Illinois supplement to the national manual on uniform traffic control devices.

"Adopted March 1990."

Illinois supplement to the national manual on uniform traffic control devices /

"March 10, 2011."--cover letter.

Report on the use of nonconsensual eavesdropping devices during 1996 /

Provides the number of reported nonconsensual eavesdropping devices used during 1996, including reports forwarded to the director by participating state's attorneys, the number of law enforcement personnel involved in the seizure of intercepts, and the total cost to the department of all activities relating to the seizure of intercepts. Also provided are the number of department personnel authorized to possess, install or operate nonconsensual eavesdropping devices and the total number of law enforcement officers trained by the Illinois State Police, Technical Investigation Section, to participate in nonconsensual wiretaps.

Report to the Illinois General Assembly on the use of eavesdropping devices during ... /

Description based on: 1982.

The effect of nuclear radiation on semiconductor devices; report to Air Research and Development Command, Wright Air Development Division.

Includes bibliography.

Bibliography of relay literature, 1940-1943; interim report by working group on relay bibliography, Relay subcommittee, AIEE Committee on protective devices ...

"Advance copy, not released for publication."

National practices for the operation and protection of school zones and crossings; an informational report by Committee on Traffic, Subcommittee on Traffic Control Devices in cooperation with Colorado Department of Highways.

Cover title.

Regulation of trade in drugs: hearings, Ninety-first Congress, second session, on S. 1575, to regulate trade in drugs and devices by prohibiting the dispensing of drugs or devices by medical practitioners and their participation in profits from the dispensing of such products, except under certain circumstances, and for other purposes, June 16 and 17, 1970.

"Serial no. 91-81."

Motion devices for linear and angular oscillation and for abrupt acceleration studies on human subjects (impact), a description of facilities in use and proposed;

Includes bibliographies.

Magnifying devices : a resource guide /

"February 2002."

An Incremental EM-based Learning Approach for On-Line Prediction of Hospital Resource Utilization

Objective: Inpatient length of stay (LOS) is an important measure of hospital activity, health care resource consumption, and patient acuity. This research work aims at developing an incremental expectation maximization (EM) based learning approach on mixture of experts (ME) system for on-line prediction of LOS. The use of a batchmode learning process in most existing artificial neural networks to predict LOS is unrealistic, as the data become available over time and their pattern change dynamically. In contrast, an on-line process is capable of providing an output whenever a new datum becomes available. This on-the-spot information is therefore more useful and practical for making decisions, especially when one deals with a tremendous amount of data. Methods and material: The proposed approach is illustrated using a real example of gastroenteritis LOS data. The data set was extracted from a retrospective cohort study on all infants born in 1995-1997 and their subsequent admissions for gastroenteritis. The total number of admissions in this data set was n = 692. Linked hospitalization records of the cohort were retrieved retrospectively to derive the outcome measure, patient demographics, and associated co-morbidities information. A comparative study of the incremental learning and the batch-mode learning algorithms is considered. The performances of the learning algorithms are compared based on the mean absolute difference (MAD) between the predictions and the actual LOS, and the proportion of predictions with MAD < 1 day (Prop(MAD < 1)). The significance of the comparison is assessed through a regression analysis. Results: The incremental learning algorithm provides better on-line prediction of LOS when the system has gained sufficient training from more examples (MAD = 1.77 days and Prop(MAD < 1) = 54.3%), compared to that using the batch-mode learning. The regression analysis indicates a significant decrease of MAD (p-value = 0.063) and a significant (p-value = 0.044) increase of Prop(MAD