Roni Rosenfeld

Generating remote control interfaces for complex appliances

The personal universal controller (PUC) is an approach for improving the interfaces to complex appliances by introducing an intermediary graphical or speech interface. A PUC engages in two-way communication with everyday appliances, first downloading a specification of the appliances functions, and then automatically creating an interface for controlling that appliance. The specification of each appliance includes a high-level description of every function, a hierarchical grouping of those functions, and dependency information, which relates the availability of each function to the appliances state. Dependency information makes it easier for designers to create specifications and helps the automatic interface generators produce a higher quality result. We describe the architecture that supports the PUC, and the interface generators that use our specification language to build high-quality graphical and speech interfaces.

HealthLine: Speech-based access to health information by low-literate users

Health information access by low-literate community health workers is a pressing need of community health programs across the developing world. We present results from a needs assessment we conducted to understand the health information access practices and needs of various types of health workers in Pakistan. We also present a prototype for speech-based health information access, as well as discuss our experiences from a pilot study involving its use by community health workers in a rural health center.

Speech vs. touch-tone: Telephony interfaces for information access by low literate users

Information access by low literate users is a difficult task. Critical information, such as in the field of healthcare, can often mean the difference between life and death. We have developed spoken language interface prototypes aimed at low literate users, and tested them with community health workers in Pakistan. We present results showing that 1) in contrast to previous reports in the literature, well-designed speech interfaces significantly outperform touch-tone equivalents for both low-literate and literate users, and that 2) literacy significantly impacts task success for both modalities.

FRED (A Framework for Reconstructing Epidemic Dynamics): an open-source software system for modeling infectious diseases and control strategies using census-based populations

BackgroundMathematical and computational models provide valuable tools that help public health planners to evaluate competing health interventions, especially for novel circumstances that cannot be examined through observational or controlled studies, such as pandemic influenza. The spread of diseases like influenza depends on the mixing patterns within the population, and these mixing patterns depend in part on local factors including the spatial distribution and age structure of the population, the distribution of size and composition of households, employment status and commuting patterns of adults, and the size and age structure of schools. Finally, public health planners must take into account the health behavior patterns of the population, patterns that often vary according to socioeconomic factors such as race, household income, and education levels.ResultsFRED (a Framework for Reconstructing Epidemic Dynamics) is a freely available open-source agent-based modeling system based closely on models used in previously published studies of pandemic influenza. This version of FRED uses open-access census-based synthetic populations that capture the demographic and geographic heterogeneities of the population, including realistic household, school, and workplace social networks. FRED epidemic models are currently available for every state and county in the United States, and for selected international locations.ConclusionsState and county public health planners can use FRED to explore the effects of possible influenza epidemics in specific geographic regions of interest and to help evaluate the effect of interventions such as vaccination programs and school closure policies. FRED is available under a free open source license in order to contribute to the development of better modeling tools and to encourage open discussion of modeling tools being used to evaluate public health policies. We also welcome participation by other researchers in the further development of FRED.

Quantifying influenza virus diversity and transmission in humans.

Influenza A virus is characterized by high genetic diversity. However, most of what is known about influenza evolution has come from consensus sequences sampled at the epidemiological scale that only represent the dominant virus lineage within each infected host. Less is known about the extent of within-host virus diversity and what proportion of this diversity is transmitted between individuals. To characterize virus variants that achieve sustainable transmission in new hosts, we examined within-host virus genetic diversity in household donor-recipient pairs from the first wave of the 2009 H1N1 pandemic when seasonal H3N2 was co-circulating. Although the same variants were found in multiple members of the community, the relative frequencies of variants fluctuated, with patterns of genetic variation more similar within than between households. We estimated the effective population size of influenza A virus across donor-recipient pairs to be approximately 100–200 contributing members, which enabled the transmission of multiple lineages, including antigenic variants.

A probabilistic generative model for GO enrichment analysis

The Gene Ontology (GO) is extensively used to analyze all types of high-throughput experiments. However, researchers still face several challenges when using GO and other functional annotation databases. One problem is the large number of multiple hypotheses that are being tested for each study. In addition, categories often overlap with both direct parents/descendents and other distant categories in the hierarchical structure. This makes it hard to determine if the identified significant categories represent different functional outcomes or rather a redundant view of the same biological processes. To overcome these problems we developed a generative probabilistic model which identifies a (small) subset of categories that, together, explain the selected gene set. Our model accommodates noise and errors in the selected gene set and GO. Using controlled GO data our method correctly recovered most of the selected categories, leading to dramatic improvements over current methods for GO analysis. When used with microarray expression data and ChIP-chip data from yeast and human our method was able to correctly identify both general and specific enriched categories which were overlooked by other methods.

Combined analysis reveals a core set of cycling genes

BackgroundGlobal transcript levels throughout the cell cycle have been characterized using microarrays in several species. Early analysis of these experiments focused on individual species. More recently, a number of studies have concluded that a surprisingly small number of genes conserved in two or more species are periodically transcribed in these species. Combining and comparing data from multiple species is challenging because of noise in expression data, the different synchronization and scoring methods used, and the need to determine an accurate set of homologs.ResultsTo solve these problems, we developed and applied a new algorithm to analyze expression data from multiple species simultaneously. Unlike previous studies, we find that more than 20% of cycling genes in budding yeast have cycling homologs in fission yeast and 5% to 7% of cycling genes in each of four species have cycling homologs in all other species. These conserved cycling genes display much stronger cell cycle characteristics in several complementary high throughput datasets.Essentiality analysis for yeast and human genes confirms these findings. Motif analysis indicates conservation in the corresponding regulatory mechanisms. Gene Ontology analysis and analysis of the genes in the conserved sets sheds light on the evolution of specific subfunctions within the cell cycle.ConclusionOur results indicate that the conservation in cyclic expression patterns is much greater than was previously thought. These genes are highly enriched for most cell cycle categories, and a large percentage of them are essential, supporting our claim that cross-species analysis can identify the core set of cycling genes.

Requirements for automatically generating multi-modal interfaces for complex appliances

Several industrial and academic research groups are working to simplify the control of appliances and services by creating a truly universal remote control. Unlike the preprogrammed remote controls available today, these new controllers download a specification from the appliance or service and use it to automatically generate a remote control interface. This promises to be a useful approach because the specification can be made detailed enough to generate both speech and graphical interfaces. Unfortunately, generating good user interfaces can be difficult. Based on user studies and prototype implementations, this paper presents a set of requirements that we have found are needed for automatic interface generation systems to create high-quality user interfaces.

Improving speech recognition performance via phone-dependent VQ codebooks and adaptive language models in SPHINX-II

This paper presents improvements in acoustic and language modeling for automatic speech recognition. Specifically, semi-continuous HMMs (SCHMMs) with phone-dependent VQ codebooks are presented and incorporated into the SPHINX-II speech recognition system. The phone-dependent VQ codebooks relax the density-tying constraint in SCHMMs in order to obtain more detailed models. A 6% error rate reduction was achieved on the speaker-independent 20000-word Wall Street Journal (WSJ) task. Dynamic adaptation of the language model in the context of long documents is also explored. A maximum entropy framework is used to exploit long distance trigrams and trigger effects. A 10%-15% word error rate reduction is reported on the same WSJ task using the adaptive language modeling technique.<<ETX>>

Flexible Modeling of Epidemics with an Empirical Bayes Framework.

Seasonal influenza epidemics cause consistent, considerable, widespread loss annually in terms of economic burden, morbidity, and mortality. With access to accurate and reliable forecasts of a current or upcoming influenza epidemic’s behavior, policy makers can design and implement more effective countermeasures. This past year, the Centers for Disease Control and Prevention hosted the “Predict the Influenza Season Challenge”, with the task of predicting key epidemiological measures for the 2013–2014 U.S. influenza season with the help of digital surveillance data. We developed a framework for in-season forecasts of epidemics using a semiparametric Empirical Bayes framework, and applied it to predict the weekly percentage of outpatient doctors visits for influenza-like illness, and the season onset, duration, peak time, and peak height, with and without using Google Flu Trends data. Previous work on epidemic modeling has focused on developing mechanistic models of disease behavior and applying time series tools to explain historical data. However, tailoring these models to certain types of surveillance data can be challenging, and overly complex models with many parameters can compromise forecasting ability. Our approach instead produces possibilities for the epidemic curve of the season of interest using modified versions of data from previous seasons, allowing for reasonable variations in the timing, pace, and intensity of the seasonal epidemics, as well as noise in observations. Since the framework does not make strict domain-specific assumptions, it can easily be applied to some other diseases with seasonal epidemics. This method produces a complete posterior distribution over epidemic curves, rather than, for example, solely point predictions of forecasting targets. We report prospective influenza-like-illness forecasts made for the 2013–2014 U.S. influenza season, and compare the framework’s cross-validated prediction error on historical data to that of a variety of simpler baseline predictors.