IAAI ON WEDNESDAY, JULY 17TH, 2013

ABSTRACT. As access to Earth and space science data and information became routine, efforts moved beyond their discipline, and vocabulary challenges arose; some were quite esoteric and jargon laden. As we understood the requirements, we chose a technology foundation that was based on a long history of artificial intelligence (AI) research set in the context of the modern world-wide-web (WWW) environment because of the promise for a declarative, extensible, re-usable platform. We developed and implemented the semantic methodology throughout the effort and found that it provided consistency as we met user requirements. While individual technology components might change, this did not affect our ability to deliver a capability that was useful and usable, especially by a broad range of people, some of whom will not be trained in all areas of science covered in the collection.

ABSTRACT. This paper describes USI Answers - a natural language question answering system for semi-structured industry data. This paper reports on our progress towards the goal offering easy access to enterprise data to a large number of business users, most of whom are not familiar with the specific syntax or semantics of the underlying data sources. Additional complications come from the nature of the data, a combination of structured and unstructured. Our solution allows users to express questions in natural language, makes apparent the system's interpretation of the query, and allows easy query adjustment and reformulation. The application is in use by more than a thousand of users from Siemens Energy. We evaluate our approach on a dataset consisting of fleet data.

ABSTRACT. One of the major challenges to building intelligent educational software is determining what kinds of feedback to give learners. Useful feedback makes use of models of domain-specific knowledge, especially models that are commonly held by potential students. To empirically determine what these models are, student data can be clustered to reveal common misconceptions or common problem-solving strategies. This paper describes how analogical retrieval and generalization can be used to cluster automatically analyzed hand-drawn sketches incorporating both spatial and conceptual information. We use this approach to cluster a corpus of hand-drawn student sketches to discover common answers. Common answer clusters can be used for the design of targeted feedback and for assessment.

ABSTRACT. Controlling the quality of tasks is one of the big challenges in crowdsourcing marketplaces. Most of the existing crowdsourcing services prohibit requesters from posting illegal or objectionable tasks. Operators in the marketplaces have to continuously monitor posted tasks to find such improper tasks, however it is too costly to manually investigate every single task. In this paper, we report about our trial study on automatic detection of improper tasks for supporting the monitoring activities by marketplace operators. We perform experiments by using real task data from a commercial crowdsourcing marketplace and first show that the classifier trained by the operators' judgments achieves high accuracy to detect improper tasks. In addition, to reduce the annotation costs of the operator and improve classification accuracy, we consider the use of crowdsourcing for task annotation. We hire a group of crowdsourcing (non-expert) workers to monitor posted tasks, and incorporate their judgments into the training data of the classifier. By applying quality control techniques to handle the variability of the workers' reliability, our results show that the use of non-expert judgments by crowdsourcing workers in combination with expert judgments improves the accuracy of detecting improper crowdsourcing tasks.

ABSTRACT. Adverse and anomalous (A\&A) events are a serious concern in medical robots. We describe a system that can rapidly detect such events and predict their occurrence. As part of this system, we describe simulation, data collection and user interface tools we build for a robot for small animal biopsies. The data we collect consists of both the hardware state of the robot and variables in the software controller. We use this data to train dynamic Bayesian network models of the joint hardware-software state-space dynamics of the robot. Our empirical evaluation shows that (i) our models can accurately model normal behavior of the robot, (ii) they can rapidly detect anomalous behavior once it starts, (iii) they can accurately predict a future A\&A event within a time window of it starting and (iv) the use of additional software variables beyond the hardware state of the robot is important in being able to detect and predict certain kinds of events.

ABSTRACT. In recent years, there has been a great increase in the use of web services for the storage, annotation, and sharing of sports video by athletic teams. Most of these web services, however, do not provide enhanced functionalities to their users that would enable, e.g., faster access to certain video moments, or reduce manual labor in video annotation. One such web service specializes in American football videos, supporting over 13,000 high school and college teams. Its users often need to fast forward the video to certain moments of snap when the corresponding plays of the football game start. To our knowledge, this paper describes the first effort toward automating this enhanced functionality. Under a very tight running-time budget, our approach reliably detects the start of a play in an arbitrary football video with minimal assumptions about the scene, viewpoint, and video resolution and shot quality. We face many challenges that are rarely addressed by a typical computer vision system, such as, e.g., a wide range of camera viewing angles and distances, and poor resolution and lighting conditions. Extensive empirical evaluation shows that our approach is very close to being usable in a real-world setting.

ABSTRACT. Future radiology practices assume that the radiology reports should be uniform, comprehensive, and easily managed. This means that reports must be "readable" to humans and machines alike. In order to improve reporting practices in breast imaging, we allow the radiologist to write structured reports with a special pen on paper with an invisible dot pattern. In this way, we provide a knowledge acquisition system for printed mammography patient forms for the combined work with printed and digital documents. In this domain, printed documents cannot be easily replaced by computer systems because they contain free form sketches and textual annotations, and the acceptance of traditional PC reporting tools is rather low among the doctors. This is due to the fact that current electronic reporting systems significantly add to the amount of time it tasks to complete the reports. We describe our real-time digital paper application and focus on the use case study of our deployed application. We think that our results motivate the design and implementation of intuitive pen-based user interfaces for the medical reporting process and similar knowledge work domains. Our system imposes only minimal overhead on traditional form-filling processes and provides for a direct, ontology-based structuring of the user input for semantic search and retrieval applications, as well as other applied artificial intelligence scenarios which involve manual form-based data acquisition.

ABSTRACT. Emergency workers engaged in strenuous work in hot environments risk overheating and mission failure. We describe a real-time application that would reduce these risks in terms of a real-time thermal-work strain index (SI) estimator; and a Markov Decision Process (MDP) to compute optimal work rate policies. We examined the thermo-physiological responses of 14 fit and experienced U.S. Army Ranger students (26±4 years 1.77±0.04 m; 78.3±7.3 kg) who participated in a strenuous 8 mile time-restricted pass/fail road march conducted under thermally stressful conditions. A thermoregulatory model was used to derive SI state transition probabilities and model the students' observed and policy driven movement rates. We found that policy end-state SI was significantly lower than SI when modeled using the student's own movement rates (3.94±0.88 vs. 5.62±1.20, P<0.001). We also found an inverse relationship between our policy impact and maximum SI (r=0.64 P<0.05). These results suggest that modeling real world missions as an MDP can provide optimal work rate policies that improve thermal safety and allow students to finish in a 'fresher' state. Ultimately, SI state estimation and MDP models incorporated into wearable physiological monitoring systems could provide real-time work rate guidance, thus minimizing thermal work-strain while maximizing the likelihood of accomplishing mission tasks.

ABSTRACT. Accurate and detailed measurement of an individual's physical activity is a key requirement for helping researchers understand the relationship between physical activity and health. Accelerometers have become the method of choice for measuring physical activity due to their small size, low cost, convenience and their ability to provide objective information about physical activity. The challenge, however, is in interpreting accelerometer data once it has been collected. In this work, we applied data mining algorithms to the problem of classifying a time series as being one of several possible physical activity types. We employed a simple but effective approach of dividing the accelerometer data into short non-overlapping windows, converting each window into a feature vector, and treating each feature vector as an i.i.d training instance for a supervised learning algorithm. In addition, we improved on this simple approach with a multi-scale ensemble method (SWEM) that did not need to commit to a single window size and was able to leverage the fact that physical activities produced time series with repetitive patterns and discriminative features for physical activity occurred at different temporal scales.