John Sadowsky

Reducing the Interaction Burden of Complex Systems

Reducing the burden of interacting with complex systems has been a long standing goal of user interface design. In our approach to this problem, we have been developing user interfaces that allow users to interact with complex systems in a natural way and in high-level, task-related terms. These capabilities help users concentrate on making important decisions without the distractions of manipulating systems and user interfaces. To attain such a goal, our approach uses a unique combination of multi-modal interaction and interaction planning. In this paper, we motivate the basis for our approach, we describe the user interface technologies we have developed, and briefly discuss the relevant research and development issues.

Multidivisional graduate education program in sensory engineering

Sensory engineering is defined to be the science and technology of synthetic environments. This emerging discipline incorporates such technologies as virtual environments and virtual reality, data visualization, human sensory system modeling, human-machine interface, and perception, cognition and performance characterization. An educational curriculum requires basic science in the fields of computer science, electrical engineering, psychology, physiology, the biomedical sciences, and mathematics. The authors present the plan for a multidivisional graduate education program in sensory engineering, being developed at the Johns Hopkins University, within the Schools of Arts and Sciences, Engineering, Medicine, and the Applied Physics Laboratory.<<ETX>>

A synthetic environment system for planning, education and data visualization

An inexpensive workstation that creates an immersive environment for several people to see and manipulate computer generated 3D graphic objects would have many innovative and important applications, such as planning and brainstorming (3D viewgraphs), education (3D chalk-board), and data visualization. We have been developing a PC-based system with a multimedia architecture. Each participant uses a head-mounted display with a video camera at each eye, and mixes the live video with computer generated graphics to create a heads-up display of the common scene with added virtual objects. We present the architecture, design problems and solutions, and application experiences.<<ETX>>

Application of feedforward neural networks to object recognition for image analysis

Summary form only given, as follows. The automated analysis of X-ray images of mechanical fuses for nondestructive evaluation (NDE) requires that objects within the images be detected and recognized and that the orientations and relative positions of these objects be computed. Neural-network-based adaptive spatial filters for performing these functions are advantageous for many reasons, including robustness, flexibility, and adaptability to changes in fuse design. A research project has been started to investigate the use of feedforward neural networks to improve the performance of an NDE image analysis system. In particular, the objective was to develop a system which learns the rules for image understanding and could be applied to new or modified fuse designs with a minimum of software modification.<<ETX>>

NEURAL NETWORK ANALYSIS OF IMAGES FOR NON-DESTRUCTIVE EVALUATION

This paper reports an effort to develop a neural network-based system that is capable of analyzing images for the presence of particular features. In particular, the system would automatically analyze X-ray images as part of a non-destructive evaluation (NDE) function. Of particular interest is the development of neural network-based systems that can easily and inexpensively be retrained when design changes are made in parts to be inspected. Backpropagation networks with one hidden layer, based on classification and image compression concepts, were designed and tested with X-rays of Army M764 fuzes.