Search

Deep learning models have demonstrated remarkable performance across various computer vision tasks, yet their vulnerability to distribution shifts remains a critical challenge. Despite sophisticated neural network architectures, existing models often struggle to maintain consistent performance when confronted with Out-of-Distribution (OOD) samples, including natural corruptions, adversarial perturbations, and anomalous patterns. We introduce LayerMix, an innovative data augmentation approach that systematically enhances model robustness through structured fractal-based image synthesis. By meticulously integrating structural complexity into training datasets, our method generates semantically consistent synthetic samples that significantly improve neural network generalization capabilities. Unlike traditional augmentation techniques that rely on random transformations, LayerMix employs a structured mixing pipeline that preserves original image semantics while introducing controlled variability. Extensive experiments across multiple benchmark datasets, including CIFAR-10, CIFAR-100, ImageNet-200, and ImageNet-1K demonstrate LayerMixs superior performance in classification accuracy and substantially enhances critical Machine Learning (ML) safety metrics, including resilience to natural image corruptions, robustness against adversarial attacks, improved model calibration and enhanced prediction consistency. LayerMix represents a significant advancement toward developing more reliable and adaptable artificial intelligence systems by addressing the fundamental challenges of deep learning generalization. The code is available at https://github.com/ahmadmughees/layermix.

The rapid growth of the Internet of Things (IoT) applications inflicts high requirements for computing resources and network bandwidth. A growing number of service providers are applying edge-cloud computing to improve the quality of their services. Deploying IoT applications to optimal computing nodes to minimize energy consumption and enhance system performance remains an open challenge. In this paper, we present an intelligent orchestration concept for breaking down IoT applications into granular microservices, called nanoservices, and deploying them in an energy-aware manner to optimal computing nodes in the edge-cloud continuum by applying resource and network slicing methods. With this consolidated slicing scheme, we can efficiently allocate network and compute resources to meet the needs of these nanoservices.

This survey provides an examination of the use of Deep Neural Networks (DNN) in Collaborative Filtering (CF) recommendation systems. As the digital world increasingly relies on data-driven approaches, traditional CF techniques face limitations in scalability and flexibility. DNNs can address these challenges by effectively modeling complex, non-linear relationships within the data. We begin by exploring the fundamental principles of both collaborative filtering and deep neural networks, laying the groundwork for understanding their integration. Subsequently, we review key advancements in the field, categorizing various deep learning models that enhance CF systems, including Multilayer Perceptrons (MLP), Convolutional Neural Networks (CNN), Recurrent Neural Networks (RNN), Graph Neural Networks (GNN), autoencoders, Generative Adversarial Networks (GAN), and Restricted Boltzmann Machines (RBM). The paper also discusses evaluation protocols, various publicly available auxiliary information, and data features. Furthermore, the survey concludes with a discussion of the challenges and future research opportunities in enhancing collaborative filtering systems with deep learning., Comment: 32 pages, 12 figures

In this study, we introduce Convolutional Transformer Neural Collaborative Filtering (CTNCF), a novel approach aimed at enhancing recommendation systems by effectively capturing high-order structural information in user-item interactions. CTNCF represents a significant advancement over the traditional Neural Collaborative Filtering (NCF) model by seamlessly integrating Convolutional Neural Networks (CNNs) and Transformer layers. This sophisticated integration enables the model to adeptly capture and understand complex interaction patterns inherent in recommendation systems. Specifically, CNNs are employed to extract local features from user and item embeddings, allowing the model to capture intricate spatial dependencies within the data. Furthermore, the utilization of Transformer layers enables the model to capture long-range dependencies and interactions among user and item features, thereby enhancing its ability to understand the underlying relationships in the data. To validate the effectiveness of our proposed CTNCF framework, we conduct extensive experiments on two real-world datasets. The results demonstrate that CTNCF significantly outperforms state-of-the-art approaches, highlighting its efficacy in improving recommendation system performance., Comment: 17 pages, 5 figures

In contrast to non-medical image denoising, where enhancing image clarity is the primary goal, medical image denoising warrants preservation of crucial features without introduction of new artifacts. However, many denoising methods that improve the clarity of the image, inadvertently alter critical information of the denoised images, potentially compromising classification performance and diagnostic quality. Additionally, supervised denoising methods are not very practical in medical image domain, since a \emph{ground truth} denoised version of a noisy medical image is often extremely challenging to obtain. In this paper, we tackle both of these problems by introducing a novel neural network based method -- \emph{Contextual Checkerboard Denoising}, that can learn denoising from only a dataset of noisy images, while preserving crucial anatomical details necessary for image classification/analysis. We perform our experimentation on real Optical Coherence Tomography (OCT) images, and empirically demonstrate that our proposed method significantly improves image quality, providing clearer and more detailed OCT images, while enhancing diagnostic accuracy., Comment: Under review in Springer Journal of Medical Systems. Code available: https://github.com/AbtahiMajeed/CheckerBoardDenoiser/tree/main

The production of silicon monoxide (SiO) can be considered as a fingerprint of shock interaction. In this work, we use high-sensitivity observations of the SiO (2-1) and H$^{13}$CO$^{+}$ (1-0) emission to investigate the broad and narrow SiO emission toward 146 massive star-forming regions in the ATOMS survey. We detected SiO emission in 136 regions and distinguished broad and narrow components across the extension of 118 sources (including 58 UC $H_{II}$ regions) with an average angular resolution of 2.5$^{\prime}$$^{\prime}$. The derived SiO luminosity ($L_{SiO}$) across the whole sample shows that the majority of $L_{SiO}$ (above 66$\%$) can be attributed to broad SiO, indicating its association with strong outflows. The comparison of the ALMA SiO images with the filamentary skeletons identified from H$^{13}$CO$^{+}$ and in the infrared data (at 4.5, 8, and 24 $mu$m), further confirms that most SiO emission originates from outflows. However, note that for nine sources in our sample, the observed SiO emission may be generated by expanding UC $H_{II}$ regions. There is a moderate positive correlation between the bolometric luminosity ($L_{bol}$) and $L_{SiO}$ for both components (narrow and broad). The UC $H_{II}$ sources show a weaker positive correlation between $L_{bol}$ and $L_{SiO}$ and higher $L_{SiO}$ compared to the sources without UC $H_{II}$ regions. These results imply that the SiO emission from UC $H_{II}$ sources might be affected by UV-photochemistry induced by UC $H_{II}$ regions., Comment: 23 pages, 14 figures

Rapid diagnostic tests are crucial for timely disease detection and management, yet accurate interpretation of test results remains challenging. In this study, we propose a novel approach to enhance the accuracy and reliability of rapid diagnostic test result interpretation by integrating artificial intelligence (AI) algorithms, including convolutional neural networks (CNN), within a smartphone-based application. The app enables users to take pictures of their test kits, which YOLOv8 then processes to precisely crop and extract the membrane region, even if the test kit is not centered in the frame or is positioned at the very edge of the image. This capability offers greater accessibility, allowing even visually impaired individuals to capture test images without needing perfect alignment, thus promoting user independence and inclusivity. The extracted image is analyzed by an additional CNN classifier that determines if the results are positive, negative, or invalid, providing users with the results and a confidence level. Through validation experiments with commonly used rapid test kits across various diagnostic applications, our results demonstrate that the synergistic integration of AI significantly improves sensitivity and specificity in test result interpretation. This improvement can be attributed to the extraction of the membrane zones from the test kit images using the state-of-the-art YOLO algorithm. Additionally, we performed SHapley Additive exPlanations (SHAP) analysis to investigate the factors influencing the model's decisions, identifying reasons behind both correct and incorrect classifications. By facilitating the differentiation of genuine test lines from background noise and providing valuable insights into test line intensity and uniformity, our approach offers a robust solution to challenges in rapid test interpretation.

In recent years, the growth of data across various sectors, including healthcare, security, finance, and education, has created significant opportunities for analysis and informed decision-making. However, these datasets often contain sensitive and personal information, which raises serious privacy concerns. Protecting individual privacy is crucial, yet many existing machine learning and data publishing algorithms struggle with high-dimensional data, facing challenges related to computational efficiency and privacy preservation. To address these challenges, we introduce an effective data publishing algorithm \emph{DP-CDA}. Our proposed algorithm generates synthetic datasets by randomly mixing data in a class-specific manner, and inducing carefully-tuned randomness to ensure formal privacy guarantees. Our comprehensive privacy accounting shows that DP-CDA provides a stronger privacy guarantee compared to existing methods, allowing for better utility while maintaining strict level of privacy. To evaluate the effectiveness of DP-CDA, we examine the accuracy of predictive models trained on the synthetic data, which serves as a measure of dataset utility. Importantly, we identify an optimal order of mixing that balances privacy guarantee with predictive accuracy. Our results indicate that synthetic datasets produced using the DP-CDA can achieve superior utility compared to those generated by traditional data publishing algorithms, even when subject to the same privacy requirements., Comment: Under review in Elsevier Array

Phishing is one of the most effective ways in which cybercriminals get sensitive details such as credentials for online banking, digital wallets, state secrets, and many more from potential victims. They do this by spamming users with malicious URLs with the sole purpose of tricking them into divulging sensitive information which is later used for various cybercrimes. In this research, we did a comprehensive review of current state-of-the-art machine learning and deep learning phishing detection techniques to expose their vulnerabilities and future research direction. For better analysis and observation, we split machine learning techniques into Bayesian, non-Bayesian, and deep learning. We reviewed the most recent advances in Bayesian and non-Bayesian-based classifiers before exploiting their corresponding weaknesses to indicate future research direction. While exploiting weaknesses in both Bayesian and non-Bayesian classifiers, we also compared each performance with a deep learning classifier. For a proper review of deep learning-based classifiers, we looked at Recurrent Neural Networks (RNN), Convolutional Neural Networks (CNN), and Long Short Term Memory Networks (LSTMs). We did an empirical analysis to evaluate the performance of each classifier along with many of the proposed state-of-the-art anti-phishing techniques to identify future research directions, we also made a series of proposals on how the performance of the under-performing algorithm can improved in addition to a two-stage prediction model

The rapid spread of misinformation, particularly through online platforms, underscores the urgent need for reliable detection systems. This study explores the utilization of machine learning and natural language processing, specifically Support Vector Machines (SVM) and BERT, to detect news that are fake. We employ three distinct text vectorization methods for SVM: Term Frequency Inverse Document Frequency (TF-IDF), Word2Vec, and Bag of Words (BoW) evaluating their effectiveness in distinguishing between genuine and fake news. Additionally, we compare these methods against the transformer large language model, BERT. Our comprehensive approach includes detailed preprocessing steps, rigorous model implementation, and thorough evaluation to determine the most effective techniques. The results demonstrate that while BERT achieves superior accuracy with 99.98% and an F1-score of 0.9998, the SVM model with a linear kernel and BoW vectorization also performs exceptionally well, achieving 99.81% accuracy and an F1-score of 0.9980. These findings highlight that, despite BERT's superior performance, SVM models with BoW and TF-IDF vectorization methods come remarkably close, offering highly competitive performance with the advantage of lower computational requirements., Comment: 6 pages, 3 tables and 6 Figures. Submitted to a conference

This paper extends a previous model for p-i-n GaAs quantum dot solar cells (QDSC) by revising the equation of photocarrier generation rate in quantum dots (QDs) inside the intrinsic region. In our model, we address a notable discrepancy that arose from the previous model where they did not consider the volume of QDs within the intrinsic region, leading to an overestimation of the photocarrier generation rate. Our present model rectifies this by incorporating the volume of quantum dots, resulting in adjustments to the photocarrier generation rate. Additionally, we determine the absorption coefficient of the QDs based on Mie theory for different diameter sizes considering the constant volume fraction of the total number of QDs in the intrinsic region. We observe in our analysis that the absorption spectra of the QDs and host material may overlap in certain cases, although the previous model assumed no overlap. This finding suggests the need for caution when evaluating spectral overlap: if the spectra do not overlap, both the previous and current modified models can be reliably applied. However, in cases of overlap, careful consideration is required to ensure accurate predictions of photocarrier generation. Furthermore, investigating the effect of QD diameter size on the photocarrier generation rate in the intrinsic region, we find that smaller QD sizes result in a higher absorption coefficient as well as a higher generation rate for a constant volume of QDs in the region. Moreover, we establish the optimization of the QDs array size by varying the size and the total volume of QDs to improve the generation rate. Our analysis reveals that a higher volume of QDs and a smaller size of QDs result in the maximum generation rate. From an experimental perspective, we propose that the optimal arrangement of QDs in such solar cells is a 0.5 volume fraction with a QD diameter of 2 nm., Comment: 22 pages, 6 figures

This research work delves into the manifestation of hallucination within Large Language Models (LLMs) and its consequential impacts on applications within the domain of mental health. The primary objective is to discern effective strategies for curtailing hallucinatory occurrences, thereby bolstering the dependability and security of LLMs in facilitating mental health interventions such as therapy, counseling, and the dissemination of pertinent information. Through rigorous investigation and analysis, this study seeks to elucidate the underlying mechanisms precipitating hallucinations in LLMs and subsequently propose targeted interventions to alleviate their occurrence. By addressing this critical issue, the research endeavors to foster a more robust framework for the utilization of LLMs within mental health contexts, ensuring their efficacy and reliability in aiding therapeutic processes and delivering accurate information to individuals seeking mental health support.

This study aims to review recent research on the collective behaviour of excitatory and inhibitory (E-I) spiking neural networks. The research methodology used is Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA) procedures, comprising three primary stages: an initial search for literature in the SCOPUS database, a screening process based on specific inclusion and exclusion criteria, and a review of the selected literatures. Out of 491 documents from 2014 to 2024, 6 research papers are qualified for review. Four distinct dynamical states have been identified: synchrony, irregular behaviour, stationary state, and oscillatory dynamics. Our review findings suggest that the collective dynamics of E-I spiking neurons stem from the interaction of intrinsic neuronal characteristics, balance mechanisms, and the type of external stimuli. Additionally, the widespread use of Quadratic Integrate-and-Fire (QIF) neurons in the literature highlights its significance as a robust candidate for exploring collective behaviours in large-scale neuronal networks., Comment: 8 pages, 3 figures, 2 tables

This work focuses on the efficiency of the knowledge distillation approach in generating a lightweight yet powerful BERT based model for natural language processing applications. After the model creation, we applied the resulting model, LastBERT, to a real-world task classifying severity levels of Attention Deficit Hyperactivity Disorder (ADHD)-related concerns from social media text data. Referring to LastBERT, a customized student BERT model, we significantly lowered model parameters from 110 million BERT base to 29 million, resulting in a model approximately 73.64% smaller. On the GLUE benchmark, comprising paraphrase identification, sentiment analysis, and text classification, the student model maintained strong performance across many tasks despite this reduction. The model was also used on a real-world ADHD dataset with an accuracy and F1 score of 85%. When compared to DistilBERT (66M) and ClinicalBERT (110M), LastBERT demonstrated comparable performance, with DistilBERT slightly outperforming it at 87%, and ClinicalBERT achieving 86% across the same metrics. These findings highlight the LastBERT model's capacity to classify degrees of ADHD severity properly, so it offers a useful tool for mental health professionals to assess and comprehend material produced by users on social networking platforms. The study emphasizes the possibilities of knowledge distillation to produce effective models fit for use in resource-limited conditions, hence advancing NLP and mental health diagnosis. Furthermore underlined by the considerable decrease in model size without appreciable performance loss is the lower computational resources needed for training and deployment, hence facilitating greater applicability. Especially using readily available computational tools like Google Colab. This study shows the accessibility and usefulness of advanced NLP methods in pragmatic world applications., Comment: 20 figures, 31 pages, review 1 from plos one journal

The present study proposes a new index to quantify the severity of non-stationary power quality (PQ) disturbance events. In particular, the severity of PQ events is estimated from their energy distribution in temporal-frequency space. The index essentially measures the $\ell_p$-norm between the energy distributions of an event and the nominal voltage signal. The efficacy of the new index is demonstrated considering a wide class of major non-stationary PQ events, including sag, swell, interruptions, oscillatory transients, and simultaneous events. The results of this investigation, with simulated, real and experimental data, convincingly demonstrate that the proposed index is generic, monotonic, easy to interpret, and can accurately quantify the severity of non-stationary events., Comment: 15 pages

We are developing a single-ion optical clock based on a surface-electrode (SE) trap that we will operate with $^{171}$Yb$^+$ ions on the electric quadrupole transition at 435.5 nm. We present heating rate measurements performed with a prototype SE trap. We also introduce a new, micro-fabricated SE trapping chip using silicon on insulator technology. Electric tests were performed under ultra-high vacuum using a testing chip, including breakdown voltages measurements and flashover detection. We present suitable trapping parameters for this chip, as well as a road-map for improving its design., Comment: 10 pages, 6 figures

Embeddings are now used to underpin a wide variety of data management tasks, including entity resolution, dataset search and semantic type detection. Such applications often involve datasets with numerical columns, but there has been more emphasis placed on the semantics of categorical data in embeddings than on the distinctive features of numerical data. In this paper, we propose a method called Gem (Gaussian mixture model embeddings) that creates embeddings that build on numerical value distributions from columns. The proposed method specializes a Gaussian Mixture Model (GMM) to identify and cluster columns with similar value distributions. We introduce a signature mechanism that generates a probability matrix for each column, indicating its likelihood of belonging to specific Gaussian components, which can be used for different applications, such as to determine semantic types. Finally, we generate embeddings for three numerical data properties: distributional, statistical, and contextual. Our core method focuses solely on numerical columns without using table names or neighboring columns for context. However, the method can be combined with other types of evidence, and we later integrate attribute names with the Gaussian embeddings to evaluate the method's contribution to improving overall performance. We compare Gem with several baseline methods for numeric only and numeric + context tasks, showing that Gem consistently outperforms the baselines on four benchmark datasets.

Recent text-to-speech (TTS) developments have made voice cloning (VC) more realistic, affordable, and easily accessible. This has given rise to many potential abuses of this technology, including Joe Biden's New Hampshire deepfake robocall. Several methodologies have been proposed to detect such clones. However, these methodologies have been trained and evaluated on relatively clean databases. Recently, ASVspoof 5 Challenge introduced a new crowd-sourced database of diverse acoustic conditions including various spoofing attacks and codec conditions. This paper is our submission to the ASVspoof 5 Challenge and aims to investigate the performance of Audio Spoof Detection, trained using data augmentation through laundering attacks, on the ASVSpoof 5 database. The results demonstrate that our system performs worst on A18, A19, A20, A26, and A30 spoofing attacks and in the codec and compression conditions of C08, C09, and C10.

Hub-filament systems are considered as natural sites for high-mass star formation. Kinematic analysis of the surroundings of hub-filaments is essential to better understand high-mass star formation within such systems. In this work, we present a detailed study of the massive Galactic protocluster IRAS 15394$-$5358, using continuum and molecular line data from the ALMA Three-millimeter Observations of Massive Star-forming Regions (ATOMS) survey. The 3~mm dust continuum map reveals the fragmentation of the massive ($\rm M=843~M_{\odot}$) clump into six cores. The core C-1A is the largest (radius = 0.04~pc), the most massive ($\rm M=157~M_{\odot}$), and lies within the dense central region, along with two smaller cores ($\rm M=7~and~3~M_{\odot}$). The fragmentation process is consistent with the thermal Jeans fragmentation mechanism and virial analysis shows that all the cores have small virial parameter values ($\rm \alpha_{vir}<<2$), suggesting that the cores are gravitationally bound. The mass vs. radius relation indicates that three cores can potentially form at least a single massive star. The integrated intensity map of $\rm H^{13}CO^{+}$ shows that the massive clump is associated with a hub-filament system, where the central hub is linked with four filaments. A sharp velocity gradient is observed towards the hub, suggesting a global collapse where the filaments are actively feeding the hub. We discuss the role of global collapse and the possible driving mechanisms for the massive star formation activity in the protocluster., Comment: 23 pages, 19 figures, accepted for publication in MNRAS

Pakistan was hit by the world's deadliest flood in June 2022, causing agriculture and infrastructure damage across the country. Remote sensing technology offers a cost-effective and efficient method for flood impact assessment. This study is aimed to assess the impact of flooding on crops and built-up areas. Landsat 9 imagery, European Space Agency-Land Use/Land Cover (ESA-LULC) and Soil Moisture Active Passive (SMAP) data are used to identify and quantify the extent of flood-affected areas, crop damage, and built-up area destruction. The findings indicate that Sindh, a province in Pakistan, suffered the most. This impact destroyed most Kharif season crops, typically cultivated from March to November. Using the SMAP satellite data, it is assessed that the high amount of soil moisture after flood also caused a significant delay in the cultivation of Rabi crops. The findings of this study provide valuable information for decision-makers and stakeholders involved in flood risk management and disaster response., Comment: AAAI Symposium 2024

Primary healthcare is a crucial strategy for achieving universal health coverage. South Asian countries are working to improve their primary healthcare system through their country specific policies designed in line with WHO health system framework using the six thematic pillars: Health Financing, Health Service delivery, Human Resource for Health, Health Information Systems, Governance, Essential Medicines and Technology, and an addition area of Cross-Sectoral Linkages. Measuring the current accessibility of healthcare facilities and workforce availability is essential for improving healthcare standards and achieving universal health coverage in developing countries. Data-driven surveillance approaches are required that can provide rapid, reliable, and geographically scalable solutions to understand a) which communities and areas are most at risk of inequitable access and when, b) what barriers to health access exist, and c) how they can be overcome in ways tailored to the specific challenges faced by individual communities. We propose to harness current breakthroughs in Earth-observation (EO) technology, which provide the ability to generate accurate, up-to-date, publicly accessible, and reliable data, which is necessary for equitable access planning and resource allocation to ensure that vaccines, and other interventions reach everyone, particularly those in greatest need, during normal and crisis times. This requires collaboration among countries to identify evidence based solutions to shape health policy and interventions, and drive innovations and research in the region.

In this paper, we present a novel approach to the development and deployment of an autonomous mosquito breeding place detector rover with the object and obstacle detection capabilities to control mosquitoes. Mosquito-borne diseases continue to pose significant health threats globally, with conventional control methods proving slow and inefficient. Amidst rising concerns over the rapid spread of these diseases, there is an urgent need for innovative and efficient strategies to manage mosquito populations and prevent disease transmission. To mitigate the limitations of manual labor and traditional methods, our rover employs autonomous control strategies. Leveraging our own custom dataset, the rover can autonomously navigate along a pre-defined path, identifying and mitigating potential breeding grounds with precision. It then proceeds to eliminate these breeding grounds by spraying a chemical agent, effectively eradicating mosquito habitats. Our project demonstrates the effectiveness that is absent in traditional ways of controlling and safeguarding public health. The code for this project is available on GitHub at - https://github.com/faiyazabdullah/MosquitoMiner, Comment: Accepted - 2024 IEEE Region 10 Symposium (TENSYMP 2024)

This paper presents a cascaded control architecture, based on nonlinear dynamic inversion (NDI), for rigid body attitude control. The proposed controller works directly with the rotation matrix parameterization, that is, with elements of the Special Orthogonal Group $\mathsf{SO(3)}$, and avoids problems related to singularities and non-uniqueness which affect other commonly used attitude representations such as Euler angles, unit quaternions, modified Rodrigues parameters, etc. The proposed NDI-based controller is capable of imposing desired linear dynamics of any order for the outer attitude loop and the inner rate loop, and gives control designers the flexibility to choose higher-order dynamic compensators in both loops. In addition, sufficient conditions are presented in the form of linear matrix inequalities (LMIs) which ensure that the outer loop controller renders the attitude loop almost globally asymptotically stable (AGAS) and the rate loop globally asymptotically stable (GAS). Furthermore, the overall cascaded control architecture is shown to be AGAS in the case of attitude error regulation. Lastly, the proposed scheme is compared with an Euler angles-based NDI scheme from literature for a tracking problem involving agile maneuvering of a multicopter in a high-fidelity nonlinear simulation., Comment: 7 pages, 6 figures, accepted in IEEE Conference on Decision and Control (CDC), 2024

Data-driven technologies have improved the efficiency, reliability and effectiveness of healthcare services, but come with an increasing demand for data, which is challenging due to privacy-related constraints on sharing data in healthcare contexts. Synthetic data has recently gained popularity as potential solution, but in the flurry of current research it can be hard to oversee its potential. This paper proposes a novel taxonomy of synthetic data in healthcare to navigate the landscape in terms of three main varieties. Data Proportion comprises different ratios of synthetic data in a dataset and associated pros and cons. Data Modality refers to the different data formats amenable to synthesis and format-specific challenges. Data Transformation concerns improving specific aspects of a dataset like its utility or privacy with synthetic data. Our taxonomy aims to help researchers in the healthcare domain interested in synthetic data to grasp what types of datasets, data modalities, and transformations are possible with synthetic data, and where the challenges and overlaps between the varieties lie., Comment: Accepted at the 23rd EFMI Special Topic Conference, Romania, November 2024

Voice-cloning (VC) systems have seen an exceptional increase in the realism of synthesized speech in recent years. The high quality of synthesized speech and the availability of low-cost VC services have given rise to many potential abuses of this technology. Several detection methodologies have been proposed over the years that can detect voice spoofs with reasonably good accuracy. However, these methodologies are mostly evaluated on clean audio databases, such as ASVSpoof 2019. This paper evaluates SOTA Audio Spoof Detection approaches in the presence of laundering attacks. In that regard, a new laundering attack database, called the ASVSpoof Laundering Database, is created. This database is based on the ASVSpoof 2019 (LA) eval database comprising a total of 1388.22 hours of audio recordings. Seven SOTA audio spoof detection approaches are evaluated on this laundered database. The results indicate that SOTA systems perform poorly in the presence of aggressive laundering attacks, especially reverberation and additive noise attacks. This suggests the need for robust audio spoof detection., Comment: Conference Paper

Deep Learning Architectures employ heavy computations and bulk of the computational energy is taken up by the convolution operations in the Convolutional Neural Networks. The objective of our proposed work is to reduce the energy consumption and size of CNN for using machine learning techniques in edge computing on ubiquitous computing devices. We propose Systematic Quality Scalable Design Methodology consisting of Quality Scalable Quantization on a higher abstraction level and Quality Scalable Multipliers at lower abstraction level. The first component consists of parameter compression where we approximate representation of values in filters of deep learning models by encoding in 3 bits. A shift and scale based on-chip decoding hardware is proposed which can decode these 3-bit representations to recover approximate filter values. The size of the DNN model is reduced this way and can be sent over a communication channel to be decoded on the edge computing devices. This way power is reduced by limiting data bits by approximation. In the second component we propose a quality scalable multiplier which reduces the number of partial products by converting numbers in canonic sign digit representations and further approximating the number by reducing least significant bits. These quantized CNNs provide almost same ac-curacy as network with original weights with little or no fine-tuning. The hardware for the adaptive multipliers utilize gate clocking for reducing energy consumption during multiplications. The proposed methodology greatly reduces the memory and power requirements of DNN models making it a feasible approach to deploy Deep Learning on edge computing. The experiments done on LeNet and ConvNets show an increase upto 6% of zeros and memory savings upto 82.4919% while keeping the accuracy near the state of the art.

Workplace accidents continue to pose significant risks for human safety, particularly in industries such as construction and manufacturing, and the necessity for effective Personal Protective Equipment (PPE) compliance has become increasingly paramount. Our research focuses on the development of non-invasive techniques based on the Object Detection (OD) and Convolutional Neural Network (CNN) to detect and verify the proper use of various types of PPE such as helmets, safety glasses, masks, and protective clothing. This study proposes the SH17 Dataset, consisting of 8,099 annotated images containing 75,994 instances of 17 classes collected from diverse industrial environments, to train and validate the OD models. We have trained state-of-the-art OD models for benchmarking, and initial results demonstrate promising accuracy levels with You Only Look Once (YOLO)v9-e model variant exceeding 70.9% in PPE detection. The performance of the model validation on cross-domain datasets suggests that integrating these technologies can significantly improve safety management systems, providing a scalable and efficient solution for industries striving to meet human safety regulations and protect their workforce. The dataset is available at https://github.com/ahmadmughees/sh17dataset.

Excitons in monolayer transition metal dichalcogenides (TMDCs) offer intriguing new possibilities for optoelectronics with no analogues in bulk semiconductors. Yet, intrinsic defects in TMDCs limit the radiative exciton recombination pathways. As a result, the photoluminescence (PL) quantum yield (QY) is limited. Methods like superacid treatment, electrical doping, and plasmonic engineering can inhibit nonradiative decay channels and enhance PL. Here, we show a more straightforward approach that allows PL enhancement. An engineered vertical van der Waals (vdW) metal-monolayer semiconductor junction (MSJ) results in PL enhancement of more than an order of magnitude at technologically relevant excitation powers. Such MSJ can be constructed by vertically stacking metals with suitable work function either above or below a monolayer semiconducting TMDC. Our experiments reveal that the underlying PL enhancement mechanism is to be the suppressed exciton quenching due to the absence of metal-induced gap states and weak Fermi level pinning, thanks to the vdW gapped interface between the metal and the TMDC. Our time-resolved PL measurements further indicate that reduced exciton-exciton annihilation, even at high generation rates, contributes to the observed PL enhancement. The PL intensity is further increased by the proximity of surface plasmons in the metal with the TMDC layer. Our findings shed light on the interaction at vdW metal-semiconductor interfaces and offer a path to improving the optoelectronic performance of semiconducting TMDCs.

Deep clustering (DC), a fusion of deep representation learning and clustering, has recently demonstrated positive results in data science, particularly text processing and computer vision. However, joint optimization of feature learning and data distribution in the multi-dimensional space is domain-specific, so existing DC methods struggle to generalize to other application domains (such as data integration and cleaning). In data management tasks, where high-density embeddings and overlapping clusters dominate, a data management-specific DC algorithm should be able to interact better with the data properties for supporting data cleaning and integration tasks. This paper presents a deep clustering algorithm for tabular data (TableDC) that reflects the properties of data management applications, particularly schema inference, entity resolution, and domain discovery. To address overlapping clusters, TableDC integrates Mahalanobis distance, which considers variance and correlation within the data, offering a similarity method suitable for tables, rows, or columns in high-dimensional latent spaces. TableDC provides flexibility for the final clustering assignment and shows higher tolerance to outliers through its heavy-tailed Cauchy distribution as the similarity kernel. The proposed similarity measure is particularly beneficial where the embeddings of raw data are densely packed and exhibit high degrees of overlap. Data cleaning tasks may involve a large number of clusters, which affects the scalability of existing DC methods. TableDC's self-supervised module efficiently learns data embeddings with a large number of clusters compared to existing benchmarks, which scale in quadratic time. We evaluated TableDC with several existing DC, Standard Clustering (SC), and state-of-the-art bespoke methods over benchmark datasets. TableDC consistently outperforms existing DC, SC, and bespoke methods.

This paper explores the concept of multiset dimensions (Mdim) of compressed zero-divisor graphs (CZDG) associated with rings. The authors investigate the interplay between the ring-theoretic properties of a ring $R$ and the associated compressed zero-divisor graph. An undirected graph consisting of a vertex set $ Z(R_E)\backslash\{[0]\} = R_E\backslash\{[0],[1]\}$, where $R_E=\{[x] : x\in R\} $ and $[x]=\{y\in R : \text{ann}(x)=\text{ann}(y)\}$ is called a compressed zero-divisor graph, denoted by $\Gamma_E (R)$. An edge is formed between two vertices $[x]$ and $[y]$ of $Z(R_E)$ if and only if $[x][y]=[xy]=[0]$, that is, iff $xy=0$. For a ring $R$, graph $G$ is said to be realizable as $\Gamma_E (R) $ if $G$ is isomorphic to $\Gamma_E (R)$. We classify the rings based on Mdim of their associated CZDG and obtain the bounds for the Mdim of the compressed zero-divisor graphs. We also study the Mdim of realizable graphs of rings. Moreover, some examples are provided to support our results. Lately, we have discussed the interconnection between Mdim, girth, and diameter of CZDG., Comment: arXiv admin note: substantial text overlap with arXiv:2405.04934

This article investigates multiset dimensions in zero divisor graphs (ZD-graphs) associated with rings. Through rigorous analysis, we establish general bounds for the multiset dimension (Mdim) in ZD-graphs, exploring various commutative rings including the ring Z_n of integers modulo n, Gaussian integers and quotient polynomial rings. Additionally, we examine the behavior of Mdim under algebraic operations and discuss bounds in terms of diameter and maximum degree. This study enhances our understanding of algebraic structures and their graphical representations.

The paper systematically classifies rings based on the dominant metric dimensions (Ddim) of their associated CZDG, establishing consequential bounds for the Ddim of these compressed zero-divisor graphs. The authors investigate the interplay between the ring-theoretic properties of a ring ( R ) and associated CZDG. An undirected graph consisting of vertex set ( Z(R_E)\{[0]}\ =\ R_E\{[0],[1]}), where ( R_E=\{[x]:\ x\in R\} ) and ([x]=\{y\in R:\ \text{ann}(x)=\text{ann}(y)\} ) is called a compressed zero-divisor graph, denoted by ( \Gamma_E(R) ). An edge is formed between two vertices ([x]) and ([y]) of ( Z(R_E) ) if and only if ([x][y]=[xy]=[0]), that is, iff ( xy=0 ). For a ring ( R ), graph ( G ) is said to be realizable as ( \Gamma_E(R) ) if ( G ) is isomorphic to ( \Gamma_E(R) ). Moreover, an exploration into the Ddim of realizable graphs for rings is conducted, complemented by illustrative examples reinforcing the presented results. A recent discussion within the paper elucidates the nuanced relationship between Ddim, diameter, and girth within the domain of compressed zero-divisor graphs. This research offers a comprehensive and insightful analysis at the intersection of algebraic structures and graph theory, providing valuable contributions to the current mathematical discourse., Comment: 13

Open-source simulation tools play a crucial role for neuromorphic application engineers and hardware architects to investigate performance bottlenecks and explore design optimizations before committing to silicon. Reconfigurable Architecture for Neuromorphic Computing (RANC) is one such tool that offers ability to execute pre-trained Spiking Neural Network (SNN) models within a unified ecosystem through both software-based simulation and FPGA-based emulation. RANC has been utilized by the community with its flexible and highly parameterized design to study implementation bottlenecks, tune architectural parameters or modify neuron behavior based on application insights and study the trade space on hardware performance and network accuracy. In designing architectures for use in neuromorphic computing, there are an incredibly large number of configuration parameters such as number and precision of weights per neuron, neuron and axon counts per core, network topology, and neuron behavior. To accelerate such studies and provide users with a streamlined productive design space exploration, in this paper we introduce the GPU-based implementation of RANC. We summarize our parallelization approach and quantify the speedup gains achieved with GPU-based tick-accurate simulations across various use cases. We demonstrate up to 780 times speedup compared to serial version of the RANC simulator based on a 512 neuromorphic core MNIST inference application. We believe that the RANC ecosystem now provides a much more feasible avenue in the research of exploring different optimizations for accelerating SNNs and performing richer studies by enabling rapid convergence to optimized neuromorphic architectures., Comment: Accepted for publication in Neuro-Inspired Computational Elements (NICE) Workshop 2024

Stability and precision of atomic devices are closely tied to the quality and stability of the internal atmosphere of the atomic vapor cells on which they rely. Such atmosphere can be stabilized by building the cell with low permeation materials such as sapphire, or aluminosilicate glass in microfabricated devices. Recently, we showed that permeation barriers made of Al$_{2}$O$_{3}$ thin-film coatings deposited on standard borosilicate glass could be an alternative for buffer gas pressure stabilization. In this study, we hence investigate how helium permeation is influenced by the thickness, ranging from 5 to 40 nm, of such Al$_{2}$O$_{3}$ thin-films coated by atomic layer deposition. Permeation rates are derived from long-term measurements of the pressure-shifted transition frequency of a coherent population trapping (CPT) atomic clock. From thicknesses of 20 nm onward, a significant enhancement of the cell hermeticity is experienced, corresponding to two orders of magnitude lower helium permeation rate. In addition, we test cesium vapor cells filled with neon as a buffer gas and whose windows are coated with 20 nm of Al$_{2}$O$_{3}$. As for helium, the permeation rate of neon is significantly reduced thanks to alumina coatings, leading to a fractional frequency stability of 4x10$^{-12}$ at 1 day when the cell is used in a CPT clock. These features outperform the typical performances of uncoated Cs-Ne borosilicate cells and highlight the significance of Al$_{2}$O$_{3}$ coatings for buffer gas pressure stabilization., Comment: 6 pages, 4 figures

In this paper, we present an integrated approach to real-time mosquito detection using our multiclass dataset (MosquitoFusion) containing 1204 diverse images and leverage cutting-edge technologies, specifically computer vision, to automate the identification of Mosquitoes, Swarms, and Breeding Sites. The pre-trained YOLOv8 model, trained on this dataset, achieved a mean Average Precision (mAP@50) of 57.1%, with precision at 73.4% and recall at 50.5%. The integration of Geographic Information Systems (GIS) further enriches the depth of our analysis, providing valuable insights into spatial patterns. The dataset and code are available at https://github.com/faiyazabdullah/MosquitoFusion.

Private information retrieval (PIR), a privacy-preserving cryptographic tool, solves a simplified version of this problem by hiding the database item that a client accesses. Most PIR protocols require the client to know the exact row index of the intended database item, which cannot support the complicated aggregation-based statistical query in a similar setting. Some works in the PIR space contain keyword searching and SQL-like queries, but most need multiple interactions between the PIR client and PIR servers. Some schemes support searching SQL-like expressive queries in a single round but fail to enable aggregate queries. These schemes are the main focus of this paper. To bridge the gap, we have built a general-purpose novel information-theoretic PIR (IT-PIR) framework that permits a user to fetch the aggregated result, hiding all sensitive sections of the complex query from the hosting PIR server in a single round of interaction. In other words, the server will not know which records contribute to the aggregation. We then evaluate the feasibility of our protocol for both benchmarking and real-world application settings. For instance, in a complex aggregate query to the Twitter microblogging database of 1 million tweets, our protocol takes 0.014 seconds for a PIR server to generate the result when the user is interested in one of 3K user handles. In contrast, for a much-simplified task, not an aggregate but a positional query, Goldberg's regular IT-PIR (Oakland 2007) takes 1.13 seconds. For all possible user handles, 300K, it takes equal time compared to the regular IT-PIR. This example shows that complicated aggregate queries through our framework do not incur additional overhead if not less, compared to the conventional query.

The recently discovered Neural collapse (NC) phenomenon states that the last-layer weights of Deep Neural Networks (DNN), converge to the so-called Equiangular Tight Frame (ETF) simplex, at the terminal phase of their training. This ETF geometry is equivalent to vanishing within-class variability of the last layer activations. Inspired by NC properties, we explore in this paper the transferability of DNN models trained with their last layer weight fixed according to ETF. This enforces class separation by eliminating class covariance information, effectively providing implicit regularization. We show that DNN models trained with such a fixed classifier significantly improve transfer performance, particularly on out-of-domain datasets. On a broad range of fine-grained image classification datasets, our approach outperforms i) baseline methods that do not perform any covariance regularization (up to 22%), as well as ii) methods that explicitly whiten covariance of activations throughout training (up to 19%). Our findings suggest that DNNs trained with fixed ETF classifiers offer a powerful mechanism for improving transfer learning across domains., Comment: ICASSP 2024. Copyright 2024 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other

Cross-stream migration of a deformable bubble is investigated computationally in a pressure-driven channel flow of a viscoelastic fluid via interface-resolved simulations. The flow equations are solved fully coupled with the Giesekus model equations using the front-tracking method and extensive simulations are performed for a wide range of flow parameters to reveal the effects of bubble deformability, fluid elasticity, shear-thinning, and fluid inertia on the bubble migration dynamics. Migration rate of a bubble is found to be much higher than that of a solid particle under similar flow conditions mainly due to free-slip condition on its surface. It is observed that direction of bubble migration can be altered by varying shear-thinning of the ambient fluid. With a strong shear-thinning, the bubble migrates towards the wall while it migrates towards the center of the channel in a purely elastic fluid without shear-thinning. An onset of elastic flow instability is observed beyond a critical Weissenberg number, which in turn causes a path instability even for a nearly spherical bubble. An inertial path instability is also observed once bubble deformation exceeds a critical value. Shear-thinning is found to be suppressing the path instability in a viscoelastic fluid with a high polymer concentration whereas it reverses its role and promotes path instability in a dilute polymer solution. It is found that bubble migration towards wall induces a secondary flow with a velocity that is about an order of magnitude higher than the one induced by a solid particle under similar flow conditions.

An obstacle toward construction robotization is the lack of methods to plan robot operations within the entire construction planning process. Despite the strength in modeling construction site conditions, 4D BIM technologies cannot perform construction robot task planning considering the contexts of given work environments. To address this limitation, this study presents a framework that integrates 4D BIM and robot task planning, presents an information flow for the integration, and performs high-level robot task planning and detailed simulation. The framework uniquely incorporates a construction robot knowledge base that derives robot-related modeling requirements to augment a 4D BIM model. Then, the 4D BIM model is converted into a robot simulation world where a robot performs a sequence of actions retrieving construction-related information. A case study focusing on the interior wall frame installation demonstrates the potential of systematic integration in achieving context-aware robot task planning and simulation in construction environments.

The increasing popularity of Deep Learning (DL) based Object Detection (OD) methods and their real-world applications have opened new venues in smart manufacturing. Traditional industries struck by capacity constraints after Coronavirus Disease (COVID-19) require non-invasive methods for in-depth operations' analysis to optimize and increase their revenue. In this study, we have initially developed a Convolutional Neural Network (CNN) based OD model to tackle this issue. This model is trained to accurately identify the presence of chairs and individuals on the production floor. The identified objects are then passed to the CNN based tracker, which tracks them throughout their life cycle in the workstation. The extracted meta-data is further processed through a novel framework for the capacity constraint analysis. We identified that the Station C is only 70.6% productive through 6 months. Additionally, the time spent at each station is recorded and aggregated for each object. This data proves helpful in conducting annual audits and effectively managing labor and material over time.

Cobalt is used in Li-ion batteries, but it is expensive and could be replaced by nickel to deliver better performance at a lower cost. With this motivation, we discuss how the character of redox orbitals of LiNiO$_2$ can be ascertained through x-ray Compton scattering measurements combined with parallel first-principles simulations. Our analysis reveals the nature of hole states in Li-doped NiO resulting from the hybridization of O 2$p$ and Ni 3$d$ orbitals. Our study also gives insight into the ferromagnetic ground state and provides a pathway toward the rational design of next-generation battery materials., Comment: 5 pages, 5 figures

]A multichain non-fungible tokens (NFTs) marketplace is a decentralized platform where users can buy, sell, and trade NFTs across multiple blockchain networks by using cross communication bridge. In past most of NFT marketplace was based on singlechain in which NFTs have been bought, sold, and traded on a same blockchain network without the need for any external platform. The singlechain based marketplace have faced number of issues such as performance, scalability, flexibility and limited transaction throughput consequently long confirmation times and high transaction fees during high network usage. Firstly, this paper provides the comprehensive overview about NFT Multichain architecture and explore the challenges and opportunities of designing and implementation phase of multichain NFT marketplace to overcome the issue of single chain-based architecture. NFT multichain marketplace architecture includes different blockchain networks that communicate with each other. Secondly, this paper discusses the concept of mainchain interacting with sidechains which refers to multi blockchain architecture where multiple blockchain networks are connected to each other in a hierarchical structure and identifies key challenges related to interoperability, security, scalability, and user adoption. Finally, we proposed a novel architecture for a multichain NFT marketplace, which leverages the benefits of multiple blockchain networks and marketplaces to overcome these key challenges. Moreover, proposed architecture is evaluated through a case study, demonstrating its ability to support efficient and secure transactions across multiple blockchain networks and highlighting the future trends NFTs and marketplaces and comprehensive discussion about the technology., Comment: 15

In this paper we build a case for providing job completion time predictions to cloud users, similar to the delivery date of a package or arrival time of a booked ride. Our analysis reveals that providing predictability can come at the expense of performance and fairness. Existing cloud scheduling systems optimize for extreme points in the trade-off space, making them either extremely unpredictable or impractical. To address this challenge, we present PCS, a new scheduling framework that aims to provide predictability while balancing other traditional objectives. The key idea behind PCS is to use Weighted-Fair-Queueing (WFQ) and find a suitable configuration of different WFQ parameters (e.g., class weights) that meets specific goals for predictability. It uses a simulation-aided search strategy, to efficiently discover WFQ configurations that lie on the Pareto front of the trade-off space between these objectives. We implement and evaluate PCS in the context of DNN job scheduling on GPUs. Our evaluation, on a small scale GPU testbed and larger-scale simulations, shows that PCS can provide accurate completion time estimates while marginally compromising on performance and fairness.

We electrically characterized melt-quenched amorphized Ge2Sb2Te5 (GST) phase-change memory cells of 20 nm thickness, ~66-124 nm width and ~100-600 nm length with and without photoexcitation in 80-275 K temperature range. The cells show distinctly different current-voltage characteristics in the low-field (< ~19 MV/m), with a clear response to optical excitation by red light (wavelength = 613 nm), and high-field (> ~19 MV/m) regimes, with very weak response to optical excitation. The reduction in carrier activation energy with photoexcitation in the low-field regime increases from ~10 meV at 80 K to ~50 meV at 150 K (highest sensitivity) and decreases again to 5 meV at 275 K. The heterojunctions at the amorphous-crystalline GST interfaces at the two sides of the amorphous region lead to formation of a potential well for holes and a potential barrier for electrons with activation energies in the order of 0.7 eV at room temperature. The alignment of the steady state energy bands suggests formation of tunnel junctions at the interfaces for electrons and an overall electronic conduction by electrons. When photoexcited, the photo-generated holes are expected to be stored in the amorphous region, leading to positive charging of the amorphous region, reducing the barrier for electrons at the junctions and hence the device resistance in the low-field regime. Holes accumulated in the amorphous region are drained under high electric fields, hence the cells' response to photoexcitation is significantly reduced. These results support electronic origin of resistance drift in amorphous GST., Comment: Submitted for publication in Applied Physics Letters

The response of neurons is highly sensitive to the stimulus. The stimulus can be associated with a direct injection in vitro experimentation (e.g., time dependent and independent inputs); or post-synaptic potentials resulting from the interaction of many neurons. A typical incoming stimulus resembles a noise which in principle can be described as a random variable. In computational neuroscience, the noise has been extensively studied for different setups. In this study, we investigate the effect of noisy inputs in a minimal network of two identical leaky integrate-and-fire (LIF) neurons interacting with finite pulses. In particular, we consider a Gaussian white noise as a standard function for stochastic modelling of neurons, while taking into account the pulse width as an elementary component for the signal transmission. By exploring the role of noise and finite pulses, the two neurons show a synchronous spiking behaviour characterized by fluctuations in the interspike intervals. Above some critical values the synchronous regime collapses onto asynchronous dynamics. The abrupt change in such dynamics is accompanied by a hysteresis, i.e., the coexistence of synchronous and asynchronous firing behaviour., Comment: 11 pages, 8 figures

This article investigates the concept of dominant metric dimensions in zero divisor graphs (ZD-graphs) associated with rings. Consider a finite commutative ring with unity, denoted as R, where nonzero elements x and y are identified as zero divisors if their product results in zero (x.y=0). The set of zero divisors in ring R is referred to as L(R). To analyze various algebraic properties of R, a graph known as the zero-divisor graph is constructed using L(R). This manuscript establishes specific general bounds for the dominant metric dimension (Ddim) concerning the ZD-graph of R. To achieve this objective, we examine the zero divisor graphs for specific rings, such as the ring of Gaussian integers modulo m, denoted as Zm[i], the ring of integers modulo n, denoted as Zn, and some quotient polynomial rings. Additionally, we present a general result outlining bounds for the dominant metric dimension expressed in terms of the maximum degree, girth, clique number, and diameter of the associated ZD-graphs. Finally, we provide insights into commutative rings that share identical metric dimensions and dominant metric dimensions. This exploration contributes to a deeper understanding of the structural characteristics of ZD-graphs and their implications for the algebraic properties of commutative rings., Comment: 16 Pages

This note focuses on the optimization of neural architectures for stock index movement forecasting following a major market disruption or crisis. Given that such crises may introduce a shift in market dynamics, this study aims to investigate whether the training data from market dynamics prior to the crisis are compatible with the data during the crisis period. To this end, two distinct learning environments are designed to evaluate and reconcile the effects of possibly different market dynamics. These environments differ principally based on the role assigned to the pre-crisis data. In both environments, a set of non-dominated architectures are identified to satisfy the multi-criteria co-evolution problem, which simultaneously addresses the selection issues related to features and hidden layer topology. To test the hypothesis of pre-crisis data incompatibility, the day-ahead movement prediction of the NASDAQ index is considered during two recent and major market disruptions; the 2008 financial crisis and the COVID-19 pandemic. The results of a detailed comparative evaluation convincingly support the incompatibility hypothesis and highlight the need to select re-training windows carefully., Comment: 11 pages

In a multi objective setting, a portfolio manager's highly consequential decisions can benefit from assessing alternative forecasting models of stock index movement. The present investigation proposes a new approach to identify a set of nondominated neural network models for further selection by the decision maker. A new coevolution approach is proposed to simultaneously select the features and topology of neural networks (collectively referred to as neural architecture), where the features are viewed from a topological perspective as input neurons. Further, the coevolution is posed as a multicriteria problem to evolve sparse and efficacious neural architectures. The well known dominance and decomposition based multiobjective evolutionary algorithms are augmented with a nongeometric crossover operator to diversify and balance the search for neural architectures across conflicting criteria. Moreover, the coevolution is augmented to accommodate the data based implications of distinct market behaviors prior to and during the ongoing COVID 19 pandemic. A detailed comparative evaluation is carried out with the conventional sequential approach of feature selection followed by neural topology design, as well as a scalarized coevolution approach. The results on the NASDAQ index in pre and peri COVID time windows convincingly demonstrate that the proposed coevolution approach can evolve a set of nondominated neural forecasting models with better generalization capabilities., Comment: 22 pages

Z-pinch platforms constitute a promising pathway to fusion energy research. Here, we present a one-dimensional numerical study of the staged Z-pinch (SZP) concept using the FLASH and MACH2 codes. We discuss the verification of the codes using two analytical benchmarks that include Z-pinch-relevant physics, building confidence on the codes' ability to model such experiments. Then, FLASH is used to simulate two different SZP configurations: a xenon gas-puff liner (SZP1*) and a silver solid liner (SZP2). The SZP2 results are compared against previously published MACH2 results, and a new code-to-code comparison on SZP1* is presented. Using an ideal equation of state and analytical transport coefficients, FLASH yields a fuel convergence ratio (CR) of approximately 39 and a mass-averaged fuel ion temperature slightly below 1 keV for the SZP2 scheme, significantly lower than the full-physics MACH2 prediction. For the new SZP1* configuration, full-physics FLASH simulations furnish large and inherently unstable CRs (> 300), but achieve fuel ion temperatures of many keV. While MACH2 also predicts high temperatures, the fuel stagnates at a smaller CR. The integrated code-to-code comparison reveals how magnetic insulation, heat conduction, and radiation transport affect platform performance and the feasibility of the SZP concept.

This paper examines the feasibility of demand-side cyberattacks on power grids launched via internet-connected high-power EV Charging Stations (EVCSs). By distorting power grid frequency and voltage, these attacks can trigger system-wide outages. Our case study focuses on Manhattan, New York, and reveals that such attacks will become feasible by 2030 with increased EV adoption. With a single EVCS company dominating Manhattan, compromising a single EVCS server raises serious power grid security concerns. These attacks can overload power lines and trip over-frequency (OF) protection relays, resulting in a power grid blackout. This study serves as a crucial resource for planning authorities and power grid operators involved in the EV charging infrastructure roll-out, highlighting potential cyberthreats to power grids stemming from high-power EVCSs., Comment: This paper is accepted for publication in the proceeding of IEEE ISGT NA 2024 in Washington DC, USA