Improvement of Imperialist Competitive Algorithm based on the Cosine Similarity Criterion of Neighboring Objects

Maryam Houtinezhad and Hamid Reza Ghaffary

Department of Computer Engineering, Ferdows Branch, Islamic Azad University, Ferdows, Iran      

Abstract: The goal of optimizing the best acceptable answer is according to the limitations and needs of the problem. For a problem, there are several different answers that are defined to compare them and select an optimal answer; a function is called a target function. The choice of this function depends on the nature of the problem. Sometimes several goals are together optimized; such optimization problems are called multi-objective issues. One way to deal with such problems is to form a new objective function in the form of a linear combination of the main objective functions. In the proposed approach, in order to increase the ability to discover new position in the Imperialist Competitive Algorithm (ICA), its operators are combined with the particle swarm optimization. The colonial competition optimization algorithm has the ability to search global and has a fast convergence rate, and the particle swarm algorithm added to it increases the accuracy of searches. In this approach, the cosine similarity of the neighboring countries is measured by the nearest colonies of an imperialist and closest competitor country. In the proposed method, by balancing the global and local search, a method for improving the performance of the two algorithms is presented. The simulation results of the combined algorithm have been evaluated with some of the benchmark functions. Comparison of the results has been evaluated with respect to metaheuristic algorithms such as Differential Evolution (DE), Ant Lion Optimizer (ALO), ICA, Particle Swarm Optimization (PSO), and Genetic Algorithm (GA).

Keywords: Imperialist competitive algorithm, particle swarm optimization, optimization problem.

Received March 24, 2018; accepted November 17, 2019

Automatic Topics Segmentation for News Video

by Clustering of Histogram of Orientation

Gradients Faces

 Mounira Hmayda, Ridha Ejbali, and Mourad Zaied

RTIM: Research Team in Intelligent Machines,University of Gabes, National Engineering School of Gabes (ENIG), Tunisia

Abstract: TV stream is a major source of multimedia data. The proposed method aims to enable a good exploitation of this source of video by multimedia services social community, and video-sharing platforms. In this work, we propose an approach to the automatic topics segmentation of news video. The originality of the approach is the use of Clustering of Histogram of Orientation Gradients (HOG) faces as prior knowledge. This knowledge is modeled as images which governs the structuring of TV stream content. This structuring is carried out on two levels. The first consists in the identification of anchorperson by Single-Linkage Clustering of HOG faces. The second level aims to identify the topics of news program due to the large audience because of the pertinent information they contain. Experiments comparing the proposed technique to similar works were carried out on the TREC Video Retrieval Evaluation (TRECVID) 2003 database. The results show significant improvements to TV news structuring exceeding 96 %.

Keywords: Anchorperson, clustering, face detection, features extraction, news program.

Received December 28, 2018; accepted April 10, 2020

Detection of Bundle Branch Block using Higher

Order Statistics and Temporal Features

Yasin Kaya

 Department of Computer Engineering, Adana Alparslan Türkeş Science and Technology University, Turkey

Abstract: Bundle Branch Block (BBB) beats are the most common Electrocardiogram (ECG) arrhythmias and can be indicators of significant heart disease. This study aimed to provide an effective machine-learning method for the detection of BBB beats. To this purpose, statistical and temporal features were calculated and the more valuable ones searched using feature selection algorithms. Forward search, backward elimination and genetic algorithms were used for feature selection. Three different classifiers, K-Nearest Neighbors (KNN), neural networks, and support vector machines, were used comparatively in this study. Accuracy, specificity, and sensitivity performance metrics were calculated in order to compare the results. Normal sinus rhythm (N), Right Bundle Branch Block (RBBB), and Left Bundle Branch Block (LBBB) ECG beat types were used in the study. All beats containing these three beat types in the MIT-BIH arrhythmia database were used in the experiments. All of the feature sets were obtained at a promising classification accuracy for BBB classification. The KNN classifier using backward elimination-selected features achieved the highest classification accuracy results in the study with 99.82%. The results showed the proposed approach to be successful in the detection of BBB beats.

Keywords: ECG, arrhythmia detection, bundle branch block, genetic algorithms, neural networks, k-nearest neighbors, support vector machines, backward elimination, forward selection.

Received August 20, 2019; accepted October 5, 2020

Emotion Recognition based on EEG Signals

in Response to Bilingual Music Tracks

Rida Zainab and Muhammad Majid

Department of Computer Engineering, University of Engineering and Technology Taxila, Pakistan

Abstract: Emotions are vital for communication in daily life and their recognition is important in the field of artificial intelligence. Music help evoking human emotions and brain signals can effectively describe human emotions. This study utilized Electroencephalography (EEG) signals to recognize four different emotions namely happy, sad, anger, and relax in response to bilingual (English and Urdu) music. Five genres of English music (rap, rock, hip-hop, metal, and electronic) and five genres of Urdu music (ghazal, qawwali, famous, melodious, and patriotic) are used as an external stimulus. Twenty-seven participants consensually took part in this experiment and listened to three songs of two minutes each and also recorded self-assessments. Muse four-channel headband is used for EEG data recording that is commercially available. Frequency and time-domain features are fused to construct the hybrid feature vector that is further used by classifiers to recognize emotional response. It has been observed that hybrid features gave better results than individual domains while the most common and easily recognizable emotion is happy. Three classifiers namely Multilayer Perceptron (MLP), Random Forest, and Hyper Pipes have been used and the highest accuracy achieved is 83.95% with Hyper Pipes classification method. 

Keywords: Emotion recognition, electroencephalography, feature extraction, classification, bilingual music.

Received September 16, 2019; accepted July 26, 2020

A Novel Machine-Learning Framework-based on LBP and GLCM Approaches for CBIR System

Meenakshi Garg¹, Manisha Malhotra¹, and Harpal Singh²

¹University Institute of Computing, Chandigarh University, India

²Department of Electronics and Communication Engineering, CEC Landran, India

Abstract: This paper presents a Multiple-features extraction and reduction-based approaches for Content-Based Image Retrieval (CBIR). Discrete Wavelet Transforms (DWT) on colored channels is used to decompose the image at multiple stages. The Gray Level Co-occurrence Matrix (GLCM) concept is used to extract statistical characteristics for texture image classification. The definition of shared knowledge is used to classify the most common features for all COREL dataset groups. These are also fed into a feature selector based on the particle swarm optimization which reduces the number of features that can be used during the classification stage. Three classifiers, called the Support Vector Machine (SVM), K-Nearest Neighbor (KNN) and Decision Tree (DT), are trained and tested, in which SVM give high classification accuracy and precise rates. In several of the COREL dataset types, experimental findings have demonstrated above 94 percent precision and 0.80 to 0.90 precision values.

Keywords: CBIR, DWT, SHO, feature selection, classification.

Received November 18, 2019; accepted July 20, 2020

Maximizing the Area Spanned by the Optical SNR of the 5G Using Digital Modulators and Filters

Guruviah Karpagarajesh and Helen Anita

Department of Electronics and Communication, Government College of Engineering Tirunelveli, India

Abstract: High security data link channels having more immunity against channel noise is the need of the century. Free Space Optical communication (FSO) is the modern technology which kick-starts it’s application in inter satellite communication, underwater communication and mobile communication to the next level of data transmission by means of complete utilisation of the allocated frequency spectrum. In Europe and Asian countries, 5G optical communication will going to expand its usage to nearly 50% in upcoming years and so bandwidth and power efficiency has to be enhanced as much as possible since the consumption rate of the users is increasing exponentially. But increasing the distance increases the attenuation in case of severe atmospheric weather condition. In this paper, 5G data rate of 50Gbps is ensured for better signal reception with maximum possible link distance between the sender and the receiver keeping variable attenuation environment. The frequency of operation is 1550nm throughout the processes. In this work, several digital modulation techniques and optical filters for receiver are designed and simulated. The better resulting modulator and filter design in terms of high Quality factor and low bit error rate are considered and is integrated with each other. The Signal to Noise Ratio (SNR) and optical SNR are calculated for the integrated design theoretically. Higher the SNR less will be BER and hence the signal connectivity can be improved in the high speed free space optical communication systems.

Keywords: Free space optics, 5G data transmission, signal to noise ratio, bit error rate, quality factor.

Received December 17, 2019; accepted June 15, 2020

 https://doi.org/10.34028/iajit/18/3/7

Full text  

Software Metrics for Reusability of Component

Based Software System: A Review

Jyoti Aggarwal¹ and Manoj Kumar²

¹Department of Computer Science (ASET), Amity University, Noida

²School of Computer Science, University of Petroleum and Energy Studies, Dehradun

Abstract: Component Based Software System (CBSS) have become most generalized and popular approach for developing reusable software applications. A software component has different important factors, but reusability is the most citing factor of any software component. Software components can be reused for the development of another software application, which further reduces the amount of time and effort of software development process. With the increase in the number of software components, requirement for identification of software metrics also increased for quantitative analysis of different aspects of components. Reusability depends on different factors and these factors have different impact on the reusability of software components. In this paper, study has been performed to identify the major reusability factors and software metrics for measuring those factors. From this research work, it will become easier to measure the reusability of software components, and software developers would be able to measure the degree of various features of any application which can be reused for developing other software applications. In this way, it would be easy and convenient to identify and compare the reusable software components and they could be reused in effective and efficient manner.

Keywords: Reusability metrics, software components, factors, software.

Received January 21, 2020; accepted December 10, 2020

MCA-MAC: Modified Cooperative Access MAC Protocol in Wireless Sensor Networks

Aya Hossam¹, Tarek Salem², Anar Abdel Hady², and Sherine Abd El-Kader²

¹Electrical Engineering Department, Faculty of Engineering (Shoubra), Benha University, Egypt

²Computers and Systems Department, Electronics Research Institute, Egypt

Abstract: Throughput, energy efficiency and average packet delivery delay are some of the most crucial metrics that should be considered in Wireless Sensor Networks (WSNs). This paper proposes a modified Medium Access Control (MAC) protocol for WSNs, called (MCA-MAC). MCA-MAC aims to improve the previous metrics and thus the overall performance of WSNs through using cooperative communication. It enables source nodes from using intermediate nodes as relays to send their data through them to the access point. MCA-MAC protocol is also acting as a cross layer protocol where the best end-to-end path between the source and destination is found through an efficient algorithm. Mathematical analysis demonstrates that MCA-MAC protocol can determine the optimal relay node that has the minimum transmission time for the given source-destination pair. Using Multi-Paradigm Programming Language (MATLAB) simulation environment, this paper estimates MCA-MAC protocol performance in terms of system throughput, energy efficiency and delay. The results show that MCA-MAC protocol outperforms the existing scheme called Throughput and Energy aware Cooperative MAC protocol (TEC-MAC) protocol under ideal and dynamic channel conditions. Under ideal conditions, MCA-MAC protocol achieved throughput, and energy efficiency improvements of 12%, and 50% respectively, more than TEC-MAC protocol. While the packet delay through using MCA-MAC has been decreased by about 48% less than TEC-MAC protocol.

Keywords: WSN, MAC protocol, cooperative communication, energy efficient.

Received April 12, 2020; accepted September 7, 2020

A New Approach for Textual Password Hardening Using Keystroke Latency Times

Khalid Mansour¹ and Khaled Mahmoud^2
1Faculty of Information Technology, Zarqa University, Jordan

²King Hussein School of Computing Sciences, Princess Sumaya University for Technology, Jordan

Abstract: Textual passwords are still widely used as an authentication mechanism. This paper addresses the problem of textual password hardening and proposes a mechanism to make textual passwords harder to be used by unauthorized persons. The mechanism introduces time gaps between keystrokes (latency times) that would add a second protection line to the password. Latency times are converted into discrete representation (symbols) where the sequence of these symbols is added to the password. For accessing system, an authorized person needs to type his/her password with a certain rhythm. This rhythm is recorded at the sign-up time.This work is an extension to a previous work that elaborates more on the local approach of discretizing time gaps between every two consecutive keystrokes. In addition, more experimental settings and results are provided and analyzed. The local approach considers the keying pattern of each user to discretize latency times. The average, median and min-max are tested thoroughly.Two experimental settings are considered here: laboratory and real-world. The lab setting includes students studying information technology while the other group are not. On the other hand, information technology professional individuals participated in the real-world experiment. The results recommend using the local threshold approach over the global one. In addition, the average method performs better than the other methods. Finally, the experimental results of the real-world setting support using the proposed password hardening mechanism.

Keywords: Textual password, password hardening, latency time, keying pattern, discretization.

Received April 26, 2020; accepted November 18, 2020

Encryption Based on Cellular Automata for Wireless Devices in IoT Environment

Harinee Shanmuganathan and Anand Mahendran*

School of Computer Science and Engineering, Vellore Institute of Technology, Vellore, Tamil Nadu, India

This email address is being protected from spambots. You need JavaScript enabled to view it.

Abstract: A large number of physical objects are interconnected and accessed through the internet along with the existing technology like cloud computing, mobile computing, wireless sensor networks and big data forms a big paradigm called the Internet of Things (IoT). Data from remote and neglected areas are collected via wireless sensors and stored in the cloud. Growth in the number of the sensing device and the server to which these are connected leads to many security issues and malicious attacks. With mirai botnet and jeep hack about 150 million user’s information from MyFitnessPal nutrition app was stolen. This paper mainly focuses on security challenges for transmitting the data in the wireless sensor network in the IoT environment. To avoid the malicious attack, eavesdropping, algebraic attacks and other attacks a new security algorithm is proposed based on Cellular Automata (CA) which has a key length of 80 bits and the text size is 64 bits. Reversible rules of CA are used in this algorithm to achieve reversibility, parallelism, stability, randomness, and uniformity. The process of encryption and decryption is performed for 15 rounds to avoid dependency between the ciphertext and the plain text. Finally, we compare the execution time, throughput and the avalanche effect of the proposed algorithm with the existing algorithm like Advanced Encryption Standard (AES), Height, Present algorithm. The proposed algorithm is verified to be a better choice for lost cost and resource-restricted devices.

Keywords: Cellular Automata, secure data transmission, security algorithm, IOT.

Received May 25, 2020; accepted September 27, 2020

https://doi.org/10.34028/iajit/18/3/11

Full text  

A New Approach to Automatically Find and Fix

Erroneous Labels in Dependency Parsing Treebanks

Metin Bilgin

Department of Computer Engineering, Bursa Uludağ University, Turkey

Abstract: Dependency Parsing (DP) is the existence of sub-term/upper-term relations between the words that make up that sentence for each sentence in the text. DP serves to produce meaningful information for high-level applications. Correct labeling of the text corpus used in DP studies is very important. There will be mistakes in the results of the studies that will be performed with the wrongly-labeled text corpus. If text corpus is labeled manually or automatically by human beings, then faulty cases will occur. As a result of the cases that may arise from human factors or annotations used for labeling, faulty labels will be on treebanks. In order to prevent these errors, detection, and correction of possible faulty labeling is very important in terms of increasing the accuracy of the studies to be carried out. Manual correction of possible faulty labels requires great effort and time. The purpose of this study is to create a model that automatically finds possible faulty labels and offers new label suggestions for faulty labels. With the help of the proposed model, it is aimed to detect and correct possible faulty labels that are included in a text corpus, and to increase consistency among the text corpus of the same language. With the help of the developed model, suggesting new labels for faulty labels by a language expert will be a great convenient for the specialist. Another advantage of the model is that the developed model provides a language-independent structure. It has succeeded in obtaining successful results in finding and correcting potentially faulty labels in experimental studies for Turkish. An increase in accuracy has been detected in studies carried out for languages other than Turkish. In investigating the accuracy of the results obtained by the system, the results were analyzed with the help of 10 different language experts.

Keywords: Natural language processing, dependency parsing, universal dependency, error detection, treebank consistency.

Received July 27, 2020; accepted January 19, 2021

Discretization Based Framework to Improve

the Recommendation Quality

Bilal Ahmed and Wang Li

Department of Information and Computer, Taiyuan University of Technology, China

Abstract: Recommendation systems are information filtering software that delivers suggestions about relevant stuff from a massive collection of data. Collaborative filtering approaches are the most popular in recommendations. The primary concern of any recommender system is to provide favorable recommendations based on the rating prediction of user preferences. In this article, we propose a novel discretization based framework for collaborative filtering to improve rating prediction. Our framework includes discretization-based preprocessing, chi-square based attribution selection, and K-Nearest Neighbors (KNN) based similarity computation. Rating prediction affords some basis for the judgment to decide whether recommendations are generated or not, subject to the ratio of performance of any recommendation system. Experiments on two datasets MovieLens and BookCrossing, demonstrate the effectiveness of our method.

Keywords: Recommender systems, collaborative filtering, prediction, discretization, chi-square.

https://doi.org/10.34028/iajit/18/3/13

Full text  

Algebraic Supports and New Forms of

the Hidden Discrete Logarithm Problem

for Post-quantum Public-key Cryptoschemes

Dmitriy Moldovyan¹, Nashwan Al-Majmar², and Alexander Moldovyan¹

¹St. Petersburg Institute for Informatics and Automation of Russian Academy of Sciences, Russia

²Computer Sciences and Information Technology Department, Ibb University, Yemen

Abstract: This paper introduces two new forms of the hidden discrete logarithm problem defined over a finite non-commutative associative algebras containing a large set of global single-sided units. The proposed forms are promising for development on their base practical post-quantum public key-agreement schemes and are characterized in performing two different masking operations over the output value of the base exponentiation operation that is executed in framework of the public key computation. The masking operations represent homomorphisms and each of them is mutually commutative with the exponentiation operation. Parameters of the masking operations are used as private key elements. A 6-dimensional algebra containing a set of p³ global left-sided units is used as algebraic support of one of the hidden logarithm problem form and a 4-dimensional algebra with p² global right-sided units is used to implement the other form of the said problem. The result of this paper is the proposed two methods for strengthened masking of the exponentiation operation and two new post-quantum public key-agreement cryptoschemes.

Mathematics subject classification: 94A60, 16Z05, 14G50, 11T71, 16S50.

Keywords: Finite associative algebra, non-commutative algebra, right-sided unit, left-sided unit, global units, discrete logarithm problem, post-quantum cryptography, public key-agreement.

Received December 23, 2019; accepted November 24, 2020