Enhancing Mobile Cloud Computing Security Using Steganography

Cloud computing is an emerging and popular method of accessing shared and dynamically configurable resources via the computer network on demand. Cloud computing is excessively used by mobile applications to offload data over the network to the cloud. There are some security and privacy concerns using both mobile devices to offload data to the facilities provided by the cloud providers. One of the critical threats facing cloud users is the unauthorized access by the insiders (cloud administrators) or the justification of location where the cloud providers operating. Although, there exist variety of security mechanisms to prevent unauthorized access by unauthorized user by the cloud administration, but there is no security provision to prevent unauthorized access by the cloud administrators to the client data on the cloud computing. In this paper, we demonstrate how steganography, which is a secrecy method to hide information, can be used to enhance the security and privacy of data (images) maintained on the cloud by mobile applications. Our proposed model works with a key, which is embedded in the image along with the data, to provide an additional layer of security, namely, confidentiality of data. The practicality of the proposed method is represented via a simple case study.

A Survey on Software Cost Estimation Techniques

The ability to accurately estimate the cost needed to complete a specific project has been a challenge over the past decades. For a successful software project, accurate prediction of the cost, time and effort is a very much essential task. This paper presents a systematic review of different models used for software cost estimation which includes algorithmic methods, non-algorithmic methods and learning-oriented methods. The models considered in this review include both the traditional and the recent approaches for software cost estimation. The main objective of this paper is to provide an overview of software cost estimation models and summarize their strengths, weakness, accuracy, amount of data needed, and validation techniques used. Our findings show, in general, neural network based models outperforms other cost estimation techniques. However, no one technique fits every problem and we recommend practitioners to search for the model that best fit their needs.

Toward Quality Attribute Driven Approach to Software Architectural Design

It has been well-documented that the software architecture of any system plays a critical role in success or failure of software intensive systems. In this paper, a method has been proposed to evaluate the software architecture’s fitness with respect to key quality attributes for a web-based system. To the end, a comparative analysis based on quality attributes scenarios and tactics is carried out to select an optimal software architecture that meets the system level requirements of a web-based system, namely, Student and Course Evaluation System (SCES). The comparative study was driven by study of quality attributes and tactics with the selected architectures to select the optimal one.

Mapping AADL to Petri Net Tool-Sets Using PNML Framework

Architecture Analysis and Design Language (AADL) has been utilized to specify and verify nonfunctional properties of Real-Time Embedded Systems (RTES) used in critical application systems. Examples of such critical application systems include medical devices, nuclear power plants, aerospace, financial, etc. Using AADL, an engineer is enable to analyze the quality of a system. For example, a developer can perform performance analysis such as end-to-end flow analysis to guarantee that system components have the required resources to meet the timing requirements relevant to their communications. The critical issue related to developing and deploying safety critical systems is how to validate the expected level of quality (e.g., safety, performance, security) and functionalities (capabilities) at design level. Currently, the core AADL is extensively applied to analyze and verify quality of RTES embed in the safety critical applications. The notation lacks the formal semantics needed to reason about the logical properties (e.g., deadlock, livelock, etc.) and capabilities of safety critical systems. The objective of this research is to augment AADL with exiting formal semantics and supporting tools in a manner that these properties can be automatically verified. Toward this goal, we exploit Petri Net Markup Language (PNML), which is a standard acting as the intermediate language between different classes of Petri Nets. Using PNML, we interface AADL with different classes of Petri nets, which support different types of tools and reasoning. The justification for using PNML is that the framework provides a context in which interoperability and exchangeability among different models of a system specified by different types of Petri nets is possible. The contributions of our work include a set of mappings and mapping rules between AADL and PNML. To show the feasibility of our approach, a fragment of RT-Embedded system, namely, Cruise Control System has been used.

Toward the Design and Implementation of Traceability Engineering Tool Support

Requirements of a system keep on changing based on the need of stakeholders or the system developers, making requirement engineering an important aspect in software development. This develops a need for appropriate requirement change management. The importance of requirements traceability is defining relationships between the requirements and artefacts extracted by the stakeholder during the software development life-cycle and gives vital information to encourage software understanding. In this paper, we have concentrated on developing a tool for requirement traceability that can be used to extend the requirement elicitation and identification of system-wide qualities using the notion of quality attribute scenarios to capture the non-functional requirements. It allows us to link the functional and non-functional requirements of the system based on the quality attribute scenarios template proposed by the Carnegie Mellon Software Engineering Institute (SEI). Apart from this, the paper focuses on tracing the functional and non-functional requirements of the system using the concept of requirement traceability matrix.

Applied Machine Learning Methods for Detecting Fractured Zones by Using Petrophysical Logs

In the last decade, a few valuable types of research have been conducted to discriminate fractured zones from non-fractured ones. In this paper, petrophysical and image logs of eight wells were utilized to detect fractured zones. Decision tree, random forest, support vector machine, and deep learning were four classifiers applied over petrophysical logs and image logs for both training and testing. The output of classifiers was fused by ordered weighted averaging data fusion to achieve more reliable, accurate, and general results. Accuracy of close to 99% has been achieved. This study reports a significant improvement compared to the existing work that has an accuracy of close to 80%.

A Systematic Review Towards Big Data Analytics in Social Media

The recent advancement in internet 2.0 creates a scope to connect people worldwide using society 2.0 and web 2.0 technologies.This new era allows the consumer to directly connect with other individuals,business corporations,and the government.People are open to sharing opinions,views,and ideas on any topic in different formats out loud.This creates the opportunity to make the"Big Social Data"handy by implementing machine learning approaches and social data analytics.This study offers an overview of recent works in social media,data science,and machine learning to gain a wide perspective on social media big data analytics.We explain why social media data are significant elements of the improved data-driven decision-making process.We propose and build the"Sunflower Model of Big Data"to define big data and bring it up to date with technology by combining 5 V’s and 10 Bigs.We discover the top ten social data analytics to work in the domain of social media platforms.A comprehensive list of relevant statistical/machine learning methods to implement each of these big data analytics is discussed in this work."Text Analytics"is the most used analytics in social data analysis to date.We create a taxonomy on social media analytics to meet the need and provide a clear understanding.Tools,techniques,and supporting data type are also discussed in this research work.As a result,researchers will have an easier time deciding which social data analytics would best suit their needs.