Adaptive Control of Nonlinear MIMO System With Orthogonal Endocrine Intelligent Controller.

In this article, a new intelligent hybrid controller is proposed. The controller is based on the combination of the orthogonal endocrine neural network (OENN) and orthogonal endocrine ANFIS (OEANFIS). The orthogonal part of the controller consists of Chebyshev orthogonal functions, which are used because of their recursive property, computational simplicity, and accuracy in nonlinear approximations. Artificial endocrine influence on the controller is achieved by introducing excitatory and inhibitory glands to the OENN part of the structure, in the form of postsynaptic potentials. These potentials provide a network with the capability of additional self-regulation in the presence of external disturbances. The intelligent structure is trained using a developed learning algorithm, which consists of both offline and online learning procedures: online learning for fitting OENN substructure and offline learning for adjusting OEANFIS parameters. The learning process is expanded by introducing the learning rate adaptation algorithm, which bases its calculations on the sign of the error difference. Finally, the proposed intelligent controller was experimentally tested for control of a nonlinear multiple-input-multiple-output two rotor aerodynamical system. During the test phase, an additional four related intelligent control logics and default PID-based controllers were used, and tracking performance comparisons were performed. The proposed controller showed notably better online results in comparison to other control algorithms. The major deficiencies of the structure are complexity and noticeably large training computation time, but these drawbacks can be neglected if tracking performances of a dynamical system are of the highest importance.

Phenotypic and genetic properties of susceptible and multidrug-resistant Pseudomonas aeruginosa isolates in Southern Serbia.

Drug resistance of Pseudomonas aeruginosa is a leading problem in hospital infections. The aim of this study was to determine the best molecular genetic discrimination method for Pseudomonas spp. isolates among 94 outpatients and inpatients and see their grouping by phenotype characteristics (biofilm formation, frequency of serotypes, pigmentation, production of different class of beta-lactamases, and susceptibility to different antibiotic classes) and genotype. The most common serotypes were P1, P6, and P11, while co-productions of pyoverdine and pyocyanin were observed in 70 % of isolates. A total of 77.66 % isolates were mostly weak and moderate biofilm producers. Isolates were susceptible to colistin (100 %), aztreonam (97.87 %), imipenem (91.49 %), doripenem (90.43 %), and meropenem (84.04 %). MICs values confirmed susceptibility to ceftazidime and cefepime and singled out meripenem as the most effective inhibitor. Most isolates were resistant to aminoglycosides and fluoroquinolones. Only two isolates produced ESBL, eight were carbapenemase producers, and five isolates produced MBLs. Twenty-nine isolates were multidrug-resistant; 82.8 % of which produced both pigments, 58.3 % were non-typeable, while the P6 and P11 serotypes were equally distributed (16.7 %). Thirteen MDR isolates were strong enzyme producers. RAPD PCR analysis using primer 272 proved the best at discriminatory fingerprinting for Pseudomonas isolates, as it allocated 12 clusters. A correlation between DNA patterns and antibiotic resistance, production of pigments, serotypes distribution, and biofilm formation was not observed, and only confirmed higher genetic heterogeneity among P. aeruginosa isolates, which suggests that other molecular methods are needed to reveal potential relations between genotypic patterns and phenotypic characteristics.

Adaptive PID control based on orthogonal endocrine neural networks.

A new intelligent hybrid structure used for online tuning of a PID controller is proposed in this paper. The structure is based on two adaptive neural networks, both with built-in Chebyshev orthogonal polynomials. First substructure network is a regular orthogonal neural network with implemented artificial endocrine factor (OENN), in the form of environmental stimuli, to its weights. It is used for approximation of control signals and for processing system deviation/disturbance signals which are introduced in the form of environmental stimuli. The output values of OENN are used to calculate artificial environmental stimuli (AES), which represent required adaptation measure of a second network-orthogonal endocrine adaptive neuro-fuzzy inference system (OEANFIS). OEANFIS is used to process control, output and error signals of a system and to generate adjustable values of proportional, derivative, and integral parameters, used for online tuning of a PID controller. The developed structure is experimentally tested on a laboratory model of the 3D crane system in terms of analysing tracking performances and deviation signals (error signals) of a payload. OENN-OEANFIS performances are compared with traditional PID and 6 intelligent PID type controllers. Tracking performance comparisons (in transient and steady-state period) showed that the proposed adaptive controller possesses performances within the range of other tested controllers. The main contribution of OENN-OEANFIS structure is significant minimization of deviation signals (17%-79%) compared to other controllers. It is recommended to exploit it when dealing with a highly nonlinear system which operates in the presence of undesirable disturbances.

Pseudomonas aeruginosa serotypes and resistance to antibiotics from wound swabs.

INTRODUCTION/AIM: Pseudomonas aeruginosa (P. aeruginosa) is the most common cause of wound infections, following the disruption of the skin or mucous membranes integrity. The aim of this study was to analyze of the presence P. aeruginosa in wound swabs, antibiotics susceptibility testing, determination of the minimum inhibitory concentrations (MICs) of antibiotics, testing of the metallo-ß-lactamases (MBLs) production, isolates serotyping and analysis of the most common serotypes resistance. METHODS: A total of 90 outpatients and 55 intpatients wound swabs were cultivated. Wound swabs were taken from the patients with wound infections symptoms. Antibiotics susceptibility testing was performed to: meropenem, imipenem, piperacillin-tazobactam, ceftazidime, cefepime, amikacin, gentamicin, netilmicin, of loxacin, ciprofloxacin and colistin (HiMedia). Polyvalent and monovalent antisera for agglutination (Biorad) were used in P. aeruginosa agglutination. RESULTS: P. aeruginosa was isolated from 36.55% wound swabs (36.66% of the inpatients wounds and 36.36% of the outpatients). The analyzed isolates showed the highest degree of sensitivity to colistin (100%) and meropenem (93.44%) and the lowest to cefepime (19.54%). The majority of the inpatients isolates had 12 µg/mL (28.57%) MIC for piperacillin-tazobactam and 16 µg/ml (28.57%) for the outpatients. The most common MICs for ciprofloxacin were 0.19 µg/mL (31.81%) for the nosocomial isolates, and 0.25 µg/mL (28.57%) for the outpatients' ones. The most common ICs for amikacin of the nosocomial isolates were 6 µg/ml (40.90%), and for the outpatients ones 4 µg/mL (33.33%). Five (9.43%) isolates produced MBLs. The most common serotypes were P11 (22.64%), P6 (15.09%) and P1 (11.32%). CONCLUSION: Neither the increased presence of P. aeruginosa was noticed in wounds swabs, nor the antibiotic resistance in the nosocomial isolates compared to those from outpatients. The analyzed isolates had the higest sensitivity to colistin and meropenem, and the lowest to cefepime.