Yang Cai

A novel imaging system for tongue inspection

A digital imaging and modeling system is developed for tongue inspection, which has been an important diagnostic method of Traditional Chinese Medicine (TCM). The system includes image acquisition, color calibration, image segmentation, feature extraction and classification functions. The preliminary results show that the color and texture features are sensitive to the abnormal tongues.

Visual transformation for interactive spatiotemporal data mining

Analytical models intend to reveal inner structure, dynamics, or relationship of things. However, they are not necessarily intuitive to humans. Conventional scientific visualization methods are intuitive, but limited by depth, dimension, and resolution. The purpose of this study is to bridge the gap with transformation algorithms for mapping the data from an abstract space to an intuitive one, which include shape correlation, periodicity, multiphysics, and spatial Bayesian. We tested this approach with the oceanographic case study. We found that the interactive visualization increases robustness in object tracking and positive detection accuracy in object prediction. We also found that the interactive method enables the user to process the image data at less than 1 min per image versus 30 min per image manually. As a result, our test system can handle at least 10 times more data sets than traditional manual analyses. The results also suggest that minimal human interactions with appropriate computational transformations or cues may significantly increase the overall productivity.

Ambient intelligence for scientific discovery

Human-Computer Interaction in scientific discovery has been gaining a momentum since the last decade due to its potential payoffs in applications, such as drug discovery, nano-materials or telecommunication. In HCI history, many advanced human interfaces were invented by members of the scientific community, such as the World Wide Web from CERN and the “Glass Cockpit” from NASA. With the growth of data streams and complexity of discovery tasks, there are demands for ambient intelligence such as peripheral vision, soft agents, data mining, and semantic web.

Feature hiding in 3D human body scans

In this paper, we explore a privacy algorithm that detects human private parts in a 3D scan data set. The analogia graph is introduced to study the proportion of structures. The intrinsic human proportions are applied to reduce the search space in an order of magnitude. A feature shape template is constructed to match the model data points using Radial Basis Functions in a non-linear regression and the relative measurements of the height and area factors. The method is tested on 100 data sets from CAESAR database. Two surface rendering methods are studied for data privacy: blurring and transparency. It is found that test subjects normally prefer to have the most possible privacy in both rendering methods. However, the subjects adjusted their privacy measurement to a certain degree as they were informed of the context of security.

Minimalism context-aware displays.

Despite the rapid development of cyber technologies, today we still have very limited attention and communication bandwidth to process the increasing information flow. The goal of the study is to develop a context-aware filter to match the information load with particular needs and capacities. The functions include bandwidth-resolution trade-off and user context modeling. From the empirical lab studies, it is found that the resolution of images can be reduced in order of magnitude if the viewer knows that he/she is looking for particular features. The adaptive display queue is optimized with real-time operational conditions and users inquiry history. Instead of measuring operators behavior directly, ubiquitous computing models are developed to anticipate users behavior from the operational environment data. A case study of the video stream monitoring for transit security is discussed in the paper. In addition, the author addresses the future direction of coherent human-machine vision systems.

A privacy algorithm for 3d human body scans

In this paper, we explore a privacy algorithm that detects human private parts in a 3D scan dataset. The intrinsic human proportions are applied to reduce the search space by an order of magnitude. A feature shape template is constructed to match the model data points using Radial Basis Functions in a non-linear regression. The feature is then detected using the relative measurements of the height and area factors. The method is tested on 100 datasets from CAESER database.

BioSim-a biomedical character-based problem solving environment

Understanding and solving biomedical problems requires insight into the complex interactions between the components of biomedical systems by domain and non-domain experts. This is challenging because of the enormous amount of data and knowledge in this domain. Therefore, non-traditional educational tools have been developed such as a biological storytelling system, animations of biomedical processes and concepts, and interactive virtual laboratories. The next-generation problem solving tools need to be more interactive to include users with any background, while remaining sufficiently flexible to target open research problems at any level of abstraction, from the conformational changes of a protein to the interaction of the various biochemical pathways in our body. Here, we present an interactive and visual problem solving environment for the biomedical domain. We designed a biological world model, in which users can explore biological interactions by role-playing characters such as cells and molecules or as an observer in a shielded vessel, both with the option of networked collaboration between simultaneous users. The system architecture of these characters contains four main components: (1) bio-behavior is modeled using cellular automata; (2) bio-morphing uses vision-based shape tracking techniques to learn from recordings of real biological dynamics; (3) bio-sensing is based on molecular principles of recognition to identify objects, environmental conditions and progression in a process; (4) bio-dynamics implements mathematical models of cell growth and fluid-dynamic properties of biological solutions. The principles are implemented in a simple world model of the human vascular system and a biomedical problem that involves an infection by Neisseria meningitides where the biological characters are white and red blood cells and Neisseria cells. Our case studies show that the problem solving environment can inspire users strategic, creative and innovative thinking.

How many pixels do we need to see things

Todays computer display devices normally provide more information than we need. In this paper, the author presents an empirical model that shows minimal pixel requirements for computer users to recognize things from digital photos under different contextual conditions. It is found that face recognition alone needs far fewer pixels than people normally thought. However, more pixels are needed for users to recognize objects within outdoor scenes and paintings. Color and age have effect on object recognition but the differences are not significant. The results can be applied to adaptive display design, computer vision, adaptive human-computer interaction and telecommunication system design.

Interactive Visualization of Network Anomalous Events

We present an interactive visualization and clustering algorithm that reveals real-time network anomalous events. In the model, glyphs are defined with multiple network attributes and clustered with a recursive optimization algorithm for dimensional reduction. The users visual latency time is incorporated into the recursive process so that it updates the display and the optimization model according to a human-based delay factor and maximizes the capacity of real-time computation. The interactive search interface is developed to enable the display of similar data points according to the degree of their similarity of attributes. Finally, typical network anomalous events are analyzed and visualized such as password guessing, etc. This technology is expected to have an impact on visual real-time data mining for network security, sensor networks and many other multivariable real-time monitoring systems.

Towards biomedical problem solving in a game environment

Biomedical systems involve complex interactions between diverse components. Problem solving in such systems requires insight, i.e. the capability to make non-obvious connections. In this paper, we present a game-based problem solving environment, where users can explore biological interactions with navigation on atomic to macroscopic scales, role-play, and networked collaboration. The study investigates the system architecture of the biological game, bio-morphing characters, and bio-interactions with biosensing and biodynamics. The prototype has been implemented on PC and tested in a preschool environment where users have little knowledge in biology. The experiment shows that the game greatly inspired users both in concept learning and entertainment.