Amir Arjomand
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Amir Arjomand has a total of 6 co-authors. Here are the top co-authors by number of shared publications:
- Kenneth Blair Kent
University of New Brunswick
4 shared publications - Georgiy Krylov
University of New Brunswick, Fredericton, Canada
3 shared publications - Amin Boudesh
Concordia Institute for Information Systems Engineering, Concordia University, Montreal, QC, Canada
2 shared publications - Arash Mohammadi
Concordia University
2 shared publications - Farnoush Bayatmakou2 shared publications
- Alireza Azadi
Faculty of Computer Science, University of New Brunswick, Fredericton, Canada
1 shared publication
Latest Publications
- Open Access
- 25 August 2026
- Published by Elsevier in Applied Soft Computing
- Vol. 203
TransfoRhythm: A transformer architecture conductive to blood pressure estimation through solo PPG signal capturing
- 25 August 2026
- Published by Elsevier in Applied Soft Computing
- Vol. 203
Open AccessTransfoRhythm: A transformer architecture conductive to blood pressure estimation through solo PPG signal capturing
- Open Access
- 16 February 2026
- Published by Elsevier in SSRN Electronic Journal
TransfoRhythm: A Transformer Architecture Conductive to Blood Pressure Estimation through Solo PPG Signal Capturing
Recent statistics indicate that approximately 1.3 billion individuals worldwide suffer from hypertension, a leading cause of premature death globally. Blood Pressure (BP) serves as a critical health indicator for accurate and timely diagnosis and/or treatment of hypertension. Traditional BP measurement methods rely on cuff-based approaches, which lack real-time, continuous, and reliable BP estimates, crucial for the timely diagnosis/treatment of hypertension. Driven by recent advancements in Artificial Intelligence (AI) and Deep Neural Networks (DNNs), there has been a surge of interest in developing data-driven and cuff-less BP estimation solutions. In this context, current literature predominantly focuses on coupling Electrocardiography (ECG) and Photoplethysmography (PPG) sensors, though this approach is constrained by reliance on multiple sensor types. An alternative, utilizing standalone PPG signals, presents challenges due to the absence of auxiliary sensors (ECG), requiring the use of morphological features while addressing motion artifacts and high-frequency noise. To address these issues, the paper introduces the TransfoRhythm framework, a Transformer-based DNN architecture built upon the recently released physiological database, MIMIC-IV. Leveraging the Multi-Head Attention (MHA) mechanism, TransfoRhythm identifies dependencies and similarities across data segments, forming a robust framework for cuff-less BP estimation solely using PPG signals. To our knowledge, this paper represents the first study to apply the MIMIC IV dataset for cuff-less BP estimation. Performance evaluation through comprehensive experiments demonstrates TransfoRhythm's superiority over its state-of-the-art counterparts. Specifically, TransfoRhythm achieves highly accurate results with a Root Mean Square Error (RMSE) of [2.21, 1.84] and a Mean Absolute Error (MAE) of [1.37, 1.06] for systolic and diastolic blood pressures, respectively.
- 16 February 2026
- Published by Elsevier in SSRN Electronic Journal
Open AccessTransfoRhythm: A Transformer Architecture Conductive to Blood Pressure Estimation through Solo PPG Signal Capturing
Recent statistics indicate that approximately 1.3 billion individuals worldwide suffer from hypertension, a leading cause of premature death globally. Blood Pressure (BP) serves as a critical health indicator for accurate and timely diagnosis and/or treatment of hypertension. Traditional BP measurement methods rely on cuff-based approaches, which lack real-time, continuous, and reliable BP estimates, crucial for the timely diagnosis/treatment of hypertension. Driven by recent advancements in Artificial Intelligence (AI) and Deep Neural Networks (DNNs), there has been a surge of interest in developing data-driven and cuff-less BP estimation solutions. In this context, current literature predominantly focuses on coupling Electrocardiography (ECG) and Photoplethysmography (PPG) sensors, though this approach is constrained by reliance on multiple sensor types. An alternative, utilizing standalone PPG signals, presents challenges due to the absence of auxiliary sensors (ECG), requiring the use of morphological features while addressing motion artifacts and high-frequency noise. To address these issues, the paper introduces the TransfoRhythm framework, a Transformer-based DNN architecture built upon the recently released physiological database, MIMIC-IV. Leveraging the Multi-Head Attention (MHA) mechanism, TransfoRhythm identifies dependencies and similarities across data segments, forming a robust framework for cuff-less BP estimation solely using PPG signals. To our knowledge, this paper represents the first study to apply the MIMIC IV dataset for cuff-less BP estimation. Performance evaluation through comprehensive experiments demonstrates TransfoRhythm's superiority over its state-of-the-art counterparts. Specifically, TransfoRhythm achieves highly accurate results with a Root Mean Square Error (RMSE) of [2.21, 1.84] and a Mean Absolute Error (MAE) of [1.37, 1.06] for systolic and diastolic blood pressures, respectively.
- Open Access
- 28 September 2025
- Published by Association for Computing Machinery (ACM)
- p. 50-55
Lightweight 1D UNet-CPCA Regression Model for Energy-Efficient Blood Pressure Estimation from Raw PPG Signals
- 28 September 2025
- Published by Association for Computing Machinery (ACM)
- p. 50-55
Open AccessLightweight 1D UNet-CPCA Regression Model for Energy-Efficient Blood Pressure Estimation from Raw PPG Signals
- Open Access
- 21 September 2023
- Published by Association for Computing Machinery (ACM)
- p. 1-8
Extending Memory Compatibility with Yosys Front-End in VTR Flow
Verilog-to-routing (VTR) is an open source Computer Aided Design (CAD) framework that is widely used for research purposes. VTR provides researchers with a comprehensive set of benchmarks and FPGA architectures to test, compare and verify their designs and CAD algorithms. VTR employs Odin, Yosys and a combination of Yosys+Odin as its front-ends for elaborating digital designs written in Verilog. Yosys is a standalone synthesis framework that is maintained separately. In order to take advantage of Yosys' latest upgrades, it is essential to upgrade VTR in tandem with Yosys to keep up with its latest changes. In our study, we investigated the integration of the latest available version of Yosys into VTR. In the course of this research, we encountered a challenge stemming from a memory incompatibility in newer versions of Yosys. Our primary research question became how to effectively facilitate netlist conversion from Yosys to Odin to overcome this incompatibility issue. We then showcase how this upgrade affects our benchmark suite, highlighting the notable changes in circuit quality and the tool performance. Our post-upgrade evaluations reveal that the STA (static timing analysis) time of placement and the placement time itself exhibited improvements of up to 11.53% and 10.43%, respectively.
- 21 September 2023
- Published by Association for Computing Machinery (ACM)
- p. 1-8
Open AccessExtending Memory Compatibility with Yosys Front-End in VTR Flow
Verilog-to-routing (VTR) is an open source Computer Aided Design (CAD) framework that is widely used for research purposes. VTR provides researchers with a comprehensive set of benchmarks and FPGA architectures to test, compare and verify their designs and CAD algorithms. VTR employs Odin, Yosys and a combination of Yosys+Odin as its front-ends for elaborating digital designs written in Verilog. Yosys is a standalone synthesis framework that is maintained separately. In order to take advantage of Yosys' latest upgrades, it is essential to upgrade VTR in tandem with Yosys to keep up with its latest changes. In our study, we investigated the integration of the latest available version of Yosys into VTR. In the course of this research, we encountered a challenge stemming from a memory incompatibility in newer versions of Yosys. Our primary research question became how to effectively facilitate netlist conversion from Yosys to Odin to overcome this incompatibility issue. We then showcase how this upgrade affects our benchmark suite, highlighting the notable changes in circuit quality and the tool performance. Our post-upgrade evaluations reveal that the STA (static timing analysis) time of placement and the placement time itself exhibited improvements of up to 11.53% and 10.43%, respectively.