International Journal of Computational Intelligence and Applications

An intrusion detection system (IDS) is an immunizing system that identifies the hostile activities in a network, and alerts the network administrator in case of detecting suspicious behaviors. Signature-based systems are the most common methods for intrusion detection, but however, they are not able to detect new attacks on the network. The main problem of these systems is to keep up to date the database of already containing known attack signatures. Neural networks have a high ability to learn and are generalizable. This study present as follow: A new intrusion detection system that is a hybrid of self-organizing map algorithm (SOM), radial basis function (RBF) and perceptron networks is proposed to solve this problem. For the first time, The Imperialist Competitive Algorithm is used to calculate the parameters of the Perceptron neural network. The proposed approach uses a hybrid architecture that tries to increase the quality of warnings. Signature-based systems using this method can detect new attacks as a self-learner. The results indicated better performance of the proposed hybrid algorithm compared to earlier methods.

Interval-valued time series (ITS) are interval-valued data that are collected in chronological order. The modeling of ITS is an ongoing issue in domain of time series analysis. This paper presents a new modeling method of ITS based on the synergy of fuzzy set theory and artificial neural networks. The proposed method involves the construction of collection of fuzzy sets describing characteristics of amplitude of ITS, the expression and reconstruction mechanism of ITS and the emergence of model of ITS based on artificial neural network (ANN). The resulting model of ITS not only supports the linguistic output but also the numeric output in interval format. A series of experimental studies is reported for two publicly available financial datasets showing different dynamic characteristics. Experimental results clearly show that the constructed ITS model has the better performance on the linguistic and numeric level.

In this paper, we investigated the customer churn prediction problem in the Internet funds industry. We designed a novel feature embedded convolutional neural networks (FE-CNN) method that can automatically learn features from both the dynamic customer behavioral data and static customer demographic data and can utilize the advantage of convolutional neural networks to automatically learn features that capture the structured information. Our results show that our FE-CNN model outperforms the other traditional machine learning models with hand-crafted features, such as logistic regression (LR), support vector machines (SVM), random forests (RF) and neural networks (NN) in terms of accuracy, area under the receiver operating characteristics curve (AUC) and top-decile lift. Furthermore, we found that after adding the demographic data feature to the basic CNN model, the performance of the FE-CNN model improved. Overall, we found that the FE-CNN is the most powerful way to solve the problem of customer churn prediction in the Internet funds industry. Our FE-CNN method can also be applied to other fields that have both dynamic data and static data.

When the basic glowworm swarm optimization (GSO) algorithm optimizes the multi-peak function, the solution accuracy is not high, the later convergence is slow. To solve these problems, the fluorescent factor is introduced to adaptively adjust the step length of the firefly, an adaptive step length firefly optimization algorithm is proposed, this algorithm is an improved self-adaptive step glowworm swarm optimization (ASGSO). In this algorithm, the behavior of glowworms are developed, the step size is dynamically adjusted by the fluorescent factor, the algorithm avoids falling into a local optimum and improves the optimization speed and accuracy. The simulation results show that the improved ASGSO can search for global optimization more quickly and precisely.

In this paper, a new idea is developed for improving the agent intelligence. In fact with the presented convolutional neural network (CNN) approach for knowledge classification, the agent will be able to manage its knowledge. This new concept allows the agent to select only the actionable rule class, instead of trying to infer its whole rule base exhaustively. In addition, through this research, we developed a comparative study between the proposed CNN approach and the classical classification approaches. As foreseeable the deep learning method outperforms the others in term of classification accuracy.

In IP networks, packets forwarding performance can be improved by adding more nodes and dividing the network into smaller segments. Being able to measure and predict traffic flows to direct to a given segment can be crucial in respecting traffic shaping, scheduling and QoS. This paper proposes to model network packets forwarding performance for optimization and prediction purposes by using multi-layer feed-forward neural network model that uses sigmoid functions to activate the hidden nodes. Gradient descent technique has been considered to optimize and enhance the MLP accuracy. Simulations of MPL neurons training stages pointed out a relative improvement of the forwarding process when network posses a larger density of neurons. Numerical results validated our theoretical analysis and confirmed that to enhance the forwarding process, it is necessary to divide the network into small segments by optimizing resources allocation.

Computation Intelligence has inspired many researchers to develop the capability of computers to learn and solve a complex task in real-world problems. In this work, we propose an Artificial Bee Colony (ABC) to deal with the Stock Selection problem. We apply a Sigmoid-based Discrete-Continuous model with ABC to select appropriate features for stock scoring. The empirical study tests the performance of ABC compared with Genetic Algorithm (GA) and Differential Evolution (DE) algorithm by using data from the Stock Exchange Thailand. The empirical results show that the novel model stock selection significantly outperforms in terms of both investment return, diversity and model robustness.