-
Enhancing Virtual Reality Usability With A ML Based Dynamic Adaptive System
Ananth Ramaseri-Chandra and Hassan Reza
Virtual reality (VR) holds tremendous potential, but cybersickness degrades the user experience. Since individuals vary, a one-size-fits-all design is insufficient. Our work introduces a dynamic adaptive system that personalizes VR experiences by learning individual cybersickness profiles from head-tracking data and sickness questionnaires while adjusting settings such as field of view and foveated rendering strength. Early results show that our system reduces post-exposure sickness scores, enhancing the user experience and highlighting the importance of personalizing VR.
-
Exploring the Feasibility of Head‐Tracking Data for Cybersickness Prediction in Virtual Reality
Ananth Ramaseri-Chandra, Hassan Reza, and Prasad Pothana
Traditional methods for predicting cybersickness rely on self-reported questionnaires or physiological signals from specialized sensors, which have their limitations. This study explores the potential of using real-time, easily acquired head-tracking data (HTD) from standard VR headsets as a scalable alternative for estimating cybersickness. Twenty-eight participants engaged in a VR session using an Oculus Quest 2 headset while their HTD was recorded. Kinematic metrics such as linear and angular velocity, acceleration, and jerk were computed from the HTD, including positional and angular parameters. Participants’ cybersickness levels were assessed using the Virtual Reality Sickness Questionnaire. The Gradient Boosting model demonstrated superior performance, accurately predicting cybersickness scores. Among these, the Gradient Boosting model demonstrated superior performance, accurately predicting cybersickness scores with prediction normalized differences of less than 4.8% on unseen data. This approach offers a scalable and practical solution for real-time cybersickness prediction in VR applications and compliments other techniques that rely on physiological sensors, hardware, or user profiles.
-
Malware Worm Attacks in Distributed Energy Resources (DERs)
Shree Ram Abayankar Balaji, Tanzim Jim Hassan, and Prakash Ranganathan
Malware is the short form of “Malicious Software” that is designed in a specific way to harm or exploit the host program with malicious intent. Often, the malware program replicates or appears as a legitimate executable program, which, upon the execution trigger, performs the programmed commands that cause systematic problems to the host machine. Malware attacks have become more sophisticated, which makes them more challenging to identify and analyze. If malware in critical infrastructures like Distributed Energy Resources (DER) are undetected, disruptions can occur in DERs. This poster discusses three types of malware worms (network, internet, and payload), historical malware attacks targeting DERs, and malware detection and classification for DERs.
-
Cybersecurity Challenges and Solutions in IoT-based Precision Farming System
Shree Ram Abayankar Balaji, Sriram Prabhakara Rao, and Prakash Ranganathan
Adaptation of technologies such as the Internet of Things (IoT), Unmanned Aerial Vehicles (UAVs), and blockchain in agriculture has revolutionized farming activities, offering several benefits such as increased efficiency, reduced costs, and improved crop yields. However, these advancements also have their fair share of security challenges, opening space for vulnerabilities that adversaries can exploit and compromising agricultural IoT networks, autonomous farming equipment, and vehicles. This may lead to compromised services and devices disrupting farming activities, causing losses to the farmers. This paper captures the state-of-the-art review of IoT-based precision farming systems, including the technological applications, cybersecurity challenges, and mitigation measures to secure the agricultural environment.
-
Generative AI-based Non-person Character (NPC) For Navigating Virtual Worlds
Ananth Ramaseri-Chandra
An innovative approach to virtual world interactions through generative AI-based Non-person Characters (NPCs). These AI-driven NPCs significantly advance over traditional, scripted characters by providing more realistic, adaptive, and dynamic interactions in various virtual environments. The work details the development process of these NPCs, from algorithm design to data integration and iterative refinement, ensuring their seamless integration into game environments. Additionally, the poster explores the wide-ranging applications of these AI NPCs, including enhancing gaming experiences, offering realistic training environments, and facilitating personalized virtual learning experiences. This research marks a substantial leap in virtual interaction, pushing the boundaries of immersion and realism in digital spaces.
Printing is not supported at the primary Gallery Thumbnail page. Please first navigate to a specific Image before printing.