Soft computing

About: Soft computing is a research topic. Over the lifetime, 6710 publications have been published within this topic receiving 118508 citations.

A novel soft computing method for engine RUL prediction

Abstract: Prognostics is an engineering discipline focused on predicting the Remaining Useful Life (RUL) of a system or a component using raw multimedia (sensor) data. This paper presents a novel machine learning model for this task, which includes a smart ensemble of gradient boosted trees (GBT) and feed-forward neural networks. It incorporates discussions on the poor performance of MLPs and the need of ensemble models. Initial stages of data exploration and pre-processing are also comprehensively documented. Experiments are performed on the four run-to-failure C-MAPSS datasets defined by the 2008 PHM Data Challenge Competition. It concludes by presenting evaluations of multiple prediction models like MLP, SVR, CNN & gradient boosted trees (GBT). Gradient Boosted Trees are efficient in the sense that they produce an encouraging scoring model with minimum effort and also return feature importance information. The proposed method uses stacking ensemble of feed-forward neural networks and gradient boosted trees, as first level learner, and, a single-hidden layer- fully-connected neural network as the meta learner. This ensemble provides better results than any of the models alone or weighted average of their predictions. The proposed method outperforms MLP, SVR, CNN and GBT.

Comparison of Groundwater Level Models Based on Artificial Neural Networks and ANFIS.

Abstract: Water table forecasting plays an important role in the management of groundwater resources in agricultural regions where there are drainage systems in river valleys. The results presented in this paper pertain to an area along the left bank of the Danube River, in the Province of Vojvodina, which is the northern part of Serbia. Two soft computing techniques were used in this research: an adaptive neurofuzzy inference system (ANFIS) and an artificial neural network (ANN) model for one-month water table forecasts at several wells located at different distances from the river. The results suggest that both these techniques represent useful tools for modeling hydrological processes in agriculture, with similar computing and memory capabilities, such that they constitute an exceptionally good numerical framework for generating high-quality models.

A novel multi attribute decision making approach for location decision under high uncertainty

Abstract: A novel soft computing approach for location decision under uncertainty is presented.A new notion named as cloud based design optimization (CBDO) which tackles high uncertainty is utilized.It is revealed out that location decision is very sensitive to the consideration of uncertainty.This study contributes to by handling high uncertainties in a location selection by utilizing CBDO as a first time.CBDO can be a helpful supportive tool for decision makers in providing solution under high uncertainty. Location selection is a multi dimensional issue which requires consideration of quantitative and qualitative evaluation criteria. Some of these criteria may have imprecise and uncertain data which make the location selection decision hard to progress. Although many multi attribute decision making (MADM) techniques are utilized in location decision study field, there is a lack of studies which provide solutions by considering high number of supply chain uncertainties. In this study, against the drawbacks of traditional MADM techniques, a novel MADM approach is applied for location decision under high uncertainty as a first time. In the proposed model, a new notion named as cloud based design optimization (CBDO) is utilized because CBDO can take into consideration certain and uncertain factors simultaneously. Furthermore, it provides robust solution within worst case scenario to existing approaches by mediating between aspects of fuzzy set theory and probability distributions. Robustness enables decision makers have managerial and operational foresights about possible unexpected situations, and take necessary actions against risk. An illustrative example is conducted in warehouse location selection problem area to indicate the performance of the proposed approach. It is revealed out that location decision is very sensitive to the consideration of uncertainty and CBDO can be a helpful supportive tool for decision makers in providing solution under high uncertainty.

Improving Software Effort Estimation Using Neuro-Fuzzy Model with SEER-SEM

Abstract: 3 Abstract - Accurate software development effort estimation is a critical part of software projects. Effective development of software is based on accurate effort estimation. Although many techniques and algorithmic models have been developed and implemented by practitioners, accurate software development effort prediction is still a challenging endeavor in the field of software engineering, especially in handling unce rtain a nd imprecise inputs and collinear characteristics. In order to address these issues, previous researchers developed and evaluated a novel soft computing framework. The aims of our research are to evaluate the prediction performance of the proposed neuro-fuzzy model with Sy stem Evaluation and Estimation of Resource Software Estimation Model (SEER- SEM) in software estimation practices and to apply the proposed architecture that combines the neuro-fuzzy technique with different algorithmic models. In this paper, an approach combining the neuro-fuzzy technique and the SEER -SEM effort estimation algorithm is described. This proposed model possesses positive characteristics such as l earning ability, decreased sensitivity, effective generalization, and knowledge integration for introducing the neuro-fuzzy technique. Moreover, continuous rating values and linguistic values can be inputs of the proposed model for avoiding the large estimation deviation among similar projects. The performance of the proposed model is accessed by designing and conducting evaluation with published projects and industrial data. The evaluation results indicate that estimation with our proposed neuro-fuzzy model containing SEER-S EM is improved in comparison with the estimation results that only use SEER- SEM algorithm. At the same time, the results of this research also demonstrate that the general neuro-fuzzy framework can function with various algorithmic models for improving the performance of software effort estimation.

MICAI 2009 : advances in artificial intelligence : 8th Mexican International Conference on Artificial Intelligence, Guanajuato, México, November 9-13, 2009 : proceedings

Abstract: Invited Talks.- Semantic Management of Heterogeneous Documents.- Logic and Reasoning.- Possibilistic Well-Founded Semantics.- Ontologies, Knowledge Management and Knowledge-Based Systems.- ACO for Solving the Distributed Allocation of a Corporate Semantic Web.- Implementing PS-Merge Operator.- Uncertainty and Probabilistic Reasoning.- Generating Explanations Based on Markov Decision Processes.- Compiling Multiply Sectioned Bayesian Networks: A Comparative Study.- Cosine Policy Iteration for Solving Infinite-Horizon Markov Decision Processes.- Transformer Diagnosis Using Probabilistic Vibration Models.- Intelligent Aircraft Damage Assessment, Trajectory Planning, and Decision-Making under Uncertainty.- A Scrabble Heuristic Based on Probability That Performs at Championship Level.- Natural Language Processing.- From Semantic Roles to Temporal Information Representation.- Dependency Language Modeling Using KNN and PLSI.- Supervised Recognition of Age-Related Spanish Temporal Phrases.- Using Nearest Neighbor Information to Improve Cross-Language Text Classification.- Ranking Refinement via Relevance Feedback in Geographic Information Retrieval.- Data Mining.- A Complex Networks Approach to Demographic Zonification.- Multiscale Functional Autoregressive Model for Monthly Sardines Catches Forecasting.- Discretization of Time Series Dataset with a Genetic Search.- Mining Social Networks on the Mexican Computer Science Community.- Machine Learning.- Probabilistic Graphical Markov Model Learning: An Adaptive Strategy.- Support Vector Optimization through Hybrids: Heuristics and Math Approach.- Pattern Recognition.- On-Line Signature Verification Based on Genetic Optimization and Neural-Network-Driven Fuzzy Reasoning.- Diagnosis of Cervical Cancer Using the Median M-Type Radial Basis Function (MMRBF) Neural Network.- Quasi-invariant Illumination Recognition for Appearance-Based Models, Taking Advantage of Manifold Information and Non-uniform Sampling.- Computer Vision and Image Processing.- Automatic Camera Localization, Reconstruction and Segmentation of Multi-planar Scenes Using Two Views.- The Nonsubsampled Contourlet Transform for Enhancement of Microcalcifications in Digital Mammograms.- Denoising Intra-voxel Axon Fiber Orientations by Means of ECQMMF Method.- A Profilometric Approach for 3D Reconstruction Using Fourier and Wavelet Transforms.- Vector Quantization Algorithm Based on Associative Memories.- Robotics.- A Two-Stage Relational Reinforcement Learning with Continuous Actions for Real Service Robots.- People Detection by a Mobile Robot Using Stereo Vision in Dynamic Indoor Environments.- Planning and Scheduling.- SAT Encoding and CSP Reduction for Interconnected Alldiff Constraints.- Phase Transition in the Bandwidth Minimization Problem.- Planning for Conditional Learning Routes.- A New Backtracking Algorithm for Constructing Binary Covering Arrays of Variable Strength.- Pipelining Memetic Algorithms, Constraint Satisfaction, and Local Search for Course Timetabling.- Fuzzy Logic.- Fuzzy Relational Compression Applied on Feature Vectors for Infant Cry Recognition.- Parametric Operations for Digital Hardware Implementation of Fuzzy Systems.- Fuzzy Logic for Combining Particle Swarm Optimization and Genetic Algorithms: Preliminary Results.- Optimization of Type-2 Fuzzy Integration in Modular Neural Networks Using an Evolutionary Method with Applications in Multimodal Biometry.- Neural Networks.- st-Alphabets: On the Feasibility in the Explicit Use of Extended Relational Alphabets in Classifier Systems.- Comparison of Neural Networks and Support Vector Machine Dynamic Models for State Estimation in Semiautogenous Mills.- Using Wolfe's Method in Support Vector Machines Learning Stage.- Direct Adaptive Soft Computing Neural Control of a Continuous Bioprocess via Second Order Learning.- Intelligent Tutoring Systems.- A Kohonen Network for Modeling Students' Learning Styles in Web 2.0 Collaborative Learning Systems.- Teaching-Learning by Means of a Fuzzy-Causal User Model.- Inferring Knowledge from Active Learning Simulators for Physics.- Bioinformatics and Medical Applications.- Leukocyte Recognition Using EM-Algorithm.- An Automaton for Motifs Recognition in DNA Sequences.- Hybrid Intelligent Systems.- A New Method for Optimal Cropping Pattern.- MultiQuenching Annealing Algorithm for Protein Folding Problem.- Outlier Detection with a Hybrid Artificial Intelligence Method.- Wind Speed Forecasting Using a Hybrid Neural-Evolutive Approach.- Hybridization of Evolutionary Mechanisms for Feature Subset Selection in Unsupervised Learning.- Evolutionary Algorithms.- A Particle Swarm Optimization Method for Multimodal Optimization Based on Electrostatic Interaction.- Ranking Methods for Many-Objective Optimization.- Why Unary Quality Indicators Are Not Inferior to Binary Quality Indicators.- Using Copulas in Estimation of Distribution Algorithms.- Redistricting by Square Cells.- Finding Minimal Addition Chains with a Particle Swarm Optimization Algorithm.- Linear Wind Farm Layout Optimization through Computational Intelligence.- Building Blocks and Search.- An Analysis of Recombination in Some Simple Landscapes.- An Empirical Investigation of How Degree Neutrality Affects GP Search.