no code implementations • 20 May 2022 • Zeeshan Ahmad, Naimul Khan
Existing review papers on emotion recognition based on physiological signals surveyed only the regular steps involved in the workflow of emotion recognition such as preprocessing, feature extraction, and classification.
1 code implementation • 21 Jul 2021 • Zeeshan Ahmad, Anika Tabassum, Ling Guan, Naimul Khan
We achieved classification accuracy of 99. 7% and 99. 2% on arrhythmia and MI classification, respectively.
no code implementations • 9 Jul 2021 • Zeeshan Ahmad, Suha Rabbani, Muhammad Rehman Zafar, Syem Ishaque, Sridhar Krishnan, Naimul Khan
In this paper, we report our findings on a new study on VR stress assessment, where three stress levels are assessed.
no code implementations • 28 May 2021 • Zeeshan Ahmad, Naimul Khan
To get the maximum advantage of CNN model for Human Action Recognition (HAR) using inertial sensor data, in this paper, we use 4 types of spatial domain methods for transforming inertial sensor data to activity images, which are then utilized in a novel fusion framework.
no code implementations • 28 May 2021 • Zeeshan Ahmad, Anika Tabassum, Naimul Khan, Ling Guan
In this paper, we present a novel Image Fusion Model (IFM) for ECG heart-beat classification to overcome the weaknesses of existing machine learning techniques that rely either on manual feature extraction or direct utilization of 1D raw ECG signal.
1 code implementation • 29 Oct 2020 • Zeeshan Ahmad, Naimul Khan
Experiments on three publicly available multimodal HAR datasets demonstrate that the proposed MGAF outperforms the previous state of the art fusion methods for depth-inertial HAR in terms of recognition accuracy while being computationally much more efficient.
no code implementations • 22 Aug 2020 • Zeeshan Ahmad, Naimul Khan
The recognition accuracies of each modality, depth data alone and sensor data alone are also calculated and compared with fusion based accuracies to highlight the fact that fusion of modalities yields better results than individual modalities.
no code implementations • 22 Aug 2020 • Zeeshan Ahmad, Naimul Khan
One of the major reasons for misclassification of multiplex actions during action recognition is the unavailability of complementary features that provide the semantic information about the actions.
no code implementations • 12 Aug 2020 • Zeeshan Ahmad, Naimul Khan
To get the maximum advantage of fusing diferent domains, we introduce a dataset with multiple stress levels and then classify these levels using a novel deep learning approach by converting ECG signal into signal images based on R-R peaks without any feature extraction.
1 code implementation • 19 Mar 2020 • Victor Venturi, Holden Parks, Zeeshan Ahmad, Venkatasubramanian Viswanathan
The large-scale search for high-performing candidate 2D materials is limited to calculating a few simple descriptors, usually with first-principles density functional theory calculations.
1 code implementation • 25 Oct 2019 • Zeeshan Ahmad, Naimul Khan
CNNs are trained on input images of each modality to learn low-level, high-level and complex features.
2 code implementations • 9 Jul 2019 • Zeeshan Ahmad, Zijian Hong, Venkatasubramanian Viswanathan
We study the dynamics of electrodeposition of a metal in contact with a liquid crystalline electrolyte.
Applied Physics Chemical Physics
no code implementations • 12 Apr 2018 • Zeeshan Ahmad, Tian Xie, Chinmay Maheshwari, Jeffrey C. Grossman, Venkatasubramanian Viswanathan
We predict over 20 mechanically anisotropic interfaces between Li metal and 6 solid electrolytes which can be used to suppress dendrite growth.