Showing papers in "Engineering Applications of Artificial Intelligence in 2017"

TL;DR: A broad spectrum of FNN optimization methodologies including conventional and metaheuristic approaches are summarized, which provides interesting research challenges for future research to cope-up with the present information processing era.

TL;DR: A new model based on a combination of adaptive neuro-fuzzy inference system (ANFIS) and satin bower bird optimization algorithm (SBO) to reach more accurate software development effort estimations is presented.

TL;DR: In this paper, some series of averaging aggregation operators have been presented under the intuitionistic fuzzy environment by considering the degrees of hesitation between the membership functions and new operational laws have been proposed for overcoming these shortcoming.

TL;DR: The proposed GWO-KELM prediction model is promising to serve as a powerful early warning tool with excellent performance for bankruptcy prediction, and rigorously compared with three competitive KELM methods.

TL;DR: This work presents an overview of the improved FPN theories and models from the perspectives of reasoning algorithms, knowledge representations and FPN models, and offers directions for future research to improve the FPN performance.

TL;DR: The efficacy and superiority of the proposed Jaya algorithm based PID controller is shown by comparing simulation results with other algorithms like particle swarm optimization (PSO), differential evolution (DE), Nelder-Mead simplex (NMS), elephant herding optimization (EHO) and teacher learner based optimization (TLBO).

TL;DR: A hybrid multi-objective discrete grey wolf optimizer (HMOGWO) is proposed to solve the dynamic welding scheduling problem and outperforms other algorithms in terms of convergence, spread and coverage.

TL;DR: The classification performance of deep learning algorithm such as deep belief networks with Restricted Boltzmann Machines are evaluated and compared with some popular credit scoring models such as logistic regression, multi-layer perceptron and support vector machine and found that DBN yields the best performance.

TL;DR: Simulations over 10 heterogeneous wireless sensor networks show that LEACH-SF outperforms the existing cluster-based routing protocols and can be adaptively tuned via ABC for any application.

TL;DR: A new hybrid methodology is developed by combining linear and nonlinear exponential smoothing models from innovation state space (ETS) with artificial neural network (ANN) to glorify the chances of capturing different combination of linear and/or nonlinear patterns in time series.

TL;DR: A new posteriori multi-objective optimization algorithm named as multi- objective Jaya (MO-Jaya) algorithm is proposed which can provide multiple optimal solutions in a single simulation run and the results have shown the better performance of the proposed algorithm.

TL;DR: A novel copy-move forgery detection method based on hybrid features that can precisely detect duplicated regions even after distortions such as rotation, scaling, JPEG compression and adding noise is proposed.

TL;DR: Simulation results show that the proposed approach combining the firefly algorithm with granular computing provides very good results in optimal design of MNNs.

TL;DR: An attempt has been made for review on AI applications in Computer Aided Process Planning (CAPP) and manufacturing and role of Evolutionary Techniques (ET) in intelligent system development, execution of PP activities and manufacturing is described.

TL;DR: A novel feature selection method call SYMON which uses symmetrical uncertainty and harmony search to weigh features with respect to their dependency to class labels, which helps to identify powerful features in retrieving the least frequent class labels.

TL;DR: Maritime inventory routing problem is addressed in this paper to satisfy the demand at different ports during the planning horizon and an effective search heuristics named Particle Swarm Optimization for Composite Particle (PSO-CP) is employed.

TL;DR: A novel data clustering algorithm based on modified Gravitational Search Algorithm is proposed, which is called Bird Flock Gravitational search Algorithm (BFGSA), which introduces a new mechanism into GSA to add diversity, a mechanism which is inspired by the collective response behavior of birds.

TL;DR: A novel particle swarm optimization based VSG (PSOVSG) approach is proposed to iteratively generate the most feasible virtual samples over the search-space, and results show the proposed PSOVSG achieves better performance than other methods.

TL;DR: A genetic-based algorithm as a meta-heuristic method to address static task scheduling for processors in heterogeneous computing systems and improves the performance of genetic algorithm through significant changes in its genetic functions and introduction of new operators that guarantee sample variety and consistent coverage of the whole space.

TL;DR: It is shown that the super-resolution-based approach improves the performance of the evaluated texture methods and thus outperforms the state of the art in benign/malignant tumor classification.

TL;DR: The aim of this paper is to rectify the lack of a survey paper in this area by providing a self-contained resource that will centralize the current state of the art, document the historical progression of Bayesian Networks in agriculture and indicate possible future lines of research.

TL;DR: The proposed SVM-DS model is found to be more accurate and effective in handling multi-faults diagnostic and classification problems commonly faced in the industries, as compared to the original SVM method.

TL;DR: It is shown in this paper that this method effectively generates the Pareto front and also, this method is easy to implement and algorithmically simple.

TL;DR: The efficacy of multitask optimization is demonstrated as a paradigm promising enhanced productivity in future decision making processes through an algorithmic realization based on a coevolutionary framework.

TL;DR: This model simultaneously considers economic, responsiveness and social aspects in designing a hub-and-spoke network and proposes a hybrid two-phase solution method based on possibilistic programming, fuzzy multi-objective programming and an efficient algorithm called self-adaptive differential evolution algorithm.

TL;DR: The hybrid metaheuristic regression model is a promising and practical methodology for real-time tracking of corrosion in steel rebar and civil engineers can use the hybrid model to schedule maintenance process that leads to risk reduction of structure failure and maintenance cost.

TL;DR: A novel Semi-Supervised Fuzzy Clustering algorithm with Spatial Constraints (SSFC-SC) that combines those processes for dental segmentation that has better accuracy than the original semi-supervised fuzzy clustering and other relevant methods is proposed.

TL;DR: The work proposes an integrated risk assessment route in relation to metropolitan construction projects based on the fuzzy set theory and explores the concept of risk matrix to categorise various risk factors at different levels of severity for the establishment of necessary actions requirement plan.

TL;DR: In this article, a theoretical evaluation model based on decision support methods for the residential house construction materials and elements selection is presented. And the proposed new theoretical composite model for selection of elements, materials and other aspects of sustainability can be practically applied in creating the decision support system for the selection of single-family house elements and materials.

TL;DR: A neural network module has been used as a discontinuous control part of the NTSMC to enhance the performance of the controller due to chattering phenomenon and an optimal Unscented Kalman Filter algorithm has been introduced that estimates the noise statistics recursively within the algorithm.