A new class of multi-stable neural networks: stability analysis and learning process.

Recently, multi-stable Neural Networks (NN) with exponential number of attractors have been presented and analyzed theoretically; however, the learning process of the parameters of these systems while considering stability conditions and specifications of real world problems has not been studied. In this paper, a new class of multi-stable NNs using sinusoidal dynamics with exponential number of attractors is introduced. The sufficient conditions for multi-stability of the proposed system are posed using Lyapunov theorem. In comparison to the other methods in this class of multi-stable NNs, the proposed method is used as a classifier by applying a learning process with respect to the topological information of data and conditions of Lyapunov multi-stability. The proposed NN is applied on both synthetic and real world datasets with an accuracy comparable to classical classifiers.

Partial stabilization of uncertain nonlinear systems.

In this paper, the problem of robust partial stabilization is considered and two approaches for partial stabilization of uncertain nonlinear systems are presented. In these approaches, the nonlinear dynamical system is divided into two subsystems, which are called the first and the second subsystems. This division is done based on the required stability properties of the system's states. The reduced input vector (the vector that includes components of the input vector appearing in the first subsystem) is designed to asymptotically stabilize the first subsystem. In the first approach, a new partial stabilization technique, based on the first order sliding mode control idea is proposed. In the proposed method, hereafter called the partial sliding mode, a sliding surface is designed such that restricting the motion on this surface guarantees the stability of only the first part of the system's state. In the second approach, a Lyapunov-based controller is proposed for partial stabilization and then an additional feedback control is designed so that the overall feedback law guarantees a robust manner in the presence of uncertainties.

Using PCA and LVQ neural network for automatic recognition of five types of white blood cells.

Designing an effective classifier has been a challenging task in the previous methods proposed in the literature. In this paper, we apply a combination of feature selection algorithm and neural network classifier in order to recognize five types of white blood cells in the peripheral blood. For this purpose, first nucleus and cytoplasm are segmented using Gram-Schmidt method and snake algorithm, respectively; second, three kinds of features are extracted from the segmented areas. Then the best features are selected using Principal Component Analysis (PCA). Finally, five types of white blood cells are classified using Learning Vector Quantization (LVQ) neural network. The performance analysis of the proposed algorithm is validated by an expert's classification results. The efficiency of the proposed algorithm is highlighted by comparing our results with those reported in a recent article which proposed a method based on the combination of Sequential Forward Selection (SFS) as the feature selection algorithm and Support Vector Machines (SVM) as the classifier.

Stabilization of nonlinear systems with a slowly varying parameter by a control Lyapunov function.

Based on a control Lyapunov function (CLF) strategy, a novel approach for designing a controller for a slowly varying nonlinear system is proposed. The approach may be thought of as being in between the time-invariant and time-varying CLF techniques. If the time-invariant technique is used to control a slowly varying system, stability will not be guaranteed. On the other hand, the time-varying CLF technique, due to the control law, has complexity and needs to measure or estimate the derivative of system parameters. The advantage of the proposed method is its independence from the measurement or estimation of the derivatives of the system parameters. It is shown that the proposed control law can even be independent of the parameters of the system. In this paper, the conditions are derived that allow using the simple CLF formula that guarantees the stability of a slowly varying system. The efficiency of the approach is shown through some simulations.

Oral poliovirus vaccine in management of recurrent aphthous stomatitis.

Oral poliovirus vaccine (OPV) is reported to be effective in treatment of recurrent herpes simplex (RHS). According to our observation during recent years, OPV was not only effective in management of RHS but also in some patients with concomitant recurrent aphthous stomatitis (RAS) reducing its severity and frequency. The purpose of this study was to evaluate the efficacy of OPV in the management of RAS. In a longitudinal, case--control study 48 patients with RAS were recruited. Twenty patients received OPV and 28 patients received placebo. OPV was administered in a dose of 4 drops at monthly intervals for 3 months to the study group while the control group received placebo. The results were registered in 3 months after the last dose. Eight cases (40%) in the OPV group showed significant reduction in the duration of the ulcers, while no change was seen in the control group (P = 0.048). The frequency of recurrence of RAS was reduced in 13 cases (65%) in the OPV group, and in 6 cases (21.4%) of the placebo group (P = 0.006). The severity of attacks was reduced in 12 cases (60%) in the OPV group and in 4 cases (14.3%) in the placebo group (P = 0.008). In conclusion OPV appeared to be effective in the management of RAS.

Efficacy of 80% phenol solution in comparison with cryotherapy in the treatment of common warts of hands.

INTRODUCTION: The common wart is a common infectious disease caused by human papilloma virus. A variety of therapeutic modalities are available. Cryotherapy (liquid nitrogen) is one of the most common treatment forms. It freezes the tissue and destroys warts. Phenol is a caustic agent. Our purpose was to evaluate and compare the efficacy of cryotherapy and 80 percent phenol solution on common warts of hands. METHODS: This single-blinded clinical trial study was performed on 60 patients with common warts referred to the dermatology clinic of Ghaem Hospital Mashhad, Iran, in 2002. Patients were randomly divided into two groups; 30 patients were treated with cryotherapy and 30 patients were treated with 80 percent phenol, on a once-weekly basis until complete clearance of the lesions or a maximum duration of six weeks. RESULTS: Complete clearance of warts after six weeks was observed in 70 percent of patients who were treated with cryotherapy, and 82.6 percent of patients in the 80 percent phenol group; there was no statistically significant difference between the two methods (p-value is 0.014). CONCLUSION: Our data indicates that 80 percent phenol and cryotherapy are effective and simple treatments for common warts of hands, and patients do not experience any pain during the treatment.