Change point detection for compositional multivariate data

Change point detection algorithms have numerous applications in areas of medical condition monitoring, fault detection in industrial processes, human activity analysis, climate change detection, and speech recognition. We consider the problem of change point detection on compositional multivariate data (each sample is a probability mass function), which is a practically important sub-class of general multivariate data. While the problem of change-point detection is well studied in univariate setting, and there are few viable implementations for a general multivariate data, the existing methods do not perform well on compositional data. In this paper, we propose a parametric approach for change point detection in compositional data. Moreover, using simple transformations on data, we extend our approach to handle any general multivariate data. Experimentally, we show that our method performs significantly better on compositional data and is competitive on general data compared to the available state of the art implementations.

     

A two-stage hybrid credit scoring model using artificial neural networks and multivariate adaptive regression splines

The objective of the proposed study is to explore the performance of credit scoring using a two-stage hybrid modeling procedure with artificial neural networks and multivariate adaptive regression splines (MARS). The rationale under the analyses is firstly to use MARS in building the credit scoring model, the obtained significant variables are then served as the input nodes of the neural networks model. To demonstrate the effectiveness and feasibility of the proposed modeling procedure, credit scoring tasks are performed on one bank housing loan dataset using cross-validation approach. As the results reveal, the proposed hybrid approach outperforms the results using discriminant analysis, logistic regression, artificial neural networks and MARS and hence provides an alternative in handling credit scoring tasks.     

Response-time simulation of multivariate point process models for multiprogrammed jobstreams

We consider simulation methods for particular marked multivariate point processes, calledR-processes, which have recently been proposed as models for multiprogrammed jobstreams. Using workload marks on events, such models facilitate the incorporation of realistic workload characteristics into computer system performance predictions. We consider R-processes in which workload marks for an individual jobstream form a stationary sequence of discrete random variables having a (generally non-Markovian) mixed moving average-autoregressive dependency structure. For such models we provide a method for obtaining from a single simulation run point and interval estimates for general characteristics of job response times.     

Bivariate quality control using two-stage intelligent monitoring scheme

In manufacturing industries, it is well known that process variation is a major source of poor quality products. As such, monitoring and diagnosis of variation is essential towards continuous quality improvement. This becomes more challenging when involving two correlated variables (bivariate), whereby selection of statistical process control (SPC) scheme becomes more critical. Nevertheless, the existing traditional SPC schemes for bivariate quality control (BQC) were mainly designed for rapid detection of unnatural variation with limited capability in avoiding false alarm, that is, imbalanced monitoring performance. Another issue is the difficulty in identifying the source of unnatural variation, that is, lack of diagnosis, especially when dealing with small shifts. In this research, a scheme to address balanced monitoring and accurate diagnosis was investigated. Design consideration involved extensive simulation experiments to select input representation based on raw data and statistical features, artificial neural network recognizer design based on synergistic model, and monitoring–diagnosis approach based on two-stage technique. The study focused on bivariate process for cross correlation function, ρ = 0.1–0.9 and mean shifts, μ = ±0.75–3.00 standard deviations. The proposed two-stage intelligent monitoring scheme (2S-IMS) gave superior performance, namely, average run length, ARL₁ = 3.18–16.75 (for out-of-control process), ARL₀ = 335.01–543.93 (for in-control process) and recognition accuracy, RA = 89.5–98.5%. This scheme was validated in manufacturing of audio video device component. This research has provided a new perspective in realizing balanced monitoring and accurate diagnosis in BQC.     

Detecting outliers in industrial systems using a hybrid ensemble scheme

Neural Computing and Applications - The massive growth of process data in industrial systems has promoted the development of data-driven techniques, while the presence of outliers in process data...     

Five-tier barrier anti-phishing scheme using hybrid approach

ABSTRACT

Though hoaxing people to make financial benefits is an old idea, phishers have realized that social engineering tools for web attacks are relatively easy to execute and are highly profitable over the Internet. One of the threatening criminal activities is phishing, in which the phishers trap users into revealing their identities and financial information to a fraudulent website. Researchers have proposed a number of anti-phishing techniques based on blacklist, whitelist, and visual similarity, but the major disadvantage with such approaches is that they are slow techniques with high false positive rates. For robust detection of phishing attacks, this article uses fundamentals of heuristic factors and a whitelist. The article proposes a safeguard scheme referred as the five-tier barrier hybrid approach. Input to the five-tier barrier is a uniform resource locator (URL), and output of the application is a status of the page (“Secure Connection” representing a legitimate URL, “Phishing Alert” representing phishing URL, and “Query Page” representing that the webpage needs to be processed further/failure of JSoup connection). In comparison to a blacklist, the five-tier barrier is competent in detecting zero-hour phishing attacks, and it is much faster than visual similarity–based anti-phishing techniques.     

Flexible multibody simulation using hybrid integration scheme

One issue in the dynamic simulation of flexible multibody system is poor computation efficiency, which is due to high frequency components in the solution associated with a deformable body. Standard explicit numerical methods should take very small time steps in order to satisfy the absolute stability condition for the high frequency components and, in turn, the computational efficiency deteriorates. In this study, a hybrid integration scheme is applied to solve the equations of motion of a flexible multibody system for achieving better computational efficiency. The computation times and simulation results are compared between the hybrid scheme and conventional methods. The results demonstrate that the efficiency of a flexible multibody simulation can be improved by using the hybrid scheme.     

Optimal back-off point determination and controller weight selection for multivariate systems under finite-horizon control

Plant economic performance is most often related to the operating point, specifically the mean values of the process variables; meanwhile, most existing performance assessment techniques involve examining the variances or covariances of the controlled variables. A combined approach is to determine the appropriate trade-off between variances of different process variables in order to operate the plant at the point that provides maximum economic benefit while satisfying the operating constraints. This problem is referred to as the minimum backed-off operating point selection, and previous works have formulated it as a non-convex constrained optimization problem. In the current work, a new technique is introduced that can provide the optimal plant operating point. Additionally, this method provides the weights for a finite horizon controller that results in the optimal trade-off in process variable variances that will allow satisfaction of the operating constraints at the optimal operating point. In this method, the plant and disturbance models for the given process are used to generate data representing possible trade-offs between process variable standard deviations. Employing a piecewise linear regression to describe the sample points of this standard deviations data allows for the operating point selection problem to be solved as a small number of linear programs. The advantages of this approach are demonstrated through the use of mathematical and simulation case studies.     

Solving two-stage hybrid flow shop using climbing depth-bounded discrepancy search

This paper investigates how to adapt a discrepancy-based search method to solve two-stage hybrid flowshop scheduling problems in which each stage consists of several identical machines operating in parallel. The objective is to determine a schedule that minimizes the makespan. We present an adaptation of the Climbing Depth-bounded Discrepancy Search (CDDS) method based on Johnson’s rule and on dedicated lower bounds for the two-stage hybrid flow shop problem. We report the results of extensive computational experiments, which show that the proposed adaptation of the CDDS method solves instances in restrained CPU time and with high quality of makespan.     

Evaluating the efficiency of a two-stage production process using data envelopment analysis

Data envelopment analysis (DEA) has been widely used to evaluate the comparative efficiencies of production processes. Most of the DEA applications assume that production processes consist of one stage. However, many production processes such as IT investments have more than one stage. In a two‐stage production process, the first stage inputs produce intermediate outputs, which are used as inputs to the second stage to produce the final outputs. In such cases, using single‐stage DEA may result in inaccurate efficiency evaluation. To address such problems, DEA models assuming two‐stage production processes have been developed. In this paper, we extend two‐stage DEA models by considering input and output slacks. We apply our model to the data from the banking industry and compare the results with those of the previous two‐stage DEA models. Our model can identify weakly efficient units of evaluation that could not be identified by the previous models.     

A new two-stage Rosenbrock scheme for differential-algebraic systems

In this work conditions for the two-stage Rosenbrock system parameters with third-order accuracy for the differential-algebraic systems of index 1 have been obtained. The coefficients of the system are complex numbers. A new system with L2 stability has been constructed with third-order accuracy for differential-algebraic systems and with fourth-order accuracy for differential systems. The convergence of this scheme is proved. This scheme was tested on standard stiff tests and compared with the already known schemes of the same class.     

Dynamic multivariate statistical process control using subspace identification

In this article, the monitoring of continuous processes using linear dynamic models is presented. It is outlined that dynamic extensions to conventional multivariate statistical process control (MSPC) models may lead to the inclusion of large numbers of variables in the condition monitor. To prevent this, a new dynamic monitoring scheme, based on subspace identification, is introduced, which can (1) determine a set of state variables for describing process dynamics, (2) produce a reduced set of variables to monitor process performance and (3) offer contribution charts to diagnose anomalous behaviour. This is demonstrated by an application study to a realistic simulation of a chemical process.     

Fast raycasting using a compound deep image for virtual point light range determination

Computational Visual Media - The concept of using multiple deep images, under a variety of different names, has been explored as a possible acceleration approach for finding ray-geometry...     

A hybrid parallel solver for systems of multivariate polynomials using CPUs and GPUs

This paper deals with a problem of finding valid solutions to systems of polynomial constraints. Although there have been several quite successful algorithms based on domain subdivision to resolve this problem, some major issues are still demanding further research. Prime obstacles in developing an efficient subdivision-based polynomial constraint solver are the exhaustive, although hierarchical, search of the zero-set in the parameter domain, which is computationally demanding, and their scalability in terms of the number of variables. In this paper, we present a hybrid parallel algorithm for solving systems of multivariate constraints by exploiting both the CPU and the GPU multicore architectures. We dedicate the CPU for the traversal of the subdivision tree and the GPU for the multivariate polynomial subdivision. By decomposing the constraint solving technique into two different components, hierarchy traversal and polynomial subdivision, each of which is more suitable to CPUs and GPUs, respectively, our solver can fully exploit the availability of hybrid, multicore architectures of CPUs and GPUs. Furthermore, our GPU-based subdivision method takes advantage of the inherent parallelism in the multivariate polynomial subdivision. We demonstrate the efficacy and scalability of the proposed parallel solver through several examples in geometric applications, including Hausdorff distance queries, contact point computations, surface–surface intersections, ray trap constructions, and bisector surface computations. In our experiments, the proposed parallel method achieves up to two orders of magnitude improvement in performance compared to the state-of-the-art subdivision-based CPU solver.     

Detection of chatter vibration in a drilling process using multivariate control charts

Time series analysis and multivariate control charts are used to devise a real-time monitoring strategy in a drilling process. The process is used to produce holes with high length-to-diameter ratio, good surface finish and straightness. It is subject to dynamic disturbances that are classified as either chatter vibration or spiralling. A new nonparametric control chart for multivariate processes is proposed. It is used to detect chatter vibration which is dominated by single frequencies. The results showed that the proposed monitoring strategy can detect chatter vibration and that some alarm signals are related to changing physical conditions of the process.     

A hybrid intelligent system for PID controller using in a steel rolling process

With the aim to improve the steel rolling process performance, this research presents a novel hybrid system for selecting the best parameters for tuning in open loop a PID controller. The novel hybrid system combines rule based system and Artificial Neural Networks. With the rule based system, it is modeled the existing knowledge of the PID controller tuning in open loop and, with Artificial Neural Network, it is completed the rule based model that allow to choose the optimal parameters for the controller. This hybrid model is tested with a long dataset to obtain the best fitness. Finally, the novel research is validated on a real steeling roll process applying the hybrid model to tune a PID controller which set the input speed in each of the gearboxes of the process.     

On-line analysis of out-of-control signals in multivariate manufacturing processes using a hybrid learning-based model

Advanced automatic data acquisition is now widely adopted in manufacturing industries and it is common to monitor several correlated quality variables simultaneously. Most of multivariate quality control charts are effective in detecting out-of-control signals based upon an overall statistics in multivariate manufacturing processes. The main problem of such charts is that they can detect an out-of-control event but do not directly determine which variable or group of variables has caused the out-of-control signal and what is the magnitude of out of control. This study presents a hybrid learning-based model for on-line analysis of out-of-control signals in multivariate manufacturing processes. This model consists of two modules. In the first module using a support vector machine-classifier, type of unnatural pattern can be recognized. Then by using three neural networks for shift mean, trend and cycle it can be recognized magnitude of mean shift, slope of trend and cycle amplitude for each variable simultaneously in the second module. The performance of the proposed approach has been evaluated using two examples. The output generated by trained hybrid model is strongly correlated with the corresponding actual target value for each quality characteristic. The main contributions of this work are recognizing the type of unnatural pattern and classification major parameters for shift, trend and cycle and for each variable simultaneously by proposed hybrid model.     

A two-stage scheme for text detection in video images

This paper proposes a two-stage system for text detection in video images. In the first stage, text lines are detected based on the edge map of the image leading in a high recall rate with low computational time expenses. In the second stage, the result is refined using a sliding window and an SVM classifier trained on features obtained by a new Local Binary Pattern-based operator (eLBP) that describes the local edge distribution. The whole algorithm is used in a multiresolution fashion enabling detection of characters for a broad size range. Experimental results, based on a new evaluation methodology, show the promising overall performance of the system on a challenging corpus, and prove the superior discriminating ability of the proposed feature set against the best features reported in the literature.     

Improvement of causal analysis using multivariate statistical process control

Statistical process control (SPC) is a conventional means of monitoring software processes and detecting related problems, where the causes of detected problems can be identified using causal analysis. Determining the actual causes of reported problems requires significant effort due to the large number of possible causes. This study presents an approach to detect problems and identify the causes of problems using multivariate SPC. This proposed method can be applied to monitor multiple measures of software process simultaneously. The measures which are detected as the major impacts to the out-of-control signals can be used to identify the causes where the partial least squares (PLS) and statistical hypothesis testing are utilized to validate the identified causes of problems in this study. The main advantage of the proposed approach is that the correlated indices can be monitored simultaneously to facilitate the causal analysis of a software process.