International Journal of Computational Intelligence and Applications

Image classification, a topic of pattern recognition in computer vision, is an approach of classification based on contextual information in images. Contextual here means this approach is focusing on the relationship of the nearby pixels also called neighborhood. An open topic of research in computer vision is to devise an effective means of transferring human’s informal knowledge into computers, such that computers can also perceive their environment. However, the occurrence of object with respect to image representation is usually associated with various features of variation causing noise in the image representation. Hence, it tends to be very difficult to actually disentangle these abstract factors of influence from the principal object. In this paper, we have proposed a hybrid model: FUSIONET, which has been modeled for studying and extracting meaning facts from images. Our proposition combines two distinct stack of convolution operation (3 × 3 and 1 × 1, respectively). Successively, these relatively low-feature maps from the above operation are fed as input to a downstream classifier for classification of the image in question.

Derivative-based algorithms have been adopted in the literature for the optimization of membership and non-membership function parameters of interval type-2 (T2) intuitionistic fuzzy logic systems (FLSs). In this study, a non-derivative-based algorithm called sliding mode control learning algorithm is proposed to tune the parameters of interval T2 intuitionistic FLS for the first time. The proposed rule-based learning system employs the Takagi–Sugeno–Kang inference with artificial neural network to pilot the learning process. The new learning system is evaluated using some nonlinear prediction problems. Analyses of results reveal that the proposed learning apparatus outperforms its type-1 version and many existing solutions in the literature and competes favorably with others on the investigated problem instances with low cost in terms of running time.

Emotion recognition using bio-signals is currently a hot and challenging topic in human–computer interferences, robotics, and affective computing. A broad range of literature has been published by analyzing the internal/external behaviors of the subjects in confronting emotional events/stimuli. Eye movements, as an external behavior, are frequently used in the multi-modal emotion recognition system. On the other hand, classic statistical features of the signal have generally been assessed, and the evaluation of its dynamics has been neglected so far. For the first time, the dynamics of single-modal eye-blinking data are characterized. Novel polar-based indices of the lagged Poincare plots were introduced. The optimum lag was estimated using mutual information. After reconstruction of the plot, the polar measures of all points were characterized using statistical measures. The support vector machine (SVM), decision tree, and Naïve Bayes were implemented to complete the process of classification. The highest accuracy of 100% with an average accuracy of 84.17% was achieved for fear/sad discrimination using SVM. The suggested framework provided outstanding performances in terms of recognition rates, simplicity of the methodology, and less computational cost. Our results also showed that eye-blinking data possesses the potential for emotion recognition, especially in classifying fear emotion.

This research is an optimal allocation of tasks to processors in order to minimize the total costs of execution and communication. This problem is called the Task Assignment Problem (TAP) with nonuniform communication costs. To solve the latter, the first step concerns the formulation of the problem by an equivalent zero-one quadratic program with a convex objective function using a convexification technique, based on the smallest eigenvalue. The second step concerns the application of the Continuous Hopfield Network (CHN) to solve the obtained problem. The calculation results are presented for the instances from the literature, compared to solutions obtained both the CPLEX solver and by the heuristic genetic algorithm, and show an improvement in the results obtained by applying only the CHN algorithm. We can see that the proposed approach evaluates the efficiency of the theoretical results and achieves the optimal solutions in a short calculation time.

The churn prediction based on telecom data has been paid great attention because of the increasing the number telecom providers, but due to inconsistent data, sparsity, and hugeness, the churn prediction becomes complicated and challenging. Hence, an effective and optimal prediction of churns mechanism, named adaptive firefly-spider optimization (adaptive FSO) algorithm, is proposed in this research to predict the churns using the telecom data. The proposed churn prediction method uses telecom data, which is the trending domain of research in predicting the churns; hence, the classification accuracy is increased. However, the proposed adaptive FSO algorithm is designed by integrating the spider monkey optimization (SMO), firefly optimization algorithm (FA), and the adaptive concept. The input data is initially given to the master node of the spark framework. The feature selection is carried out using Kendall’s correlation to select the appropriate features for further processing. Then, the selected unique features are given to the master node to perform churn prediction. Here, the churn prediction is made using a deep convolutional neural network (DCNN), which is trained by the proposed adaptive FSO algorithm. Moreover, the developed model obtained better performance using the metrics, like dice coefficient, accuracy, and Jaccard coefficient by varying the training data percentage and selected features. Thus, the proposed adaptive FSO-based DCNN showed improved results with a dice coefficient of 99.76%, accuracy of 98.65%, Jaccard coefficient of 99.52%.

In this work, efficient human activity recognition (HAR) algorithm based on deep learning architecture is proposed to classify activities into seven different classes. In order to learn spatial and temporal features from only 3D skeleton data captured from a “Microsoft Kinect” camera, the proposed algorithm combines both convolution neural network (CNN) and long short-term memory (LSTM) architectures. This combination allows taking advantage of LSTM in modeling temporal data and of CNN in modeling spatial data. The captured skeleton sequences are used to create a specific dataset of interactive activities; these data are then transformed according to a view invariant and a symmetry criterion. To demonstrate the effectiveness of the developed algorithm, it has been tested on several public datasets and it has achieved and sometimes has overcome state-of-the-art performance. In order to verify the uncertainty of the proposed algorithm, some tools are provided and discussed to ensure its efficiency for continuous human action recognition in real time.

In this paper, the optimal distribution generation (DG) size and location for power flow analysis at the smart grid by hybrid method are proposed. The proposed hybrid method is the Interactive Autodidactic School (IAS) and the Most Valuable Player Algorithm (MVPA) and commonly named as IAS-MVPA method. The main aim of this work is to reduce line loss and total harmonic distortion (THD), similarly, to recover the voltage profile of system through the optimal location and size of the distributed generators and optimal rearrangement of network. Here, IAS-MVPA method is utilized as a rectification tool to get the maximum DG size and the maximal reconfiguration of network at environmental load variation. In case of failure, the IAS method is utilized for maximizing the DG location. The IAS chooses the line of maximal power loss as optimal location to place the DG based on the objective function. The fault violates the equality and inequality restrictions of the safe limit system. From the control parameters, the low voltage drift is improved using the MVPA method. The low-voltage deviation has been exploited for obtaining the maximum capacity of the DG. After that, the maximum capacity is used at maximum location that improves the power flow of the system. The proposed system is performed on MATLAB/Simulink platform, and the effectiveness is assessed by comparing it with various existing processes such as generic algorithm (GA), Cuttle fish algorithm (CFA), adaptive grasshopper optimization algorithm (AGOA) and artificial neural network (ANN).