Showing papers in "Engineering Applications of Artificial Intelligence in 2015"

TL;DR: Three alternatives for fuzzy clustering of time series using DTW distance are proposed, including a DTW-based averaging technique proposed in the literature, which has been applied to the Fuzzy C-Means clustering.

TL;DR: This work proposes to estimate crowd density by an optimized convolutional neural network (ConvNet) first introduced for crowd density estimation, and introduces a cascade of two ConvNet classifier which improves both of the accuracy and speed.

TL;DR: This paper will review MAS concepts, architectures, develop platforms and processes, provide example applications, and discuss limitations, to survey applications of MAS in the control and operation of microgrids.

TL;DR: The Multi-Objective Fully Informed Particle Swarm (MOFIPS) optimization algorithm is found to return valid PIs for both rivers and for the three CL considered of 90%, 95% and 99%, indicating a viable option for straightforward design of more reliable interval-based streamflow forecasting models.

TL;DR: This review categorizes and delineates several crowd density estimation and counting methods that have been applied for the examination of crowd scenes and covers two main approaches which are direct approach (i.e., object based target detection) and indirect approach (e.g. pixel- based, texture-based, and corner points based analysis).

TL;DR: This proposed approach, believed to have taken full advantage of the strengths of both filter and wrapper methods, first uses the Partial Mutual Information based filter method to filter out most of the irrelevant and redundant features, and subsequently applies a wrapper method to further reduce the redundant features without degrading the forecasting accuracy.

TL;DR: It can be concluded that the DE and ACO algorithms are considerably more adaptive in optimizing the forecasting problem for the HNN model, which is based on fuzzy pattern-recognition and continuity equation.

TL;DR: This paper proposes a novel method, named the Classifier Selection Based on Clustering (CSBS), for ensemble creation, which uses the clustering of classifiers technique and investigates the influence of cluster number on the performance of the CSBC method.

TL;DR: A new evolutionary-based algorithm is developed to simultaneously evolve the topology and the connection weights of ANNs by means of a new combination of grammatical evolution and genetic algorithm, which produces much simpler ANNs that have better generalization ability and are easy to implement.

TL;DR: The machine learning based features outperform the human expert features, which supports the idea to use data mining to improve maintenance operations in this domain.

TL;DR: This research reviews the application of SI in GL through a comprehensive and extensive investigation and analysis of extant literature, which includes 115 publications in the last twenty years.

TL;DR: The concept of hesitance degree of hesitant fuzzy element which describes the decision maker?s hesitance in decision making process is introduced and several novel distance and similarity measures between hesitant fuzzy sets (HFSs) are developed, in which both the values and the numbers of values of HFE are taken into account.

TL;DR: Experimental comparisons on 90 realistic flowshop rescheduling instances with other efficient algorithms indicate that the proposed DTLBO algorithm is competitive in terms of its searching quality, robustness, and efficiency.

TL;DR: An email detection system that is designed based on an improvement in the negative selection algorithm and the proposed model with the best accuracy is used to differentiate between spam and non-spam in a network that is developed based on a client–server network for spam detection.

TL;DR: A novel hybrid approach for rectifying the data imbalance problem by employing k Reverse Nearest Neighborhood and One Class support vector machine (OCSVM) in tandem is proposed and it turned out that GMDH, SVM and LR are not statistically different and GMDH yielded very high Area Under Curve at ROC.

TL;DR: Results for ORPD problem demonstrate superiority in terms of solution quality of the GBTLBO and MGBTLBO algorithms over original TLBO algorithm and other algorithm.

TL;DR: A new methodology for simultaneous sizing, topology, and shape optimization of free-form steel space-frame roof structures with complex geometries using evolutionary computing is presented.

TL;DR: A new approach for semantic similarity measuring which is based on edge-counting and information content theory is presented, and the proposed measure nonlinearly transforms the weighted shortest path length between the compared concepts to achieve the semantic similarity results.

TL;DR: The results show that the proposed graph-theoretic approach for unsupervised feature selection has produced consistently better classification accuracies and has been compared to the well-known and state-of-the-art methods.

TL;DR: A better variation of CLPSO is proposed, called the parallel comprehensive learning particle swarm optimizer (PCLPSO) which has multiple swarms based on the master-slave paradigm and works cooperatively and concurrently.

TL;DR: A two level hierarchical control method for integrating EVs into the distribution network is proposed to coordinate the self-interests and operational constraints of two actors, the EV owner and Distribution system operator (DSO), facilitated by the introduction of the fleet operator (FO) and the grid capacity market operator (CMO).

TL;DR: A forecasting model combining the modified fuzzy c-means and information granulation for solving the problem of time series long-term prediction and results show that the proposed model is both accurate and interpretable.

TL;DR: A possible architecture for FDDR systems is suggested, and the immune system concepts, components and mechanisms are organized in such a way to show how they are applied for each of the detection, diagnosis and recovery tasks.

TL;DR: The proposed methodology reveals better generalization capability compared to previous works and it is validated by an online bearing fault diagnosis and the proposed strategy can be applied for the decision making of several assets.

TL;DR: A novel population based metaheuristic search algorithm by combination of gravitational search algorithm (GSA) and quantum computing (QC), called a Binary Quantum-Inspired Gravitational Search Algorithm (BQIGSA), is proposed to present a robust optimization tool to solve binary encoded problems.

TL;DR: An adaptive control algorithm is presented for nonlinear vibration control of large structures subjected to dynamic loading based on integration of a self-constructing wavelet neural network developed specifically for structural system identification with an adaptive fuzzy sliding mode control approach.

TL;DR: A new standard Thai handwritten character dataset is provided for comparison of feature extraction techniques and methods and the results show that the local gradient feature descriptors significantly outperform directly using pixel intensities from the images.

TL;DR: This paper shows how Least Squares Support Vector Machines (LS-SVMs) can be used effectively for early fault detection in an online fashion and illustrates a nonlinear auto-regressive (NAR) model, thus a supervised learning technique, in the LS-SVM framework.

TL;DR: A novel matrix factorization method called IMULT, which utilizes imputed rating to mitigate the sparsity problem, is proposed and results show that IMULT performed better than ALS, SGD, RSGD, SVD++ and MULT.

TL;DR: Experimental results show that MAPSO can substantially enhance the ability of PSOs to jump out of the local optimal solutions and significantly improve the search efficiency and convergence speed.