Wireless sensor networks have battery-operated sensor nodes, which need to be conserved to have prolonged network lifetime. The amount of power consumed for routing sensed data from the sensor node... Show More

Wireless sensor networks have battery-operated sensor nodes, which need to be conserved to have prolonged network lifetime. The amount of power consumed for routing sensed data from the sensor node to the sink node is large. Thus, in order to optimize the energy usage in sensor network efficient data aggregation techniques are needed. Particle swarm optimization (PSO) is a speculative and evolutionary computing technique based on swarm intelligence for solving optimization problems in sensor network such as nodes deployment, node scheduling, data clustering, and aggregation. The paper proposes a PSO-based sensor network aggregation protocol (PSO-SNAP) with K-means to provide initial centroid. The PSO has been used to find the optimal aggregated value having minimum quantization error. The output of the K-means algorithm is used as an initial centroid in PSO. Apart from K-means, K-medoid and simple average has also been used to provide initial seed to the PSO algorithm and results of all three approaches are compared.

Evolutionary algorithms are inspired by the biological model of evolution and natural selection and are used to solve computationally hard problems, also known as NP-hard problems. The main motive... Show More

Evolutionary algorithms are inspired by the biological model of evolution and natural selection and are used to solve computationally hard problems, also known as NP-hard problems. The main motive to use these algorithms is their robust and adaptive nature to provide best search techniques for complex problems. This paper presents a comparative analysis of classification of algorithm's family instead of algorithms comparison using KEEL tool. This work compares SSMA-C, DROP3PSO-C, FURIA-C, GFS-MaxLogitBoost-Cand CPSO-C algorithms. Further, these selected evolutionary algorithms are compared against two statistical classifiers using the Wilcoxon signed rank test and Friedman test on following datasets—bupa, ecoli, glass, haberman, iris, monks, vehicle, and wine—to calculate classification efficiencies of these algorithms. Experimental results reveal some differences among these algorithms. Visualization module in the model has been used to give overall results as a summary while statistical test using Clas-Wilcoxin-ST compared the algorithms in a pair-wise fashion to conclude experimental findings.

The application layer HTTP flooding attack is the primary threat to web servers hosting web services in the cloud network. Due to varying network changes in the cloud, the traditional security... Show More

The application layer HTTP flooding attack is the primary threat to web servers hosting web services in the cloud network. Due to varying network changes in the cloud, the traditional security methods are not sufficient to detect the attack. Therefore, a novel approach is proposed, which uses Teacher Learner Based Optimization (TLBO) for clustering to identify the attack requests. In this work, the logs of a web server under attack are collected and pre-processed. Further, Principal Component Analysis (PCA) is used to reduce the dimensionality of the pre-processed data. Thereafter the data is clustered using TLBO clustering, which will separate the application layer HTTP flooding attack in one cluster and rest of the requests in the other cluster. The results prove that the proposed approach performs better than other traditional and bio-inspired clustering techniques. The proposed approach also attains the peak detection rate and lowermost false alarm, which proves the efficacy of the proposed approach among another state of the art approaches.

This paper presents an automatic human ear localization technique for handling uncontrolled scenarios such as illumination variation, poor contrast, partial occlusion, pose variation, ear ornaments... Show More

This paper presents an automatic human ear localization technique for handling uncontrolled scenarios such as illumination variation, poor contrast, partial occlusion, pose variation, ear ornaments, and background noise. The authors developed entropy-based binary Jaya algorithm (EBJA) and weighted doubly modified Hausdorff distance (W-MHD) to use edge information rather than pixels intensity values of the side face image. First, it embodies skin segmentation procedure using skin color model and successively remove spurious and non-ear edges which reduces the search space of the skin regions. Secondly, EBJA is proposed to trace dense edge regions as probable ear candidates. Thirdly, this paper developed an edge based weight function to represent the ear shape along with for the edge based template matching using W-MHD to identify true ear from a set of probable ear candidates. Experimental results using publicly available benchmark datasets demonstrate the competitiveness of the proposed technique in comparison to the state-of-the-art methods.

The inverted pendulum system (IPS) is considered the milestone of many robotic-based industries. In this paper, a new variant of variable structure adaptive fuzzy (VSAF) is used with new reduced... Show More

The inverted pendulum system (IPS) is considered the milestone of many robotic-based industries. In this paper, a new variant of variable structure adaptive fuzzy (VSAF) is used with new reduced linear quadratic regulator (RLQR) and feedforward gain for enhancing the stability of IPS. The optimal determining of VSAF parameters as well as Q and R matrices of RLQR are obtained by using a modified grey wolf optimizer with adaptive constants property via particle swarm optimization technique (GWO/PSO-AC). A comparison between the hybrid GWO/PSO-AC and classical GWO/PSO based on multi-objective function is provided to justify the superiority of the proposed technique. The IPS equipped with the hybrid GWO/PSO-AC-based controllers has minimum settling time, rise time, undershoot, and overshoot results for the two system outputs (cart position and pendulum angle). The system is subjected to robustness tests to ensure that the system can cope with small as well as significant disturbances.

Metaheuristics algorithms are competitive methods for solving assignment problems. This paper reports on nature inspired algorithms approach which is the particle swarm optimization (PSO) method... Show More

Metaheuristics algorithms are competitive methods for solving assignment problems. This paper reports on nature inspired algorithms approach which is the particle swarm optimization (PSO) method hybrid with a local search (LS) algorithm for solving the quadratic three-dimensional assignment problem (Q3AP) where population-based metaheuristics like PSO or GA failed to solve. Q3AP is one of the combinatorial problems proven to be NP-Hard. It is an extension of the quadratic assignment problem (QAP). Solving the Q3AP consists of finding an optimal symbol mapping over two vectors, whereas solving the QAP consists of finding an optimal symbol mapping over one vector only. The authors tested the proposed hybrid algorithm on many instances where some of them haven't been used in the previous works for solving Q3AP. The results show that compared with the PSO algorithm and the genetic algorithm (GA), the proposed hybrid PSO-ILS(TS) algorithm is promising for finding the optimal/best known solution.