Soft Computation Research Articles

Необходимость применения интеллектуальных систем управления в экспериментальных ядерно-физических комплексах (типа NICA). Ч.I: Проблема нештатных ситуаций

In the article (Part I) the necessity of application of end-to-end quantum technologies of intelligent computing in problems of structure elements control of complex experimental accelerator complex NICA is analyzed. Given a description of possible unforeseen situations, their classification is given to include adjustments to the decision-making application of production rules, logic knowledge bases of intelligent control systems based on emerging information risk increment. In the second part (Part II) the proposed two-level intelligent control system, a physical experimental setup of the NICA complex, in which the lower Executive level is a traditional control system based on expert control using the Tango control system Controls, while the upper (intelligent) level control actions are generated using the methods of quantum end-to-end IT design quantum fuzzy controller. Part II presents the QSCIT (Quantum Soft Computational Intelligence Toolkit), based on soft and quantum computing, to design robust knowledge bases in self-organizing intelligent control systems.

Integrating and extending data and decision tools for sustainable third-party reverse logistics provider selection

Third-party reverse logistics provider (3PRLP) selection plays an important role in the operation and implemention of reverse logistics or reverse supply chains. Economic and cost based partner relationships are no longer acceptable for 3PRLPs or for organizations that seek to introduce sustainable supply chain management. Recent emphasis on sustainability has made 3PRLP evaluation and selection more complex. In order to advance this area of research and to help further incorporate sustainability into 3PRLPs selection modeling, a novel multi-stage, multi-method, multi-criteria approach is developed. Methodologically, this is the first time that neighborhood rough set (NRS) theory is integrated with TOPSIS and VIKOR techniques. Neighborhood rough set, as a data management and soft computation tool, can help reduce the number of 3PRLP to be evaluated and ranked using TOPSIS combined with VIKOR's compromise conception decision tools. A conceptual application is developed using business, environmental, and social factors within the context of reverse logistics management decisions. A sensitivity analysis evaluating various neighborhood rough set parameters is also introduced to investigate robustness of solutions using the multi-stage methodology. Methodological implications and future research and application directions conclude the paper.

Green product deletion decisions

PurposeThe purpose of this paper is to identify how organizations can evaluate the green product deletion decision within an environmentally sustainable consumption and production environment through a hybrid multistage multiple criteria evaluation approach.Design/methodology/approachThis paper proposes a decision-making model by integrating “soft computation” using neighborhood rough set theory, fuzzy cluster means, and cumulative prospect theory. Literature is used to identify various factors for the decision environment. An illustrative problem provides insights into the methodology and application.FindingsThe results indicate that green products can be evaluated from both their relative environmental burdens and benefits. Sustainable consumption and production factors that play a role in this multifactor decision are identified. The results show that a comprehensive evaluation can capture an effective overall picture on which green product(s) to delete.Research limitations/implicationsThe opaqueness of the proposed methodology may cause less acceptance by management. The methodology made a number of assumptions related to the data. An actual application of the tool rather than just an illustrative example is needed.Originality/valueThe main contribution of this study is the novel integration of supply chain perspectives, both upstream (supply and production) and downstream (demand/usage), with green product deletion decision making. The hybrid multistage technique has advantages of being able to incorporate many factors that have a variety of quantitative and qualitative characteristics to help managers address green product deletion issues as well as its impact on greening of supply chains and organizational environmental sustainability. This paper adds value to product deletion, supply chain management, and sustainable production and consumption literatures.

Responsible consumption and production (RCP) in corporate decision-making models using soft computation

Responsible consumption and production (RCP) in corporate decision-making models using soft computation

Estimation of hazen williams’s constant for a residential water distribution network; GMDH and PSO approach

Hazen-William equation is used to estimate the Fluid flow in closed channel. There are various models for estimation of pipe flow, however the accuracy and reliability of models varies due to the empirical nature of the Hazen-William constant .the applicability of model also become constrained due to the dependency of constant on pipe material, dimension and flow potential. Different type of pipeline arranged in different Networks will require different value of the constant and is generally retrieved from the data collected for the pipe network. The case dependency of the model has makes the model erroneous and often subjective that is why the present study tries to propose a model which can be used for any network where the output will depend upon the inputs. In this aspect the soft computation techniques: - GMDH and PSO was utilized in an unconventional way to establish the value of CHW =f (H, L, V, D). According to result the GMDH becomes the better model than the PSO where the accuracy is about 76.315%.

Technology of hybrid computational intellect and problems associated with intelligent vehicle control systems development

Abstract The authors of this article are presenting the concepts of intelligent vehicle control systems development on the basis of author’s concept of mathematical modeling of complex systems by method of heuristic correction of basic analytical dependences by heuristic knowledge and soft computation. The authors are formulating the basic provisions of “knowledge genesis” method intended for the development of particular class of mathematic models capable (based on flexible computation) (i) to integrate determinate, indeterminate and uncertain knowledge in one and the same system and (ii) to change (accommodate) its structure in the course of modeling the object of evolution. The authors are (i) representing functional scheme of future-oriented on-board intelligent system of motor vehicle (hereinafter referred to as “ATS”) control developed on the basis of hybrid computational intellect and (ii) giving an example of hybrid computational model of unmanned ATS dynamic behavior developed on the basis of “knowledge genesis” method. The proposed methodological and application-oriented concepts of soft mathematical modeling (made on the basis of “knowledge genesis” method) could become the basis for the development of a range of future-oriented intelligent systems capable to exercise control of advanced high-technology vehicles (including unmanned vehicles and vehicles pertaining to civil and military spheres of application).

Soft Computation Vector Autoregressive Neural Network (VAR-NN) GUI-Based

Vector autoregressive model proposed for multivariate time series data. Neural Network, including Feed Forward Neural Network (FFNN), is the powerful tool for the nonlinear model. In autoregressive model, the input layer is the past values of the same series up to certain lag and the output layers is the current value. So, VAR-NN is proposed to predict the multivariate time series data using nonlinear approach. The optimal lag time in VAR are used as aid of selecting the input in VAR-NN. In this study we develop the soft computation tools of VAR-NN based on Graphical User Interface. In each number of neurons in hidden layer, the looping process is performed several times in order to get the best result. The best one is chosen by the least of Mean Absolute Percentage Error (MAPE) criteria. In this study, the model is applied in the two series of stock price data from Indonesia Stock Exchange. Evaluation of VAR-NN performance was based on train-validation and test-validation sample approach. Based on the empirical stock price data it can be concluded that VAR-NN yields perfect performance both in in-sample and in out-sample for non-linear function approximation. This is indicated by the MAPE value that is less than 1% .

The Step Construction of Geographically Weighted Panel Regression in Air Polluter Standard Index (APSI) Data

Geographically Weighted Panel Regression or GWPR is a local linear regression model that combines GWR model and panel data regression model with considering spatial effect, especially spatial heterogeneity problem. This article is focused on the soft computation of GWPR model using Fixed Effect Model (FEM). Parameter estimation in GWPR is obtain by Weighted Least Squares (WLS) methods and the resulting model for each location will be different from one to another. This study will compare the fixed-effect GWPR model with several weighting functions. The best model is determined based on the biggest coefficient of determination (R2) value. In this study, the model is applied in the Air Polluter Standard Index (APSI) in Surabaya City, East Java. The results of this study indicate that Fixed Effect GWPR model with a fixed exponential kernel weighting function is the best model to describe the APSI because it has the smallest AIC.

Intelligent Molecular Searcher from Logic Computing Network Based on Eu(III) Functionalized UMOFs for Environmental Monitoring

By taking advantage of facile preparation and sensitive recognition capacity, the first example of a fluorescence system based on Eu(III) functionalized UiO(bpdc) (UMOFs) has been constructed for effective combination of ions recognition and logic computing. All the ions, including Hg2+, Ag+, and S2− in the system are water harmful, which can be recognized through affecting energy transfer or framework structure. By the self‐assembling, competing and connecting with each other, Eu(III)@UMOFs and the ions have achieved the implementation of Boolean logic network system connecting the elementary logic operations (NOR, INH, and IMP) and integrative logic operation (OR + INH), also obtaining computing keypad‐lock security system by sequential logic operation. To deal with uncertain information in the analog region of nonlinear response (fluorescence and concentration), soft computation through the formulation of fuzzy logic operation has been constructed. On the basis of Boolean logic and fuzzy logic, one intelligent molecular searcher can be realized by taking chemical events (Hg2+, Ag+, and S2−) as programmable words and chemical interactions as syntax. Considering the particularity of all the input ions, the approach is helpful in developing the advanced logic program based on Eu(III)@UMOFs for application in environmental monitoring.

Comparing sat-based bounded model checking rtectl and ectl properties

We compare two SAT-based bounded model checking algorithms for the properties expressed in the existential fragment of a soft real-time computation tree logic (RTECTL) and in the existential fragment of computation tree logic (ECTL). To this end, we use the generic pipeline paradigm (GPP) and the train controller system (TC), the classic concurrency problems, which we formalise by means of a finite transition system. We consider several properties of the problems that can be expressed in both RTECTL and ECTL, and we present the performance evaluation of the mentioned bounded model checking methods by means of the running time and the memory used.

Soft and evolutionary computation based data association approaches for tracking multiple targets in the presence of ECM

This paper proposes two novel soft and evolutionary computing based hybrid data association techniques to track multiple targets in the presence of electronic countermeasures (ECM), clutter and false alarms. Joint probabilistic data association (JPDA) approach is generally used for tracking multiple targets. Fuzzy clustering means (FCM) technique was proposed earlier as an efficient method for data association, but its cluster centers may fall to local minima. Hence, new hybrid data association approaches based on fuzzy particle swarm optimization (Fuzzy-PSO) and fuzzy genetic algorithm (Fuzzy-GA) clustering techniques have been presented as robust methods to overcome local minima problem. The data association matrix is evaluated for all tracks using validated measurements obtained by phased array radar for four different cases applying four data association methods (JPDA, FCM, Fuzzy-PSO, and Fuzzy-GA). Therefore, two hybrid data association approaches are designed and tested for multi-target tracking using intelligent techniques. Experimental results indicate that Fuzzy-GA data association technique provides improved performance compared to all other methods in terms of position and velocity RMSE values (38.69% and 33.19% average improvement for target-1;31.17% and 9.68% average improvement for target-2) respectively for crossing linear targets case. However, FCM technique gives better performance in terms of execution time (94.88% less average execution time) in comparison with other three techniques(JPDA, Fuzzy-GA, and Fuzzy-PSO) for the case of linear crossing targets. Thus accomplishing efficient and alternative multiple target tracking algorithms based on expert systems. The results have been validated with 100 Monte Carlo runs.

New Results for Kharal’s Similarity Measures of Soft Sets

In this paper, we prove that Lemma 5.7, Proposition 6.8 and Proposition 6.9 of Kharal [A. Kharal, Distance and similarity measures for soft sets, New Mathematics and Natural Computation 6(3) (2010) 321–334] are not correct w.r.t his Definition 5.5. We give suitable examples to show that Lemma 5.7 is not correct. Moreover, we rectify Lemma 5.7, Proposition 6.8 and Proposition 6.9 by providing suitable proofs.

Defuzzification and application of trapezoidal type-2 fuzzy variables to green solid transportation problem

The main objective of this investigation is to propose a defuzzification process of a trapezoidal type-2 fuzzy variable centred on critical value-based reduction method and nearest interval approximation, i.e. $$\alpha $$ź-cut of fuzzy number. In this context, this paper proposes some theorems with proof. Also as an application of the proposed defuzzification process, a new multi-objective green solid transportation model has been formulated with all of its parameters as trapezoidal type-2 fuzzy variables, where the objectives are profit maximization and minimization of carbon emission produced by the modes of transport depending upon their loads, fuel type used, type of engine, driving characteristics, etc. After defuzzification, to solve the equivalent crisp multi-objective solid transportation problem the intuitionistic fuzzy programming technique is used. Also we have proposed the MOGA and LINGO 13.0 iterative platform for the soft computation related to the problem. At the end, proposed methodologies are finally illustrated by providing numerical examples which incorporate some real-life data and demonstrate how a decision maker makes a balance between the maximum profit and minimum carbon emission. Also a comparative study with N---T method has been provided, and some managerial decisions are drawn.

Assembly quality analysis method research of automotive body outer cover panels

This paper proposes an assembly variation modelling method of automotive body sheet metal parts for the assembly quality analysis of outer cover panels. In this method an influencing relationship between the measurement point variation and assembly locating unit variation is constructed through the space motion analysis. The gap and flush between two outer cover panels are two direction distances of their involved two measurement points near the gap. When the assembly variation of one gap or flush is analysed, only the locating variation of locating units that influences the gap or flush will be considered. One case application of a fender and a front door demonstrates the assembly quality analysis process of outer cover panels. Three steps are given when an assembly analysis of a gap or flush is dealt with. The given case analysis results that compares with commercial soft computation results show the feasibility of this method. By these computation results the assembly quality of outer cover panels can be predicted, and the optimisation of locating units also can be achieved.

Assembly quality analysis method research of automotive body outer cover panels

This paper proposes an assembly variation modelling method of automotive body sheet metal parts for the assembly quality analysis of outer cover panels. In this method an influencing relationship between the measurement point variation and assembly locating unit variation is constructed through the space motion analysis. The gap and flush between two outer cover panels are two direction distances of their involved two measurement points near the gap. When the assembly variation of one gap or flush is analysed, only the locating variation of locating units that influences the gap or flush will be considered. One case application of a fender and a front door demonstrates the assembly quality analysis process of outer cover panels. Three steps are given when an assembly analysis of a gap or flush is dealt with. The given case analysis results that compares with commercial soft computation results show the feasibility of this method. By these computation results the assembly quality of outer cover panels can be predicted, and the optimisation of locating units also can be achieved.

Soft computation based spectral and temporal models of linguistically motivated Assamese telephonic conversation recognition

Speech is the natural communication means, though not the typical input means afforded by computers. The interaction between humans and machines would have become easier, if speech were an alternative effective input means supplementing the keyboard and mouse. With advancement in techniques for signal processing and model building leading to the empowerment of computing devices with expanding list of abilities, significant progress has been made in speech recognition research, and various speech based applications have been developed. In such a backdrop, telephone speech technology have been receiving more attention in many new applications of spoken language processing. From the literature it has been found that the spectro-temporal features gives a significant performance improvement for telephone speech recognition in comparison to the conventionally used features for speech/speaker identification. Speech recognition systems can be characterized by many parameters. The commonly used method to measure the performance of a speech recognition system is the recognition accuracy. For obtaining proper accuracy it is necessary to design an efficient classifier for the recognition purpose which will lead to correct recognition results.

Securing a Cyber Physical System in Nuclear Power Plants Using Least Square Approximation and Computational Geometric Approach

Abstract In industrial plants such as nuclear power plants, system operations are performed by embedded controllers orchestrated by Supervisory Control and Data Acquisition (SCADA) software. A targeted attack (also termed a control aware attack) on the controller/SCADA software can lead a control system to operate in an unsafe mode or sometimes to complete shutdown of the plant. Such malware attacks can result in tremendous cost to the organization for recovery, cleanup, and maintenance activity. SCADA systems in operational mode generate huge log files. These files are useful in analysis of the plant behavior and diagnostics during an ongoing attack. However, they are bulky and difficult for manual inspection. Data mining techniques such as least squares approximation and computational methods can be used in the analysis of logs and to take proactive actions when required. This paper explores methodologies and algorithms so as to develop an effective monitoring scheme against control aware cyber attacks. It also explains soft computation techniques such as the computational geometric method and least squares approximation that can be effective in monitor design. This paper provides insights into diagnostic monitoring of its effectiveness by attack simulations on a four-tank model and using computation techniques to diagnose it. Cyber security of instrumentation and control systems used in nuclear power plants is of paramount importance and hence could be a possible target of such applications.

Soft computing in assessment of earthquake-triggered landslide susceptibility

This study compared two soft computing methods that are applied to soft computation in assessment of earthquake-triggered landslide susceptibility: the support vector machine (SVM) and artificial neural networks (ANN). As a case study, a series of landslide susceptibility maps were constructed for the affected area of the 2013 Minxian-Zhangxian, Gansu Province, China Mw 5.9 earthquake. From data available, 2330 coseismic landslides were partitioned into two subsets which were used as a training dataset and a test dataset, respectively. In addition, other 1631 points on the map were randomly selected as non-landslide samples in those areas were not influenced by the coseismic landslides. Ten conditioning factors of landslides were considered, including elevation, relative relief, slope angle, slope aspect, slope curvature, slope position, lithology, peak ground acceleration (PGA), distance from the probable seismogenic fault, and distance along the fault. Using the ANN and SVM, ten landslide susceptibility maps were produced for the study area. Cross comparisons and validations of these ten resulting maps with real coseismic landslides show that the polynomial kernel type with a high enough polynomial degree term value (e.g., 5 or 6) of the SVM technology is most appropriate for coseismic landslide susceptibility assessment, which is a challenge to the previously held notion that the SVM method with radial basis function is the most suitable.

Prediction of scour in plunge pools below outlet bucket using artificial intelligence

Accurate prediction of sediment scour hole dimensions downstream of hydraulic structures, e.g. the outlet bucket, is a complex and not straight forward engineering problem encountered worldwide. Dimensions of a scour hole are usually determined by empirical equations which their validation is limited by experimental conditions. As constructing physical models has its own difficulty, determining of scour hole parameters has been applied in this paper for a collection of previous experimental studies. Two artificial intelligence techniques (ANN & ANFIS) are used and the results are compared with empirical equation for maximum scour holes using nonlinear regression method. Artificial Neural Network (ANN) simply represents interconnection of neurons, each of which carries out the task of combining the input, determining its strength by comparing the combination and finding out the result. On the other hand, ANFIS is a hybrid scheme which uses the learning capability of the ANN to derive the fuzzy rules with membership functions. The results showed that maximum error caused by applying ANFIS techniques in estimating scour hole dimensions was 5.2 percent while the error in neural network model was 10.38 percent. The significance of different parameters was discussed and a simple, innovative formula was proposed. This formula is an interesting tool for the engineering community due to its preferences for estimating the parameters of complex phenomena like erosion procedures. It has been established that scour estimations could be improved if soft computation is used in place of the traditional formulae.

Soft Computation Technique based Fire Evacuation System

Occurrence of fire is an unpredictable activity needing very high attention. Early response for fire may lead to less damage of life and property. In this paper a work is proposed for evacuating the people to a safe point once fire accident occurs. The objective of the proposed work is to process the data acquired from smoke and temperature sensor to indicate the direction for movement of people. Computational technique is used to collect data from sensors and display safest path for people to evacuate from the building. Artificial Neural Network (ANN) is trained using particle swarm optimization to produce evacuation information. To test working of proposed technique it is subjected to several test cases, results obtained proves successful implementation of proposed work. Keywords: Evacuation, Fire Safety, LabVIEW, Soft Computing