RESUMO
In wireless sensor networks (WSNs), the problem of measurement origin uncertainty for observed data has a significant impact on the precision of multi-target tracking. In this paper, a novel algorithm based on least squares support vector machine (LS-SVM) is proposed to classify measurement points for adjacent targets. Extended Kalman filter (EKF) algorithm is firstly adopted to compute the predicted classification line for each sampling period, which will be used to classify sampling points and calculate observed centers of closely moving targets. Then LS-SVM algorithm is utilized to train the classified points and get the best classification line, which will then be the reference classification line for the next sampling period. Finally, the locations of the targets will be precisely estimated by using observed centers based on EKF. A series of simulations validate the feasibility and accuracy of the new algorithm, while the experimental results verify the efficiency and effectiveness of the proposal.
RESUMO
OBJECTIVE: To investigate the role of replacement of third-generation cephalosporins by piperacillin-tazobactam (pip-tazo) in influencing the colonization of extended-spectrum beta-lactamases (ESBLs)-producing Escherichia coli (E. coli) in intestinal tract. METHODS: The study was divided into two phases lasting altogether 9 months, namely the pre-replacement phase (phase I, 3 months) and replacement phase (phase II, 6 months). In the latter phase, third-generation cephalosporins was restricted and replaced by pip-tazo. In phase I and phase IIb (the last 3 months of phase II), clinical data and rectal swab were taken for E. coli isolation as follow: within 24 hrs after admission (baseline screening), every week and 48 hrs before discharge. ESBLs production was detected with double disc test. Acquisition rate of ESBLs-producing E. coli were calculated both in ES1 group (patients' rectal swab collected and tests at least 2 times) and ES2 group (ES1 but with negative ESBLs either at the time of screening on admission or at anytime during the hospital stay). Continuous variable was compared using unpaired t-test and categorical variables was compared using Pearson Chi square test. Fisher's exact test was used in the two phases. RESULTS: In phase IIb, as compared with in phase I, the total consumption of antibiotics other than pip-tazo was reduced by 38.40%, the third-generation cephalosporins consumption was reduced by 70.11%, but pip-tazo consumption was raised by 895.35%. Meanwhile, the acquisition rate of ESBLs-producing E. coli in rectal swab was significantly decreased in phase IIb as compared with phase I (11.4% vs 24.0%) in ES1 group and the same is true in ES2 group (11.8% vs 27.9%). CONCLUSION: Replacement of third-generation cephalosporin with pip-tazo can reduce colonization of ESBLs--producing E. coli in intestinal tract.