Hybrid Computational Model Research Articles

Prediction of non-hydrocarbon gas components in separator by using Hybrid Computational Intelligence models

Accurate prediction of non-hydrocarbon (Non-HC) gas components in the gas-oil separators reduces the cost of gas and oil production in petroleum engineering. However, this task is difficult because there is no known relation among the properties of crude oil and the separators. There are studies that attempt to predict hydrocarbons (HCs) components using either Computational Intelligence (CI) techniques or conventional techniques like Equitation-of-State (EOS) and Empirical Correlation (EC). In this paper, we explore the applicability of CI techniques such as Artificial Neural Network, Support Vector Regressions, and Adaptive Neuro-Fuzzy Inference System to predict the Non-HC gas components in gas-oil separator tank. Further, we incorporate Genetic Algorithms (GA) into the Hybrid Computational Intelligence (HCI) models to enhance the accuracy of prediction. GA is used to determine the most favorable values of the tuning parameters in the CI models. The performances of the CI and HCI models are compared with the performance of the conventional techniques like EOS and EC. The experimental results show that accuracy of prediction by CI and HCI models outperform the conventional methods for N2 and H2S gas components. Furthermore, the HCI models perform better than the non-optimized CI models while predicting the Non-HC gas components.

Hybrid Computational Model of High-Current Vacuum Arcs With External Axial Magnetic Field

This paper deals with the computer modeling of a high-current (total current $\ge 10$ kA) vacuum arc with an external axial magnetic field. This arc is typical for certain kind of vacuum interrupters. The described hybrid model treats electrons as a massless fluid and ions as macroparticles. The macroparticle dynamics are calculated with the use of the particle-in-cell method. Ion-ion Coulomb collision is considered with the use of the Monte Carlo method. The model can simulate high-current vacuum arcs as a whole including separate cathode plasma jets, mixing zone, and common plasma column. The hybrid model is able to calculate V-shape volt-tesla characteristics, which correlate well with experimental results.

A hybrid computational model to predict chemotactic guidance of growth cones.

The overall strategy used by growing axons to find their correct paths during the nervous system development is not yet completely understood. Indeed, some emergent and counterintuitive phenomena were recently described during axon pathfinding in presence of chemical gradients. Here, a novel computational model is presented together with its ability to reproduce both regular and counterintuitive axonal behaviours. In this model, the key role of intracellular calcium was phenomenologically modelled through a non standard Gierer-Meinhardt system, as a crucial factor influencing the growth cone behaviour both in regular and complex conditions. This model was able to explicitly reproduce neuritic paths accounting for the complex interplay between extracellular and intracellular environments, through the sensing capability of the growth cone. The reliability of this approach was proven by using quantitative metrics, numerically supporting the similarity between in silico and biological results in regular conditions (control and attraction). Finally, the model was able to qualitatively predict emergent and counterintuitive phenomena resulting from complex boundary conditions.

A computational model to monitor and predict trends in bacterial resistance.

Current concern over the emergence of multidrug-resistant superbugs has renewed interest in approaches that can monitor existing trends in bacterial resistance and make predictions of future trends. Recent advances in bacterial surveillance and the development of online repositories of susceptibility tests across wide geographical areas provide an important new resource, yet there are only limited computational tools for its exploitation. Here we propose a hybrid computational model called BARDmaps for automated analysis of antibacterial susceptibility tests from surveillance records and for performing future predictions. BARDmaps was designed to include a structural computational model that can detect patterns among bacterial resistance changes as well as a behavioural computational model that can use the detected patterns to predict future changes in bacterial resistance. Data from the European Antimicrobial Resistance Surveillance Network (EARS-Net) were used to validate and apply the model. BARDmaps was compared with standard curve-fitting approaches used in epidemiological research. Here we show that BARDmaps can reliably predict future trends in bacterial resistance across Europe. BARDmaps performed better than other curve-fitting approaches for predicting future resistance levels. In addition, BARDmaps was also able to detect abrupt changes in bacterial resistance in response to outbreaks and interventions as well as to compare bacterial behaviour across countries and drugs. In conclusion, BARDmaps is a reliable tool to automatically predict and analyse changes in bacterial resistance across Europe. We anticipate that BARDmaps will become an invaluable tool both for clinical providers and governmental agencies to help combat the threat posed by antibiotic-resistant bacteria.

Hybrid Computation Model for Intelligent System Design by Synergism of Modified EFC with Neural Network

In recent past, it has been seen in many applications that synergism of computational intelligence techniques outperforms over an individual technique. This paper proposes a new hybrid computation model which is a novel synergism of modified evolutionary fuzzy clustering with associated neural networks. It consists of two modules: fuzzy distribution and neural classifier. In first module, mean patterns are distributed into the number of clusters based on the modified evolutionary fuzzy clustering, which leads the basis for network structure selection and learning in associated neural classifier. In second module, training and subsequent generalization is performed by the associated neural networks. The number of associated networks required in the second module will be same as the number of clusters generated in the first module. Whereas, each network contains as many output neurons as the maximum number of members assigned to each cluster. The proposed hybrid model is evaluated over wide spectrum of benchmark problems and real life biometric recognition problems even in presence of real environmental constraints such as noise and occlusion. The results indicate the efficacy of proposed method over related techniques and endeavor promising outcomes for biometric applications with noise and occlusion.

Hybrid Computational Model for Forecasting Taiwan Construction Cost Index

AbstractThe ability to accurately forecast future trends in the Construction Cost Index (CCI) is critical for construction cost managers to prepare accurate budgets for owners and prepare proper bids for contractors. However, CCI forecasting accuracy is affected by concurrent fluctuations in numerous factors (e.g., domestic/international economic conditions, economic indicators, and the price of energy). The main contribution of this study to the body of knowledge is the creation of a new procedure and a novel inference model, the self-adaptive structural radial basis neural network intelligence machine (SSRIM), to help cost engineers deal with the variability of CCI. In SSRIM, multivariate adaptive regression splines (MARS) analyzes the relative importance of various potential factors of influence on CCI, with those factors identified as significant assigned as input variables in the radial basis function neural network (RBFNN) and used to forecast CCI values. Meanwhile, the artificial bee colony (ABC) a...

Designing Heuristics: Hybrid Computational Models for Teaching the Negotiation of Complex Contracts

The negotiation of even the most straightforward real-world contracts tends to be quite complex. A contract with only 25 distinct issues with two alternatives each presents the parties with more than 33 million possible contracts, far too many to be evaluated exhaustively within feasible time constraints. Furthermore, contract issues that exhibit high levels of interdependence result in highly nonlinear utility functions with the possibility of many local optima. This paper employs hybrid computational models, integrating both simulated annealing and tabu list optimization, to aid in the design of social heuristics and institutional mechanisms that may serve to improve the effectiveness of human negotiators.

Non-linear feature selection-based hybrid computational intelligence models for improved natural gas reservoir characterization

With the recent state-of-the-art sensor-based data acquisition tools in the oil and gas industry, datasets sometimes come in very high dimensions. There is the need to extract the most relevant features out of these datasets to keep predictive models simple, accurate and free of pollution with irrelevant information. Multi-variate regression methods and evolutionary algorithms have been used to achieve this feat. However, the former could not handle the non-linearity in most problems that involve natural phenomena such as oil and gas reservoir characterization. The latter have been shown to introduce computational and time complexities, and are sometimes not very efficient. Accurate predictions of oil and gas reservoir properties are important for more efficient exploration and production of fossil energy resources. This paper proposes three non-linear feature selection based hybrid models in the prediction of porosity and permeability of two geographically and lithologically differentiated heterogeneous reservoirs. The hybrid models utilized the non-linear feature selection capabilities of Functional Networks (FN), Decision Trees (DT) and Fuzzy Ranking (FR) algorithms with the excellent functional approximation capability of Support Vector Machines (SVM). The results of the proposed models were then compared with a previously implemented FN-based Type-2 Fuzzy Logic hybrid model and the respective standalone components of the hybrid models. The comparative results provided more understanding of the architecture of these feature selection algorithms and further confirmed the importance of the feature selection process in oil and gas reservoir characterization. In the overall, the FN–SVM hybrid model showed superior performance in terms of correlation coefficient, root mean square error and execution time.

Hybrid computational model for predicting bridge scour depth near piers and abutments

Efficient bridge design and maintenance requires a clear understanding of channel bottom scouring near piers and abutment foundations. Bridge scour, a dynamic phenomenon that varies according to numerous factors (e.g., water depth, flow angle and strength, pier and abutment shape and width, material properties of the sediment), is a major cause of bridge failure and is critical to the total construction and maintenance costs of bridge building. Accurately estimating the equilibrium depths of local scouring near piers and abutments is vital for bridge design and management. Therefore, an efficient technique that can be used to enhance the estimation capability, safety, and cost reduction when designing and managing bridge projects is required. This study investigated the potential use of genetic algorithm (GA)-based support vector regression (SVR) model to predict bridge scour depth near piers and abutments. An SVR model developed by using MATLAB® was optimized using a GA, maximizing generalization performance. Data collected from the literature were used to evaluate the bridge scour depth prediction accuracy of the hybrid model. To demonstrate the capability of the computational model, the GA–SVR modeling results were compared with those obtained using numeric predictive models (i.e., classification and regression tree, chi-squared automatic interaction detector, multiple regression, artificial neural network, and ensemble models) and empirical methods. The proposed hybrid model achieved error rates that were 81.3% to 96.4% more accurate than those obtained using other methods. The GA–SVR model effectively outperformed existing methods and can be used by civil engineers to efficiently design safer and more cost-effective bridge substructures.

Mechanical cell-matrix feedback explains pairwise and collective endothelial cell behavior in vitro.

In vitro cultures of endothelial cells are a widely used model system of the collective behavior of endothelial cells during vasculogenesis and angiogenesis. When seeded in an extracellular matrix, endothelial cells can form blood vessel-like structures, including vascular networks and sprouts. Endothelial morphogenesis depends on a large number of chemical and mechanical factors, including the compliancy of the extracellular matrix, the available growth factors, the adhesion of cells to the extracellular matrix, cell-cell signaling, etc. Although various computational models have been proposed to explain the role of each of these biochemical and biomechanical effects, the understanding of the mechanisms underlying in vitro angiogenesis is still incomplete. Most explanations focus on predicting the whole vascular network or sprout from the underlying cell behavior, and do not check if the same model also correctly captures the intermediate scale: the pairwise cell-cell interactions or single cell responses to ECM mechanics. Here we show, using a hybrid cellular Potts and finite element computational model, that a single set of biologically plausible rules describing (a) the contractile forces that endothelial cells exert on the ECM, (b) the resulting strains in the extracellular matrix, and (c) the cellular response to the strains, suffices for reproducing the behavior of individual endothelial cells and the interactions of endothelial cell pairs in compliant matrices. With the same set of rules, the model also reproduces network formation from scattered cells, and sprouting from endothelial spheroids. Combining the present mechanical model with aspects of previously proposed mechanical and chemical models may lead to a more complete understanding of in vitro angiogenesis.

Sequence-specific flexibility organization of splicing flanking sequence and prediction of splice sites in the human genome.

More and more reported results of nucleosome positioning and histone modifications showed that DNA structure play a well-established role in splicing. In this study, a set of DNA geometric flexibility parameters originated from molecular dynamics (MD) simulations were introduced to discuss the structure organization around splice sites at the DNA level. The obtained profiles of specific flexibility/stiffness around splice sites indicated that the DNA physical-geometry deformation could be used as an alternative way to describe the splicing junction region. In combination with structural flexibility as discriminatory parameter, we developed a hybrid computational model for predicting potential splicing sites. And the better prediction performance was achieved when the benchmark dataset evaluated. Our results showed that the mechanical deformability character of a splice junction is closely correlated with both the splice site strength and structural information in its flanking sequences.

An Architecture for Personality-based, Nonverbal Behavior in Affective Virtual Humanoid Character

As humans we perceive other humans as individually different based – amongst other things – on a consistent pattern of affect, cognition, and behavior. Here we propose a biologically and psychologically grounded cognitive architecture for the control of nonverbal behavior of a virtual humanoid character during dynamic interactions with human users. Key aspects of the internal states and overt behavior of the virtual character are modulated by high-level personality parameters derived from the scientific literature. The virtual character should behave naturally and consistently while responding dynamically to the environment's feedback. Our architecture strives to yield consistent patterns of behavior though personality traits that have a modulatory influence at different levels of the hierarchy. These factors affect on the one hand high-level components such as ‘emotional reactions’ and ‘coping behavior’, and on the other hand low-level parameters such as the ‘speed of movements and repetition of gestures. Psychological data models are used as a reference to create a map between personality factors and patterns of behavior. We present a novel hybrid computational model that combines the control of discrete behavior of the virtual character moving through states of the interaction with continuous updates of the emotional state of the virtual character depending on feedback from interactions with the environment. To develop and evaluate the hybrid model, a testing scenario is proposed that is based on a turn-taking interaction between a human participant and a 3D representation of the humanoid character. We believe that our work contributes to individualized, and ultimately more believable humanoid artifacts that can be deploy in a wide range of application scenarios.

A cognitive computational model inspired by the immune system response.

The immune system has a cognitive ability to differentiate between healthy and unhealthy cells. The immune system response (ISR) is stimulated by a disorder in the temporary fuzzy state that is oscillating between the healthy and unhealthy states. However, modeling the immune system is an enormous challenge; the paper introduces an extensive summary of how the immune system response functions, as an overview of a complex topic, to present the immune system as a cognitive intelligent agent. The homogeneity and perfection of the natural immune system have been always standing out as the sought-after model we attempted to imitate while building our proposed model of cognitive architecture. The paper divides the ISR into four logical phases: setting a computational architectural diagram for each phase, proceeding from functional perspectives (input, process, and output), and their consequences. The proposed architecture components are defined by matching biological operations with computational functions and hence with the framework of the paper. On the other hand, the architecture focuses on the interoperability of main theoretical immunological perspectives (classic, cognitive, and danger theory), as related to computer science terminologies. The paper presents a descriptive model of immune system, to figure out the nature of response, deemed to be intrinsic for building a hybrid computational model based on a cognitive intelligent agent perspective and inspired by the natural biology. To that end, this paper highlights the ISR phases as applied to a case study on hepatitis C virus, meanwhile illustrating our proposed architecture perspective.

Hybrid simulation of brain–skull growth

This paper describes a hybrid model that includes both a standard finite element model and also volume-preserving structural modeling for a clinical application involving skull development in infants, with particular application to craniostosis modeling. To accommodate the growing brain, the skull needs to grow quickly in the first few months of life, and most of the growth of the skull at that time occurs at the sutures. Craniosynostosis, which is a developmental abnormality, occurs when one or more sutures are fused early in life (even in utero) while the skull is growing, resulting in an abnormal skull shape. To study normal brain–skull growth and to develop a model of craniosynostosis, we have developed a hybrid computational model to simulate the relationship between the growing deformable brain and the rigid skull. Our model is composed of the nine segmented skull plates as rigid surfaces, deformable sutures, and a volumetrically controllable deformable brain. The Cranial Index (ratio of biparietal width to fronto-occipital length) is measured during the simulation, showing a characteristic peak during development. Measures of linear growth along each dimension show characteristic increases over time. The hybrid simulation framework shows promise to support further investigations into abnormal skull development. By varying the properties of the sutures in our model, we can now simulate different craniosynostosis models, such as scaphocephaly and trigonocephaly. In this paper, we show results on the evolution of the Cranial Index as calculated using standard landmarks and compare to the normal index, and thereby evaluate our model by comparing it with patient data.

Cross-Reactive Immune Responses as Primary Drivers of Malaria Chronicity

The within-host dynamics of an infection with the malaria parasite Plasmodium falciparum are the result of a complex interplay between the host immune system and parasite. Continual variation of the P. falciparum erythrocyte membrane protein (PfEMP1) antigens displayed on the surface of infected red blood cells enables the parasite to evade the immune system and prolong infection. Despite the importance of antigenic variation in generating the dynamics of infection, our understanding of the mechanisms by which antigenic variation generates long-term chronic infections is still limited. We developed a model to examine the role of cross-reactivity in generating infection dynamics that are comparable to those of experimental infections. The hybrid computational model we developed is attuned to the biology of malaria by mixing discrete replication events, which mimics the synchrony of parasite replication and invasion, with continuous interaction with the immune system. Using simulations, we evaluated the dynamics of a single malaria infection over time. We then examined three major mechanisms by which the dynamics of a malaria infection can be structured: cross-reactivity of the immune response to PfEMP1, differences in parasite clearance rates, and heterogeneity in the rate at which antigens switch. The results of our simulations demonstrate that cross-reactive immune responses play a primary role in generating the dynamics observed in experimentally untreated infections and in lengthening the period of infection. Importantly, we also find that it is the primary response to the initially expressed PfEMP1, or small subset thereof, that structures the cascading cross-immune dynamics and allows for elongation of the infection.

A hybrid computational model for the effects of maspin on cancer cell dynamics

Cancer metastasis is a complex multistep process which allows cancer cells to establish new tumours in distant organs. The process of metastasis involves cell migration and invasion; it is what makes cancer a fatal disease. The efficiency of most cancer treatments depends on metastasis suppression. Maspin is a type II tumour metastasis suppressor which has multiple cellular effects. It has been described as a key regulatory protein in both the intracellular and extracellular environments. Maspin has been shown to reduce cell migration, invasion, proliferation and angiogenesis, and increase apoptosis and cell–cell adhesion in in vitro and in vivo experiments. The clinical data regarding the predictive effects of maspin expression are variable. To date, the whole cellular mechanisms that maspin uses to influence tumour cell behaviours have not been clearly defined. The diversity of the effects of maspin motivated us to develop an intelligent model to investigate its effects on cellular proliferation and migration. This paper reports a hybrid model of solid tumour growth in order to investigate the impact of maspin on the growth and evolutionary dynamics of the cancer cell. A feed-forward neural network was used to model the behaviours (proliferation, quiescence, apoptosis and/or movement) of each cell, which has been suggested as a suitable model of cell signalling pathways. Results show that maspin reduces migration by 10–40%, confirmed by published in vitro data. The model also shows a reduction in cell proliferation by 20–30% in the presence of maspin. So far, this is the first attempt to model the effect of maspin in a computational model to verify in vitro data. This will provide new insights into the tumour suppressive properties of maspin and inform the development of novel cancer therapies.

Empirical Study of Homogeneous and Heterogeneous Ensemble Models for Software Development Effort Estimation

Accurate estimation of software development effort is essential for effective management and control of software development projects. Many software effort estimation methods have been proposed in the literature including computational intelligence models. However, none of the existing models proved to be suitable under all circumstances; that is, their performance varies from one dataset to another. The goal of an ensemble model is to manage each of its individual models’ strengths and weaknesses automatically, leading to the best possible decision being taken overall. In this paper, we have developed different homogeneous and heterogeneous ensembles of optimized hybrid computational intelligence models for software development effort estimation. Different linear and nonlinear combiners have been used to combine the base hybrid learners. We have conducted an empirical study to evaluate and compare the performance of these ensembles using five popular datasets. The results confirm that individual models are not reliable as their performance is inconsistent and unstable across different datasets. Although none of the ensemble models was consistently the best, many of them were frequently among the best models for each dataset. The homogeneous ensemble of support vector regression (SVR), with the nonlinear combiner adaptive neurofuzzy inference systems-subtractive clustering (ANFIS-SC), was the best model when considering the average rank of each model across the five datasets.

Modeling the response of dual cross-linked nanoparticle networks to mechanical deformation

We develop a hybrid computational model for the behavior of a network of cross-linked polymer-grafted nanoparticles (PGNs). The individual nanoparticles are composed of a rigid core and a corona of grafted polymers that encompass reactive end groups. With the overlap of the coronas on adjacent particles, the reactive end groups can form permanent or labile bonds, which lead to the formation of a “dual cross-linked” network. To capture these multi-scale interactions, our approach integrates the essential structural features of the polymer grafted nanoparticles, the interactions between the overlapping coronas, and the kinetics of bond formation and rupture between the reactive groups on the chain ends. Via this model, we determine the tensile properties of the dual cross-linked samples. We find that the mechanical behavior of the network can be tailored by altering the bond energies of the labile bonds, the fraction of permanent bonds in the network and the thickness of the polymer corona. In particular, for a network with weaker labile bonds, an increase in fraction of permanent bonds and the contour length of the chain can yield a tough network that behaves like a polymeric material, which exhibits cold drawing/necking. On the other hand, similar changes to the network with stronger labile bonds lead to an increase in toughness, with the network characteristics being similar to that of a purely ductile material. Variations in the ratio between the strain rate and the bond rupture rate are also found to affect the response of the networks. Our model provides a powerful approach for predicting how critical features of the system affect the performance of cross-linked polymer-grafted nanoparticles.

Effect of nonlinearity in hybrid kinetic Monte Carlo–continuum models

Recently there has been interest in developing efficient ways to model heterogeneous surface reactions with hybrid computational models that couple a kinetic Monte Carlo (KMC) model for a surface to a finite-difference model for bulk diffusion in a continuous domain. We consider two representative problems that validate a hybrid method and show that this method captures the combined effects of nonlinearity and stochasticity. We first validate a simple deposition-dissolution model with a linear rate showing that the KMC-continuum hybrid agrees with both a fully deterministic model and its analytical solution. We then study a deposition-dissolution model including competitive adsorption, which leads to a nonlinear rate, and show that in this case the KMC-continuum hybrid and fully deterministic simulations do not agree. However, we are able to identify the difference as a natural result of the stochasticity coming from the KMC surface process. Because KMC captures inherent fluctuations, we consider it to be more realistic than a purely deterministic model. Therefore, we consider the KMC-continuum hybrid to be more representative of a real system.

Directed self-assembly of Janus nanorods in binary polymer mixture: towards precise control of nanorod orientation relative to interface

The ability to control the organization of anisotropic nanoparticles, such as nanorods, with high precision would greatly facilitate the fabrication of functional materials. Using a hybrid computational model, we systematically investigate the directed self-assembly of Janus nanorods, with two chemically different surface compartments, in binary polymer mixtures. Our simulations demonstrate that the energetic contributions from the surface chemistry of the Janus nanorods, the rod–rod interaction, and the spatial confinement from the polymer phases can be tailored to tune the orientation angle of the nanorods with respect to phase interface, leading to the formation of “lying”, tilt, and “standing” interfacial superstructures. A detailed insight into the mechanism regarding this precise control of nanorod orientation at the interface is obtained by evaluating the rod–phase interaction energy and the entropic energy of the tethered ligands on the rods. Furthermore, since the Janus rods are localized at the interface between two polymer phases, the structural evolution of the polymer nanocomposites is dramatically curtailed. This kinetic arrest is found to depend on the surface chemistry and the aspect ratio of Janus rods. The results demonstrated in this paper offer a novel approach to achieve morphological and kinetic control in nanoscopic composites towards unique photovoltaic and mechanical properties.