We describe a wireless link management framework for an ocean platform-to-shore communication system that uses time series forecasting to predict the available link capacity using ocean platform sensor data metrics to boost link robustness and to efficiently manage quality of service. Based on the predicted link capacity the OCTT Wireless Link (OWL) manager coordinates transmission scheduling of XML/HTTP sensor data at the web service layer and controls queue management for IP packet routing. To validate our framework, we developed a link management tool, the OCTT Wireless Link (OWL) manager to ensure optimal throughput and quality of service (QoS) for the wireless communication system linking ocean-based instrumented platforms with users on the shore. OWL applies sensor fusion to the platform attribute data which is then used to forecast the throughput of the wireless link in the harsh and rapidly fluctuating oceanic environment. OWL continually sends this forecast to the Queue Manager (QM) and when the signal power is forecast to drop outside the ideal range, using Linux networking tools, OWL provides bandwidth provisioning at the IP layer over each of the wireless radios in the network. This article describes our work on this project and experimentation with the OWL manager applied to sensory data collected from early stage OCTT platform testing.

This paper details the architecture and describes the preliminary experimentation with the proposed framework for anomaly detection in medical wireless body area networks for ubiquitous patient and healthcare monitoring. The architecture integrates novel data mining and machine learning algorithms with modern sensor fusion techniques. Knowing wireless sensor networks are prone to failures resulting from their limitations i.e. limited energy resources and computational power, using this framework, the authors can distinguish between irregular variations in the physiological parameters of the monitored patient and faulty sensor data, to ensure reliable operations and real time global monitoring from smart devices. Sensor nodes are used to measure characteristics of the patient and the sensed data is stored on the local processing unit. Authorized users may access this patient data remotely as long as they maintain connectivity with their application enabled smart device. Anomalous or faulty measurement data resulting from damaged sensor nodes or caused by malicious external parties may lead to misdiagnosis or even death for patients. The authors' application uses a Support Vector Machine to classify abnormal instances in the incoming sensor data. If found, the authors apply a periodically rebuilt, regressive prediction model to the abnormal instance and determine if the patient is entering a critical state or if a sensor is reporting faulty readings. Using real patient data in our experiments, the results validate the robustness of our proposed framework. The authors further discuss the experimental analysis with the proposed approach which shows that it is quickly able to identify sensor anomalies and compared with several other algorithms, it maintains a higher true positive and lower false negative rate.

Various implementations of wireless sensor networks (i.e. personal area-, wireless body area- networks) are prone to node and network failures by such characteristics as limited node energy resources and hardware damage incurred from their surrounding environment (i.e. flooding, forest fires, a patient falling). This may jeopardize their reliability to act as early warning systems, monitoring systems for patients and athletes, and industrial and environmental observation networks. Following the current trend and widespread use of hand held, mobile communication devices, we outline an application architecture designed to detect and predict faulty nodes in wireless sensor networks. Furthermore, we implement our design as a proof of concept prototype for Android-based smartphones, which may be extended to develop other applications used for monitoring networked wireless personal area and body sensors used in other capacities. We have conducted several preliminary experiments to demonstrate the use of our design, which is capable of monitoring networks of wireless sensor devices and predicting node faults based on several localized metrics. As attributes of such networks may change over time, any models generated when the application is initialized must be updated periodically such that the applied machine learning algorithm maintains high levels of both accuracy and precision. The application is designed to discover node faults and, once identified, alert the user so that appropriate action may be taken.

The System Hazard Indication and Extraction Learning Diagnosis (SHIELD) methodology was developed as a novel method to perform system hazard analysis and resilient design. In an earlier paper we described SHIELD conceptually and outlined the details necessary to conduct the analysis manually. This approach integrates state space examination into the analysis process in order to facilitate efficient and comprehensive identification of undiscovered risks and hazard scenarios. SHIELD requires that three phases be performed serially to achieve a system hazard evaluation: decomposition, evaluation and prescription. The first phase of SHIELD, decomposition, breaks the system down hierarchically and recursively into smaller components so that the state space associated with each component is more manageable for the user. In the evaluation phase experts analyze the associated state space and transitions for each component, recursively, bottom-up. The prescription phase applies a set of heuristics to the results from the preceding phase to reduce system hazard. The main contribution of this paper is the automation of the methodology to reduce the effort used for analysis without sacrificing accuracy or overlooking hazardous state combinations. We describe in detail our automation concept and preliminary tests with the prototype.

Wireless Sensor Networks are vulnerable to a plethora of different fault types and external attacks after their deployment. We focus on sensor networks used in healthcare applications for vital sign collection from remotely monitored patients. These types of personal area networks must be robust and resilient to sensor failures as their capabilities encompass highly critical systems. Our objective is to propose an anomaly detection algorithm for medical wireless sensor networks. Our proposed approach firstly classifies instances of sensed patient attributes as normal and abnormal. Once we detect an abnormal instance, we use regression prediction to discern between a faulty sensor reading and a patient entering into a critical state. Our experimental results on real patient datasets show that our proposed approach is able to quickly detect patient anomalies and sensor faults with high detection accuracy while maintaining a low false alarm ratio.

In this paper we introduce a new methodology that integrates system resilience engineering and hazard analysis into complex system design. We then demonstrate its performance by applying it to the design of a Prognosis and Health Monitoring (PHM) system for an ocean current power generator. Three common methodologies for system hazard analysis were tested by applying them to the PHM system's network topology architecture; STAMP-based Process Analysis (STPA), Hazard and Operability Analysis (HAZOP), and a Resilience Engineering, Heuristic-based approach. While all three approaches adequately revealed most PHM system hazards, which assisted in identifying the means with which to mitigate them, none of the approaches fully addressed the multi-state dimensionality of the sub-components of the system, missing risky and hazardous scenarios. We developed the System Hazard Indication and Extraction Learning Diagnosis (SHIELD) methodology for system hazard analysis and resilient design. SHIELD integrates state space analysis into the hazard analysis process in order to facilitate the location of undiscovered hazard scenarios. Our approach uses recursive, top-down system decomposition with subsystem, interface, and process cycle identification. Then, a bottom-up recursive evaluation is completed where we analyze the subsystem state space and state transitions with regard to hazards/failures in process cycles. This yields a comprehensive list of failure states and scenarios. Finally, a top-down prioritized application of resilient engineering heuristics which address hazard scenarios is prescribed. This final phase results in a comprehensive, complete analysis of complex system architectures forcing resilience into the final system design.