Vol. 22 No. 4/2018

Issue Topic: Image Processing

From a Smart Education Environment to an Eco-School through Fog & Cloud Computing in IoT Context 5
Marian STOICA, Marinela MIRCEA, Bogdan GHILIC-MICU, Cristian Răzvan USCATU
One of the most visible domains of the last decade emerging technological explosion is educa-tion. In this paper we will analyze the educational field seen as an intelligent learning environment, in the context of a modern information and communication technology paradigm: fog & cloud computing. An intelligent educational environment built on the IoT (Internet of Things) ecosystem involves at least two dimensions: conceptual and functional. These aspects will be highlighted in this paper, identifying the intensity of cloud computing relations and fog computing – IoT, as global infrastructure for building an intelligent education environment. In the current economic, social and environmental conditions, developing an intelligent educational frame must take into account multiple aspects. Among them are critical factors, like legal frame, ecological dimension and quality insurance. Any intelligent educational frame must consider the environmental factors and converge towards and ecological structure, an eco-school.
Keywords: Fog & Cloud Computing, Eco-School, Internet of Things, Smart Education, Holistic Approach.

Facial Image Retrieval on Semantic Features Using Adaptive Genetic Algorithm 15
Marwan Ali SHNAN, Taha H. RASSEM
The emergence of larger databases has made image retrieval techniques an essential compo-nent, and has led to the development of more efficient image retrieval systems. Retrieval can be either content or text-based. In this paper, the focus is on the content-based image retrieval from the FGNET database. Input query images are subjected to several processing techniques in the database before computing the squared Euclidean distance (SED) between them. The images with the shortest Euclidean distance are considered as a match and are retrieved. The processing techniques involve the application of the median modified Weiner filter (MMWF), extraction of the low-level features using histogram-oriented gradients (HOG), discrete wavelet transform (DWT), GIST, and Local tetra pattern (LTrP). Finally, the features are selected using Viola-Jones algorithm. In this study, the average PSNR value obtained after applying Wiener filter was 45.29. The performance of the AGA was evaluated based on its precision, F-measure, and recall, and the obtained average values were respectively 0.75, 0.692, and 0.66. The performance matrix of the AGA was compared to those of particle swarm optimization al-gorithm (PSO) and genetic algorithm (GA) and found to perform better; thus, proving its effi-ciency.
Keywords: Euclidean distance, Median modified Weiner filter, Histogram oriented gradients, Discrete wavelet transform, Local tetra pattern, Genetic algorithm, Particle swarm optimization algorithm

Using Face Recognition with Twitter Data for the Study of International Migration 31
Alexandru FLOREA, Monica ROMAN
The level of widely used technology has tremendously increased in recent years, and the inter-net has genuinely reshaped the way we learn, communicate and live. As a result, social data availability, complexity, and diversity steadily grow. In the same time, the computational ma-chine power constantly unlocks opportunities to provide innovative techniques. By leveraging that power in statistics, powerful algorithms, such as neural networks, started to be applied in various fields. Image Processing has been a subject of broad interest and face recognition has been an essential part of this field in recent years. This paper aims to leverage all these re-sources to provide an overview of how social media data can be collected and analyzed using R. The result of this paper is represented by an innovative algorithm able to retrieve and analyze Twitter information. Moreover, this paper also provides a snapshot of the Romanian Twitter users’ demographics and mobility.
Keywords: Internet technology, Image processing, Face recognition, Twitter, Social media Data Collection, International migration

Automated Supply Chain Formation – A Theoretical Framework 47
Florina Livia COVACI
The purpose of this paper is to review the different concepts and approaches regarding auto-mated supply chain formation (SCF) in order to create a theoretical framework and identify gaps in existing research in SCF regarding the complexity of practical implementation in the context of Industry 4.0. The research is conducted through analyzing three perspectives regard-ing the complexity of the SCF process: 1) the existence of a central authority, 2) the mecha-nisms employed for communication between entities in the supply chain, 3) one/multi-unit dimension for the traded goods. A theoretical framework was created and the following gaps and issues were identified in the existing research literature: 1) Parameters used in order to pair-wise suppliers/consumers are limited. 2) The resulted supply chains are assessed mainly using a profit optimization function for the end-consumer. 3) The possible risks associated with participating entities in the supply chain are not considered.
Keywords: Automated Supply Chain Formation, Theoretical framework, Industry 4.0

Cloud Computing – Emerging Technology for Computational Services 61
Dan-Cristian CEARNĂU
The evolution of the Internet, the web development, the complexity of Internet businesses, as well as the volume of data and concurrent application users have determined IT&C specialists to design client/server applications on multiple layers, and on some cases even distributed solutions. The expansion of the Internet Service Providers networks and the accessibility of the Internet services have greatly increased the number of users that are using the Internet. This meant that new markets were opened for building new Internet businesses that rapidly grew in popularity. Because of the scaling issues generated by the large number of new users that are using Internet services, the IT&C specialists have developed solutions to share resources between companies in order to reduce operational costs. By scaling down internal resources and migrating their applications to cloud computing services, companies are cutting-down costs, increasing availability of their applications and increasing their security.
Keywords: Cloud computing, Cloud computing architecture, Cloud computing models, Big data, IoT

Real Time Agile Metrics for Measuring Team Performance 70
Eduard Nicolae BUDACU, Paul POCATILU
In order to track the improvements of agile teams, a system of metrics and indicators is very important to be implemented. Agile Software Development (ASD) promotes working software as the primary way of measuring progress. The current set of metrics are more output oriented rather than using lines of code to estimate productivity. This paper presents the results of a background research in order to identify the most important metrics, indicators, measures and tools software development teams use in relation with agile-based methodologies. The paper also presents a case study based on data gathered in a software outsourcing company. The paper proposes an architecture of an automated system used to provide real-time metrics for measuring agile team performance.
Keywords: Agile Development, Metrics, Indicators, Measurements, Velocity, Lead Time, Cycle Time

ISCED Classification Influence on E-Learning Education Systems 80
Cătălin-Ionut SILVESTRU, Virgil ION, Corina BOTEZ (CONSTANTIN), Vasilica-Cristina ICOCIU
The ISCED classification used in education is the most important step in designing and constructing forecasts and prevision models. The very basis of the classification is applicable both on the formal education and on the non-formal education. While the education process nowadays is conducted in universities, there are many categories of education providers that choose e-learning platforms. To better understand how their trajectory can be correct, the present article sustains the idea that the ISCED classification points e-learning platforms in the right direction. This direction is meant to compress the education idea to basic competencies, skills and learning outcomes that the graduate can acquire during the education process. Using variables collected on the base of the ISCED classification and statistical distributions, we present the e-learning concept in Romania. The article is divided into two main sections. The first section focuses on e-learning platforms and the percentage of the population that used such platforms for education. The second section presents the inclusion of the ISCED classification in e-learning platforms. Using the ISCED classification, we can conclude that people with higher levels of education have a higher chance of using e-learning instruments.
Keywords: E-learning, ISCED 1997, ISCED 2011, Online courses

Network Anomaly Detection by Means of Machine Learning: Random Forest Approach with Apache Spark 89
Hesamaldin HAJIALIAN, Cristian TOMA
Nowadays the network security is a crucial issue and traditional intrusion detection systems are not a sufficient way. Hence the intelligent detection systems should have a major role in network security by taking into consideration to process the network big data and predict the anomalies behavior as fast as possible. In this paper, we implemented a well-known supervised algorithm Random Forest Classifier with Apache Spark on NSL-KDD dataset provided by the University of New Brunswick with the accuracy of 78.69% and 35.2% false negative ratio. Empirical results show this approach is well in order to use for intrusion detection system as well as we seeking the best number of trees to be used on Random Forest Classifier for getting higher accuracy and lower cost for the intrusion detection system.
Keywords: Random Forest, Network Security, Anomaly Detection, NSL-KDD, Apache Spark, Machine Learning, Intrusion Detection Systems (IDS)

The 18th International Conference on Informatics in Economy, IE 2019 99

Publishing Guide for Authors 100

INFOREC Association 102