Maysam F. Abbod

A new hybrid ensemble credit scoring model based on classifiers consensus system approach

A new hybrid ensemble model for credit scoring problem is proposed.An improved data filtering technique is developed based on GNG method.GNG with MARS combined proved to be better than applying them individually.Our model is validated on four performance measures over seven credit datasets.Classifiers decisions after consensus effectively improved prediction performance. During the last few years there has been marked attention towards hybrid and ensemble systems development, having proved their ability to be more accurate than single classifier models. However, among the hybrid and ensemble models developed in the literature there has been little consideration given to: 1) combining data filtering and feature selection methods 2) combining classifiers of different algorithms; and 3) exploring different classifier output combination techniques other than the traditional ones found in the literature. In this paper, the aim is to improve predictive performance by presenting a new hybrid ensemble credit scoring model through the combination of two data pre-processing methods based on Gabriel Neighbourhood Graph editing (GNG) and Multivariate Adaptive Regression Splines (MARS) in the hybrid modelling phase. In addition, a new classifier combination rule based on the consensus approach (ConsA) of different classification algorithms during the ensemble modelling phase is proposed. Several comparisons will be carried out in this paper, as follows: 1) Comparison of individual base classifiers with the GNG and MARS methods applied separately and combined in order to choose the best results for the ensemble modelling phase; 2) Comparison of the proposed approach with all the base classifiers and ensemble classifiers with the traditional combination methods; and 3) Comparison of the proposed approach with recent related studies in the literature. Five of the well-known base classifiers are used, namely, neural networks (NN), support vector machines (SVM), random forests (RF), decision trees (DT), and naive Bayes (NB). The experimental results, analysis and statistical tests prove the ability of the proposed approach to improve prediction performance against all the base classifiers, hybrid and the traditional combination methods in terms of average accuracy, the area under the curve (AUC) H-measure and the Brier Score. The model was validated over seven real world credit datasets.

EEG artifacts reduction by multivariate empirical mode decomposition and multiscale entropy for monitoring depth of anaesthesia during surgery

Electroencephalography (EEG) has been widely utilized to measure the depth of anaesthesia (DOA) during operation. However, the EEG signals are usually contaminated by artifacts which have a consequence on the measured DOA accuracy. In this study, an effective and useful filtering algorithm based on multivariate empirical mode decomposition and multiscale entropy (MSE) is proposed to measure DOA. Mean entropy of MSE is used as an index to find artifacts-free intrinsic mode functions. The effect of different levels of artifacts on the performances of the proposed filtering is analysed using simulated data. Furthermore, 21 patients’ EEG signals are collected and analysed using sample entropy to calculate the complexity for monitoring DOA. The correlation coefficients of entropy and bispectral index (BIS) results show 0.14xa0±xa00.30 and 0.63xa0±xa00.09 before and after filtering, respectively. Artificial neural network (ANN) model is used for range mapping in order to correlate the measurements with BIS. The ANN method results show strong correlation coefficient (0.75xa0±xa00.08). The results in this paper verify that entropy values and BIS have a strong correlation for the purpose of DOA monitoring and the proposed filtering method can effectively filter artifacts from EEG signals. The proposed method performs better than the commonly used wavelet denoising method. This study provides a fully adaptive and automated filter for EEG to measure DOA more accuracy and thus reduce risk related to maintenance of anaesthetic agents.

Arrhythmia Evaluation in Wearable ECG Devices

This study evaluates four databases from PhysioNet: The American Heart Association database (AHADB), Creighton University Ventricular Tachyarrhythmia database (CUDB), MIT-BIH Arrhythmia database (MITDB), and MIT-BIH Noise Stress Test database (NSTDB). The ANSI/AAMI EC57:2012 is used for the evaluation of the algorithms for the supraventricular ectopic beat (SVEB), ventricular ectopic beat (VEB), atrial fibrillation (AF), and ventricular fibrillation (VF) via the evaluation of the sensitivity, positive predictivity and false positive rate. Sample entropy, fast Fourier transform (FFT), and multilayer perceptron neural network with backpropagation training algorithm are selected for the integrated detection algorithms. For this study, the result for SVEB has some improvements compared to a previous study that also utilized ANSI/AAMI EC57. In further, VEB sensitivity and positive predictivity gross evaluations have greater than 80%, except for the positive predictivity of the NSTDB database. For AF gross evaluation of MITDB database, the results show very good classification, excluding the episode sensitivity. In advanced, for VF gross evaluation, the episode sensitivity and positive predictivity for the AHADB, MITDB, and CUDB, have greater than 80%, except for MITDB episode positive predictivity, which is 75%. The achieved results show that the proposed integrated SVEB, VEB, AF, and VF detection algorithm has an accurate classification according to ANSI/AAMI EC57:2012. In conclusion, the proposed integrated detection algorithm can achieve good accuracy in comparison with other previous studies. Furthermore, more advanced algorithms and hardware devices should be performed in future for arrhythmia detection and evaluation.

A new MIMO ANFIS-PSO based NARMA-L2 controller for nonlinear dynamic systems

The proposal of this study is a new nonlinear autoregressive moving average, NARMA-L2 controller, which is based on an adaptive neuro-fuzzy inference system, ANFIS architecture. The new control configuration employs Sugeno-type fuzzy inference system FIS submodels to map input characteristics to the output of a dynamic and nonlinear system. The commonly used learning algorithm, which is called a hybrid method (Backpropagation and Least Square Error), has been carried out as well as particle swarm optimisation (PSO) approach, in order to select the optimal parameters of the ANFIS submodels. Once the system has been modelled efficiently and accurately, the proposed controller is designed by rearranging the generalised submodels. The controller performance is evaluated by simulations conducted on a binary distillation column, which is characterised by a nonlinear and dynamic behaviour. The obtained results show that the PSO-ANFIS based NARMA-L2 achieved more efficient modelling and control performances when compared with other controllers. These controllers include ANN-based NARMA-L2, (PD, PI and PID like) fuzzy-tuned by GA and PSO and traditional PID, which are also implemented to the column for comparison. Stability and robustness of the proposed controller regarding system inputs variance have also been tested by applying asynchronous setpoints of both inputs of the process.

Nonthermal Plasma System for Marine Diesel Engine Emission Control

A nonthermal plasma reactor (NTPR) using two 2.45-GHz microwave (MW) generators for the abatement of nitrogen oxides (NOx) and sulfur (SOx) contained in the exhaust gas of a 200-kW marine diesel engine was built and tested. Numerical analysis based on a nonthermal plasma kinetics model for the abatement of NOx and SOx from marine diesel engine exhaust gas was performed. A generic kinetic model that implements electron collisions and plasma chemistry has been developed for applications involving low-temperature (50-100 K) nonthermal plasma. Abatement efficiencies of NOx and SOx were investigated for a range of mean electron energies, which directly impact on the rate constants of electron collisions. The simulation was conducted using the expected composition of exhaust gas from a typical two-stroke, slow-speed marine diesel engine. The simulation results predict that mean electron energy of 0.25-3.2 eV gives abatement efficiency of 99% for NOx and SOx. The minimum residence time required was found to be 80 ns for the mean electron energy of 1 eV. Multimode cavity was designed using COMSOL multiphysics. The NTPR performance in terms of NOx and SOx removal was experimentally tested using the exhaust from a 2-kW lab scale, two-stroke diesel engine. The experimental results also show that the complete removal of NO is possible with the MW plasma (yellow color) generated. However, it was found that generating required MW plasma is a challenging task and requires further investigation.

Predicting Financial Time Series Data Using Hybrid Model

Prediction of financial time series is described as one of the most challenging tasks of time series prediction, due to its characteristics and their dynamic nature. Support vector regression (SVR), Support vector machine (SVM) and back propagation neural network (BPNN) are the most popular data mining techniques in prediction financial time series. In this paper a hybrid combination model is introduced to combine the three models and to be most beneficial of them all. Quantization factor is used in this paper for the first time to improve the single SVM and SVR prediction output. And also genetic algorithm (GA) used to determine the weights of the proposed model. FTSE100, S&P 500 and Nikkei 225 daily index closing prices are used to evaluate the proposed model performance. The proposed hybrid model numerical results shows the outperform result over all other single model, traditional simple average combiner and the traditional time series model Autoregressive (AR).

A hybrid intelligent approach for optimising software-defined networks performance

A new hybrid intelligent approach for optimising the performance of Software-Defined Networks (SDN), based on heuristic optimisation methods integrated with neural network paradigm, is presented. Evolutionary Optimisation techniques, such as Particle Swarm Optimisation (PSO) and Genetic Algorithms (GA), are employed to find the best set of inputs that give the maximum performance of an SDN. The Neural Network model is trained and applied as an approximator of SDN behaviour. An analytical investigation has been conducted to distinguish the optimal optimisation approach based on SDN performance as an objective function as well as the computational time. After getting the general model of the Neural Network through testing it with unseen data, this model has been implemented with PSO and GA to find the best performance of SDN. The PSO approach combined with SDN, represented by ANN, is identified as a comparatively better configuration regarding its performance index as well as its computational efficiency.

Electroencephalogram Similarity Analysis Using Temporal and Spectral Dynamics Analysis for Propofol and Desflurane Induced Unconsciousness

Important information about the state dynamics of the brain during anesthesia is unraveled by Electroencephalogram (EEG) approaches. Patterns that are observed through EEG related to neural circuit mechanism under different molecular targets dependent anesthetics have recently attracted much attention. Propofol, a Gamma-amino butyric acid, is known with evidently increasing alpha oscillation. Desflurane shares the same receptor action and should be similar to propofol. To explore their dynamics, EEG under routine surgery level anesthetic depth is analyzed using multitaper spectral method from two groups: propofol (n = 28) and desflurane (n = 23). The time-varying spectrum comparison was undertaken to characterize their properties. Results show that both of the agents are dominated by slow and alpha waves. Especially, for increased alpha band feature, propofol unconsciousness shows maximum power at about 10 Hz (mean ± SD; frequency: 10.2 ± 1.4 Hz; peak power, −14.0 ± 1.6 dB), while it is approximate about 8 Hz (mean ± SD; frequency: 8.3 ± 1.3 Hz; peak power, −13.8 ± 1.6 dB) for desflurane with significantly lower frequency-resolved spectra for this band. In addition, the mean power of propofol is much higher from alpha to gamma band, including slow oscillation than that of desflurane. The patterns might give us an EEG biomarker for specific anesthetic. This study suggests that both of the anesthetics exhibit similar spectral dynamics, which could provide insight into some common neural circuit mechanism. However, differences between them also indicate their uniqueness where relevant.

Ensemble Genetic Fuzzy Neuro Model Applied for the Emergency Medical Service via Unbalanced Data Evaluation

Equally partitioned data are essential for prediction. However, in some important cases, the data distribution is severely unbalanced. In this study, several algorithms are utilized to maximize the learning accuracy when dealing with a highly unbalanced dataset. A linguistic algorithm is applied to evaluate the input and output relationship, namely Fuzzy c-Means (FCM), which is applied as a clustering algorithm for the majority class to balance the minority class data from about 3 million cases. Each cluster is used to train several artificial neural network (ANN) models. Different techniques are applied to generate an ensemble genetic fuzzy neuro model (EGFNM) in order to select the models. The first ensemble technique, the intra-cluster EGFNM, works by evaluating the best combination from all the models generated by each cluster. Another ensemble technique is the inter-cluster model EGFNM, which is based on selecting the best model from each cluster. The accuracy of these techniques is evaluated using the receiver operating characteristic (ROC) via its area under the curve (AUC). Results show that the AUC of the unbalanced data is 0.67974. The random cluster and best ANN single model have AUCs of 0.7177 and 0.72806, respectively. For the ensemble evaluations, the intra-cluster and the inter-cluster EGFNMs produce 0.7293 and 0.73038, respectively. In conclusion, this study achieved improved results by performing the EGFNM method compared with the unbalanced training. This study concludes that selecting several best models will produce a better result compared with all models combined.

Improved spectrum analysis in EEG for measure of depth of anesthesia based on phase-rectified signal averaging

The definition of the depth of anesthesia (DOA) is still controversial and its measurement is not completely standardized in modern anesthesia. Power spectral analysis is an important method for feature detection in electroencephalogram (EEG) signals. Several spectral parameters derived from EEG have been proposed for measuring DOA in clinical applications. In the present paper, an improved method based on phase-rectified signal averaging (PRSA) is designed to improve the predictive accuracy of relative alpha and beta power, a frequency band power ratio, total power, median frequency (MF), spectral edge frequency 95 (SEF95), and spectral entropy for assessing anesthetic drug effects. Fifty-six patients undergoing general anesthesia in an operating theatre are studied. All EEG signals are continuously recorded from the awake state to the end of the recovery state and then filtered using multivariate empirical mode decomposition (MEMD). All parameters are evaluated using the commercial bispectral index (BIS) and expert assessment of conscious level (EACL), respectively. The ability to predict DOA is estimated using the area under the receiver-operator characteristics curve (AUC). All indicators based on the improved method can clearly discriminate the conscious state from the anesthetized state after filtration (pu2009u2009<u2009u20090.05). A significantly larger mean AUC (pu2009u2009<u2009u20090.05) shows that the improved method performs better than the conventional method to measure the DOA in most circumstances. Especially for raw EEG contaminated by artifacts, when the BIS index is used to indicate the consciousness level, the improvement is 7.37% (pu2009u2009<u2009u20090.05), 9.04% (pu2009u2009<u2009u20090.05), 18.46% (pu2009u2009<u2009u20090.05), 27.73% (pu2009u2009<u2009u20090.05), 14.65% (pu2009u2009<u2009u20090.05), 2.52%, 5.38% and 6.24% (pu2009u2009<u2009u20090.05) for relative alpha and beta power, power ratio, total power, MF, SEF, RE and SE, respectively. However, when the EACL is used to indicate the consciousness level, the improvement is 3.30% (pu2009u2009<u2009u20090.05), 16.69% (pu2009u2009<u2009u20090.05), 15.08% (pu2009u2009<u2009u20090.05), 34.83% (pu2009u2009<u2009u20090.05), 27.78% (pu2009u2009<u2009u20090.05), 5.89% (pu2009u2009<u2009u20090.05), 26.05% (pu2009u2009<u2009u20090.05) and 23.42% (pu2009u2009<u2009u20090.05). Spectral parameters derived from PRSA are more useful to measure the DOA in noisy cases.