Anomaly Detection and Security for Medical Wireless Sensor Networks

Medical Wireless Sensor Networks (WSNs) are comprised of numerous small devices attached to or implanted in the body of a patient to collect vital signs. At present, many existing medical wireless devices are used to collect various patient physiological metrics and vital signs, such as Heart Rate (HR), pulse, oxygen saturation (SpO2), Respiration Rate (RR), Body Temperature (BT), ElectroCardioGram (ECG), ElectroMyoGram (EMG), Blood Pressure (BP), Blood Glucose Levels (BGL), Pedometers (P) for activity analysis and Galvanic Skin Response (GSR). These networked medical sensors accumulate and transmit collected data to a central device (i.e. base station, smart phone, …) for processing and storage, This data may be then reevaluated and used to trigger medical alarms for caregivers or healthcare professionals, upon detection of anomalies in the physiological data, or clinical deterioration of monitored patients, to quickly react [1, 2, 3] by taking the appropriate actions. The use of medical WSNs has been extended to monitor individuals having chronic deasises (i.e. cardiovascular, Alzheimer’s, Parkinson’s, Diabetes, Epilepsy, Asthma) where these networks have enhanced the quality of life by : (i) reducing the healthcare costs (overcapacity, waiting, sojourn time, number of nurses, etc.), and (ii) providing mobility, while continuously collecting and relaying critical physiological data to their associated healthcare providers, e.g. long-term monitoring of patient recovery from surgical procedure after leaving the hospital, kinematic and rehabilitation assessment. Medical sensors with wireless capabilities are available in the market (MICAz, TelosB, Imote2, Shimmer [4], etc.). For example, ECG wireless sensor is connected to three electrodes attached to the chest for real time monitoring of heart problems. The pulse oximeter is used to measure the pulse and blood oxygenation ratio (SpO2), through the use of infrared light and photosensor. These valuable information can be exploited to detect asphyxia, insufficient oxygen (hypoxia) or pneumonia. A normal SpO2 ratio typically exceeds 95%.When this ratio is lower than 90%, an emergency alarm must be triggered due to possible lung problems or respiratory failure. Sensor readings are unreliable and inaccurate [6, 7], due to constrained sensor resources and wireless communication interferences, which make them susceptible to various sources of errors and attack techniques. An improperly attached pulse oximeter clip or an external fluorescent light may cause inaccurate readings. Faulty measurements from sensors (or injected data in network) negatively influence the measured results and lead to diagnosis errors. Furthermore, this may threaten the life of a patient after alerting emergency personnel for a code blue.

The security of communications with the constrained resources of sensors has been proven to be very weak. Jay Radcliffe in black hat security conference demonstrates the vulnerability of an US widely deployed Continuous Glucose Monitoring devices including an insulin pump to attacks (injection, replaying, jamming, etc). A light encryption algorithm with dynamic key management mechanism are required to prevent such security attacks. Furthermore, we want to study and to propose a new lightweight anomaly-based intrusion detection technique [5,6] for the detection and classification of : (i) sensor faults (ii) security attacks, (iii) critical diseases. Minimizing the misclassification rate is required to reduce the number of false alarms triggered by outlier values, and to prevent unnecessary intervention of caregiver. The detection of patient heath degradation is also required to distinguish between faulty sensors, attacks and heath degradation. Parkinson’s and Alzheimer’s disease are common type of dementia, which destroy neurons and their connections in the brain, leading to loss of cognitive function. Today, the detection of such diseases is realized through either Magnetic Resonance Imaging (MRI) or Positron Emission Tomography (PET). We seek to propose a new method for the early detection of such diseases through the use of WSNs and the analysis of physiological data (such as ECG, EMG, etc.).

References

1. H. Alemdar and C. Ersoy, “Wireless sensor networks for healthcare : A survey,” Comput. Netw., vol. 54, no. 15, pp. 2688–2710, 2010. 2. K. Grgic, D. Zagar, and V. Krizanovic, “Medical applications of wireless sensor networks – current status and future directions,” Medicinski Glasnik, vol. 9, no. 1, pp. 23–31, 2012. 3. A. B. Sharma, L. Golubchik, and R. Govindan, “Sensor Faults : Detection Methods and Prevalence in Real-World Datasets,” ACM Trans. Sen. Netw., vol. 6, no. 3, pp. 1–39, 2010. 4. Adrian Burns, Barry R. Greene, Michael J. McGrath, Terrance J. O’Shea, Benjamin Kuris, Steven M. Ayer, Florin Stroiescu, and Victor Cionca. SHIMMER™– A Wireless Sensor Platform for Noninvasive Biomedical Research. IEEE Sensor Journal, 10(9):1527–1534, 2010. 5. Osman Salem, Yaning Liu, Ahmed Mehaoua, "A Lightweight Anomaly Detection Framework for Medical Wireless Sensor Networks ", IEEE Wireless Communications and Networking Conference, WCNC 2013, ShangHai, China. 7-10 April, 2013. 6. Osman Salem, Alexey Guerassimov, Ahmed Mehaoua, Anthony Marcus, Borko Furht, "Sensor Fault and Patient Anomaly Detection and Classification in Medical Wireless Sensor Networks", IEEE International Conference on Communications, ICC’2013, Budapest, Hungary, June 2013.

This research activity will be in collaboration with three research groups from USA (Florida Atlantic University), China (Beijing Univ. of Post and Telecommunications), and Korea (Pohang Univ. of Science and Technology). Some visits will be planned during the Ph.d thesis period.

Required Skills :
 Sensor networks hardware and software architectures (TinyOS, ...)
 Personal Area Network protocols : ZigBee/Bluetooth/802.15.4
 Anomaly Detection and Security in Networks and Systems Machine Learning, Decision Theory, Statistical data analysis.

Programming skills in C/C++, MatLab, TinyOS/NestC.

Writting in english, Autonomy and initiative.