APTIKOM Journal on Computer Science and Information Technologies https://aptikom-journal.id/index.php/csit IAIC Publisher en-US APTIKOM Journal on Computer Science and Information Technologies 2528-2417 Genome Feature Optimization and Coronary Artery Disease Prediction using Cuckoo Search https://aptikom-journal.id/index.php/csit/article/view/336 <p>CVD (Cardiovascular Diseases) is among the major health ailment issue leading to millions of deaths every year. CVDs are resulting as an outcome of implications in terms of environmental and the genetic factors that result in the CVD for individuals. Phenomenal advancements that has taken place in the diagnosis solutions like usage of genomic tools are contributing towards predicting and diagnosis of heart diseases more accurately. In recent past, analyzing gene expression data, particularly using machine learning strategies to predict and classify the given unlabeled gene expression record is a generous research issue. Concerning this, a substantial requirement is feature optimization, which is since the overall genes observed in human body are closely 25000 and among them 636 are cardio vascular related genes. Hence, it complexes the process of training the machine learning models using these entire cardio vascular gene features. Hence, this manuscript is using bidirectional pooled variance strategy of ANOVA standard to select optimal features. Along the side to surpass the constraint observed in traditional classifiers, which is unstable accuracy at k-fold cross validation, this manuscript proposed a classification strategy that build upon the swarm intelligence technique called cuckoo search. The experimental study indicating that the number of optimal features those selected by proposed model is substantially low that compared to the other contemporary model that selects features using Forward Feature Selection and classifies using SVM classifier (FFS&amp;SVM). The experimental study evinced that the proposed model, which selects feature by bidirectional pooled variance estimation and classifies using proposed classification strategy that build on cuckoo search (BPVE&amp;CS) outperformed the selected contemporary model (FFS&amp;SVM).</p> E. Neelima M.S. Prasad Babu Copyright (c) 2020 APTIKOM Journal on Computer Science and Information Technologies 2020-11-03 2020-11-03 6 1 1 13 10.34306/csit.v6i1.336 An optimized Rubber Sheet Model for Normalization Phase of IRIS Recognition https://aptikom-journal.id/index.php/csit/article/view/356 <p>Iris recognition is a promising biometric authentication approach and it is a very active topic in both research and realistic applications because the pattern of the human iris differs from person to person, even between twins. In this paper, an optimized iris normalization method for the conversion of segmented image into normalized form has been proposed. The existing methods are converting the Cartesian coordinates of the segmented image into polar coordinates. To get more accuracy, the proposed method is using an optimized rubber sheet model which converts the polar coordinates into spherical coordinates followed by localized histogram equalization. The experimental result shows the proposed method scores an encouraging performance with respect to accuracy.</p> Selvamuthukumaran. S Ramkumar. T Shantharajah SP Copyright (c) 2020 APTIKOM Journal on Computer Science and Information Technologies 2020-11-17 2020-11-17 6 1 20 29 10.34306/csit.v6i1.356 Design of Eight-Phase Sequences using Modified Particle Swarm Optimization for Spread Spectrum and Radar Applications https://aptikom-journal.id/index.php/csit/article/view/368 <p><em><span style="font-weight: 400;">&nbsp;For a multiple access communication system and radar system, it is desirable to have a set of sequences such that each sequence has a peaky autocorrelation and each pair of sequence has a negligible cross-correlation as possible. Peakyness of the auto-correlation of a sequence is measured in terms of its discrimination, which is to be maximized. The negligibility of a cross-correlation is judged based on the energy in the cross-correlation which is to be minimized. Obtaining such sequences is a combinatorial problem for which many global optimization algorithms like genetic algorithm, particle swarm optimization algorithm, simulated annealing algorithm were reported in the literature. In this paper a Modified Particle Swarm Optimization (MPSO) Algorithm is being designed to achieve these sequences. The MPSO Algorithm is a combination of the Hamming Scan Algorithm (HAS) and Particle Swarm Optimization (PSO) and has the fast convergence rate of Hamming Scan and global minima convergence of Particle Swarm Optimization. Eight-phase sequences of lengths varying from 40 to 300 have been synthesized using MPSO and synthesized sequence sets achieved have better values of the above two properties compared with the literature.</span></em></p> S. Srinivasa Rao P Siddaiah Copyright (c) 2020 APTIKOM Journal on Computer Science and Information Technologies 2020-11-23 2020-11-23 6 1 30 40 10.34306/csit.v6i1.368 Design of a Low Noise Amplifier Based on E-PHEMT Transistors for 4G Applications https://aptikom-journal.id/index.php/csit/article/view/389 <p><em><span style="font-weight: 400;">&nbsp;In this paper, we have modeled a low noise amplifier LNA for 4G applications and study the key properties of EPHEMT LNAs in terms of high gain, low noise figure, good input and output matching and unconditional stability at the lowest possible current draw from the amplifier in the front-end design. A well-designed LNA is simulated using Advanced Design System.The design uses microstrip lines in the matching networks, inductors and capacities for DC Biasing. The simulation results of a two-stage low noise amplifier show at 2.6 GHz a gain of 44.701 dB, noise figure of 0.576 dB ,while the reflection loss S12 is -65.02 dB .The input return loss S11 is -34.125 dB and the output return loss S22 is -9.996 dB with biasing voltage at 5 V.</span></em></p> Houda Laaouane Seddik Bri Jaouad Fosh Copyright (c) 2020 APTIKOM Journal on Computer Science and Information Technologies 2020-12-01 2020-12-01 6 1 41 52 10.34306/csit.v6i1.389 Modification Data Attack inside Computer Systems: A critical Review https://aptikom-journal.id/index.php/csit/article/view/410 <p>This paper is a review of types of modification data attack based on computer systems and it explores the vulnerabilities and mitigations. Altering information is a kind of cyber-attack during which intruders interfere, catch, alter, take or erase critical data on the PCs and applications through using network exploit or by running malicious executable codes on victim's system. One of the most difficult and trendy areas in information security is to protect the sensitive information and secure devices from any kind of threats. Latest advancements in information technology in the field of information security reveal huge amount of budget funded for and spent on developing and addressing security threats to mitigate them. This helps in a variety of settings such as military, business, science, and entertainment. Considering all concerns, the security issues almost always come at first as the most critical concerns in the modern time. As a matter of fact, there is no ultimate security solution; although recent developments in security analysis are finding daily vulnerabilities, there are many motivations to spend billions of dollars to ensure there are vulnerabilities waiting for any kind of breach or exploit to penetrate into the systems and networks and achieve particular interests. In terms of modifying data and information, from old-fashioned attacks to recent cyber ones, all of the attacks are using the same signature: either controlling data streams to easily breach system protections or using non-control-data attack approaches. Both methods can damage applications which work on decision-making data, user input data, configuration data, or user identity data to a large extent. In this review paper, we have tried to express trends of vulnerabilities in the network protocols’ applications.</p> Vahid Kaviani J Parvin Ahmadi Doval Amiri Farsad Zamani Brujeni Nima Akhlaghi Copyright (c) 2020 APTIKOM Journal on Computer Science and Information Technologies 2020-12-11 2020-12-11 6 1 53 60 10.34306/csit.v6i1.410 Smart Camera Network Supervision for Competent Exploitation of Energy Recourses in vision Task https://aptikom-journal.id/index.php/csit/article/view/418 <p><em><span style="font-weight: 400;">Face Detection by Smart Camera Network in static mode and dynamic mode is done by the allocation of multitasking. This might result in the absence of some of the pedestrians and consumption of more energy for single target. This paper mainly presents most widely used energy optimization technique in dynamic mode. Tasks are scheduled on periodic basis, with inadequate time period for target switching and task switching. Face Detection in vision task is done by rectangular features of Haar and AdaBoost in Viola Jones Algorithm. Energy utility factor is allocated on Largest Task first algorithm basis. Task is allocated to the camera with uppermost amount of utility rate that can detect the face more approximately. Energy Consumption is optimized by the distributive market based bidding process and Adaptive strategy selection. This boosts existence of camera and drop in the power consumption with restricted amount of Camera’s.</span></em></p> Gudapati Ramyasri Sharma .S Copyright (c) 2020 APTIKOM Journal on Computer Science and Information Technologies 2020-12-18 2020-12-18 6 1 61 68