An early warning system for hypoglycemic/hyperglycemic events based on fusion of adaptive prediction models

Early warning of future hypoglycemic and hyperglycemic events can improve the safety of type 1 diabetes mellitus (T1DM) patients. The aim of this study is to design and evaluate a hypoglycemia/hyperglycemia early warning system (EWS) for T1DM patients under sensor-augmented pump (SAP) therapy.

PROOF OF CONCEPT PROTOTYPE FOR A RAILROAD PEDESTRIAN WARNING SYSTEM USING WIRELESS SENSOR NETWORKS

Wireless sensor network is an emerging research topic due to its vast and ever-growing applications. Wireless sensor networks are made up of small nodes whose main goal is to monitor, compute and transmit data. The nodes are basically made up of low powered microcontrollers, wireless transceiver chips, sensors to monitor their environment and a power source. The applications of wireless sensor networks range from basic household applications, such as health monitoring, appliance control and security to military application, such as intruder detection. The wide spread application of wireless sensor networks has brought to light many research issues such as battery efficiency, unreliable routing protocols due to node failures, localization issues and security vulnerabilities. This report will describe the hardware development of a fault tolerant routing protocol for railroad pedestrian warning system. The protocol implemented is a peer to peer multi-hop TDMA based protocol for nodes arranged in a linear zigzag chain arrangement. The basic working of the protocol was derived from Wireless Architecture for Hard Real-Time Embedded Networks (WAHREN).

An Early-Warning System for Hypo-/Hyperglycemic Events Based on Fusion of Adaptive Prediction Models

Introduction: Early warning of future hypoglycemic and hyperglycemic events can improve the safety of type 1 diabetes mellitus (T1DM) patients. The aim of this study is to design and evaluate a hypoglycemia / hyperglycemia early warning system (EWS) for T1DM patients under sensor-augmented pump (SAP) therapy. Methods: The EWS is based on the combination of data-driven online adaptive prediction models and a warning algorithm. Three modeling approaches have been investigated: (i) autoregressive (ARX) models, (ii) auto-regressive with an output correction module (cARX) models, and (iii) recurrent neural network (RNN) models. The warning algorithm performs postprocessing of the models′ outputs and issues alerts if upcoming hypoglycemic/hyperglycemic events are detected. Fusion of the cARX and RNN models, due to their complementary prediction performances, resulted in the hybrid autoregressive with an output correction module/recurrent neural network (cARN)-based EWS. Results: The EWS was evaluated on 23 T1DM patients under SAP therapy. The ARX-based system achieved hypoglycemic (hyperglycemic) event prediction with median values of accuracy of 100.0% (100.0%), detection time of 10.0 (8.0) min, and daily false alarms of 0.7 (0.5). The respective values for the cARX-based system were 100.0% (100.0%), 17.5 (14.8) min, and 1.5 (1.3) and, for the RNN-based system, were 100.0% (92.0%), 8.4 (7.0) min, and 0.1 (0.2). The hybrid cARN-based EWS presented outperforming results with 100.0% (100.0%) prediction accuracy, detection 16.7 (14.7) min in advance, and 0.8 (0.8) daily false alarms. Conclusion: Combined use of cARX and RNN models for the development of an EWS outperformed the single use of each model, achieving accurate and prompt event prediction with few false alarms, thus providing increased safety and comfort.

Multi-Model Data Fusion to Improve an Early Warning System for Hypo-/Hyperglycemic Events

Correct predictions of future blood glucose levels in individuals with Type 1 Diabetes (T1D) can be used to provide early warning of upcoming hypo-/hyperglycemic events and thus to improve the patient's safety. To increase prediction accuracy and efficiency, various approaches have been proposed which combine multiple predictors to produce superior results compared to single predictors. Three methods for model fusion are presented and comparatively assessed. Data from 23 T1D subjects under sensor-augmented pump (SAP) therapy were used in two adaptive data-driven models (an autoregressive model with output correction - cARX, and a recurrent neural network - RNN). Data fusion techniques based on i) Dempster-Shafer Evidential Theory (DST), ii) Genetic Algorithms (GA), and iii) Genetic Programming (GP) were used to merge the complimentary performances of the prediction models. The fused output is used in a warning algorithm to issue alarms of upcoming hypo-/hyperglycemic events. The fusion schemes showed improved performance with lower root mean square errors, lower time lags, and higher correlation. In the warning algorithm, median daily false alarms (DFA) of 0.25%, and 100% correct alarms (CA) were obtained for both event types. The detection times (DT) before occurrence of events were 13.0 and 12.1 min respectively for hypo-/hyperglycemic events. Compared to the cARX and RNN models, and a linear fusion of the two, the proposed fusion schemes represents a significant improvement.

Weather Inputs to a Warning System for Sooty Blotch and Flyspeck of Apple

Sooty blotch and flyspeck (SBFS) is a mid- to late-season disease of apple. SBFS fungi show up as dark smudges and clusters of black dots on the fruit surface. Since blemished fruit are downgraded, crop losses can exceed 90 percent of the fresh market value.

Testing a Warning System for Anthracnose Fruit Rot on Day-neutral Strawberry

Anthracnose fruit rot (AFR) of strawberry is caused by three Colletotrichum spp. In the Midwest, however, only Colletotrichum acutatum is found. This fungus can attach itself to apparently healthy plants and spread throughout without causing symptoms on the foliage. When fruit begin to ripen and weather conditions are rainy and warm, AFR can suddenly cause great damage to the fruit. To protect against AFR where it has appeared in the past, growers need to spray every 7 to 10 days beginning at the start of bloom until harvest.

Sensory chemical pesticide warning system : experimental, summary and recommendations : final report covering the period June 1974-July 1975 /

Mode of access: Internet.

Provision of an airborne early warning system for Pakistan [microform] : hearings before the Subcommittee on Asian and Pacific Affairs of the Committee on Foreign Affairs, House of Representatives, One Hundredth Congress, first session, May 21 and June 11, 1987.

CIS Microfiche Accession Numbers: CIS 89 H381-7

Invehicle Safety Advisory and Warning System (IVSAWS).

"March 1996."

Feasibility of an automatic truck warning system. Final report.

Federal Highway Administration, Office of Safety and Traffic Operations Research and Development, McLean, Va.

Field evaluation of the Radar Control Systems (RCS) radar anti-collision warning system.

Partners for Advanced Transit and Highways, Berkeley, Calif.

Investigation of materials for use in a heat transfer system containing liquid lead alloys, report no. XII : final report April 1, 1950 to June 30, 1951 /

"U. S. Government Printing Office: 1955."--P. 34.

Flood warning system : does your community need one? /

Mode of access: Internet.

Hand receipt covering contents of components of end item (COEI), basic issue items (BII), and additional authorization list (ALL) for platoon early warning system AN/TRS-2(V)1 (NSN 5895-01-063-8103) ... AN/TRS-2(V)6 (NSN 5895-01-068-6749).

"20 July 1981."