Systems and Computer Engineering, Carleton University

Professor

James worked at Systems and Computer Engineering, Carleton University as a Professor

Systems and Computer Engineering, Carleton University

Associate Professor

James worked at Systems and Computer Engineering, Carleton University as a Associate Professor

Molecular Mining Corp.

Computational Scientist

Computational analysis of microarray gene expression data.
Algorithm development.

Implementation of Artifact Detection in Critical Care: A Methodological Review

IEEE Reviews in Biomedical Engineering

Implementation of Artifact Detection in Critical Care: A Methodological Review

IEEE Reviews in Biomedical Engineering

MP-PIPE: A Massively Parallel Protein-Protein Interaction Prediction Engine

Proceedings of the International Conference on Supercomputing (ICS)

Implementation of Artifact Detection in Critical Care: A Methodological Review

IEEE Reviews in Biomedical Engineering

MP-PIPE: A Massively Parallel Protein-Protein Interaction Prediction Engine

Proceedings of the International Conference on Supercomputing (ICS)

Using Local Binary Patterns For Non-contact Optical Tongue Tracking

36th Canadian Medical and Biological Engineering Conference (CMBEC)

In this study, a real-time tongue tracking system is developed. The goal is to track a user’s tongue in a safe, non-contact manner using a webcam and image processing algorithms. This system functions in a two-level architecture. First, it detects the approximate location of the mouth. Then, exact mouth state and tongue direction are determined. A rapid object detection algorithm which makes use of Multi-scale Block Local Binary Patterns (MB-LBP) is applied in this system. Instead of pixel intensities, this algorithm employs MB-LBP features for computations in processing digital images which significantly reduces computational requirements and increases the frame rate. The Gentle Adaptive Boosting meta-algorithm (AdaBoost) is used to obtain a classifier for each mouth/tongue state. Six-state classification accuracy is measured using a hold-out test with six subjects of varying ethnicities. Accuracy is comparable with that of our previous prototype, but is more robust to ambient lighting and head pose. Accuracy is expected to further increase with the collection of more training data.

Implementation of Artifact Detection in Critical Care: A Methodological Review

IEEE Reviews in Biomedical Engineering

MP-PIPE: A Massively Parallel Protein-Protein Interaction Prediction Engine

Proceedings of the International Conference on Supercomputing (ICS)

Using Local Binary Patterns For Non-contact Optical Tongue Tracking

36th Canadian Medical and Biological Engineering Conference (CMBEC)

In this study, a real-time tongue tracking system is developed. The goal is to track a user’s tongue in a safe, non-contact manner using a webcam and image processing algorithms. This system functions in a two-level architecture. First, it detects the approximate location of the mouth. Then, exact mouth state and tongue direction are determined. A rapid object detection algorithm which makes use of Multi-scale Block Local Binary Patterns (MB-LBP) is applied in this system. Instead of pixel intensities, this algorithm employs MB-LBP features for computations in processing digital images which significantly reduces computational requirements and increases the frame rate. The Gentle Adaptive Boosting meta-algorithm (AdaBoost) is used to obtain a classifier for each mouth/tongue state. Six-state classification accuracy is measured using a hold-out test with six subjects of varying ethnicities. Accuracy is comparable with that of our previous prototype, but is more robust to ambient lighting and head pose. Accuracy is expected to further increase with the collection of more training data.

Differentiating two daily activities through analysis of short ambulatory video clips

MeMeA IEEE

Automatically detecting daily activities using wearable smartphones would provide valuable information to clinicians. While accelerometer data is effective in this area, classifying stair ascent can be difficult. In this paper, video content analysis is performed on short videos captured from a wearable smartphone in order to distinguish between level ground walking and stair climbing. High contrast image features, such as corners, were tracked across consecutive video frames to create feature paths. Computing the median of the slope of the paths in each frame revealed substantial differences, in both magnitude and variation over time, for stair climbing as opposed to walking. A time series of median slope values was produced for each video clip, and the number of local maxima and minima above a threshold of 1.0 were computed. Results revealed that the number of peaks during stair climbing were substantially larger than walking and, therefore, could be used as a feature for distinguishing between these two activities.

Implementation of Artifact Detection in Critical Care: A Methodological Review

IEEE Reviews in Biomedical Engineering

MP-PIPE: A Massively Parallel Protein-Protein Interaction Prediction Engine

Proceedings of the International Conference on Supercomputing (ICS)

Using Local Binary Patterns For Non-contact Optical Tongue Tracking

36th Canadian Medical and Biological Engineering Conference (CMBEC)

In this study, a real-time tongue tracking system is developed. The goal is to track a user’s tongue in a safe, non-contact manner using a webcam and image processing algorithms. This system functions in a two-level architecture. First, it detects the approximate location of the mouth. Then, exact mouth state and tongue direction are determined. A rapid object detection algorithm which makes use of Multi-scale Block Local Binary Patterns (MB-LBP) is applied in this system. Instead of pixel intensities, this algorithm employs MB-LBP features for computations in processing digital images which significantly reduces computational requirements and increases the frame rate. The Gentle Adaptive Boosting meta-algorithm (AdaBoost) is used to obtain a classifier for each mouth/tongue state. Six-state classification accuracy is measured using a hold-out test with six subjects of varying ethnicities. Accuracy is comparable with that of our previous prototype, but is more robust to ambient lighting and head pose. Accuracy is expected to further increase with the collection of more training data.

Differentiating two daily activities through analysis of short ambulatory video clips

MeMeA IEEE

Automatically detecting daily activities using wearable smartphones would provide valuable information to clinicians. While accelerometer data is effective in this area, classifying stair ascent can be difficult. In this paper, video content analysis is performed on short videos captured from a wearable smartphone in order to distinguish between level ground walking and stair climbing. High contrast image features, such as corners, were tracked across consecutive video frames to create feature paths. Computing the median of the slope of the paths in each frame revealed substantial differences, in both magnitude and variation over time, for stair climbing as opposed to walking. A time series of median slope values was produced for each video clip, and the number of local maxima and minima above a threshold of 1.0 were computed. Results revealed that the number of peaks during stair climbing were substantially larger than walking and, therefore, could be used as a feature for distinguishing between these two activities.

Real-time non-contact optical tongue tracking

Journal of Medical and Biological Engineering (JMBE)

In this study, a real-time tongue tracking system is developed. The general goal of this system is 20 to track a user’s tongue in a safe, non-contact manner using a webcam and image processing 21 algorithms. Ultimately, such a system may be useful as part of speech therapy or stroke-recovery 22 regimes. This system first detects the approximate location of the mouth. Then, the exact mouth 23 state and tongue direction is determined by image classification and post-processing. A rapid 24 object detection algorithm which makes use of Multi-scale Block Local Binary Patterns (MB- 25 LBP) is applied in this system. Instead of pixel intensities, this algorithm employs MB-LBP 26 features for computations in processing digital images which significantly reduces computational 27 requirements and increases the frame rate. The Gentle Adaptive Boosting meta-algorithm 28 (Gentle AdaBoost) is used to obtain one classifier for each mouth/tongue state. Six-state 29 classification accuracy is measured using a 6-fold cross-validation test with six subjects of 30 varying ethnicities recorded in two dissimilar lighting conditions. A 6-way classification 31 accuracy of 89.01% is achieved, which is comparable with our previous prototype, but is more 32 robust to variations in ambient lighting and head pose, and more effective in distinguishing faces 33 from background. In addition, two sets of leave-one-out tests are performed in a third lighting 34 condition (accuracy of 95.8% observed), demonstrating the system’s ability to generalize to new 35 environments – a key requirement for eventual deployment. The system can be conveniently 36 extended to cover even more diverse mouth/tongue shapes, skin tone, and also lighting 37 conditions with further training. Ultimately, this system may enable gamification of speech and 38 language therapy by permitting users to control an engaging application with their tongues.

Implementation of Artifact Detection in Critical Care: A Methodological Review

IEEE Reviews in Biomedical Engineering

MP-PIPE: A Massively Parallel Protein-Protein Interaction Prediction Engine

Proceedings of the International Conference on Supercomputing (ICS)

Using Local Binary Patterns For Non-contact Optical Tongue Tracking

36th Canadian Medical and Biological Engineering Conference (CMBEC)

In this study, a real-time tongue tracking system is developed. The goal is to track a user’s tongue in a safe, non-contact manner using a webcam and image processing algorithms. This system functions in a two-level architecture. First, it detects the approximate location of the mouth. Then, exact mouth state and tongue direction are determined. A rapid object detection algorithm which makes use of Multi-scale Block Local Binary Patterns (MB-LBP) is applied in this system. Instead of pixel intensities, this algorithm employs MB-LBP features for computations in processing digital images which significantly reduces computational requirements and increases the frame rate. The Gentle Adaptive Boosting meta-algorithm (AdaBoost) is used to obtain a classifier for each mouth/tongue state. Six-state classification accuracy is measured using a hold-out test with six subjects of varying ethnicities. Accuracy is comparable with that of our previous prototype, but is more robust to ambient lighting and head pose. Accuracy is expected to further increase with the collection of more training data.

Differentiating two daily activities through analysis of short ambulatory video clips

MeMeA IEEE

Automatically detecting daily activities using wearable smartphones would provide valuable information to clinicians. While accelerometer data is effective in this area, classifying stair ascent can be difficult. In this paper, video content analysis is performed on short videos captured from a wearable smartphone in order to distinguish between level ground walking and stair climbing. High contrast image features, such as corners, were tracked across consecutive video frames to create feature paths. Computing the median of the slope of the paths in each frame revealed substantial differences, in both magnitude and variation over time, for stair climbing as opposed to walking. A time series of median slope values was produced for each video clip, and the number of local maxima and minima above a threshold of 1.0 were computed. Results revealed that the number of peaks during stair climbing were substantially larger than walking and, therefore, could be used as a feature for distinguishing between these two activities.

Real-time non-contact optical tongue tracking

Journal of Medical and Biological Engineering (JMBE)

In this study, a real-time tongue tracking system is developed. The general goal of this system is 20 to track a user’s tongue in a safe, non-contact manner using a webcam and image processing 21 algorithms. Ultimately, such a system may be useful as part of speech therapy or stroke-recovery 22 regimes. This system first detects the approximate location of the mouth. Then, the exact mouth 23 state and tongue direction is determined by image classification and post-processing. A rapid 24 object detection algorithm which makes use of Multi-scale Block Local Binary Patterns (MB- 25 LBP) is applied in this system. Instead of pixel intensities, this algorithm employs MB-LBP 26 features for computations in processing digital images which significantly reduces computational 27 requirements and increases the frame rate. The Gentle Adaptive Boosting meta-algorithm 28 (Gentle AdaBoost) is used to obtain one classifier for each mouth/tongue state. Six-state 29 classification accuracy is measured using a 6-fold cross-validation test with six subjects of 30 varying ethnicities recorded in two dissimilar lighting conditions. A 6-way classification 31 accuracy of 89.01% is achieved, which is comparable with our previous prototype, but is more 32 robust to variations in ambient lighting and head pose, and more effective in distinguishing faces 33 from background. In addition, two sets of leave-one-out tests are performed in a third lighting 34 condition (accuracy of 95.8% observed), demonstrating the system’s ability to generalize to new 35 environments – a key requirement for eventual deployment. The system can be conveniently 36 extended to cover even more diverse mouth/tongue shapes, skin tone, and also lighting 37 conditions with further training. Ultimately, this system may enable gamification of speech and 38 language therapy by permitting users to control an engaging application with their tongues.

Service oriented architecture to support real-time implementation of artifact detection in critical care monitoring

33rd Annual International Conference of the IEEE EMBS, pp. 4925-4928.

Implementation of Artifact Detection in Critical Care: A Methodological Review

IEEE Reviews in Biomedical Engineering

MP-PIPE: A Massively Parallel Protein-Protein Interaction Prediction Engine

Proceedings of the International Conference on Supercomputing (ICS)

Using Local Binary Patterns For Non-contact Optical Tongue Tracking

36th Canadian Medical and Biological Engineering Conference (CMBEC)

In this study, a real-time tongue tracking system is developed. The goal is to track a user’s tongue in a safe, non-contact manner using a webcam and image processing algorithms. This system functions in a two-level architecture. First, it detects the approximate location of the mouth. Then, exact mouth state and tongue direction are determined. A rapid object detection algorithm which makes use of Multi-scale Block Local Binary Patterns (MB-LBP) is applied in this system. Instead of pixel intensities, this algorithm employs MB-LBP features for computations in processing digital images which significantly reduces computational requirements and increases the frame rate. The Gentle Adaptive Boosting meta-algorithm (AdaBoost) is used to obtain a classifier for each mouth/tongue state. Six-state classification accuracy is measured using a hold-out test with six subjects of varying ethnicities. Accuracy is comparable with that of our previous prototype, but is more robust to ambient lighting and head pose. Accuracy is expected to further increase with the collection of more training data.

Differentiating two daily activities through analysis of short ambulatory video clips

MeMeA IEEE

Automatically detecting daily activities using wearable smartphones would provide valuable information to clinicians. While accelerometer data is effective in this area, classifying stair ascent can be difficult. In this paper, video content analysis is performed on short videos captured from a wearable smartphone in order to distinguish between level ground walking and stair climbing. High contrast image features, such as corners, were tracked across consecutive video frames to create feature paths. Computing the median of the slope of the paths in each frame revealed substantial differences, in both magnitude and variation over time, for stair climbing as opposed to walking. A time series of median slope values was produced for each video clip, and the number of local maxima and minima above a threshold of 1.0 were computed. Results revealed that the number of peaks during stair climbing were substantially larger than walking and, therefore, could be used as a feature for distinguishing between these two activities.

Real-time non-contact optical tongue tracking

Journal of Medical and Biological Engineering (JMBE)

In this study, a real-time tongue tracking system is developed. The general goal of this system is 20 to track a user’s tongue in a safe, non-contact manner using a webcam and image processing 21 algorithms. Ultimately, such a system may be useful as part of speech therapy or stroke-recovery 22 regimes. This system first detects the approximate location of the mouth. Then, the exact mouth 23 state and tongue direction is determined by image classification and post-processing. A rapid 24 object detection algorithm which makes use of Multi-scale Block Local Binary Patterns (MB- 25 LBP) is applied in this system. Instead of pixel intensities, this algorithm employs MB-LBP 26 features for computations in processing digital images which significantly reduces computational 27 requirements and increases the frame rate. The Gentle Adaptive Boosting meta-algorithm 28 (Gentle AdaBoost) is used to obtain one classifier for each mouth/tongue state. Six-state 29 classification accuracy is measured using a 6-fold cross-validation test with six subjects of 30 varying ethnicities recorded in two dissimilar lighting conditions. A 6-way classification 31 accuracy of 89.01% is achieved, which is comparable with our previous prototype, but is more 32 robust to variations in ambient lighting and head pose, and more effective in distinguishing faces 33 from background. In addition, two sets of leave-one-out tests are performed in a third lighting 34 condition (accuracy of 95.8% observed), demonstrating the system’s ability to generalize to new 35 environments – a key requirement for eventual deployment. The system can be conveniently 36 extended to cover even more diverse mouth/tongue shapes, skin tone, and also lighting 37 conditions with further training. Ultimately, this system may enable gamification of speech and 38 language therapy by permitting users to control an engaging application with their tongues.

Service oriented architecture to support real-time implementation of artifact detection in critical care monitoring

33rd Annual International Conference of the IEEE EMBS, pp. 4925-4928.

Short Co-occurring Polypeptide Regions Can Predict Global Protein Interaction Maps

Scientific Reports

Implementation of Artifact Detection in Critical Care: A Methodological Review

IEEE Reviews in Biomedical Engineering

MP-PIPE: A Massively Parallel Protein-Protein Interaction Prediction Engine

Proceedings of the International Conference on Supercomputing (ICS)

Using Local Binary Patterns For Non-contact Optical Tongue Tracking

36th Canadian Medical and Biological Engineering Conference (CMBEC)

In this study, a real-time tongue tracking system is developed. The goal is to track a user’s tongue in a safe, non-contact manner using a webcam and image processing algorithms. This system functions in a two-level architecture. First, it detects the approximate location of the mouth. Then, exact mouth state and tongue direction are determined. A rapid object detection algorithm which makes use of Multi-scale Block Local Binary Patterns (MB-LBP) is applied in this system. Instead of pixel intensities, this algorithm employs MB-LBP features for computations in processing digital images which significantly reduces computational requirements and increases the frame rate. The Gentle Adaptive Boosting meta-algorithm (AdaBoost) is used to obtain a classifier for each mouth/tongue state. Six-state classification accuracy is measured using a hold-out test with six subjects of varying ethnicities. Accuracy is comparable with that of our previous prototype, but is more robust to ambient lighting and head pose. Accuracy is expected to further increase with the collection of more training data.

Differentiating two daily activities through analysis of short ambulatory video clips

MeMeA IEEE

Automatically detecting daily activities using wearable smartphones would provide valuable information to clinicians. While accelerometer data is effective in this area, classifying stair ascent can be difficult. In this paper, video content analysis is performed on short videos captured from a wearable smartphone in order to distinguish between level ground walking and stair climbing. High contrast image features, such as corners, were tracked across consecutive video frames to create feature paths. Computing the median of the slope of the paths in each frame revealed substantial differences, in both magnitude and variation over time, for stair climbing as opposed to walking. A time series of median slope values was produced for each video clip, and the number of local maxima and minima above a threshold of 1.0 were computed. Results revealed that the number of peaks during stair climbing were substantially larger than walking and, therefore, could be used as a feature for distinguishing between these two activities.

Real-time non-contact optical tongue tracking

Journal of Medical and Biological Engineering (JMBE)

In this study, a real-time tongue tracking system is developed. The general goal of this system is 20 to track a user’s tongue in a safe, non-contact manner using a webcam and image processing 21 algorithms. Ultimately, such a system may be useful as part of speech therapy or stroke-recovery 22 regimes. This system first detects the approximate location of the mouth. Then, the exact mouth 23 state and tongue direction is determined by image classification and post-processing. A rapid 24 object detection algorithm which makes use of Multi-scale Block Local Binary Patterns (MB- 25 LBP) is applied in this system. Instead of pixel intensities, this algorithm employs MB-LBP 26 features for computations in processing digital images which significantly reduces computational 27 requirements and increases the frame rate. The Gentle Adaptive Boosting meta-algorithm 28 (Gentle AdaBoost) is used to obtain one classifier for each mouth/tongue state. Six-state 29 classification accuracy is measured using a 6-fold cross-validation test with six subjects of 30 varying ethnicities recorded in two dissimilar lighting conditions. A 6-way classification 31 accuracy of 89.01% is achieved, which is comparable with our previous prototype, but is more 32 robust to variations in ambient lighting and head pose, and more effective in distinguishing faces 33 from background. In addition, two sets of leave-one-out tests are performed in a third lighting 34 condition (accuracy of 95.8% observed), demonstrating the system’s ability to generalize to new 35 environments – a key requirement for eventual deployment. The system can be conveniently 36 extended to cover even more diverse mouth/tongue shapes, skin tone, and also lighting 37 conditions with further training. Ultimately, this system may enable gamification of speech and 38 language therapy by permitting users to control an engaging application with their tongues.

Service oriented architecture to support real-time implementation of artifact detection in critical care monitoring

33rd Annual International Conference of the IEEE EMBS, pp. 4925-4928.

Short Co-occurring Polypeptide Regions Can Predict Global Protein Interaction Maps

Scientific Reports

Computational Approaches Toward the Design of Pools for the in Vitro Selection of Complex Aptamers

RNA

It is well known that using random RNA/DNA sequences for SELEX experiments will generally yield low-complexity structures. Early experimental results suggest that having a structurally diverse library, which, for instance, includes high-order junctions, may prove useful in finding new functional motifs. Here, we develop two computational methods to generate sequences that exhibit higher structural complexity and can be used to increase the overall structural diversity of initial pools for in vitro selection experiments. Random Filtering selectively increases the number of five-way junctions in RNA/DNA pools, and Genetic Filtering designs RNA/DNA pools to a specified structure distribution, whether uniform or otherwise. We show that using our computationally designed DNA pool greatly improves access to highly complex sequence structures for SELEX experiments (without losing our ability to select for common one-way and two-way junction sequences).

Implementation of Artifact Detection in Critical Care: A Methodological Review

IEEE Reviews in Biomedical Engineering

MP-PIPE: A Massively Parallel Protein-Protein Interaction Prediction Engine

Proceedings of the International Conference on Supercomputing (ICS)

Using Local Binary Patterns For Non-contact Optical Tongue Tracking

36th Canadian Medical and Biological Engineering Conference (CMBEC)

In this study, a real-time tongue tracking system is developed. The goal is to track a user’s tongue in a safe, non-contact manner using a webcam and image processing algorithms. This system functions in a two-level architecture. First, it detects the approximate location of the mouth. Then, exact mouth state and tongue direction are determined. A rapid object detection algorithm which makes use of Multi-scale Block Local Binary Patterns (MB-LBP) is applied in this system. Instead of pixel intensities, this algorithm employs MB-LBP features for computations in processing digital images which significantly reduces computational requirements and increases the frame rate. The Gentle Adaptive Boosting meta-algorithm (AdaBoost) is used to obtain a classifier for each mouth/tongue state. Six-state classification accuracy is measured using a hold-out test with six subjects of varying ethnicities. Accuracy is comparable with that of our previous prototype, but is more robust to ambient lighting and head pose. Accuracy is expected to further increase with the collection of more training data.

Differentiating two daily activities through analysis of short ambulatory video clips

MeMeA IEEE

Automatically detecting daily activities using wearable smartphones would provide valuable information to clinicians. While accelerometer data is effective in this area, classifying stair ascent can be difficult. In this paper, video content analysis is performed on short videos captured from a wearable smartphone in order to distinguish between level ground walking and stair climbing. High contrast image features, such as corners, were tracked across consecutive video frames to create feature paths. Computing the median of the slope of the paths in each frame revealed substantial differences, in both magnitude and variation over time, for stair climbing as opposed to walking. A time series of median slope values was produced for each video clip, and the number of local maxima and minima above a threshold of 1.0 were computed. Results revealed that the number of peaks during stair climbing were substantially larger than walking and, therefore, could be used as a feature for distinguishing between these two activities.

Real-time non-contact optical tongue tracking

Journal of Medical and Biological Engineering (JMBE)

In this study, a real-time tongue tracking system is developed. The general goal of this system is 20 to track a user’s tongue in a safe, non-contact manner using a webcam and image processing 21 algorithms. Ultimately, such a system may be useful as part of speech therapy or stroke-recovery 22 regimes. This system first detects the approximate location of the mouth. Then, the exact mouth 23 state and tongue direction is determined by image classification and post-processing. A rapid 24 object detection algorithm which makes use of Multi-scale Block Local Binary Patterns (MB- 25 LBP) is applied in this system. Instead of pixel intensities, this algorithm employs MB-LBP 26 features for computations in processing digital images which significantly reduces computational 27 requirements and increases the frame rate. The Gentle Adaptive Boosting meta-algorithm 28 (Gentle AdaBoost) is used to obtain one classifier for each mouth/tongue state. Six-state 29 classification accuracy is measured using a 6-fold cross-validation test with six subjects of 30 varying ethnicities recorded in two dissimilar lighting conditions. A 6-way classification 31 accuracy of 89.01% is achieved, which is comparable with our previous prototype, but is more 32 robust to variations in ambient lighting and head pose, and more effective in distinguishing faces 33 from background. In addition, two sets of leave-one-out tests are performed in a third lighting 34 condition (accuracy of 95.8% observed), demonstrating the system’s ability to generalize to new 35 environments – a key requirement for eventual deployment. The system can be conveniently 36 extended to cover even more diverse mouth/tongue shapes, skin tone, and also lighting 37 conditions with further training. Ultimately, this system may enable gamification of speech and 38 language therapy by permitting users to control an engaging application with their tongues.

Service oriented architecture to support real-time implementation of artifact detection in critical care monitoring

33rd Annual International Conference of the IEEE EMBS, pp. 4925-4928.

Short Co-occurring Polypeptide Regions Can Predict Global Protein Interaction Maps

Scientific Reports

Computational Approaches Toward the Design of Pools for the in Vitro Selection of Complex Aptamers

RNA

It is well known that using random RNA/DNA sequences for SELEX experiments will generally yield low-complexity structures. Early experimental results suggest that having a structurally diverse library, which, for instance, includes high-order junctions, may prove useful in finding new functional motifs. Here, we develop two computational methods to generate sequences that exhibit higher structural complexity and can be used to increase the overall structural diversity of initial pools for in vitro selection experiments. Random Filtering selectively increases the number of five-way junctions in RNA/DNA pools, and Genetic Filtering designs RNA/DNA pools to a specified structure distribution, whether uniform or otherwise. We show that using our computationally designed DNA pool greatly improves access to highly complex sequence structures for SELEX experiments (without losing our ability to select for common one-way and two-way junction sequences).

Binding Site Prediction for Protein-Protein Interactions and Novel Motif Discovery using Re-occurring Polypeptide Sequences

BMC Bioinformatics

Implementation of Artifact Detection in Critical Care: A Methodological Review

IEEE Reviews in Biomedical Engineering

MP-PIPE: A Massively Parallel Protein-Protein Interaction Prediction Engine

Proceedings of the International Conference on Supercomputing (ICS)

Using Local Binary Patterns For Non-contact Optical Tongue Tracking

36th Canadian Medical and Biological Engineering Conference (CMBEC)

In this study, a real-time tongue tracking system is developed. The goal is to track a user’s tongue in a safe, non-contact manner using a webcam and image processing algorithms. This system functions in a two-level architecture. First, it detects the approximate location of the mouth. Then, exact mouth state and tongue direction are determined. A rapid object detection algorithm which makes use of Multi-scale Block Local Binary Patterns (MB-LBP) is applied in this system. Instead of pixel intensities, this algorithm employs MB-LBP features for computations in processing digital images which significantly reduces computational requirements and increases the frame rate. The Gentle Adaptive Boosting meta-algorithm (AdaBoost) is used to obtain a classifier for each mouth/tongue state. Six-state classification accuracy is measured using a hold-out test with six subjects of varying ethnicities. Accuracy is comparable with that of our previous prototype, but is more robust to ambient lighting and head pose. Accuracy is expected to further increase with the collection of more training data.

Differentiating two daily activities through analysis of short ambulatory video clips

MeMeA IEEE

Automatically detecting daily activities using wearable smartphones would provide valuable information to clinicians. While accelerometer data is effective in this area, classifying stair ascent can be difficult. In this paper, video content analysis is performed on short videos captured from a wearable smartphone in order to distinguish between level ground walking and stair climbing. High contrast image features, such as corners, were tracked across consecutive video frames to create feature paths. Computing the median of the slope of the paths in each frame revealed substantial differences, in both magnitude and variation over time, for stair climbing as opposed to walking. A time series of median slope values was produced for each video clip, and the number of local maxima and minima above a threshold of 1.0 were computed. Results revealed that the number of peaks during stair climbing were substantially larger than walking and, therefore, could be used as a feature for distinguishing between these two activities.

Real-time non-contact optical tongue tracking

Journal of Medical and Biological Engineering (JMBE)

In this study, a real-time tongue tracking system is developed. The general goal of this system is 20 to track a user’s tongue in a safe, non-contact manner using a webcam and image processing 21 algorithms. Ultimately, such a system may be useful as part of speech therapy or stroke-recovery 22 regimes. This system first detects the approximate location of the mouth. Then, the exact mouth 23 state and tongue direction is determined by image classification and post-processing. A rapid 24 object detection algorithm which makes use of Multi-scale Block Local Binary Patterns (MB- 25 LBP) is applied in this system. Instead of pixel intensities, this algorithm employs MB-LBP 26 features for computations in processing digital images which significantly reduces computational 27 requirements and increases the frame rate. The Gentle Adaptive Boosting meta-algorithm 28 (Gentle AdaBoost) is used to obtain one classifier for each mouth/tongue state. Six-state 29 classification accuracy is measured using a 6-fold cross-validation test with six subjects of 30 varying ethnicities recorded in two dissimilar lighting conditions. A 6-way classification 31 accuracy of 89.01% is achieved, which is comparable with our previous prototype, but is more 32 robust to variations in ambient lighting and head pose, and more effective in distinguishing faces 33 from background. In addition, two sets of leave-one-out tests are performed in a third lighting 34 condition (accuracy of 95.8% observed), demonstrating the system’s ability to generalize to new 35 environments – a key requirement for eventual deployment. The system can be conveniently 36 extended to cover even more diverse mouth/tongue shapes, skin tone, and also lighting 37 conditions with further training. Ultimately, this system may enable gamification of speech and 38 language therapy by permitting users to control an engaging application with their tongues.

Service oriented architecture to support real-time implementation of artifact detection in critical care monitoring

33rd Annual International Conference of the IEEE EMBS, pp. 4925-4928.

Short Co-occurring Polypeptide Regions Can Predict Global Protein Interaction Maps

Scientific Reports

Computational Approaches Toward the Design of Pools for the in Vitro Selection of Complex Aptamers

RNA

It is well known that using random RNA/DNA sequences for SELEX experiments will generally yield low-complexity structures. Early experimental results suggest that having a structurally diverse library, which, for instance, includes high-order junctions, may prove useful in finding new functional motifs. Here, we develop two computational methods to generate sequences that exhibit higher structural complexity and can be used to increase the overall structural diversity of initial pools for in vitro selection experiments. Random Filtering selectively increases the number of five-way junctions in RNA/DNA pools, and Genetic Filtering designs RNA/DNA pools to a specified structure distribution, whether uniform or otherwise. We show that using our computationally designed DNA pool greatly improves access to highly complex sequence structures for SELEX experiments (without losing our ability to select for common one-way and two-way junction sequences).

Binding Site Prediction for Protein-Protein Interactions and Novel Motif Discovery using Re-occurring Polypeptide Sequences

BMC Bioinformatics

Heart disease classification through HRV analysis using parallel cascade identification and fast orthogonal search

IEEE International Workshop on Medical Measurements and Applications Proceedings (MeMeA), pp. 134-139.

IEEE EMBS Ottawa

Secretary

urn:li:fs_position:(ACoAAAUwG8QByQ4wPquk0BbI64ln8jZW79Pwf5k,140220826)

IEEE EMBS Ottawa

Vice-Chair

urn:li:fs_position:(ACoAAAUwG8QByQ4wPquk0BbI64ln8jZW79Pwf5k,140220826)

IEEE EMBS Ottawa

Secretary

urn:li:fs_position:(ACoAAAUwG8QByQ4wPquk0BbI64ln8jZW79Pwf5k,140220826)

IEEE EMBS Ottawa

Vice-Chair

urn:li:fs_position:(ACoAAAUwG8QByQ4wPquk0BbI64ln8jZW79Pwf5k,140220826)

IEEE EMBS Ottawa

Secretary

urn:li:fs_position:(ACoAAAUwG8QByQ4wPquk0BbI64ln8jZW79Pwf5k,140220826)

IEEE EMBS Ottawa

Vice-Chair

urn:li:fs_position:(ACoAAAUwG8QByQ4wPquk0BbI64ln8jZW79Pwf5k,140220826)

IEEE EMBS Ottawa

Secretary

urn:li:fs_position:(ACoAAAUwG8QByQ4wPquk0BbI64ln8jZW79Pwf5k,140220826)

IEEE EMBS Ottawa

Vice-Chair

urn:li:fs_position:(ACoAAAUwG8QByQ4wPquk0BbI64ln8jZW79Pwf5k,140220826)

IEEE EMBS Ottawa

Secretary

urn:li:fs_position:(ACoAAAUwG8QByQ4wPquk0BbI64ln8jZW79Pwf5k,140220826)

IEEE EMBS Ottawa

Vice-Chair

urn:li:fs_position:(ACoAAAUwG8QByQ4wPquk0BbI64ln8jZW79Pwf5k,140220826)

IEEE EMBS Ottawa

Secretary

urn:li:fs_position:(ACoAAAUwG8QByQ4wPquk0BbI64ln8jZW79Pwf5k,140220826)

IEEE EMBS Ottawa

Vice-Chair

urn:li:fs_position:(ACoAAAUwG8QByQ4wPquk0BbI64ln8jZW79Pwf5k,140220826)

IEEE EMBS Ottawa

Secretary

urn:li:fs_position:(ACoAAAUwG8QByQ4wPquk0BbI64ln8jZW79Pwf5k,140220826)

IEEE EMBS Ottawa

Vice-Chair

urn:li:fs_position:(ACoAAAUwG8QByQ4wPquk0BbI64ln8jZW79Pwf5k,140220826)

IEEE EMBS Ottawa

Secretary

urn:li:fs_position:(ACoAAAUwG8QByQ4wPquk0BbI64ln8jZW79Pwf5k,140220826)

IEEE EMBS Ottawa

Vice-Chair

urn:li:fs_position:(ACoAAAUwG8QByQ4wPquk0BbI64ln8jZW79Pwf5k,140220826)

IEEE EMBS Ottawa

Secretary

urn:li:fs_position:(ACoAAAUwG8QByQ4wPquk0BbI64ln8jZW79Pwf5k,140220826)

IEEE EMBS Ottawa

Vice-Chair

urn:li:fs_position:(ACoAAAUwG8QByQ4wPquk0BbI64ln8jZW79Pwf5k,140220826)

IEEE EMBS Ottawa

Secretary

urn:li:fs_position:(ACoAAAUwG8QByQ4wPquk0BbI64ln8jZW79Pwf5k,140220826)

IEEE EMBS Ottawa

Vice-Chair

urn:li:fs_position:(ACoAAAUwG8QByQ4wPquk0BbI64ln8jZW79Pwf5k,140220826)

IEEE EMBS Ottawa

Secretary

urn:li:fs_position:(ACoAAAUwG8QByQ4wPquk0BbI64ln8jZW79Pwf5k,140220826)

IEEE EMBS Ottawa

Vice-Chair

urn:li:fs_position:(ACoAAAUwG8QByQ4wPquk0BbI64ln8jZW79Pwf5k,140220826)

IEEE EMBS Ottawa

Secretary

urn:li:fs_position:(ACoAAAUwG8QByQ4wPquk0BbI64ln8jZW79Pwf5k,140220826)

IEEE EMBS Ottawa

Vice-Chair

urn:li:fs_position:(ACoAAAUwG8QByQ4wPquk0BbI64ln8jZW79Pwf5k,140220826)

IEEE EMBS Ottawa

Secretary

urn:li:fs_position:(ACoAAAUwG8QByQ4wPquk0BbI64ln8jZW79Pwf5k,140220826)

IEEE EMBS Ottawa

Vice-Chair

urn:li:fs_position:(ACoAAAUwG8QByQ4wPquk0BbI64ln8jZW79Pwf5k,140220826)