R.A. Goubran

Bruyère Research Institute, Ottawa, Ontario, Canada

Are you R.A. Goubran?

Claim your profile

Publications (215)118.76 Total impact

  • [Show abstract] [Hide abstract]
    ABSTRACT: Remote Patient Monitoring (RPM) systems will play an important role in the future of healthcare. They will be used to monitor chronic conditions, but may also be employed to detect acute medical conditions and generate alarms in real-time. This real-time responsiveness is a critical design criterion for acute condition detection. The data rate of each sensor represents a hard real-time threshold; if an RPM system cannot process incoming data as quickly as it arrives, its perception of a patient's health status will gradually begin to lag behind that patient's actual status. One effective way to address this issue is to select an operating system (OS) that can effectively manage data analysis for the highest priority tasks under all possible CPU load conditions. This paper evaluates the performance of a real-time operating system (RTOS)-based multi-sensor RPM system. The real-time system performance is measured against a hard realtime processing threshold for five simulated sensor inputs with varying priority levels. The results demonstrate that preemptive scheduling, employed by the RTOS, allows an RPM system under heavy processing load to consistently meet the hard real-time threshold requirements for acute condition detection.
    2014 IEEE International Symposium on Medical Measurements and Applications (MeMeA); 06/2014
  • [Show abstract] [Hide abstract]
    ABSTRACT: The sit-to-stand transfer has been examined in depth using many different methods. Pressure mats and or force plates have been used to partition the transfer into phases. These phases help to identify the beginning and end of the transfer and describe the movement performance, therefore characterizing the transition. The methods of phase breakdown, however, vary depending on the source. In this paper, the objective was to distinguish between a vigorous sit to stand transfer and a slower, less stable sit to stand transfer using a different approach. Ten subjects performed two sit-to-stand transfers each on a hospital mattress, while pressure sensors underneath the mattress gathered movement data. The center of mass was calculated and three features were extracted, then evaluated by a classifier to determine if the features could distinguish between the two movements. Examination of the results determined that two of the three features yielded total accuracy, despite inconsistencies in subject performance. These results suggest that the center of pressure can be used to distinguish between slow, unstable sit-to-stand transfers and vigorous ones. Future work will include the examination of center of pressure in the measurement of balance, as well as the overall assessment of sit-to-stand performance.
    2014 IEEE International Symposium on Medical Measurements and Applications (MeMeA); 06/2014
  • Jelena Nikolic-Popovic, Rafik Goubran
    [Show abstract] [Hide abstract]
    ABSTRACT: Proliferation of wearable devices and the “quantified self” behavior creates massive amounts of data acquired from physiological sensors. Unfortunately this vast amount of data is to date largely untapped for clinical purposes because of low data reliability caused by issues such as contact noise and motion artifacts. One important physiological signal is ECG and one of its important features is the heart rate, obtained from the QRS complex of the ECG signal or beat detection algorithms. This feature is important in characterizing Heart Rate Variability (HRV) and detecting various pathologies such as arrhythmia, chronic heart failure, or sleep apnea. Many such algorithms simply discard data segments which are deemed “unreliable” due to errors in QRS detection. This paper analyzes the impact of changing the noise level and noise duration on the percentage of data segments that are discarded. The paper proposes an approach to improve the usability of ECG data corrupted by noise by analyzing the impact of noise on features of interest and adapting relevant system parameters accordingly. The proposed approach can be used with any classifier operating on short-term HRV features.
    2014 IEEE International Symposium on Medical Measurements and Applications (MeMeA); 06/2014
  • [Show abstract] [Hide abstract]
    ABSTRACT: Immobility in older patients is a costly problem for both patients and healthcare workers. The Hierarchical Assessment of Balance and Mobility (HABAM) is a clinical tool able to assess immobile patients and predict morbidity, yet could become more reliable and informative through automation. This paper proposes an algorithm to automatically determine which of three enacted HABAM scores (associated with bedridden patients) had been performed by volunteers. A laptop was used to gather pressure data from three mats placed on a standard hospital bed frame while five volunteers performed three enactments each. A system of algorithms was created, consisting of three subsystems. The first subsystem used mattress data to calculate individual sensor sums and eliminate the weight of the mattress. The second subsystem established a baseline pressure reading for each volunteer and used percentage change to identify and distinguish between two enactments. The third subsystem used calculated weight distribution ratios to determine if the data represented the remaining enactment. The system was tested for accuracy by inputting the volunteer data and recording the assessment output (a score per data set). The system identified 13 of 15 sets of volunteer data as expected. Examination of these results indicated that the two sets of data were not misidentified; rather, the volunteers had made mistakes in performance. These results suggest that this system of algorithms is effective in distinguishing between the three HABAM score enactments examined here, and emphasizes the potential for pervasive computing to improve traditional healthcare.
    Conference proceedings: ... Annual International Conference of the IEEE Engineering in Medicine and Biology Society. IEEE Engineering in Medicine and Biology Society. Conference 07/2013; 2013:4271-4274.
  • [Show abstract] [Hide abstract]
    ABSTRACT: OBJECTIVE: Falls cause significant morbidity and mortality in long term care facilities. Dual-stiffness flooring (DSF) has previously shown promise in reducing such morbidity in experimental models. This study set out to measure the impact of SmartCell flooring on falls-related morbidity in a nursing home. METHODS: All falls occurring at an Arizona nursing home between July 1, 2008, and December 31, 2010, were reviewed for age, sex, diagnosis of osteoporosis, number of medications, history of previous falls, type of flooring (normal vs DSF), time of day, type of injury, and resulting actions. Fall-related outcomes were compared across room types using chi-square and logistic regression methods. RESULTS: Eighty-two falls on the DSF were compared with 85 falls on the regular floor. There was a tendency for residents falling on DSF to have less bruising and abrasions, while having more redness and cuts. There were 2 fractures on regular flooring (2.4% fracture rate) and none on the DSF flooring (0% fracture rate). CONCLUSIONS: The fracture rate of 2.4% of falls on the regular floor is consistent with previous reports in the literature, whereas a 0% rate found on the DSF floor is a clinically significant improvement. This suggests that DSF may be a practical approach for institutions and consumers to reduce fall-related injuries. A larger scale controlled study to confirm these encouraging preliminary findings is warranted.
    Journal of the American Medical Directors Association 01/2013; · 5.30 Impact Factor
  • B. Wallace, R. Goubran, F. Knoefel
    [Show abstract] [Hide abstract]
    ABSTRACT: This paper explores the detection of cognitive change in individuals by sensing a high cognition task (driving). The paper proposes algorithms for the analysis of a set of training trips by a driver to create baseline attributes and features for measurement of baseline navigational performance. Algorithms are proposed for the measurement of subsequent trips through comparison to the baseline performance attributes and the paper shows that trips with common coping mechanisms for cognitive decline can be identified and classified. Common coping mechanisms include use of familiar routes by backtracking to home or reduction in trip complexity through reduction in the variety of stops or in the number of stops are all identified. In addition, algorithms are proposed that identify changes in the navigation ability by indicating routing mistakes or poor choices. The paper shows that the measurement of patient performance can be compared to gold standard Google Maps based routing and navigation choices providing a baseline for a patient's cognitive performance and that cognitive change could be detected in behavior change relative to this baseline including less efficient trip planning, reduced trip complexity or less optimal navigation through use of inefficient but more familiar routes as coping mechanisms.
    Medical Measurements and Applications Proceedings (MeMeA), 2013 IEEE International Symposium on; 01/2013
  • [Show abstract] [Hide abstract]
    ABSTRACT: Cough sound discriminator algorithms are capable of distinguishing between dry and wet cough types. The performance of such algorithms, however, is affected by noise and reverberation in the environment. The effect of reverberation on the performance of cough sound discriminators was previously studied in [1]. In this paper, the effect of noise on the performance of cough sound discriminator is studied and quantitatively measured using previously defined Linear Separation Score (LSS) [1]. Experiments revealed a significant decrease in the performance of cough sound discriminator in the presence of white noise using a single microphone for cough sound acquisition. A microphone array structure containing a maximum of 7 microphones along with delay-and-sum beamforming algorithm was used to improve the performance of the cough sound discriminator. Experimental results showed improvement in the performance of the cough sound discriminator in the presence of white noise using microphone arrays.
    Instrumentation and Measurement Technology Conference (I2MTC), 2013 IEEE International; 01/2013
  • [Show abstract] [Hide abstract]
    ABSTRACT: Pressure ulcers are of great cost to both the patient and the healthcare system. Devices have been developed with the goal of pressure ulcer prevention, but many available technically complex devices have been shown to be no more effective than low pressure overlays or mattresses. This paper proposes a subject dependent algorithm capable of automatically detecting when and where pressure points have been relieved from underneath a supine subject, without any user inputs or assumptions. Pressure sensitive mats, associated software, a laptop and a video camera were used to measure and collect pressure signals generated by a supine subject performing 3 movements: the subject rolling to one side of the body, then to the other side, and the subject attempting to roll without lifting any pressure points off the mattress. The data was zeroed, baseline values were found, differences in sensor score from baseline were calculated, and instances during which a valley on one side coincided with a peak on the other, were recorded. Examination of these results indicated that the algorithm was capable of determining when and where pressure points underneath the sacrum and foot regions were lifted off the bed, but not capable of determining if a scapula pressure point was relieved. These results suggest that the proposed algorithm is effective for some, but not all regions of the body. Future work will therefore focus on detection of all pressure points, and the adjustment of the algorithm for subject independence.
    Medical Measurements and Applications Proceedings (MeMeA), 2013 IEEE International Symposium on; 01/2013
  • J. Nikolic-Popovic, R. Goubran
    [Show abstract] [Hide abstract]
    ABSTRACT: Analysis of Heart Rate Variability (HRV) is an active area of research in the engineering and the medical communities. Current studies use medical-grade ECG signals, from a limited number of available databases. On the other hand, the trend for physiological measurements is towards less obtrusive, wearable devices. It is therefore of interest to apply HRV analysis to signals from such wearable sensors, whose outputs could exhibit varying levels of noise caused by motion artifacts. The main contribution of this paper is the quantification of the impact of imperfect HRV measurements due to motion artifacts on classifiers which use standard time domain and spectral HRV features. The analysis could potentially lead to development of more robust features and classifiers for use in wearable and non-controlled environments.
    Medical Measurements and Applications Proceedings (MeMeA), 2013 IEEE International Symposium on; 01/2013
  • B. Wallace, F. Knoefel, R. Goubran
    [Show abstract] [Hide abstract]
    ABSTRACT: This paper explores the potential for sensor systems to instrument the performance of a high cognition task (driving) as a means to detect cognitive change/decline. Clinical measurement of cognitive function is a sample at a point in time and impacted by variability in how the subject feels and their environment at that point and may not reflect the progression of cognitive illness. Hence it is not a good predictor of a subject's ability or change in ability to perform instrumental activities of daily living. Specifically in this paper, cognition for navigation is measured using GPS tracking data and analyzed to determine a number of attributes of cognitive ability such as navigation decisions for trip stops, route and road path choice. These are then correlated with the attributes for a gold standard (derived Google maps routing) trip reference. The measurement of efficiency for the overall trip and specific navigation choices provides a baseline for a patient's cognitive performance. Cognitive change could be detected through changes in behavior relative to this baseline including less efficient trip planning, reduced trip complexity or less optimal navigation through use of inefficient but more familiar routes as coping mechanisms.
    Instrumentation and Measurement Technology Conference (I2MTC), 2013 IEEE International; 01/2013
  • V. Joshi, P. Moradshahi, R. Goubran
    [Show abstract] [Hide abstract]
    ABSTRACT: The Remote Patient Monitoring (RPM) is becoming vital part of healthcare improving quality of care. The RPM system uses variety of sensors and wireless technologies to monitor multiple biological and environmental signals simultaneously providing status and trend data for the patient. The RPM system can also provide alarms/alerts for the patient or the caregiver in real-time so that the patient gets assistance in timely manner when an acute event occurs. The RPM system must detect such events in real-time to generate alarms/alerts. Use of mobile devices like smartphones and/or tablets for RPM enables patient mobility and provides real-time monitoring capability. The mobile device Operating System (OS) used for real-time RPM needs to meet the hard real-time requirements for alerts/alarms generation. The General Purpose OS (GPOS) uses fair scheduling algorithm for multitasking while Real Time OS (RTOS) uses preemptive scheduling. This paper evaluates the real-time performance of GPOS and a RTOS (QNX) under variety of load condition for RPM application. The results of the measurements indicate that the mobile device OS used for RPM must provide a prioritizing mechanism to satisfy the hard real-time requirements when the mobile device is multitasking and/or overloaded.
    Medical Measurements and Applications Proceedings (MeMeA), 2013 IEEE International Symposium on; 01/2013
  • M. Taylor, T. Grant, F. Knoefel, R. Goubran
    [Show abstract] [Hide abstract]
    ABSTRACT: There is a growing demand for systems that support independent living into advanced age. Technologies that monitor changes in the amount of time older adults spend in bed have the potential to detect critical changes in mobility and support earlier health intervention. Although under mattress sensors have been used previously, processing algorithms were designed for short term monitoring. The objective of this paper was to develop an algorithm and determine optimal sampling rate to obtain bed occupancy characteristics over the longer term. Under mattress sensors were installed in the home of an older adult and data collected over a 3 month period. A processing algorithm was developed to extract bed occupancy information including time in bed, number of bed exits and time of first morning exit. Data were compared using various sampling rates and processing times. Findings indicate that the ideal down sample time for the application was 5 seconds (0.2Hz) and that computational time requirements could be reduced significantly without sacrificing the ability to accurately measure bed occupancy. Features of bed occupancy were plotted and patterns discovered which may be of interest to health clinicians and sleep researchers.
    Medical Measurements and Applications Proceedings (MeMeA), 2013 IEEE International Symposium on; 01/2013
  • Source
    Ming Y Yuan, James R Green, Rafik Goubran
    [Show abstract] [Hide abstract]
    ABSTRACT: The stove is one of the most frequent sources of fire accidents in the home, many of which are caused by human error or forgetfulness, a problem which may become more serious with advanced age. An automated stove-top monitoring system could significantly increase kitchen safety. This study develops such a system, which uses a thermal camera to detect dangerous situations and behaviours, and alerts the user before a fire occurs. It is hoped that this system will serve to promote independent living among the elderly, leading to increased quality of life and decreased health care costs. The stove-top monitoring system consists of four subsystems: burner status (active/inactive), burner temperature trend, pot presence/absence, and human activity detection. Twenty-two experiments were conducted using ceramic, electric coil, and gas stove tops. Rule-based algorithms were developed to combine the outputs of the four subsystems, and to alert the user or caregiver when a dangerous situation occurs. Excellent performance was achieved for alert generation (sensitivity = 94%, positive predictive value = 83%). Furthermore, no modifications are required to the stove top, allowing this system to be retrofitted on any stove top.
    Journal of Medical and Biological Engineering 11/2012; 33(4):380-387. · 0.90 Impact Factor
  • [Show abstract] [Hide abstract]
    ABSTRACT: The high speed mobile networks like 4G and beyond are making a ubiquitous remote patient monitoring (RPM) system using multiple sensors and wireless sensor networks a realistic possibility. The high speed wireless RPM system will be an integral part of the mobile health (mHealth) paradigm reducing cost and providing better service to the patients. While the high speed wireless RPM system will allow clinicians to monitor various chronic and acute medical conditions, the reliability of such system will depend on the network Quality of Service (QoS). The RPM system needs to be resilient to temporary reduced network QoS. This paper presents a highly survivable bed pressure mat RPM system design using an adaptive information content management methodology for the monitored sensor data. The proposed design improves the resiliency of the RPM system under adverse network conditions like congestion and/or temporary loss of connectivity. It also shows how the proposed RPM system can reduce the information rate and correspondingly reduce the data transfer rate by a factor of 5.5 and 144 to address temporary network congestion. The RPM system data rate reduction results in a lower specificity and sensitivity for the features being monitored but increases the survivability of the system from 1 second to 2.4 minutes making it highly robust.
    Conference proceedings: ... Annual International Conference of the IEEE Engineering in Medicine and Biology Society. IEEE Engineering in Medicine and Biology Society. Conference 08/2012; 2012:268-71.
  • [Show abstract] [Hide abstract]
    ABSTRACT: Unobtrusive and continuous monitoring of patients, especially at their place of residence, is becoming a significant part of the healthcare model. A variety of sensors are being used to monitor different patient conditions. Bed occupancy monitoring provides clinicians a quantitative measure of bed entry/exit patterns and may provide information relating to sleep quality. This paper presents a bed occupancy monitoring system using a bed pressure mat sensor. A clinical trial was performed involving 8 patients to collect bed occupancy data. The trial period for each patient ranged from 5-10 weeks. This data was analyzed using a participatory design methodology incorporating clinician feedback to obtain bed occupancy parameters. The parameters extracted include the number of bed exits per night, the bed exit weekly average (including minimum and maximum), the time of day of a particular exit, and the amount of uninterrupted bed occupancy per night. The design of a clinical user interface plays a significant role in the acceptance of such patient monitoring systems by clinicians. The clinician user interface proposed in this paper was designed to be intuitive, easy to navigate and not cause information overload. An iterative design methodology was used for the interface design. The interface design is extendible to incorporate data from multiple sensors. This allows the interface to be part of a comprehensive remote patient monitoring system.
    Conference proceedings: ... Annual International Conference of the IEEE Engineering in Medicine and Biology Society. IEEE Engineering in Medicine and Biology Society. Conference 08/2012; 2012:5810-4.
  • [Show abstract] [Hide abstract]
    ABSTRACT: This paper demonstrates the use of a bed-based optical pressure sensor array to unobtrusively recognize sitting and lying postures as well as lie-to-sit postural transitions. Young healthy, older healthy, older post-stroke, and older post-hip-fracture participants performed a bed entry and exit routine. Data was collected using a pressure sensor array and video cameras. Lying and sitting postures and transitions were analyzed by our system and compared to video analysis from two medical students. For posture identification, eight pressure signal features and three classification techniques were compared. For transition detection, a movement detection algorithm was implemented and combined with the posture identification system. Postural detection accuracy of 100% was achievable using a combination of pressure features. Postural transition detection held a very low miss rate. Differences in measurement of transition duration between our system and video analysis were statistically insignificant.
    01/2012;
  • R B Wallace, R M Dansereau, R A Goubran
    [Show abstract] [Hide abstract]
    ABSTRACT: The electrocardiogram (ECG) is a measurement of the electrical signals associated with the heart and is a key diagnostic tool and patient monitoring device for clinicians. This work presents and compares algorithms for per cycle temporal location of the key ECG phases using 5 methods: 2 pt and 5 pt slope, correlation, wavelet analysis and empirical mode decomposition (EMD). A new wavelet algorithm is proposed using the Daubechies DB6 wavelet and octave band decomposition followed by a series of reconstruction estimates used for temporal localization of each of the ECG phases and it is shown to detect R waves accurately (97.6% — st dev 0.048). A new EMD algorithm is proposed that uses reconstruction estimates to determine the temporal location of each of the ECG phases and it is shown to detect R waves accurately (98.5% — st dev 0.042).
    01/2012;
  • [Show abstract] [Hide abstract]
    ABSTRACT: A new understanding about the role and importance of sleep in health combined with rapidly aging demographics presents opportunities for research and development of new approaches in sleep monitoring. As well, challenges with the current sleep-monitoring solution can be addressed by studying the suitability of new monitoring technologies. This paper presents a small-scale validation of the unobtrusive pressure sensor array compared with traditional polysomnography (PSG), for use as a central apnea (CA) screening tool. Algorithms developed for the pressure sensor array provided a very good detection of the CAs as compared to the gold-standard data for the six patients studied whose body-mass index was appropriate for the sensor. For the retained patients, the algorithm classified CA events with an average sensitivity of 87.6%, specificity of 99.9%, and Cohen's kappa value of 0.875. This work evaluates the ability of an algorithm applied to the unobtrusive pressure sensor array to detect CAs. The sensor array was compared to three other signals: 1) expert PSG interpreters; 2) inductance plethysmography (IP) bands alone; and 3) IP bands combined with an airflow or oxygen-saturation sensor. The impact of unobtrusive CA detection on an older adult's health could be in the areas of broadening of the access to sleep monitoring, longitudinal monitoring of the disease progression, and possibly providing information on the interaction between CA and other disease processes.
    IEEE Transactions on Instrumentation and Measurement 01/2012; 61(7):1857-1865. · 1.71 Impact Factor
  • V. Joshi, R. Goubran, F. Knoefel
    [Show abstract] [Hide abstract]
    ABSTRACT: This paper presents robust adaptive information content system design using contiguous buffering scheme buffers for high data rate real-time applications like e-health, telemedicine and 3-D video using IP network. The design improves the resiliency of the realtime systems under adverse network conditions like congestion and/or temporary loss of connectivity and ensures that critical application data is not lost. The proposed adaptive information content management design for a high data rate real-time application shows how information content can be adaptively managed using contiguous sender buffer to reduce the data transfer rate when underlying network capacity changes over a time period, improving the survivability interval of the system. There is a tradeoff between loss of features, data rate reduction, criticality of the lost information and survivability time of the systems.
    Communications (ICC), 2012 IEEE International Conference on; 01/2012
  • Advances in Acoustics and Vibration 01/2012; 2012:1-10.

Publication Stats

1k Citations
118.76 Total Impact Points

Institutions

  • 2010–2013
    • Bruyère Research Institute
      Ottawa, Ontario, Canada
  • 1986–2013
    • Carleton University
      • Department of Systems and Computer Engineering
      Ottawa, Ontario, Canada
  • 2000–2008
    • University of Ottawa
      Ottawa, Ontario, Canada
  • 2003–2004
    • University of Missouri
      • Department of Electrical and Computer Engineering
      Columbia, MO, United States
  • 1997–2003
    • National Research Council Canada
      • Institute for Microstructural Sciences (IMS)
      Ottawa, Ontario, Canada