Narrow Results

Hypoxic-ischemic (HI) studies in preterms lack reliable prognostic biomarkers for diagnostic tests of HI encephalopathy (HIE). Our group’s observations from in utero fetal sheep models suggest that potential biomarkers of HIE in the form of developing HI micro-scale epileptiform transients emerge along suppressed EEG/ECoG background during a latent phase of 6–7h post-insult. However, having to observe for the whole of the latent phase disqualifies any chance of clinical intervention. A precise automatic identification of these transients can help for a well-timed diagnosis of the HIE and to stop the spread of the injury before it becomes irreversible. This paper reports fusion of Reverse-Biorthogonal Wavelets with Type-1 Fuzzy classifiers, for the accurate real-time automatic identification and quantification of high-frequency HI spike transients in the latent phase, tested over seven in utero preterm sheep. Considerable high performance of 99.78 ± 0.10% was obtained from the Rbio-Wavelet Type-1 Fuzzy classifier for automatic identification of HI spikes tested over 42h of high-resolution recordings (sampling-freq:1024Hz). Data from post-insult automatic time-localization of high-frequency HI spikes reveals a promising trend in the average rate of the HI spikes, even in the animals with shorter occlusion periods, which highlights considerable higher number of transients within the first 2h post-insult.

This article studies quantum games with imprecise payoffs simulated by means of fuzzy numbers. Three two-person game-types are scrutinized via the iterated confronting of a large number of players laying in a two-dimensional lattice. In every iteration, every player interacts with his nearest neighbours and adopts the strategy of his best paid mate. Variable degree of quantum entanglement and of optimism in the fuzzy payoffs are taken into consideration in the study.

Image retrieval based on content not only relies heavily upon the type of descriptors, but on the steps taken further. This has been an extensively utilized methodology for finding and fetching out images from the big database of images. Nowadays, a number of methodologies have been organized to increase the CBIR performance. This has an ability to recover pictures relying upon their graphical information. In the proposed method, Neuro-Fuzzy classifier and Deep Neural Network classifier are used to classify the pictures from a given dataset. The proposed approach obtained the highest accuracy in terms of Precision, Recall, and F-measure. To show the efficiency and effectiveness of proposed approach, statistical testing is used in terms of standard deviation, skewness, and kurtosis. The results reveal that the proposed algorithm outperforms other approaches using low computational efforts.

The detection of insulators contamination is difficult in power systems because many factors can influence the pollution. The contamination condition of insulators is usually estimated by detecting the root mean square (r.m.s) of surface leakage current via online-monitoring system. It ignores the influence of environmental factors, such as temperature, humidity, etc. As these factors are fuzzy-characterized, a new method based on Fuzzy Neural Network (FNN) is proposed to improve traditional insulation contamination detection. The renewed structure of FNN is put forward. The evaluation of contamination severity of insulators is achieved through FNN, which are trained by the field samples. The results prove the validity of the method proposed in the paper and can be used to eliminate the insulator from flashover fault and improve the condition-based maintenance (CBM).

A versatile low-voltage CMOS circuit with a trapezoidal transconductance characteristic and independently programmable slope, height and horizontal position is designed in 0.18$\mu$m standard CMOS technology. The proposed circuit is constructed from combination of two linearization methods to enhance the linearity in low voltage applications. A $-$118dB THD was obtained for a 400mV peak to peak differential input voltage at 125KHz. Simulation results using HSPICE that verify the functionality of circuit with 1.5V supply are presented. The total power consumption is only 120$\mu$W. The circuit can find application in the implementation of membership functions in analogue and mixed-signal neuro-fuzzy systems.

This paper propounded a novel method of design and realization of a digital fuzzy controlled buck integrated power factor correction (PFC) converter. It derives its advantages through the low buck capacitor voltage and single control switch (SW1), which leads to reduced complex control and price. Sub-harmonic oscillations generated in the peak current mode technique can be nullified by using the ramp signal, thereby improving the overall performance of the converter. The fuzzy logic controller (FLC) is robust and effective than the conventional linear controllers like P, PI, PID. In this paper, the digital fuzzy current mode controlled integrated PFC converter with external ramp compensation signal for 100 W load operating in the universal range of voltage (90V–265V), 50Hz has been designed and implemented using MATLAB/Simulink, verified in hardware using the TMS320F2812 digital processor board, and the results are found to be complying with international regulatory standards (IEC 6100-3-2 and IEEE 519-1992).

In this paper, a simple and systematic control design method is proposed for making a continuous-time Takagi–Sugeno (T–S) fuzzy system chaotic. The concept of parallel distributed compensation is employed to determine the structure of a fuzzy controller from a T–S fuzzy model. The fuzzy controller makes the T–S fuzzy model, which could be stable or unstable, bounded and chaotic. The verification of chaos in the closed-loop T–S fuzzy system is done by the following procedure. First, we establish an asymptotically approximate relationship between a continuous-time T–S fuzzy system with time-delay and a discrete-time T–S fuzzy system. Then, we verify the chaos in the closed-loop T–S fuzzy system by applying the Marotto theorem to its associated discrete-time T–S fuzzy system. The generated chaos is in the sense of Li and Yorke. Two examples are given to show that this methodology is simple and effective for anticontrol of chaos for a continuous-time T–S fuzzy system.

This paper presents a decision support system for radiotherapy treatment planning for head, neck and brain cancer. The aim of a treatment plan is to apply radiation to kill tumor cells, while minimizing the damage to healthy tissue and critical organs. Since treatment planning is a complex decision making process that relies heavily on the subjective experience of clinicians, we propose the use of case-based reasoning (CBR), in which problems are solved based on the solutions of similar past problems. This paper focuses on the case retrieval process of a CBR system. The attributes, which describe the cases, are selected by assessing their effect on the performance of the CBR system. We have developed a context sensitive local weighting scheme that assigns weights to attributes based on their value and the values of other attributes in the target case. A novel two phase retrieval mechanism is developed, in which each phase is optimized to retrieve a particular part of the solution. We also present an original use of fuzzy logic in order to represent nonlinearity in the similarity measure. Experiments, which evaluate the similarity measure using real brain cancer patient cases, show promising results.

A method to assign fuzzy labels to unlabeled hypertext documents based on hyperlink structure information is first proposed. Then, the construction of the fuzzy transductive support vector machines is described. Also, an algorithm to train the fuzzy transductive support vector machines is presented. While in the transductive support vector machines all the test examples are treated equally, in the fuzzy transductive support vector machines, test examples are treated discriminatively according to their fuzzy labels, hence a more reliable decision function. Experimental results on the WebKB corpus show that, by fusing the plain text information and the hyperlink structure information, much better classification performance can be achieved.

Industrial process quality control has as yet been carried out using Shewhart's classic charts and control charts with probabilistic limits, using sampling statistics for average and deviation and , respectively, or C_p and C_pk, derived from them, in order to determine whether the process is precise or imprecise. Although these statistics has been formulated using crisp mathematics, their use returns statements about "quality control" which are full of vagueness (for example, the aforementioned idea of precise or imprecise processes). For this reason, it seems both natural and interesting to introduce tools from Fuzzy Sets Theory for the formulation of quality control models.

Fuzzy Sets shall be used to study process quality capability and to generate a bilateral simultaneous control for the central tendency and a unilateral one for variability. We shall define linguistic rules in order to perform this control and membership functions for the sample control mean and deviation, and ŝ.

The aim of the present paper is to establish an extended Chebyshev type inequality for semi(co)normed fuzzy integrals based on an aggregation function and a scale transformation. The extended Chebyshev type inequality given in this paper provides a generalization of some previous results. Finally, some conclusions are drawn and some problems for further investigations are given.

Group decision making is an important category of problem solving techniques for complicated problems, among which the Delphi method has been widely applied. In this paper an improved Delphi method based on Cloud model is proposed in order to deal with the fuzziness and uncertainty in experts' subjective judgments. The proposed Cloud Delphi Method (CDM) describes experts' opinions by Cloud model and we aggregate the experts' Cloud opinions by synthetic algorithm and weighted average algorithm. Another key point of CDM is to stabilize and accommodate the individual fuzzy estimates by the defined stability rules rather than having to force them to converge, or reduce. The Cloud opinions and aggregation results can be exhibited in a graphically way leading experts to judge intuitively and it can decrease the number of repetitive surveys and/or interviews. Moreover, it is more scientific and easier to represent experts' opinion base on Cloud model which can combine fuzziness and uncertainty well. A numerical example is examined to demonstrate applicability and implementation process of CDM.

In the domain of law, various real situations are expressed as relations and/or combinations of legal knowledge items (legal concepts, articles of law, etc). Such knowledge items (legal facts, events) cannot be precisely defined. Legal judgement is performed based on resemblance of legal knowledge and facts. In our system, vague legal knowledge is saved in the fuzzy relational database, and legal inference is realized as fuzzy inference. The target law for this system is the United Nations Convention on Contracts for the International Sale of Goods (CISG).

Many applications of probability theory are based on the assumption that, as the number of cases increase, the relative frequency of cases with a certain property tends to a number – probability that this property is true. L. Zadeh has shown that in many real-life situations, the frequency oscillates and does not converge at all. It is very difficult to describe such situations by using methods from traditional probability theory. Fuzzy logic is not based on any convergence assumptions and therefore, provides a natural description of such situations. However, a natural next question arises: how can we describe this oscillating behavior? Since we cannot describe it by using a single parameter (such as probability), we need to use a multi-D formalism. In this paper, we describe an optimal formalism for describing such oscillations, and show that it complements traditional probability techniques in the same way as fractals complement smooth curves and surfaces.

In this paper, we present an overview of TUBERDIAG, a rule-based expert system for diagnosis of pulmonary tuberculosis. This system was developed as a 2-year joint project by the Institute of Information Technology (National Center for Science and Technology) and the National Institute of Tuberculosis and Lung Diseases, Hanoi. After designing and building a suitable inference engine for this system, we have done a lot of work to create an effective knowledge base; at present, this knowledge base contains more than 1,000 rules. The paper focuses on how the rule base is constructed, managed, and used. We also present here the first evaluation of TUBERDIAG by the doctors at the National Institute of Tuberculosis and Lung Diseases, who have been playing a very important role in the project – providing the system with their knowledge.

The safety evaluations of structures are usually performed by assuming uncertain 18 input parameters either as probabilistic or possibilistic in nature. Safety evaluations of structural systems characterized by some of the input parameters as possibilistic and others that are sufficient enough to model as probabilistic are unsuitable and restricted to gross assumption at early stages of modeling. The present paper deals with the safety analysis of such a hybrid uncertain system. Relying on the fundamental concept of entropy-based transformation; the feasibility of reliability analysis of a hybrid uncertain system in a possibilistic format is demonstrated in the present study. This will enable the designers to model the structural parameter uncertainty probabilistically as well possibilistically depending on the nature and quality of the input data. The bounds on the probability of failure based on the evidence theory are also computed to study the consistency of the possibility of failure results obtained by the transformation-based algorithm. A numerical example illustrates the capability of the proposed possibilistic approach of safety evaluation of hybrid uncertain system.

University students face immense challenges in current situations in ideological and political research. Therefore, the way ideological work constantly needs to be adapted, and the exchange of advanced experience strengthened to increase ideological and political education (IPE) in universities. Specific methods of university administration may include only ideological and political courses. Courses information and student grades did not conduct an ideological or political evaluation of the student. They assessed the psychological behaviors of the student based on their success, nor did them include clear information on the course schedule for specific ideological and political courses. This article, Supervised learning-based teaching evaluation approach (SL-TEA), has been proposed to focus on supervised learning from ideas about machine learning technology and the current IPE status, to be developed using a brief analysis procedure. Supervised learning uses a practice set to provide the necessary quality through teaching models. Inputs and correct outputs that allow the model to learn over time are part of this training data. The study uses the system of experts to manage, operate and monitor model evaluation data and create a related database for a real-time update. Besides, to check the impact of the model and to run simulation tests. This study SL-TEA model follows the real needs of the system that the ideological and political teaching content of colleges and colleges can be evaluated. Thus, the experimental results show the better performance through the highest student accuracy ratio of 97.1 %, a high-performance ratio of 94.3%, improved political thinking rate of 92.8%, improved actual positive rate of 90.2%, the false-positive rate of 92.2%, enhance learning rate of 96.6% and reduce the error rate 21.2%, compared to other methods.

The sum total of millions of cardiac cell depolarization potentials can be represented using an electrocardiogram (ECG). By inspecting the P-QRS-T wave in the ECG of a patient, the cardiac health can be diagnosed. Since the amplitude and duration of the ECG signal are too small, subtle changes in the ECG signal are very difficult to be deciphered. In this work, the heart rate variability (HRV) signal has been used as the base signal to observe the functioning of the heart. The HRV signal is non-linear and non-stationary. Recurrence quantification analysis (RQA) has been used to extract the important features from the heart rate signals. These features were fed to the fuzzy, Gaussian mixture model (GMM), and probabilistic neural network (PNN) classifiers for automated classification of cardiac bio-electrical contractile disorders. Receiver operating characteristics (ROC) was used to test the performance of the classifiers. In our work, the Fuzzy classifier performed better than the other classifiers and demonstrated an average classification accuracy, sensitivity, specificity, and positive predictive value of more than 83%. The developed system is suitable to evaluate large datasets.

This paper describes a computer-based identification system of normal and alcoholic Electroencephalography (EEG) signals. The identification system was constructed from feature extraction and classification algorithms. The feature extraction was based on wavelet packet decomposition (WPD) and energy measures. Feature fitness was established through the statistical t-test method. The extracted features were used as training and test data for a competitive 10-fold cross-validated analysis of six classification algorithms. This analysis showed that, with an accuracy of 95.8%, the k-nearest neighbor (k-NN) algorithm outperforms naïve Bayes classification (NBC), fuzzy Sugeno classifier (FSC), probabilistic neural network (PNN), Gaussian mixture model (GMM), and decision tree (DT). The 10-fold stratified cross-validation instilled reliability in the result, therefore we are confident when we state that EEG signals can be used to automate both diagnosis and treatment monitoring of alcoholic patients. Such an automatization can lead to cost reduction by relieving medical experts from routine and administrative tasks.

Electroencephalography (EEG) is a measure which represents the functional activity of the brain. We show that a detailed analysis of EEG measurements provides highly discriminant features which indicate the mental state of patients with clinical depression. Our feature extraction method revolves around a novel processing structure that combines wavelet packet decomposition (WPD) and non-linear algorithms. WPD was used to select appropriate EEG frequency bands. The resulting signals were processed with the non-linear measures of approximate entropy (ApEn), sample entropy (SampEn), renyi entropy (REN) and bispectral phase entropy (Ph). The features were selected using t-test and only discriminative features were fed to various classifiers, namely probabilistic neural network (PNN), support vector machine (SVM), decision tree (DT), k-nearest neighbor algorithm (k-NN), naive bayes classification (NBC), Gaussian mixture model (GMM) and Fuzzy Sugeno Classifier (FSC). Our classification results show that, with a classification accuracy of 99.5%, the PNN classifier performed better than the rest of classifiers in discriminating between normal and depression EEG signals. Hence, the proposed decision support system can be used to diagnose, and monitor the treatment of patients suffering from depression.