Factorial Hidden Markov Models

We present a framework for learning in hidden Markov models with distributed state representations. Within this framework, we derive a learning algorithm based on the Expectation--Maximization (EM) procedure for maximum likelihood estimation. Analogous to the standard Baum-Welch update rules, the M-step of our algorithm is exact and can be solved analytically. However, due to the combinatorial nature of the hidden state representation, the exact E-step is intractable. A simple and tractable mean field approximation is derived. Empirical results on a set of problems suggest that both the mean field approximation and Gibbs sampling are viable alternatives to the computationally expensive exact algorithm.

Estimating Dependency Structure as a Hidden Variable

This paper introduces a probability model, the mixture of trees that can account for sparse, dynamically changing dependence relationships. We present a family of efficient algorithms that use EMand the Minimum Spanning Tree algorithm to find the ML and MAP mixtureof trees for a variety of priors, including the Dirichlet and the MDL priors.

Estimating Dependency Structure as a Hidden Variable

This paper introduces a probability model, the mixture of trees that can account for sparse, dynamically changing dependence relationships. We present a family of efficient algorithms that use EM and the Minimum Spanning Tree algorithm to find the ML and MAP mixture of trees for a variety of priors, including the Dirichlet and the MDL priors. We also show that the single tree classifier acts like an implicit feature selector, thus making the classification performance insensitive to irrelevant attributes. Experimental results demonstrate the excellent performance of the new model both in density estimation and in classification.

Testing for Hidden Information and Action in Automobile Insurance Market

I test the presence of hidden information and action in the automobile insurance market using a data set from several Colombian insurers. To identify the presence of hidden information I find a common knowledge variable providing information on policyholder s risk type which is related to both experienced risk and insurance demand and that was excluded from the pricing mechanism. Such unused variable is the record of policyholder s traffic offenses. I find evidence of adverse selection in six of the nine insurance companies for which the test is performed. From the point of view of hidden action I develop a dynamic model of effort in accident prevention given an insurance contract with bonus experience rating scheme and I show that individual accident probability decreases with previous accidents. This result brings a testable implication for the empirical identification of hidden action and based on that result I estimate an econometric model of the time spans between the purchase of the insurance and the first claim, between the first claim and the second one, and so on. I find strong evidence on the existence of unobserved heterogeneity that deceives the testable implication. Once the unobserved heterogeneity is controlled, I find conclusive statistical grounds supporting the presence of moral hazard in the Colombian insurance market.

Adobe Photoshop : Adjustment and Fill Layers

Find out more about Photoshop Adjustment and Fill Layers with this share of video tutorials.

User Experience (a hidden barrier) in OER

More Open Education Resources (OER) and learning environments are being created and starting to mature and there are a number of barriers to learning and creator participation. One often overlooked barrier that has been given less attention, especially within OERs, is user experience (UX). UX is the way a person feels about using a product, system or service. We are creatures with emotional needs and, in the rush to get great content open and available sometimes the usability, the wow factor and good design principles get left by the wayside. I will demonstrate ways to think about UX for your OER and learning environments and why this is an important factor in helping engage learners with our educational materials. ‘The real payoff comes when we can make that remarkability last. When we can make people continually feel our work is worthy of discussion. When—for weeks, months, maybe even years— the people who engage with our work continue to sing its praises to everybody they meet’– (Jared Spool in Walter, A. Designing for Emotion). Walter, A. (2011) Designing for Emotion, A Book Apart. http://www.abookapart.com/products/designing-for-emotion

Identification of plasmodium vivax proteins with potential role in invasion using sequence redundancy reduction and profile hidden markov models

Background: This study describes a bioinformatics approach designed to identify Plasmodium vivax proteins potentially involved in reticulocyte invasion. Specifically, different protein training sets were built and tuned based on different biological parameters, such as experimental evidence of secretion and/or involvement in invasion-related processes. A profile-based sequence method supported by hidden Markov models (HMMs) was then used to build classifiers to search for biologically-related proteins. The transcriptional profile of the P. vivax intra-erythrocyte developmental cycle was then screened using these classifiers. Results: A bioinformatics methodology for identifying potentially secreted P. vivax proteins was designed using sequence redundancy reduction and probabilistic profiles. This methodology led to identifying a set of 45 proteins that are potentially secreted during the P. vivax intra-erythrocyte development cycle and could be involved in cell invasion. Thirteen of the 45 proteins have already been described as vaccine candidates; there is experimental evidence of protein expression for 7 of the 32 remaining ones, while no previous studies of expression, function or immunology have been carried out for the additional 25. Conclusions: The results support the idea that probabilistic techniques like profile HMMs improve similarity searches. Also, different adjustments such as sequence redundancy reduction using Pisces or Cd-Hit allowed data clustering based on rational reproducible measurements. This kind of approach for selecting proteins with specific functions is highly important for supporting large-scale analyses that could aid in the identification of genes encoding potential new target antigens for vaccine development and drug design. The present study has led to targeting 32 proteins for further testing regarding their ability to induce protective immune responses against P. vivax malaria.

Hidden gold.

Diseñado para proporcionar un fácil apoyo para los alumnos que necesitan para ganar la confianza y la motivación en su lectura. La historia trata de un grupo de amigos que viven y asisten a la escuela en una zona llamada Wolf Hill. Además de las divertidas aventuras, la historia también se ocupa de cuestiones sobre la amistad, la escuela y la vida en un moderno entorno urbano. Diseñada en capítulos, para que parezca novela popular para niños mayores, y así aumentar la confianza y el interés de aquellos que pueden gustarles la lectura de historias destinadas a los niños más pequeños. Loz y sus amigos encuentran algunas monedas antiguas en un escondite secreto y quieren saber si tienen valor.

Layers of generality and types of generalization in pattern activities. 'Niveles de generalidad y tipos de generalizaciones en actividades de patrones'.

Resumen basado en el de la publicación

Helping immigrants identify as 'university-bound students' : unexpected difficulties in teaching the hidden curriculum. 'Ayudar a los inmigrantes a identificarse como 'estudiantes con destino a la universidad' : dificultades inesperadas en la enseñanza del currículo oculto'.

Monográfico con el título: 'Identidad y educación'. Resumen basado en el de la publicación

Atomic diffusion induced by stress relaxation in InGaAs/GaAs epitaxial layers

The origin of the microscopic inhomogeneities in InxGa1-xAs layers grown on GaAs by molecular beam epitaxy is analyzed through the optical absorption spectra near the band gap. It is seen that, for relaxed thick layers of about 2.8μm, composition inhomogeneities are responsible for the band edge smoothing into the whole compositional range (0.05layers strain inhomogeneities are dominant. This evolution in line with layer thickness is due to the atomic diffusion at the surface during growth, induced by the strain inhomogeneities that arise from stress relaxation. In consequence, the strain variations present in the layer are converted into composition variations during growth. This process is energetically favorable as it diminishes elastic energy. An additional support to this hypothesis is given by a clear proportionality between the magnitude of the composition variations and the mean strain

The biometeorology of high-altitude insect layers.

Flight at high altitude is part of a migration strategy that maximises insect population displacement. This thesis represents the first substantial analysis of insect migration and layering in Europe. Vertical-looking entomological radar has revealed specific characteristics of high-altitude flight: in particular layering (where a large proportion of the migrating insects are concentrated in a narrow altitude band). The meteorological mechanisms underpinning the formation of these layers are the focus of this thesis. Aerial netting samples and radar data revealed four distinct periods of high-altitude insect migration: dawn, daytime, dusk, and night-time. The most frequently observed nocturnal profiles during the summertime were layers. It is hypothesised that nocturnal layers initiate at a critical altitude (200–500 m above ground level) and time (20:00–22:00 hours UTC). Case study analysis, statistical analysis, and a Lagrangian trajectory model showed that nocturnal insect layers probably result from the insects’ response to meteorological conditions. Temperature was the variable most correlated with nocturnal insect layer presence and intensity because insects are poikilothermic, and temperatures experienced during high-altitude migration in temperate climates are expected to be marginal for many insects’ flight. Hierarchical effects were detected such that other variables—specifically wind speed—were only correlated with insect layer presence and intensity once temperatures were warm. The trajectory model developed comprised: (i) insect flight characteristics; (ii) turbulent winds (which cause vertical spread of the layer); and (iii) mean wind speed, which normally leads to horizontal displacements of hundreds of kilometres in a single migratory flight. This thesis has revealed that there is considerable migratory activity over the UK in the summer months, and a range of fascinating phenomena can be observed (including layers). The UK has moved from one of the least studied to perhaps the best studied environments of aerial insect migration and layering in the world.

Layers of nocturnal insect migrants at high-altitude: the influence of atmospheric conditions on their formation

1 Radar studies of nocturnal insect migration have often found that the migrants tend to form well-defined horizontal layers at a particular altitude. 2 In previous short-term studies, nocturnal layers were usually observed to occur at the same altitude as certain meteorological features, most notably at the altitudes of temperature inversions or nocturnal wind jets. 3 Statistical analyses are presented of four years’ data that compared the presence, sharpness and duration of nocturnal layer profiles (observed using continuously-operating entomological radar) with meteorological variables at typical layer altitudes over the UK. 4 Analysis of these large datasets demonstrated that temperature was the foremost meteorological factor persistently associated with the presence and formation of longer-lasting and sharper layers of migrating insects over southern UK.