arXiv subjects

Zeeshan Ahmad

Publications and source records attributed to Zeeshan Ahmad.

At least 37 records · Page 2Linked to original sources

arXiv2021

A Sequential Supervised Machine Learning Approach for Cyber Attack Detection in a Smart Grid System

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.

cs.CR↗

arXiv2021

ECG Heartbeat Classification Using Multimodal Fusion

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.

cs.LG↗

arXiv2021

Multi-level Stress Assessment from ECG in a Virtual Reality Environment using Multimodal Fusion

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.

cs.LG↗

arXiv2021

Extended frequency range of transverse-electric surface plasmon polaritons in graphene

The dispersion relation of surface plasmon polaritons in graphene that includes optical losses is often obtained for complex wave vectors while the frequencies are assumed to be real. This approach, however, is not suitable for describing the temporal dynamics of optical excitations and the spectral properties of graphene. Here, we propose an alternative approach that calculates the dispersion relation in the complex frequency and real wave vector space. This approach provides a clearer insight into the optical properties of a graphene layer and allows us to find the surface plasmon modes of a graphene sheet in the full frequency range, thus removing the earlier reported limitation (1.667 < $\hbarω/μ$ < 2) for the transverse-electric mode. We further develop a simple analytic approximation which accurately describes the dispersion of the surface plasmon polariton modes in graphene. Using this approximation, we show that transverse-electric surface plasmon polaritons propagate along the graphene sheet without losses even at finite temperature.

cond-mat.mes-hall↗

arXiv2021

Inertial Sensor Data To Image Encoding For Human Action Recognition

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.

cs.CV↗

arXiv2021

ECG Heart-beat Classification Using Multimodal Image Fusion

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.

eess.SP↗

arXiv2020

Interfacial Effects on Solid Electrolyte Interphase in Lithium-ion Batteries

The existence of passivating layers at the interfaces is a major factor enabling modern lithium-ion (Li-ion) batteries. Their properties determine the cycle life, performance, and safety of batteries. A special case is the solid electrolyte interphase (SEI), a heterogeneous multi-component film formed due to the instability and subsequent decomposition of the electrolyte at the surface of the anode. The SEI acts as a passivating layer that hinders further electrolyte disintegration, which is detrimental to the Coulombic efficiency. In this work, we use first-principles simulations to investigate the kinetic and electronic properties of the interface between lithium fluoride (LiF) and lithium carbonate (Li$_2$CO$_3$), two common SEI components present in Li-ion batteries with organic liquid electrolytes. We find a coherent interface between these components that restricts the strain in each of them to below 3%. We find that the interface causes a large increase in the formation energy of the Frenkel defect, generating Li vacancies in LiF and Li interstitials in Li$_2$CO$_3$ responsible for transport. On the other hand, the Li interstitial hopping barrier is reduced from $0.3$ eV in bulk Li$_2$CO$_3$ to $0.10$ or $0.22$ eV in the interfacial structure considered, demonstrating the favorable role of the interface. Controlling these two effects in a heterogeneous SEI is crucial for maintaining fast ion transport in the SEI. We further perform Car-Parrinello molecular dynamics simulations to explore Li ion conduction in our interfacial structure, which reveal an enhanced Li ion diffusion in the vicinity of the interface. Understanding the interfacial properties of the multiphase SEI represents an important frontier to enable next-generation batteries.

physics.chem-ph↗

arXiv2020

CNN based Multistage Gated Average Fusion (MGAF) for Human Action Recognition Using Depth and Inertial Sensors

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.

cs.CV↗

arXiv2020

Towards Improved Human Action Recognition Using Convolutional Neural Networks and Multimodal Fusion of Depth and Inertial Sensor Data

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.

cs.CV↗

arXiv2020

Multidomain Multimodal Fusion For Human Action Recognition Using Inertial Sensors

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.

cs.CV↗

arXiv2020

Multi-level Stress Assessment Using Multi-domain Fusion of ECG Signal

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%.

cs.CV↗

arXiv2020

Design rules for liquid crystalline electrolytes for enabling dendrite-free lithium metal batteries

Dendrite free electrodeposition of lithium metal is necessary for the adoption of high energy density rechargeable lithium metal batteries. Here, we demonstrate a new mechanism of using a liquid crystalline electrolyte to suppress dendrite growth with a lithium metal anode. A nematic liquid crystalline electrolyte modifies the kinetics of electrodeposition by introducing additional overpotential due to its bulk distortion and anchoring free energy. By extending the phase-field model, we simulate the morphological evolution of the metal anode and explore the role of bulk distortion and anchoring strengths on the electrodeposition process. We find that adsorption energy of liquid crystalline molecules on lithium surface can be a good descriptor for the anchoring energy and obtain it using first-principles density functional theory calculations. Unlike other extrinsic mechanisms, we find that liquid crystals with high anchoring strengths can ensure smooth electrodeposition of lithium metal, thus paving the way for practical applications in rechargeable batteries based on metal anodes.

physics.app-ph↗

arXiv2020

Machine Learning Enabled Discovery of Application Dependent Design Principles for Two-dimensional Materials

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.

cond-mat.mtrl-sci↗

arXiv2020

Dataset of raw and pre-processed speech signals, Mel Frequency Cepstral Coefficients of Speech and Heart Rate measurements

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.

eess.AS↗

arXiv2019

Human Action Recognition Using Deep Multilevel Multimodal (M2) Fusion of Depth and Inertial Sensors

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.

cs.LG↗

arXiv2019

Universal Chemomechanical Design Rules for Solid-Ion Conductors to Prevent Dendrite Formation in Lithium Metal Batteries

Dendrite formation during electrodeposition while charging lithium metal batteries compromises their safety. While high shear modulus solid-ion conductors (SICs) have been prioritized to resolve pressure-driven instabilities that lead to dendrite propagation and cell shorting, it is unclear whether these or alternatives are needed to guide uniform lithium electrodeposition, which is intrinsically density-driven. Here, we show that SICs can be designed within a universal chemomechanical paradigm to access either pressure-driven dendrite-blocking or density-driven dendrite-suppressing properties, but not both. This dichotomy reflects the competing influence of the SICs mechanical properties and partial molar volume of Li+ relative to those of the lithium anode on plating outcomes. Within this paradigm, we explore SICs in a previously unrecognized dendrite-suppressing regime that are concomitantly soft, as is typical of polymer electrolytes, but feature atypically low Li+ partial molar volume, more reminiscent of hard ceramics. Li plating mediated by these SICs is uniform, as revealed using synchrotron hard x-ray microtomography. As a result, cell cycle-life is extended, even when assembled with thin Li anodes and high-voltage NMC-622 cathodes, where 20 percent of the Li inventory is reversibly cycled.

cond-mat.mtrl-sci↗

arXiv2018

Machine Learning Enabled Computational Screening of Inorganic Solid Electrolytes for Dendrite Suppression with Li Metal Anode

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.

cond-mat.mtrl-sci↗

arXiv2017

Stability of Electrodeposition at Solid-Solid Interfaces and Implications for Metal Anodes

We generalize the conditions for stable electrodeposition at isotropic solid-solid interfaces using a kinetic model which incorporates the effects of stresses and surface tension at the interface. We develop a stability diagram that shows two regimes of stability: previously known pressure-driven mechanism and a new density-driven stability mechanism that is governed by the relative density of metal in the two phases. We show that inorganic solids and solid polymers generally do not lead to stable electrodeposition, and provide design guidelines for achieving stable electrodeposition.

cond-mat.mtrl-sci↗