Search

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., Comment: 31 pages, 14 figures

In the present work, we investigate the impact of finite volume on the in-medium properties of kaons ($K^+$, $K^0$) and antikaons ($K^-$, $\bar{K^0}$), and $\phi$ mesons in the isospin asymmetric strange hadronic medium at finite density and temperature. We use the chiral SU(3) hadronic mean-field model, which accounts for the interactions between baryons through the exchange of scalar ($\sigma, \zeta, \delta $) and vector ($\omega$, $\rho$, $\phi$) fields. To investigate the effects of finite volume, we apply the multiple reflection expansion (MRE) technique for calculations of the density of states. The non-strange scalar field $\sigma$ shows significant variation in an asymmetric medium, while the strange scalar field $\zeta$ shows good dependency in the strange medium. We use the medium-modified masses of kaons and antikaons calculated using the chiral SU(3) model to obtain the masses and decay width of $\phi$ mesons in finite volume hadronic medium. To obtain the masses and decay widths of $\phi$ mesons, an effective Lagrangian approach with $\phi$$K$$\bar{K}$ interactions at one-loop level is used in the present work. We obtain the effective masses and decay widths in the finite volume matter, for the spherical geometry of the medium with Neumann and Dirichlet boundary conditions as well as for the cubic geometry. The finite volume effects are found to be appreciable at high baryon densities., Comment: 40 pages and 13 figures

It is now widely recognized that surface and interfacial defects exhibit distinct behavior compared to bulk defects in metal halide perovskites. However, the transition from bulk to surface behavior and the spatial extent of the surface's influence are not well understood. To address this, we conducted first-principles calculations on iodine vacancies and interstitial defects in methylammonium lead iodide and cesium lead iodide at various depths from the surface, enabling us to map out depth-dependent behavior. We find that the defect formation energy follows a saturating exponential curve as the defect moves away from the surface to the bulk. Using first-principles calculated defect formation energies, we quantify the extent of the surface's influence by calculating the decay length associated with each defect. The difference between the surface and bulk defect formation energy is found to be as high as 1.12 eV for the negatively charged iodine vacancy in methylammonium lead iodide, leading to the enrichment of the surface with defects. Through analysis of defective structures, we find that the differences in the bulk and surface defect properties are a consequence of different bond lengths and in some cases, even changes in bonding and coordination environments. Finally, we determine how the defect transition levels change as a function of the layer index, which could contribute to increased non-radiative recombination. Our findings pave the way for a systematic treatment of non-radiative losses in perovskite solar cells that incorporate spatially dependent defect densities and transition levels., Comment: 28 pages + 10 pages of supporting information

Alkali metal anodes paired with solid ion conductors offer promising avenues for enhancing battery energy density and safety. To facilitate rapid ion transport crucial for fast charging and discharging, it is essential to understand point defects within these conductors. In this study, we investigate the heterogeneity of defect distribution in Li$_3$OCl solid ion conductor, quantifying the defect formation energy (DFE) of lithium vacancies and interstitials as a function of distance from the surface through first-principles simulations. Our results reveal that the surface DFE is consistently lower than bulk except for one surface termination, indicating significant defect aggregation at surfaces. This difference can cause the defect density to be up to 14 orders of magnitude higher at surfaces compared to the bulk. Moreover, we unveil the transition in DFE when moving from the surface to the bulk through the DFE function, which exhibits an exponentially decaying relationship. Incorporating this exponential trend, we develop a revised model for the average behavior of defects that offers a more accurate description of the influence of grain size. Surface effects dominate for grain sizes $\lesssim$ 1 $\mu$m, highlighting the importance of surface defect engineering and the DFE function for accurately capturing ion transport in devices. We further explore the kinetics of defect redistribution by calculating the migration barriers for defect movement between bulk and surfaces. We find a highly asymmetric energy landscape for the lithium vacancies, exhibiting lower migration barriers for movement towards the surface compared to the bulk, while interstitial defects exhibit comparable kinetics between surface and bulk regions. These insights underscore the importance of considering both thermodynamic and kinetic factors in the design of solid ion conductors., Comment: 29 pages of main text + 11 pages of Supporting Information; 8 figures and 2 tables

Transverse-electric (TE) surface plasmon polaritons are unique eigenmodes of a homogeneous graphene layer that are tunable with the chemical potential and temperature. However, as their dispersion curve spectrally lies just below the light line, they cannot be resonantly excited by an externally incident wave. Here, we propose a way of exciting the TE modes and tuning their peaks in the transmission by introducing a one-dimensional graphene grating. Using the scattering-matrix formalism, we show that periodic modulations of graphene make the transmission more pronounced, potentially allowing for experimental observation of the TE modes. Furthermore, we propose the use of turbostratic graphene to enhance the role of the surface plasmon polaritons in optical spectra., Comment: 15 pages, 13 figures

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.

V$_{2}$O$_{5}$ in its $\omega$ phase (Li$_{3}$V$_{2}$O$_{5}$) with excess lithium is a potential alternative to the graphite anode for lithium-ion batteries at low temperature and fast charging conditions due to its safer voltage (0.6 V vs Li$^{+}$/Li(s)) and high lithium transport rate. In-operando cationic disorder, as observed in most ordered materials, can produce significant changes in charge compensation mechanisms, anionic activity, lithium diffusion and operational voltages. In this work, we report the variation in structural distortion, electronic structure and migration barrier accompanied by disorder using first-principles calculations. Due to segregation of lithium atoms in the disordered state, we observe greater distortion, emergence of metallic behaviour and potential anionic activity from non-bonding oxygen states near the Fermi level. Redox capacity can be tuned by doping with 3d metals which can adjust the participating cationic states, and by fluorine substitution which can stabilize or suppress anionic states. Moreover, suppression of anionic activity is found to decrease structural distortion, crucial for mitigating voltage fade and hysteresis. Diffusion barrier calculations in the presence of disorder indicate the activation of the remaining 3D-paths for lithium hopping which are unavailable in the ordered configuration, explaining its fast-charging ability observed in experiments., Comment: 23 pages, 6 figures

The presence of unreacted lead iodide in organic-inorganic lead halide perovskite solar cells is widely correlated with an increase in power conversion efficiency. We investigate the mechanism for this increase by identifying the role of surfaces and interfaces present between methylammonium lead iodide perovskite films and excess lead iodide. We show how type I and II band alignments arising under different conditions result in either passivation of surface defects or hole injection. Through first-principles simulations of solid-solid interfaces, we find that lead iodide captures holes from methylammonium lead iodide and modulates the formation of defects in the perovskite, affecting recombination. Using surface-sensitive optical spectroscopy techniques, such as transient reflectance and time-resolved photoluminescence, we show how excess lead iodide affects the diffusion and surface recombination velocity of charge carriers in methylammonium lead iodide films. Our coupled experimental and theoretical results elucidate the role of excess lead iodide in perovskite solar cells., Comment: 4 figures, 1 table, 21 pages + 13 pages of Supporting Information

Solid electrolytes are widely considered as the enabler of lithium metal anodes for safe, durable, and high energy density rechargeable lithium-ion batteries. Despite the promise, failure mechanisms associated with solid-state batteries are not well-established, largely due to limited understanding of the chemomechanical factors governing them. We focus on the recent developments in understanding solid-state aspects including the effects of mechanical stresses, constitutive relations, fracture, and void formation, and outline the gaps in the literature. We also provide an overview of the manufacturing and processing of solid-state batteries in relation to chemomechanics. The gaps identified provide concrete directions towards the rational design and development of failure-resistant solid-state batteries., Comment: 49 pages, 10 figures

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., Comment: 6 pages, 7 figures, to be published in North Americal Power Systems (NAPS 2021) Conference

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.

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., Comment: Under review

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 < $\hbar\omega/\mu$ < 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., Comment: 13 pages, 7 figures

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.

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.

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., Comment: arXiv admin note: text overlap with arXiv:1910.11482

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., Comment: 24 + 6 + 1 pages, 7 figures, 6 pages of Supporting Information. v2: more detailed explanation of defective structure, added references etc

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.