Search

Recently, there has been an increased use of wireless sensor networks and embedded systems in the medical sector. Healthcare providers are now attempting to use these devices to monitor patients in a more accurate and automated way. This would permit healthcare providers to have up-todate patient information without physical interaction, allowing for more accurate diagnoses and better treatment. One group of patients that can greatly benefit from this kind of daily monitoring is asthma patients. Healthcare providers need daily information in order to understand the current risk factors for asthma patients and to provide appropriate advice. It is not only important to monitor patients’ lung health, but also to monitor other physiological parameters, environmental factors, medication, and subjective feelings. We develop a smartphone, sensor rich, and cloud based asthma system called AsthmaGuide, in which a smartphone is used as a hub for collecting comprehensive information. The data, including data over time, is then displayed in a cloud web application for both patients and healthcare providers to view. AsthmaGuide also provides an advice and alarm infrastructure based on the collected data and parameters set by healthcare providers. With these components, AsthmaGuide provides a comprehensive ecosystem that allows patients to be involved in their own health and also allows doctors to provide more effective day-today care. Using real asthma patient wheezing sounds, we also develop two different types of classification approaches and show that one is 96% accurate, the second is 98.6% accurate and both outperform the state of art which is 87% accurate at automatically detecting wheezing. AsthmaGuide has both English and Korean language implementations.

We present a novel real-time algorithm to predict the path of pedestrians in cluttered environments. Our approach makes no assumption about pedestrian motion or crowd density, and is useful for short-term as well as long-term prediction. We interactively learn the characteristics of pedestrian motion and movement patterns from 2D trajectories using Bayesian inference. These include local movement patterns corresponding to the current and preferred velocities and global characteristics such as entry points and movement features. Our approach involves no precomputation and we demonstrate the real-time performance of our prediction algorithm on sparse and noisy trajectory data extracted from dense indoor and outdoor crowd videos. The combination of local and global movement patterns can improve the accuracy of long-term prediction by 12–18% over prior methods in high-density videos.

We present an adaptive data-driven algorithm for interactive crowd simulation. Our approach combines realistic trajectory behaviors extracted from videos with synthetic multi-agent algorithms to generate plausible simulations. We use statistical techniques to compute the movement patterns and motion dynamics from noisy 2D trajectories extracted from crowd videos. These learned pedestrian dynamic characteristics are used to generate collision-free trajectories of virtual pedestrians in slightly different environments or situations. The overall approach is robust and can generate perceptually realistic crowd movements at interactive rates in dynamic environments. We also present results from preliminary user studies that evaluate the trajectory behaviors generated by our algorithm.

We present an adaptive data-driven algorithm for interactive crowd simulation. Our approach combines realistic trajectory behaviors extracted from videos with synthetic multi-agent algorithms to generate plausible simulations. We use statistical techniques to compute the movement patterns and motion dynamics from noisy 2D trajectories extracted from crowd videos. These learned pedestrian dynamic characteristics are used to generate collision-free trajectories of virtual pedestrians in slightly different environments or situations. The overall approach is robust and can generate perceptually realistic crowd movements at interactive rates in dynamic environments. We also present results from preliminary user studies that evaluate the trajectory behaviors generated by our algorithm.

We present an interactive approach for analyzing crowd videos and generating content for multimedia applications. Our formulation combines online tracking algorithms from computer vision, non-linear pedestrian motion models from computer graphics, and machine learning techniques to automatically compute the trajectory-level pedestrian behaviors for each agent in the video. These learned behaviors are used to detect anomalous behaviors, perform crowd replication, augment crowd videos with virtual agents, and segment the motion of pedestrians. We demonstrate the performance of these tasks using indoor and outdoor crowd video benchmarks consisting of tens of human agents, moreover, our algorithm takes less than a tenth of a second per frame on a multi-core PC. The overall approach can handle dense and heterogeneous crowd behaviors and is useful for realtime crowd scene analysis applications.

Understanding and modeling how a crowd behaves in a wide variety of situations is an important problem in many areas. For example, during the planning stages, city, traffic, and evacuation engineers use crowd behavior modeling to predict usage patterns and to do safety analysis of their designs. Several research areas benefit from realistic simulation of crowds such as augmented reality, animation, games, virtual therapy, and virtual training. Not only is a realistic rendering of a virtual environment required for these applications, but also a realistic simulation of virtual humans is essential to providing an immersive experience for the users. The goal of my research is to provide an interactive simulation of a crowd, where large numbers of human-like agents interact with each other. A large part of my research comes from understanding and observing what human-like behavior is and how it affects interactions with others and the environment. In this proposal, I discuss my approaches to model crowd behaviors with variation and dynamic changes.