webinar for Women in Engineering

IEEE WIE in Engineering is an initiative with the goal to facilitate the recruitment and retention of women in technical disciplines globally. We envisage a vibrant community of IEEE women and men collectively using their diverse talents to innovate for the benefit of humanity.

Speaker: Dr Shidrokh Goudarzi

Area of career: Academia

Research interest: Wireless networks, artificial intelligence, machine learning, next-generation networks, Internet of Things (IoT) and mobile/distributed/cloud computing

Talk title: Optimised Edge Computing for Industrial IoT via UAV-Assisted Mobile Edge Servers

Summary: Edge computing optimises Industrial IoT by offloading demanding tasks from devices to potent edge servers. Mobile Edge Computing (MEC) is facilitated for ground nodes via UAV-enabled edge servers using time-division multiple access. Despite current MEC limitations with rising MNs or sparse resources, remotely controlled UAVs offer adaptability.

Accessibility through MNs in wireless networks poses a challenge. Addressing this, a cooperative computation model optimises resource allocation, ensuring MN task timeliness and energy efficiency. A multilayer data flow system incorporates cloud, UAV-assisted MEC servers, and mobile devices for enhanced computational utilization. Numerical analysis confirms the superiority of the scheme over traditional methods.

Biography: Shidrokh Goudarzi is a lecturer in Computer Science at the School of Computing and Engineering at the University of West London. Prior to this, she was working at the Centre for Vision, Speech, and Signal Processing (CVSSP), University of Surrey.

She received her PhD degree in communication systems and wireless networks. She serves as a reviewer for several journals.

Speaker: Dr Yuhan Liu

Area of career: Academia

Research interests: Intelligent autonomous systems, learning-based control, data-driven modeling and control, space vehicles, Gaussian process and applications on quadrotors.

Talk title: Learning for predictive control: A Dual Gaussian Process Approach

Summary: An important issue in model-based control design is that an accurate dynamic model of the system is generally nonlinear, complex, and costly to obtain. This limits achievable control performance in practice. In this talk, we will present a novel Dual Gaussian Process (DGP) based model predictive control (MPC) strategy that enables efficient use of online learning based predictive control to have the advantages of both forgetting prevention and without the danger of catastrophic forgetting. Furthermore, a novel recursive online update strategy for the GP model is proposed to successively improve the learnt model during online operation in an efficient way.

Biography: Yuhan Liu received the M.Sc. and Ph.D. degrees in control science and engineering from Harbin Institute of Technology, Harbin, China, in 2017 and 2022, respectively.

She is currently a postdoctoral researcher with the Control Systems Group, Eindhoven University of Technology (TU/e), Eindhoven, the Netherlands. Her current research interests include intelligent autonomous systems, data-driven modeling and control and learning-based control.

Speaker: Shahed Alghrsi

Area of career: Industry

Research interests: Generative Models

Talk title: A Comparative Approach on Generative Models in Art Generation

Summary: Generative models are a class of machine learning models that are designed to learn and model the underlying probability distribution of a given dataset. These models are capable of generating new samples that resemble the training data and can be used to generate new, previously unseen data points, the talk will highlight the social impact of technology on our day-to-day lives, war destruction images were used as a reference in the generation process.

Biography: Shahed Alghrsi MLOps Engineer @Virgin Media O2 worked in different industries building ML pipelines for different projects, delivered several sessions and workshops with Google developers and IEEE, interested in computer vision and did her masters in ML for visual data analytics at Queen Mary University.

Speaker: Hooman Sarvghadi

Area of career: Academia

Research interests: Wireless Sensor Networks

Talk title: BLUE-TSCH: Decentralised Blacklisting Method for Large-Scale Multi-Hop Time-Slotted Channel Hopping (TSCH) Networks

Summary: BLUE-TSCH is a new blacklisting method for IWSNs that can significantly improve network performance by preventing packet loss in noisy environments. BLUE-TSCH allows each node to create its own hopping sequence list based on the environmental conditions it feels around, which ensures that only the most reliable radio channels are used.

Biography: https://www.linkedin.com/in/hooman-sarvghadi