LOG FILE TEMPLATE DETECTION AS A MULTI-OBJECTIVE OPTIMIZATION PROBLEM

There is a need for automatic log file template detection tool to find out all the log messages through search space. On the other hand, the template detection tool should cope with two constraints: (i) it could not be too general and (ii) it could not be too specific These constraints are, contradict to one another and can be considered as a multi-objective optimization problem. Thus, a novel multi-objective optimization based log-file template detection approach named LTD-MO is proposed in this paper. It uses a new multi-objective based swarm intelligence algorithm called chicken swarm optimization for solving the hard optimization issue. Moreover, it analyzes all templates in the search space and selects a Pareto front optimal solution set for multi-objective compensation. The proposed approach is implemented and evaluated on eight publicly available benchmark log datasets. The empirical analysis shows LTD-MO detects large number of appropriate templates by significantly outperforming the existing techniques on all datasets.

LOG FILE TEMPLATE DETECTION AS A MULTI-OBJECTIVE OPTIMIZATION PROBLEM

There is a need for automatic log file template detection tool to find out all the log messages through search space. On the other hand, the template detection tool should cope with two constraints: (i) it could not be too general and (ii) it could not be too specific These constraints are, contradict to one another and can be considered as a multi-objective optimization problem. Thus, a novel multi-objective optimization based log-file template detection approach named LTD-MO is proposed in this paper. It uses a new multi-objective based swarm intelligence algorithm called chicken swarm optimization for solving the hard optimization issue. Moreover, it analyzes all templates in the search space and selects a Pareto front optimal solution set for multi-objective compensation. The proposed approach is implemented and evaluated on eight publicly available benchmark log datasets. The empirical analysis shows LTD-MO detects large number of appropriate templates by significantly outperforming the existing techniques on all datasets.

Real-time implementation of Fuzzy Logic Controller based on chicken swarm optimization for the ball and plate system

The ball and Plate (BaP) system is the typical example of the nonlinear dynamic system that is used in a wide range of engineering applications. So, many researchers in the control field are using the Bap system to check robust controllers under several points that challenge it, such as internal and external disturbances. Our manuscript proposed a position control intelligent technique with two directions (2D) for the BaP system by optimized multi Fuzzy Logic Controllers (FLC’s) with Chicken Swarm Optimization (CSO) for each one. The gains and rules of the FLC’s can tune based on the CSO. This proposal utilizes the ability of the FLC’s to observe the position of the ball. At our work, the BaP system that belonged to Control Laboratory/Systems and Control Engineering department is used for real-time proposal implementation. The results have been showing a very good percentage enhancement in settling time, rise time, and overshoot, of the X-axis and Y-axis, respectively.

Enhanced Face Recognition Using Adaptive Local Tri Weber Pattern with Improved Deep Learning Architecture

Effective face recognition is accomplished using the extraction of features and classification. Though there are multiple techniques for face image recognition, full face recognition in real-time is quite difficult. One of the emerging and promising methods to address this challenge in face recognition is deep learning networks. The inevitable network tool associated with the face recognition method with deep learning systems is convolutional neural networks (CNNs). This research intends to develop a new method for face recognition using adaptive intelligent methods. The main phases of the proposed method are (a) data collection, (b) image pre-processing, (c) normalization, (d) pattern extraction, and (e) recognition. Initially, the images for face recognition are gathered from CPFW, Yale datasets, and the MIT-CBCL dataset. The image pre-processing is performed by the Gaussian filtering method. Further, the normalization of the image will be done, which is a process that alters the range of pixel intensities and can handle the poor contrast due to glare. Then a new descriptor called adaptive local tri Weber pattern (ALTrWP) acts as a pattern extractor. In the recognition phase, the VGG16 architecture with new chick updated-chicken swarm optimization (NSU-CSO) is used. As the modification, VGG16 architecture will be enhanced by this optimization technique. The performance of the developed method is analyzed on two standards face database. Experimental results are compared with different machine learning approaches concerned with noteworthy measures, which demonstrate the efficiency of the considered classifier.

A hybrid ant lion optimization chicken swarm optimization algorithm for charger placement problem

Transportation electrification is known to be a viable alternative to deal with the alarming issues of global warming, air pollution, and energy crisis. Public acceptance of Electric Vehicles (EVs) requires the availability of charging infrastructure. However, the optimal placement of chargers is indeed a complex problem with multiple design variables, objective functions, and constraints. Chargers must be placed with the EV drivers’ convenience and security of the power distribution network being taken into account. The solutions to such an emerging optimization problem are mostly based on metaheuristics. This work proposes a novel metaheuristic considering the hybridization of Chicken Swarm Optimization (CSO) with Ant Lion Optimization (ALO) for effectively and efficiently coping with the charger placement problem. The amalgamation of CSO with ALO can enhance the performance of ALO, thereby preventing it from getting stuck in the local optima. Our hybrid algorithm has the strengths from both CSO and ALO, which is tested on the standard benchmark functions as well as the above charger placement problem. Simulation results demonstrate that it performs moderately better than the counterpart methods.