Probabilistic neural networks combined with wavelet coefficients for analysis of electroencephalogram signals

Abstract: In this paper, the probabilistic neural network is presented for classification of electroencephalogram (EEG) signals. Decision making is performed in two stages: feature extraction by wavelet transform and classification using the classifiers trained on the extracted features. The purpose is to determine an optimum classification scheme for this problem and also to infer clues about the extracted features. The present research demonstrates that the wavelet coefficients obtained by the wavelet transform are features which represent the EEG signals well. The conclusions indicate that the probabilistic neural network trained on the wavelet coefficients achieves high classification accuracies (the total classification accuracy is 97.63%).     

Adaptive neuro-fuzzy inference system employing wavelet coefficients for detection of alterations in sleep EEG activity during hypopnoea episodes

The Obstructive Sleep Apnoea Hypopnoea Syndrome (OSAH) means “cessation of breath” during the sleep hours and the sufferers often experience related changes in the electrical activity of the brain and heart. This paper describes the application of adaptive neuro-fuzzy inference system (ANFIS) model for automatic detection of alterations in the human electroencephalogram (EEG) activities during hypopnoea episodes. Decision making was performed in two stages: feature extraction by computation of wavelet coefficients and classification by the ANFIS trained with the backpropagation gradient descent method in combination with the least squares method. The EEG signals (pre and during hypopnoea) from three electrodes (C3, C4 and O2) were used as input patterns of the three ANFIS classifiers. To improve diagnostic accuracy, the fourth ANFIS classifier (combining ANFIS) was trained using the outputs of the three ANFIS classifiers as input data. The proposed ANFIS model combined the neural network adaptive capabilities and the fuzzy logic qualitative approach. Some conclusions concerning the saliency of features on detecting any possible changes in the human EEG activity due to hypopnoea (mild case of cessation of breath) occurrences were drawn through analysis of the ANFIS. The performance of the ANFIS model was evaluated in terms of training performance and classification accuracies and the results confirmed that the proposed ANFIS model has potential in detecting changes in the human EEG activity due to hypopnoea episodes.     

Combining eigenvector methods and support vector machines for detecting variability of Doppler ultrasound signals

In this paper, the multiclass support vector machines (SVMs) with the error correcting output codes (ECOC) were presented for detecting variabilities of the multiclass Doppler ultrasound signals. The ophthalmic arterial (OA) Doppler signals were recorded from healthy subjects, subjects suffering from OA stenosis, subjects suffering from ocular Behcet disease. The internal carotid arterial (ICA) Doppler signals were recorded from healthy subjects, subjects suffering from ICA stenosis, subjects suffering from ICA occlusion. Methods of combining multiple classifiers with diverse features are viewed as a general problem in various application areas of pattern recognition. Because of the importance of making the right decision, better classification procedures for Doppler ultrasound signals are searched. Decision making was performed in two stages: feature extraction by eigenvector methods and classification using the SVMs trained on the extracted features. The research demonstrated that the multiclass SVMs trained on extracted features achieved high accuracy rates.     

Implementing wavelet transform/mixture of experts network for analysis of electrocardiogram beats

Abstract: Mixture of experts (ME) is a modular neural network architecture for supervised learning. This paper illustrates the use of the ME network structure to guide model selection for classification of electrocardiogram (ECG) beats. The expectation maximization algorithm is used for training the ME so that the learning process is decoupled in a manner that fits well with the modular structure. The ECG signals were decomposed into time–frequency representations using discrete wavelet transforms and statistical features were calculated to depict their distribution. The ME network structure was implemented for ECG beats classification using the statistical features as inputs. To improve classification accuracy, the outputs of expert networks were combined by a gating network simultaneously trained in order to stochastically select the expert that is performing the best at solving the problem. Five types of ECG beats (normal beat, congestive heart failure beat, ventricular tachyarrhythmia beat, atrial fibrillation beat, partial epilepsy beat) obtained from the Physiobank database were classified with an accuracy of 96.89% by the ME network structure. The ME network structure achieved accuracy rates which were higher than those of the stand-alone neural network models.     

Recurrent neural networks employing Lyapunov exponents for analysis of doppler ultrasound signals

The implementation of recurrent neural networks (RNNs) with the Lyapunov exponents for Doppler ultrasound signals classification is presented. This study is based on the consideration that Doppler ultrasound signals are chaotic signals. This consideration was tested successfully using the nonlinear dynamics tools, like the computation of Lyapunov exponents. Decision making was performed in two stages: computation of Lyapunov exponents as representative features of the Doppler ultrasound signals and classification using the RNNs trained on the extracted features. The present research demonstrated that the Lyapunov exponents are the features which well represent the Doppler ultrasound signals and the RNNs trained on these features achieved high classification accuracies.     

Sorption of boron by invasive marine seaweed: Caulerpa racemosa var. cylindracea

The sorption of boron from aqueous solution onto Caulerpa racemosa var. cylindracea (CRC), collected from Seferihisar/Izmir region in Turkey, was investigated as a function of pH, temperature, initial boron concentration, adsorbent dosage, contact time and ionic strength. Optimum conditions for the sorption of boron were obtained at pH 7.5, 318 K, 8 mg L⁻¹ initial boron concentration, 0.2 g of CRC, 2.5 h contact time and greater ionic strength (10⁻¹ M NaCl). As the temperature was increased the boron removal took place with higher percentages. In experiments conducted at optimum conditions, maximum boron sorption was determined to be about 63%. The experimental data were analyzed by Freundlich, Langmuir and Dubinin–Radusckevich (DR) equations. Freundlich and DR models provide best conformity with the experimental data. In order to describe kinetics of boron sorption onto CRC, first-order Lagergren equation, pseudo-second-order kinetic model and intraparticle diffusion model were used. It was seen that the first order Lagergren equation was better described than the pseudo-second-order kinetic model. Thermodynamic parameters of sorption process were also calculated. It was obtained that sorption process was not spontaneous. The characterization of CRC was carried out by Fourier transform infrared spectroscopy (FTIR) analysis.     

Some compositional properties of main Malatya apricot (Prunus armeniaca L.) varieties

Malatya apricot (Prunus armeniaca L.) varieties are among the most important agricultural products of Turkey and protected as a geographical indication. In this research, it was aimed to determine some important analytical properties (dry matter, soluble solid content, a_w, ash, titratable acidity, pH, color, total phenolics, total carotenoids, β-carotene, sugars, organic acids, and mineral content) of Malatya apricots and to reveal the characteristic properties that differ these products from the similar ones. The apricot varieties, namely Hac?halilo?lu, Hasanbey, So?anc?, Kabaa??, Çatalo?lu, Çölo?lu, and Hac?k?z that are widely cultivated in Malatya region and other regions (Ere?li, ?zmir, I?d?r, and Bursa) of Turkey were involved in the study. All analytical properties were found to be significantly different (p < 0.05) among different apricot varieties. The results have shown that dry matter and sugar content of Malatya apricot varieties are considerably higher than the other apricot varieties investigated in this study, as well as the data of other researches on apricots. All apricot varieties were found to be a good source of phenolic compounds (4233.70–8180.49 mg of gallic acid equiv/100 g of dry weight), carotenoids (14.83–91.89 mg of β-carotene equiv/100 g of dry weight), and β-carotene (5.74–48.69 mg/100 g of dry weight). Sucrose, glucose, and fructose were determined as the major sugars in all apricot varieties. In addition, sorbitol contents (16.91–26.84 mg/100 g of dry weight) of Malatya apricots were remarkably higher than the other apricot varieties. This was considered to be the one of the unique properties of Malatya apricots. Malic acid was the predominant organic acid in all Malatya apricot varieties. The results have also shown that the potassium content of Malatya apricots was significantly high and these apricots were important sources of Mg, Zn, and Se. This study has revealed that Malatya apricot contains functional food components with high nutritional value.     

Bioavailability of wastewater-derived organic nitrogen to the alga Selenastrum Capricornutum

Recent attempts to control cultural eutrophication in nitrogen-limited systems have focused on the simultaneous control of all forms of nitrogen with the underlying assumption that inorganic and organic nitrogen are equally bioavailable. To assess the validity of this assumption, algal growth bioassays were conducted on denitrified wastewater effluent samples, in the presence and absence of bacteria isolated from an effluent-receiving surface water. Bioassay results indicated that wastewater-derived dissolved organic nitrogen (DON) is not bioavailable to the algae Selenastrum Capricornutum in the absence of bacteria. However, approximately half of the wastewater-derived organic nitrogen was available to the algae in the presence of bacteria during a 2-week incubation. These results suggest that while it is inappropriate to assume that wastewater-derived DON cannot cause cultural eutrophication, it will not cause as much eutrophication as inorganic nitrogen. Additional research is needed to develop methods of minimizing the discharge of bioavailable forms of wastewater-derived organic nitrogen by wastewater treatment plants.     

Advanced mathematical model for the passive direct borohydride/peroxide fuel cell

In the literature a mathematical model has been developed for the direct borohydride fuel cells by Verma et al. [1]. This model simply simulates the fuel cell system via kinetic mechanisms of the borohydride and oxygen. Their mathematical expression contains the activation losses caused by the oxidation of the borohydride and the concentration overpotential increased by the reduction of oxygen. In this study a direct borohydride/peroxide fuel cell has been constructed using hydrogen peroxide (H₂O₂) as oxidant instead of the oxygen. Therefore we created an advanced model for peroxide fuel cells, including the activation overpotential of the peroxide. The goal of our model is to provide the information about the peroxide reduction effect on the cell performance. Our comprehensive mathematical model has been developed by taking Verma’s model into account. KH₂O₂ used in the advanced model was calculated as 6.72 × 10⁻⁴ mol cm⁻² s⁻¹ by the cyclic voltammogram of Pt electrode in the acidic peroxide solution.