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 the BRAINovations and BRAINStorming sections) peer-reviewed 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 These articles should be original, unpublished articles of the authors.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 also independent reviewers.

Some innovative young researchers from around the world had the idea to edit and publish the BRAIN journal in order to make an agora of interdisciplinary study of the brain. Young scientists and seniors in artificial intelligence, cognitive sciences and neurology fields are expected to publish their original works in our journal.

The contactless automatic anthropometric system is proposed for the reconstruction of the 3D-model of the human body using the conventional smartphone. Our 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.  

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 magnified 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. In 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.

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 synthesis 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 weaknesses 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 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.

This article details a set of participatory pedagogical experiments conducted within a  research grant 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 Danubian 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 were 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 heritage.

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

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 MICALK 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.

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 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.

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 energysaving  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 number 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.