Home » STEM

Category Archives: STEM

Calendar

April 2018
M T W T F S S
« Mar    
 1
2345678
9101112131415
16171819202122
23242526272829
30  

Read these articles

  • BRAIN: Integrating MOOCs in Embedded Systems Blended Courses
    The Massive Open Online Course (MOOC) phenomenon has been growing in popularity and importance in the last decade, receiving valuable recognition from renowned universities from all over the world. MOOC can be simply defined as …
  • BRAND: A New Perspective on Corporate Social ResponsabilityBRAND: A New Perspective on Corporate Social Responsability
    This is the new BRAND: Broad Research in Accounting, Negotiation, and Distribution. The aim of the journal is to make an agora of different experts in economics, social and political sciences. We look for articles …
  • BRAIN: Artificial Intelligence as a Decision-making Tool in Planning the Research
    Because of their ability to reproduce the biological neural networks, ANNs (Artificial neural networks) have found uncountable applications to a wide range of disciplines. Simina Maris, Titus Slavici, Petre Nenu and Liliana Baciu will present …
  • BRAIN: Team Management Styles within the Present Social and Economic ContextBRAIN: Team Management Styles within the Present Social and Economic Context
    Organizational performance is given by the efficiency of the employees and how well they work as a team. The paper “Team Management Styles within the Present Social and Economic Context”, written by Costin Dămășaru, Colonescu …
  • SMART 2016 – Scientific Methods in Academic Research and TeachingSMART 2016 – Scientific Methods in Academic Research and Teaching
    Timișoara, Romania, November 17-20, 2016 Venue The sessions will be held in the amphitheatres of the Central Library of the University Politehnica of Timisoara, Bul. V. Parvan No. 2B, Timisoara – http://www.upt.ro/Informatii_library-of-upt_409_en.html. Programme The conference …
  • LiBRI: When Apologies Are Not Sincere ApologiesLiBRI: When Apologies Are Not Sincere Apologies
    PhD Ahmad Kareem Salem Al-Wuhaili will present in the latest volume of the LiBRI journal an article about the duality of political apologies, aiming to reveal the fact that important political faces apologise without meaning …
  • LiBRI: From Passion to Cynism in Peter Shaffer’s EquusLiBRI: From Passion to Cynism in Peter Shaffer’s Equus
    The present paper plans to offer a diagram of Dixon’s From Passions to Emotions: The Creation of a Secular Psychological Category and Pugmire’s Sound Sentiments: Integrity in the Emotions, underlining the chronicled development and drop …
  • LiBRI: On Studying Teacher’s Self EsteemLiBRI: On Studying Teacher’s Self Esteem
    Baghli Asmaa is bringing to light a new discussion in LiBRI journal: On Studying Teacher’s Self Esteem Based on Revised Janis Scale Application. An actual and controversial research that brings out some intensely sought answers …
  • BRAND: Symbolic Relationships in AdvertisementsBRAND: Symbolic Relationships in Advertisements
    When talking about advertisements, one would certainly link them to the word “symbol”, as the advertisements prepare for the products that they recommend a rich symbolic life. Since the products are different, the symbolic life should also …
  • LiBRI: Kant and Coleridge on the Issue of MoralityLiBRI: Kant and Coleridge on the Issue of Morality
    LiBRI has a very interesting article written by Nicolae-Andrei Popa. He is giving some insight on the Issue of Morality from the point of view of Kant and Coleridge. This paper seeks to contrast Kant’s …
  • BRAIN: Evaluation of Readiness for Distance Education of Students in European  UniversitiesBRAIN: Evaluation of Readiness for Distance Education of Students in European Universities
    Nowadays, learning is not anymore a passive process. It has become more dynamic and it has begun to use another medium than the written word or the exercise book. In the article titled Evaluation of …
  • BRAIN: Sentiment Analysis on Embedded Systems Blended CoursesBRAIN: Sentiment Analysis on Embedded Systems Blended Courses
    The paper written by Răzvan Bogdan from the Department of Computers and Information Technology, Politehnica University of Timisoara, includes a presentation of a modality of integrating Embedded Systems Massive Open Online Courses (MOOCs) into blended …

Categories

Emotion Extractions from Facial Expressions by Using Artificial Intelligence Techniques

We all know what emotions are and how they can influence someone’s decisions. In many fields, emotions play a big role and almost every time they can be seen on someone’s face. It is difficult to read the emotions on somebody’s face when you actually concentrate more on what the person is saying. Not everyone can be a multi-tasking master and pay attention to the body language as well (which by the way, sometimes shows the true feelings of a person). In marketing for example, we can see very clearly the attitude that a customer has over a product just by looking at his face. Let us all agree, life would be way easier if we would be always aware of what a person is truly feeling.

Taking in account all that, researchers Hakan Boz and Utku Kose conducted a study and wrote an article called ’’Emotion Extractions from Facial Expressions by Using Artificial Intelligence Techniques’’. Nowadays, in an era where technology becomes more and more dominant in each and every field, these researchers developed a system that is actually able to identify the emotion of a person based on his facial expression. In detail, the system considered a Cascade Feedforward Artificial Neural Network model trained by a recent optimization algorithm called as Vortex Optimization Algorithm.

The main objective is generally finding the points determining different parts of a face. After determining the related parts of a face, it becomes easier to have idea about i.e. facial expression. On the other hand, it is also important that different genders, different races and even changing sizes of a head – face can affect the way of detecting facial expression. So, it has always been important, especially for researchers working on detecting facial expressions by intelligent systems, to use appropriate types of data. The researchers Boz and Kose applied 3 sets of data, the first set containing 490 photos with genders, and adjusted for 7 emotions, the second set including 810 photos with genders, races, and adjusted for 7 emotions and the third set (the authors’ choices) 100 photos chosen randomly and adjusted for 7 emotions.

 Different data sets for the application of emotion extraction from facial expressions
Different data sets for the application of emotion extraction from facial expressions

In order to train the system, the researchers used Microsoft Kinect 3D infrastructure to gather 3D face points. Microsoft Kinect 3D is a popular system of both hardware and software solutions for effective recognition processes from photos or videos. The results had been positive and the system was able to extract the emotions from different photographs. They used the Vortex Optimization Algorithm. This is an intelligent, Swarm Intelligence based algorithm, which was developed by Kose and Arslan by inspiring from dynamics of vortices in the nature. In detail, the algorithm uses some role-based and evolutionary mechanisms to achieve the optimization solution processes.

In conclusion, the researchers succeeded in developing a system that is effective enough to extract different emotions from photos related to individuals with different gender and even different race. We are all sure that this is the future of technology and soon enough, emotion reading won’t be a secret for the humankind anymore.

Ecaterina Filimon

Related Posts

  • 40
    Technology has become more than a phenomenon used for innovation, it is now a science put in the service of making human life easier. If in the past, taking a picture of yourself required a voluminous camera with an obscure chamber, nowadays we have our cameras to ourselves for they are incorporated in our gadgets. Therefore, we take pictures of everything we see – recording reality is just one swipe away and ready in the blink of an eye. However, sometimes is difficult to skim through thousands of photos in order to find a specific one. Nabil M. Hewahi and…
    Tags: networks, neural, photos, based, recognition, artificial, intelligence
  • 39
    The article written by Ahmet Demir from Harahalli Vocational School, Usak University, Ușak, Turkey and Utku Kose from Computer Sciences Application and Research Center, Usak University, Ușak, Turkey is a research which takes into account the importance of optimization and of solving its problems. They propose intelligent optimization techniques based on Artificial Intelligence in order to use them for optimization problems. So that they can provide a comparative study on the employment of classical optimization solutions and Artificial Intelligence solutions, two optimization algorithms are proposed: Vortex Optimization Algorithm (VOA) and Cognitive Development Optimization Algorithm (CoDOA). Optimization is defined as choosing…
    Tags: optimization, algorithm, vortex, artificial, intelligence
  • 29
    Because of their ability to reproduce the biological neural networks, ANNs (Artificial neural networks) have found uncountable applications to a wide range of disciplines. Simina Maris, Titus Slavici, Petre Nenu and Liliana Baciu will present in the latest volume of BRAIN journal an article about the usage of artificial intelligence, especially artificial neural networks (ANNs), in the development of an efficient research plan for studying the quality of finite products, in particular wood briquettes obtained from various biomass mixtures. Their work is a response to the needs expressed by a private company (SC Andrei Slavici SRL) searching for innovation in…
    Tags: artificial, intelligence, networks, neural, data, set
  • 23
    In the field of computer vision and pattern recognition, face orientation recognition stands as a significant topic. In the paper A Robust Approach of Facial Orientation Recognition from Facial Features, the authors Stefan Andrei, Kishor Datta Gupta, Md Manjurul Ahsan and Kazi Md. Rokibul Alam introduce us to an image mapping technique for face analysis. The methodology of the study consists of two main phases: Face Feature Extraction and creating the graph image, and Matching Graph image with stored images. The Face Feature Extraction presents four steps that include Face Detection, Feature Extraction, Obtaining Feature Data and Creating image with…
    Tags: face, facial, data, recognition

BRAIN: Sentiment Analysis on Embedded Systems Blended Courses

The paper written by Răzvan Bogdan from the Department of Computers and Information Technology, Politehnica University of Timisoara, includes a presentation of a modality of integrating Embedded Systems Massive Open Online Courses (MOOCs) into blended courses. More than that, it also provides an evaluation of this approach: the sentiment analysis technique.

Twitter sentiment analysis results
Twitter sentiment analysis results

Starting with the explanation of MOOCs, the author insists on one type of courses which is still underrepresented in the field of blended courses – that of embedded systems. Consequently, we can understand that the aim of this paper is to understand, with the help of sentiment analysis, the way in which students react to blending embedded systems MOOCs into embedded system courses. We also find out that the blending variant is applied to Embedded Systems course at “Politehnica” University of Timisoara in Romania, third year of study.

(more…)

Related Posts

  • 54
    The Massive Open Online Course (MOOC) phenomenon has been growing in popularity and importance in the last decade, receiving valuable recognition from renowned universities from all over the world. MOOC can be simply defined as an online course aimed at unlimited participation and open access via the web. In the latest issue of the BRAIN Journal, Răzvan Bogdan’s paper approaches a modality of integrating MOOCs into embedded systems higher education. The academic field of Embedded Systems aims to enhance student’s understanding through various methods, however students find the concepts as being very monotonous and tend to avoid building practical solutions.…
    Tags: embedded, students, systems, courses, moocs, course, mooc, methods, paper, author
  • 36
    Timișoara, Romania, November 17-20, 2016 Venue The sessions will be held in the amphitheatres of the Central Library of the University Politehnica of Timisoara, Bul. V. Parvan No. 2B, Timisoara - http://www.upt.ro/Informatii_library-of-upt_409_en.html. Programme The conference program is subject to change. Tuesday, Nov. 1, 2016 Extended deadline: Nov. 6, 2016 Nov. 6: abstract submission and conference registration (including payment) The final papers should be sent after the day of the conference (by December 15, 2016) Thursday, Nov. 17, 2016: Arrival of participants Friday, Nov. 18, 2016 09:00-09.10: Welcome Talks 09:10-09.50: Keynote speaker Dr. Maria Perifanou (University of Macedonia, CONTA Lab, Greece,…
    Tags: university, timisoara, politehnica
  • 25
    SMART 2017 - Scientific Methods in Academic Research and Teaching is an international conference, which will be held in Timișoara, Romania, between September 8 and September 9, 2017. This year, the conference will focus on three major themes: artificial intelligence neuroscience cognitive sciences All papers will be published in BRAIN journal, indexed by Thomson-Reuters, in Web of Science. This year, the SMART conference will be held together with the final conference of the NOVAMOOC project: Development and innovative implementation of MOOCs in Higher Education. NOVAMOOC is a project funded by CNCS – UEFISCDI, Human Resources Programme *(Project number: PN-II-RU-TE-2014-4-2040, Contract number: 285 / 01.10.2015, Period: October…
    Tags: university, timisoara
  • 22
    SMART 2017 - Scientific Methods in Academic Research and Teaching is an international conference, which will be held in Timișoara, Romania, between September 8 and September 9, 2017. This year, the conference will focus on three major themes: artificial intelligence neuroscience cognitive sciences All papers will be published in BRAIN journal, indexed by Thomson-Reuters, in Web of Science. This year, the SMART conference will be held together with the final conference of the NOVAMOOC project: Development and innovative implementation of MOOCs in Higher Education. NOVAMOOC is a project funded by CNCS – UEFISCDI, Human Resources Programme *(Project number: PN-II-RU-TE-2014-4-2040, Contract number: 285 / 01.10.2015, Period: October…
    Tags: university, timisoara

BRAIN: Solving Optimization Problem via Vortex Optimization Algorithm and Cognitive Development Optimization Algorithm

The article written by Ahmet Demir from Harahalli Vocational School, Usak University, Ușak, Turkey and Utku Kose from Computer Sciences Application and Research Center, Usak University, Ușak, Turkey is a research which takes into account the importance of optimization and of solving its problems. They propose intelligent optimization techniques based on Artificial Intelligence in order to use them for optimization problems. So that they can provide a comparative study on the employment of classical optimization solutions and Artificial Intelligence solutions, two optimization algorithms are proposed: Vortex Optimization Algorithm (VOA) and Cognitive Development Optimization Algorithm (CoDOA).

Flow chart of the VOA
Flow chart of the VOA

Optimization is defined as choosing the best set of alternatives for a certain thing, but also taking some rules into consideration. It is not important just in science, but in real life, too. A lot of fields in our life function now according to different applications which use optimization. But things do not stop here. Optimization also brings certain problems with it, as it is constantly changing. Consequently, different advanced optimization solutions have been introduced in time.

(more…)

Related Posts

  • 48
    Starting with 2010, we edit and publish 3 academic journals for scholars around the world. These journals are indexed by various international  indexing services, like Web of Science (Clarivate Analytics / Thomson-Reuters). EBSCO, DOAJ, Google Scholar, CiteSeerX etc. Our journals are interdisciplinary and they cover three main domains of science: BRAIN: Broad Research in Artificial Intelligence and Neuroscience, ISSN: 2067-3957, E-ISSN: (1-4 issues per year, English) The aim of this journal is to create links between researchers from apparently different scientific fields, such as Computer Science and Neurology. In fact, there are a lot of topics such as Artificial Intelligence, Cognitive…
    Tags: science, intelligence, artificial, optimization, computer
  • 40
    The aim of this journal is to create links between researchers from apparently different scientific fields, such as Computer Science and Neurology. In fact, there are a lot of topics such as Artificial Intelligence, Cognitive Sciences and Neurosciences that can intersect in the study of the brain and its intelligent functions. Our journal contains (in section BRAINovations and BRAINStorming) peer review articles. These articles should be original unpublished articles of the authors. The peer review process is a blind one. The reviewers are well recognized scientists who are part of our scientific board, and independent reviewers. Some innovative young researchers…
    Tags: intelligence, artificial, computer, science
  • 39
    We all know what emotions are and how they can influence someone’s decisions. In many fields, emotions play a big role and almost every time they can be seen on someone’s face. It is difficult to read the emotions on somebody’s face when you actually concentrate more on what the person is saying. Not everyone can be a multi-tasking master and pay attention to the body language as well (which by the way, sometimes shows the true feelings of a person). In marketing for example, we can see very clearly the attitude that a customer has over a product just…
    Tags: algorithm, optimization, intelligence, artificial, vortex
  • 28
    Social Media in Academia: Research and Teaching provides relevant theoretical frameworks, and the latest research on social media and its challenges in the educational and political context. Our conference is essential for professionals aiming to improve their understanding of social media at different levels of education and in civic/social/political engagement, as well as researchers in the fields of e-learning, educational science, political science, new media, information and communication sciences, and much more. Details about SMART 2015 Keynote speakers Topics of the conference Committees Deadlines and instructions for authors Fee and registration Location of SMART 2015 Participants and Schedule This year, our…
    Tags: science, artificial, intelligence

BRAIN: The Role of the Conceptual Invariants Regarding the Prevention of the Software Artefacts’ Obsolescence

Răzvan Bocu and Dorin Bocu from the Department of Mathematics and Computer Science, Transilvania University of Brașov, Romania, wrote a paper on the role of the conceptual invariats concerning the prevention of the artefacts’ obscolescence, emphasizing the software engineering. The aim is to understand the invariants’ role considering the continuous qualitative progress of the human artefacts, making a connection with software systems engineering. Approaching the artefacts’ obscolence is possible only through changes. They generate discomfort for other artefacts and the amplification of this discomfort beyond a certain tolerance may be called obsolescence.

Structure and behaviour during the specification of an artefact
Structure and behaviour during the specification of an artefact

There are works which underline the importance of the concept of structure during the modeling process of the systemic artefacts and the importance of the interface considering the capability of an artefact to cooperate. The structure (S) and the interface (I) are invariants and they are featured by certain stability (ST). By using these terms, the researchers want to explain which role the stability of these invariants plays regarding the obsolescence of the software systems.

(more…)

Related Posts

  • 31
    Sebastian Fuicu, Mircea Popa, Dalibor Dobrilovic, Marius Marcu and Razvan Bogdan offer a paper named "Developing Distance Learning Environments in the Context of Cross-Border Cooperation" which consists of a collaboration between Politehnica University of Timisoara, Romania and the Technical Faculty "Mihajlo Pupin" of Zrenjanin, Serbia. This paper comes up with a low maintenance cooperation model based on a web cast system that gives both countries the opportunity to access one another's educational material, which is very helpful for pupils and students. Developing different programs and techniques to achieve the best results of distance learning has become a very important point…
    Tags: software, e-learning

BRAIN: Auto-generative Learning Objects in Online Assessment of Data Structures Disciplines

Nowadays, the IT industry is in a human resources crisis. The students tend to use their laptops and phones more often than in the last decades. The tutors are more and more loaded with teaching, research and administrative tasks. Consequently, the universities should take into account the use of technologies like LMSs (Learning Managements Systems), MOOCs (Massive Open Online Courses), GLOs (Generative Learning Objects) or AGLOs (Auto-Generative Learning Objects). This paper, written by Ciprian-Bogdan Chirila from Politehnica University of Timisoara, focuses on computer science disciplines (data structures and algorithms) and shows the way in which a tutor can build several auto-generative learning objects in order to assess the knowledge of a class of students.

AGLO-online-assessment-approach
The AGLO online assessment approach

Section 2 of the paper presents related works in the area of learning objects. We can find works which present a generative model for teaching computer science disciplines using Lego robots, principles for designing e-learning tools dedicated to the local automotive andustry, a similar model to the AGLO approach controlled by parameters but enhanced with dynamic learning and evaluation functionalities and so on. We discover that there are a lot of original model which can be used in the area of learning objects.

(more…)

Related Posts

  • 29
    Sebastian Fuicu, Mircea Popa, Dalibor Dobrilovic, Marius Marcu and Razvan Bogdan offer a paper named "Developing Distance Learning Environments in the Context of Cross-Border Cooperation" which consists of a collaboration between Politehnica University of Timisoara, Romania and the Technical Faculty "Mihajlo Pupin" of Zrenjanin, Serbia. This paper comes up with a low maintenance cooperation model based on a web cast system that gives both countries the opportunity to access one another's educational material, which is very helpful for pupils and students. Developing different programs and techniques to achieve the best results of distance learning has become a very important point…
    Tags: learning, students, paper, order, area, e-learning
  • 29
    Nowadays, learning is not anymore a passive process. It has become more dynamic and it has begun to use another medium than the written word or the exercise book. In the article titled Evaluation of Readiness for Distance Education of Students in European Universities, professors Diana Vasilevska, Baiba Rivza and Răzvan Bogdan present the results of an evaluation process concerning one of the most spread and new educational movements – distant education. The evaluation included students from different states of Europe as Poland, Serbia, Lithuania, Latvia, Belarus and Romania. The aim of this demarche was to see if all the…
    Tags: students, evaluation, e-learning, learning