International Journal of Computational Intelligence and Applications

Intrusion is one of the biggest problems in wireless sensor networks. Because of the evolution in wired and wireless mechanization, various archetypes are used for communication. But security is the major concern as networks are more prone to intrusions. An intrusion can be dealt in two ways: either by detecting an intrusion in a wireless sensor network or by preventing an intrusion in a wireless sensor network. Many researchers are working on detecting intrusions and less emphasis is given on intrusion prevention. One of the modern techniques for averting intrusions is through fuzzy logic. In this paper, we have defined a fuzzy rule-based system to avert intrusions in wireless sensor network. The proposed system works in three phases: feature extraction, membership value computation and fuzzified rule applicator. The proposed method revolves around predicting nodes in three categories as “red”, “orange” and “green”. “Red” represents that the node is malicious and prevents it from entering the network. “Orange” represents that the node “might be malicious” and marks it suspicious. “Green” represents that the node is not malicious and it is safe to enter the network. The parameters for the proposed FzMAI are packet send to base station, energy consumption, signal strength, a packet received and PDR. Evaluation results show an accuracy of 98.29% for the proposed system. A detailed comparative analysis concludes that the proposed system outperforms all the other considered fuzzy rule-based systems. The advantage of the proposed system is that it prevents a malicious node from entering the system, thus averting intrusion.

Wireless sensor networks (WSNs) are beginning to be deployed at an accelerated pace, and they have attracted significant attention in a broad spectrum of applications. WSNs encompass a large number of sensor nodes enabling a base station (BS) to sense and transmit data over the area where WSN is spread.

As most sensor nodes have a limited energy capacity and at the same time transmit critical information, enhancing the lifetime and the reliability of WSNs are essential factors in designing these networks. Among many approaches, clustering of sensor nodes has proved to be an effective method of reducing energy consumption and increasing lifetime of WSNs.

In this paper, a new energy-efficient clustering protocol is implemented using a two-step Genetic Algorithm (GA). In the first step of GA, cluster heads (CHs) are selected, and in the second step, cluster members are chosen based on their distance to the selected CHs. Compared to other clustering protocols, the lifetime of WSNs in the proposed clustering is improved. This improvement is the consequence of the fact that this clustering considers energy efficient parameters in clustering protocol.

Single-objective bilevel optimization is a specialized form of constraint optimization problems where one of the constraints is an optimization problem itself. These problems are typically non-convex and strongly NP-Hard. Recently, there has been an increased interest from the evolutionary computation community to model bilevel problems due to its applicability in real-world applications for decision-making problems. In this work, a partial nested evolutionary approach with a local heuristic search has been proposed to solve the benchmark problems and have outstanding results. This approach relies on the concept of intermarriage-crossover in search of feasible regions by exploiting information from the constraints. A new variant has also been proposed to the commonly used convergence approaches, i.e., optimistic and pessimistic. It is called an extreme optimistic approach. The experimental results demonstrate the algorithm converges differently to known optimum solutions with the optimistic variants. Optimistic approach also outperforms pessimistic approach. Comparative statistical analysis of our approach with other recently published partial to complete evolutionary approaches demonstrates very competitive results.

Groundwater management problems are typically of a large-scale nature, involving complex nonlinear objective functions and constraints, which are commonly evaluated through the use of numerical simulation models. Given these complexities, metaheuristic optimization algorithms have recently become popular choice for solving such complex problems which are difficult to solve by traditional methods. However, the practical applications of metaheuristics are severely challenged by the requirement of large number of function evaluations to achieve convergence. To overcome this shortcoming, many new metaheuristics and different variants of existing ones have been proposed in recent years. In this study, a recently developed algorithm called flower pollination algorithm (FPA) is investigated for optimal groundwater management. The FPA is improved, combined with the widely used groundwater flow simulation model MODFLOW, and applied to solve two groundwater management problems. The proposed algorithm, denoted as IFPA, is first tested on a hypothetical aquifer system, to minimize the total pumping to contain contaminated groundwater within a capture zone. IFPA is then applied to maximize the total annual pumping from existing wells in Rhis-Nekor unconfined coastal aquifer on the northern of Morocco. The obtained results indicate that IFPA is a promising method for solving groundwater management problems as it outperforms the standard FPA and other algorithms applied to the case studies considered, both in terms of convergence rate and solution quality.

The study on the prediction of mine pressure, while exploiting in coal mine, is a critical and technical guarantee for coal mine safety and production. In this paper, primarily due to the actual demand for the prediction of mine pressure, a practical prediction model Mine Pressure Prediction (MPP) was proposed based on fuzzy cognitive maps (FCMs). The Real Coded Genetic Algorithm (RCGA) was proposed to solve the problem by introducing the weight regularization and dropout regularization. A numerical example involving in-situ monitoring data is studied. Mean Square Error (MSE) and fitness function were used to evaluate the applicability of MPP model which is trained by RCGA, Regularization Genetic Algorithm (RGA) and Weight and Dropout RGA optimization algorithms. The numerical results demonstrate that the proposed Weight and Dropout RGA is better than the other two algorithms, and realizing the requirement for prediction of mine pressure in the coal mine production.

In biomedical signal processing, artificial intelligence techniques are used for identifying and extracting relevant information. However, it lacks effective solutions based on machine learning for the prediction of cardiac arrhythmias. The heart diseases diagnosis rests essentially on the analysis of various properties of ECG signal. The arrhythmia is one of the most common heart diseases. A cardiac arrhythmia is a disturbance of the heart rhythm. It occurs when the heart beats too slowly, too fast or anarchically, with no apparent cause. The diagnosis of cardiac arrhythmias is based on the analysis of the ECG properties, especially, the durations (P, QRS, T), the amplitudes (P, Q, R, S, T), the intervals (PQ, QT, RR), the cardiac frequency and the rhythm. In this paper we propose a system of arrhythmias diagnosis assistance based on the analysis of the temporal and frequential properties of the ECG signal. After the features extraction step, the ECG properties are then used as input for a convolutional neural network to detect and classify the arrhythmias. Finally, the classification results are used to perform a prediction of arrhythmias with nonlinear regression model. The method is illustrated using the MIT-BIH database.