Abstracts

BRAIN. Broad Research in Artificial Intelligence and Neuroscience

Volume 7, Issue 3

August 2016

www.brain.edusoft.ro

Editor in Chief: Bogdan Pătruţ

1. Automatic Anthropometric System Development Using Machine Learning

Long The Nguyen, Irkutsk National Technical University, Irkutsk, Russia
Huong Thu N guyen, Irkutsk National Technical University, Irkutsk, Russia
Abstract

The contactless automatic anthropometric system is proposed for the reconstruction of the 3D-
model of the human body using the conventional smartphone. O ur approach involves three main

steps. The first step is the extraction of 12 anthropological features. Then we determine the most
important features. Finally, we employ these features to build the 3D model of the human body and
classify them according to gender and the commonly used sizes.

2. The Technological Advent and Dynamics of the Network Society. The "Middle -Aged

Approach"

Elena-Mădălina Vătămănescu, Bucharest University of Economic Studies, Bucharest, Romania

Elena-Alexandra Gorgos, National University of Political Studies and Public Administration,
Bucharest, Romania

Andreia-Gabriela Andrei, Alexandru Ioan C uza University of Iasi, Iasi, Romania
Vlad-Andrei Alexandru, Center for Research in Management and Leadership, National University
of Political Studies and Public Administration, Bucharest, Romania

Abstract
Nowadays, scholars have become interested in the ways new media influence young people, but its

influence on middle-aged people have not been thoroughly examined. This age category is often
ignored as most of the online activities are performed by young persons. New media gathers a wide
range of phenomena which may become concepts of the network society through their diversity,

knowledge and novelty. Interactivity is the most important characteristic, turning the user into a
content creator, not just into a receiver. Moreover, what was once considered to be a personal state

of mind tends to become a part of the public domain. Starting from these premises, the article
advances the idea that the Internet can be beneficial not just for teenagers, but also for the middle-
aged group oriented towards keeping in touch with relatives and friends and towards finding online

useful information. At this level, the present paper aims to discover direc tions given by network
society in the lives of middle-aged people. To this end, the research relies on an interview-based

survey which addresses the way people may adapt to communication technology and to its
particularities, exploring advantages or discovering potential drawbacks.

Abs tracts

3. A Synoptic of Software Implementation for Shift Registers Based on 16
th

Degree Primitive

Polynomials

Mirella Amelia Mioc, Stefan cel Mare University of Suceava, Suceava, Romania
Abstract

Almost all of the major applications in the specific Fields of Communication used a well-known
device called Linear Feedback Shift Register. Usually LFSR functions in a Galois Field GF(2

n
),

meaning that all the operations are done with arithmetic modulo n degree Irreducible and especially

Primitive Polynomials. Storing data in Galois Fields allows effective and manageable manipulation,
mainly in computer cryptographic applications. The analysis of functioning for Primitive

Polynomials of 16th degree shows that almost all the obtained results are in the same time
distribution.

4. Micro Expression Recognition Using the Eulerian Video Magnification Method

Elham Zarezadeh, Science and Art University, Yazd, Iran
Mehdi Rezaeian, Faculty of Computer Engineering, Yazd University, Yazd, Iran
Abstract

In this paper we propose a new approach for facial micro expressions recognition. For this purpose
the Eulerian Video Magnification (EVM) method is used to retrieve the subtle motions of the face.

The results of this method are obtained as in the ma gnified images sequence. In this study the
numerical tests are performed on two databases: Spontaneous Micro expression (SMIC) and
Category and Sourcing Managers Executive (CASME). We evaluate our proposed method in two

phases using the eigenface method. I n phase 1 we recognize the type of a micro expression, for
example emotional versus unemotional in SMIC database. Phase 2 classifies the recognized micro

expression as negative versus positive in SMIC database and happiness versus disgust in CASME
database. The results show that the eigenface method by the EVM method for the retrieval of subtle
motions of the face increases the performance of micro expression recognition. Moreover, the

proposed approach is more accurate and promising than the previous works in micro expressions
recognition.

5. The Ambivalence of Strengths and Weaknesses of E-Learning Educational Services

Venera-Mihaela Cojocariu, Vasile Alecsandri University of Bacau, Bacau, Romania
Iuliana Lazar, Vasile Alecsandri University of Bacau, Bacau, Romania

Gabriel Lazar, Vasile Alecsandri University of Bacau, Bacau, Romania
Abstract
This paper represents a thorough phase in the effort to identify and assort the strengths and

weaknesses of e- learning educational services. This paper reviews a synt hesis of the assessments on
the e-learning educational services through a survey of the specialized literature from 2000 to 2012

in order to identify the strengths and weaknesses of e- learning educational services which were
reported during the past decade. The steps of our approach are the following: 1. The identification of
a large number of specialized studies that analyze the above mentioned issue; 2. A basic theoretical

review of the research from the perspective of identifying the strengths and weakne sses of the e-
learning educational services and some of their implications on the intellectual development of the

beneficiaries; 3. A descriptive statistical data analysis which is carried out in order to extract
information about strengths and weaknesses relevant to the literature taken into consideration; 4.
Results classification and interpretation; 5. Formulating practical suggestions for the notion of e -

learning educational services considering the development of studies on the impact of their use on
the intellectual development of the beneficiaries. The study results highlighted that strengths and

weaknesses are not 'pure', but ambivalent, simultaneously incorporating meanings and limits with
different weights. A predictive model of future e- learning educational services can be designed on

Abs tracts

the basis of the results obtained in the research. This predictive model is based on a pedagogical
concept that takes into account the ambivalence of the higher indices which have been identified.

6. New Computer Assisted Diagnostic to Detect Alzheime r Disease

Ben Rabeh Amira, National Engineering School of Tunis (ENIT), Tunis, Tunisia
Benzarti Faouzi, National Engineering School of Tunis (ENIT), Tunis, Tunisia
Amiri Hamid, National Engineering School of Tunis (ENIT), Tunis, Tunisia

Mouna Ben Djebara, Hospital Razi, Manouba, Tunis, Tunisia
Abstract

We describe a new Computer Assisted Diagnosis (CAD) to automatically detect Alzheimer Patients
(AD), Mild Cognitive Impairment (MCI) and elderly Controls, based on the segmentation and
classification of the Hippocampus (H) and Corpus Calosum (CC) from Magnetic Resonance Images

(MRI). For the segmentation we used a new method based on a deformable model to extract the
area wishes, and then we computed the geometric and texture features. For the classification we

proposed a new supervised method. We evaluated the accuracy of our method in a group of 25
patients with AD (age±standard-deviation (SD) =70±6 years), 25 patients with MCI (age±SD=65±8
years) and 25 elderly healthy controls (age±SD=60±8 years). For the AD patients we found an

accuracy of the classification of 92%, for the MCI we found 88% and for the elderly patients we
found 96%. Overall, we found our method to be 92% accurate. Our method can be a useful tool for

diagnosing Alzheimer’s Disease in any of these Steps.

7. Participative Teaching with Mobile Devices and Social Networks for K -12 Children

Livia Ştefan, Institute for Computers ITC SA Bucharest, Romania

Dragoş Gheorghiu, Doctoral School, National University of Arts, Bucharest, Romania
Abstract
This article details a set of participatory pedagogical experiments conducted within a research gra nt

PN II IDEI (”Time Maps. Real communities, virtual worlds, experimented pasts”) performed with
the purpose of helping rural communities in identifying their cultural heritage and transmitting it to

the younger generations by means of modern IT technologies, including web 2.0. In a Danub ian
rural community, several points of archaeological interest (POIs) were identified, which were then
included in a geographic Augmented Reality application for smartphones and tablets. Subsequently,

the geographic data we re collected from the archaeological site by the K -12 children, under the
coordination of an academic staff member of the National University of Arts in Bucharest, and

stored on their devices using Google Maps. The augmented information provided on the site was
annotated and shared with other K-12 children, through different social networks sites (SNS) and
content postings. This first stage experiment was extended to the development of a social learning

environment complementary to the educational site ( www.timemaps.net) to support the
transmission of several traditional technologies (textile, ceramic, glass) in a collaborative manner.

We consider that our experiments can significantly increase the visibility of the information
pertaining to the identity of target places and communities among the younger generation. A
mobile- learning paradigm, in combination with web 2.0 technologies, was the support for a

distributed and low-cost platform for communication and collaboration. Social networks linked the
archaeological heritage and the academic research with the larger community of rural K -12

children. The article analyzes this platform as a solution for creating, collecting and sharing
educational content, and presents conclusions on using social media for effective blended learning
and transmittal of the cultural he ritage.

Abs tracts

8. Prediction of Thyroid Disease Using Data Mining Techniques

Irina Ioniţă, Petroleum-Gas University of Ploieşti, Ploieşti, Romania

Liviu Ioniţă, Petroleum- Gas University of Ploieşti, Ploieşti, Romania
Abstract

Recently, thyroid diseases are more and more spread worldwide. In Romania, for example, one of
eight women suffers from hypothyroidism, hyperthyroidism or thyroid cancer. Various research
studies estimate that about 30% of Romanians are diagnosed with endemic goiter. Factors that

affect the thyroid function are: stress, infection, trauma, toxins, low-calorie diet, certain medication
etc. It is very important to prevent such diseases rather than cure them, because the majority of

treatments consist in long term medication or in chirurgical intervention. The current study refers to
thyroid disease classification in two of the most common thyroid dysfunctions (hyperthyroidism
and hypothyroidism) among the population. The authors analyzed and compared four classification

models: Naive Bayes, Decision Tree, Multilayer Perceptron and Radial Basis Function Network.
The results indicate a significant accuracy for all the classification models mentioned above, the

best classification rate being that of the Decision Tree model. The data set used to build and to
validate the classifier was provided by UCI machine learning repository and by a website with
Romanian data. The framework for building and testing the classification models was KNIME

Analytics Platform and Weka, two data mining software.

9. An Efficient Combined Meta-Heuristic Algorithm for Solving the Traveling Salesman

Proble m

Majid Yousefikhoshbakht, Bu-Ali Sina University, Hamedan, Iran
Azam Dolatnejad, Islamic Azad University, Tehran, Iran

Abstract
The traveling salesman problem (TSP) is one of the most important NP-hard Problems and probably
the most famous and extensively studied problem in the field of combinatorial optimization. In this

problem, a salesman is required to visit each of n given nodes once and only once, starting from any
node and returning to the original place of departure. This paper presents an efficient evolutionary

optimization algorithm developed through combining imperialist competitive algorithm and lin-
kernighan algorithm called (MICALK) in order to solve the TSP. The MIC ALK is tested on 44 TSP
instances involving from 24 to 1655 nodes from the literature so that 26 best known solutions of the

benchmark problem are also found by our algorithm. Furthermore, the performance of MICALK is
compared with several metaheuristic algorithms, including GA, BA, IBA, ICA, GSAP, ABO, PSO

and BCO on 32 instances from TSPLIB. The results indicate that the MICALK performs well and is
quite competitive with the above algorithms.

10. A Repeated Signal Difference for Recognising Patterns

Kieran Greer, Distributed Computing Systems, Belfast, UK
Abstract
This paper describes a new mechanism that might help with defining pattern sequences, by the fact

that it can produce an upper bound on the ensemble value that can persistently oscillate with the
actual values produced from each pattern. With every firing event, a node also receives an on/off

feedback switch. If the node fires then it sends a feedback result depending on the input signal
strength. If the input signal is positive or larger, it can store an ‘on’ switch feedback for the next
iteration. If the signal is negative or smaller it can store an ‘off’ switch feedback for the next

iteration. If the node does not fire, then it does not affect the current feedback situation and receives
the switch command produced by the last active pattern event for the same neuron. The upper

bound therefore also represents the largest or most enclosing pattern set and the lower value is for
the actual set of firing patterns. If the pattern sequence repeats, it will oscillate between the two

Abs tracts

values, allowing them to be recognised and measured more easily, over time. Tests show that
changing the sequence ordering produces different value sets, which can also be measured.

11. An Energy-Saving Concept of the Smart B uilding Power Grid with Separated Lines for

Standby Devices

Dmytro Zubov, Universidad Politécnica de San Luis Potosí, San Luis Potosí, Mexico
Abstract
Standby power takes 5-10 % of the residential electricity around the world. Some countries lose

more than 14 % of the total electricity used in the residential sector. Hence, a new energy-saving
concept that could help to decrease the power losses is discussed in this paper. Firstly, the two

power lines of infrastructure for continuously connected equipment and for standby devices is
proposed for new smart buildings. Secondly, the segmented infrastructure with unified hardware
units is proposed for existing smart buildings (the new one can apply this principle as well). The

contactors (i.e. unified hardware units) consist of the NodeMcu Lua ESP8266 WiFi IoT
development board, ACS712T ELC-30A current sensor, and the Songle relay. The automatic mode

is based on three steps: measurement of the current using ACS712T ELC -30A sensor in all
segments except the root; switching off the relays with the current less than or equal to any numb er
in the historical data; switching off the root contactor if all the descendent relays (i.e. contactors) are

switched off. Second step represents the linear classification with sliding window in machine
learning. The software consists of two parts, low- level Arduino sketches and high- level C#

Windows form app. They are connected by MQTT broker Mosquitto. The proposed concept was
successfully tested using a prototype with three segments, one of which includes smart lighting. The
payback period is of approximately one month and a half for the whole-building switch concept.

INSTRUCTIONS FOR AUTHORS

Author Guidelines

Authors must submit their papers via email to brain@edusoft.ro or they can create an
account and submit their papers online, at www.brain.edusoft.ro. Submitted papers must be
written in DOC format (Microsoft Word document), in as clear and as simple as possible English.

Preferred maximum paper length for the papers is 20 pages, including figures.
The template for the paper is at this address:

http://brain.edusoft.ro/Ne w_Te mplate_for_BRAIN.doc

The text is single-spaced; uses a 12-point Times New Roman font; employs italics, rather
than underlining (except with URL addresses); and all illustrations, figures, and tables are placed

within the text at the appropriate points, rather than at the end. The title will be bold 14-point, and
the author will be 12-point italic. Figures have caption in bottom-center side, and tables have
captions in left-top side. Use a tab for identing each paragraph and the subtitles, too. The subtitles

will be bold 12-point. Please use Microsoft Word 97-2003, or Word 2010, 2013.
We encourage the authors to use the camera ready format even for the first submission. All

paper submissions will be carefully reviewed b y an editor, and by the members of the scientific
board or independent experts, who will provide a written feedback with comments and ratings.
Authors will be notified of acceptance in maximum 3 weeks. Accepted manuscripts should be

revised according to the comments of the reviewers and of the editors.
For questions concerning manuscript submission, contact Mr. Bogdan Patrut by mail at

bogdan@edusoft.ro.

Submission Preparation Checklist

As part of the submission process, authors are required to check off their submission's
compliance with all of the following items, and submissions may be returned to authors that do not
adhere to these guidelines.

1. The submission has not been previously published, nor is it before another journal for
consideration (or an explanation has been provided in Comments to the Editor).

2. The submission file is in Microsoft Word (DOC, DOCX) or RTF document file format.
3. Where available, URLs for the references have been provided.
4. The text is single-spaced; uses a 12-point font; employs italics, rather than underlining

(except with URL addresses); and all illustrations, figures, and tables are placed within the text at
the appropriate points, rather than at the end.

5. The text adheres to the stylistic and bibliographic requirements outlined in the Author
Guidelines, which is found in About the Journal.

6. The instructions in Ensuring a Blind Review have been followed.

Ensuring a Blind Peer Review

To ensure the integrity of the blind peer-review for submission to this journal, every effort

should be made to prevent the identities of the authors and reviewers from being known to each
other. This involves the authors, editors, and reviewers (who upload documents as part of their

review) checking to see if the following steps have been taken with regard to the text and the file
properties:

BRAIN. Broad Res earch i n Arti fi ci al Intelli gence and Neuros ci ence

Vol ume 5, Is s ues 1-4, December 2014, ISSN 2067-3957 (onli ne), ISSN 2068 - 0473 (pri nt)

1. The authors of the document have deleted their names from the text, with "Author" and
year used in the references and footnotes, instead of the authors' name, article title, etc.

2. With Microsoft Office documents, author identification should also be removed from the
properties for the file (see under File in Word), by clicking on the following, beginning with File on

the main menu of the Microsoft application: File > Save As > Tools (or Options with a Mac) >
Security > Remove personal information from file properties on save > Save.

3. With PDFs, the authors' names should also be removed from Document Properties found

under File on Adobe Acrobat's main menu.

Authors retain copyright and grant the journal right of first publication with the work
simultaneously licensed under a Creative Commons Attribution License that allows others to share

the work with an acknowledgement of the work's authorship and initial publication in this journal.
Authors are able to enter into separate, additional contractual arrangements for the non-

exclusive distribution of the journal's published version of the work (e.g., post it to an institutional

repository or publish it in a book), with an acknowledgement of its initial publication in this journal.
Authors are permitted and encouraged to post their work online (e.g., in institutional

repositories or on their website) prior to and during the submission process, as it can lead to
productive exchanges, as well as earlier and greater citation of published work

Privacy Statement

The names and email addresses entered in this journal site will be used exclusively for the

stated purposes of this journal and will not be made available for any other purpose or to any other

party.

Indexing

Our journal is currently indexed/listed in the following indexing services and

international databases:

1. Emerging Sources C itation Index, ESCI - Web Of Science (Thomson-Reuters)
2. Directory of Open Access Journals (DOAJ)
3. EBSCO (EBSCO Open Access Computer Science, EBSCO Open Access Journals,

EBSCO Open Access Medical and Health Collection)
4. IndexCopernicus

5. The Linguist List
6. Google Academic
7. Ulrichs

8. getCITED
9. Genamics JournalSeek

10. Zeitschriftendatenbank (ZDB)
11. J-Gate
12. SHERPA/RoMEO

13. Dayang Journal System
14. Public Knowledge Project

15. BIUM (Bibliothèque interuniversitaire de medecine et d'odontologie)
16. NewJour
17. ArticleReach Direct

18. Link+

Also, some universities and organizations list our journal in their online libraries:

1. Geneva Foundation for Medical Education and Research
2. BASE (Bielefeld Academic Search Engine)

3. River Campus Libraries (Univ. of Rochester)
4. Tulips (University of Tsukuba Library))

5. Showa University Library
6. Keio University (Shinamomachi Media Center)
7. University of Pennsylvania

8. University of Modena and Reggio Emilia
9. Tel Aviv University, Gitter-Smolarz Library of Life Sciences and Medicine

10. National Autonomous University of Mexico, Genomic Sciences Center, Institute of
Biotechnology

11. Saint Petersburg State University

12. University of Puerto Rico
13. Vrije Universiteit Brussel

14. Queensland University of Technology
15. University of Florida
16. John Brown University

17. Université Paris-Descartes
18. University of Regensburg

19. Michigan State University
20. University of Colorado Boulder
21. University of Glasgow

22. Washington University in Saint Louis
23. Wayne State University

24. California State University, Long Beach
25. Brown University, Providence, Rhode Island

http://wokinfo.com/media/pdf/S024651_Flyer.pdf

26. The University of Honk Kong
27. University of Nevada, Reno
28. Ludwig-Maximilians-Universität München

29. Dowling College, New York State
30. Colgate University, New York State

http://library.colgate.edu/record=b3185340*eng

TAB LE OF CONTEN TS

1. Automatic Anthropometric System Development Using Machine Learning 5

Long The Nguyen, Huong Thu Nguyen

2. The Technological Advent and Dynamics of the Network Society. The "Middle -Aged

Approach" 16

Elena-Mădălina Vătămănescu, Elena-Alexandra Gorgos, Andreia-Gabriela Andrei, Vlad-Andrei

Alexandru

3. A Synoptic of Software Implementation for Shift Registers Based on 16
th

Degree Primitive

Polynomials 31

Mirella Amelia Mioc

4. Micro Expression Recognition Using the Eulerian Video Magnification Method 43

Elham Zarezadeh, Mehdi Rezaeian

5. The Ambivalence of Strengths and Weaknesses of E-Learning Educational Services 55

Venera-Mihaela Cojocariu, Iuliana Lazar, Gabriel Lazar

6. New Computer Assisted Diagnostic to Detect Alzheime r Disease 75
Ben Rabeh Amira, Benzarti Faouzi, Amiri Hamid, Mouna Ben Djebara

7. Participative Teaching with Mobile Devices and Social Networks for K -12 Children 94

Livia Ştefan, Dragoş Gheorghiu

8. Prediction of Thyroid Disease Using Data Mining Techniques 115

Irina Ioniţă, Liviu Ioniţă

9. An Efficient Combined Meta-Heuristic Algorithm for Solving the Traveling Salesman

Proble m 125

Majid Yousefikhoshbakht, Azam Dolatnejad

10. A Repeated Signal Difference for Recognising Patterns 139

Kieran Greer

11. An Energy-Saving Concept of the Smart B uilding Power Grid with Separated Lines for

Standby Devices 148

Dmytro Zubov

Abstracts 157

Instructions for authors 162