Search

This paper proposes a new hybrid method for training high-order Takagi–Sugeno fuzzy systems using sparse regressions and metaheuristic optimization. The fuzzy system is considered with Gaussian fuzzy sets in the antecedents and high-order polynomials in the consequents of fuzzy rules. The fuzzy sets can be chosen manually or determined by a metaheuristic optimization method (particle swarm optimization, genetic algorithm or simulated annealing), while the polynomials are obtained using ordinary least squares, ridge regression or sparse regressions (forward selection, least angle regression, least absolute shrinkage and selection operator, and elastic net regression). A quality criterion is proposed that expresses a compromise between the prediction ability of the fuzzy model and its sparsity. The conducted experiments showed that: (a) the use of sparse regressions and/or metaheuristic optimization can reduce the validation error compared with the reference method, and (b) the use of sparse regressions may simplify the fuzzy model by zeroing some of the coefficients.

This paper proposes a method for training Takagi–Sugeno fuzzy systems using sparse regressions and particle swarm optimization. The fuzzy system is considered with Gaussian fuzzy sets in the antecedents and high-order polynomials in the consequents of the inference rules. The proposed method can be applied in two variants: without or with particle swarm optimization. In the first variant, ordinary least squares, ridge regression, or sparse regressions (forward selection, least angle regression, least absolute shrinkage and selection operator, and elastic net regression) determine the polynomials in the fuzzy system in which the fuzzy sets are known. In the second variant, we have a hybrid method in which particle swarm optimization determines the fuzzy sets, while ordinary least squares, ridge regression, or sparse regressions determine the polynomials. The first variant is simpler to implement but less accurate, the second variant is more complex, but gives better results. A new quality criterion is proposed in which the goal is to make the validation error and the model density as small as possible. Experiments showed that: (a) the use of sparse regression and/or particle swarm optimization can reduce the validation error and (b) the use of sparse regression may simplify the model by zeroing some of the coefficients.

This paper proposes two methods for training Takagi–Sugeno (T-S) fuzzy systems using batch least squares (BLS) and particle swarm optimization (PSO). The T-S system is considered with triangular and Gaussian membership functions in the antecedents and higher-order polynomials in the consequents of fuzzy rules. In the first method, the BLS determines the polynomials in a system in which the fuzzy sets are known. In the second method, the PSO algorithm determines the fuzzy sets, whereas the BLS determines the polynomials. In this paper, the ridge regression is used to stabilize the solution when the problem is close to the singularity. Thanks to this, the proposed methods can be applied when the number of observations is less than the number of predictors. Moreover, the leave-one-out cross-validation is used to avoid overfitting and this way to choose the structure of a fuzzy model. A method of obtaining piecewise linear regression by means of the zero-order T-S system is also presented.

Ekspresja określonych alleli zgodności tkankowej stanowi czynnik ryzyka chorob reumatycznych. W reumatoidalnym zapaleniu stawow jest to obecnośc antygenow HLA-DRB1, z charakterystyczną sekwencją pieciu aminokwasow (glutamina, lizyna, arginina, alanina) w pozycjach od 70 do 74 lancucha, nazywanych najcześciej wspolnym epitopem. Charakterystyczna dla zesztywniającego zapalenie stawow kregoslupa jest ekspresja antygenu zgodności tkankowej HLA-B27, ktory moze prezentowac nieprawidlowo przetworzone peptydy antygenowe. Wydaje sie, ze cząsteczki HLA-B27 mogą z wiekszą wydajnością prezentowac autoreaktywnym limfocytom T patogenne peptydy bakteryjne albo endogenne peptydy artrytogenne. W biologii chorob reumatycznych wazną role mogą odgrywac takze polimorfizmy pojedynczego nukleotydu (SNP, single nucleotide polymorphism ) czy mechanizmy epigenetyczne, wplywające na ekspresje genow. Forum Reumatol. 2019, tom 5, nr 1: 33–42

This paper proposes a novel classification model called sparse fuzzy classifier (SFC), which uses a sparse Takagi-Sugeno fuzzy system to classify data. This system is considered with Gaussian fuzzy sets in the antecedents and first-order polynomials in the consequents of fuzzy rules. The input fuzzy sets are determined using a metaheuristic optimization method (particle swarm optimization, genetic algorithm, simulated annealing, or pattern search). The output polynomials are obtained by a sparse regression represented by the elastic net. A quality criterion based on the confusion value is used to select the best model. The experiments showed that the proposed method could reduce the confusion and simplify fuzzy models by zeroing some of the polynomial coefficients.

In the gait recognition problem, most studies are devoted to developing gait descriptors rather than introducing new classification methods. This paper proposes hybrid methods that combine regularized discriminant analysis (RDA) and swarm intelligence techniques for gait recognition. The purpose of this study is to develop strategies that will achieve better gait recognition results than those achieved by classical classification methods. In our approach, particle swarm optimization (PSO), grey wolf optimization (GWO), and whale optimization algorithm (WOA) are used. These techniques tune the observation weights and hyperparameters of the RDA method to minimize the objective function. The experiments conducted on the GPJATK dataset proved the validity of the proposed concept.

This paper presents a web-oriented expert system, named iHurdling, to predict results and generate training loads for 110 and 400 m hurdles races. The database contains 40 annual training programmes for the 110 m hurdles and 48 programmes for the 400 m hurdles. The predictive models include linear regressions in the form of ordinary least squares, ridge, LASSO, elastic net and nonlinear models in the form of a radial basis function neural network and fuzzy rule-based system. The leave-one-out cross-validation method is used to compare, and choose the best model. It shows that the proposed fuzzy-based model has the lowest validation error. The developed web application can support a coach in planning training programmes for hurdles races. It allows the athlete’s results to be predicted and can generate training loads for an athlete, selected from database. The application can be run on a computer or a mobile device. The system was implemented using the R programming language with the Shiny framework and additional packages. The limitations of the presented approach are related to the lack of consideration of an athlete’s physiological and psychological parameters, but the generated training programs might be used as a suggestion for the coach.

This paper presents a novel approach to planning training loads in hurdling using artificial neural networks. The neural models performed the task of generating loads for athletes’ training for the 400 meters hurdles. All the models were calculated based on the training data of 21 Polish National Team hurdlers, aged 22.25 ± 1.96, competing between 1989 and 2012. The analysis included 144 training plans that represented different stages in the annual training cycle. The main contribution of this paper is to develop neural models for planning training loads for the entire career of a typical hurdler. In the models, 29 variables were used, where four characterized the runner and 25 described the training process. Two artificial neural networks were used: a multi-layer perceptron and a network with radial basis functions. To assess the quality of the models, the leave-one-out cross-validation method was used in which the Normalized Root Mean Squared Error was calculated. The analysis shows that the method generating the smallest error was the radial basis function network with nine neurons in the hidden layer. Most of the calculated training loads demonstrated a non-linear relationship across the entire competitive period. The resulting model can be used as a tool to assist a coach in planning training loads during a selected training period.

This paper presents an evaluation of the annual cycle for 400 m hurdles using artificial neural networks. The analysis included 21 Polish national team hurdlers. In planning the annual cycle, 27 variables were used, where 5 variables describe the competitor and 22 variables represent the training loads. In the presented solution, the task of generating training loads for the assumed result were considered. The neural models were evaluated by cross-validation method. The smallest error was obtained for the radial basis function network with nine neurons in the hidden layer. The performed analysis shows that at each phase of training the structure of training loads is different.

This paper presents a method of monocular human motion tracking for estimation of hurdle clearance kinematic parameters. The analysis involved 10 image sequences of five hurdlers at various training levels. Recording of the sequences was carried out under simulated starting conditions of a 110 m hurdle race. The parameters were estimated using the particle swarm optimization algorithm and they are based on analysis of the images recorded with a 100 Hz camera. The proposed method does not involve using any special clothes, markers, inertial sensors, etc. As the quality criteria, the mean absolute error and mean relative error were used. The level of computed errors justifies the use of this method to estimate hurdle clearance parameters.

Unfortunately, the equation 39 has been published incorrectly in the online publication of the article.

This initial research presents the multiview human body tracking method as a tool to measure hurdle clearance parameters. This study was conducted on high level hurdlers, who were members of the Polish national team. The video sequences were recorded by a multicamera system consisting of three 100 Hz Full HD cameras. The sequences were registered under the simulated starting conditions of a 110 m hurdles race. Kinematic parameters were estimated based on the analysis of images from the multicamera system. These parameters were compared with the parameters obtained from ground truth poses. Mean absolute error and mean relative error were selected as the quality criteria. The main advantage of the method presented here is that it does not need any special clothes, markers or the support of other estimation techniques.

This paper presents a mobile expert system for Android platform, named R-tificial Trainer, to support the work of a hurdles coach in planning training programmes. The main feature of the developed application is the ability to generate training loads and predict results for an athlete. It includes a database of players and allows the user to generate training plan in PDF format. The application has been tested on a dataset of athletes practising hurdles on the 110 metres. The database contains 120 training programmes made by 18 athletes. The application uses the Predictive Model Markup Language standard. The predictive models include linear models in the form of ordinary least squares and LASSO regressions and nonlinear model in the form of a multilayer perceptron with exponential function. To choose the best method, the leave-one-out cross-validation is used. The lowest validation error was achieved by multilayer perceptron.

This paper presents a comparison of selected fuzzy particle swarm optimization algorithms. Two non-fuzzy and four fuzzy algorithms are considered. The Takagi–Sugeno fuzzy system is used to change the parameters of these algorithms. A modified fuzzy particle swarm optimization method is proposed in which each of the particles has its own inertia weight and coefficients of the cognitive and social components. The evaluation is based on the common nonlinear benchmark functions frequently used for testing optimization methods. The ratings of the algorithms are assigned on the basis of the mean of the objective function final value.

The global expansion of cylindrospermopsin (CYN) producing cyanobacteria in surface freshwater increases the risk of human exposure and poisoning. Following ingestion, CYN is transported with blood in general circulation to the liver and kidneys, and can potentially interact with immune system cells. In the present study, we investigated whether CYN (0.01-1.0 μg ml(-1)) can alter the function of human peripheral blood lymphocytes isolated from healthy donors. It was found that CYN demonstrates significant antiproliferative activity in lymphocytes during different phases of their activation. The most remarkable effects (decrease by>90%) were observed in lymphocytes exposed to 1 μg ml(-1) CYN at the beginning of activation. Further analyses revealed a cell-cycle arrest at G0/G1 and prolonged S phase in lymphocytes undergoing activation and significant apoptosis inducement in activated cells. Reduced abilities to fight pathogenic microorganisms or malignant cells should be taken into consideration in CYN exposure and risk assessments.

Introduction: Cigarette smoking is considered an important risk factor for developing Crohn’s disease (CD), contributing to a more severe course of the disease. Conversely, smoking is believed to have a beneficial effect on the course of ulcerative colitis (UC), a second major condition of inflammatory bowel disease (IBD). Aim: To investigate the effect of tobacco use on the clinical course of IBD. Material and methods: A group of 95 adults with IBD were enrolled to the study. Demographic and clinical data of patients as well as their smoking status were analysed based on their medical history. Values were considered significant when p ≤ 0.05. Results: Current smokers constituted the majority of CD patients. They tended to develop a more severe course of the disease, compared to former smokers and non-smokers. Current smokers suffered a moderate-to-severe form of the disease and required immunosuppressive therapy more frequently. They were also hospitalised and underwent surgeries more frequently than patients from other investigated subgroups. The study failed, however, to fully confirm the beneficial effect of smoking on the clinical outcome of UC. The investigated non-smokers and former smokers suffered a more severe disease, but the analysis did not find any statistical differences in the frequencies of hospitalisations nor immunosuppressant usage among the investigated subgroups. Conclusions: The study confirmed a detrimental effect of smoking on the outcome of CD, but failed to fully confirm its beneficial effect on UC.

The biological role of cyanobacteria secondary metabolites is relatively unknown although several possible hypotheses have been discussed. In the following study the effect of cylindrospermopsin (CYN) and metabolites of non-CYN producing Cylindrospermopsis raciborskii strain on growth, alkaline phosphatase (ALP) activity and microcystin-LR (MC-LR) production in Microcystis aeruginosa was evaluated. Higher concentrations of CYN (10 and 50 μg L−1) induced toxicity effects demonstrated by significant growth inhibition and M. aeruginosa cell necrosis. Lower concentrations of CYN (1 and 5 μg L−1) slightly decreased growth rates but significantly up-regulated ALP activity. Moreover, under all studied CYN concentrations MC-LR production strongly decreased. Spent C. raciborskii medium mimicked the CYN action by inducing strong inhibition of M. aeruginosa growth and MC-LR production and through up-regulation of ALP activity. On the other hand, spent M. aeruginosa medium did not affect C. raciborskii growth and no alterations in ALP activity were observed. Co-culturing of these two species resulted in an increase of C. raciborskii contribution at the expense of M. aeruginosa. From the results we conclude that CYN can be involved in interspecific competition in cyanobacteria and that non-CYN producing C. raciborskii strains may produce a hitherto unknown bioactive compound(s) which can mimic CYN action.

The growth of human population leads to intensification of agriculture and promotes, through eutrophication, development of cyanobacteria. One of the most widespread and bloom-forming species in freshwater is toxic Microcystis aeruginosa (M. aeruginosa). Combustion of fossil fuels and metallurgical processes are the main sources of heavy metals contamination in surface water including cadmium (Cd) and lead (Pb). The following study was conducted in order to determine the effect of 1–20 mg·L−1 of Cd and Pb on photochemistry (using flow cytometry) and growth (based on chlorophyll concentration) of M. aeruginosa as well as to estimate levels of metal bioaccumulation. We have found that 1–10 mg·L−1 of Cd and 1–5mg·L−1 of Pb induced continuous enhancement of chlorophyll fluorescence during 24 h of incubation. No significant degradation of chlorophyll was observed in these samples. At higher concentrations of 20 mg·L−1 of Cd and 10–20 mg·L−1 of Pb chlorophyll level significantly decreased and its fluorescence was quenched. M. aeruginosa demonstrated high capability of Cd and Pb bioaccumulation, proportionally to initial metal concentration. In samples with initial concentration of 20 mg·L−1 of Cd and Pb bioaccumulation of 87.3% and 90.1% was observed, respectively. Our study demonstrates that M. aeruginosa can potentially survive in highly metals polluted environments, be a primary source of toxic metals in the food chain and consequently contribute to enhanced toxicity of heavy metals to living organisms including human.

An increased level of low-density lipoprotein (LDL) is a very well established risk factor of coronary artery disease (CAD). Unoxidized LDL is an inert transport vehicle of cholesterol and other lipids in the body and is thought to be atherogenic. Recently it has been appreciated that oxidized products of LDL are responsible for plaque formation properties previously attributed to the intact particle. The goal of this article is to review the recent understanding of the LDL oxidation pathway. The role of oxidized products and key enzymes (lipoprotein-associated phospholipase A2 and carboxyl ester lipase) are also extensively discussed in the context of clinical conditions.

This paper is devoted to an evaluation of selected fuzzy particle swarm optimization algorithms. Two non-fuzzy and four fuzzy algorithms are considered. The Takagi-Sugeno fuzzy system is utilized to change the parameters of these algorithms. A modified fuzzy particle swarm optimization method is proposed, in which each of the particles has its own inertia weight and coefficients of the cognitive and social components. The evaluation is based on the common nonlinear benchmark functions used for testing optimization methods. The ratings of the algorithms are assigned on the basis of the mean of the objective function and the relative success.

The present study was undertaken in order to determine the effect of low frequency electromagnetic field (EMF) on reactive oxygen species (ROS) production in human neutrophils in peripheral blood in vitro. We investigated how differently generated EMF and several levels of magnetic induction affect ROS production. To evaluate the level of ROS production, two fluorescent dyes were used: 2'7'-dichlorofluorscein-diacetate and dihydrorhodamine. Phorbol 12-myristate 13-acetate (PMA), known as strong stimulator of the respiratory burst, was also used. Alternating magnetic field was generated by means of Viofor JPS apparatus. Three different levels of magnetic induction have been analyzed (10, 40 and 60 μT). Fluorescence of dichlorofluorescein and 123 rhodamine was measured by flow cytometry. The experiments demonstrated that only EMF tuned to the calcium ion cyclotron resonance frequency was able to affect ROS production in neutrophils. Statistical analysis showed that this effect depended on magnetic induction value of applied EMF. Incubation in EMF inhibited cell activity slightly in unstimulated neutrophils, whereas the activity of PMA-stimulated neutrophils has increased after incubation in EMF.

The toxic effect of six heavy metals on cyanobacteria Synechocystis aquatilis was studied by absorption, fluorescence, flow cytometry, and photothermal measurements. This study indicates that at the concentration used, the cyanobacteria are more sensitive to silver, copper, and mercury than to cadmium, lead, and zinc metals. Disregarding the decrease in the yields of the related radiative processes caused by photochemical processes and/or damage to phycobilisomes, no changes were detected in the efficiency of thermal deactivation processes within a few microseconds, which can indicate the lack of disturbances in the photosynthetic light reaction and the lack of damage to the photosystem caused by the heavy metal ions in the concentrations used. The results demonstrate that the relative values of fluorescence yield as well as promptly generated heat calculated for the metal-affected and unaffected (reference) bacteria are sensitive indicators of environmental pollution with heavy metal ions, whereas the complementary methods proposed could be used as a noninvasive and fast procedure for in vivo assessment of their toxicity.

Introduction: The aim of the study was to assess quantitative acute phase protein (APP) level changes in patients with non-small cell lung cancer (NSCLC) subjected to radical resections, as well as their influence on long-term survival. We analysed the correlation between quantitative APP changes and the histological type of the carcinoma, as well as the TNM stage and grade. Materials and methods: The study group comprised 46 patients subjected to surgical treatment of NSCLC during the period between 2003 and 2004. Average patient age amounted to 61 years (ranging between 45 and 77 years). The most frequent histological types of cancer were: squamous cell lung cancer (24 patients) and adenocarcinoma (17 patients). The majority of patients were diagnosed with stage II B (15 patients) and III A (14 patients). We evaluated the levels of the following APP: C-reactive protein (CRP), α1-acid glycoprotein (AGP), α1-antichymotrypsin (ACT), α1-antitrypsin (AT), α2-macroglobulin (M), ceruloplasmin (Cp), haptoglobin (Hp), and transferrin (Tf) by means of rocket immunoelectrophoresis (Laurell’s method). Results: The level of AT was significantly higher in patients with adenocarcinoma, as compared to other histological types of cancer. In the case of patients with squamous cell lung cancer, significantly higher M and Cp levels were observed. We found no correlation between the APP level and tumour grading. The levels of five APP: CRP, AGP, ACT, M and Cp were significantly higher in the group of patients with T3 or T4 category, while N1 or N2 patients presented with significantly higher concentrations of AT, CRP and Hp. Multivariate analysis confirmed the influence of the following factors on long-term survival: N stage, histological type of cancer and preoperative serum levels of AGP and Hp. Conclusions: The serum concentration of some acute phase proteins can correlate with the more aggressive clinical course of non-small cell lung cancer (NSCLC). Patients with adenocarcinoma and local lymph node metastases present with significantly higher levels of AT. Thus, it seems that the elevated preoperative levels of AGP and Hp might unfavourably influence long-term survival. The above-mentioned proteins might prove useful as prognostic factors when assessing the risk of neoplastic recurrence following surgical management.