Search

Background: Dealing with the high dimension of both neuroimaging data and genetic data is a difficult problem in the association of genetic data to neuroimaging. In this article, we tackle the latter problem with an eye toward developing solutions that are relevant for disease prediction. Supported by a vast literature on the predictive power of neural networks, our proposed solution uses neural networks to extract from neuroimaging data features that are relevant for predicting Alzheimer's Disease (AD) for subsequent relation to genetics. The neuroimaging-genetic pipeline we propose is comprised of image processing, neuroimaging feature extraction and genetic association steps. We present a neural network classifier for extracting neuroimaging features that are related with the disease. The proposed method is data-driven and requires no expert advice or a priori selection of regions of interest. We further propose a multivariate regression with priors specified in the Bayesian framework that allows for group sparsity at multiple levels including SNPs and genes. Results: We find the features extracted with our proposed method are better predictors of AD than features used previously in the literature suggesting that single nucleotide polymorphisms (SNPs) related to the features extracted by our proposed method are also more relevant for AD. Our neuroimaging-genetic pipeline lead to the identification of some overlapping and more importantly some different SNPs when compared to those identified with previously used features. Conclusions: The pipeline we propose combines machine learning and statistical methods to benefit from the strong predictive performance of blackbox models to extract relevant features while preserving the interpretation provided by Bayesian models for genetic association. Finally, we argue in favour of using automatic feature extraction, such as the method we propose, in addition to ROI or voxelwise analysis to find potentially novel disease-relevant SNPs that may not be detected when using ROIs or voxels alone. [ABSTRACT FROM AUTHOR]

Photovoltaic (PV) power forecasting is essential for the integration of renewable energy sources into the grid and for the optimisation of energy management systems. In this paper, we address the problem of probabilistic day-ahead forecasting of PV power generation for an operating plant with imperfect measurements and incomplete information. We compare four probabilistic forecasting methodologies: one physical irradiance-to-power method based on a model of the power plant and on weather forecasts, and four statistical methods based on quantile regression and classification techniques. We evaluate the performance of these methods in terms of deterministic and probabilistic accuracy, as well as the influence of the forecast horizon and the autoregressive component. The results show that statistical methods outperform the physical method, that conformalized quantile regression achieves the highest probabilistic accuracy, and that weather forecasts are more important than autoregressive predictors for the forecast procedure. To our knowledge, this is one of the first studies to compare different probabilistic forecasting approaches on the same case and provides information on the relative importance of the factors affecting the accuracy of the forecast. • Conformalized quantile regression attains superior probabilistic accuracy in tests. • Weather forecasts are pivotal for improved accuracy. • Statistical methods outperform a hybridised physical method in the test case. [ABSTRACT FROM AUTHOR]

The authors continued their research on the development of an intelligent automatic ships pilot containing a controller based on fuzzy logic. Its features are determined by the optimizer based on a genetic algorithm. It also contains a modular unit of neural network models of ship navigation paths, as well as a neural network classifier. This paper is devoted to the description of a neural network classifier designed to classify the movement patterns of marine vessels to identify the peculiarities of the ship depending on its type and sailing conditions. The introduction of such classifier to an autopilot allows for more precise consideration of multivariate and difficult to formalize factors affecting the vessel while operating, such as varying weather conditions, irregular waves, hydrodynamic characteristics of the vessel, draft, water under the keel, rate of the vessel sailing, etc. The article outlines the technique concerning the development of a neural network classifier and the results of its computer modelling on the example of a refrigerated transport vessel type. The authors used such methods for obtaining and processing findings as spectral estimation, machine learning methods, in particular, neural network technology and computer or simulation modelling. [ABSTRACT FROM AUTHOR]

Electrical impedance tomography (EIT) uses non-invasive and non-radiative imaging to detect inhomogeneous electrical properties in tissues. The inverse problem of EIT is a highly nonlinear, ill-posed problem, which causes inaccuracy in target size calculation. We propose a novel approach to discretize the target size and use a neural network (NN) classifier to classify the unknown size in discrete steps. The target size is discretized into distinct steps, and each step can be a unique class. The data is pre-processed with the cumulative distribution transform (CDT) to enhance distinguishability. First, the NN is trained with simulated datasets, divided into time difference (t-d) group and CDT group. After training, the NN classifier is tested by experimental data recorded in a phantom experiment. Linear discriminant analysis (LDA) is performed to assess the distinguishability of classes. There is a significant increase in distance between classes after the CDT pre-processing. The density of the classes has an upward trend with a higher degree of clustering after CDT pre-processing. The CDT data clustering into distinguishable classes is essential to excellent NN classification results. Such an approach is a significant paradigm shift by turning the cumbersome inverse calculation with uncertain accuracy into a classification problem with predetermined step errors. The accuracy and resolution can be further extended by increasing the discretization steps. [ABSTRACT FROM AUTHOR]

Imaging modalities play a major role in early detection and diagnosis of various medical conditions related to the patient. Retinal image segmentation has been taken up for investigation in this research paper to efficiently detect the presence of eye disorder which could be indicators of major onset of conditions like hypertension, cataracts, diabetic retinopathy, age-related macular disorders, etc. A machine learning method for classification of given pixels in the search space into regions containing blood vessels and those that do not contain blood vessels is implemented using a three-stage neural classifier in this paper. Prior to classification, an optimization algorithm namely ant colony optimization derived from nature-inspired phenomena is used to provide an optimal feature vector set to set high standards for the neural network based classification approach. The novelty and merits of the paper lie in back tracing of the segmentation process in which optimization is done first on the preprocessed features followed by classification for segmented output on the optimized features. This results in elimination of redundant feature vectors which tend to occupy much memory as well increase the computational overhead on the process. The entire implemented system is automated by the machine learning process and tested on 30 samples, 15 each on DRIVE and STARE databases. Classification rates of nearly 98% on an average scenario have been achieved for segmentation and 96.5% for abnormality detection. The performances have been compared against Bayesian set models and standalone ANN models. [ABSTRACT FROM AUTHOR]

Exploration (factor, cluster, and decision tree), regression (multiple linear regression), and neural network (regression, classification) models of clustering, approximation and prediction of the stability constants of cation complexes with ionophore antibiotics (nonactin, monactin, dinactin, trinactin, ennatin B, monensin A, and valinomycin) according to the properties of organic solvents (methanol, ethanol, acetonitrile, and nitrobenzene) and cations (Li+, Na+, K+, Rb+, Cs+, Tl+, Ag+, NH4+, Mg2+, Ca2+, Sr2+, Ba2+, and Mn2+) have been developed. It has been shown that neural network performance is better than that of multiple linear regression (the correlation coefficient on the training sample 0.756 compared to 0.697). The neural network classifier and the classification tree has confirmed the clustering of stability of ionophore–cation complexes carried out by the exploratory k-means method by 97.2%. The prognostic capabilities of the constructed multilayer perceptron have been demonstrated. [ABSTRACT FROM AUTHOR]

Stress relaxation plays an important role in the design of underground stopes. The aim of this paper is to assess the stope stability in connection with the stress relaxation using a classification approach. Three types of stress relaxation were clearly defined, namely partial relaxation, tangential relaxation and full relaxation. A neural network classifier was implemented to assess the stability of the stopes on the basis of case histories of stope performances. The results of the classification were compared to existing empirical methods of quantifying the stress relaxation. Overall, the present study shows higher classification accuracies, especially when the stress relaxation was considered. The results suggested that the relaxation type can be a good predictor of stability. Relaxed stope (full and tangential stress relaxation) cases are the most critical in the sense that lower accuracies were obtained and the probability of correct classification is rather erratic. [ABSTRACT FROM AUTHOR]

An ability to categorise and recognise a spoken language is an essential task in a multi-lingual society like India. Language identification (LID) is the process of identifying the language spoken by some unknown speaker using a given speech sample. In this article, textural descriptors extracted from spectrogram image and evolutionary feature selection is presented for Indian language identification. Language-specific long-term cues and prosodic information present in various frequency zones of the spectrogram image can efficiently modelled using textural descriptors. Firstly, an input audio sample is converted into a spectrogram visual representation which characterises the band of frequencies of a signal with respect to time. Then, completed local binary pattern (CLBP), local binary pattern histogram Fourier (LBPHF) and discrete Wavelet transform based texture descriptors are used to extract the features from the spectrogram image. Later, using grey wolf optimiser (GWO) feature selection, irrelevant and redundant features are removed, and only optimal features are selected from the dataset. GWO-based feature selection supports to construct the classification model with optimal features and the performance of the classifier is optimised. Finally, using the artificial neural network classifier and Indic-TTS database 96.9659% accuracy was obtained. [ABSTRACT FROM AUTHOR]

Models of multiple linear regression and multilayer artificial neural network have been developed for modeling and predicting the stability constants of sodium and potassium coronates basing on the properties of aqueous-organic solvents (water-methanol, water-propan-2-ol, water-acetonitrile, and water-acetone). The values of the coronates stability constants in water-ethanol solvents have been predicted, and the predictions of the models of multiple linear regression and an artificial neural network models have been compared. The contributions of electrostatic, cohesive, and electron-donating interactions to the increase in the stability of the coronates have been quantitatively assessed basing on the models of multiple linear regression and the principle of free energies linearity. Neural network models based on unsupervised (multilayer perceptrons) and supervised (Kohonen networks) learning algorithms have been developed to classify the stability of sodium and potassium coronates. The neural network classifiers have fully confirmed the classification of the coronated stability via the k-means exploration method. [ABSTRACT FROM AUTHOR]

A method for cloud detection using the machine-learning algorithm based on a convolutional neural network is presented. Input data are satellite images received from the MSU-MR multispectral low-resolution scanning unit onboard the Meteor-M No. 2 satellite. The developed method can be an alternative to the traditional algorithms of cloud detection based on the calculation of differential indices and thresholds. The algorithm is verified using the machine-learning metrics, comparing the resulting cloud mask with the reference one obtained by interpreting the satellite image by an experienced meteorologist. It was also compared (for verification) with a similar product based on VIIRS spectroradiometer data. The cloud mask computed using the algorithm allows the automatic thematic processing of satellite images. [ABSTRACT FROM AUTHOR]

In recent years, face recognition has rapidly developed in the field of smartphones and control systems. It has been used to unlock the telephone and face-payment applications. With such rapid development, more and more demands are placed on the security of face recognition. However, face biometric-based recognition technologies are still vulnerable to spoofing attacks. Thus, developing robust and reliable antispoofing attack detection is critical to guarantee the security of facial analysis-based authentication. As deep learning techniques have achieved satisfactory performances in computer vision, they can also be employed to face spoofing detection. We present a multichannel linear local binary pattern optimization algorithm, which combines with Lucas–Kanade optical flow algorithm. The extracted facial features are fused and sent to a deep belief network classifier for classification and learning, and finally tested on the MSU-mobile facial spoofing database. Compared with existing deep leaning-based detection methods, our face spoofing detection algorithm has better scalability and robustness. To evaluate the performance of the proposed algorithm, the experiments are conducted on three crossed standard spoofing databases and excellent performance is also achieved. [ABSTRACT FROM AUTHOR]

Machine learning-guided optical proximity correction, called ML-OPC in this paper, has recently been proposed to alleviate long runtime of model-based OPC. ML-OPC using regression methods has been presented but with limited prediction accuracy. We propose neural network classifier-based OPC (NNC-OPC), in which a neural network classifier serves as a mask bias model. A few techniques are applied to enhance basic NNC-OPC: parameterization of layout segments using polar Fourier transform signals, dimensionality reduction through weighted principal component analysis, and sampling of training layout segments. Training segments are typically imbalanced over the range of mask biases, which may cause large prediction error for segments that appear less frequently. This is resolved by three techniques: 1) synthetic data generation; 2) class reorganization; and 3) an adaptive learning rate. Experiments with NNC-OPC with all techniques applied indicate that prediction error of mask bias and training time are reduced by 29% and 80%, respectively, compared to state-of-the-art ML-OPC with regression methods. [ABSTRACT FROM AUTHOR]

Highlights • Robust multi-parametric NCO-tracking controllers do not entail a discretization of the continuous-time dynamics. • The robust-counterpart multi-parametric dynamic optimization (mp-DO) problem retains the same complexity as nominal mp-DO. • Data classifiers based on deep learning can accurately describe the critical regions in (nominal or robust) mp-DO. • The methodology is demonstrated for a fluid catalytic cracking (FCC) unit and a chemical reactor cascade. Abstract This paper presents an extension of the recent multi-parametric (mp-)NCO-tracking methodology by Sun et al. [Comput. Chem. Eng. 92 (2016) 64–77] for the design of robust multi-parametric controllers for constrained continuous-time linear systems in the presence of uncertainty. We propose a robust-counterpart formulation and solution of multi-parametric dynamic optimization (mp-DO), whereby the constraints are backed-off based on a worst-case propagation of the uncertainty using either interval analysis or ellipsoidal calculus and an ancillary linear state feedback. We address the case of additive uncertainty, and we discuss approaches to dealing with multiplicative uncertainty that retain tractability of the mp-NCO-tracking design problem, subject to extra conservativeness. In order to assist with the implementation of these controllers, we also investigate the use of data classifiers based on deep learning for approximating the critical regions in continuous-time mp-DO problems, and subsequently searching for a critical region during on-line execution. We illustrate these developments with the case studies of a fluid catalytic cracking (FCC) unit and a chemical reactor cascade. [ABSTRACT FROM AUTHOR]

A new simulation and processing methodology based on open source tools to produce high fidelity synthetic aperture radar (SAR) simulations of ground vehicles of varying types, as well as analysis of an applied automatic target recognition (ATR) technique is presented in this Letter. This work is based around the RaySAR open‐source model and the outputs have been configured for both monostatic and bistatic geometries. Input CAD models of various military and civilian vehicles are used to produce the SAR imagery. This output imagery was then used to train a tiny you only look once convolutional neural network (CNN) classifier. The classification success of the CNN applied was showed to produce significantly accurate results and the whole pipeline of processing enabled rapid evaluation of potential ATR methods against targets of choice. [ABSTRACT FROM AUTHOR]

The nearest neighbor partitioning (NNP) method is a high performance approach which is used for improving traditional neural network classifiers. However, the construction process of NNP model is very time-consuming, particularly for large data sets, thus limiting its range of application. In this study, a parallel NNP method is proposed to accelerate NNP based on Compute Unified Device Architecture(CUDA). In this method, blocks and threads are used to evaluate potential neural networks and to perform parallel subtasks, respectively. Experimental results manifest that the proposed parallel method improves performance of NNP neural network classifier. Furthermore, the application of parallel NNP in performance evaluation of cement microstructure indicates that the proposed approach has favorable performance. [ABSTRACT FROM AUTHOR]

Background and objective Myocardial Infarction (MI) is one of the most frequent diseases, and can also cause demise, disability and monetary loss in patients who suffer from cardiovascular disorder. Diagnostic methods of this ailment by physicians are typically invasive, even though they do not fulfill the required detection accuracy. Methods Recent feature extraction methods, for example, Auto Regressive (AR) modelling; Magnitude Squared Coherence (MSC); Wavelet Coherence (WTC) using Physionet database, yielded a collection of huge feature set. A large number of these features may be inconsequential containing some excess and non-discriminative components that present excess burden in computation and loss of execution performance. So Hybrid Firefly and Particle Swarm Optimization (FFPSO) is directly used to optimise the raw ECG signal instead of extracting features using the above feature extraction techniques. Results Provided results in this paper show that, for the detection of MI class, the FFPSO algorithm with ANN gives 99.3% accuracy, sensitivity of 99.97%, and specificity of 98.7% on MIT-BIH database by including NSR database also. Conclusions The proposed approach has shown that methods that are based on the feature optimization of the ECG signals are the perfect to diagnosis the condition of the heart patients. [ABSTRACT FROM AUTHOR]

This work introduces an optimized wavelet designed by fractionally delaying the coefficients of the unit delay filter. The wavelets produced by optimized fractionally delayed filter coefficients are named as fraclets. Fraclet has been utilized in the real-time power quality events' detection and classification which has been hitherto addressed with the help of unit delay filters. Normal signal, voltage sag, swell, harmonics, sag with harmonics, swell with harmonics, sag and swell with harmonics, and sag and swell with interruption are considered in this work to validate the performance of proposed algorithm based on fraclet. Along with real-time generation of various power quality events with TMS320C6748 DSP board, different events have also been simulated by using parametric equations. The upper hand of fraclets over wavelets has been highlighted by maximally flat frequency response of fraclets. Moreover, fraclets facilitate better multiresolution analysis by providing low energy compaction ratio (ECR). Further, 11 characteristic features have also been extracted from each decomposition level of PQ signal up to fifth level and fed to the modified probabilistic neural network (MPNN) for validating the proposed power quality event detection and classification algorithm. MPNN has outperformed the support vector machine (SVM), both with fraclet and wavelet. The proposed algorithm relying on fraclets has shown better results as compared with wavelet. [ABSTRACT FROM AUTHOR]

In this study, a framework to super resolve and recognise the long range captured iris polar images is proposed. The proposed framework consists of best frame selection algorithm, modified diamond search algorithm, Gaussian process regression (GPR) based and enhanced iterated back projection (EIBP)‐based super‐resolution approach, fuzzy entropy‐based feature selector and neural network (NN) classifier. The framework uses linear kernel co‐variance function in local patch‐based GPR and EIBP algorithms and it super resolves the iris images depending on the contents of the patches, without an external dataset. NN classifier classifies the iris images by using features extracted using discrete cosine transform domain based no‐reference image quality assessment model, Gray level co‐occurrence matrix, Hu seven moments and statistical features. The framework is tested using CASIA long range iris database by comparing and analysing the peak signal‐to‐noise ratio, structural similarity index matrix and visual information fidelity in pixel domain of proposed algorithms with Yang and Nguyen framework. The results demonstrate that the proposed framework is well suited for recognition of iris images captured at a long distance. [ABSTRACT FROM AUTHOR]

Objective: By modeling the cochlear implant (CI) electrode-to-nerve interface and quantifying electrode discriminability in the model, we address the questions of how many individual channels can be distinguished by CI recipients and the extent to which performance might be improved by inserting electrodes deeper into the cochlea. Method: We adapt an artificial neural network to model electrode discrimination as well as a commonly used psychophysical measure (four-interval forced-choice) in CI stimulation and predict how well the locations of the stimulating electrodes can be inferred from simulated auditory nerve spiking patterns. Results: We show that a longer electrode leads to better electrode place discrimination in our model. For a simulated four-interval forced-choice procedure, correct classification rates significantly reduce with decreasing distance between the test electrodes and the reference electrodes, and higher correct classification rates may be achieved by the basal electrodes than apical electrodes. Conclusion: Our results suggest that enhanced electrode discriminability results from a longer CI electrode array, and the locations where the errors occur along the electrode array are not only affected by the distance between electrodes but also the twirling angle between electrodes. Significance: Our models and simulations provide theoretical insights into several important clinically relevant problems that will inform future designs of CI electrode arrays and stimulation strategies. [ABSTRACT FROM AUTHOR]

Predictive correlation-regression and neural network models for description of the properties of aqueous-organic solvents on the strength of acetic and benzoic acids have been developed. Significant descriptors affecting the dissociation equilibrium of the acids have been found. The features of the solvation (reflected in the electrostatic, cohesion, and electron accepting interactions) on the acids strength have been disclosed. Prediction of the dissociation constants of acetic and benzoic acids has been successfully performed using a three-layer perceptron. Prospects of the neural network modeling for prediction of organic acids strength in aqueous-organic media have been demonstrated. A neural network classifier of acetic and benzoic acids strength based on the aqueous-alcoholic solvents descriptors has been developed and trained. [ABSTRACT FROM AUTHOR]

In this study, a framework to super resolve and recognise the long range captured iris polar images is proposed. The proposed framework consists of best frame selection algorithm, modified diamond search algorithm, Gaussian process regression (GPR) based and enhanced iterated back projection (EIBP)‐based super‐resolution approach, fuzzy entropy‐based feature selector and neural network (NN) classifier. The framework uses linear kernel co‐variance function in local patch‐based GPR and EIBP algorithms and it super resolves the iris images depending on the contents of the patches, without an external dataset. NN classifier classifies the iris images by using features extracted using discrete cosine transform domain based no‐reference image quality assessment model, Gray level co‐occurrence matrix, Hu seven moments and statistical features. The framework is tested using CASIA long range iris database by comparing and analysing the peak signal‐to‐noise ratio, structural similarity index matrix and visual information fidelity in pixel domain of proposed algorithms with Yang and Nguyen framework. The results demonstrate that the proposed framework is well suited for recognition of iris images captured at a long distance. [ABSTRACT FROM AUTHOR]

High resolution digital cameras and state-of-the-art image editing software tools has given rise to large amount of manipulated images leaving no traces of being subjected to any manipulation. Passive or blind forgery detection algorithms are used in order to determine its authenticity. In this paper, an algorithm is proposed that blindly detects global rescaling operation using the statistical models computed based on quadrature mirror filter (QMF) decomposition. Fuzzy entropy measure is employed to choose the relevant features and to remove non-important features whereas artificial neural network classifier is used for forgery detection. Experimental results are presented on grayscale and -component images of UCID database to prove the validity of the algorithm under different interpolation schemes. Results are provided for the detection of rescaled images with JPEG compression, arbitrary cropping and white Gaussian noise addition. Further, results are shown using USC-SIPI database to prove the robustness of the algorithm against the type of database. [ABSTRACT FROM AUTHOR]

This paper presents a novel coarse to fine moving object segmentation framework for H.264/AVC compressed videos. The proposed framework integrates the global motion estimation and global motion compensation steps in the segmentation pipeline unlike previous techniques which did not consider such an integration. The integration is based on testing for presence of global motion by classifying the interframe motion vectors into moving camera class and still camera class. The decision boundary separating these two classes is learnt from the training video data. The integration automates the moving object segmentation to be applicable for static, moving and combination of static/moving camera cases which to the best of our knowledge has not been carried out earlier. Further, a novel coarse segmentation technique is proposed by decomposing the inter-frame motion vectors into wavelet sub-bands and utilizing logical operations on LH, HL and HH sub-band wavelet coefficients. The premise is based on the fact that since the LH, HL and HH sub-bands contain the detail information pertaining to horizontal, vertical and diagonal moving blocks respectively, they can be exploited to identify the coarse moving boundaries. The coarse segmentation is fast in comparison to state-of-the-art coarse segmentation methods as demonstrated by our experiments. Finally, these coarse boundaries are modeled in an energy minimization framework and shown that by minimizing the energy using graph cut optimization the segmentation is refined to obtain the fine segmentation. The proposed framework is tested on a number of standard video sequences encoded with H.264/AVC JM encoder and comparison is carried out with state-of-the-art compressed domain moving object segmentation methods as well as with an existing state-of-the-art pixel domain method to establish and validate the proposed moving object segmentation framework. [ABSTRACT FROM AUTHOR]

In current decades, various Evolutionary Algorithms(EAs) raise as well as many kinds of benchmarks are popular in evaluations of EAs׳ performances. Since there exists randomness in EAs׳ performances, the evaluations are made by a large number of runs in simulations or experiments in order to present a relatively fair comparison. However, there still exit several problems that have not been well explained. Does it make sense to deem two algorithms have equal ability if they have same final results? Is it convinced to decide winners or losers in comparisons just by tiny difference in performances? Besides the final results, how to compare algorithms׳ performances during the optimization iterations? In this paper, a neural network classifier based on extreme learning machine (ELM) is proposed to solve these problems. A novel role of classifier is first proposed to convince the differences between algorithms. If the classifier succeeds to classify algorithms based on their performances recorded in all generations, we deem the two algorithms have so convinced difference that comparisons of two algorithms can reflect algorithms׳ disparity. Therefore, the conclusions to judge the two algorithms are feasible and acceptable. Otherwise, if classifiers cannot distinguish two algorithms, we deem the two have similar performances so that it is meaningless to differ two algorithms just by tiny differences. By employing a set of classical benchmarks and six EAs, the simulations and computations are conducted. According to the analysis results, the proposed classifier can provide more information to reflect true abilities of algorithms, which is a novel view to compare EAs. [ABSTRACT FROM AUTHOR]

A method to infer the terrain of unobserved fields as well as navigation paths using vibrations from vehicle–terrain interactions is presented. The relationships between adjacent terrain grids and robot paths are modelled by Markov random field (MRF) for inferring the classes of unobserved field. In order to approximate the complex likelihood of vibration features as a tractable distribution, a variational auto‐encoder is adopted. By projecting intractable features to the latent space, an approximated likelihood that gives similar performance to a neural network classifier is obtained. Then the numerical maximum a posterior inference for MRF is obtained. The result of inferred terrain maps are compared with that from the feature likelihood as a Gaussian‐mixture model. [ABSTRACT FROM AUTHOR]

For a class of discrete‐time multi‐variable systems with time‐varying parametric uncertainty, the parameter identification method and switching control architecture are developed in this study to implement smooth switching control. Specifically, the identification algorithm based on the least geometric mean squares is derived for the multi‐variable system. In addition, the switching control system, with model reference control technique as the basis of control design for each local model, is proposed to achieve satisfactory control performance, especially to eliminate the oscillations at the switching boundaries which can be attributed to the difference in the input–output dynamics between the pre‐ and post‐switching closed‐loop subsystems. Furthermore, the switching strategy based on neural network classifier is put forward for the accurate switching among a set of model reference controllers which are correspondingly designed for the identified subsystems. Finally, the feasibility and effectiveness of the proposed identification and control schemes are verified by numerical simulations, which show that the desirable identification and control performances are guaranteed under the proposed schemes. Moreover, the advantage of the presented switching control system in terms of smooth switching is validated through comparison with other kinds of control schemes. [ABSTRACT FROM AUTHOR]

Gesture is one of the fundamental ways of human machine natural interaction. To understand gesture, the system should be able to interpret 3D movements of human. This paper presents a computer vision-based real-time 3D gesture recognition system using depth image which tracks 3D joint position of head, neck, shoulder, arms, hands and legs. This tracking is done by Kinect motion sensor with OpenNI API and 3D motion gesture is recognized using the movement trajectory of those joints. User to Kinect sensor distance is adapted using proposed center of gravity (COG) correction method and 3D joint position is normalized using proposed joint position normalization method. For gesture learning and recognition, data mining classification algorithms such as Naive Bayes and neural network is used. The system is trained to recognize 12 gestures used by umpires in a cricket match. It is trained and tested using about 2000 training instances for 12 gesture of 15 persons. The system is tested using 5-fold cross validation method and achieved 98.11% accuracy with neural network and 88.84% accuracy with Naive Bayes classification method. [ABSTRACT FROM AUTHOR]

This paper develops a primitive gas recognition system for discriminating between industrial gas species. The system under investigation consists of an array of eight micro-hotplate-based SnO2 thin film gas sensors with different selectivity patterns. The output signals are processed through a signal conditioning and analyzing system. These signals feed a decision-making classifier, which is obtained via a Field Programmable Gate Array (FPGA) with Very High-Speed Integrated Circuit Hardware Description Language. The classifier relies on a multilayer neural network based on a back propagation algorithm with one hidden layer of four neurons and eight neurons at the input and five neurons at the output. The neural network designed after implementation consists of twenty thousand gates. The achieved experimental results seem to show the effectiveness of the proposed classifier, which can discriminate between five industrial gases. [ABSTRACT FROM AUTHOR]

Abstract: Present study proposes a computer-aided diagnostic system to assist radiologists in identifying focal liver lesions in B-mode ultrasound images. The proposed system can be used to discriminate focal liver diseases such as Cyst, Hemangioma, Hepatocellular carcinoma and Metastases, along with Normal liver. The study is performed with 111 real ultrasound images comprising of 65 typical and 46 atypical images, which were taken from 88 subjects. These images are first enhanced and then regions of interest are segmented into 800 non-overlapping segmented regions-of-interest. Subsequently 208-texture based features are extracted from each segmented region-of-interest. A two step neural network classifier is designed for classification of five liver image categories. In the first step, a neural network classifier gives classification among five liver image categories. If neural network decision is for more than one class as obtained from the first step, binary neural network classifiers are used in the second step for crisp classification between two classes. Test results of two-step neural network classifier showed correct decisions of 432 out of 500 segmented regions-of-interest in test set with classification accuracy of 86.4%. The classifier has given correct diagnosis of 90.3% (308/340) in the tested segmented regions-of-interest from typical cases and 77.5% (124/160) in tested segmented regions-of-interest from atypical cases. [Copyright &y& Elsevier]

Abstract: This work presents an eddy-current testing system based on a giant magnetoresistive (GMR) sensing device. Non-destructive tests in aluminum plates are applied in order to extract information about possible defects: cracks, holes and other mechanical damages. Eddy-current testing (ECT) presents major benefits such as low cost, high checking speed, robustness and high sensitivity to large classes of defects. Coil based architecture probes or coil-magnetoresistive probes are usually used in ECT. In our application the GMR sensor is used to detect a magnetic field component parallel to a plate surface, when an excitation field perpendicular to the plate is imposed. A neural network processing architecture, including a multilayer perceptron and a competitive neural network, is used to classify defects using the output amplitude of the eddy-current probe (ECP) and its operation frequency. The crack detection, classification and estimation of the geometrical characteristics, for different classes of defects, are described in the paper. [ABSTRACT FROM AUTHOR]

Abstract: In this paper, we present a new method for the automated detection of sperm whale regular clicks and creaks based on statistical computations. In the first stage, a spectrogram is computed from the input waveform, followed by a noise normalisation process. A frequency domain filter is then applied, and the energy accumulated in each time frame is calculated. Two-second time-windows are then classified as containing either regular clicks, creaks, or noise based on statistical parameters using a neural network classifier. Finally, previously obtained statistical parameters are used to implement an energy-based detection criterion for the classified time-windows. Individual regular clicks and creaks are isolated by linking contiguous detected time frames. The proposed method was tested on five recordings of sperm whale sounds. Comparison of the detection performances to hand-labelled regular clicks and creaks revealed that this method outperforms two recently reported waveform-based methods when working with the same recordings files. An average percentage of detection of 86.97% was attained for the set of files. This method consumes also little computation time. [Copyright &y& Elsevier]

This paper presents a novel biologically-inspired and wavelet-based model for extracting features of faces from face images. The biological knowledge about the distribution of light receptors, cones and rods, over the surface of the retina, and the way they are associated with the nerve ends for pattern vision forms the basis for the design of this model. A combination of classical wavelet decomposition and wavelet packet decomposition is used for simulating the functional model of cones and rods in pattern vision. The paper also describes the experiments performed for face recognition using the features extracted on the AT & T face database (formerly, ORL face database) containing 400 face images of 40 different individuals. In the recognition stage, we used the Artificial Neural Network Classifier. A feature vector of size 40 is formed for face images of each person and recognition accuracy is computed using the ANN classifier. Overall recognition accuracy obtained for the AT & T face database is 95.5%. [ABSTRACT FROM AUTHOR]

Abstract: A novel supervised neural network-based algorithm is designed to reliably distinguish in electrocardiographic (ECG) records between normal and ischemic beats of the same patient. The basic idea behind this paper is to consider an ECG digital recording of two consecutive R-wave segments (RRR interval) as a noisy sample of an underlying function to be approximated by a fixed number of Radial Basis Functions (RBF). The linear expansion coefficients of the RRR interval represent the input signal of a feed-forward neural network which classifies a single beat as normal or ischemic. The system has been evaluated using several patient records taken from the European ST-T database. Experimental results show that the proposed beat classifier is very reliable, and that it may be a useful practical tool for the automatic detection of ischemic episodes. [Copyright &y& Elsevier]

Machine Learning (ML) methodologies have become a worthy choice for X-ray screening. X-ray imaging is a method used for the identification of bone fractures. But every so often, the dimensions and locations of a fracture are detected incorrectly. Therefore, this paper aims to design a system that would accurately detect and classify fractured and non-fractured bone images. This proposed system comprises four principal phases. The first is the image acquisition phase, in which few input images are acquired from the X-ray machine, and few input images are collected from the imaging centre. The second is a pre-processing phase to see their informative areas like location, edges and shape. So, the wavelet transform method helps to compress the images to store and remove noises. The third is the feature extracting phase; the Harris corner detection technique is used to locate the broken points as corner features and intensifies the quality of the X-ray images. Before applying the Harris corner algorithm, the image sharpening method was used. Then images are equipped to be fed into a fourth phase, i.e. classification phase; two techniques are used in this phase: Support Vector Machine (SVM) and Error Backpropagation Neural Network (EBP-NN). Classification by SVM and EBP-NN both methods are tested on various fractured and non-fractured bone images. Finally, found that classification done by the SVM technique is more accurate than EBP-NN. The classification by the SVM approach has higher efficiency and a higher classification rate of 94%, which is 2% more than the EBP-NN technique. [ABSTRACT FROM AUTHOR]

Abstract: In this paper, we propose a new recursive classifier based on a recurrent neural network. A supervised algorithm is employed to estimate the classifier parameters. The proposed classifier is used to form a non-linear Decision Feedback Equalizer (DFE) for communication channels. A new procedure allowing the estimation of the decision delay is also presented so that the classifier parameters and the decision delay are estimated at the same time. This new DFE leads to suitable equalization performances even in presence of non-linear and non–minimum phase channels. [Copyright &y& Elsevier]

Classification of harvested apples when predicting their storage potential is an important task. This paper describes how chlorophyll a fluorescence images taken in blue light through a red filter, can be used to classify apples. In such an image, fluorescence appears as a relatively homogenous area broken by a number of small nonfluorescing spots, corresponding to normal corky tissue patches, lenticells, and to damaged areas that lower the quality of the apple. The damaged regions appear more longish, curved or boat-shaped compared to the roundish, regular lenticells. We propose an apple classification method that employs a hierarchy of two neural networks. The first network classifies each spot according to geometrical criteria and the second network uses this information together with global attributes to classify the apple. The system reached 95% accuracy using a test material classified by an expert for "bad" and "good" apples. [ABSTRACT FROM AUTHOR]

• The root cause analysis (RCA) is fundamental for transformers' diagnosis. • This paper proposes a methodology for to RCA with Machine learning. • High correlation is achieved with Machine learning techniques. • A case study is implemented with 868 data sets. The root cause analysis, diagnosis and classification of faults in power transformers with high accuracy and efficiency is the fundamental key to ensure reliability and power quality with least interruptions. In this research, a new proposal was developed for an intelligent Genetic Algorithm tuned artificial neural network (ANN) classifier for transformer faults for to improve the root cause analysis, in this case, this new proposal is able to segregate all fault types using Dissolved Gas Analysis (DGA) samples from power transformers of a large range of providers and from other research papers, these input data have been pre-processed using the Fast Decision tree learner (FDTL), tree learner advanced, and M5 Rule (M5R) algorithm and NN. We replace the conventional action selection procedure of Reinforcement Learning (RL) by a machine learning based optimizer. In this research, a new proposal for computationally least expensive in comparison to other approaches is presented. Our proposed classifier could serve as an important tool in ensuring healthy operation of power transformers, the correlation is higher than 0.98 with tree learner classifier, with a validation of the over-fitting perspective. [ABSTRACT FROM AUTHOR]

Abstract: An integral part of the Comprehensive Nuclear-Test-Ban Treaty (CTBT) International Monitoring System is an infrasound-monitoring network. This network has the capability to detect and verify infrasonic signals-of-interest (SOI), e.g., nuclear explosions, from other unwanted infrasound noise sources. This paper presents classification results of infrasonic events using parallel neural network classification banks (PNNCB). The PNNCB presented are structured by parallelization of classical neural networks. The PNNCB algorithm has capability of multiple events classification and show enhanced overall classification performance. [Copyright &y& Elsevier]