Publications
This paper discusses the problem of abstract ing conditional probabilistic actions. We identify two distinct types of abstraction: intraaction abstraction and interaction ab straction. We define what it means for the abstraction of an action to be correct and then derive two methods of intraaction ab straction and two methods of interaction ab straction which are correct according to this criterion. We illustrate the developed tech niques by applying them to actions described with the temporal action representation used in the drips decisiontheoretic planner and we describe how the planner uses abstraction to reduce the complexity of planning.
An intelligent reactive planning agent for partially ob servable stochastic domains requires a number of di verse capabilities. First, the agent must be able to intelligently allocate its resources. This means that it must be able to decide how much time to allocate to deliberation in a way that is responsive to the environ ment in which the agent finds itself. It must also be able to decide when to sense and how much time and effort to spend sensing.
Finally, the agent must be capable of coordinate planning and acting. This means that it must be able to recognize when an action is completed and should be able to deliberate while acting. It also may need to translate between the highlevel action representa tion used by the planner and lowlevel commands to its effectors.
Since the question of metalevel control to determine optimal deliberation times has been well studied, in this paper we focus on the required planning capabil ities, as well as on the coordination of planning with execution.
| Aim To evaluate the effectiveness of haptic virtual reality (VR)simulator training using microcomputed tomography (micro-CT) tooth models on minimizing procedural errors in endodontic access preparation.
Methodology Fourth year dental students underwent a pre-training assessment of access cavity preparation on an extracted maxillary molar tooth mounted on a phantom head. Students were then randomized to training on either the micro-CT tooth models with a haptic VR simulator (n = 16) or extracted teeth in a phantom head (n = 16) training environments for 3 days, after which the assessment was repeated. The main outcome measure was procedural errors assessed by an expert blinded to trainee and training status. The secondary outcome measures were tooth mass loss and task completion time. The Wilcoxon test was used to examine the differences between pre-training and posttraining error scores, on the same group. The Mann–Whitney test was used to detect any differences between haptic VR training and phantom head training groups. The independent t-test was used to make a comparison on tooth mass removed and task completion time between the haptic VR training and phantom head training groups.
Results Post-training performance had improved compared with pre-training performance in error scores in both groups (P < 0.05). However, error score reduction between the haptic VR simulator and the conventional training group was not significantly different (P > 0.05). The VR simulator group decreased significantly (P < 0.05) the amount of hard tissue volume lost on the post-training exercise. Task completion time was not significantly different (P > 0.05) in both groups.
Conclusions Training on the haptic VR simulator and conventional phantom head had equivalent effects on minimizing procedural errors in endodontic access cavity preparation.
|
Sketching is ubiquitous in medicine. Physicians commonly use sketches as part of their note taking in patient records and to help convey diagnoses and treatments to patients. Medical students frequently use sketches to help them think through clinical problems in individual and group problem solving. Applications ranging from automated patient records to medical education software could benefit greatly from the richer and more natural interfaces that would be enabled by the ability to understand sketches. In this paper we take the first steps toward developing a system that can understand anatomical sketches. Understanding an anatomical sketch requires the ability to recognize what anatomical structure has been sketched and from what view (e.g. parietal view of the brain), as well as to identify the anatomical parts and their locations in the sketch (e.g. parts of the brain), even if they have not been explicitly drawn. We present novel algorithms for sketch recognition and for part identification. We evaluate the accuracy of the recognition algorithm on sketches obtained from medical students. We evaluate the part identification algorithm by comparing its results to the judgment of an experienced physician.
Download: haddawy-pub-48.pdf (489.7 KB)
|
Sketching is ubiquitous in medicine. Physicians commonly use sketches as part of their note taking in patient records and to help convey diagnoses and treatments to patients. Medical students frequently use sketches to help them think through clinical problems in individual and group problem solving. Applications ranging from automated patient records to medical education software could benefit greatly from the richer and more natural interfaces that would be enabled by the ability to understand sketches. In this paper we take the first steps toward developing a system that can understand anatomical sketches.
Methods: Understanding an anatomical sketch requires the ability to recognize what anatomical structure has been sketched and from what view (e.g. parietal view of the brain), as well as to identify the anatomical parts and their locations in the sketch (e.g. parts of the brain), even if they have not been explicitly drawn.We present novel algorithms for sketch recognition and for part identification. We evaluate the accuracy of the recognition algorithm on sketches obtained from medical students. We evaluate the part identification algorithm by comparing its results to the judgment of an experienced physician. |
We define a language for representing contextsensitive probabilistic knowledge. A knowledge base consists of a set of universally quantified probability sentences that include context constraints, which allow inference to be focused on only the relevant portions of the probabilistic knowledge. We provide a declarative semantics for our language. We present a query answering procedure which takes a query Q and a set of evidence E and constructs a Bayesian network to compute P (QjE). The posterior probability is then computed using any of a number of Bayesian network inference algorithms. We use the declarative semantics to prove the query procedure sound and complete. We use concepts from logic programming to justify our approach.
This paper proposes and investigates an approach to deduction in probabilistic logic, using as its medium a language that generalizes the propositional version of Nilsson's probabilistic logic by incorporating conditional probabilities. Unlike many other approaches to deduction in probabilistic logic, this approach is based on inference rules and therefore can produce proofs to explain how conclusions are drawn. We show how these rules can be incorporated into an anytime deduction procedure that proceeds by computing increasingly narrow probability intervals that contain the tightest entailed probability interval. Since the procedure can be stopped at any time to yield partial information concerning the probability range of any entailed sentence, one can make a tradeoff between precision and computation time. The deduction method presented here contrasts with other methods whose ability to perform logical reasoning is either limited or requires finding all truth assignments consistent with the given sentences.
|
This paper proposes and investigates an approach to deduction in probabilistic logic, using as its medium a language that generalizes the propositional version of Nilsson's probabilistic logic by incorporating conditional probabilities. Unlike many other approaches to deduction in probabilistic logic, this approach is based on inference rules and therefore can produce proofs to explain how conclusions are drawn. We show how these rules can be incorporated into an anytime deduction procedure that proceeds by computing increasingly narrow probability intervals that contain the tightest entailed probability interval. Since the procedure can be stopped at any time to yield partial information concerning the probability range of any entailed sentence, one can make a tradeoff between precision and computation time. The deduction method presented here contrasts with other methods whose ability to perform logical reasoning is either limited or requires finding all truth assignments consistent with the given sentences. |
We have developed a haptic virtual reality system for dental skill training. In this study we examined several kinds of kinematic information about the movement provided by the system supplement knowledge of results (KR) in dental skill acquisition. The kinematic variables examined involved force utilization (F) and mirror view (M). This created three experimental conditions that received augmented kinematic feedback (F, M, FM) and one control condition that did not (KR-only). Thirty-two dental students were randomly assigned to four groups. Their task was to perform access opening on the upper first molar with the haptic virtual reality system. An acquisition session consisted of two days of ten trials of practice in which augmented kinematic feedback was provided for the appropriate experimental conditions after each trial. One week after, a retention test consisting of two trials without augmented feedback was completed. The results showed that the augmented kinematic feedback groups had larger mean performance scores than the KR-only group in Day 1 of the acquisition and retention sessions (ANOVA, p<0.05). The apparent differences among feedback groups were not significant in Day 2 of the acquisition session (ANOVA, p>0.05). The trends in acquisition and retention sessions suggest that the augmented kinematic feedback can enhance the performance earlier in the skill acquisition and retention sessions.
We have developed a virtual reality (VR) and an augmented reality (AR) dental training simulator utilizing a haptic device. The simulators utilize volumetric force feedback computation and real time modification of the volumetric data. They include a virtual mirror to facilitate indirect vision during a simulated operation. The AR environment allows students to practice surgery in correct postures by combining the 3D tooth and tool models with the real-world view and displaying the result through a video see-through head-mounted display (HMD). Preliminary results from an initial evaluation show that the system is a promising tool to supplement dental training and that there are advantages of the AR over the VR approach.
In this paper, we describe the operation of barter trade exchanges by identifying key techniques used by trade brokers to stimulate trade and satisfy member needs, and present algorithms to automate some of these techniques. In particular, we develop algorithms that emulate the practice of trade brokers by matching buyers and sellers in such a way that the volume of goods traded is maximized while the balance of trade is maintained as much as possible. We show that the buyer/seller matching and trade balance problems can be decoupled, permitting efficient solution as well as numerous options for matching strategies. We model the trade balance problem as a minimum cost circulation problem (MCC) on a network. When the goods have uniform cost or when the goods can be traded in fractional units, we solve the problem exactly using a simplified version of the minimum mean cycle canceling algorithm. Otherwise, we present a novel stochastic rounding algorithm that takes the fractional optimal solution to the trade balance problem and produces a valid integer solution. We then make use of a greedy heuristic that attempts to match buyers and sellers so that the average number of sellers matched to a buyer of a good is minimized. Finally, we also present results on the empirical evaluation of our algorithms on test problems and simulations. The solutions from our stochastic rounding algorithm are always within 0.7% of the solution obtained from a commercial mixed integer programming package. We evaluate the effectiveness of our algorithm on maintaining balance and on stimulating trade using a simulator built using transaction history data from a trade exchange. The simulation results confirm the barter trade exchange rule of thumb that maximizing single-period trade volume while maintaining balance of trade helps to maximize trade volume over the long run.
Download: haddawy-pub-41.pdf (395.31 KB)n this paper, we describe the operation of barter trade exchanges by identifying key techniques used by trade brokers to stimulate trade and satisfy member needs, and present algorithms to automate some of these techniques. In particular, we develop algorithms that emulate the practice of trade brokers by matching buyers and sellers in such a way that trade volume is maximized while the balance of trade is maintained as much as possible. We show that the buyer/seller matching and trade balance problems can be decoupled, permitting efficient solution as well as numerous options for matching strategies.
We present results on the empirical evaluation of our algorithms on test problems and simulations. Experiments show that our algorithm (MCC + stochastic rounding) runs in a fraction of the time of a commercial mixed integer programming (MIP) package while producing solutions that are always within 0.7% of the MIP solution.
We evaluate the effectiveness of our algorithm on maintaining balance and on stimulating trade using two different simulation techniques, both based on transaction history data from a trade exchange. The simulation results support the barter trade exchange rule of thumb that maximizing single-period trade volume while maintaining balance of trade helps to maximize trade volume over the long run.
We present an educational tool for bringing the information contained in a Bayesian network to the end user in an easily intelligible form. The banter shell is designed to tutor users in evaluation of hypotheses and selection of optimal diagnostic procedures. banter can be used with any Bayesian network containing nodes that can be classified into hypotheses, observations, and diagnostic procedures. The system enables one to present various types of queries to the network, to test one's ablity to select optimal diagnostic procedures, and to request explanations. We describe the system's capabil ities by illustrating how it functions with two structurally different network models of realworld medical problems.
Today a great many medical schools have turned to a problem-based learning (PBL) approach to teaching. While PBL has many strengths, effective PBL requires the tutor to provide a high degree of personal attention to the students, which is difficult in the current academic environment of increasing demands on faculty time. This paper describes intelligent tutoring in a collaborative medical tutor for PBL. The main contribution of our work is the development of representational techniques and algorithms for generating tutoring hints in PBL group problem solving, as well as the implementation of these techniques in a collaborative intelligent tutoring system, COMET. The system combines concepts from computer-supported collaborative learning with those from intelligent tutoring systems.
Methods and materials: The system uses Bayesian networks to model individual student clinical reasoning, as well as that of the group. The prototype system incorporates substantial domain knowledge in the areas of head injury, stroke and heart attack. Tutoring in PBL is particularly challenging since the tutor should provide as little guidance as possible while at the same time not allowing the students to get lost. From studies of PBL sessions at a local medical school, we have identified and implemented eight commonly used hinting strategies. In order to evaluate the appropriateness and quality of the hints generated by our system, we compared the tutoring hints generated by COMET with those of experienced human tutors. We also compared the focus of group activity chosen by COMETwith that chosen by human tutors.
We present a firstorder logic of time, chance, and probability that is capable of expressing the four types of higherorder probability sentences relating subjective probability and objective chance at different times. We define a causal notion of objective chance and show how it can be used in conjunction with subjective probability to distinguish between causal and evidential correlation by distinguishing between conditions, events, and actions that 1) influence the agent's belief in chance and 2) the agent believes to influence chance. Furthermore, the semantics of the logic captures some commonsense inferences concerning objective chance and causality. We show that an agent's subjective probability is the expected value of its beliefs concerning objective chance. We also prove that an agent using this representation believes with certainty that the past cannot be causally influenced. To appear in IEEE SMC special issue on HigherOrder Probability.
Download: haddawy-pub-15.pdf (253.54 KB)We present a firstorder logic of time, chance, and probability that is capable of expressing the four types of higherorder probability sentences relating subjective probability and objective chance at different times. We define a causal notion of objective chance and show how it can be used in conjunction with subjective probability to distinguish between causal and evidential correlation by distinguishing between conditions, events, and actions that 1) influence the agent's belief in chance and 2) the agent believes to influence chance. Furthermore, the semantics of the logic captures some commonsense inferences concerning objective chance and causality. We show that an agent's subjective probability is the expected value of its beliefs concerning objective chance. We also prove that an agent using this representation believes with certainty that the past cannot be causally influenced. To appear in IEEE SMC special issue on HigherOrder Probability.
|
Previous bibliometric analyses of research activity in Sustainable Development have procured scientific articles by searching for the term “sustainability” or “sustainable” in the titles, abstracts and keywords (Yarime et al., 2010; Kajikawa et al., 2007). But such an approach cannot adequately retrieve articles in the field and cannot be used to conduct analyses of research activities in the sub-areas. Our present work seeks to build a rich hierarchy representing the field of Sustainable Development and its sub-areas. Since Sustainable Development is highly inter-disciplinary in nature and yet evolving, it has been a matter of debate as to what should be included in a definition of the field. There have been efforts to provide a research core and framework of Sustainable Development by identifying sub-areas of Sustainable Development through bibliometric analysis (Kajikawa, 2008). In particular, using topological clustering, Kajikawa et al. (2007) identified the following sub-areas of sustainability science: Agriculture, Fisheries, Ecological Economics, Forestry, Business, Tourism, Water, Urban Planning, Rural Sociology, Energy, Health, Soil, Wildlife and Climate Change. In this paper we use this taxonomy as our definition of Sustainable Development and its sub-areas.Given the recognized critical need for countries to develop more sustainable development paths and the rapid increase in resources now being invested in this area, it becomes important to clearly understand the current state of research activity in this area. For this quantitative bibliometric analyses are well suited, but conducting such analyses in highly interdisciplinary and emerging areas like this is highly challenging.In this paper we a present bibliometric study of research activity in Sustainable Development. Sustainable Development concerns nature (e.g., climate, ocean, rivers, plants, and other components of the natural environment), artifacts (e.g., machinery, biotechnology, materials, chemicals, and energy), and society (e.g., economy, industry, finance, demography, culture, ethics, and history) (Le´le´, 1991; Goodland, 1995). In recent years, Sustainable Development and its various sub-areas such as Renewable Energy and Climate Change have been declared as national priority areas by numerous countries and international organizations.
|
We present a language for representing context sensitive temporal probabilistic knowledge. Con text constraints allow inference to be focused on only the relevant portions of the probabilistic knowledge. We provide a declarative semantics for our language and an implemented algorithm (BNG) that generates Bayesian networks to com pute the posterior probabilities of queries. We il lustrate the use of the BNG system by applying it to the problem of modeling the effects of medica tions and other interventions on the condition of a patient in cardiac arrest.
This paper describes COMET, a collaborative intelligent tutoring system for medical problem-based learning. COMET uses Bayesian networks to model individual student knowledge and activity, as well as that of the group. Generic domain-independent tutoring algorithms use the models to generate tutoring hints. We present an overview of the system and then the results of two evaluation studies. The validity of the modeling approach is evaluated in the areas of head injury, stroke and heart attack. Receiver operating characteristic (ROC) curve analysis indicates that, the models are accurate in predicting individual student actions. Comparison of learning outcomes shows that student clinical reasoning gains from our system are significantly higher than those obtained from human tutored sessions (Mann-Whitney, p = 0.011).
Download: haddawy-pub-47.pdf (275.13 KB)
This paper describes COMET, a collaborative intelligent tutoring system for medical problem-based learning. The system uses Bayesian networks to model individual student knowledge and activity, as well as that of the group. It incorporates a multi-modal interface that integrates text and graphics so as to provide a rich communication channel between the students and the system, as well as among students in the group. Students can sketch directly on medical images, search for medical concepts, and sketch hypotheses on a shared workspace. The prototype system incorporates substantial domain knowledge in the area of head injury diagnosis. A major challenge in building COMET has been to develop algorithms for generating tutoring hints. Tutoring in PBL is particularly challenging since the tutor should provide as little guidance as possible while at the same time not allowing the students to get lost. From studies of PBL sessions at a local medical school, we have identified and implemented eight commonly used hinting strategies. We compared the tutoring hints generated by COMET with those of experienced human tutors. Our results show that COMET’s hints agree with the hints of the majority of the human tutors with a high degree of statistical agreement (McNemar test, p = 0.652, Kappa = 0.773).
Download: haddawy-pub-43.pdf (822.41 KB)