No-Reference Video Quality Assessment using novel hybrid features and two-stage hybrid regression for score level fusion

This paper presents a novel No-Reference Video Quality Assessment (NR-VQA) model that utilizes proposed 3D steerable wavelet transform-based Natural Video Statistics (NVS) features as well as human perceptual features. Additionally, we proposed a novel two-stage regression scheme that significantly improves the overall performance of quality estimation. In the first stage, transform-based NVS and human perceptual features are separately passed through the proposed hybrid regression scheme: Support Vector Regression (SVR) followed by Polynomial curve fitting. The two visual quality scores predicted from the first stage are then used as features for the similar second stage. This predicts the final quality scores of distorted videos by achieving score level fusion. Extensive experiments were conducted using five authentic and four synthetic distortion databases. Experimental results demonstrate that the proposed method outperforms other published state-of-the-art benchmark methods on synthetic distortion databases and is among the top performers on authentic distortion databases. The source code is available at https://github.com/anishVNIT/two-stage-vqa.     

Classification of the cardiotocogram data for anticipation of fetal risks using machine learning techniques

The aim of the research is evaluating the classification performances of eight different machine-learning methods on the antepartum cardiotocography (CTG) data. The classification is necessary to predict newborn health, especially for the critical cases. Cardiotocography is used for assisting the obstetricians’ to obtain detailed information during the pregnancy as a technique of measuring fetal well-being, essentially in pregnant women having potential complications. The obstetricians describe CTG shortly as a continuous electronic record of the baby's heart rate took from the mother's abdomen. The acquired information is necessary to visualize unhealthiness of the embryo and gives an opportunity for early intervention prior to happening a permanent impairment to the embryo. The aim of the machine learning methods is by using attributes of data obtained from the uterine contraction (UC) and fetal heart rate (FHR) signals to classify as pathological or normal. The dataset contains 1831 instances with 21 attributes, examined by applying the methods. In the paper, the highest accuracy displayed as 99.2%.     

A new decomposition based evolutionary algorithm with uniform designs for many-objective optimization

For many-objective optimization problems, how to get a set of solutions with good convergence and diversity is a difficult and challenging work. In this paper, a new decomposition based evolutionary algorithm with uniform designs is proposed to achieve the goal. The proposed algorithm adopts the uniform design method to set the weight vectors which are uniformly distributed over the design space, and the size of the weight vectors neither increases nonlinearly with the number of objectives nor considers a formulaic setting. A crossover operator based on the uniform design method is constructed to enhance the search capacity of the proposed algorithm. Moreover, in order to improve the convergence performance of the algorithm, a sub-population strategy is used to optimize each sub-problem. Comparing with some efficient state-of-the-art algorithms, e.g., NSGAII-CE, MOEA/D and HypE, on six benchmark functions, the proposed algorithm is able to find a set of solutions with better diversity and convergence.     

Application of higher order spectral features and support vector machines for bearing faults classification

Condition monitoring and fault diagnosis of rolling element bearings timely and accurately are very important to ensure the reliability of rotating machinery. This paper presents a novel pattern classification approach for bearings diagnostics, which combines the higher order spectra analysis features and support vector machine classifier. The use of non-linear features motivated by the higher order spectra has been reported to be a promising approach to analyze the non-linear and non-Gaussian characteristics of the mechanical vibration signals. The vibration bi-spectrum (third order spectrum) patterns are extracted as the feature vectors presenting different bearing faults. The extracted bi-spectrum features are subjected to principal component analysis for dimensionality reduction. These principal components were fed to support vector machine to distinguish four kinds of bearing faults covering different levels of severity for each fault type, which were measured in the experimental test bench running under different working conditions. In order to find the optimal parameters for the multi-class support vector machine model, a grid-search method in combination with 10-fold cross-validation has been used. Based on the correct classification of bearing patterns in the test set, in each fold the performance measures are computed. The average of these performance measures is computed to report the overall performance of the support vector machine classifier. In addition, in fault detection problems, the performance of a detection algorithm usually depends on the trade-off between robustness and sensitivity. The sensitivity and robustness of the proposed method are explored by running a series of experiments. A receiver operating characteristic (ROC) curve made the results more convincing. The results indicated that the proposed method can reliably identify different fault patterns of rolling element bearings based on vibration signals.     

Improving the prediction of petroleum reservoir characterization with a stacked generalization ensemble model of support vector machines

The ensemble learning paradigm has proved to be relevant to solving most challenging industrial problems. Despite its successful application especially in the Bioinformatics, the petroleum industry has not benefited enough from the promises of this machine learning technology. The petroleum industry, with its persistent quest for high-performance predictive models, is in great need of this new learning methodology. A marginal improvement in the prediction indices of petroleum reservoir properties could have huge positive impact on the success of exploration, drilling and the overall reservoir management portfolio. Support vector machines (SVM) is one of the promising machine learning tools that have performed excellently well in most prediction problems. However, its performance is a function of the prudent choice of its tuning parameters most especially the regularization parameter, C. Reports have shown that this parameter has significant impact on the performance of SVM. Understandably, no specific value has been recommended for it. This paper proposes a stacked generalization ensemble model of SVM that incorporates different expert opinions on the optimal values of this parameter in the prediction of porosity and permeability of petroleum reservoirs using datasets from diverse geological formations. The performance of the proposed SVM ensemble was compared to that of conventional SVM technique, another SVM implemented with the bagging method, and Random Forest technique. The results showed that the proposed ensemble model, in most cases, outperformed the others with the highest correlation coefficient, and the lowest mean and absolute errors. The study indicated that there is a great potential for ensemble learning in petroleum reservoir characterization to improve the accuracy of reservoir properties predictions for more successful explorations and increased production of petroleum resources. The results also confirmed that ensemble models perform better than the conventional SVM implementation.     

Facial expression recognition of intercepted video sequences based on feature point movement trend and feature block texture variation

Facial Expression Recognition (FER) is an important subject of human–computer interaction and has long been a research area of great interest. Accurate Facial Expression Sequence Interception (FESI) and discriminative expression feature extraction are two enormous challenges for the video-based FER. This paper proposes a framework of FER for the intercepted video sequences by using feature point movement trend and feature block texture variation. Firstly, the feature points are marked by Active Appearance Model (AAM) and the most representative 24 of them are selected. Secondly, facial expression sequence is intercepted from the face video by determining two key frames whose emotional intensities are minimum and maximum, respectively. Thirdly, the trend curve which represents the Euclidean distance variations between any two selected feature points is fitted, and the slopes of specific points on the trend curve are calculated. Finally, combining Slope Set which is composed by the calculated slopes with the proposed Feature Block Texture Difference (FBTD) which refers to the texture variation of facial patch, the final expressional feature are formed and inputted to One-dimensional Convolution Neural Network (1DCNN) for FER. Five experiments are conducted in this research, and three average FER rates 95.2%, 96.5%, and 97% for Beihang University (BHU) facial expression database, MMI facial expression database, and the combination of two databases, respectively, have shown the significant advantages of the proposed method over the existing ones.     

A hybrid multiple feature construction approach for classification using Genetic Programming

The purpose of feature construction is to create new higher-level features from original ones. Genetic Programming (GP) was usually employed to perform feature construction tasks due to its flexible representation. Filter-based approach and wrapper-based approach are two commonly used feature construction approaches according to their different evaluation functions. In this paper, we propose a hybrid feature construction approach using genetic programming (Hybrid-GPFC) that combines filter’s fitness function and wrapper’s fitness function, and propose a multiple feature construction method that stores top excellent individuals during a single GP run. Experiments on ten datasets show that our proposed multiple feature construction method (Fcm) can achieve better (or equivalent) classification performance than the single feature construction method (Fcs), and our Hybrid-GPFC can obtain better classification performance than filter-based feature construction approaches (Filter-GPFC) and wrapper-based feature construction approaches (Wrapper-GPFC) in most cases. Further investigations on combinations of constructed features and original features show that constructed features augmented with original features do not improve the classification performance comparing with constructed features only. The comparisons with three state-of-art methods show that in majority of cases, our proposed hybrid multiple feature construction approach can achieve better classification performance.     

Benchmark value determination of energy efficiency indexes for coal-fired power units based on data mining methods

The operational optimisation of coal-fired power units is important for saving energy and reducing losses in the electric power industry. One of the key issues is how to determine the benchmark values of the energy efficiency indexes of the units. Therefore, a new framework for determining these benchmark values is proposed, based on data mining methods. First, the energy efficiency key performance indicators (KPIs) associated with the net coal consumption rate (NCCR) were selected based on the domain knowledge. Second, the decision-making samples with minimal NCCR were acquired with the fuzzy C-means (FCM) clustering algorithm, and the corresponding clustering centres were employed as the benchmark values. Finally, based on the support vector regression (SVR) algorithm, the target values of the NCCR were obtained with the KPIs as input, and the energy saving potential was evaluated by comparing the target values with the historical values of the NCCR. An actual on-duty 1000 MW unit was taken as study unit, and the results show that the energy saving potential is remarkable when the operators adjust the KPIs based on the calculated benchmark values.     

Using electroencephalogram to continuously discriminate feelings of personal thermal comfort between uncomfortably hot and comfortable environments

Thermal comfort is an important factor for the design of buildings. Although it has been well recognized that many physiological parameters are linked to the state of thermal comfort or discomfort of humans, how to use physiological signal to judge the state of thermal comfort has not been well studied. In this paper, the feasibility of continuously determining feelings of personal thermal comfort was discussed by using electroencephalogram (EEG) signals in private space. In the study, 22 subjects were exposed to thermally comfortable and uncomfortably hot environments, and their EEG signals were recorded. Spectral power features of the EEG signals were extracted, and an ensemble learning method using linear discriminant analysis or support vector machine as a sub-classifier was used to build the discriminant model. The results show that an average discriminate accuracy of 87.9% can be obtained within a detection window of 60 seconds. This study indicates that it is feasible to distinguish whether a person feels comfortable or too hot in their private space by multi-channel EEG signals without interruption and suggests possibility for further applications in neuroergonomics.     

PMU based voltage security assessment of power systems exploiting principal component analysis and decision trees

The need for feature selection and dimension reduction is felt as a fundamental step in security assessment of large power systems in which the number of features representing the state of power grids dramatically increases. These large amounts of attributes are not proper to be used for computational intelligence (CI) techniques as inputs, because it may lead to a time consuming procedure with insufficient results and they are not suitable for on-line purposes and updates.This paper proposes a combined method for an online voltage security assessment in which the dimension of the token data from phasor measurement units (PMUs) is reduced by principal component analysis (PCA). Then, the features with different stability indices are put into several categories and feature selection is done by correlation analysis in each category. These selected features are then given to decision trees (DTs) for classification and security assessment of power systems.The method is applied to 39-bus test system and a part of Iran power grid. It is seen from the results that the DTs with reduced data have simpler splitting rules, better performance in saving time, reasonable DT error and they are more suitable for constant updates.