Component Selection Problem Research Articles

A multivariate monitoring method based on kernel principal component analysis and dual control chart

The kernel principal component analysis (KPCA) method has been widely applied in process monitoring. However, the KPCA method still has two challenging problems that need to be solved: the principal component selection problem and the problem of determining Gaussian kernel width without fault data. The principal component selection plays an important role in the performance of the KPCA method, which is determined by the cumulative contribution rate, cross-validation, average eigenvalue, etc. However, these selection methods ignore the principal components corresponding to small eigenvalues, which are still very important for fault detection. Therefore, this paper proposes a multivariate monitoring method based on the KPCA and Dual Control Chart (KPCA-DCC), which adopts a scheme of monitoring all principal components and solves the selection problem. The Gaussian kernel width is usually determined by training an appropriate coefficient to times the variable number, which may not be possible to train the coefficient in the absence of fault data while the industrial process works at the initial stage of its operation. Furthermore, different systems may have the same number of variables, and their Gaussian kernel widths should vary because of different variables’ features. Therefore, this paper proposes an empirical equation for estimating Gaussian kernel width according to data characteristics, which makes the Gaussian kernel width can be estimated without fault data. In addition, this paper also gives the detection theory of the DCC method from the probability perspective, which is not presented in the previous work. The Tennessee Eastman (TE) process and blast furnace ironmaking process are adopted to verify the effectiveness of the proposed methods.

Space-Time Independent Component Analysis of Brain Signals: Component Selection and the Curse of Dimensionality.

Performing Independent Component Analysis (ICA) on biomedical signals is quite commonplace. ICA is usually applied to multi-channel data however not always with great success. In previous work we realized an innovation to standard ICA which we call space-time ICA (ST-ICA). This method brings into play both spatial and temporal/spectral information to perform very powerful extractions and overcomes the individual limitations of ensemble (spatial) ICA and single-channel (temporal) ICA. The cost in implementing ST-ICA is the curse of dimensionality since spatio-temporal analysis of multi-channel physiological data recorded at suitable sampling speeds results in large unwieldy datasets which become impossible to parse without any form of truncation or at least an automated component selection process. Here we address the component selection problem on the application of ST -ICA to real-world neurophysiological data-specifically in extracting seizure data from EEG recordings. We assess the information held in each of the spatio-temporal features resulting from ST-ICA and comment on the development of an efficient method to extract them, as well as using dimensional reduction techniques to reduce the curse of dimensionality resulting successful separation of meaningful physiological data from noisy, artifact laden datasets. Clinical Relevance-These methods will allow for the automatic identification and extraction of poorly defined episodes of physiologically meaningful activity in noisy multi-channel recordings of brain signals.

A novel multivariate statistical process monitoring algorithm: Orthonormal subspace analysis

Partial least squares (PLS) and canonical correlation analysis (CCA) are two most popular key performance indicators (KPI) monitoring algorithms, which have shortcomings in dealing with the KPI-related information leakage problem, the model identification problem, the component selection problem, and the process hypothesis problem. To overcome these shortcomings, this study proposes a new multivariate statistics-based process monitoring (MSPM) method called the orthonormal subspace analysis (OSA) method. OSA divides process data and KPI data into three orthonormal subspaces through an analytic solution. Hence, OSA not only can detect a fault but also can judge whether the fault is KPI-related or KPI-unrelated. OSA is always effective irrespective of the availability of the KPI variables in the online monitoring stage. In OSA, the cumulative percent variance (CPV) method is adopted for principal component selection. In brief, OSA is a more effective method than PLS and CCA, and it achieves superior performance in fault detection and classification.

Optimal components selection based on fuzzy-intra coupling density for component-based software systems under build-or-buy scheme

Component-Based Software Engineering (CBSE) is an approach to building and developing software systems based on software components. In component-based software systems, there are various software components, including Commercial off the Shelf (COTS) and in-house components. Software developers can build their desired software component as in-house or COTS. The problem of deciding optimally between COTS and in-house components is one of the major challenges of software developers, which is known as the component selection problem. This can be resolved by evaluating the criteria for optimality in component selection and then solving the component selection problem by optimization techniques. In this paper, an attempt was made to optimize the component selection problem through the multi-objective optimization by maximizing the Fuzzy-Intra Coupling Density (Fuzzy-ICD) and functionality as objective functions, and also taking into account budget, delivery time, reliability, and Fuzzy-ICD as constraints of multi-objective problems. Fuzzy ICD is a more accurate criterion to calculate the relationship between Cohesion and Coupling of components, which is obtained through the fuzzy computing of each of them, based on the Meyers classification. Thus, after a two-criterion optimization model formulation, this optimization problem was solved by fuzzy multi objectives approach. Finally, the proposed method was evaluated by performing the case study of financial-accounting system. Comparison of the results showed that the proposed method could select optimal components with maximum functionality and Fuzzy-ICD and fewer rates of time and Budget (0.29, 0.43, 1.1 s, and 88$ were the improved rates of functionality, Fuzzy-ICD, time, and budget, respectively).

Automatic Selection and Parameter Configuration of Big Data Software Core Components Based on Retention Pattern

This paper conducts an in-depth analysis and research on the automatic selection and parameter configuration of the core components of Big Data software by using the retention model and the automatic selection of Big Data components by establishing a standardized requirement index and using the decision tree model to solve the problem of component selection in Big Data application development. By establishing standardized demand indicators and based on the retention model, a data transmission intermediate platform for bidirectional data detection is proposed based on the three demands of user input: storage, computation, and analysis, as well as the problem of undetectable packet loss in data transmission of existing IoT and Web service platforms. The data communication module of the data transmission intermediate platform enables mutual monitoring and detection of data interaction between IoT smart terminals and cloud platforms. The retention mode is built separately to realize the automatic selection of Big Data components. In this paper, we start from several mainstream distributed storage systems and use Cassandra as an example for experiments and tests. We use the multiple regression fitting method to build a corresponding performance model for hardware parameters, take user requirements as input, and use the performance model to configure system hardware parameters; by studying its system principle, architecture, features, and application scenarios, we build a software parameter configuration knowledge base to guide the software. This solves the difficult problem of selecting, deploying, and configuring parameters for Big Data applications.

Underlying Trend Extraction via Joint Ensemble Intrinsic Timescale Decomposition Algorithm and Matching Pursuit Approach

Time series usually consist of an underlying trend and the irregularities. Therefore, the underlying trend extraction plays an important role in the analysis of the time series. This paper proposes a method which combines the ensemble intrinsic timescale decomposition (EITD) algorithm and the matching pursuit (MP) approach for performing the underlying trend extraction. In order to extract the underlying trend, the EITD algorithm is applied to obtain a set of components. Then, the first component which contains most of the noise is removed. Next, some appropriate components are selected by the MP approach. In particular, the total number of components that composites of the underlying trend is minimized. To guarantee that the underlying trend tracks the signal, it is required to impose a constraint on the maximum absolute error between the underlying trend and the denoised signal. As the selection of the EITD components is binary, this component selection problem is formulated as an $$ L_{0} $$ -norm binary programming problem subject to the specification on the maximum absolute error between the denoised signal and the underlying trend. This optimization problem is further solved by the MP approach. Finally, the underlying trend is constructed. Compared with the conventional empirical mode decomposition algorithm and the ensemble empirical mode decomposition algorithm, our proposed approach could extract a better underlying trend for some random time series.

Temporally constrained ICA with threshold and its application to fMRI data

BackgroundAlthough independent component analysis (ICA) has been widely applied to functional magnetic resonance imaging (fMRI) data to reveal spatially independent brain networks, the order indetermination of ICA leads to the problem of target component selection. The temporally constrained independent component analysis (TCICA) is capable of automatically extracting the desired spatially independent components by adding the temporal prior information of the task to the mixing matrix for fMRI data analysis. However, the TCICA method can only extract a single component that tends to be a mix of multiple task-related components when there exist several independent components related to one task.MethodsIn this study, we proposed a TCICA with threshold (TCICA-Thres) method that performed TCICA outside the threshold and performed FastICA inside the threshold to automatically extract all the target components related to one task. The proposed approach was tested using simulated fMRI data and was applied to a real fMRI experiment using 13 subjects. Additionally, the performance of TCICA-Thres was compared with that of FastICA and TCICA.ResultsThe results from the simulation and the fMRI data demonstrated that TCICA-Thres better extracted the task-related components than TCICA. Moreover, TCICA-Thres outperformed FastICA in robustness to noise, spatial detection power and computational time.ConclusionsThe proposed TCICA-Thres solves the limitations of TCICA and extends the application of TCICA in fMRI data analysis.

The Computational Complexity of and Approximation Algorithms for Variants of the Component Selection Problem

In the past decades, there has been a burst of activity to simplify implementation of complex software systems. The solution framework in software engineering community for this problem is called component-based software design (CBSD), whereas in the modeling and simulation community it is called composability. Composability is a complex feature due to the challenges of creating components, selecting combinations of components, and integrating the selected components. In this paper, we address the challenge through the analysis of Component Selection (CS), the NP-complete process of selecting a minimal set of components to satisfy a set of objectives. Due to the computational complexity of CS, we consider approximation algorithms that make the component selection process practical. We define three variations of CS and present good approximation algorithms to find near optimal solutions. In spite of our creation of approximable variants of Component Selection, we prove that the general Component Selection problem is inapproximable.

Data envelopment analysis based multi-objective optimization model for evaluation and selection of software components under optimal redundancy

Software developers face the challenge of developing in-time, low cost, high profit and high-quality software to meet competitive requirements and user demands. The software components for the same can be selected either from the available commercial-off-the-shelf repository or developed in-house. In this paper, we propose a data envelopment analysis (DEA) based nonlinear multi-objective optimization model for selecting software components in the presence of optimal redundancy to ensure software reliability. The proposed optimization model integrates both build and/or buy decisions for selection of components. We use DEA technique for evaluating the fitness of software components based upon multiple inputs and outputs provided by various members of the decision group. The overall efficiency score of each software component is obtained from the aggregated information. The proposed optimization model minimizes the total cost of software system and maximizes the total value of purchasing using constraints corresponding to compatibility of selected components, reliability, execution time, and delivery time of the software system. It also provides the information on the testing efforts needed to be performed on in-house developed components. A real-world case study of modular software development is discussed to illustrate the efficiency of the proposed optimization model. To the best of our knowledge, there exists no previous study on integrated optimization model for the software component selection problem involving build and/or buy decisions under optimal redundancy.

A multi-objective optimization model of component selection in enterprise information system integration

Abstract Integrating legacy IT assets and new commercial software components together into a flexible IT architecture is one of open challenges facing modern enterprises today. Most of previous studies focused on using re-engineering to improve the flexibility of IT architectures, rather than employing optimization theory in architecture design problem, especially the problem of component selection and re-allocation in IT architecture. Moreover, a scant amount of literature is available on considering the architectural flexibility and integration cost simultaneously. To fill in this gap, based on a modified quantitative method of measuring the relationship between couplings and cohesions in architecture, we devise a nonlinear multi-objective binary integer programming to select components from legacy candidates and commercial candidates, and to group them into services under the service-oriented architecture (SOA) environment. The customized SPEA2 algorithm is further used to solve the problem, and some managerial insights are provided based on experiments and sensitivity analysis with the model.

Third Case Study for the Dynamic Multilevel Component Selection

The architecture of a system changes after the deployment phase due to new requirements from the stakeholders. The software architect must make decisions about the selection of the right software components out of a range of choices to satisfy a set of requirements. This paper deals with the component selection problem with a multilevel system view in a dynamic environment. To validate our approach we have used the case study method. Three different case studies were performed but only one is presented in the current paper. The research design was conducted using a research question, propositions and for interpreting the study's findings we have used the Wilcoxon signed ranks statistical test. The tests performed show the potential of evolutionary algorithms for the dynamic multilevel component selection problem.

Multilevel component selection optimization toward an optimal architecture

Component-based software engineering uses components to construct systems, being a means to increase productivity by promoting software reuse. This work deals with the component selection problem. A multiobjective optimization approach is used to formulate the problem. The contribution of the current paper is threefold: the multilevel decomposition approach, the use of both functional and non-functional requirements (cost of a component, thus cost of the solution as sum of the costs of the constituent components) as objectives, and the use of metrics values to evaluate the architecture of the obtained solutions. As advantages over the existing literature we mention: the automatic computation of component interactions and of the constituent components for each module, multiple solutions obtained in a single run, and the new architecture evaluation step based on metrics values that is not present in other approaches. The decomposition offers valuable insights about internal structure of the system which led us to identify metrics to assess coupling and cohesion of the architecture design. The internal structure influences the external quality; thus, a highly cohesive module exhibits high reusability and loosely coupled systems enable easy maintenance. In this context, when selecting the best solution out of a set of available ones, we aim to maximize the cohesion of modules and to minimize the coupling between them, obtaining thus the “best” reusable and maintenable solution. To evaluate our approach, we discuss a case study for building a reservation system. In order to obtain the best parameters to run the evolutionary approach, three different studies were applied. The tests performed show the potential of evolutionary algorithms for this particular problem and for other similar ones.

Vortex search algorithm for the analog active filter component selection problem

Optimal selection of passive components is one of the most crucial design steps in analog active filter design problems. As the number of possible combinations increases, it becomes infeasible to perform an exhaustive search for optimum component values. Thus, intelligent algorithms are required for a fast and optimum selection of the passive component values. In this study, a newly proposed metaheuristic, the vortex search (VS) algorithm, is utilized for this purpose. To evaluate the performance of the VS algorithm, two different analog active filter topologies, the fourth-order Butterworth low-pass filter and the state variable low-pass filter, are used. The component values of the active filter topologies are selected within three different series of (E12, E24 and E96) passive components for both the resistors and the capacitors. The results are compared to other metaheuristics such as the particle swarm optimization (PSO2011), artificial bee colony (ABC), differential evolution (DE) and harmony search (HS) algorithms. It is shown that, the VS algorithm finds the minimum fitness values for both of the active filter topologies which in turn provides the optimum component values for each of the used component series.

Improved Framework for Appropriate Components Selection

Component based software engineering (CBSE) approach is used to develop a software system from preexisting software components. It is difficult to select a suitable component from the library of components for the problem of CBSE. Appropriate software component selection plays an important role for the success of project. Many approaches are suggested to solve component selection problem. In this paper, the component selection is done by improving the integrated component selection framework by including the pliability metric to cut down the time and cost. Pliability is a flexible measure that assesses software quality. We anticipate that the proposed solution will solve the component selection problem of software industry.

Component Selection in the Additive Regression Model

Abstract. Similar to variable selection in the linear model, selecting significant components in the additive model is of great interest. However, such components are unknown, unobservable functions of independent variables. Some approximation is needed. We suggest a combination of penalized regression spline approximation and group variable selection, called the group‐bridge‐type spline method (GBSM), to handle this component selection problem with a diverging number of correlated variables in each group. The proposed method can select significant components and estimate non‐parametric additive function components simultaneously. To make the GBSM stable in computation and adaptive to the level of smoothness of the component functions, weighted power spline bases and projected weighted power spline bases are proposed. Their performance is examined by simulation studies. The proposed method is extended to a partial linear regression model analysis with real data, and gives reliable results.

New Algorithm for Component Selection to Develop Component-Based Software with X Model

is an approach which is used to enhance the reusability with the development of component-based software from the preexisting software components or with the components which is developed from the scratch. A new algorithm is proposed for component selection by using best-fit strategy and first-fit strategy through X model which is used to develop componentbased software with two approaches likely development for reuse and development with reuse. But when reuse a preexisting software component through the development with reuse, component selection play an important role. Component selection for Component-Based Software Development (CBSD) is very challenging field for researchers and practitioners. This paper also presents the two component selection problem viz. Simple Component Selection Problems (SCSP) and Criteria Component Selection Problem (CCSP). On the basis of these two problems, this paper presents a new optimal solution with new algorithm for optimal component selection from repositories. Lastly, paper summarizes the factors used in algorithm for optimal selection of components with the help of X model repositories to fulfill the requirements of client by using SCSP and CCSP.

A graph based requirements clustering approach for component selection

In recent years, Component Based System (CBS) development has found widespread application, particularly in the domain of engineering software where it is often necessary to adapt and integrate existing software tools to handle new problems. The ability to identify suitable components that match system requirements is fundamental to CBS success. To date, CBS selection techniques often make an ideal assumption that there is one-to-one mapping between requirements and components. In reality, components are usually designed for general purposes and provide a range of features that can be adapted to meet the needs of a CBS. This implies that a component can potentially match more than one functionality of a CBS. On the other hand, system requirements are usually not independent of each other and a component selection process needs to consider the dependencies between system goals. Furthermore, the existing component selection methodologies usually provide a single solution for the component selection problem, thus limiting the options available to a CBS developer. In this paper, we present a component selection process that uses a signed graph to model interdependencies of CBS-to-be needs and groups related goals into clusters, based on the usage, non-functional and threat dependencies. Subsequently, the matching index of each cluster of related goals is used as a criterion to identify a portfolio of candidate components for a CBS, providing multiple solutions for the component selection problem whenever possible. The component selection process helps a developer to elicit stakeholder needs, analyze their interdependencies and select components for a CBS. We also present application of our approach to a Meeting Scheduling System (MSS) and a Construction Management System (CMS).

Optimal Component Selection Problem for Cots Based Software System under Consensus Recovery Block Scheme: A Goal Programming Approach

Cost, reliability and time are the three main quality attributes of a software system. Now days much software are designed on COTS component in order to facilitate timely development with reduced cost and improved reliability. Software deigned to handle critical control systems have very high reliability requirements. Fault tolerance is designed in these systems for some or all of the software modules so that execution can be resumed even after failure with minimal loss of data and time. Designing fault tolerance requires extra resources. Even though reliability requirement are very high the developers can’t spend endless resources on any project. This is a trade off problem between reliability and cost. Many such problems have been discussed in literature considering distinct objectives and constraints and have given good results. An effective approach to discuss this problem is to formulate a multi-objective problem with cost minimization and reliability maximization as the two objectives with an upper bound on cost and lower bound on reliability. In this paper we formulate this bi-criteria problem and discuss the solution methodology. The problem is formulated for consensus recovery block fault tolerant scheme. In case a feasible solution for the problem exists, criterion vector approach is used to solve the problem and otherwise if the bounds are contradictory a goal programming approach is used to solve the problem to obtain a compromised solution. Alternative goal solutions are obtained assigning different weights for the objective to facilitate the decision maker with correct decision.

An Statistical Research on Feed Forward Neural Networks for Forecasting Time Series

In recent years, artificial neural networks have being successfully used in time series analysis. Using linear methods such as ARIMA and exponential smoothing for non linear time series cannot produce satisfactory results. Although there are various non linear methods, these methods have an important drawback that all of them require a specific model assumption. On the other hand, artificial neural networks have no restrictions such as linearity or model assumptions. In many applications within the time series analysis, it has been seen that artificial neural networks produce more accurate results than those obtained from traditional methods. In spite of the fact that artificial neural networks provide some advantages, re- searchers keep working on the component selection problem of the method. The answer of the question that which compo- nents of the method should be used is a vital issue in terms of forecasting performance. In this study, the effects of number of hidden layer and length of test set on forecasting performance of artificial neural networks are examined. Eight real time series are used in the implementation. The obtained results are analyzed by using statistical analysis and are interpreted.

An optimization model for software component selection under multiple applications development

Component based software development (CBSD) is well acknowledged as a methodology which establishes reusability of software and reduce development cost effectively. While developing enterprise application using component based software engineering (CBSE) methods, software component selection plays a very important role in the process of component retrieval, adaptation and assembly. However, most of current researches focus on technical aspects from domain engineering and application engineering to improve reusability and system efficiency rather than application of optimization methods in CBSD management, especially application in component selection. Moreover, few existing researches have concerned about the situation where a software developer or enterprise develops multi-applications at the same time. By introducing the concept of reusability and a new formulation of compatibility matrix, an optimization model is proposed to solve component selection problem considering reusability and compatibility simultaneously. The model can be used to assist software developers in selecting software components when multi-applications are undertaken concurrently. Four experiments are conducted with the purpose to provide some insights in management perspective.