Daniel R. Schlegel

AirTouch: Interacting with computer systems at a distance

We present AirTouch, a new vision-based interaction system. AirTouch uses computer vision techniques to extend commonly used interaction metaphors, such as multitouch screens, yet removes any need to physically touch the display. The user interacts with a virtual plane that rests in between the user and the display. On this plane, hands and fingers are tracked and gestures are recognized in a manner similar to a multitouch surface. Many of the other vision and gesture-based human-computer interaction systems presented in the literature have been limited by requirements that users do not leave the frame or do not perform gestures accidentally, as well as by cost or specialized equipment. AirTouch does not suffer from these drawbacks. Instead, it is robust, easy to use, builds on a familiar interaction paradigm, and can be implemented using a single camera with off-the-shelf equipment such as a webcam-enabled laptop. In order to maintain usability and accessibility while minimizing cost, we present a set of basic AirTouch guidelines. We have developed two interfaces using these guidelines-one for general computer interaction, and one for searching an image database. We present the workings of these systems along with observational results regarding their usability.

Natural language understanding for soft information fusion

Tractor is a system for understanding English messages within the context of hard and soft information fusion for situation assessment. Tractor processes a message through syntactic processors, and represents the result in a formal knowledge representation language. The result is a hybrid syntactic-semantic knowledge base that is mostly syntactic. Tractor then adds relevant ontological and geographic information. Finally, it applies hand-crafted syntax-semantics mapping rules to convert the syntactic information into semantic information, although the final result is still a hybrid syntactic-semantic knowledge base. This paper presents the various stages of Tractors natural language understanding process, with particular emphasis on discussions of the representation used and of the syntax-semantics mapping rules.

Visually interacting with a knowledge base using frames, logic, and propositional graphs

The knowledge base of a knowledge representation and reasoning system can simultaneously be thought of as being logic-, frame-, and graph-based. We present a method for naturally extending this three-fold view to methods for visual interaction with the knowledge base in the context of SNePS 3 and its newly developed user interface. Addition to, and querying of, the knowledge base are tasks well suited to a frame or logical representation. Visualization and exploration on the other hand are best done through the use of propositional graphs. We show how these interaction techniques, which are extensions of the underlying knowledge base representation, augment each other to allow users to manipulate and view large knowledge bases.

Artificial Intelligence: Bayesian versus Heuristic Method for Diagnostic Decision Support

Evoking strength is one of the important contributions of the field of Biomedical Informatics to the discipline of Artificial Intelligence. The University at Buffalos Orthopedics Department wanted to create an expert system to assist patients with self-diagnosis of knee problems and to thereby facilitate referral to the right orthopedic subspecialist. They had two independent sports medicine physicians review 469 cases. A board-certified orthopedic sports medicine practitioner, L.B., reviewed any disagreements until a gold standard diagnosis was reached. For each case, the patients entered 126 potential answers to 26 questions into a Web interface. These were modeled by an expert sports medicine physician and the answers were reviewed by L.B. For each finding, the clinician specified the sensitivity (term frequency) and both specificity (Sp) and the heuristic evoking strength (ES). Heuristics are methods of reasoning with only partial evidence. An expert system was constructed that reflected the posttest odds of disease-ranked list for each case. We compare the accuracy of using Sp to that of using ES (original model, p < 0.0008; term importance * disease importance [DItimesTI] model, p < 0.0001: Wilcoxon ranked sum test). For patient referral assignment, Sp in the DItimesTI model was superior to the use of ES. By the fifth diagnosis, the advantage was lost and so there is no difference between the techniques when serving as a reminder system.

Comparing Small Graph Retrieval Performance for Ontology Concepts in Medical Texts

Some terminologies and ontologies, such as SNOMED CT, allow for post–coordinated as well as pre-coordinated expressions. Post–coordinated expressions are, essentially, small segments of the terminology graphs. Compositional expressions add logical and linguistic relations to the standard technique of post-coordination. In indexing medical text, many instances of compositional expressions must be stored, and in performing retrieval on that index, entire compositional expressions and sub-parts of those expressions must be searched. The problem becomes a small graph query against a large collection of small graphs. This is further complicated by the need to also find sub-graphs from a collection of small graphs. In previous systems using compositional expressions, such as iNLP, the index was stored in a relational database. We compare retrieval characteristics of relational databases, triplestores, and general graph databases to determine which is most efficient for the task at hand.