Golara Ahmadi Azar
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Research Subjects
Golara Ahmadi Azar has a total of 15 co-authors. Here are the top co-authors by number of shared publications:
- Qin Hu
Department of Electrical and Computer Engineering, New York University, New York, NY, USA
2 shared publications - Seyed Farokh Atashzar
Department of Electrical and Computer Engineering, New York University (NYU), USA
2 shared publications - Sundeep Rangan
NYU Tandon School of Engineering
2 shared publications Alyson Fletcher
Department of Electrical and Computer Engineering and Department of Statistics, Mathematics, and Computer Science, University of California at Los Angeles (UCLA), Los Angeles, CA, USA
1 shared publication- Alyson K. Fletcherc
Dept. Statistics Dept. ECE NYU Dept. ECE Dept. ECE UC Los Angeles The Ohio State Univ The Ohio State Univ
1 shared publication - Babak Hossein Khalaj
Department of Electrical Engineering Department of Electrical Engineering Department of Electrical Engineering Department of Electrical Engineering Sharif University of Technology Sharif University of Technology Sharif University of Technology Sharif University of Technology Sharif University of Technology Sharif University of Technology
1 shared publication
Latest Publications
- Open Access
- 15 November 2025
- Published by Association for Computing Machinery (ACM)
- p. 1502-1511
MoE-Inference-Bench: Performance Evaluation of Mixture of Expert Large Language and Vision Models
- 15 November 2025
- Published by Association for Computing Machinery (ACM)
- p. 1502-1511
Open AccessMoE-Inference-Bench: Performance Evaluation of Mixture of Expert Large Language and Vision Models
- 17 May 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Journal of Selected Topics in Signal Processing
- Vol. 18 (3) , 419-430
ViT-MDHGR: Cross-Day Reliability and Agility in Dynamic Hand Gesture Prediction via HD-sEMG Signal Decoding
Surface electromyography (sEMG) and high-density sEMG (HD-sEMG) biosignals have been extensively investigated for myoelectric control of prosthetic devices, neurorobotics, and more recently human-computer interfaces because of their capability for hand gesture recognition/prediction in a wearable and non-invasive manner. High intraday (same-day) performance has been reported. However, the interday performance (separating training and testing days) is substantially degraded due to the poor generalizability of conventional approaches over time, hindering the application of such techniques in real-life practices. There are limited recent studies on the feasibility of multi-day hand gesture recognition. The existing studies face a major challenge: the need for long sEMG epochs makes the corresponding neural interfaces impractical due to the induced delay in myoelectric control. This paper proposes a compact ViT-based network for multi-day dynamic hand gesture prediction. We tackle the main challenge as the proposed model only relies on very short HD-sEMG signal windows (i.e., 50 ms, accounting for only one-sixth of the convention for real-time myoelectric implementation), boosting agility and responsiveness. Our proposed model can predict 11 dynamic gestures for 20 subjects with an average accuracy of over 71% on the testing day, 3-25 days after training. Moreover, when calibrated on just a small portion of data from the testing day, the proposed model can achieve over 92% accuracy by retraining less than 10% of the parameters for computational efficiency.
- 17 May 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Journal of Selected Topics in Signal Processing
- Vol. 18 (3) , 419-430
ViT-MDHGR: Cross-Day Reliability and Agility in Dynamic Hand Gesture Prediction via HD-sEMG Signal Decoding
Surface electromyography (sEMG) and high-density sEMG (HD-sEMG) biosignals have been extensively investigated for myoelectric control of prosthetic devices, neurorobotics, and more recently human-computer interfaces because of their capability for hand gesture recognition/prediction in a wearable and non-invasive manner. High intraday (same-day) performance has been reported. However, the interday performance (separating training and testing days) is substantially degraded due to the poor generalizability of conventional approaches over time, hindering the application of such techniques in real-life practices. There are limited recent studies on the feasibility of multi-day hand gesture recognition. The existing studies face a major challenge: the need for long sEMG epochs makes the corresponding neural interfaces impractical due to the induced delay in myoelectric control. This paper proposes a compact ViT-based network for multi-day dynamic hand gesture prediction. We tackle the main challenge as the proposed model only relies on very short HD-sEMG signal windows (i.e., 50 ms, accounting for only one-sixth of the convention for real-time myoelectric implementation), boosting agility and responsiveness. Our proposed model can predict 11 dynamic gestures for 20 subjects with an average accuracy of over 71% on the testing day, 3-25 days after training. Moreover, when calibrated on just a small portion of data from the testing day, the proposed model can achieve over 92% accuracy by retraining less than 10% of the parameters for computational efficiency.
- 20 March 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Sensors Journal
- Vol. 24 (9) , 14778-14791
A Deep Learning Sequential Decoder for Transient High-Density Electromyography in Hand Gesture Recognition Using Subject-Embedded Transfer Learning
Hand gesture recognition (HGR) has gained significant attention due to the increasing use of AI-powered human-computer interfaces that can interpret the deep spatiotemporal dynamics of biosignals from the peripheral nervous system, such as surface electromyography (sEMG). These interfaces have a range of applications, including the control of extended reality, agile prosthetics, and exoskeletons. However, the natural variability of sEMG among individuals has led researchers to focus on subject-specific solutions. Deep learning methods, which often have complex structures, are particularly data-hungry and can be time-consuming to train, making them less practical for subject-specific applications. The main contribution of this paper is to propose and develop a generalizable, sequential decoder of transient high-density sEMG (HD-sEMG) that achieves 73% average accuracy on 65 gestures for partially-observed subjects through subject-embedded transfer learning, leveraging pre-knowledge of HGR acquired during pre-training. The use of transient HD-sEMG before gesture stabilization allows us to predict gestures with the ultimate goal of counterbalancing system control delays. The results show that the proposed generalized models significantly outperform subject-specific approaches, especially when the training data is limited and there is a significant number of gesture classes. By building on pre-knowledge and incorporating a multiplicative subject-embedded structure, our method comparatively achieves more than 13% average accuracy across partially-observed subjects with minimal data availability. This work highlights the potential of HD-sEMG and demonstrates the benefits of modeling common patterns across users to reduce the need for large amounts of data for new users, enhancing practicality.
- 20 March 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Sensors Journal
- Vol. 24 (9) , 14778-14791
A Deep Learning Sequential Decoder for Transient High-Density Electromyography in Hand Gesture Recognition Using Subject-Embedded Transfer Learning
Hand gesture recognition (HGR) has gained significant attention due to the increasing use of AI-powered human-computer interfaces that can interpret the deep spatiotemporal dynamics of biosignals from the peripheral nervous system, such as surface electromyography (sEMG). These interfaces have a range of applications, including the control of extended reality, agile prosthetics, and exoskeletons. However, the natural variability of sEMG among individuals has led researchers to focus on subject-specific solutions. Deep learning methods, which often have complex structures, are particularly data-hungry and can be time-consuming to train, making them less practical for subject-specific applications. The main contribution of this paper is to propose and develop a generalizable, sequential decoder of transient high-density sEMG (HD-sEMG) that achieves 73% average accuracy on 65 gestures for partially-observed subjects through subject-embedded transfer learning, leveraging pre-knowledge of HGR acquired during pre-training. The use of transient HD-sEMG before gesture stabilization allows us to predict gestures with the ultimate goal of counterbalancing system control delays. The results show that the proposed generalized models significantly outperform subject-specific approaches, especially when the training data is limited and there is a significant number of gesture classes. By building on pre-knowledge and incorporating a multiplicative subject-embedded structure, our method comparatively achieves more than 13% average accuracy across partially-observed subjects with minimal data availability. This work highlights the potential of HD-sEMG and demonstrates the benefits of modeling common patterns across users to reduce the need for large amounts of data for new users, enhancing practicality.
- 17 October 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Mobile Computing
- Vol. 23 (6) , 6758-6769
Hybrid Non-Intrusive QoE Assessment of VoIP Calls Based on an Ensemble Learning Model
While the Mean Opinion Score (MOS) is the most well-known way to quantify Quality of Experience (QoE), it only provides average insight. In this paper, we will demonstrate that instead of only relying on the MOS value, predicting users’ perceived quality through probabilistic metrics provides service providers with more accurate insight to improve their network decisions, relying on more accurate measures of how many of them are satisfied or not with the provided service. Furthermore, a hybrid non-intrusive ensemble learner based on the selection of multiple base learners is designed to estimate the QoE of the VoIP signal. The performance of our proposed model is compared to that of individual learners, demonstrating that the proposed scheme outperforms earlier schemes. In addition, in contrast with earlier schemes that relied on their own laboratory-generated dataset, another key advantage of our approach is that it extracts a wide variety of different system parameters, such as noise type and echo delay, and signal parameters, such as fundamental frequency, only from the degraded signal. Finally, we show how the more accurate predicted QoE values can be used by service providers to properly modify network parameters to get closer to the required QoE levels.
- 17 October 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Mobile Computing
- Vol. 23 (6) , 6758-6769
Hybrid Non-Intrusive QoE Assessment of VoIP Calls Based on an Ensemble Learning Model
While the Mean Opinion Score (MOS) is the most well-known way to quantify Quality of Experience (QoE), it only provides average insight. In this paper, we will demonstrate that instead of only relying on the MOS value, predicting users’ perceived quality through probabilistic metrics provides service providers with more accurate insight to improve their network decisions, relying on more accurate measures of how many of them are satisfied or not with the provided service. Furthermore, a hybrid non-intrusive ensemble learner based on the selection of multiple base learners is designed to estimate the QoE of the VoIP signal. The performance of our proposed model is compared to that of individual learners, demonstrating that the proposed scheme outperforms earlier schemes. In addition, in contrast with earlier schemes that relied on their own laboratory-generated dataset, another key advantage of our approach is that it extracts a wide variety of different system parameters, such as noise type and echo delay, and signal parameters, such as fundamental frequency, only from the degraded signal. Finally, we show how the more accurate predicted QoE values can be used by service providers to properly modify network parameters to get closer to the required QoE levels.