no code implementations • 25 Mar 2024 • Ali Abedi, Shehroz S. Khan
It uses facial landmarks, which carry no personally identifiable information, extracted from videos via the MediaPipe deep learning solution.
no code implementations • 5 Mar 2024 • Mark Karlov, Ali Abedi, Shehroz S. Khan
Exercise-based rehabilitation programs have proven to be effective in enhancing the quality of life and reducing mortality and rehospitalization rates.
no code implementations • 27 Nov 2023 • Reza Basiri, Milos R. Popovic, Shehroz S. Khan
Diabetic Foot Ulcer (DFU) is a condition requiring constant monitoring and evaluations for treatment.
no code implementations • 6 Nov 2023 • Stefan Denkovski, Shehroz S. Khan, Alex Mihailidis
Anomaly detection frameworks using autoencoders and their variants can be used for fall detection due to the data imbalance that arises from the rarity and diversity of falls.
no code implementations • 31 Oct 2023 • Reza Basiri, Karim Manji, Francois Harton, Alisha Poonja, Milos R. Popovic, Shehroz S. Khan
The findings highlight the potential of diffusion models for generating synthetic DFU images and their impact on medical training programs and research in wound detection and classification.
no code implementations • 15 Jun 2023 • Ali Abedi, Mobin Malmirian, Shehroz S. Khan
This paper introduces a novel approach to assessing the quality of rehabilitation exercises using RGB video.
no code implementations • 24 Apr 2023 • Zakary Georgis-Yap, Milos R. Popovic, Shehroz S. Khan
We further develop novel unsupervised deep learning approaches to train the models on only normal EEG, and detecting pre-seizure EEG as an anomalous event.
1 code implementation • 19 Apr 2023 • Ali Abedi, Paritosh Bisht, Riddhi Chatterjee, Rachit Agrawal, Vyom Sharma, Dinesh Babu Jayagopi, Shehroz S. Khan
This paper presents a novel approach for segmenting and counting the repetitions of rehabilitation exercises performed by patients, based on their skeletal body joints.
no code implementations • 7 Feb 2023 • Zhidong Meng, Andrea Iaboni, Bing Ye, Kristine Newman, Alex Mihailidis, Zhihong Deng, Shehroz S. Khan
Agitation is one of the most prevalent symptoms in people with dementia (PwD) that can place themselves and the caregiver's safety at risk.
no code implementations • 17 Jan 2023 • Ali Abedi, Chinchu Thomas, Dinesh Babu Jayagopi, Shehroz S. Khan
Compared to the existing sequential and spatiotemporal approaches for engagement measurement, the proposed non-sequential approach improves the state-of-the-art results.
no code implementations • 31 Dec 2022 • Pratik K. Mishra, Alex Mihailidis, Shehroz S. Khan
Appearance-based features can also be sensitive to pixel-based noise, straining the anomaly detection methods to model the changes in the background and making it difficult to focus on the actions of humans in the foreground.
no code implementations • 20 Dec 2022 • Pratik K. Mishra, Andrea Iaboni, Bing Ye, Kristine Newman, Alex Mihailidis, Shehroz S. Khan
Our work differs from most existing approaches for video anomaly detection that focus on appearance-based features, which can put the privacy of a person at risk and is also susceptible to pixel-based noise, including illumination and viewing direction.
1 code implementation • 18 Nov 2022 • Shehroz S. Khan, Ali Abedi
One measure of physical activity, the step count, is well known as a predictor of long-term morbidity and mortality.
no code implementations • 13 Nov 2022 • Ali Abedi, Shehroz S. Khan
Student engagement is an important factor in meeting the goals of virtual learning programs.
no code implementations • 7 Nov 2022 • Ali Abedi, Faranak Dayyani, Charlene Chu, Shehroz S. Khan
In this paper, we propose MAISON, a scalable cloud-based platform of commercially available smart devices capable of collecting desired multimodal sensor data from older adults and patients living in their own homes.
no code implementations • 9 Aug 2022 • Shehroz S. Khan, Ali Abedi, Tracey Colella
The reviewed SE datasets used very diverse and inconsistent definitions and annotation protocols.
1 code implementation • 25 Jun 2022 • Stefan Denkovski, Shehroz S. Khan, Brandon Malamis, Sae Young Moon, Bing Ye, Alex Mihailidis
From a machine learning perspective, developing an effective fall detection system is challenging because of the rarity and variability of falls.
1 code implementation • 9 Sep 2021 • Shehroz S. Khan, Ziting Shen, Haoying Sun, Ax Patel, Ali Abedi
We showed our results on a driver anomaly detection dataset that contains 783 minutes of video recordings of normal and anomalous driving behaviors of 31 drivers from the various top and front cameras (both depth and infrared).
1 code implementation • 20 Apr 2021 • Ali Abedi, Shehroz S. Khan
The 2D ResNet extracts spatial features from consecutive video frames, and the TCN analyzes the temporal changes in video frames to detect the level of engagement.
no code implementations • 15 Apr 2021 • Shehroz S. Khan, Thaejaesh Sooriyakumaran, Katherine Rich, Sofija Spasojevic, Bing Ye, Kristine Newman, Andrea Iaboni, Alex Mihailidis
Agitation is a symptom that communicates distress in people living with dementia (PwD), and that can place them and others at risk.
1 code implementation • 6 Nov 2020 • Ali Abedi, Shehroz S. Khan
Since the proposed framework is privacy-preserving, segments of multiple-segment sequential data cannot be shared between clients or between clients and server.
1 code implementation • 6 Oct 2020 • Shehroz S. Khan, Faraz Khoshbakhtian, Ahmed Bilal Ashraf
Therefore, we formulate the problem of identifying early cases in a pandemic as an anomaly detection problem, in which the data for healthy patients is abundantly available, whereas no training data is present for the class of interest (COVID-19 in our case).
1 code implementation • 17 Apr 2020 • Vineet Mehta, Abhinav Dhall, Sujata Pal, Shehroz S. Khan
A larger reconstruction error indicates the occurrence of a fall.
no code implementations • 19 May 2019 • Shehroz S. Khan, Jacob Nogas, Alex Mihailidis
In this paper, we take an alternate philosophy to detect falls in the absence of their training data, by training the classifier on only the normal activities (that are available in abundance) and identifying a fall as an anomaly.
no code implementations • 31 Jan 2019 • Amir Ahmad, Shehroz S. Khan
Generally, these algorithms use random partition as a starting point, which tends to produce different clustering results for different runs.
no code implementations • 11 Nov 2018 • Amir Ahmad, Shehroz S. Khan
Mixed data comprises both numeric and categorical features, and mixed datasets occur frequently in many domains, such as health, finance, and marketing.
1 code implementation • 30 Aug 2018 • Jacob Nogas, Shehroz S. Khan, Alex Mihailidis
Human falls rarely occur; however, detecting falls is very important from the health and safety perspective.
1 code implementation • 1 Feb 2018 • Shehroz S. Khan, Amir Ahmad, Alex Mihailidis
In this paper, we present several variants of combining single and multiple imputation with bootstrapping to create ensembles that can model uncertainty and diversity in the data, and that are robust to high missingness in the data.
no code implementations • 12 Oct 2016 • Shehroz S. Khan, Babak Taati
We propose two methods for automatic tightening of reconstruction error from only the normal activities for better identification of unseen falls.
no code implementations • 30 May 2016 • Shehroz S. Khan, Jesse Hoey
In this paper, we present a taxonomy for the study of fall detection from the perspective of availability of fall data.
no code implementations • 6 Apr 2016 • Shehroz S. Khan, Amir Ahmad
In one-class classification problems, only the data for the target class is available, whereas the data for the non-target class may be completely absent.
no code implementations • 8 Apr 2015 • Shehroz S. Khan, Michelle E. Karg, Dana Kulic, Jesse Hoey
This paper proposes an approach for the identification of falls using a wearable device in the absence of training data for falls but with plentiful data for normal ADL.
no code implementations • 30 Nov 2013 • Shehroz S. Khan, Michael G. Madden
In this paper we present a unified view of the general problem of OCC by presenting a taxonomy of study for OCC problems, which is based on the availability of training data, algorithms used and the application domains applied.