Feature extraction is one of the fundamental challenges in improving the accuracy of document classification. While there has been a large body of research literature on document classification, most existing approaches either do not have a high classification accuracy or require massive training sets. In this paper, we propose a simple feature extraction algorithm that can achieve high document classification accuracy in the context of development-centric topics. Our feature extraction algorithm exploits two distinct aspects in development-centric topics: most of these topics tend to be very focused (unlike semantically hard classification topics such as chemistry or banks) due to local language and cultural underpinnings in these topics, the authentic pages tend to use several region specific features. Our algorithm uses a combination of popularity and rarity as two separate metrics to extract features that describe a topic. Given a topic, our output feature set comprises of: (i) a list of popular keywords closely related to the topic; (ii) a list of rare keywords closely related to the topic. We show that a simple joint classifier based on these two feature sets can achieve high classification accuracy while each feature sub-set in itself is insufficient. We have tested our algorithm across a wide range of development-centric topics.

This paper gives a short overview of time representations in current symbol grounding architectures. Furthermore we report on a recently developed embodied language acquisition system that acquires object words from a linguistically unconstrained human-robot dialogue. Conceptual issues in future development of the system towards the acquisition of action words will be discussed briefly.

Medical experts routinely need to identify the shapes of anatomical structures, and surgeons report that they depend substantially on touch to help them with this process. In this paper, we discuss possible reasons why touch may be especially important for anatomical shape recognition in surgery, and why in this domain haptic cues may be at least as informative about shape as visual cues. We go on to discuss modern surgical methods, in which these haptic cues are substantially diminished. We conclude that a potential future challenge is to find ways to reinstate these important cues and to help surgeons recognize shapes in the restricted sensory conditions of minimally invasive surgery.

This paper addresses the use of unmanned aircraft systems to provide embedded reasoning for atmospheric science. In particular, a specific form of heterogeneous unmanned aircraft system (UAS) is introduced. This UAS is comprised of two classes of aircraft with significantly different, though complementary, attributes: miniature daughterships that provide improved flexibility and spatio-temporal diversity of sensed data and larger motherships that carry and deploy the daughterships while facilitating coordination through increased mobility, computation, and communication. Current efforts designing unmanned aircraft for in situ sensing are described as well as future architectures for embedded reasoning by autonomous systems within complex atmospheric phenomena.

This paper presents a brief summary of a number of different approaches to the semantic representation and automated interpretation of engineering data. In this context, engineering data is represented as Computer-Aided Design (CAD) files, 3D models or assemblies. Representing and reasoning about these objects is a highly interdisciplinary problem, requiring techniques that can handle the complex interactions and data types that occur in the engineering domain. This paper presents several examples, taken from different problem areas that have occupied engineering and computer science researchers over the past 15 years. Many of the issues raised by these problems remain open, and the experience of past efforts can serve to identify fertile opportunities for investigation today.

As educators, we have high hopes for Electronic Tangibles (ETs), we expect ETs to: Interest more students in the study of computing Broaden students' views of computing Invite non-majors to learn something about the computing Attract students to computer science as a major Help students learn about particular ETs Attract students to our classes by incorporating a flashy ET in the course material Improve student understanding of some difficult topics Maintain student interest throughout the class However some important questions arise: Can we and should we extend these benefits throughout the K-20 curriculum? And if we can't, are we guilty of bait-and-switch?

There is a wealth of information on the Web about any number of topics. Many communities in developing regions are often interested in information relating to specific topics. For example, health workers are interested in specific medical information regarding epidemic diseases in their region while teachers and students are interested in educational information relating to their curriculum. This paper presents the design of Contextual Information Portals, searchable information portals that contain a vertical slice of the Web about arbitrary topics tailored to a specific context. Contextual portals are particularly useful for communities that lack Internet or Web access or in regions with very poor network connectivity. This paper outlines the design space for constructing contextual information portals and describes the key technical challenges involved. We have implemented a proof-of-concept of our ideas, and performed an initial evaluation on a variety of topics relating to epidemiology, agriculture, and education.

Road traffic accidents (RTAs) are a major public health concern, resulting in an estimated 1.2 million deaths and 50 million injuries worldwide each year. In the developing world, RTAs are among the leading cause of death and injury; Ethiopia in particular experiences the highest rate of such accidents. Thus, methods to reduce accident severity are of great interest to traffic agencies and the public at large. In this work, we applied data mining technologies to link recorded road characteristics to accident severity in Ethiopia, and developed a set of rules that could be used by the Ethiopian Traffic Agency to improve safety.

Many educators believe that activities centered on electronic tangibles (ET) and robots are fun and motivating for their students. However, it is often difficult, given the nature of both new hardware and new curricula to tease apart the nature and causes of this excitement. Formally planned educational evaluations can help build a deeper understanding of the effects of the new program on students. However, evaluating the impact of new ETs can be a challenge. Classes and workshops utilizing ETs as teaching devices are by their nature hands-on and may not lend themselves to traditional exam-based assessments. After all of the effort required to design a new ET, plan an educational experience utilizing the technology, and then implement that plan with students, evaluation is sometimes left as an afterthought. Strong evaluation methods can provide important insights into ways to improve a design and help to show the impact of a program, resulting in increased opportunities for funding, dissemination, and replication.

Although the various VA methods do Challenges for Global Health (Varmus et al. 2003) have not predict causes of deaths with vague symptoms as helped to reinforce the need for evidence-based global accurately as laboratory diagnostics can, verbal autopsy health priorities. Accurate health metrics and improved can predict causes of death with distinct symptoms with statistics can provide crucial decision-making inputs that some degree of accuracy (WHO 2007). For some areas of enable more efficient allocation of scarce financial the world verbal autopsies provide the only information resources towards the most pressing health needs (Murray about mortality currently available. Provided they can and Frenk 2008). Mortality statistics are a widely-used match or improve upon the accuracy of physician-coded resource for setting spending priorities, but out of 192 VA and expert algorithms, data-driven methods should be countries worldwide, only 23 have high-quality death used because they require less time from doctors or registration data, and 75 have no cause-specific mortality medical experts, and may provide valid reproducible fraction information at all (King and Lu 2008).