Recurrent neural networks and robust time series prediction

We propose a robust learning algorithm and apply it to recurrent neural networks. This algorithm is based on filtering outliers from the data and then estimating parameters from the filtered data. The filtering removes outliers from both the target function and the inputs of the neural network. The filtering is soft in that some outliers are neither completely rejected nor accepted. To show the need for robust recurrent networks, we compare the predictive ability of least squares estimated recurrent networks on synthetic data and on the Puget Power Electric Demand time series. These investigations result in a class of recurrent neural networks, NARMA(p,q), which show advantages over feedforward neural networks for time series with a moving average component. Conventional least squares methods of fitting NARMA(p,q) neural network models are shown to suffer a lack of robustness towards outliers. This sensitivity to outliers is demonstrated on both the synthetic and real data sets. Filtering the Puget Power Electric Demand time series is shown to automatically remove the outliers due to holidays. Neural networks trained on filtered data are then shown to give better predictions than neural networks trained on unfiltered time series.     

Prevention and Mitigation Strategies to Address Recent Brittle Fractures in Steel Bridges

Brittle fracture results in unplanned loss of service, very costly repairs, concern regarding the future safety of the structure, and potential loss of life. These types of failures are most critical when there is no evidence of fatigue cracking leading up to the fracture and the fracture origin is concealed from view. Hence, the failure occurs without warning and the details are, essentially, noninspectable. In these cases, it appears desirable to take a proactive approach and introduce preventative retrofits to reduce the potential for future crack development. These efforts will help ensure that the likelihood of unexpected fractures is minimized. This paper examines the behavior of two bridge structures in which brittle fractures have developed in recent times, discusses the causes of the failures, and offers suggested design strategies for prevention and retrofit mitigation techniques. In situations where considerable uncertainty exists in the prediction of accumulated damage or in the ability to reliably inspect critical details, preemptive retrofit strategies appear to be highly desirable.     

The partial testing design: a less costly way to test equivalence for sensitivity and specificity

We propose a new, less costly, design to test the equivalence of digital versus analogue mammography in terms of sensitivity and specificity. Because breast cancer is a rare event among asymptomatic women, the sample size for testing equivalence of sensitivity is larger than that for testing equivalence of specificity. Hence calculations of sample size are based on sensitivity. With the proposed design it is possible to achieve the same power as a completely paired design by increasing the number of less costly analogue mammograms and not giving the more expensive digital mammograms to some randomly selected subjects who are negative on the analogue mammogram. The key idea is that subjects who are negative on the analogue mammogram are unlikely to have cancer and hence contribute less information for estimating sensitivity than subjects who are positive on the analogue mammogram. To ascertain disease state among subjects not biopsied, we propose another analogue mammogram at a later time determined by a natural history model. The design differs from a double sampling design because it compares two imperfect tests instead of combining information from a perfect and imperfect test.     

Human cholesterol synthesis measurement using deuterated water. Theoretical and procedural considerations

Creation of a dynamic levator aponeurosis fold or double eye adds to the beauty of the East Asian. The eyes are larger and less puffy, and the eyelashes appear longer and curve up and out instead of down. The distance from the ciliary border to the eyebrow is decreased and more in proportion. The Mongolian trait is preserved.     

Examining the effects of caching,compression and popup filtering on internet surfing

Over the years the number of Web users has increased dramatically unfortunately leading to the inherent problem of congestion. This can affect each user's surfing experience. This paper investigates download times associated with a web request, identifies where delays occur, and provides guidelines which can be followed by web developers to enable a faster and more efficient download and service for their users. We conclude that delays in Internet traffic and congestion can often be attributed to poorly developed sites (e.g. excessive image size). Copyright © 2005 John Wiley & Sons, Ltd.     

Knowledge-based interpretation of architectural drawings

A method for machine interpretation of architectural (or other) schematic drawings is presented. The central problem is to build an efficient drawing parser (i.e., a program that identifies the semantic entities, characteristics, and relationships that are represented in the drawing). The parser is built from specifications of the drawing grammar and an underlying spatial model. The grammar describes what to look for, and the spatial model enables the parser to find it quickly. Coupled with existing optical recognition technology, this technique enables the use of drawings directly as: (1) a database to drive various Architecture-Engineering-Construction (AEC) applications; (2) a communication protocol to integrate CAD systems; (3) a traditional user interface.     

Dieldrin in fish and shellfish from the Mersey Estuary and Liverpool Bay

OBJECT: The authors studied the reliability of a new method for noninvasive assessment of cerebral perfusion pressure (CPP) in head-injured patients in which mean arterial blood pressure (ABP) and transcranial Doppler middle cerebral artery mean and diastolic flow velocities are measured. METHODS: Cerebral perfusion pressure was estimated (eCPP) over periods of continuous monitoring (20 minutes-2 hours, 421 daily examinations) in 96 head-injured patients (Glasgow Coma Scale score < 13) who were admitted to the intensive care unit. All patients were sedated, paralyzed, and ventilated. The eCPP and the measured CPP (ABP minus intracranial pressure, measured using an intraparenchymal microsensor) were compared. The correlation between eCPP and measured CPP was r=0.73; p < 10(-6). In 71% of the examinations, the estimation error was less than 10 mm Hg and in 84% of the examinations, the error was less than 15 mm Hg. The method had a high positive predictive power (94%) for detecting low CPP (< 60 mm Hg). The eCPP also accurately reflected changes in measured CPP over time (r > 0.8; p < 0.001) in situations such as plateau and B waves of intracranial pressure, arterial hypotension, and refractory intracranial hypertension. A good correlation was found between the average measured CPP and eCPP when day-by-day variability was assessed in a group of 41 patients (r=0.71). CONCLUSIONS: Noninvasive estimation of CPP by using transcranial Doppler ultrasonography may be of value in situations in which monitoring relative changes in CPP is required without invasive measurement of intracranial pressure.     

Using Survey Data and Mathematical Modeling to Prioritize Water Interventions in Developing Countries

Water Resources Management - A traditional cost-benefit analysis of potential water interventions in a given locality is a laborious and time-intensive process. To help decision makers identify...