In the development of and research into multi-character fighting computer games, Non-Player Characters (NPCs) frequently seem less intelligent owing to them having a single focus. As such, multi-character fighting becomes one-on-one fighting; one character will encounter another character only once the previous opponent is defeated. This study develops a new model in multi-character fighting, in which each NPC can simultaneously fight against many characters. Following this model, each character becomes an agent that makes his own decisions. The first advantage of this model is the integration of multi-character behaviors in fights. Each character can seek out enemies/opponents, select one target opponent, avoid obstacles, approach the target opponent, change the target opponent, and then defeat the opponent or be defeated by the opponent; in other words, each character can thus fight against many opponents. All of the behaviors in the fight take place automatically. The second advantage of this model is that each character does not only focus on the opponent being targeted, but also on the other opponents surrounding him. Each character can move from one opponent to another, even when the target opponent is not yet defeated. The third advantage of this model is that each character can move to another fight cluster, thus ensuring that fights seem more dynamic. This research has experimented with the model using a 3D application that can run on personal computers or smart phones.

This work is about the definition of cyber threats in the information system. The cyber threats lead to significant loss of network resources and cause the system disability as a whole. Detecting countermeasures in certain threats can reduce the impact on the system by changing the topology of the network in advance. Consequently, the interruption of a cyberattack forces the intruders to seek for alternative ways to damage the system. The most important task in the information system work is the state of network equipment monitoring. Also it’s the support of the network infrastructure in working order.
The purpose of the work is to develop a method for detecting cyber threats for the information system. The system can independently detect cyber threats and develop countermeasures against them. The main feature of the counteractions is to protect network nodes from compromising.
To ensure the functional stability, the most important issues are providing safety metrics. This technique allows to increase the functional stability of the system, which works in real time.

In computer vision, face tracking is having wider opportunities for research activities using different background video sequences because of various factors and constraints. Due to the challenges that are increasing day by day, old/existing algorithms are becoming obsolete. There are many powerful algorithms that are limited to certain set of video sequences. In this paper, we are proposing an algorithm that detect and track multiple faces in different background video sequences. Viola-Jones face detection algorithm is used in such a way that, new face/first face need not to be in the starting frame of the selected video sequence. The proposed algorithm successfully detect new face(s) along with existing face(s) by keeping track of the facial data using BRISK feature points. The mean of the old points and new points are calculated based on the area of the facial data. The detected face(s) in further frames undergoes similarity check with existing facial data. If detected facial data and existing facial data mismatches, then the detected facial data is entered into face tracks structure. By using point tracker method, the proposed algorithm track those points that has been set for each of the facial data.

Computational Intelligence (CI) is an as of emerging area in addressing complex real world problems. The WOA has taken its root from the collective intelligent foraging behavior of humpback whales (Megaptera Novaeangliae). The standard WOA is suffers from the selection of best agent while whales searching and encircling prey. This research paper deals with the multi-swarm cooperative strategies for finding the best agents which balances the two phase’s exploration and exploitation. The performance of invoked Multi-Swarm cooperative strategies into standard WOA i.e, MsWOA is first benchmarked on a set of 23 standard mathematical benchmark function problems which includes 7 Uni-Modal, 6 Multi-modal and 10 fixed dimension multi-modal functions. The obtained graphical and statistical results have been portrayed along with the previously established techniques. The obtained results depicts that the proposed cooperative strategies for WOA outperforms in solving optimization problems of standard benchmark functions. This paper also studies the numerical efficiency of proposed techniques on the problem of data clustering where 10 real data clustering problems have been taken from data repository https://archive.ics.uci.edu.data. Statistical results for the obtained cluster centroids, intra-cluster distances and inter-cluster distances confirms that the cooperative strategies for best whale agent selection improves the performance WOA for function optimization problems as well as data clustering problems.

Lung is a vital organ that plays a pivotal role in every second of our lives. Lungs may be affected by a number of diseases, including pulmonary edema and cancer. These diseases deemed life-sustained diseases, so they possess high preferences in detection, diagnosis, and possible treatments. In this paper, we presented a textural feature analysis framework that is capable of detecting lung abnormalities (edema or cancer) using Laws masks texture features. Laws masks are conventional texture feature extractor, and considered as one of the best methods for texture analysis in image processing. However, computing and extracting the texture features through various masks are very time consuming, whereas lung diseases demand rapid yet accurate diagnosis. Today, increased efficiency is being achieved through parallelism, and this trend is believed to continue in the future, with all computing devices likely to have many processors. Therefore, our objective is to investigate a multi-level parallel algorithm on Laws masks to describe structural variations of lung abnormalities. To our knowledge, there are no published researches that employed parallel strategies for lung abnormalities detection using Laws method. The proposed system has been experimented on real CT lung images. The results indicate that Laws texture features are capable of discriminating among normal, edema and cancerous lungs. Furthermore, applying parallel processing approaches improves significantly the overall system performance.

This paper proposes an adaptive traffic control system that dynamically manages traffic phases and durations at cross-intersection. The developed model optimally schedules green light timing in accordance with traffic condition on each lane in order to minimize the Average Waiting Time (AWT) at the cross intersection. A MATLAB based Graphic User Interface (GUI) traffic control simulator was developed. Three scenarios of vehicular traffic control were simulated and the results presented. The results show that scenario one and two demonstrated the variation of the AWT and Performance of the developed algorithm with changes in the maximum allowable green light timing over the simulation interval. In the third scenario, an AWT of 38sec was recorded against a maximum allowable green light duration of 120sec, during which 1382 vehicles were evacuated from the intersection, leaving 22 vehicles behind. The algorithm also had a performance of 98.43% over a simulation duration of 1800sec.

Dimensionality reduction or the optimal selection of features is a challenging task due to large search space. Currently, many research has been performed in this domain to improve the accuracy as well as to minimize the computational complexity. Particle Swarm Optimization (PSO) based feature selection approach seems very promising and has been extensively used for this work. In this paper, a Threshold Controlled Binary Particle Swarm Optimization (TC-BPSO) along with Multi-Class Support Vector Machine (MC-SVM) is proposed and compared with Conventional Binary Particle Swarm Optimization (C-BPSO). TC-BPSO is used for the selection of features while MC-SVM is used to calculate the classification accuracy. 70% of the data is used to train the MC-SVM model while the test has been performed on rest 30% data to calculate the accuracy. Proposed approach is tested on ten different datasets having varying difficulties such as some datasets having large number of features while some have small, some have just two classes while some have many classes, some datasets having small number of instances while some have large number of instances and the results obtained on these datasets are compared with some of the existing methods. Experiments show that the obtained results are very promising and achieved the best accuracy in minimum possible features. Proposed approach outperforms C-BPSO in all contexts on most of the datasets and 3-4 times computationally faster. It also outperforms in all context when compared with the existing work and 5-8 times computationally faster.

This paper aims to finding happiness in human face with minimal feature vectors. In this system, the face detection and tracking are carried out by Constrained Local Model (CLM). Using CLM grid node, the entire and minimal feature vector displacement is obtained through extracted features. The feature vector displacements are computed in multi-classes of Twin- Support Vector Machines (TWSVM) classifier to evaluate the happiness. In training and testing phases, the following databases are used such as MMI database, Cohn-Kanade (CK), Extended-CK, Mahnob-Laughter and also Real Time data. Also, this paper compares the Supervised Support Vector Machines and Unsupervised Twin Support Vector Machines classifier with cross data-validation. Using the normalization of Min-max and Z-norm technique, the overall accuracy of finding happiness are computed as 86.29% and 83.79% respectively.