Volume 17 (2017): Issue 2 (June 2017)

Big Data analytics has been the main focus in all the industries today. It is not overstating that if an enterprise is not using Big Data analytics, it will be a stray and incompetent in their businesses against their Big Data enabled competitors. Big Data analytics enables business to take proactive measure and create a competitive edge in their industry by highlighting the business insights from the past data and trends. The main aim of this review article is to quickly view the cutting-edge and state of art work being done in Big Data analytics area by different industries. Since there is an overwhelming interest from many of the academicians, researchers and practitioners, this review would quickly refresh and emphasize on how Big Data analytics can be adopted with available technologies, frameworks, methods and models to exploit the value of Big Data analytics.

In this article we present a novel linguistically driven evaluation method and apply it to the main approaches of Machine Translation (Rule-based, Phrase-based, Neural) to gain insights into their strengths and weaknesses in much more detail than provided by current evaluation schemes. Translating between two languages requires substantial modelling of knowledge about the two languages, about translation, and about the world. Using English-German IT-domain translation as a case-study, we also enhance the Phrase-based system by exploiting parallel treebanks for syntax-aware phrase extraction and by interfacing with Linked Open Data (LOD) for extracting named entity translations in a post decoding framework.

Data mining on vertically or horizontally partitioned dataset has the overhead of protecting the private data. Perturbation is a technique that protects the revealing of data. This paper proposes a perturbation and anonymization technique that is performed on the vertically partitioned data. A third-party coordinator is used to partition the data recursively in various parties. The parties perturb the data by finding the mean, when the specified threshold level is reached. The perturbation maintains the statistical relationship among attributes.

The increased number of connected devices and Machine-to-Machine (M2M) applications becomes business and technical challenge for network operators. The complexity of connectivity challenge yields for appropriate connectivity management solutions. The explosion of M2M services may result in undesired service interaction. Despite of the considerable progress in service interaction management, there is a lack of knowledge on the kind of interaction in real M2M communication systems. In this paper, a method for service orchestration between M2M applications which add value to basic device connectivity management is proposed. The automatic resolving of service interaction using policies allows service self-configuration and provisioning of adaptive service continuity to end users.

The performance of the interconnection network doesn’t only depend on the topology, but it also depends on the Routing algorithm used. The simplest Routing algorithm for the mesh topology in networks on chip is the XY Routing algorithm. The level based Routing algorithm has been proved to be more efficient than the XY Routing algorithm. In this paper, level based Routing algorithm using the dynamic programming has been proposed. The proposed Routing algorithm proves to be more efficient in the terms of the computation. The proposed Routing algorithm has achieved up to two times bigger speed.

Cloud computing offers scalable services to the user where computing resources are owned by a cloud provider. The resources are offered to clients on pay-per-use basis. However, since multiple clients share the cloud’s resources, they could potentially interfere with each others’ task during peak load instances. The environment changes every instant of time with a new set of job requests demanding resource while another set of jobs relieving another set of resources. A major challenge among the service providers is to maintain a balance without compromising Service Level Agreement (SLA). In case of peak load, when each client strives for a particular resource in minimal time, the resource allocation problem becomes more challenging. The important issue is to fulfil the SLA criterion without delaying the resource allocation.

The paper proposes a n-player game-based Machine learning strategy that would forecast outcome using a priori information available and measure/estimate existing parameters such as utilization and delay in an optimal load-balanced paradigm. The simulation validates the conclusion of the theorem by showing that average delay is low and stays in that range as the number of job requests increase. In future, we shall extend this work to multi-resource, multi-user environment.

The Intelligent Transportation System (ITS) is used as a term for integrating requirements and functionalities towards transportation systems, which in urban environment raises complex exploitation and control problems. Important part of the ITS is the control which has to be applied for traffic flows. The control processes are strongly linked with requirements and targets for optimization of the transportation behavior. The paper applies new optimization formal description of control by bi-level optimization. Except the trivial traffic lights control, the bi-level formalization allows additional traffic characteristics to be defined like maximal/minimal values. The paper defines, solves and provides numerical simulations for minimization of the vehicle queues in front of the traffic lights. Such bi-level optimization problem is applied simultaneously for maximization the traffic flows on arterial and important directions of the urban transportation network. The formal description of the bi-level problem is provided. The results of the bi-level control have been compared with the cases of single optimization of the vehicles queues. The simulation results prove that the bi-level problem gives benefits satisfying an additional goal, which improves additional characteristic of the transport behavior. The bi-level optimization formalism can be used as a tool for implementation of integration of ITS control policies.

The progress of image search engines still proceeds, but there are some challenges yet in complex queries. In this paper, we present a new semantic image search system, which is capable of multiple object retrieval using only visual content of the images. We have used the state-of-the-art image processing methods prior to the search, such as Fisher-vector and C-SVC classifier, in order to semantically classify images containing multiple objects. The results of this offline classification are stored for the latter search task. We have elaborated more search methods for combining the results of binary classifiers of objects in images. Our search methods use confidence values of object classifiers and after the evaluation, the best method is selected for thorough analysis. Our solution is compared with the famous web images search engines (Google, Bing and Flickr), and there is a comparison of their Mean Average Precision (MAP) values. It can be concluded that our system reaches the benchmark; moreover, in most cases our method outperforms the others, especially in the cases of queries with many objects.

It is still very challenging to establish a unified and robust framework to perform accurate and complete crack extraction from images with cluttered background, various morphological differences and even with shadow influence. In this paper, an improved neuron segmentation model with two stages is proposed for crack segmentation. Firstly, a robust crack indicator function is designed based on local directional filtering; it makes up for the traditional function based on hessian matrix, which is resulting in problem of local structure discontinuities. After obtaining the indicator function, the crack detection is performed in an integrated mode; it is incorporating the automated directional region growing without manual intervention by adopting level sets; then efficient and complete crack segmentation is realized by iterative contour evolution. The performance of the proposed model is demonstrated by experiments on three kinds of grouped crack sample images and the quantitative evaluation. We also argue that the proposed model is applicable for biomedical image segmentation.

Traditionally, (k, n) secret image sharing is an approach of breaking down a secret image into n number of shadow images to assign them to n number of users, so that any k or more then k users can bring back the secret image. But in case of less than k, users cannot reveal any partial information about the original image. We have proposed a significant secret image sharing technique based on XOR with arithmetic operations that upgrade the performance of traditional secret image sharing approaches by serving importance to shadow images according to user’s significance. This scheme also conserves the fault tolerance property which plays a vital role in image sharing field.

The paper contributes to the design and implementation of the ultrasonic positioning system based on new multifunctional hardware components, newly released. A moving object coordinates’ determination is described analytically and a matrix equation in respect to unknown coordinates with coefficients, measurement distances, is derived. Stages of data packet processing are formulated, and a pseudo pyramid of measurement distances is built. HX7TR multifunctional ultrasonic devises, transceivers, are used to implement the positioning system. A C# program source code for coordinate determination and 3D visualization is created. The algorithm for moving object coordinate computation, and its program realization as well as HX7TR ultrasonic devises can be used in development of indoor ultrasonic positioning systems embedded in IoT and robotics applications.

This paper presents a study on Predicting Student Performance (PSP) in academic systems. In order to solve the task, we have proposed and investigated different strategies. Specifically, we consider this task as a regression problem and a rating prediction problem in recommender systems. To improve the performance of the former, we proposed the use of additional features based on course-related skills. Moreover, to effectively utilize the outputs of these two strategies, we also proposed a combination of the two methods to enhance the prediction performance. We evaluated the proposed methods on a dataset which was built using the mark data of students in information technology at Vietnam National University, Hanoi (VNU). The experimental results have demonstrated that unlike the PSP in e-Learning systems, the regression-based approach should give better performance than the recommender system-based approach. The integration of the proposed features also helps to enhance the performance of the regression-based systems. Overall, the proposed hybrid method achieved the best RMSE score of 1.668. These promising results are expected to provide students early feedbacks about their (predicted) performance on their future courses, and therefore saving times of students and their tutors in determining which courses are appropriate for students’ ability.

This paper presents an environment which generates tests automatically. It is designed for assistance in the software engineering education and is part of the Virtual Education Space. The environment has two functionalities – generation and assessment of different types of test questions. In the paper, the architecture of the environment is described in detail. The test generation is supported by specialized ontologies, which are served by two intelligent agents known as Questioner Operative and Assessment Operative.