In recent years, underwater wireless sensor networks (UWSNs) have been widely applied to aquatic and military applications. Network survivability is an essential attribute to be considered in UWSN ...

Certain Investigations on Energy-Efficient Fault Detection and Recovery Management in Underwater Wireless Sensor Networks

Electronic health records (EHRs) are increasingly employed to maintain, store and share varied types of patient data. The data can also be utilized for various research purposes, such as clinical trials or epidemic control strategies. With the increasing cost and scarcity of healthcare services, healthcare organizations feel at ease in outsourcing these services to cloud-based EHRs. That serves as pay-as-you-go (PAYG) “e-health cloud” models to aid the healthcare organizations handling with existing and imminent demands yet restricting their costs. Technologies can host some risks; hence the privacy of information in these systems is of utmost importance. Regardless of its increased effectiveness and growing eagerness in its adoption, not much care is being employed to the privacy issues that might arise. Privacy preservation need to be reviewed about the changing privacy rules and legislations regarding sensitive personal data. Our work aims at answering three major questions: firstly, how privacy models and privacy techniques correlate with each other, secondly, how we can fix the privacy-utility-trade off by using different combinations of privacy models and privacy techniques and lastly, what are the most relevant privacy techniques that can be adapted to achieve privacy of EHR on cloud.

/pdf/privacy-preservation-in-e-health-cloud-taxonomy-privacy-14cxiuzfio.pdf

Privacy preservation in e-health cloud: taxonomy, privacy requirements, feasibility analysis, and opportunities

Energy and security are major challenges in a wireless sensor network, and they work oppositely. As security complexity increases, battery drain will increase. Due to the limited power in wireless sensor networks, options to rely on the security of ordinary protocols embodied in encryption and key management are futile due to the nature of communication between sensors and the ever-changing network topology. Therefore, machine learning algorithms are one of the proposed solutions for providing security services in this type of network by including monitoring and decision intelligence. Machine learning algorithms present additional hurdles in terms of training and the amount of data required for training. This paper provides a convenient reference for wireless sensor network infrastructure and the security challenges it faces. It also discusses the possibility of benefiting from machine learning algorithms by reducing the security costs of wireless sensor networks in several domains; in addition to the challenges and proposed solutions to improving the ability of sensors to identify threats, attacks, risks, and malicious nodes through their ability to learn and self-development using machine learning algorithms. Furthermore, this paper discusses open issues related to adapting machine learning algorithms to the capabilities of sensors in this type of network.

/pdf/machine-learning-for-wireless-sensor-networks-security-an-38gnhtpd.pdf

Machine Learning for Wireless Sensor Networks Security: An Overview of Challenges and Issues

The current study aims to understand as to how tourists use internet to search for information related to eco-tourism. Besides the mediating role of perceived usefulness, this study also attempts t...

Ecotourism related search for information over the internet: a technology acceptance model perspective

Privacy preservation of electronic health records with adversarial attacks identification in hybrid cloud

Sensor devices in wireless sensor networks are vulnerable to faults during their operation in unmonitored and hazardous environments. Though various methods have been proposed by researchers to detect sensor faults, only very few research studies have reported on capturing the dynamics of the inherent states in sensor data during fault occurrence. The continuous density hidden Markov model (CDHMM) is proposed in this research to determine the dynamics of the state transitions due to fault occurrence, while neural networks are utilized to classify the faults based on the state transition probability density generated by the CDHMM. Therefore, this paper focuses on the fault detection and classification using the hybridization of CDHMM and various neural networks (NNs), namely the learning vector quantization, probabilistic neural network, adaptive probabilistic neural network, and radial basis function. The hybrid models of each NN are used for the classification of sensor faults, namely bias, drift, random, and spike. The proposed methods are evaluated using four performance metrics which includes detection accuracy, false positive rate, F1-score, and the Matthews correlation coefficient. The simulation results show that the learning vector quantization NN classifier outperforms the detection accuracy rate when compared to the other classifiers. In addition, an ensemble NN framework based on the hybrid CDHMM classifier is built with majority voting scheme for decision making and classification. The results of the hybrid CDHMM ensemble classifiers clearly indicates the efficacy of the proposed scheme in capturing the dynamics of change of statesm which is the vital aspect in determining rapidly-evolving instant faults that occur in wireless sensor networks.

/pdf/hybrid-continuous-density-hmm-based-ensemble-neural-networks-b1k621210k.pdf

Hybrid Continuous Density Hmm-Based Ensemble Neural Networks for Sensor Fault Detection and Classification in Wireless Sensor Network.

Migration of the healthcare applications to cloud computing needs certain features to be fulfilled for complete user satisfaction. The users quench for satisfaction can be fulfilled by attaining the cloud computing characteristics such as data storage, accessibility, information sharing, interoperability, security, service availability, scalability, resiliency, resource management, and monitoring. The work is a survey on the cloud computing characteristics and its implementation in healthcare applications.

Survey on HealthCloud characteristics

Sensor grid is a platform that combines wireless sensor networks and grid computing with the aim of exploiting the complementary advantages of the two systems. Proper integration of these distinct systems into effective, logically single platform is challenging. This paper presents an approach for practical sensor grid implementation and management. The proposed approach uses a metamodeling technique and performance analysis and tuning as well as a middleware infrastructure that enable practical sensor grid implementation and management. The paper presents our implementation and analysis of the sensor grid.

https://dro.deakin.edu.au/eserv/DU:30069178/chandrasekaran-sensorgrid-2014.pdf

Sensor Grid Middleware Metamodeling and Analysis

Liquefied Petroleum Gas (LPG) gas is the most commonly used gas for cooking in India and it is considered highly flammable since it is a combination of hydrocarbon gases such as Propane (C3H8), N-butane and Isobutane (C4H10). These elements contribute to its high density and long-distance travelling capabilities. This results in an extensive gas outspread during leakage with multiple avenues for ignition, primarily due to the electric circuitry at home. The primary focus of our project is to simulate a network map of a gas leakage warning system so as to showcase its implementation in an apartment-based setup. The network map can be scaled up for implementation in residential sectors, petroleum and oil fields, sewage lines, etc. based on our proof of concept. In our use case, we would implement LPG Gas Sensors to Microcontroller for providing a logical binary output of fire warning indication.

Gas Leakage Warning System

This paper aims at implementing an efficient sensor middleware for maintaining and managing big data and analysing the efficiency of such a sensor middleware. The work focused on designing of sensor middleware and performance analysis of the sensor middleware. The Hadoop framework, which was used as a sensor middleware, was responsible for maintaining and managing the distributed sensor environment. A prominent monitoring tool such as Zabbix was used to monitor the Hadoop processes and provide alerts for custom trigger events. Performance analysis for the sensor middleware such as Hadoop was done using tools such as collectl and colplot. Performance analysis of Hadoop cluster was performed using an evaluation metric such as total runtime of the job. A brief discussion on the Hadoop tuning tool such as starfish, that makes the Hadoop cluster efficient through configuration changes, is also presented.

Srimathi Chandrasekaran

Papers

Hybrid Continuous Density Hmm-Based Ensemble Neural Networks for Sensor Fault Detection and Classification in Wireless Sensor Network.

Survey on HealthCloud characteristics

Sensor Grid Middleware Metamodeling and Analysis

Gas Leakage Warning System

Analysis of sensor middleware using big data as a cloud computing utility