مجال التميز | تميز دراسي و بحثي + جائزة تفوقية |
البحوث المنشورة |
|
البحث (1): | |
عنوان البحث: |
Deep Learning for Monitoring of Human Gait a Review |
رابط إلى البحث: | |
تاريخ النشر: |
15/07/2019 |
موجز عن البحث: |
The essential human gait parameters are briefly reviewed, followed by a detailed review of the state of the art in deep learning for the human gait analysis. The modalities for capturing the gait data are grouped according to the sensing technology: video sequences, wearable sensors, and floor sensors, as well as the publicly available datasets. The established artificial neural network architectures for deep learning are reviewed for each group, and their performance are compared with particular emphasis on the spatiotemporal character of gait data and the motivation for multi-sensor, multi-modality fusion. It is shown that by most of the essential metrics, deep learning convolutional neural networks typically outperform shallow learning models. In the light of the discussed character of gait data, this is attributed to the possibility to extract the gait features automatically in deep learning as opposed to the shallow learning from the handcrafted gait features. |
البحث (2): |
|
عنوان البحث: |
Gait Spatiotemporal Signal Analysis for Parkinsons Disease Detection and Severity Rating |
رابط إلى البحث: | |
تاريخ النشر: |
20/08/2020 |
موجز عن البحث: |
Deep learning models are used to process and fuse raw data of gait-induced ground reaction force (GRF) for Parkinson’s disease (PD) patients and healthy subjects with the aim to categorize PD severity. This is achieved by learning automatically, end-to-end, the spatiotemporal GRF signals, resulting in an effective PD severity classification with mean performance F1-score of 95.5% and F1-score standard errors of 0.28%. Layer-wise relevance propagation (LRP) is used to interpret the models’ output and provide insight into which features in the spatiotemporal gait GRF signals are most significant for the models’ predictions. This allows their assignment to gait events, implying that while for the classification of healthy gait the heel strike and body balance are the most indicative gait elements, foot landing and body balance are those most affected in advanced stages of PD. The proposed models are resilient to noise and are computationally efficient for processing and classification of large longitudinal GRF signal datasets, therefore they can be useful for detecting deterioration in the postural balance and rating PD severity. |
البحث (3): | |
عنوان البحث: |
Deep learning in gait analysis for security and healthcare |
رابط إلى البحث: |
https://link.springer.com/chapter/10.1007/978-3-030-31760-7_10 |
تاريخ النشر: |
24/10/2019 |
موجز عن البحث: |
Human motion is an important spatio-temporal pattern as it can be a powerful indicator of human well-being and identity. In particular, human gait offers a unique motion pattern of an individual. Gait refers to the study of locomotion in both humans and animals. It involves the coordination of several parts of the human body: the brain, the spinal cord, the nerves, muscles, bones, and also joints. Gait analysis has been studied for a variety of applications including healthcare, biometrics, sports, and many others. Until recently, the analysis has been done mainly by human observation, using parameters and features established in existing practice and therefore limited by the nature of measurements captured by the gait sensing modalities. In this chapter, we reviewed key conceptual and algorithmic facets of deep learning applied to gait analysis in two important contexts: security and healthcare. |
المؤتمرات العلمية |
|
المؤتمر (1): | |
عنوان المؤتمر: |
The 28th International Symposium on Industrial Electronics (ISIE) |
تاريخ الإنعقاد: |
12/06/2019 |
مكان الإنعقاد: |
Vancouver, BC, Canada |
طبيعة المشاركة: |
Paper presentation |
عنوان المشاركة: |
Deep Learning for Ground Reaction Force Data Analysis Application to Wide-Area Floor Sensing |
ملخص المشاركة: |
Deep learning methods are proposed to process and fuse raw spatiotemporal ground reaction forces (GRF) to accurately categorize gait pattern. These methods are based on convolutional neural network and long short-term memory networks architectures to learn spatiotemporal features, automatically end-to-end from raw GRF sensor signals. In a case study on Parkinson’s disease (PD) data, spatiotemporal signals of gait for PD patient and healthy subjects are processed and classified, resulting an effective gait pattern classification with a precision performance of 96%. Deep learning considerably achieved better classification results, compared to the shallow learning methods with the handcrafted features. This implies that for the purpose of automatic decision-making, it is beneficial to utilize deep learning methods to analyse GRF. This insight is portable across a range of industrial tasks that involve complex spatiotemporal GRF signals classification. The proposed models are computationally efficient and able to achieve high classification precision from a large set of GRF signals. |
الرابط: | |
المؤتمر (2): | |
عنوان المؤتمر: |
2020 IEEE Sensors Applications Symposium (SAS) |
تاريخ الإنعقاد: |
9-11 March 2020 |
مكان الإنعقاد: |
Kuala Lumpur, Malaysia |
طبيعة المشاركة: |
Paper presentation |
عنوان المشاركة: |
Sensor Fusion for Analysis of Gait under Cognitive Load: Deep Learning Approach |
ملخص المشاركة: |
Human mobility requires substantial cognitive resources, thus elevated complexity in the navigated environment instigates gait deterioration due to naturally limited cognitive load capacity. This work uses deep learning methods for 116 sensors fusion to study the effects of cognitive load on human gait of healthy subjects. We demonstrate classifications, achieving 86% precision with Convolutional Neural Networks (CNN), of normal gait as well as 15 subjects’ gait under two types of cognitive demanding tasks. Floor sensors capturing multiples of up to 4 uninterrupted steps were utilized to harvest the raw gait spatiotemporal signals, based on the ground reaction force (GRF). A Layer-Wise Relevance Propagation (LRP) technique is proposed to interpret the CNN prediction in terms of relevance to standard events in the gait cycle. LRP projects the model predictions back to the input gait spatiotemporal signal, to generate a “heat map” over the original training set, or an unknown sample classified by the model. This allows valuable insight into which parts of the gait spatiotemporal signal have the heaviest influence on the gait classification and consequently, which gate events are mostly affected by cognitive load. |
الرابط: | |
المؤتمر (3): | |
عنوان المؤتمر: |
2020 IEEE Sensors Applications Symposium (SAS) |
تاريخ الإنعقاد: |
9-11 March 2020 |
مكان الإنعقاد: |
Kuala Lumpur, Malaysia |
طبيعة المشاركة: |
Paper presentation |
عنوان المشاركة: |
Multi-modality sensor fusion for gait classification using deep learning |
ملخص المشاركة: |
Human gait has been acquired and studied through modalities such as video cameras, inertial sensors and floor sensors etc. Due to many environmental constraints such as illumination, noise, drifts over extended periods or restricted environment, the classification f-score of gait classifications is highly dependent on the usage scenario. This is addressed in this work by proposing sensor fusion of data obtained from 1) ambulatory inertial sensors (AIS) and 2) plastic optical fiber-based floor sensors (FS). Four gait activities are executed by 11 subjects on FS whilst wearing AIS. The proposed sensor fusion method achieves classification f-scores of 88% using artificial neural network (ANN) and 91% using convolutional neural network (CNN) by learning the best data representations from both modalities. |
الرابط: | |
المؤتمر (4): | |
عنوان المؤتمر: |
The 28th International Symposium on Industrial Electronics (ISIE). |
تاريخ الإنعقاد: |
12/06/2019 |
مكان الإنعقاد: |
Vancouver, BC, Canada |
طبيعة المشاركة: |
Paper presentation |
عنوان المشاركة: |
Multi-modality fusion of floor and ambulatory sensors for gait classification |
ملخص المشاركة: |
In a case study of gait classification from floor and ambulatory sensors, we compare results with data from each modality. The automatic extraction of features is achieved by Principle Component Analysis and Canonical Correlation Analysis, the latter performing better even with a reduced number of components used. Non-linear classifiers are most efficient for fused features. With a Kernel Support Vector Machine around 94% accuracy is demonstrated, improving over the 87% and 79% accuracies obtained with separate floor and ambulatory sensor data, respectively. |
الرابط: | |
المؤتمر (5): | |
عنوان المؤتمر: |
International Conference on Intelligent Data Engineering and Automated Learning. IDEAL 2019 |
تاريخ الإنعقاد: |
18/10/2019 |
مكان الإنعقاد: |
Manchester, UK |
طبيعة المشاركة: |
Paper presentation |
عنوان المشاركة: |
Deep Learning and Sensor Fusion Methods for Studying Gait Changes Under Cognitive Load in Males and Females |
ملخص المشاركة: |
Human gait is the manner of walking in people. It is influenced by weight, age, health condition or the interaction with the surrounding environment. In this work, we study gait changes under cognitive load in healthy males and females, using machine learning methods. A deep learning model with multi-processing pipelining and back propagation techniques, is proposed for cognitive load gait analysis. The IMAGiMAT floor system enabling sensor fusion from plastic optical fiber (POF) elements, is utilized to record gait raw data on spatiotemporal ground reaction force (GRF). A deep parallel Convolutional Neural Network (CNN) is engineered for POF sensors fusion, and gait GRF classification. The Layer-Wise Relevance Propagation (LRP), is applied to reveal which gait events are relevant towards informing the parallel CNN prediction. The CNN differentiates between males and females with 95% weighted average precision, and cognitive load gait classification with 93% weighted average precision. These findings present a new hypothesis, whereas larger dataset holds promise for human activity analysis. |
الرابط: |
https://link.springer.com/chapter/10.1007/978-3-030-33607-3_25 |
جوائز التكريم |
|
الجائزة (1): | |
مسمى الجائزة: |
Best student paper award IDEAL 2019 |
الجهة المانحة: |
Springer Nature |
تاريخ الجائزة: |
15 Nov 2019 |
مجال التكريم: |
Best paper award for the paper: “Deep Learning and Sensor Fusion Methods for Studying Gait Changes Under Cognitive Load in Males and Females “presented in 20th International Conference on Intelligent Data Engineering and Automated Learning (IDEAL) |
الرابط: |
https://www.research.manchester.ac.uk/portal/files/149151831/best_student_paper_award.pdf |