Zeeshan Ahmad

Zeeshan Ahmad, Naimul Khan

Physiological Signals are the most reliable form of signals for emotion recognition, as they cannot be controlled deliberately by the subject. 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. While these are important steps, such steps are required for any signal processing application. Emotion recognition poses its own set of challenges that are very important to address for a robust system. Thus, to bridge the gap in the existing literature, in this paper, we review the effect of inter-subject data variance on emotion recognition, important data annotation techniques for emotion recognition and their comparison, data preprocessing techniques for each physiological signal, data splitting techniques for improving the generalization of emotion recognition models and different multimodal fusion techniques and their comparison. Finally we discuss key challenges and future directions in this field.

Zeeshan Ahmad, Naimul Khan

Vision Transformers have shown tremendous success in numerous computer vision applications; however, they have not been exploited for stress assessment using physiological signals such as Electrocardiogram (ECG). In order to get the maximum benefit from the vision transformer for multilevel stress assessment, in this paper, we transform the raw ECG data into 2D spectrograms using short time Fourier transform (STFT). These spectrograms are divided into patches for feeding to the transformer encoder. We also perform experiments with 1D CNN and ResNet-18 (CNN model). We perform leave-onesubject-out cross validation (LOSOCV) experiments on WESAD and Ryerson Multimedia Lab (RML) dataset. One of the biggest challenges of LOSOCV based experiments is to tackle the problem of intersubject variability. In this research, we address the issue of intersubject variability and show our success using 2D spectrograms and the attention mechanism of transformer. Experiments show that vision transformer handles the effect of intersubject variability much better than CNN-based models and beats all previous state-of-the-art methods by a considerable margin. Moreover, our method is end-to-end, does not require handcrafted features, and can learn robust representations. The proposed method achieved 71.01% and 76.7% accuracies with RML dataset and WESAD dataset respectively for three class classification and 88.3% for binary classification on WESAD.

Swayam Rajat Mohanty, Moin Uddin Maruf, Vaibhav Singh et al.

Solar photovoltaic (PV) modules are prone to damage during manufacturing, installation and operation which reduces their power conversion efficiency. This diminishes their positive environmental impact over the lifecycle. Continuous monitoring of PV modules during operation via unmanned aerial vehicles is essential to ensure that defective panels are promptly replaced or repaired to maintain high power conversion efficiencies. Computer vision provides an automatic, non-destructive and cost-effective tool for monitoring defects in large-scale PV plants. We review the current landscape of deep learning-based computer vision techniques used for detecting defects in solar modules. We compare and evaluate the existing approaches at different levels, namely the type of images used, data collection and processing method, deep learning architectures employed, and model interpretability. Most approaches use convolutional neural networks together with data augmentation or generative adversarial network-based techniques. We evaluate the deep learning approaches by performing interpretability analysis on classification tasks. This analysis reveals that the model focuses on the darker regions of the image to perform the classification. We find clear gaps in the existing approaches while also laying out the groundwork for mitigating these challenges when building new models. We conclude with the relevant research gaps that need to be addressed and approaches for progress in this field: integrating geometric deep learning with existing approaches for building more robust and reliable models, leveraging physics-based neural networks that combine domain expertise of physical laws to build more domain-aware deep learning models, and incorporating interpretability as a factor for building models that can be trusted. The review points towards a clear roadmap for making this technology commercially relevant.

Zeeshan Ahmad, Shudi Bao, Meng Chen

Medical image classification plays an increasingly vital role in identifying various diseases by classifying medical images, such as X-rays, MRIs and CT scans, into different categories based on their features. In recent years, deep learning techniques have attracted significant attention in medical image classification. However, it is usually infeasible to train an entire large deep learning model from scratch. To address this issue, one of the solutions is the transfer learning (TL) technique, where a pre-trained model is reused for a new task. In this paper, we present a comprehensive analysis of TL techniques for medical image classification using deep convolutional neural networks. We evaluate six pre-trained models (AlexNet, VGG16, ResNet18, ResNet34, ResNet50, and InceptionV3) on a custom chest X-ray dataset for disease detection. The experimental results demonstrate that InceptionV3 consistently outperforms other models across all the standard metrics. The ResNet family shows progressively better performance with increasing depth, whereas VGG16 and AlexNet perform reasonably well but with lower accuracy. In addition, we also conduct uncertainty analysis and runtime comparison to assess the robustness and computational efficiency of these models. Our findings reveal that TL is beneficial in most cases, especially with limited data, but the extent of improvement depends on several factors such as model architecture, dataset size, and domain similarity between source and target tasks. Moreover, we demonstrate that with a well-trained feature extractor, only a lightweight feedforward model is enough to provide efficient prediction. As such, this study contributes to the understanding of TL in medical image classification, and provides insights for selecting appropriate models based on specific requirements.

Moin Uddin Maruf, Sungmin Kim, Zeeshan Ahmad

Machine learning interatomic potentials (MLIPs) provide a computationally efficient alternative to quantum mechanical simulations for predicting material properties. Message-passing graph neural networks, commonly used in these MLIPs, rely on local descriptor-based symmetry functions to model atomic interactions. However, such local descriptor-based approaches struggle with systems exhibiting long-range interactions, charge transfer, and compositional heterogeneity. In this work, we develop a new equivariant MLIP incorporating long-range Coulomb interactions through explicit treatment of electronic degrees of freedom, specifically global charge distribution within the system. This is achieved using a charge equilibration scheme based on predicted atomic electronegativities. We systematically evaluate our model across a range of benchmark periodic and non-periodic datasets, demonstrating that it outperforms both short-range equivariant and long-range invariant MLIPs in energy and force predictions. Our approach enables more accurate and efficient simulations of systems with long-range interactions and charge heterogeneity, expanding the applicability of MLIPs in computational materials science.

Zeeshan Ahmad, Shudi Bao, Meng Chen

In recent years, generative adversarial networks (GANs) have made significant progress in generating audio sequences. However, these models typically rely on bandwidth-limited mel-spectrograms, which constrain the resolution of generated audio sequences, and lead to mode collapse during conditional generation. To address this issue, we propose Deformable Periodic Network based GAN (DPN-GAN), a novel GAN architecture that incorporates a kernel-based periodic ReLU activation function to induce periodic bias in audio generation. This innovative approach enhances the model's ability to capture and reproduce intricate audio patterns. In particular, our proposed model features a DPN module for multi-resolution generation utilizing deformable convolution operations, allowing for adaptive receptive fields that improve the quality and fidelity of the synthetic audio. Additionally, we enhance the discriminator network using deformable convolution to better distinguish between real and generated samples, further refining the audio quality. We trained two versions of the model: DPN-GAN small (38.67M parameters) and DPN-GAN large (124M parameters). For evaluation, we use five different datasets, covering both speech synthesis and music generation tasks, to demonstrate the efficiency of the DPN-GAN. The experimental results demonstrate that DPN-GAN delivers superior performance on both out-of-distribution and noisy data, showcasing its robustness and adaptability. Trained across various datasets, DPN-GAN outperforms state-of-the-art GAN architectures on standard evaluation metrics, and exhibits increased robustness in synthesized audio.

Yasir Ali Farrukh, Irfan Khan, Zeeshan Ahmad et al.

Modern smart grid systems are heavily dependent on Information and Communication Technology, and this dependency makes them prone to cyberattacks. The occurrence of a cyberattack has increased in recent years resulting in substantial damage to power systems. For a reliable and stable operation, cyber protection, control, and detection techniques are becoming essential. Automated detection of cyberattacks with high accuracy is a challenge. To address this, we propose a two-layer hierarchical machine learning model having an accuracy of 95.44 % to improve the detection of cyberattacks. The first layer of the model is used to distinguish between the two modes of operation (normal state or cyberattack). The second layer is used to classify the state into different types of cyberattacks. The layered approach provides an opportunity for the model to focus its training on the targeted task of the layer, resulting in improvement in model accuracy. To validate the effectiveness of the proposed model, we compared its performance against other recent cyber attack detection models proposed in the literature.

Zeeshan Ahmad, Anika Tabassum, Ling Guan et al.

Electrocardiogram (ECG) is an authoritative source to diagnose and counter critical cardiovascular syndromes such as arrhythmia and myocardial infarction (MI). Current machine learning techniques either depend on manually extracted features or large and complex deep learning networks which merely utilize the 1D ECG signal directly. Since intelligent multimodal fusion can perform at the stateof-the-art level with an efficient deep network, therefore, in this paper, we propose two computationally efficient multimodal fusion frameworks for ECG heart beat classification called Multimodal Image Fusion (MIF) and Multimodal Feature Fusion (MFF). At the input of these frameworks, we convert the raw ECG data into three different images using Gramian Angular Field (GAF), Recurrence Plot (RP) and Markov Transition Field (MTF). In MIF, we first perform image fusion by combining three imaging modalities to create a single image modality which serves as input to the Convolutional Neural Network (CNN). In MFF, we extracted features from penultimate layer of CNNs and fused them to get unique and interdependent information necessary for better performance of classifier. These informational features are finally used to train a Support Vector Machine (SVM) classifier for ECG heart-beat classification. We demonstrate the superiority of the proposed fusion models by performing experiments on PhysioNets MIT-BIH dataset for five distinct conditions of arrhythmias which are consistent with the AAMI EC57 protocols and on PTB diagnostics dataset for Myocardial Infarction (MI) classification. We achieved classification accuracy of 99.7% and 99.2% on arrhythmia and MI classification, respectively.

Zeeshan Ahmad, Suha Rabbani, Muhammad Rehman Zafar et al.

ECG is an attractive option to assess stress in serious Virtual Reality (VR) applications due to its non-invasive nature. However, the existing Machine Learning (ML) models perform poorly. Moreover, existing studies only perform a binary stress assessment, while to develop a more engaging biofeedback-based application, multi-level assessment is necessary. Existing studies annotate and classify a single experience (e.g. watching a VR video) to a single stress level, which again prevents design of dynamic experiences where real-time in-game stress assessment can be utilized. In this paper, we report our findings on a new study on VR stress assessment, where three stress levels are assessed. ECG data was collected from 9 users experiencing a VR roller coaster. The VR experience was then manually labeled in 10-seconds segments to three stress levels by three raters. We then propose a novel multimodal deep fusion model utilizing spectrogram and 1D ECG that can provide a stress prediction from just a 1-second window. Experimental results demonstrate that the proposed model outperforms the classical HRV-based ML models (9% increase in accuracy) and baseline deep learning models (2.5% increase in accuracy). We also report results on the benchmark WESAD dataset to show the supremacy of the model.

Zeeshan Ahmad, Anika Tabassum, Naimul Khan et al.

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. At the input of IFM, we first convert the heart beats of ECG into three different images using Gramian Angular Field (GAF), Recurrence Plot (RP) and Markov Transition Field (MTF) and then fuse these images to create a single imaging modality. We use AlexNet for feature extraction and classification and thus employ end to end deep learning. We perform experiments on PhysioNet MIT-BIH dataset for five different arrhythmias in accordance with the AAMI EC57 standard and on PTB diagnostics dataset for myocardial infarction (MI) classification. We achieved an state of an art results in terms of prediction accuracy, precision and recall.

Zeeshan Ahmad, Naimul Khan

Convolutional Neural Networks (CNNs) are successful deep learning models in the field of computer vision. 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. These four types of activity images are Signal Images (SI), Gramian Angular Field (GAF) Images, Markov Transition Field (MTF) Images and Recurrence Plot (RP) Images. Furthermore, for creating a multimodal fusion framework and to exploit activity image, we made each type of activity images multimodal by convolving with two spatial domain filters : Prewitt filter and High-boost filter. Resnet-18, a CNN model, is used to learn deep features from multi-modalities. Learned features are extracted from the last pooling layer of each ReNet and then fused by canonical correlation based fusion (CCF) for improving the accuracy of human action recognition. These highly informative features are served as input to a multiclass Support Vector Machine (SVM). Experimental results on three publicly available inertial datasets show the superiority of the proposed method over the current state-of-the-art.

Zeeshan Ahmad, Naimul khan

Convolutional Neural Network (CNN) provides leverage to extract and fuse features from all layers of its architecture. However, extracting and fusing intermediate features from different layers of CNN structure is still uninvestigated for Human Action Recognition (HAR) using depth and inertial sensors. To get maximum benefit of accessing all the CNN's layers, in this paper, we propose novel Multistage Gated Average Fusion (MGAF) network which extracts and fuses features from all layers of CNN using our novel and computationally efficient Gated Average Fusion (GAF) network, a decisive integral element of MGAF. At the input of the proposed MGAF, we transform the depth and inertial sensor data into depth images called sequential front view images (SFI) and signal images (SI) respectively. These SFI are formed from the front view information generated by depth data. CNN is employed to extract feature maps from both input modalities. GAF network fuses the extracted features effectively while preserving the dimensionality of fused feature as well. The proposed MGAF network has structural extensibility and can be unfolded to more than two modalities. 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. We increase the accuracy by an average of 1.5 percent while reducing the computational cost by approximately 50 percent over the previous state of the art.

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. In different domains these features are present with different scales and intensities. In existing literature, features are extracted independently in different domains, but the benefits from fusing these multidomain features are not realized. To address this challenge and to extract complete set of complementary information, in this paper, we propose a novel multidomain multimodal fusion framework that extracts complementary and distinct features from different domains of the input modality. We transform input inertial data into signal images, and then make the input modality multidomain and multimodal by transforming spatial domain information into frequency and time-spectrum domain using Discrete Fourier Transform (DFT) and Gabor wavelet transform (GWT) respectively. Features in different domains are extracted by Convolutional Neural networks (CNNs) and then fused by Canonical Correlation based Fusion (CCF) for improving the accuracy of human action recognition. Experimental results on three inertial datasets show the superiority of the proposed method when compared to the state-of-the-art.

Zeeshan Ahmad, Naimul Khan

This paper attempts at improving the accuracy of Human Action Recognition (HAR) by fusion of depth and inertial sensor data. Firstly, we transform the depth data into Sequential Front view Images(SFI) and fine-tune the pre-trained AlexNet on these images. Then, inertial data is converted into Signal Images (SI) and another convolutional neural network (CNN) is trained on these images. Finally, learned features are extracted from both CNN, fused together to make a shared feature layer, and these features are fed to the classifier. We experiment with two classifiers, namely Support Vector Machines (SVM) and softmax classifier and compare their performances. 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. Experimental results on UTD-MHAD and Kinect 2D datasets show that proposed method achieves state of the art results when compared to other recently proposed visual-inertial action recognition methods.

Zeeshan Ahmad, Naimul Khan

Stress analysis and assessment of affective states of mind using ECG as a physiological signal is a burning research topic in biomedical signal processing. However, existing literature provides only binary assessment of stress, while multiple levels of assessment may be more beneficial for healthcare applications. Furthermore, in present research, ECG signal for stress analysis is examined independently in spatial domain or in transform domains but the advantage of fusing these domains has not been fully utilized. 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. Moreover, We made signal images multimodal and multidomain by converting them into time-frequency and frequency domain using Gabor wavelet transform (GWT) and Discrete Fourier Transform (DFT) respectively. Convolutional Neural networks (CNNs) are used to extract features from different modalities and then decision level fusion is performed for improving the classification accuracy. The experimental results on an in-house dataset collected with 15 users show that with proposed fusion framework and using ECG signal to image conversion, we reach an average accuracy of 85.45%.

Victor Venturi, Holden Parks, Zeeshan Ahmad et al.

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. In this work, we alleviate this issue by extending and generalizing crystal graph convolutional neural networks to systems with planar periodicity, and train an ensemble of models to predict thermodynamic, mechanical, and electronic properties. To demonstrate the utility of this approach, we carry out a screening of nearly 45,000 structures for two largely disjoint applications: namely, mechanically robust composites and photovoltaics. An analysis of the uncertainty associated with our methods indicates the ensemble of neural networks is well-calibrated and has errors comparable with those from accurate first-principles density functional theory calculations. The ensemble of models allows us to gauge the confidence of our predictions, and to find the candidates most likely to exhibit effective performance in their applications. Since the datasets used in our screening were combinatorically generated, we are also able to investigate, using an innovative method, structural and compositional design principles that impact the properties of the structures surveyed and which can act as a generative model basis for future material discovery through reverse engineering. Our approach allowed us to recover some well-accepted design principles: for instance, we find that hybrid organic-inorganic perovskites with lead and tin tend to be good candidates for solar cell applications.

Mohammed Usman, Zeeshan Ahmad, Mohd Wajid

Heart rate is an important vital sign used in the diagnosis of many medical conditions. Conventionally, heart rate is measured using a medical device such as pulse oxymeter. Physiological parameters such as heart rate bear a correlation to speech characteristics of an individual. Hence, there is a possibility to measure heart rate from speech signals using machine learning and deep learning, which would also allow non-invasive, non contact based and remote monitoring of patients. However, to design such a scheme and verify its accuracy, it is necessary to collect speech recordings along with heart rates measured using a medical device, simultaneously during the recording. This article provides a dataset as well as the procedure used to create the dataset which could be used to facilitate research in developing techniques to estimate heart rate accurately by observing speech signal.

Zeeshan Ahmad, Naimul Khan

Multimodal fusion frameworks for Human Action Recognition (HAR) using depth and inertial sensor data have been proposed over the years. In most of the existing works, fusion is performed at a single level (feature level or decision level), missing the opportunity to fuse rich mid-level features necessary for better classification. To address this shortcoming, in this paper, we propose three novel deep multilevel multimodal fusion frameworks to capitalize on different fusion strategies at various stages and to leverage the superiority of multilevel fusion. At input, we transform the depth data into depth images called sequential front view images (SFIs) and inertial sensor data into signal images. Each input modality, depth and inertial, is further made multimodal by taking convolution with the Prewitt filter. Creating "modality within modality" enables further complementary and discriminative feature extraction through Convolutional Neural Networks (CNNs). CNNs are trained on input images of each modality to learn low-level, high-level and complex features. Learned features are extracted and fused at different stages of the proposed frameworks to combine discriminative and complementary information. These highly informative features are served as input to a multi-class Support Vector Machine (SVM). We evaluate the proposed frameworks on three publicly available multimodal HAR datasets, namely, UTD Multimodal Human Action Dataset (MHAD), Berkeley MHAD, and UTD-MHAD Kinect V2. Experimental results show the supremacy of the proposed fusion frameworks over existing methods.

Zeeshan Ahmad, Tian Xie, Chinmay Maheshwari et al.

Next generation batteries based on lithium (Li) metal anodes have been plagued by the dendritic electrodeposition of Li metal on the anode during cycling, resulting in short circuit and capacity loss. Suppression of dendritic growth through the use of solid electrolytes has emerged as one of the most promising strategies for enabling the use of Li metal anodes. We perform a computational screening of over 12,000 inorganic solids based on their ability to suppress dendrite initiation in contact with Li metal anode. Properties for mechanically isotropic and anisotropic interfaces that can be used in stability criteria for determining the propensity of dendrite initiation are usually obtained from computationally expensive first-principles methods. In order to obtain a large dataset for screening, we use machine learning models to predict the mechanical properties of several new solid electrolytes. We train a convolutional neural network on the shear and bulk moduli purely on structural features of the material. We use AdaBoost, Lasso and Bayesian ridge regression to train the elastic constants, where the choice of the model depended on the size of the training data and the noise that it can handle. Our models give us direct interpretability by revealing the dominant structural features affecting the elastic constants. The stiffness is found to increase with a decrease in volume per atom, increase in minimum anion-anion separation, and increase in sublattice (all but Li) packing fraction. Cross-validation/test performance suggests our models generalize well. We predict over 20 mechanically anisotropic interfaces between Li metal and 6 solid electrolytes which can be used to suppress dendrite growth. Our screened candidates are generally soft and highly anisotropic, and present opportunities for simultaneously obtaining dendrite suppression and high ionic conductivity in solid electrolytes.