Data Mining Practical Machine Learning Tools and Techniques

The power of feedback.

Autonomous underwater vehicles (AUVs) are submersible underwater vehicles controlled by onboard computers. AUV formation is a cooperative control which focuses on controlling multiple AUVs to move in a group while executing tasks. In contrast to a single AUV, multi-AUV formation represents higher efficiency and better stability for many applications, such as oil and gas industries, hydrographic surveys, and military missions, etc. To achieve better formation, there are several key factors, including AUV performance, formation control, and communication capability. However, most studies in the field of AUV formation mainly focus on formation control methods. We observe that the research of communication capability and AUV performance of multiple AUV formation is still in an early stage. It is beneficial to researchers to present a comprehensive survey of the state of the art of AUV formation research and development. In this paper, we study AUV, formation control, and underwater acoustic communication capability in detail. We propose a classification framework with three dimensions, including AUV performance, formation control, and communication capability. This framework provides a comprehensive classification method for future AUV formation research. It also can be used to compare different methods and help engineers choose suitable formation methods for various applications. Moreover, our survey discusses formation architecture with communication constraints and we identify some common misconceptions and questionable research for formation control related to communication.

A Survey of Autonomous Underwater Vehicle Formation: Performance, Formation Control, and Communication Capability

In underwater sensor network(UWSN) research, it is highly expensive to deploy a complete test bed involving complex network structure and data links to validate a network protocol or an algorithm. This practical challenge points to the need of a simulation environment which can reproduce the actual underwater scenario without the loss of generality. Since so many simulators are proposed for UWSN simulation, the selection of an appropriate tool based on the research requirement is very important in validation and interpretation of results. This paper provides an in-depth survey of different simulation tools available for UWSN simulation. We compared the features offered by each tool, pre-requirements, and provide the run time experiences of some of the open source tools. We conducted simulation of sample scenarios in some of the open source tools and compared the results. This survey helps a researcher to identify a simulation tool satisfying their specific research requirements.

/pdf/simulation-tools-for-underwater-sensor-networks-a-survey-3jdiozune8.pdf

Simulation Tools for Underwater Sensor Networks: A Survey

This paper proposes a novel scheme for the leaker identification that deals with the dynamic scenario by handling the requests of the users in an online custom. A distribution strategy is introduced having less risk associated with exposing the data and furthermore improves the likelihood of identifying the leaker when the information is revealed by the malicious user. The observed results signify an improvement of up to 41%, 368%, and 318% for average probability, average success rate, and detection rate respectively compared to the prior work. Also, the proposed framework significantly minimizes the possibility of data leakage up to 88% and synchronously achieves a 100% efficacy rate.

Online information leaker identification scheme for secure data sharing

In this research article of modeling Underwater Wireless Sensor Network Simulators, we provide a comprehensive overview of the various currently available simulators used in UWSN modeling. In this work, we compare their working environment, software platform, simulation language, key features, limitations and corresponding applications. Based on extensive experimentation and performance analysis, we provide their efficiency for specific applications. We have also provided guidelines for developing protocols in different layers of the protocol stack, and finally these parameters are also compared and tabulated. This analysis is significant for researchers and designers to find the right simulator for their research activities. Keywords—Underwater Wireless Sensor networks (UWSN), SUNSET, NS2, OPNET, WOSS, DESERT, RECORDS, AquaSim, AquaNet Mate.

Modeling UWSN Simulators – A Taxonomy

Sharing multimedia information through the means of internet has increased many folds in this digital world. Information needs to be send across various secure channel as it contains sensitive data such as bank account details, medical reports or any financial documents. Due to the importance of information sharing, security is the most important objective that needs to be addressed while sharing this sensitive information. In order to share the information securely, one such way is visual secret sharing or visual cryptography. In this paper, introduced Enhanced Semantic Visual Secret Sharing (ESVSS) Scheme that transmits a gray-scale secret image to the receiver using two color cover images. At the receiver end, the secret image is reconstructed by digitally stacking the shares together. The result analysis shows that the ESVSS achieves security and improves the quality of the reconstructed image. The quality is measured by Peak Signal to Noise Ratio (PSNR) up to +39 dB and Mean Square Error is reduced to 6. The Universal Image Quality Index (UIQI) results are recorded up to 90% for the reconstructed image with minimal computational complexity.

Enhanced semantic visual secret sharing scheme for the secure image communication

Fake news or fabricated news, refers to false information published under the guise of being authentic news, often to influence political views. Fabricated news articles are a threat to people’s trust in the government and in effect, one of the biggest threats that modern-day democracies are facing. As the menace of fake news is growing with each passing day, so is the research community getting more actively involved in curbing this issue. This paper reviews the current progress of the advancements done to solve the issue. The paper also presents various ensemble techniques to perform the binary classification of news articles. Additionally, the paper focuses on sources of articles to widen misclassification tolerance and make more accurate predictions. Evaluation metrics such as accuracy score, precision, recall, f-1 score have been used to make comparison among various models. The best performing model has been an ensemble of Decision Tree, Logistic Regression, Bagging Classifier used with a hard-voting ensemble technique, which gives the accuracy of over 88%.

An Ensemble Technique to Detect Fabricated News Article Using Machine Learning and Natural Language Processing Techniques

Knowledge management establishes connections among Information and Communication Technology (ICT), education, leadership, organizational behavior and strategy. The goal of this research is to investigate whether there is a significant difference between multiple intelligences and learning behavior of engineering students in the subject named Theory of Computation (TOC). This study intended to reveal how students differ in the ways they learn. Although, all the students are inclined to learn, however their way of learning is different from person to person as well in absorbing new information. Considering student's multiple intelligences this study was aimed at summarizing the ways in which ICT is used, and how it creates new learning opportunities. This study examines the impact of Multiple Intelligences on knowledge sharing and knowledge acquisition behavior.

Use of multiple intelligences and instructional technologies in learning theory of computation: An experimental case study

Performance evaluation plays a fundamental role in the desi gn of modern underwater wireless communication systems, which are growing rapidly. In this system, performance eval uation of systems plays a fundamental role in determining th e effectiveness of the system. Analysis of backlog and delay in any underwate r wireless communication networks becomes a tough task. In p ast few years, the stochastic growth of modern networks resulted in complexity of analysing the algorithms and application. Si nce traditional mathematical modeling theories such as queuing theory, eff ective bandwidth, and deterministic networks calculus are not applicable to analyze the Quality of Service (QoS) for the present day pack et switched multimedia networks due to their inherently ran dom behavior. To analyze the present day networks, non-deterministic net work calculus is much needed. Stochastic network calculus e merges as an appropriate mathematical tool for modeling and calculatin g he performance of wireless network and wired networks. Wh ile research in stochastic network calculus is in early days, it is still g aining much attention in the research community for analyzi ng any wireless communication networks. In this research article, the auth ors ave analyzed and created a mathematical model for under water wireless communication channel. The channel is subjected to Rician f ading based on SNC that obtains Stochastic Arrival Curve and Stochastic Service Curve, as an extension to the Rayleigh fading. This m odel is adopted for deriving the performance of delay and bac klog bounds in underwater acoustic Rician fading channels using Stocha stic Network Calculus.

Rajeev Sukumaran

Papers

Modeling UWSN Simulators – A Taxonomy

Enhanced semantic visual secret sharing scheme for the secure image communication

An Ensemble Technique to Detect Fabricated News Article Using Machine Learning and Natural Language Processing Techniques

Use of multiple intelligences and instructional technologies in learning theory of computation: An experimental case study

Stochastic Network Calculus for Rician Fading in Underwater Wireless Networks