4 resultados para Hierarchical regression model
em DigitalCommons@University of Nebraska - Lincoln
Resumo:
Analyses of ecological data should account for the uncertainty in the process(es) that generated the data. However, accounting for these uncertainties is a difficult task, since ecology is known for its complexity. Measurement and/or process errors are often the only sources of uncertainty modeled when addressing complex ecological problems, yet analyses should also account for uncertainty in sampling design, in model specification, in parameters governing the specified model, and in initial and boundary conditions. Only then can we be confident in the scientific inferences and forecasts made from an analysis. Probability and statistics provide a framework that accounts for multiple sources of uncertainty. Given the complexities of ecological studies, the hierarchical statistical model is an invaluable tool. This approach is not new in ecology, and there are many examples (both Bayesian and non-Bayesian) in the literature illustrating the benefits of this approach. In this article, we provide a baseline for concepts, notation, and methods, from which discussion on hierarchical statistical modeling in ecology can proceed. We have also planted some seeds for discussion and tried to show where the practical difficulties lie. Our thesis is that hierarchical statistical modeling is a powerful way of approaching ecological analysis in the presence of inevitable but quantifiable uncertainties, even if practical issues sometimes require pragmatic compromises.
Resumo:
Translucent WDM optical networks use sparse placement of regenerators to overcome the impairments and wavelength contention introduced by fully transparent networks, and achieve a performance close to fully opaque networks with much less cost. Our previous study proved the feasibility of translucent networks using sparse regeneration technique. We addressed the placement of regenerators based on static schemes allowing only fixed number of regenerators at fixed locations. This paper furthers the study by proposing a suite of dynamical routing schemes. Dynamic allocation, advertisement and discovery of regeneration resources are proposed to support sharing transmitters and receivers between regeneration and access functions. This study follows the current trend in optical networking industry by utilizing extension of IP control protocols. Dynamic routing algorithms, aware of current regeneration resources and link states, are designed to smartly route the connection requests under quality constraints. A hierarchical network model, supported by the MPLS-based control plane, is also proposed to provide scalability. Experiments show that network performance is improved without placement of extra regenerators.
Resumo:
The abundance of harbor seals (Phoca vitulina richardii) has declined in recent decades at several Alaska locations. The causes of these declines are unknown, but there is concern about the status of the populations, especially in the Gulf of Alaska. To assess the status of harbor seals in the Gulf of Alaska, we conducted aerial surveys of seals on their haul-out sites in August-September 1996. Many factors influence the propensity of seals to haul out, including tides, weather, time of day, and time of year. Because these “covariates” cannot simultaneously be controlled through survey design, we used a regression model to adjust the counts to an estimate of the number of seals that would have been ashore during a hypothetical survey conducted under ideal conditions for hauling out. The regression, a generalized additive model, not only provided an adjustment for the covariates, but also confirmed the nature and shape of the covariate effects on haul-out behavior. The number of seals hauled out was greatest at the beginning of the surveys (mid-August). There was a broad daily peak from about 1100-1400 local solar time. The greatest numbers were hauled out at low tide on terrestrial sites. Tidal state made little difference in the numbers hauled out on glacial ice, where the area available to seals did not fluctuate with the tide. Adjusting the survey counts to the ideal state for each covariate produced an estimate of 30,035 seals, about 1.8 times the total of the unadjusted counts (16,355 seals). To the adjusted count, we applied a correction factor of 1.198 from a separate study of two haul-out sites elsewhere in Alaska, to produce a total abundance estimate of 35,981 (SE 1,833). This estimate accounts both for the effect of covariates on survey counts and for the proportion of seals that remained in the water even under ideal conditions for hauling out.
Resumo:
INVESTIGATION INTO CURRENT EFFICIENCY FOR PULSE ELECTROCHEMICAL MACHINING OF NICKEL ALLOY Yu Zhang, M.S. University of Nebraska, 2010 Adviser: Kamlakar P. Rajurkar Electrochemical machining (ECM) is a nontraditional manufacturing process that can machine difficult-to-cut materials. In ECM, material is removed by controlled electrochemical dissolution of an anodic workpiece in an electrochemical cell. ECM has extensive applications in automotive, petroleum, aerospace, textile, medical, and electronics industries. Improving current efficiency is a challenging task for any electro-physical or electrochemical machining processes. The current efficiency is defined as the ratio of the observed amount of metal dissolved to the theoretical amount predicted from Faraday’s law, for the same specified conditions of electrochemical equivalent, current, etc [1]. In macro ECM, electrolyte conductivity greatly influences the current efficiency of the process. Since there is a certain limit to enhance the conductivity of the electrolyte, a process innovation is needed for further improvement in current efficiency in ECM. Pulse electrochemical machining (PECM) is one such approach in which the electrolyte conductivity is improved by electrolyte flushing in pulse off-time. The aim of this research is to study the influence of major factors on current efficiency in a pulse electrochemical machining process in macro scale and to develop a linear regression model for predicting current efficiency of the process. An in-house designed electrochemical cell was used for machining nickel alloy (ASTM B435) by PECM. The effects of current density, type of electrolyte, and electrolyte flow rate, on current efficiency under different experimental conditions were studied. Results indicated that current efficiency is dependent on electrolyte, electrolyte flow rate, and current density. Linear regression models of current efficiency were compared with twenty new data points graphically and quantitatively. Models developed were close enough to the actual results to be reliable. In addition, an attempt has been made in this work to consider those factors in PECM that have not been investigated in earlier works. This was done by simulating the process by using COMSOL software. However, it was found that the results from this attempt were not substantially different from the earlier reported studies.