International Journal of Computational Intelligence and Applications

Traditional machine learning methods for water body extraction need complex spectral analysis and feature selection which rely on wealth of prior knowledge. They are time-consuming and hard to satisfy our request for accuracy, automation level and a wide range of application. We present a novel deep learning framework for water body extraction from Landsat imagery considering both its spectral and spatial information. The framework is a hybrid of convolutional neural networks (CNN) and logistic regression (LR) classifier. CNN, one of the deep learning methods, has acquired great achievements on various visual-related tasks. CNN can hierarchically extract deep features from raw images directly, and distill the spectral–spatial regularities of input data, thus improving the classification performance. Experimental results based on three Landsat imagery datasets show that our proposed model achieves better performance than support vector machine (SVM) and artificial neural network (ANN).

The cytochrome P450 (CYP) superfamily, exists in the human liver, is responsible for more than 90% of the metabolism of clinical drugs. So it is necessary to adopt a new kind of computer simulation methods that can predict the rejection capability of compounds for a concrete CYPs isoform. In this work, a model is presented for classification of CYP450 1A2 inhibitors and noninhibitors based on a multi-tiered deep belief network (DBN) on a large dataset. The dataset composed of more than 13,000 heterogeneous compounds was acquired from PubChem. Firstly, 139 2D and 53 3D descriptors are calculated and preprocessed. Then, the unsupervised learning method is used to train DBN model to automatically extract multiple levels of distributed representation from the descriptors of training set. Finally, by using testing set and external validation set, we evaluate the classified performance of DBN for the inhibition of CYP1A2. Meanwhile, the proposed model is compared with shallow machine learning models (support vector machine (SVM) and artificial neural network (ANN)). We also discussed the performance of DBN by comparing it with different features combination. The experimental results showed that DBN has a better prediction ability compared with SVM and ANN. And these models combined with the features of 2D and 3D obtain the best forecast accuracy.

As improving system reliability in a basic system has been always one of the important concerns in reliability engineering; many studies have been developed in this regard. In this paper, a novel intelligent PSO (PSO-IM) is proposed. In suggested approach two different types of mutation operator, which controlled by Fuzzy controller, are applied to standard PSO for finding the best solution of reliability-redundancy allocation problems (RRAP). Also a heuristic inertia weight equation is introduced in our proposed PSO-IM. The main objective of our solution is to achieve maximum reliability in a basic system with acceptable redundancy allocation subject to cost, weight, volume. The proposed method (PSO-IM) significantly improves the search ability of basic PSO and finds the maximum reliability in comparison with previous works.

To uncover an appropriate latent subspace for data representation, we propose in this paper a new extension of the random forests method which leads to the unsupervised feature selection called Feature Selection with Random Forests (RFS) based on SOM variants that evaluates the out-of-bag feature importance from a set of partitions. Every partition is created using a several bootstrap samples and a random features subset. We obtain empirical results on 19 benchmark datasets specifying that RFS, boosted with a recursive feature elimination (RFE) method, can lead to important enhancement in terms of clustering accuracy with a very restricted subset of features.

Simulations are performed on nine different benchmarks, including face data, handwritten digit data, and document data. Promising experimental results and theoretical analysis prove the efficiency and effectiveness of the proposed method for feature selection in comparison with competitive representative algorithms.

The solution set of any multi-objective optimization problem can be expressed as an approximation set of Pareto front. The number of solution candidates in this set could be large enough to cover the entire Pareto front as a general belief. However, among the sufficiently close points on the objective space, almost same accurate solutions can obtain. Hence, in this set, it is possible to eliminate some of the solutions without detriment to the overall performance. Therefore, in this research, the authors propose a population size reduction method which systematically reduced the population size based on the distance and angle relations between any consecutive solutions. The results are evaluated based on two-objective benchmark problems and compared with the results of NSGA-II algorithm with respect to three different performance evaluation metrics.

A number of benchmark problems exist for evaluating multi-objective evolutionary algorithms (MOEAs) in the objective space. However, the decision space performance analysis is a recent and relatively less explored topic in evolutionary multi-objective optimization research. Among other implications, such analysis can lead to designing more realistic test problems, gaining better understanding about optimal and robust design areas, and design and evaluation of knowledge-based optimization algorithms. This paper complements the existing research in this area and proposes a new method to generate multi-objective optimization test problems with clustered Pareto sets in hyper-rectangular defined areas of decision space. The test problem is parametrized to control number of decision variables, number and position of optimal areas in the decision space and modality of fitness landscape. Three leading MOEAs, including NSGA-II, NSGA-III, and MOEA/D, are evaluated on a number of problem instances with varying characteristics. A new metric is proposed that measures the performance of algorithms in terms of their coverage of the optimal areas in the decision space. The empirical analysis presented in this research shows that the decision space performance may not necessarily be reflective of the objective space performance and that all algorithms are sensitive to population size parameter for the new test problems.

Punishment and reward are usually regarded as two potential mechanisms to explain the evolution of cooperation especially among multiple participators. However, the performance of these two scenarios in spatial environment needs to be discussed. To figure out this issue, we resort to the $n$-player Iterated Snowdrift Dilemma (ISD) game and Iterated Prisoner’s Dilemma (IPD) game. More importantly, the evolution of punishment and reward in social network-structured populations has not been formally addressed. The numerical results show the equilibrium cooperation frequency can be influenced by cost-to-benefit ratio $r$, the punishment-to-benefit ratio $p∕b$ and the reward-to-benefit ratio $r∕b$. And one intriguing observation is that under the same situation, the punishment is more effective than reward to the population. Then we further probe the effectiveness of neighborhood relationship to the cooperation, which is reflected by the random rewired probability $p_r$. From the distribution of the four roles of the participator we can find that individuals can cooperate easily when they have close relationship. The results of this paper may be helpful to understand the cooperation in complex project or among industry–university–research cooperation project.