Papers by Keyword: Soft Computing

Abstract: High-entropy alloys (HEAs) have excellent properties that are being explored for potential applications in many engineering fields. Their excellent properties strongly depend on their phases. The vastness of alloy compositions that can be synthesized makes it extremely challenging to experimentally investigate all the possible HEA types. To mitigate these challenges, more efficient and systematic computational techniques can be applied to the existing experimental data to accelerate HEA design and discovery. Therefore, this study developed three soft computing classification models based on artificial neural network, k-nearest neighbor (kNN), and support vector machine (SVM) to classify solid solution, amorphous and intermetallic phases in HEAs. Empirical studies showed that hyperparameter optimization improved classification accuracies of the classifiers with kNN (92%) outperforming ANN (86%) and SVM (90%) using all five predictive features. Feature selection did not improve the classification accuracy of any of the model. This studied demonstrated the importance of applying soft computing techniques and hyperparameter optimization for enhancing the classification accuracies of models to predict the phases in HEAs.

Abstract: Fabricating three dimensional shaped surfaces from flat sheet metals by laser forming, both out-of-plane and in-plane deformations are required. This article presents the modeling of coupling mechanism activated laser forming of sheet metals based on experimental data for prediction and optimization of bending and thickening deformations. Experiments were performed based on a central composite design of experiments on coupling mechanism based laser metal forming process considering the input process parameters like laser power, scan speed and spot diameter, bending and thickening were taken as the outputs. Neural network and neuro-fuzzy system-based models were developed to carry out both forward and inverse modeling of the laser metal forming process under the coupling mechanism. Multi-objective optimization based on the non-dominated sorting genetic algorithm was used to obtain multiple optimal solutions to achieve different amounts of out-of-plane and in-plane deformations. The proposed method could guide for a suitable selection of the process parameters to produce three-dimensional shapes utilizing coupling mechanism-based laser forming using multiple laser line heating.

Abstract: In the last two decades, developing countries are facing heavy increase in diabetes among their population that is leading to other severe diseases. Hence, there is a great need to develop some effective prediction methods to prevent diabetes. In this paper an attempt has been made to develop Firefly-BAT (FFBAT) optimized Rule Based Fuzzy Logic (RBFL) prediction algorithm for diabetes. The algorithm has two main steps. First, Locality Preserving Projections (LPP) algorithm is used for feature reduction and then classification of diabetes is done by means of RBFL classifier. LPP algorithm has been used to identify the related attributes and then the fuzzy rules are produced from RBFL. The rules are optimized using FFBAT algorithm. Next, the fuzzy system is designed with the help of optimized fuzzy rules and membership functions that will classify the diabetes data. FFBAT is the optimization algorithm which combines the features of BAT and Firefly (FF) optimization techniques. The experiment analysis shows that the RBFL-FFBAT algorithm outperforms the existing approaches.

Abstract: This paper presents an overview of research works on the utilizing of soft computing in the optimization of process parameters and in the prediction of thin film properties in sputtering processes. The papers from this review were obtained from relevant databases and from various scientific journals. The papers collected were published from 2008 to 2012. The focus of the review is to provide an outlook on the utilization of soft computing techniques in sputtering processes. Based on the review, the soft computing techniques which have been applied so far are ANN, GA and Fuzzy Logic. The first finding of this review is that soft computing technique is a promising and more reliable approach to optimize and predict process parameters compared to the traditional methods. The second finding is that the utilizing of soft computing techniques in sputtering processes are still limited and still in exploratory phase as they have not yet been extensively and stably applied. The techniques applied are also limited to ANN, GA and Fuzzy, whereas the exploration into other techniques is also necessary to be conducted in order to seek the most reliable technique and so as to expand the application of soft computing approach. Future research could focus on the exploration of other soft computing techniques for optimization in order to find the best optimization techniques based on the specific processes.

Abstract: In neural networks modeling approach, a non-linear model is estimated based on machine learning methods. The study discusses, analytically and numerically demonstrates the quality and interpretability of the obtained prediction accuracy results from prediction models based on advanced statistical methods and models based on neural networks (intelligent methods). Both proposed approaches are applied to the financial time series of s of VUB bond prices. We found that it is possible to achieve significant risk reduction in managerial decision-making by applying intelligent forecasting models based on the latest information technologies. In a comparative study is shown, that both presented modeling approaches are able to model and predict high frequency data with reasonable accuracy, but the neural network approach is more effective.

Abstract: In the present paper the influence of the main cutting parameters on process performance during longitudinal turning of PA66 GF-30 Glass Fiber Reinforced Polyamide is investigated. The selected cutting parameters are cutting speed and feed-rate whilst depth of cut is kept constant. As outputs (responses), cutting force components F_t, F_V and F_r were selected. Test specimens in the form of round bars and cemented carbide cutting tool were used during the experimental process. Fifteen experiments were conducted having all different combinations of cutting parameter values. Analysis of Variance (ANOVA), statistical approaches and soft computing techniques (artificial neural network) were applied in order to formulate stochastic models for relating the responses with main cutting parameters. The results obtained, indicate that the proposed soft computing techniques can be effectively used to predict the cutting force components (F_t, F_V and F_r) thus; facilitating decision making during process planning since costly and time-consuming experimentation can be avoided.

Abstract: Rough set theory is a kind of ambiguity and imprecision new mathematical tools, using precise mathematical analysis of imprecise system an ideal method. Rough set theory has powerful data reduction capability, this paper rough set theory to model the stock time series data, reduction, rule extraction, study the ups and downs of the relationship between the stock price, the use of advanced data mining techniques to dig out price linkage between stock association rules, has a very important significance.

Abstract: The main aim of this paper is to analyze the various recruitment decision making policies using granular computing based on rough set perspective and fuzzy distance approach for recruiting a candidate in any organization. An information table has been presented in this article which consists of various factors like appearance, qualification, experience and communication skills to evaluate a candidate for recruitment. Depending upon the granularity of knowledge obtained from the information table, the concept of rough set has been applied to generate fuzzy decision rules which in turns form the eligibility criteria for the candidates appearing in the interview for recruitment. The experts in the interview committee have stated their opinion about the candidates linguistically. A relationship has been established between the eligibility criteria required for the job and the expert opinions about the candidates appeared in the interview using a fuzzy subset representation. The index of fuzziness of various experts’ opinion are measured and compared. A candidate with higher grade of merit has been selected using fuzzy distance approach.

Abstract: Path planning is one of the most important and challenging problems of mobile robot. It is one of the keys that will make the mobile robots fully autonomous. In this paper, we summarized the application of soft computing approaches in path planning for mobile robot. Finally the future works of path planning for mobile robots are prospected.

Abstract: This paper discusses the research of optimal process for lightguiding plate of backlight module of liquid crystal display. The PMMA material was used on lightguiding plate. This paper indicates that the different processing parameters (mold temperature, injection temperature, first period injection speed, second period injection speed, third period injection speed, packing pressure and packing time) are important for optimal research for lightguiding plate of backlight module. This paper introduces the extension engineering, simulated annealing and genetic algorithm on soft computing for optimal process and compares the results with experiment. The results show that the optimal process group is A1 B1C2 D3 E2 F2 G3 for extension engineering, simulated annealing, genetic algorithm or experiment. The mold temperature is the most important processing parameter of the flatness of lightguiding plate for soft computing and experiment. The calculation times for extension engineering, simulated annealing and genetic algorithm are less than experiment’s time.