Zachary McBride Lazri

Zachary McBride Lazri

Auto-generated profile, based on publicly available information

Zachary McBride Lazri

Department of Electrical and Computer Engineering, University of Maryland, College Park, Maryland, USA

Research Focus & Metrics

Academic Career Length

5Years (2022-Present)

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

Representative Publications

View All Publications
13 August 2024 in IEEE Transactions on Biomedical Engineering
Verified
Journal Article
Closed access
QZQiang Zhu
Qiang Zhu
CWChau-Wai Wong
Chau-Wai Wong
ZLZachary McBride Lazri
Zachary McBride Lazri
MCMingliang Chen
Mingliang Chen
CFChang-Hong Fu
Chang-Hong Fu
MWMin Wu
Min Wu
Performance improvements obtained by recent principled approaches for pulse rate (PR) estimation have typically been achieved by adding or modifying certain modules within a reconfigurable system. Yet, evaluations are usually performed only at the system level. To better understand each module's contribution and facilitate future research in explainable learning and artificial intelligence for physiological monitoring, this paper conducts a comparative study of video-based, principled PR tracking algorithms, with a particular focus on challenging fitness scenarios. A review of the progress achieved over the last decade and a half in this field is utilized to construct the major processing modules of a reconfigurable remote pulse rate sensing system. Experiments are conducted on two challenging datasets—an internal collection of 25 videos of two Asian males exercising on stationary-bike, elliptical, and treadmill machines and 34 videos from a public ECG fitness database of 14 men and 3 women exercising on elliptical and stationary-bike machines. The signal-to-noise ratio (SNR), Pearson's correlation coefficient, error count ratio, error rate, and root mean squared error are used for performance evaluation. The top-performing configuration produces respective values of $-$ 0.8 dB, 0.86, 9%, 1.7%, and 3.3 beats per minute (bpm) for the internal dataset and 1.3 dB, 0.77, 28.6%, 6.0%, and 8.1 bpm for the ECG Fitness dataset, achieving significant improvements over alternative configurations. Our results indicate a synergistic effect between pulse color mapping and adaptive motion filtering, as well as the importance of a robust frequency tracking algorithm for PR estimation in low SNR settings.

24 March 2022 in IEEE Access
Verified
Journal Article
Open access
ZLZachary Mcbride Lazri
Zachary Mcbride Lazri
QZQiang Zhu
Qiang Zhu
MCMingliang Chen
Mingliang Chen
MWMin Wu
Min Wu
QWQuanzeng Wang
Quanzeng Wang
Infrared thermographs (IRTs, also called thermal cameras) have been used to remotely measure elevated body temperature (BT) and respiratory rate (RR) during infectious disease outbreaks, such as COVID-19. To facilitate the fast measurement of BT and RR using IRTs in densely populated venues, it is desirable to have IRT algorithms that can automatically identify the best facial locations in thermal images to extract these vital signs. The IEC 80601-2-59:2017 standard suggests that the regions medially adjacent to the inner canthi of the eyes are robust BT measurement sites. The nostril regions, on the other hand, are often used for RR estimation. However, it is more difficult to automatically identify inner canthi and nostrils in thermal images than in visible-light images, which are rich with exploitable features. In this paper, a unique system that can detect inner canthi and outer nostril edges directly in thermal images in two phases is introduced. In Phase I, original thermal images were processed in four different ways to enhance facial features to facilitate inner canthus and nostril detection. In Phase II, landmarks of the inner canthi and outer nostril edges were detected in two steps: (1) face detection using the Single Shot Multibox Detector (SSD) and (2) facial landmark detection to locate the inner canthi and outer nostril edges. The face detection, facial landmark detection, and overall system accuracies were evaluated using the intersection over union, normalized Euclidean distance, and success detection rate metrics on a set of 36 thermal images collected from 12 subjects using three different IRTs. Additional validation was performed on a subset of 40 random thermal images from the publicly available Tufts Face Database. The results revealed that the processed images—referred to as ICLIP images—yielded the highest landmark localization accuracy from the four types of processed thermal images, verifying that the system can automatically and accurately estimate the inner canthus and nostril locations in thermal images. The proposed system can be applied in IRT algorithms to provide reliable temperature measurements and RR estimates during infectious disease outbreaks.

17 June 2024 in IEEE Transactions on Information Forensics and Security
Verified
Journal Article
Closed access
ZLZachary McBride Lazri
Zachary McBride Lazri
IBIvan Brugere
Ivan Brugere
XTXin Tian
Xin Tian
DDDana Dachman-Soled
Dana Dachman-Soled
APAntigoni Polychroniadou
Antigoni Polychroniadou
MWMin Wu
Min Wu
Increases in the deployment of machine learning algorithms for applications that deal with sensitive data have brought attention to the issue of fairness in machine learning. Many works have been devoted to applications that require different demographic groups to be treated fairly. However, algorithms that aim to satisfy inter-group fairness (also called group fairness) may inadvertently treat individuals within the same demographic group unfairly. To address this issue, we introduce a formal definition of within-group fairness that maintains fairness among individuals from within the same group. We propose a pre-processing framework to meet both inter- and within-group fairness criteria with little compromise in performance. The framework maps the feature vectors of members from different groups to an inter-group-fair canonical domain before feeding them into a scoring function. The mapping is constructed to preserve the relative relationship between the scores obtained from the unprocessed feature vectors of individuals from the same demographic group, guaranteeing within-group fairness. We apply this framework to the Adult, COMPAS risk assessment, and Law School datasets and compare its performance in achieving inter-group and within-group fairness with two regularization-based methods.

14 November 2024 in TechRxiv
Verified
Preprint
Open access
CSCarl F Steinhauser
Carl F Steinhauser
ZLZachary Lazri
Zachary Lazri
XTXin Tian
Xin Tian
MWMin Wu
Min Wu
Remote photoplethysmography (rPPG) is an active area of research that has extended beyond heart rate (HR) estimation to estimate more complex cardiac signals such as HR variability and blood oxygen saturation (SpO 2). As these applications extend to more challenging domains, the SNR of the physiological signal is increasingly important. This research is particularly useful for enhancing the accessibility and impact of rPPG technologies in consumer electronic devices, such as RGB cameras. Almost all videos recorded with consumer devices use prevailing codec settings, and such video compression is a source of signal degradation. While prior works have assessed the performance of rPPG algorithms under various video compression rates, they have not explored how specific compression configurations can be strategically optimized to better preserve the integrity of rPPG signals. This paper aims to address this gap by identifying a close connection between the projection plane from the principled plane-orthogonal-to-skin (POS) algorithm to the YCbCr color space commonly used in compression. Namely, these projection planes are equivalent, which is a crucial connection that motivates the consideration of alternative color spaces for video compression in physiological monitoring applications. Improved rPPG signal preservation at low bitrates can be achieved using the RGB24 color space for compression compared to YUV444 and YUV420. These results suggest opportunities to reduce error in rPPG applications by treating the video compression color space as a tunable setting in a system's design.

18 September 2025 in ACM Transactions on Knowledge Discovery From Data
Verified
Journal Article
Open access
ZLZachary McBride Lazri
Zachary McBride Lazri
DDDanial Dervovic
Danial Dervovic
APAntigoni Polychroniadou
Antigoni Polychroniadou
IBIvan Brugere
Ivan Brugere
DDDana Dachman-Soled
Dana Dachman-Soled
MWMin Wu
Min Wu
Fair decision-making in Machine Learning (ML) remains a critical challenge, particularly when access to sensitive information is restricted due to legal, ethical, or organizational constraints. These limitations affect both accuracy and fairness, creating tradeoffs central to the deployment of ML systems in the real world. While prior work has studied fairness-accuracy tradeoffs, most approaches focus on model outputs rather than directly examining how restricted data access impacts fairness. This leaves an important gap: understanding how fairness constraints affect model performance under real-world data restrictions . To address this gap, we propose a framework that explicitly models fairness-accuracy tradeoffs in data-restricted environments. Unlike prior work, our approach analyzes the behavior of the optimal Bayesian classifier using a discrete approximation of the data distribution, allowing us to systematically isolate the effects of fairness constraints. We evaluate our framework on three benchmark datasets—Adult, Law, and Dutch Census—revealing key insights: (1) enforcing equal accuracy on imbalanced datasets can substantially degrade performance under additional fairness constraints, (2) individual and group fairness often impose conflicting constraints, and (3) decorrelating sensitive attributes from features does not usually reduce accuracy. These findings demonstrate that our framework provides an effective, structured approach for practitioners to assess fairness constraints in decision-making pipelines.

8 March 2025 in TechRxiv
Verified
Preprint
Open access
QZQiang Zhu
Qiang Zhu
CWChau-Wai Wong
Chau-Wai Wong
ZLZachary McBride Lazri
Zachary McBride Lazri
MCMingliang Chen
Mingliang Chen
CFChang-Hong Fu
Chang-Hong Fu
MWMin Wu
Min Wu
Performance improvements obtained by recent principled approaches for pulse rate (PR) estimation have typically been achieved by adding or modifying certain modules within a reconfigurable system. Yet, evaluations are usually performed only at the system level. To better understand each module's contribution and facilitate future research in explainable learning and artificial intelligence for physiological monitoring, this paper conducts a comparative study of video-based, principled PR tracking algorithms, with a particular focus on challenging fitness scenarios. A review of the progress achieved over the last decade and a half in this field is utilized to construct the major processing modules of a reconfigurable remote pulse rate sensing system. Experiments are conducted on two challenging datasets---an internal collection of 25 videos of two Asian males exercising on stationary-bike, elliptical, and treadmill machines and 34 videos from a public ECG fitness database of 14 men and 3 women exercising on elliptical and stationary-bike machines. The signal-to-noise ratio (SNR), Pearson's correlation coefficient, error count ratio, error rate, and root mean squared error are used for performance evaluation. The top-performing configuration produces respective values of -0.8 dB, 0.86, 9%, 1.7%, and 3.3 beats per minute (bpm) for the internal dataset and 1.3 dB, 0.77, 28.6%, 6.0%, and 8.1 bpm for the ECG Fitness dataset, achieving significant improvements over alternative configurations. Our results indicate a synergistic effect between pulse color mapping and adaptive motion filtering, as well as the importance of a robust frequency tracking algorithm for PR estimation in low SNR settings.