A three-stage learning algorithm for deep multilayer perceptron (DMLP) with effective weight initialisation based on sparse auto-encoder is proposed in this paper, which aims to overcome difficulties in training deep neural networks with limited training data in high-dimensional feature space. At the first stage, unsupervised learning is adopted using sparse auto-encoder to obtain the initial weights of the feature extraction layers of the DMLP. At the second stage, error back-propagation is used to train the DMLP by fixing the weights obtained at the first stage for its feature extraction layers. At the third stage, all the weights of the DMLP obtained at the second stage are refined by error back-propagation. Network structures an

Periodontitis is a multifactorial chronic inflammatory disease that affects tooth-supporting soft/hard tissues of the dentition. The dental plaque biofilm is considered as a primary etiological factor in susceptible patients; however, other factors contribute to progression, such as diabetes and smoking. Current management utilizes mechanical biofilm removal as the gold standard of treatment. Antibacterial agents might be indicated in certain conditions as an adjunct to this mechanical approach. However, in view of the growing concern about bacterial resistance, alternative approaches have been investigated. Currently, a range of antimicrobial agents and protocols have been used in clinical management, but these remain largely non-v

The inhibitive action of polyvinyl alcohol –sodium nitrite (PVASN) composite on the corrosion of mild steel in simulated cooling water (SCW) has been investigated by weight loss and potentiodynamic polarization. The effect of composite concentration (PVA/SN) , pH, and exposure time on corrosion rate of mild steel were verified using 2 levels factorial design and surface response analysis through weight loss approach, while the electrochemical measurements were used to study the behavior of mild steel in (SCW) with pH between 6 and 8 and in absence and presence of (PVA) in solution containing different concentration of NaNO2. It was verified that all three main variables studied were statistically significant while their interaction is

The tested isolate of Rhizobium leguminosarum bv. viciae was isolated from root nodules of vicia faba plant from Baghdad ,the isolated bacteria was examined for bioemulsifier production when growing in mineral salt medium that containing 1% sunflower oil as sole carbon source . Rhizobium isolate was able to produce bioemulsifier with initial emulsification index E24% was 38%. Many of physical and nutritional cultural conditions for optimum emulsifier production was examined including : pH , temperature ,incubation period ,carbon and nitrogen source. The maximum bioemulsifier production form Rhizobium isolate was 64.5% when bacteria growing in mineral salt medium with pH 9 ,incubated at temperature 30 ºC , incubation period was 10 days ,

This paper presents a cognition path planning with control algorithm design for a nonholonomic wheeled mobile robot based on Particle Swarm Optimization (PSO) algorithm. The aim of this work is to propose the circular roadmap (CRM) method to plan and generate optimal path with free navigation as well as to propose a nonlinear MIMO-PID-MENN controller in order to track the wheeled mobile robot on the reference path. The PSO is used to find an online tune the control parameters of the proposed controller to get the best torques actions for the wheeled mobile robot. The numerical simulation results based on the Matlab package show that the proposed structure has a precise and highly accurate distance of the generated refere

A total of 47 samples were collected from different clinical specimens (urine, wounds, burns, sputum, blood, stools) during the period from November 2013 to
January 2014, only 18 isolates (38.29%) were identified as Klebsiella pneumoniae ,11isolates (23.4%) as E. coli , 9 isolates (19.1%) as S. aureus, 3isolates (6.3%) as Psedomonase spp., 2 isolates (4.2 %) as K. terrigena and 4 isolates (8.5%) as K. oxytoca. The results were shown the elevation of K. pneumoniae percentage among the bacterial isolates depending on cultural, microscopically, biochemically characteristics and confirmed by using the API 20E and VITEK 2 system . Also K. pneumoniae isolates were more frequently in sputum samples then burns, stools , urine, wounds ,and blo

This paper presents a new design of a nonlinear multi-input multi-output PID neural controller of the active brake steering force and the active front steering angle for a 2-DOF vehicle model based on modified Elman recurrent neural. The goal of this work is to achieve the stability and to improve the vehicle dynamic’s performance through achieving the desired yaw rate and reducing the lateral velocity of the vehicle in a minimum time period for preventing the vehicle from slipping out the road curvature by using two active control actions: the front steering angle and the brake steering force. Bacterial forging optimization algorithm is used to adjust the parameters weights of the proposed controller. Simulation resul

Abstract. In this paper, a high order extended state observer (HOESO) based a sliding mode control (SMC) is proposed for a flexible joint robot (FJR) system in the presence of time varying external disturbance. A composite controller is integrated the merits of both HOESO and SMC to enhance the tracking performance of FJR system under the time varying and fast lumped disturbance. First, the HOESO estimator is constructed based on only one measured state to precisely estimate unknown system states and lumped disturbance with its high order derivatives in the FJR system. Second, the SMC scheme is designed based on such accurate estimations to govern the nominal FJR system by well compensating the estimation errors in the states and the lumped