Sunday Olusanya Olatunji

Estimation of surface energies of hexagonal close packed metals using computational intelligence technique

We developed SVR-based model for estimating surface energy of materials.We used the developed SVR-based model to estimate surface energy of HCP metals.Our results show excellent agreement with the experimental values.Our model outperforms existing theoretical models. Surface phenomena such as corrosion, crystal growth, catalysis, adsorption and oxidation cannot be adequately comprehended without the full knowledge of surface energy of the concerned material. Despite these significances of surface energy, they are difficult to obtain experimentally and the few available ones are subjected to certain degree of inaccuracies due to extrapolation of surface tension to 0K. In order to cater for these difficulties, we have developed a model using computational intelligence technique on the platform of support vector regression (SVR) to establish a database of surface energies of hexagonal close packed metals (HCP). The SVR based-model was developed through training and testing SVR using fourteen experimental data of periodic metals. The developed model shows accuracy of 99.08% and 100% during training and testing phase, respectively, using test-set cross validation technique. The developed model was further used to obtain surface energies of HCP metals. The surface energies obtained from SVR-based model are closer to the experimental values than the results of the well-known existing theoretical models. The outstanding performance of this developed model in estimating surface energies of HCP metals with high degree of accuracy, in the presence of few experimental data, is a great achievement in the field of surface science because of its potential to circumvent experimental difficulties in determining surface energies of materials.

Performance Comparison of SVM and ANN in Predicting Compressive Strength of Concrete

Concrete compressive strength prediction is very important in structure and building design, particularly in specifying the quality and measuring performance of concrete as well as determination of its mix proportion. The conventional method of determining the strength of concrete is complicated and time consuming hence artificial neural network (ANN) is widely proposed in lieu of this method. However, ANN is an unstable predictor due to the presence of local minima in its optimization objective. Hence, in this paper we have studied the performance of support vector machine (SVM), a stable and robust learning algorithm, in concrete strength prediction and compare the result to that of ANN. It is found that SVM displayed a slightly better performance compared to ANN and is highly stable.

Application of computational intelligence technique for estimating superconducting transition temperature of YBCO superconductors

We developed CIM for estimating TC of doped YBCO superconductors.The developed CIM is characterized with high degree of accuracy.The results of the developed CIM agree well with the experimental results.TC of any doped YBCO superconductor can be accurately estimated using CIM. Yttrium barium copper oxide (YBCO) is a high temperature superconductor with excellent potential for long distance power transmission applications as well as other applications involving generation of high magnetic field such as magnetic resonance imaging machines in hospitals. Among the uniqueness of this material is its perpetual current carrying ability without loss of energy. Practical applications of YBCO superconductor depend greatly on the value of the superconducting transition temperature (TC) attained by YBCO superconductor upon doping with other external materials. The number of holes (i.e. doping) present in an atom of copper in CuO2 planes of YBCO superconductor controls its TC. Movement of the apical oxygen along CuO2 planes due to doping gives insight to the way of determining the effect of doping on TC using the bound related quantity (lattice parameter) that is easily measurable with reasonable high precision. This work employs excellent predictive and generalization ability of computational intelligence technique via support vector regression (SVR) to develop a computational intelligence-based model (CIM) that estimates the TC of thirty-one different YBCO superconductors using lattice parameters as the descriptors. The estimated superconducting transition temperatures agree with the experimental values with high degree of accuracy. The developed CIM allows quick and accurate estimation of TC of any fabricated YBCO superconductor without the need for any sophisticated equipment.

Estimation of physical, mechanical and hydrological properties of permeable concrete using computational intelligence approach

Four different models were developed for estimating properties of PC using SVR.The developed models were optimized using test-set-cross validation technique.The developed models are characterized with high CC, low RMSE and low MAE.The values of the estimated properties agreed well with the experimental values. Permeable concrete (PC) has gained a wide range of applications as a result of its unique properties which result into highly connected macro-porosity and large pore sizes. However, experimental determination of these properties is intensive and time consuming which necessitates the need for modeling technique that has a capability to estimate the properties of PC with high degree of accuracy. This present work estimates the physical, mechanical and hydrological properties of PC using computational intelligent technique on the platform of support vector regression (SVR) due to excellent generalization and predictive ability of SVR in the presences of few descriptive features. Four different models were built using twenty-four data-points characterized with four descriptive features. The estimated properties of PC agree well with experimental values. Excellent generalization and predictive ability recorded in the developed models indicate their high potentials for enhancing the performance of PC through quick and accurate estimation of its properties which are experimentally demanding and time consuming.

Modeling permeability and PVT properties of oil and gas reservoir using hybrid model based on type-2 fuzzy logic systems

Abstract In this work, the power of type-2 fuzzy logic system is demonstrated by using it to improve the prediction of permeability and PVT properties in a hybrid model setup. Hybrid intelligent model through the fusion of type-2 FLS (T2) and sensitivity-based linear learning method (SBLLM) is presented, and is hereby referred to as T2-SBLLM hybrid model. SBLLM, as a learning tool, has gained popularity due to its unique characteristics and performance. However, the generalization capability of SBLLM and other neural network-based solutions often depends on the nature of the dataset, particularly on whether uncertainty is present in the dataset or not. This work proposes a hybrid system through a combination of type-2 fuzzy logic systems (type-2 FLS) and SBLLM, and then uses it to model both permeability and PVT properties of oil and gas reservoir; type-2 FLS has been chosen to be a precursor to SBLLM in order to better handle uncertainties existing in the datasets. The type-2 FLS is used to first handle uncertainties in the reservoir data so that the final output is then passed to the SBLLM for training and then final prediction is done using the unseen testing dataset. Comparative studies have been carried out using different industrial reservoir data for both permeability and PVT properties. Empirical results show that the proposed T2-SBLLM hybrid system outperformed each of the type-2 FLS and SBLLM, as the two constituent models, in all cases, with the improvement made to the SBLLM performance being far higher compared to that of type-2 FLS, since type-2 FLS is originally adept at modeling uncertainties.

Computational intelligence method of estimating solid-liquid interfacial energy of materials at their melting temperatures

The reversible work required in forming an interface between a crystal and its coexisting liquid plays significant roles in many phase transformation and controls many processes such as nucleation, crystal growth, surface roughening and surface melting among others. Despite these significances, its experimental determination is difficult and only few experimental results are available in the literatures. This present work aims at circumventing these experimental challenges by developing a computational intelligence (CI) based model that relates solid-liquid interfacial energies of materials with their melting temperatures using support vector regression (SVR) with test-set cross validation optimization technique. The results of the developed CI-based model show persistent closeness to the few available experimental data than other compared existing theoretical models such as Miedema and den Broeder model, Granasy and Tegze model, Jiang combined model and Ewing model. The outstanding performance of the developed CI-based model as well as its implementation which only needs the value of melting temperature of the concerned material, is of immense importance in circumventing the experimental challenges in the practical attainment of equilibrium between a crystal and its melt for solid-liquid interfacial energy determination.

Computational Intelligence Approach for Estimating Superconducting Transition Temperature of Disordered MgB2 Superconductors Using Room Temperature Resistivity

Doping and fabrication conditions bring about disorder in MgB2 superconductor and further influence its room temperature resistivity as well as its superconducting transition temperature (). Existence of a model that directly estimates of any doped MgB2 superconductor from the room temperature resistivity would have immense significance since room temperature resistivity is easily measured using conventional resistivity measuring instrument and the experimental measurement of wastes valuable resources and is confined to low temperature regime. This work develops a model, superconducting transition temperature estimator (STTE), that directly estimates of disordered MgB2 superconductors using room temperature resistivity as input to the model. STTE was developed through training and testing support vector regression (SVR) with ten experimental values of room temperature resistivity and their corresponding using the best performance parameters obtained through test-set cross validation optimization technique. The developed STTE was used to estimate of different disordered MgB2 superconductors and the obtained results show excellent agreement with the reported experimental data. STTE can therefore be incorporated into resistivity measuring instruments for quick and direct estimation of of disordered MgB2 superconductors with high degree of accuracy.

Estimation of average surface energies of transition metal nitrides using computational intelligence technique

Several properties of transition metal nitrides (TMN) that make them useful in many applications are closely related to the state of their surfaces. Meanwhile, high melting points which characterize these materials make the determination of their surface energies experimentally difficult. This work presents a computational intelligence technique using support vector regression (SVR) to establish, for the first time, a complete database of average surface energies of all members of TMN series. SVR-based model was developed by training and testing SVR with best parameters obtained through test-set–cross-validation technique using thirty-five experimental data of periodic metals. The developed SVR-based model was used to estimate average surface energies of 3d, 4d and 5d-TMN, and the obtained results agree well with the existing theoretical values. Simple and effective computational approach of the developed model together with its accurate estimation of average surface energies of all the members of TMN series contributes to the uniqueness of this developed model over the existing theoretical methods.

A Novel Homogenous Hybridization Scheme for Performance Improvement of Support Vector Machines Regression in Reservoir Characterization

Hybrid computational intelligence is defined as a combination of multiple intelligent algorithms such that the resulting model has superior performance to the individual algorithms. Therefore, the importance of fusing two or more intelligent algorithms to achieve better performance cannot be overemphasized. In this work, a novel homogenous hybridization scheme is proposed for the improvement of the generalization and predictive ability of support vector machines regression SVR. The proposed and developed hybrid SVR HSVR works by considering the initial SVR prediction as a feature extraction process and then employs the SVR output, which is the extracted feature, as its sole descriptor. The developed hybrid model is applied to the prediction of reservoir permeability and the predicted permeability is compared to core permeability which is regarded as standard in petroleum industry. The results show that the proposed hybrid scheme HSVR performed better than the existing SVR in both generalization and prediction ability. The outcome of this research will assist petroleum engineers to effectively predict permeability of carbonate reservoirs with higher degree of accuracy and will invariably lead to better reservoir. Furthermore, the encouraging performance of this hybrid will serve as impetus for further exploring homogenous hybrid system.

Type-2 Fuzzy Logic Based Prediction Model of Object Oriented Software Maintainability

In this work, a maintainability prediction model for an object-oriented software system based on type-2 fuzzy logic system is presented. With the proliferation of object-oriented software systems, it has become very essential for concerned organizations to maintain those systems appropriately and effectively. However, it is pathetic to note that just very few number of maintainability prediction models are currently available for object oriented software systems. In this work, maintainability prediction model based on type-2 fuzzy logic systems is developed for an object-oriented software system. Earlier published object-oriented metric dataset was used in building the proposed model. Comparative studies involving the prediction accuracy of the proposed model was carried out in relation to the earlier used models on the same datasets. Empirical results from experiments carried out indicates that the proposed type-2 fuzzy logic system produced better and interesting results in terms of prediction accuracy measures authorized in object oriented software maintainability literatures. In fact, the proposed method satisfies the three major conditions stated in the literatures as basis to determining a good maintainability prediction model.