Jacob Nogas

Jacob Nogas

Auto-generated profile, based on publicly available information

Jacob Nogas

Jacob Nogas University of Toronto Canada

Research Focus & Metrics

Academic Career Length

8Years (2019-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
18 December 2019 in Journal of Healthcare Informatics Research
Verified
Journal Article
Closed access
PDF file
JNJacob Nogas
Jacob Nogas
SKShehroz S Khan
Shehroz S Khan
AMAlex Mihailidis
Alex Mihailidis

1 July 2019
Verified
Conference Paper
Closed access
SKShehroz S Khan
Shehroz S Khan
SSSofija Spasojevic
Sofija Spasojevic
JNJacob Nogas
Jacob Nogas
BYBing Ye
Bing Ye
AMAlex Mihailidis
Alex Mihailidis
KNKristine Newman
Kristine Newman
People Living with Dementia (PLwD) often exhibit behavioral and psychological symptoms of dementia; with agitation being one of the most prevalent symptoms. Agitated behaviour in PLwD indicates distress and confusion and increases the risk to injury to both the patients and the caregivers. In this paper, we present the use of wearable devices to detect agitation in PLwD. We hypothesize that combining multi-modal sensor data can help in building better classifiers to identify agitation in PLwD in comparison to a single sensor. We present a unique study to collect motion and physiological data from PLwD. This multi-modal sensor data is subsequently used to build predictive models to detect agitation in PLwD. The results on Random Forest for 28 days of data from PLwD show a strong evidence to support our hypothesis and highlight the importance of using multi-modal sensor data for detecting agitation events amongst them.

1 July 2020 in Pattern Analysis and Applications
Verified
Journal Article
Closed access
PDF file
SKShehroz S Khan
Shehroz S Khan
JNJacob Nogas
Jacob Nogas
AMAlex Mihailidis
Alex Mihailidis

23 November 2022 in arXiv
Verified
Preprint
Open access
PDF file
TLTong Li
Tong Li
JNJacob Nogas
Jacob Nogas
HSHaochen Song
Haochen Song
HKHarsh Kumar
Harsh Kumar
ADAudrey Durand
Audrey Durand
JWJoseph J. Williams
Joseph J. Williams
Multi-armed bandit algorithms like Thompson Sampling (TS) can be used to conduct adaptive experiments, in which maximizing reward means that data is used to progressively assign participants to more effective arms. Such assignment strategies increase the risk of statistical hypothesis tests identifying a difference between arms when there is not one, and failing to conclude there is a difference in arms when there truly is one. We tackle this by introducing a novel heuristic algorithm, called TS-PostDiff (Posterior Probability of Difference). TS-PostDiff takes a Bayesian approach to mixing TS and Uniform Random (UR): the probability a participant is assigned using UR allocation is the posterior probability that the difference between two arms is 'small' (below a certain threshold), allowing for more UR exploration when there is little or no reward to be gained. We evaluate TS-PostDiff against state-of-the-art strategies. The empirical and simulation results help characterize the trade-offs of these approaches between reward, False Positive Rate (FPR), and statistical power, as well as under which circumstances each is effective. We quantify the advantage of TS-PostDiff in performing well across multiple differences in arm means (effect sizes), showing the benefits of adaptively changing randomization/exploration in TS in a "Statistically Considerate" manner: reducing FPR and increasing statistical power when differences are small or zero and there is less reward to be gained, while exploiting more when differences may be large. This highlights important considerations for future algorithm development and analysis to better balance reward and statistical analysis.

27 April 2020 in arXiv
Verified
Preprint
Open access
PDF file
JNJacob Nogas
Jacob Nogas
SKShehroz S Khan
Shehroz S Khan
AMAlex Mihailidis
Alex Mihailidis
Human falls rarely occur; however, detecting falls is very important from the health and safety perspective. Due to the rarity of falls, it is difficult to employ supervised classification techniques to detect them. Moreover, in these highly skewed situations it is also difficult to extract domain specific features to identify falls. In this paper, we present a novel framework, \textit{DeepFall}, which formulates the fall detection problem as an anomaly detection problem. The \textit{DeepFall} framework presents the novel use of deep spatio-temporal convolutional autoencoders to learn spatial and temporal features from normal activities using non-invasive sensing modalities. We also present a new anomaly scoring method that combines the reconstruction score of frames across a temporal window to detect unseen falls. We tested the \textit{DeepFall} framework on three publicly available datasets collected through non-invasive sensing modalities, thermal camera and depth cameras and show superior results in comparison to traditional autoencoder methods to identify unseen falls.

2 March 2020 in arXiv
Verified
Preprint
Open access
PDF file
SKShehroz S Khan
Shehroz S Khan
JNJacob Nogas
Jacob Nogas
AMAlex Mihailidis
Alex Mihailidis
Fall detection is an important problem from both the health and machine learning perspective. A fall can lead to severe injuries, long term impairments or even death in some cases. In terms of machine learning, it presents a severely class imbalance problem with very few or no training data for falls owing to the fact that falls occur rarely. 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. To realize such a classifier, we use an adversarial learning framework, which comprises of a spatio-temporal autoencoder for reconstructing input video frames and a spatio-temporal convolution network to discriminate them against original video frames. 3D convolutions are used to learn spatial and temporal features from the input video frames. The adversarial learning of the spatio-temporal autoencoder will enable reconstructing the normal activities of daily living efficiently; thus, rendering detecting unseen falls plausible within this framework. We tested the performance of the proposed framework on camera sensing modalities that may preserve an individual's privacy (fully or partially), such as thermal and depth camera. Our results on three publicly available datasets show that the proposed spatio-temporal adversarial framework performed better than other baseline frame based (or spatial) adversarial learning methods.