"Annals. Computer Science Series" Journal
Romania, 300559 Timişoara, 6 Lascăr Catargiu str.
Phone: 004 0256 220 687 | Fax: 004 0256 220 690
E-mail: conference.fcia [@] tibiscus [.] ro | conference.fcia [@] gmail [.] com




Web design:
Ovidiu Crista
Updating:
Tiberiu Marius Karnyanszky
Editor-in-Chief

Annals. Computer Science Series
Tome 16, Fasc. 2


ISSN: 1583-7165 (printed journal)
ISSN: 2065-7471 (e-journal)
Owner: "Tibiscus" University of Timişoara, România
Editor: Mirton Publishing House of Timişoara, România
Distributor: "Tibiscus" University of Timişoara, România
Appearance: December, 2018


Next papers follows the review process for the Journal inclusion:

  • [ARR: 28.04.2017] Saheed Y.K., Arowolo M.O., Ibrahim S.A. - Artificial Neural Network For Breast Cancer Diagnosis
  • [ARR: 25.07.2017] G. Ojemeri, S. Abdulsalam, J. F. Yayock - Mathematical Modeling of Radiative Heat Source and Magnetic Field Effects on Free Convection Flow Embedded in a Moving Vertical Permeable Plate in the Presence of Porous Medium
  • [ARR: 26.07.2017] Y.K. Saheed, K. A. Gbolagade - Chinese Remainder Theorem Based Domain Name Security System
  • [ARR: 07.10.2017] Muhsin Hassanu Saleh, Mukhtar Bello - Online Hospital Management System
  • [ARR: 27.11.2017] Yakubu A. Ibrahim, Tunji S. Ibiyemi - Technical Algorithms For Efficient Optical Character Recognition System: An Overview
  • [ARR: 05.12.2017] Osuolale Peter Popoola, Matthew Taiwo Odusina - Survey of Strategies for Teaching Statistics at School
  • [ARR: 19.01.2018] Y. Zakari, A. Hassan - Application of First Order Differential Equation in Growth and Decay Problems Problems
  • [ARR: 19.01.2018] Adebayo O.Y., Adigun A.A., Isola E.O., Sijuade A.A. - Comparative Performance of Fingerprint and Face Recognition System
  • [ARR: 23.01.2018] Tochukwu Churchill Micheal AKUBUE - IoT; the Future of Industrial/Machine Automation
  • [ARR: 27.03.2018] Nguyen Thu Ha - The Trend of Education Reform in the World at the Present Context of Integration and Knowledge Economy
  • [ARR: 10.05.2018] Fagbola Temitayo Matthew, Oloyede Ayodele, Egbetola Funmilola Ikeolu, Akinpelu James Abiodun - CALPAS - An Employee Information and Payroll System for a Prototype University Enterprise in a Developing Economy Context
  • [ARR: 19.05.2018] Aliyu Rufai Yauri ,Salim Yusha’u - Hausa-English Cross Language Information Retrieval Disambiguation Approach
  • [ARR: 21.05.2018] S. O. Yusuff, I. A. Osinuga, O. J. Adeniran, S. A. Onashoga - Robust Three-step Broyden-like Algorithms for Functions of Several Variables
  • [ARR: 17.06.2018] Dharm Singh Jat, Chucknorris Garikayi Madamombe - Qualitative Study to Enhance the Security Features of Automated Teller Machines
  • [ARR: 21.06.2018] Onatunji, Adewale.P. - Application of Seemingly Unrelated Regression and Ordinary Least Squares Estimators on Blood Pressure
  • [ARR: 26.06.2018] Nikolaos Diamantopoulos, Ilias Spanos - STEM Education with Educational Robotics to Tackle Failure in Mathematics
  • [ARR: 28.06.2018] Osuolale Peter Popoola, Omotola Omotayo Dawodu, Olufemi Olusola Yusuff, Ayaniyi Wole Ayanrinde - Modelling the Effect of Climatic Change using Quadratic Regression and Factorial Analysis on Global Food Production
  • [ARR: 01.07.2018] Nikolaos Diamantopoulos, Anastasia Brami, Ilias Spanos - Flipped Classroom STEM Teaching: An Innovative Practice of Technologically Supported Teaching of Physics
  • [ARR: 11.07.2018] Adriana Mariş, Florin Mariş - Global Math Project - seeing algebra in a different light
  • [ARR: 23.07.2018] Yakubu A. Ibrahim, Silas A. Faki, Tunji S. Ibiyemi - Automatic Speech Recognition using MFCC in Feature Extraction based HMM for Human Computer Interaction in Hausa
  • [ARR: 03.08.2018] S. O. Adejuwon, V. G. Jemilohun, A. O. Ilesanmi - Application of one Server Queuing Models to Customers Management in the Cafeteria: A Case Study of Afe Babalola University, Ado-Ekiti (Abuad)
  • [ARR: 17.08.2018] Usman M. A., Sikiru A. B., Olayiwola M. O. - Analytical Solution of a Reactive Hydromagnetic Fluid through Porous Media between Permeable Pipes under Optically Thick Limit Radiation
  • [ARR: 03.09.2018] Gizela – Agneta Fuioagă - Optional Course for High School Learners Discover Real Everywhere Applications of Maths
  • [ARR: 04.09.2018] Alexandra Fortiș, Minerva Patriciu - Integrating Geogebra into Interactive Electronic Books
  • [ARR: 04.09.2018] Mihai Ș. Neamțu, Mihaela Neamțu - Derivative Application in Navigation into Outerspace
  • [ARR: 07.09.2018] Virginia Popovic, Kristijan Cincar - Complexity of Mathematical Concepts in Poetical Work of Ion Barbu (Dan Barbilian)
  • [ARR: 11.09.2018] Daniel-Zoltan Erzse - Dynamic Mathematics Software Use Cases To Introductory Calculus In Secondary School
  • [ARR: 20.09.2018] Dan L. Lacrama, Florentina A. Pintea, Tiberiu M. Karnyanszky, Florin Alexa - Brain-Computer Interfaces Development Trends
  • [ARR: 22.09.2018] Tajudeen Niyi Madandola, Kazeem Alagbe Gbolagade - A Framework for Improving the Speed of Principal Component Analysis Algorithm Based on Chinese Remainder Theorem
  • [ARR: 10.10.2018] Baale Adebisi Abimbola, Olasunkanmi Olawumi Roseline, Adelodun Felicia Ojiyovwi - Mobile Students’ Academic Record Manager
  • [ARR: 11.10.2018] A.Jerome Robinson, K.Satyanarayana, S.Ranganathan - Implementation of Cloud Computing in Archaeology to Track the Visitor for Prediction by Using the Hormonal Changes
  • [ARR: 11.10.2018] Oluyinka T. Adedeji, Adeleye S. Falohun, Oluwaseun M. Alade, Elijah O. Omidiora, Stephen O. Olabiyisi - Clonal Selection Algorithm for Feature Level Fusion of Multibiometric Systems
  • [ARR: 16.10.2018] Onitilo, Sefiu Adekunle, Usman, Mustapha Adewale - Mathematical Analysis of Blood Flow through a Stenosed Human Artery
  • [ARR: 17.10.2018] Isaac O. Ajao, Alademomi Aladesuyi, Oluwafemi S. Obafemi - Spatial patterns and socio-demographic determinants of the decision maker on large household purchases in Nigeria: A Bayesian Semi-parametric Geo-Additive model
  • [ARR: 21.10.2018] Abimbola Akintola, Tunji Ibiyemi, Amos Bajeh - Evaluation of an Optical Character Recognition Model for Yoruba Text
  • [ARR: 22.10.2018] K. O. Adetunji, A. O. Adejumo - A Modified Ratio Techniques in Successive Sampling on Two Occasions
  • [ARR: 26.10.2018] Rafiu Ganiyu, Oladotun Okediran, Omotola Busirat, Taofeeq Badmus - Development of a Modularized Model for a Multi-Process Food Manufacturing System using Hierarchical Timed Coloured Petri Nets
  • [ARR: 08.11.2018] Abba Almu, Abubakar Roko, Aminu Mohammed and Ibrahim Sa’idu - Towards Refining Unrated and Uninterested Items for Effective Collaborative Filtering Recommendations
  • [ARR: 11.11.2018] Ali Sadiqui, Ahmed Zinedine, Mohamed El Hari - Arabic digital resources in the service of learning
  • [ARR: 12.11.2018] Yaser Sadra - A New Image Compression by Gradient Haar Wavelet

    Next papers follows the Journal publication process:

  • [ACK: 06.04.2018] Adebowale Olusola Adejumo, James Daniel - Time Series Analysis of Brent Crude Oil Prices Per Barrel: A Box-Jenkins Approach
  • [ACK: 15.05.2018] Adebowale Olusola Adejumo, Tobi Oladayo Oloyede, Oluyemisi Adedola Adejumo, Pelumi Emmanuel Oguntunde, Oluwole Akinwumi Odetunmibi, Nehemiah Arhoesere Ikoba, Obalowu Job - Modelling of Enugu State Monthly Rainfall Using Box and Jenkins Methodology
  • [ACK: 26.07.2018] Adebowale Olusola Adejumo, James Daniel - A Bootstrap Method for Box-Jenkins Models With Application on Brent Crude Oil Prices Per Barrel
  • [ACK: 04.09.2018] P. A. Ozoh, M. O. Olayiwola - Predicting Energy Consumption using Typical Machine Learning and Computational Techniques
  • [ACK: 07.11.2018] Jinmisayo Awokola, Justice Emuoyibofarhe, Funmi Ajala - Performance Evaluation of a Cloud-based Picture Archivin and Communication System (PACS)
  • [ACK: 07.11.2018] Pradeepthi Nimirthi, Venkata Krishna P. - Deep Learning Based Sentiment Analysis for Recommender System
  • [ACK: 07.11.2018] J. G. Olawuwo, Olabisi O. Ugbebor - Modelling Extinction of Polio Transmission Agents by Stochastic Differential Equations

    » Analytic Approach To Face Emotion Recognition With SVM Kernels

    » Omobolaji F. Oyedokun, Elijah O. Omidiora, Ibrahim A. Adeyanju and Fagbola M. Temitayo

    ABSTRACT:

    Face emotion recognition is one of the challenges known with emotion recognition and it has received much attention during the recent years due to its application in different fields. SVM kernels were adopted to increase the robustness of face emotion recognition systems and to identify the most suitable kernel for emotion recognition. This paper uses radial basis function, linear function, sigmoid and polynomial function to identify the six basic emotions and neutral inclusive. In an attempt to achieve this aim the following steps were taken; collection of face emotion images, image pre- processing, features extraction and classification. Face emotion database was created by taken emotional photographs of persons who willing volunteer to help in this paper. The database contains 714 images from 51 persons. However, the photographs were converted from colored images to grayscale images for uniform distribution of colors. Relevant features for classification were extracted from the processed images such as the eyelids, cheeks, nose, eyebrows and lips. Our face emotion database was splitted into two dataset: training set and testing set. SVM classifier used images in the training set to train while images in the testing set were used to test SVM models. The evaluation of the system was performed on MATLAB using classification accuracy and classification time to identify the most suitable kernel for the system. The results obtained shows that sigmoid outperformed other kernels in terms of classification accuracy with overall performance accuracy of 99.33% while polynomial achieved the shortest classification time. In the future, we intend to investigate other classifiers for face emotion recognition and to classify more emotions.

    KEYWORDS:

    Feature, extraction, image preprocessing, classifiers, SVM, recognition, Kernels, face emotion.

    » Received: 30 October 2017
    » Accepted: 18 January 2018

    9 - 13

    imag/pdf.ico.gif PDF

    » A perspective of metacognition in solving math problems in Vietnam secondary schools

    » Nguyen Thi Huong Lan

    ABSTRACT:

    In an effort to innovate teaching and learning process to prepare for a new generation for the demands of the new era, many educators have discovered the value of metacognition. Students will need both mathematical skills and problem-solving skills, therefore, teachers should focus on both math content and thinking processes in students’ math learning. This paper presents the importance of metacognition in solving mathematical problems. A project was conducted for students at the age of thirteen, and the findings suggest that students used four problem-solving steps highlighted by George Polya. However, students feel better when they adjust their thinking processes or use metacognitive skills in the process of solving math problems.

    KEYWORDS:

    Skill, metacognition, problem-solving, mathematical thinking.

    » Received: 05 March 2018
    » Accepted: 15 May 2018

    14 - 20

    imag/pdf.ico.gif PDF

    » Homogenous Ensembles of Data Mining Algorithms in Predicting Liver Disease

    » Samuel Omokanye and Taye Aro

    ABSTRACT:

    Application of data mining algorithms to medical fields have been of interest as it helps patients get access to a better and faster healthcare. In this study, the effect of homogenous ensemble methods of bagging and boosting has been investigated as related to the prediction of the presence or absence of liver diseases. Experimental results show that while bagging and boosting did not improve the accuracy and sensitivity of algorithms in predicting liver disease, Boosting increased the specificity of algorithms.

    KEYWORDS:

    Homogenous, Bagging, Boosting, algorithms, data mining, classification.

    » Received: 03 November 2017
    » Accepted: 15 February 2018

    21 - 24

    imag/pdf.ico.gif PDF

    » Topology Management for Wireless Mesh Network

    » Justice Emuoyibofarhe, T. Madandola and Elizabeth Amusan

    ABSTRACT:

    This research formulated and simulated a topology management scheme for wireless mesh network (WMN) in areas of scalability and reliability; considering its vast present limitations in commercialization in many application areas. WMNs framework was devised and OMNeT++network simulator was used to simulate the WMNs model. A research method structure was devised that showed clearly how the project is carried out. An improved model for WMNs that use better approach To Mobile Adhoc Network routing protocol over the existing model was designed and formulated. Pearson Product Moment Correlation (PPMC) was used to find out the correlation between the Scenarios. PPMC produced 0.923 coefficients which showed a high positive correlation between the scenarios indicating that WMNs is reliable and scalable even with additional gateways.

    KEYWORDS:

    Correlation, Mesh, Scalability, Simulator, Topology, Wireless router.

    » Received: 23 May 2018
    » Accepted: 27 july 2018

    25 - 30

    imag/pdf.ico.gif PDF

    » Analysis of the Electrocardiogram by Means of Characteristics of the Disproportionality of Numerical Functions

    » Munther Al Shehab, Safwan Al Salaimeh, Shaker Dwairy and Wa’ed Hatamleh

    ABSTRACT:

    Electrocardiography: this is a method of recording the potential difference between two points in the electric field of the heart during its excitation. The modern technology allow you to record ECG on a long time interval in condition of person normal life(portable cardio); when carrying out functional tasks with doses physical exertion (bicycle ergometer, treadmill) and tests with the introduction of medicament preparations. To solve the problem, the following non-proportionality can be used: by the first - order derivative, by the value of the first order, as well as the disproportionality for the function y(t) by x(t), given parametrically. In this paper was an analyzed ECG assistant with the characteristics of the proportionality of numerical functions.

    KEYWORDS:

    ECG, Process, Excitation, Function, Proportionality, Record.

    » Received: 28 June 2018
    » Accepted: 27 July 2018

    31 - 34

    imag/pdf.ico.gif PDF

    » A Predictive Model for Tweet Sentiment Analysis and Classification

    » Abdullah K.-K. A., Folorunso S. O., Solanke O. O. and Sodimu S. M.

    ABSTRACT:

    Sentiment analysis over Twitter offers organisations and users a fast and effective way to monitor publics’ feelings towards events especially during crises, hence, motivated much work on twitter data. In this study, predictions on positive, negative and neutral sentiment based on security are analysed. A polarity classification of tweet messages was done with VADER algorithm considering contextual analysis. The analysis was performed by removing stop words in the tweet along with Wordnet lemmatiser for the morphological analysis of words in the features sets. As well as subjected to word sense disambiguation to consider contextual usages of words using a path length corpus based lexicon. Term Frequency (TF) and Term Frequency Inverse Document Frequency (TFIDF) are used as feature extraction from tweets and evaluation of the features reduction was carried out by calculating the accuracy of the predictions on sentiment and tweet messages with Chi-Square to explore the possibly useful features. Finally, validations are done with machine learning models at different sequence to compare the performance between each model.

    KEYWORDS:

    Sentiment analysis, Word sense disambiguation, Natural Language Processing, Chi-Square, VADER.

    » Received: 12 June 2018
    » Accepted: 25 July 2018

    35 - 44

    imag/pdf.ico.gif PDF

    » Neuro-Fuzzy Expert System For Diagnosis Of Thyroid Diseases

    » Tinuke Omolewa Oladele, Chuwunonso David Okonji, Adegun Adekanmi and Funke Florence Abiola

    ABSTRACT:

    The computerization of medical procedures has been identified to be one of the major challenges in the medical sector. Several techniques have been used in order to automate the processes in diagnosis of diseases; such processes include incorporation of artificial neural network and fuzzy logic techniques as expert systems with the knowledge about the domain. Such expert systems help to hasten the speed of diseases diagnosis, its accuracy and efficiency. In this paper, two artificial intelligence techniques; neural network and fuzzy logic system are considered. The two techniques are used to develop a hybrid intelligent computational system for the diagnosis of thyroid diseases. The experimental results obtain depend on the inputs to the neural network and also are set using a decision making system for making decisions on the thyroid disease according to the output of the neuro-fuzzy system.

    KEYWORDS:

    Expert System, Fuzzy Logic, Neural Network, Diagnosis, Thyroid Diseases.

    » Received: 29 May 2018
    » Accepted: 26 July 2018

    45 - 54

    imag/pdf.ico.gif PDF

    » Modelling Queuing System with Inverse Gamma Distribution: A Spreedsheet Simulation Approach

    » Olumide S. Adesina, Gbadebo Odularu and Adedodun Adedayo Funmi

    ABSTRACT:

    There is a need to provide user friendly approach to modeling and simulation for learners and business modeler. This study offers process-driven queuing simulation via spreadsheet which provides a user friendly, yet a readily available excel platform. Spreadsheet queuing simulation suggest a better way of understanding queue behavior than dedicated simulation software as it offers many benefits to students, practitioners and managers; helping them have to experience with modeling. In this study, single server queue is being simulated using Inverse Gama distribution. Creating single server queue (G/G/1) has been considered difficult to create, but this study presents easy to comprehend and applicable formulation. The spreadsheet simulation technique was applied to students queue at eatery in University of Lagos, Nigeria and results obtained were displayed and interpreted accordingly. This study recommends modelling and simulation of queuing systems with spreadsheet for students and business managers.

    KEYWORDS:

    Queuing theory, Simulation, Spreadsheets, Inverse Gamma distribution, G/G/1.

    » Received: 10 June 2018
    » Accepted: 27 July 2018

    55 - 60

    imag/pdf.ico.gif PDF

    » A Study On Efficient Automatic Speech Recognition System Techniques And Algorithms

    » Yakubu A. Ibrahim and Tunji S. Ibiyemi

    ABSTRACT:

    Automatic speech recognition is a system by which computer recognizes and responds accordingly to a spoken words of a person on the basis of his or her voice signal waveform. ASR system is being adopted in different aspects of life, such as telephones and home computer control system. Despite their growing presence, a proper technique for efficient ASR system remains a major issue for researchers. This study explains an analysis of different techniques and algorithms that can be used in ASR system such as LPC, LPCC, PLP, MFCC for feature extraction and DTW, SVM, HMM, VQ, GMM, MLP, ANN, KNN for feature classification and pattern recognition.

    KEYWORDS:

    ASR, DTW, HMM, Feature extraction, LPC, MFCC, SVM.

    » Received: 23 December 2017
    » Accepted: 26 July 2018

    61 - 68

    imag/pdf.ico.gif PDF

    » Usuability Evaluation Of Twitter Micro-Blog Using Heuristic Approach

    » Abdullahi Yola Musa and Rasheed Gbenga Jimoh

    ABSTRACT:

    The innovations that accompany the introduction of social media as a tool of communication have really set a pace at which several activities are carried out. The social network has attracted so many users across the world. Twitter becoming the second most widely used micro-blog after facebook, as real-time sharing information electronic tool. However, numerous user-interface challenges have been identified in twitter micro blog, ranging from credibility of the information shared on twitter to icons improvement. This paper applies heuristic evaluation techniques on twitter microblog. A web-based e-questionnaire is used as a means of collecting data from different level of users (Novice, Beginner and Professional). Over 100 users filled e-questionnaire to express their user experience which serves as source of data used in this study. The result according to the weighted score values state that the twitter as one example of micro-blog proved to be one of the best social networks, which also show that all information is credible in the platform. The statistical T-Test analysis presents outstanding results that the usability evaluation of twitter platform is of great significant.

    KEYWORDS:

    Micro-blog, Twitter, Statistical T-Test, e-questionnaire, Usability evaluation.

    » Received: 16 August 2018
    » Accepted: 4 October 2018

    69 - 76

    imag/pdf.ico.gif PDF

    » An In-depth Study of Typical Machine Learning Methods via Computational Techniques

    » P. A. Ozoh, M. O. Olayiwola and A. A. Adigun

    ABSTRACT:

    The ability to model and perform decision modeling and analysis is an essential feature of many real-world applications ranging from emergency medical treatment in intensive care units to military command and control systems. Models are essential in providing support for businesses processes, systems and dealing with complex problems. The development of appropriate models for planning and management is a tool for improving efficiency in real world problems. Consequently, a thorough study of common machine learning techniques is undertaken with the aim of comparing the techniques and identifying a suitable technique that is applicable to modeling and forecasting real world data. Modeling helps make informed decisions, using techniques for analysis, estimation and, forecasting. There is a lot of research published about machine learning techniques, with the intention of developing models for estimations. In order to identify an appropriate machine learning technique, it is necessary to carry out a comparative study of commonly used machine learning techniques. For this purpose, a review of Box-Jenkins technique, regression method and artificial neural network (ANN) is undertaken with the aim of identifying a reliable and accurate technique for modeling data.

    KEYWORDS:

    Machine learning, models, planning, estimation, efficiency.

    » Received: 30 May 2018
    » Accepted: 04 September 2018

    77 - 81

    imag/pdf.ico.gif PDF

    » Developing Predictive Models using Typical Machine Learning and Computational Techniques

    » P. A. Ozoh, Shapiee Abd-Rahman and Moruf Olayiwola

    ABSTRACT:

    This study investigates the accuracy of developing predictive models using machine learning techniques. The machine learning techniques considered in this study include artificial neural network (ANN) and Kalman filter adaptation algorithm. Predictive values are computed based on these techniques. These techniques are tested on daily electricity consumption data and are computed using ANN technique and Kalman filter adaptation algorithm. The accuracy of the predicted values of these techniques are investigated using statistical parameters. This research identified Kalman technique as more accurate in making predictions than ANN technique.

    KEYWORDS:

    Accuracy, modelling, prediction, machine learning, perfornance measures.

    » Received: 31 July 2018
    » Accepted: 04 September 2018

    82 - 85

    imag/pdf.ico.gif PDF

    » Genetic Algorithm Approach for Fabric Pattern Generation in Textile Industries

    » Obe O. and Egwuche O. S.

    ABSTRACT:

    It is a known fact that there are more possibilities in nature than human brain can conceive. This phenomenon is more pronounced in fabric industry where experts struggle daily for creation of new fabric patterns when in reality the number of patterns seems infinite. In this research, we developed a system that will complements human reasoning in creation of more possible fabric patterns in locally made fabric in Nigeria. The possibility of Genetic Algorithm for pattern generation in textile production processes is investigated. The system has good credibility and ability to generate fabric patterns faster, easier and in more quantities than team of fabric designers. The system developed is able to save this cultural heritage from extinction as there are more patterns to produce.

    KEYWORDS:

    Genetic Algorithm, Textiles, Pattern Generation.

    » Received: 21 April 2018
    » Accepted: 04 September 2018

    86 - 91

    imag/pdf.ico.gif PDF

    » Technical Methods and Algorithms for Developing Efficient Optical Character Recognition System: An Overview

    » Yakubu A. Ibrahim and Tunji S. Ibiyemi

    ABSTRACT:

    Machine recognition problem of printed documents in Optical Character Recognition has been the target of research in the area of pattern recognition. Study in this aspect has been controlled by a need to join the natural process of image input with the data processing abilities of computer system. In this regard, engineers and scientists are not able to make judicious use of OCR systems for their technical work because they lack effective algorithms for interpretation of complex expressions even though it is important part of a Human Computer Interaction system. However, OCR in a nut shell is the electronic change of printed or handwritten text into images using machine encoding scheme representation like ASCII or Unicode. Hence, various methods and algorithms have been demonstrated in the study to increase the efficiency of system to effectively solve OCR problems. The study shows the concept of various OCR algorithms such as support vector machine, decision tree classifier, statistical, structural, artificial neural networks and template matching algorithms.

    KEYWORDS:

    ASCII, Unicode, Computer, HCI, OCR, Pattern recognition.

    » Received: 19 March 2018
    » Accepted: 04 September 2018

    92 - 99

    imag/pdf.ico.gif PDF

    » Rotation Invariant Skin Detection Approach based on Combination of Probabilistic Distribution Estimation and Single Scale Retinex

    » Shervan Fekri-Ershad

    ABSTRACT:

    Skin detection is one of the main steps in many image processing systems such as face detection, human identicaton, etc. Since now, many methods are proposed to done it accurately. Most of previous methods have tried to find best match intensity distribution with skin pixels in input image. Experimental Results show that these methods cannot provide accurate results for each kind of human skin colors. In this paper, a two step approach is proposed to solve this problem using color probabilistic distribution estimation technique. The proposed approach consist two steps. In the first step, skin intensity distribution is estimated using some train photos of pure skin. In the second step, the skin areas are detected using Gaussian model and optimal threshold tuning. Single scale retinex technique is used as preprocessing step to increase detection rate. In the result part, the proposed approach is applied on human images and the accuracy rate is computed. The proposed approach can be used for all kinds of skin using train stage which is the main advantages of it. Low sensitivity to impulse noise, low run time complexity, and rotation invariant are another advantages of the proposed approach.

    KEYWORDS:

    Skin detection, Probabilistic Estimation, Threshold tuning, Image Processing, Gaussian Model.

    » Received: 14 November 2017
    » Accepted: 04 September 2018

    100 - 107

    imag/pdf.ico.gif PDF

    » An Improved Procedure for Fourier Regression Analysis

    » Abass Taiwo and Timothy Olatayo

    ABSTRACT:

    Fourier regression is a method used to represent time series by a set of elementary functions called basis. This work was used to propose a new procedure for Fourier regression which has the ability to reveal the period of significant frequencies and can be used to fit a periodic trend. The procedure involved the use of spectral analysis for component identification, discrete Fourier transform for estimating the coefficients and 95% confidence bound of the autocorrelation function for residual diagnostic check. The method was applied to Nigerian road accidental death time series data in order to test the efficiency. From the results, the spectral analysis magnitude plot revealed one and three components Fourier regression model. The periodic trend of one and three components Fourier regression model was fitted. The three components Fourier regression model was the most suitable and appropriate model since it has a close pattern to the original series and as well revealed the cyclical movement in Nigerian road accidental death. This was validated based on the three components residual autocorrelation function values which fell within the 95% confidence bound and this indicated the residuals are whiten. In conclusion, the proposed procedure for Fourier regression model was adequate for studying the important periodicities and their frequencies, fitting periodic trend and suitable for forecasting Nigerian road accidental death time series data.

    KEYWORDS:

    Fourier regression, Spectral density function, Periodic time series, Autocorrelation function and Road accidental death.

    » Received: 12 July 2018
    » Accepted: 04 September 2018

    108 - 112

    imag/pdf.ico.gif PDF

    » Development of an Expert System for Selected Blood Diseases Diagnosis and Treatment

    » Olusayo D. Fenwa, Funmilola A. Ajala and Adeleye S. Falohun

    ABSTRACT:

    Research had stated that there is increase in the number of people dying of blood diseases likewise there is a large number of people suffering from different kinds of blood diseases due to unavailability of human experts and inaccessibility of Haematology consultation. Hence this paper designs an expert system application for diagnosing selected blood diseases using rule-based method. The computer programming language employed was the C# programming language and MySQL as the Relational Database Management System (RDBMS). The results obtained showed that the expert system was able to successfully diagnose blood diseases corresponding to the selected symptoms entered as query.

    KEYWORDS:

    Expert System, Anaemia, Haemophilia, Leukaemia, Homochromatic, Knowledge base, Inference Engine, Interface and Knowledge Acquisition.

    » Received: 28 August 2018
    » Accepted: 02 October 2018

    113 - 120

    imag/pdf.ico.gif PDF

    » Steady Flow of a Reactive MHD Fluid through a Permeable Pipe under Optically Thick Limit Radiation

    » Usman M. A., Olayiwola M. O. and Sikiru A. B.

    ABSTRACT:

    This research work investigates the analytical solution of the temperature profile distribution of a one-dimensional fluid under the influence of magnetic fluid strength of a reactive hydromagnetic fluid flow through porous media between permeable beds under optically thick limit radiation. The fluid is considered to be incompressible and electrically conducting fluid flowing steadily through porous media with the effect of magnetic strength. The analytical solutions of the non-linear dimensionless energy equations governing the fluid flow are obtained using integration and series solution of Adomian Decomposition Method (ADM) and the effects of all important flow properties on the fluid flow are presented graphically and discussed.

    KEYWORDS:

    Temperature, Permeable Pipe, Optically Thick Limit, Radiation, Porous Media, Hydromagnetic Fluid.

    » Received: 19 August 2018
    » Accepted: 02 October 2018

    121 - 129

    imag/pdf.ico.gif PDF

    » Alternative Estimator for Multivariate Location and Scatter Matrix in the Presence of Outlier

    » Obafemi O. S. and Oyeyemi G. M.

    ABSTRACT:

    It is generally known that in estimating location and scatter matrix of multivariate data when outliers are presents, the method of classical is not robust. The Maximum Likelihood Estimator (MLE) is always very sensitive to some deviations from the assumptions made on the data, especially, presence of outliers. To get over the above stated problem, many alternative estimators that are robust have been proposed in the last decades. Some of these estimators include the Minimum Covariance Determinant (MCD), the Minimum Volume Ellipsoid (MVE), S-Estimators, M-Estimators and Minimum Regularized Covariance Determinant (MRCD) among others. All the methods converged on tackling the problem of robust estimation by finding a sufficiently large subset of the data. In this paper, a robust method of estimating multivariate location and scatter matrix in the presence of outliers is proposed. The proposed estimator is obtained using the best units (samples) from the available data set that satisfied a set of three optimality criteria (CA,CH,CG).The performance of the proposed robust method was compared with two of the existing robust methods (MCD and MVE) and the classical method with their application in Principal component analysis data simulation. The measure of performance used was the Mean Square Errors (MSE) of the characteristic roots (eigen-values) of the variance-covariance matrix. Generally, the proposed alternative method is better than other robust methods and classical method, when the level of magnitude of outliers is small and also performed considerably well with MCD and MVE when the level of magnitude is high at all percentages of outliers.

    KEYWORDS:

    Eigen-values, Scatter matrix, Mean Square Errors, Outliers, Robust.

    » Received: 28 August 2018
    » Accepted: 02 October 2018

    130 - 136

    imag/pdf.ico.gif PDF

    » Using Predictive Machine Learning Regression Model To Predict The Population Of Nigeria

    » Odunayo Olanloye, Esther Oduntan and Olawumi Olasunkanmi

    ABSTRACT:

    In any nation, there is always a government in place charged with the responsibly of governing the citizens of the country and for effective governance, there should be plan based on the number of citizens (population) in such country. Government therefore spends a lot on census exercises which is meant to count the number of people living in the country. Census exercises in Nigeria were characterized by various abnormalities resulting into inaccuracies in the results obtained. Series of research work have been published on how to solve this problem. In this research, different types of predictive models to characterize the population of Nigeria were developed using machine learning regression method. The best of the models was selected and used to predict the population of Nigeria up to the year 2050. By 2050, all things being equal, the population was predicted to be 400,000,000. The instrument used for the implementation is Matlab modeling toolbox. The research work will serve as a very useful tool in the area of population prediction and assist the government in her future plan.

    KEYWORDS:

    Algorithm, Artificial Intelligence, Government, Machine Learning, Population, Prediction.

    » Received: 8 August 2018
    » Accepted: 1 October 2018

    137 - 142

    imag/pdf.ico.gif PDF

    » New Trends in Modelling Climate Change in the Era of Big Data

    » Osuolale Peter Popoola and Nicholas Nsowah Nuamah

    ABSTRACT:

    Big data is data sets that are so voluminous and complex that traditional data processing application software are inadequate to deal with. It is typically characterized by the so called, seven “V’s” namely; volume, velocity, variety, Value, Veracity, variability and validity. Big Data can be thus defined as very high volume, velocity and variety of data that require a new high-performance processing. Thus, this research work survey different technique for handling big data for modelling climate change. Various statistical models were examined and X-ray. The survey shows that ANCOVA (analysis of covariance) is the appropriate technique for handling big data. ANCOVA contains a mixture of qualitative variables associated with analysis of variance (ANOVA) and the quantitative variables associated with regression analysis. ANCOVA is the meeting point under the umbrella of analysis of variance and regression techniques.

    KEYWORDS:

    Big Data, Pooled Data, Analysis of Variance, Analysis of Covariance and Multiple Regression.

    » Received: 28 July 2018
    » Accepted: 04 September 2018

    143 - 148

    imag/pdf.ico.gif PDF

    » Performance Evaluation of PSO, PSOCA and MPSOCA for Solving University Timetabling Problem

    » Oluwaseun O. Alade, Christopher A. Oyeleye, Oluyinka T. Adedeji, Elijah O. Omidiora and Stephen O. Olabiyisi

    ABSTRACT:

    In this paper, performance evaluation of Particle Swarm Optimization algorithm (PSO), Particle Swarm Optimization based Cultural Algorithm (PSOCA) and Modified Particle Swarm Optimization based Cultural Algorithm (MPSOCA) was carried out using simulation time, fitness value and number of unallocated courses as performance metrics. The evaluation results of PSO, PSOCA and MPSOCA yielded average simulation times of 35.29, 37.68 and 17.42 seconds, respectively. Also, fitness values of 85, 89 and 90% were recorded for PSO, PSOCA and MPSOCA, respectively. PSO have a total average number of 60 subjects unallocated compare to PSOCA and MPSOCA that successfully allocated all the subjects.

    KEYWORDS:

    Particle Swarm Optimization Algorithm, Cultural Algorithm, Timetabling.

    » Received: 21 September 2018
    » Accepted: 11 November 2018

    149 - 155

    imag/pdf.ico.gif PDF

  • 
    » www.fcia.tibiscus.ro |  » www.ccsitia.tibiscus.ro |  » www.geogebra.tibiscus.ro |  » www.tibiscus.ro |  © 2003-2018, Last update: 12.11.2018 / 11:00