Seyed Iman Mirzadeh

Seyed Iman Mirzadeh

Auto-generated profile, based on publicly available information

Seyed Iman Mirzadeh

Washington State University

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
13 January 2024 in ACM Transactions on Computing for Healthcare
Verified
Journal Article
Open access
AAAsiful Arefeen
Asiful Arefeen
AAAli Akbari
Ali Akbari
SMSeyed Iman Mirzadeh
Seyed Iman Mirzadeh
RJRoozbeh Jafari
Roozbeh Jafari
BSBehrooz A. Shirazi
Behrooz A. Shirazi
HGHassan Ghasemzadeh
Hassan Ghasemzadeh
Inter-beat interval (IBI) measurement enables estimation of heart-tare variability (HRV) which, in turn, can provide early indication of potential cardiovascular diseases (CVDs). However, extracting IBIs from noisy signals is challenging since the morphology of the signal gets distorted in the presence of noise. Electrocardiogram (ECG) of a person in heavy motion is highly corrupted with noise, known as motion-artifact, and IBI extracted from it is inaccurate. As a part of remote health monitoring and wearable system development, denoising ECG signals and estimating IBIs correctly from them have become an emerging topic among signal-processing researchers. Apart from conventional methods, deep-learning techniques have been successfully used in signal denoising recently, and diagnosis process has become easier, leading to accuracy levels that were previously unachievable. We propose a deep-learning approach leveraging tiramisu autoencoder model to suppress motion-artifact noise and make the R-peaks of the ECG signal prominent even in the presence of high-intensity motion. After denoising, IBIs are estimated more accurately expediting diagnosis tasks. Results illustrate that our method enables IBI estimation from noisy ECG signals with SNR up to -30 dB with average root mean square error (RMSE) of 13 milliseconds for estimated IBIs. At this noise level, our error percentage remains below 8% and outperforms other state-of-the-art techniques.

17 May 2021 in IEEE Sensors Journal
Verified
Journal Article
Closed access
MPMahdi Pedram
Mahdi Pedram
SMSeyed Iman Mirzadeh
Seyed Iman Mirzadeh
SRSeyed Ali Rokni
Seyed Ali Rokni
RFRamin Fallahzadeh
Ramin Fallahzadeh
DWDiane Myung-Kyung Woodbridge
Diane Myung-Kyung Woodbridge
HGHassan Ghasemzadeh
Hassan Ghasemzadeh
Fluid intake tracking is crucial in providing interventions that assist individuals to stay hydrated by maintaining an adequate amount of fluid. It also helps to manage calorie intake by accounting for the amount of calorie consumed from beverages. While staying hydrated and controlling calorie intake is critical in both physical wellness and cognitive health, existing technologies do not provide a solution for monitoring both fluid type and fluid volume. To address this limitation, we present the design, implementation, and validation of Liquid Intake Detection System (LIDS) for real-time tracking of fluid intake type and volume. The system devises a sensing module that is composed of ultrasonic, RGB color, temperature, and accelerometer sensors as well as a computational framework for machine-learning-based fluid intake type classification, volume estimation, and bottle-state-recognition. The developed sensing unit is small and light-weight that can be mounted, from inside, on the lid of a drinking bottle. We conduct extensive experiments to collect data in a variety of bottles and environmental settings. The results show that the accuracy of fluid type detection ranges from 74.93% to 94.98% while trying to detect the fluid of an unseen bottle. Our results for volume estimation show that the regression-based volume estimation supports a root-relative-squared-error that ranges from 1.12% to 13.36%.

12 July 2023 in Sensors
Verified
Journal Article
Open access
PDF file
PAParastoo Alinia
Parastoo Alinia
AAAsiful Arefeen
Asiful Arefeen
ZAZhila Esna Ashari
Zhila Esna Ashari
SMSeyed Iman Mirzadeh
Seyed Iman Mirzadeh
HGHassan Ghasemzadeh
Hassan Ghasemzadeh
Activity recognition using data collected with smart devices such as mobile and wearable sensors has become a critical component of many emerging applications ranging from behavioral medicine to gaming. However, an unprecedented increase in the diversity of smart devices in the internet-of-things era has limited the adoption of activity recognition models for use across different devices. This lack of cross-domain adaptation is particularly notable across sensors of different modalities where the mapping of the sensor data in the traditional feature level is highly challenging. To address this challenge, we propose ActiLabel, a combinatorial framework that learns structural similarities among the events that occur in a target domain and those of a source domain and identifies an optimal mapping between the two domains at their structural level. The structural similarities are captured through a graph model, referred to as the dependency graph, which abstracts details of activity patterns in low-level signal and feature space. The activity labels are then autonomously learned in the target domain by finding an optimal tiered mapping between the dependency graphs. We carry out an extensive set of experiments on three large datasets collected with wearable sensors involving human subjects. The results demonstrate the superiority of ActiLabel over state-of-the-art transfer learning and deep learning methods. In particular, ActiLabel outperforms such algorithms by average F1-scores of 36.3%, 32.7%, and 9.1% for cross-modality, cross-location, and cross-subject activity recognition, respectively.

1 September 2019
Verified
Conference Paper
Closed access
SMSeyed Iman Mirzadeh
Seyed Iman Mirzadeh
JAJessica Ardo
Jessica Ardo
RFRamin Fallahzadeh
Ramin Fallahzadeh
Bryan MinorBryan Minor
Bryan Minor
LELorraine S. Evangelista
Lorraine S. Evangelista
HGHassan Ghasemzadeh
Hassan Ghasemzadeh
While inferring human activities from sensors embedded in mobile devices using machine learning algorithms has been studied, current research relies primarily on sensor data that are collected in controlled settings often with healthy individuals. Currently, there exists a gap in research about how to design activity recognition models based on sensor data collected with chronically-ill individuals and in free-living environments. In this paper, we focus on a situation where free-living activity data are collected continuously, activity vocabulary (i.e., class labels) are not known as a priori, and sensor data are annotated by end-users through an active learning process. By analyzing sensor data collected in a clinical study involving patients with cardiovascular disease, we demonstrate significant challenges that arise while inferring physical activities in uncontrolled environments. In particular, we observe that activity labels that are distinct in syntax can refer to semantically-identical behaviors, resulting in a sparse label space. To construct a meaningful label space, we propose LabelMerger, a framework for restructuring the label space created through active learning in uncontrolled environments in preparation for training activity recognition models. LabelMerger combines the semantic meaning of activity labels with physical attributes of the activities (i.e., domain knowledge) to generate a flexible and meaningful representation of the labels. Specifically, our approach merges labels using both word embedding techniques from the natural language processing domain and activity intensity from the physical activity research. We show that the new representation of the sensor data obtained by LabelMerger results in more accurate activity recognition models compared to the case where original label space is used to learn recognition models.

9 October 2020 in arXiv
Verified
Preprint
Open access
PDF file
SMSeyed Iman Mirzadeh
Seyed Iman Mirzadeh
MFMehrdad Farajtabar
Mehrdad Farajtabar
DGDilan Gorur
Dilan Gorur
RPRazvan Pascanu
Razvan Pascanu
HGHassan Ghasemzadeh
Hassan Ghasemzadeh
Continual (sequential) training and multitask (simultaneous) training are often attempting to solve the same overall objective: to find a solution that performs well on all considered tasks. The main difference is in the training regimes, where continual learning can only have access to one task at a time, which for neural networks typically leads to catastrophic forgetting. That is, the solution found for a subsequent task does not perform well on the previous ones anymore. However, the relationship between the different minima that the two training regimes arrive at is not well understood. What sets them apart? Is there a local structure that could explain the difference in performance achieved by the two different schemes? Motivated by recent work showing that different minima of the same task are typically connected by very simple curves of low error, we investigate whether multitask and continual solutions are similarly connected. We empirically find that indeed such connectivity can be reliably achieved and, more interestingly, it can be done by a linear path, conditioned on having the same initialization for both. We thoroughly analyze this observation and discuss its significance for the continual learning process. Furthermore, we exploit this finding to propose an effective algorithm that constrains the sequentially learned minima to behave as the multitask solution. We show that our method outperforms several state of the art continual learning algorithms on various vision benchmarks.

16 March 2020 in arXiv
Verified
Preprint
Open access
PDF file
PAParastoo Alinia
Parastoo Alinia
IMIman Mirzadeh
Iman Mirzadeh
HGHassan Ghasemzadeh
Hassan Ghasemzadeh
Sensor-based human activity recognition has become a critical component of many emerging applications ranging from behavioral medicine to gaming. However, an unprecedented increase in the diversity of sensor devices in the Internet-of-Things era has limited the adoption of activity recognition models for use across different domains. We propose ActiLabel a combinatorial framework that learns structural similarities among the events in an arbitrary domain and those of a different domain. The structural similarities are captured through a graph model, referred to as the it dependency graph, which abstracts details of activity patterns in low-level signal and feature space. The activity labels are then autonomously learned by finding an optimal tiered mapping between the dependency graphs. Extensive experiments based on three public datasets demonstrate the superiority of ActiLabel over state-of-the-art transfer learning and deep learning methods.