Tutorial Lecture 

Tutorial Lectures

 Tutorial Lecture

Title: HCI in IoT-based Modern Systems  

Dr. Urjaswala Vora, Ph.D.

College of Information Sciences and Technology

The Pennsylvania State University, State College, USA

 Link for personal Webpage

Urjaswala Vora is working as Associate Teaching Professor at the Pennsylvania State University since January 2022. Earlier she was working as Associate Director at the Centre for Development of Advanced Computing, an Autonomous Premier Research and Development Society of the Government of India. She has more than 25 years of project experience that includes delivery of projects in the domains of Smart Cities, Biometrics, eGovernance and Enterprise Architectures . She has taught and mentored undergraduate as well as graduate students for more than 23 years. Her research interests include Complex Systems, Software Architecture, Internet of Things, Distributed Computing and Software Engineering. She has a PhD in Computer Science and Engineering from IIT Bombay and a bachelor’s degree in computer science from the University of Pune.  

Lecture Description 

The focus of my lecture is using crowdsourcing in the IoT-based modern systems. Each of these systems is a complex system of systems and the quality attributes that are to be considered in the design of these systems as well the sustainability of their operations varies based on its component systems as well as their functional integration. For example, a Surveillance System requires edge devices, edge computing as well as emergency response systems integrated along with people interacting with certain edge devices to trigger certain events. Another example is of a Transportation system that requires the predictive modeling for sustainable infrastructure design and integrated infrastructure components that may include self-driving cars, hyperloop, congestion pricing modeling and virtual traffic lights along with people adding real-time data deriving right inferences for self-adaptive system components. Howe [1] defines “Crowdsourcing” as the act of taking a task traditionally performed by a designated agent and outsourcing it by making an open call to an undefined but large group of people. It harnesses the collective intelligence or knowledge base of crowd's wisdom and in the right set of conditions, the crowd always tends to outperform any number of employees. Ensuring this right set of conditions is the key to success [5]. During this tutorial we will discuss the usage of crowdsourcing in the development process as well as the self-sustainability of IoT-based systems 


Topics to be Covered. 

• Modern Systems

• Why System of Systems

• Design Issues

• Use Cases 

o Design Solutions as individual domain 

o Design Challenges as Multidisciplinary engineering systems 

o Crowdsourcing used at design level and at self-adaptive operations’ level 

• Open Research Challenges 

o At the Technology-level 

o At the Application-domain-level 

o For Crowdsourcing 

• Design Exercises 

o Review Design Solutions 

o Thinking out-of-the-box 

o Analyzing the Submitted solutions. 

               Shael Brown 

         Colleen M. Farrelly

      Yashbir (Yash) Singh

 Tutorial Lecture

Title: Medical Data Study: Exploring Text Embeddings through Machine Learning and Topological Data Analysis   

Shael Brown is a PhD student at McGill University using topology to study the neural mechanisms of human vision. He has worked as a data scientist in the professional sports and energy sectors, focusing on applications of machine learning. His R software package, TDApplied, is the first publicly available toolbox for analyzing groups of persistence diagrams with published machine learning and statistical inference procedures. 

Colleen M. Farrelly is an industry mathematician whose work focuses on applications of topology and geometry to machine learning. She received her MS in Biostatistics from University of Miami, where her research focused on topology-based psychometrics and dynamic systems. Her current research focuses on geometric and topological methods in natural language processing, network science, and generative AI. She’s worked a variety of fields, including healthcare, nuclear engineering, quantum computing, consumer goods, educational technology, and marketing. Her first book, The Shape of Data, focuses on machine learning from a geometric perspective. A second book focusing on network science applications is forthcoming.  

Dr. Yashbir (Yash) Singh, Ph.D., is an Assistant Professor of Radiology at the Mayo Clinic, Rochester, MN. His accomplished career includes a role as a Medical Scientist at WVU Medicine, USA, a DAAD fellow, and he is an active member of the New York Academy of Sciences. Dr. Singh's research concentrates on deep learning-based artificial intelligence (AI) and topological data analysis within medical imaging, specifically enhancing the interpretability of AI models and discovering new disease imaging biomarkers. 

Lecture Description 

The digital era has brought forth an explosion of textual data, leading to the evolution of sophisticated embedding techniques and analytical methods. This tutorial offers a holistic exploration of text embeddings, their application in machine learning, and the innovative ways to analyze them through topological data analysis. Dive deep into the world of embeddings, uncover biases, and discern the intricate topological structures inherent in high-dimensional text data.

Topics to be Covered.