Search

The use of Sentinel-2 images to compute Normalized Difference Water Index (NDWI) has many applications, including water body area detection. However, cloud cover poses significant challenges in this regard, which hampers the effectiveness of Sentinel-2 images in this context. In this paper, we present a deep learning model that can generate NDWI given Sentinel-1 images, thereby overcoming this cloud barrier. We show the effectiveness of our model, where it demonstrates a high accuracy of 0.9134 and an AUC of 0.8656 to predict the NDWI. Additionally, we observe promising results with an R2 score of 0.4984 (for regressing the NDWI values) and a Mean IoU of 0.4139 (for the underlying segmentation task). In conclusion, our model offers a first and robust solution for generating NDWI images directly from Sentinel-1 images and subsequent use for various applications even under challenging conditions such as cloud cover and nighttime.

With the recent advancements in artificial intelligence, researchers and industries are deploying gigantic models trained on billions of samples. While training these models consumes a huge amount of energy, human brains produce similar outputs (along with other capabilities) with massively lower data and energy requirements. For this reason, more researchers are increasingly considering alternatives. One of these alternatives is known as synthetic biological intelligence, which involves training \textit{in vitro} neurons for goal-directed tasks. This multidisciplinary field requires knowledge of tissue engineering, bio-materials, digital signal processing, computer programming, neuroscience, and even artificial intelligence. The multidisciplinary requirements make starting synthetic biological intelligence research highly non-trivial and time-consuming. Generally, most labs either specialize in the biological aspects or the computational ones. Here, we propose how a lab focusing on computational aspects, including machine learning and device interfacing, can start working on synthetic biological intelligence, including organoid intelligence. We will also discuss computational aspects, which can be helpful for labs that focus on biological research. To facilitate synthetic biological intelligence research, we will describe such a general process step by step, including risks and precautions that could lead to substantial delay or additional cost.

The intersection of technology and mental health has spurred innovative approaches to assessing emotional well-being, particularly through computational techniques applied to audio data analysis. This study explores the application of Convolutional Neural Network (CNN) and Long Short-Term Memory (LSTM) models on wavelet extracted features and Mel-frequency Cepstral Coefficients (MFCCs) for emotion detection from spoken speech. Data augmentation techniques, feature extraction, normalization, and model training were conducted to evaluate the models' performance in classifying emotional states. Results indicate that the CNN model achieved a higher accuracy of 61% compared to the LSTM model's accuracy of 56%. Both models demonstrated better performance in predicting specific emotions such as surprise and anger, leveraging distinct audio features like pitch and speed variations. Recommendations include further exploration of advanced data augmentation techniques, combined feature extraction methods, and the integration of linguistic analysis with speech characteristics for improved accuracy in mental health diagnostics. Collaboration for standardized dataset collection and sharing is recommended to foster advancements in affective computing and mental health care interventions.

Traffic signal control plays a crucial role in urban mobility. However, existing methods often struggle to generalize beyond their training environments to unseen scenarios with varying traffic dynamics. We present TransferLight, a novel framework designed for robust generalization across road-networks, diverse traffic conditions and intersection geometries. At its core, we propose a log-distance reward function, offering spatially-aware signal prioritization while remaining adaptable to varied lane configurations - overcoming the limitations of traditional pressure-based rewards. Our hierarchical, heterogeneous, and directed graph neural network architecture effectively captures granular traffic dynamics, enabling transferability to arbitrary intersection layouts. Using a decentralized multi-agent approach, global rewards, and novel state transition priors, we develop a single, weight-tied policy that scales zero-shot to any road network without re-training. Through domain randomization during training, we additionally enhance generalization capabilities. Experimental results validate TransferLight's superior performance in unseen scenarios, advancing practical, generalizable intelligent transportation systems to meet evolving urban traffic demands., Comment: AAAI Workshop Paper (MALTA)

The Extended Crosswise Model is a popular randomized response design that employs a sensitive and a randomized innocuous statement, and asks respondents if one of these statements is true, or that none or both are true. The model has a degree of freedom to test for response biases, but is unable to detect random answering. In this paper, we propose two new methods to indirectly estimate and correct for random answering. One method uses a non-sensitive control statement and a quasi-randomized innocuous statement to which both answers are known to estimate the proportion of random respondents. The other method assigns less weight in the estimation procedure to respondents who complete the survey in an unrealistically short time. For four surveys among elite athletes, we use these methods to correct the prevalence estimates of doping use for random answering.

Baryon Acoustic Oscillation (BAO) provides a powerful tool to measure cosmic expansion and consequently the nature of the Dark Energy (DE). Recent precise BAO measurements by Dark Energy Spectroscopic Instrument data release 1 (DESI DR1), when combined with Cosmic Microwave Background (CMB) data from Planck and Supernovae of Type Ia (SN Ia), favor evolving dark energy over cosmological constant. This result is strongly related to the assumed priors on the Chevallier-Polarski-Linder (CPL) parameterization of DE. We test another parametrization which introduces two free parameters $n$ and $\alpha$, only $n$ is independent. Thus, it reduces the parameter space compared to the CPL model, which derives a more robust preference for evolving DE, if any. The model potentially produces three cosmological scenarios according to the values of its parameters. For $n=3$, the $\Lambda$CDM model is recovered, quintessence for $n<3$, and phantom for $n>3$. In the present study, we test the model on the background level, and, to our knowledge for the first time, on the linear perturbation level. Bayesian evidence analysis shows a weak preference for dynamical DE in the phantom regime over the cosmological constant DE using Planck, DESI, and PantheonPlus\&SH0ES data. The model predicts current phantom DE $w_{de,0} = -1.073 \pm 0.032$ and $H_0=70.9\pm 1.4$ km/s/Mpc when Planck+DESI data is used, which decreases the tension with $H_0$ local measurements to $1.2\sigma$ level., Comment: 24 pages, 9 figures, 4 tables

High-Performance Computing (HPC) systems are among the most energy-intensive scientific facilities, with electric power consumption reaching and often exceeding 20 megawatts per installation. Unlike other major scientific infrastructures such as particle accelerators or high-intensity light sources, which are few around the world, the number and size of supercomputers are continuously increasing. Even if every new system generation is more energy efficient than the previous one, the overall growth in size of the HPC infrastructure, driven by a rising demand for computational capacity across all scientific disciplines, and especially by artificial intelligence workloads (AI), rapidly drives up the energy demand. This challenge is particularly significant for HPC centers in Germany, where high electricity costs, stringent national energy policies, and a strong commitment to environmental sustainability are key factors. This paper describes various state-of-the-art strategies and innovations employed to enhance the energy efficiency of HPC systems within the national context. Case studies from leading German HPC facilities illustrate the implementation of novel heterogeneous hardware architectures, advanced monitoring infrastructures, high-temperature cooling solutions, energy-aware scheduling, and dynamic power management, among other optimizations. By reviewing best practices and ongoing research, this paper aims to share valuable insight with the global HPC community, motivating the pursuit of more sustainable and energy-efficient HPC operations., Comment: 30 pages, 3 figures, 4 tables

The recent discovery of an axial amplitude (Higgs) mode in the long-studied charge density wave (CDW) systems GdTe$_3$ and LaTe$_3$ suggests a heretofore unidentified hidden order. A theoretical study proposed that the axial Higgs results from a hidden ferroaxial component of the CDW, which could arise from non-trivial orbital texture. Here, we report extensive experimental studies on ErTe$_3$ and HoTe$_3$ that possess a high-temperature CDW similar to other RTe$_3$ (R = rare earth), along with an additional low-temperature CDW with an orthogonal ordering vector. Combining Raman spectroscopy with large-angle convergent beam electron diffraction (LACBED), rotational anisotropy second-harmonic generation (RA-SHG), and muon-spin relaxation ($\mu$SR), we provide unambiguous evidence that the high-temperature CDW breaks translation, rotation, and all vertical and diagonal mirror symmetries, but not time-reversal or inversion. In contrast, the low-temperature CDW only additionally breaks translation symmetry. Simultaneously, Raman scattering shows the high-temperature CDW produces an axial Higgs mode while the low-temperature mode is scalar. The weak monoclinic structural distortion and clear axial response in Raman and SHG are consistent with a ferroaxial phase in RTe$_3$ driven by coupled orbital and charge orders. Thus, our study provides a new standard for uncovering unconventional orders and confirms the power of Higgs modes to reveal them., Comment: 28 pages, 5 figures

Despite recent progress in reducing road fatalities, the persistently high rate of traffic-related deaths highlights the necessity for improved safety interventions. Leveraging large-scale graph-based nationwide road network data across 49 states in the USA, our study first posits the Concurrency Hypothesis from intuitive observations, suggesting a significant likelihood of incidents occurring at neighboring nodes within the road network. To quantify this phenomenon, we introduce two novel metrics, Average Neighbor Crash Density (ANCD) and Average Neighbor Crash Continuity (ANCC), and subsequently employ them in statistical tests to validate the hypothesis rigorously. Building upon this foundation, we propose the Concurrency Prior (CP) method, a powerful approach designed to enhance the predictive capabilities of general Graph Neural Network (GNN) models in semi-supervised traffic incident prediction tasks. Our method allows GNNs to incorporate concurrent incident information, as mentioned in the hypothesis, via tokenization with negligible extra parameters. The extensive experiments, utilizing real-world data across states and cities in the USA, demonstrate that integrating CP into 12 state-of-the-art GNN architectures leads to significant improvements, with gains ranging from 3% to 13% in F1 score and 1.3% to 9% in AUC metrics. The code is publicly available at https://github.com/xiwenc1/Incident-GNN-CP., Comment: Accepted by Sigspatial 2024

We develop a robust translation model for four low-resource Indic languages: Khasi, Mizo, Manipuri, and Assamese. Our approach includes a comprehensive pipeline from data collection and preprocessing to training and evaluation, leveraging data from WMT task datasets, BPCC, PMIndia, and OpenLanguageData. To address the scarcity of bilingual data, we use back-translation techniques on monolingual datasets for Mizo and Khasi, significantly expanding our training corpus. We fine-tune the pre-trained NLLB 3.3B model for Assamese, Mizo, and Manipuri, achieving improved performance over the baseline. For Khasi, which is not supported by the NLLB model, we introduce special tokens and train the model on our Khasi corpus. Our training involves masked language modelling, followed by fine-tuning for English-to-Indic and Indic-to-English translations., Comment: Published in WMT 2024. Low-Resource Indic Language Translation Shared Task

Software vulnerabilities are a fundamental cause of cyber attacks. Effectively identifying these vulnerabilities is essential for robust cybersecurity, yet it remains a complex and challenging task. In this paper, we present SafePyScript, a machine learning-based web application designed specifically to identify vulnerabilities in Python source code. Despite Python's significance as a major programming language, there is currently no convenient and easy-to-use machine learning-based web application for detecting vulnerabilities in its source code. SafePyScript addresses this gap by providing an accessible solution for Python programmers to ensure the security of their applications. SafePyScript link: https://safepyscript.com/

Domain Generation Algorithms (DGAs) are malicious techniques used by malware to dynamically generate seemingly random domain names for communication with Command & Control (C&C) servers. Due to the fast and simple generation of DGA domains, detection methods must be highly efficient and precise to be effective. Large Language Models (LLMs) have demonstrated their proficiency in real-time detection tasks, making them ideal candidates for detecting DGAs. Our work validates the effectiveness of fine-tuned LLMs for detecting DGAs and DNS exfiltration attacks. We developed LLM models and conducted comprehensive evaluation using a diverse dataset comprising 59 distinct real-world DGA malware families and normal domain data. Our LLM model significantly outperformed traditional natural language processing techniques, especially in detecting unknown DGAs. We also evaluated its performance on DNS exfiltration datasets, demonstrating its effectiveness in enhancing cybersecurity measures. To the best of our knowledge, this is the first work that empirically applies LLMs for DGA and DNS exfiltration detection., Comment: Accepted in Proceedings of the Workshop at AI for Cyber Threat Intelligence (WAITI), 2024

Diagnosing knee osteoarthritis (OA) early is crucial for managing symptoms and preventing further joint damage, ultimately improving patient outcomes and quality of life. In this paper, a bioimpedance-based diagnostic tool that combines precise hardware and deep learning for effective non-invasive diagnosis is proposed. system features a relay-based circuit and strategically placed electrodes to capture comprehensive bioimpedance data. The data is processed by a neural network model, which has been optimized using convolutional layers, dropout regularization, and the Adam optimizer. This approach achieves a 98% test accuracy, making it a promising tool for detecting knee osteoarthritis musculoskeletal disorders.

The financial sector's dependence on digital infrastructure increases its vulnerability to cybersecurity threats, requiring strong IT security protocols with other entities. This collaboration, however, is often identified as the most vulnerable link in the chain of cybersecurity. Adopting both symbolic and substantive measures lessens the impact of IT security spending on decreasing the frequency of data security breaches in the long run. The Protection Motivation Theory clarifies actions triggered by data sharing with other organizations, and the Institutional theory aids in comprehending the intricate relationship between transparency and organizational conduct. We investigate how things like regulatory pressure, teamwork among institutions, and people's motivations to protect themselves influence cybersecurity. By using simple theories to understand these factors, this research aims to provide insights that can help financial institutions make better decisions to protect. We have also included the discussion, conclusion, and future directions in regard to collaboration in financial sector cybersecurity for exploring impact of resource sharing., Comment: 8 pages, 2 figures

Single-orbital Hubbard models exhibit remarkably nontrivial correlation phenomena, even on nonfrustrated bipartite lattices. Some of these, like non-Fermi-liquid metal states, or the coexistence of heavy and light quasi-particles, are reminiscent of the properties of more complex multi-orbital or Kondo-lattice systems. Here, we use basis transformations to map single-orbital models to effective multi-orbital descriptions and clarify how a ferromagnetic Kondo-lattice-like behavior emerges in prototypical models with flat bands or van Hove singularities in the density of states: the Hubbard model on the diamond chain, square-lattice, Lieb lattice and honeycomb lattice. In particular, this mapping explains the non-Fermi-liquid states and pseudo-gaps found in the correlated metal regime.

Thyroid carcinoma, a significant yet often controllable cancer, has seen a rise in cases, largely due to advancements in diagnostic methods. Differentiated thyroid cancer (DTC), which includes papillary and follicular varieties, is typically associated with a positive prognosis in academic circles. Nevertheless, there are still some individuals who may experience a recurrence. This study employs machine learning, particularly deep learning models, to predict the recurrence of DTC, with the goal of improving patient care through personalized treatment approaches. By analysing a dataset containing clinicopathological features of patients, the model achieved remarkable accuracy rates of 98% during training and 96% during testing. To improve the model's interpretability, we used techniques like LIME and Morris Sensitivity Analysis. These methods gave us valuable insights into how the model makes decisions. The results suggest that combining deep learning models with interpretability techniques can be extremely useful in quickly identifying the recurrence of thyroid cancer in patients. This can help in making informed therapeutic choices and customizing treatment approaches for individual patients.

Understanding protein motion within the cell is crucial for predicting reaction rates and macromolecular transport in the cytoplasm. A key question is how crowded environments affect protein dynamics through hydrodynamic and direct interactions at molecular length scales. Using megahertz X-ray Photon Correlation Spectroscopy (MHz-XPCS) at the European X-ray Free Electron Laser (EuXFEL), we investigate ferritin diffusion at microsecond time scales. Our results reveal anomalous diffusion, indicated by the non-exponential decay of the intensity autocorrelation function $g_2(q,t)$ at high concentrations. This behavior is consistent with the presence of cage-trapping in between the short- and long-time protein diffusion regimes. Modeling with the $\delta\gamma$-theory of hydrodynamically interacting colloidal spheres successfully reproduces the experimental data by including a scaling factor linked to the protein direct interactions. These findings offer new insights into the complex molecular motion in crowded protein solutions, with potential applications for optimizing ferritin-based drug delivery, where protein diffusion is the rate-limiting step.

In recent times, a considerable number of research studies have been carried out to address the issue of Missing Value Imputation (MVI). MVI aims to provide a primary solution for datasets that have one or more missing attribute values. The advancements in Artificial Intelligence (AI) drive the development of new and improved machine learning (ML) algorithms and methods. The advancements in ML have opened up significant opportunities for effectively imputing these missing values. The main objective of this article is to conduct a comprehensive and rigorous review, as well as analysis, of the state-of-the-art ML applications in MVI methods. This analysis seeks to enhance researchers' understanding of the subject and facilitate the development of robust and impactful interventions in data preprocessing for Data Analytics. The review is performed following the Preferred Reporting Items for Systematic Reviews and Meta-Analysis (PRISMA) technique. More than 100 articles published between 2014 and 2023 are critically reviewed, considering the methods and findings. Furthermore, the latest literature is examined to scrutinize the trends in MVI methods and their evaluation. The accomplishments and limitations of the existing literature are discussed in detail. The survey concludes by identifying the current gaps in research and providing suggestions for future research directions and emerging trends in related fields of interest.

In this paper, we report the long-range and wireless interrogation of multiple chipless sensors from the isoline processing of three-dimensional polarimetric radar images. A Frequency-Modulated Continuous-Wave Radar operating at 24 GHz is used for the indoor interrogation of four sensors in the basement of a Laboratory. In such cluttered environment, the proposed radar image processing based on isolines computation allows the wireless measurement range of sensors up to 5.8m.

Modern computers rely on USB and HDMI ports for connecting external peripherals and display devices. Despite their built-in security measures, these ports remain susceptible to passive power-based side-channel attacks. This paper presents a new class of attacks that exploit power consumption patterns at these ports to infer GPU activities. We develop a custom device that plugs into these ports and demonstrate that its high-resolution power measurements can drive successful inferences about GPU processes, such as neural network computations and video rendering. The ubiquitous presence of USB and HDMI ports allows for discreet placement of the device, and its non-interference with data channels ensures that no security alerts are triggered. Our findings underscore the need to reevaluate and strengthen the current generation of HDMI and USB port security defenses.

In today's digitally driven landscape, robust Information Technology (IT) risk assessment practices are essential for safeguarding systems, digital communication, and data. This paper introduces 'AssessITS', an actionable method designed to provide organizations with comprehensive guidelines for conducting IT and cybersecurity risk assessments. Drawing extensively from NIST 800-30 Rev 1, COBIT 5, and ISO 31000, 'AssessITS' bridges the gap between high-level theoretical standards and practical implementation challenges. The paper outlines a step-by-step methodology that organizations can simply adopt to systematically identify, analyze, and mitigate IT risks. By simplifying complex principles into actionable procedures, this framework equips practitioners with the tools needed to perform risk assessments independently, without too much reliance on external vendors. The guidelines are developed to be straightforward, integrating practical evaluation metrics that allow for the precise quantification of asset values, threat levels, vulnerabilities, and impacts on confidentiality, integrity, and availability. This approach ensures that the risk assessment process is not only comprehensive but also accessible, enabling decision-makers to implement effective risk mitigation strategies customized to their unique operational contexts. 'AssessITS' aims to enable organizations to enhance their IT security strength through practical, actionable guidance based on internationally recognized standards., Comment: 25 pages, 8 figures, 7 tables

Unmanned Aerial Vehicles (UAVs) play an increasingly critical role in Intelligence, Surveillance, and Reconnaissance (ISR) missions such as border patrolling and criminal detection, thanks to their ability to access remote areas and transmit real-time imagery to processing servers. However, UAVs are highly constrained by payload size, power limits, and communication bandwidth, necessitating the development of highly selective and efficient data transmission strategies. This has driven the development of various compression and optimal transmission technologies for UAVs. Nevertheless, most methods strive to preserve maximal information in transferred video frames, missing the fact that only certain parts of images/video frames might offer meaningful contributions to the ultimate mission objectives in the ISR scenarios involving moving object detection and tracking (OD/OT). This paper adopts a different perspective, and offers an alternative AI-driven scheduling policy that prioritizes selecting regions of the image that significantly contributes to the mission objective. The key idea is tiling the image into small patches and developing a deep reinforcement learning (DRL) framework that assigns higher transmission probabilities to patches that present higher overlaps with the detected object of interest, while penalizing sharp transitions over consecutive frames to promote smooth scheduling shifts. Although we used Yolov-8 object detection and UDP transmission protocols as a benchmark testing scenario the idea is general and applicable to different transmission protocols and OD/OT methods. To further boost the system's performance and avoid OD errors for cluttered image patches, we integrate it with interframe interpolations.

Integration of probabilistic and non-probabilistic samples for the estimation of finite population totals (or means) has recently received considerable attention in the field of survey sampling; yet, to the best of our knowledge, this framework has not been extended to cumulative distribution function (CDF) estimation. To address this gap, we propose a novel CDF estimator that integrates data from probability samples with data from (potentially large) nonprobability samples. Assuming that a set of shared covariates are observed in both samples, while the response variable is observed only in the latter, the proposed estimator uses a survey-weighted empirical CDF of regression residuals trained on the convenience sample to estimate the CDF of the response variable. Under some regularity conditions, we show that our CDF estimator is both design-consistent for the finite population CDF and asymptotically normally distributed. Additionally, we define and study a quantile estimator based on the proposed CDF estimator. Furthermore, we use both the bootstrap and asymptotic formulae to estimate their respective sampling variances. Our empirical results show that the proposed CDF estimator is robust to model misspecification under ignorability, and robust to ignorability under model misspecification. When both assumptions are violated, our residual-based CDF estimator still outperforms its 'plug-in' mass imputation and naive siblings, albeit with noted decreases in efficiency.

When fossil fuel supplies can no longer be replenished and hence fossil fuel power generation becomes outdated, wind energy will become a vital solution to the impending energy crisis. A horizontal-axis wind turbine is a widely used technology that is highly dependent on the design of high-performing airfoils. In this paper, we have studied the performance of the NACA6309 airfoil and designed it by modifying the airfoil with a trailing edge plain flap. Computational Fluid Dynamic (CFD) simulations are utilized for this purpose. We have designed sixteen configurations of NACA 6309 airfoil by using plain flaps at the trailing edge and studied their aerodynamic performance. After comparing the lift, drag, and lift-to-drag ratios, it is evident that the \(1^\circ\) up-flap configuration generates the best output. In addition, the \(10^\circ\) down flap provides the worst performance among all configurations. Finally, pressure contours and velocity contours around the airfoils are presented, which describe the overall characteristics.

Due to the augmentation of the significance of wind energy, giving a high priority to the \text{airfoil's} efficiency enhancement is obligatory. To improve the performance of airfoils, many impressive techniques are already invented. In this article, the trailing edge of the NACA 4412 airfoil is modified by changing the thickness. CFD is used in this study, which aids in the identification of several important details. For our investigation, we choose the reliable Spalart Almaras model and the Reynolds number is 300k. Overall, the results demonstrate that using \(0.8\%\) thickness at the trailing edge of the NACA 4412 airfoil is viable to obtain the best output. The predominant reason is that not only the better coefficient of lift but also the preferable lift-to-drag \(\frac{C_L}{C_D}\) ratio is found in this configuration. However, using \(0.2\%\) thickness at the trailing edge reduces performance as a whole. So, it is recommended to utilize \(0.2\%\) thickness on the trailing edge of the NACA 4412 airfoil.

Since the invention of the laser nonlinear effects such as filamentation, Rabi-cycling and collective emission have been explored in the optical regime leading to a wide range of scientific and industrial applications. X-ray free electron lasers (XFELs) have led to the extension of many optical techniques to X-rays for their advantages of angstrom scale spatial resolution and elemental specificity. One such example is XFEL driven population inversion of 1s core hole states resulting in inner-shell K${\alpha}$ (2p to 1s) X-ray lasing in elements ranging from neon to copper, which has been utilized for nonlinear spectroscopy and development of next generation X-ray laser sources. Here we show that strong lasing effects, similar to those observed in the optical regime, can occur at 1.5 to 2.1 angstrom wavelengths during high intensity (> ${10^{19}}$ W/cm${^{2}}$) XFEL driven inner-shell lasing and superfluorescence of copper and manganese. Depending on the temporal substructure of the XFEL pump pulses, the resulting inner-shell X-ray laser pulses can exhibit strong spatial inhomogeneities as well as spectral inhomogeneities and broadening. Through 3D Maxwell Bloch theory we show that the observed spatial inhomogeneities result from X-ray filamentation, and that the spectral broadening is driven by Rabi cycling with sub-femtosecond periods. These findings indicate that we have generated Angstrom-wavelength x-ray pulses (containing ${10^{6}}$ - ${10^{8}}$ photons) in the strong lasing regime, some of them with pulse lengths of less than 100 attoseconds.

Benchmarks are essential in the design of modern HPC installations, as they define key aspects of system components. Beyond synthetic workloads, it is crucial to include real applications that represent user requirements into benchmark suites, to guarantee high usability and widespread adoption of a new system. Given the significant investments in leadership-class supercomputers of the exascale era, this is even more important and necessitates alignment with a vision of Open Science and reproducibility. In this work, we present the JUPITER Benchmark Suite, which incorporates 16 applications from various domains. It was designed for and used in the procurement of JUPITER, the first European exascale supercomputer. We identify requirements and challenges and outline the project and software infrastructure setup. We provide descriptions and scalability studies of selected applications and a set of key takeaways. The JUPITER Benchmark Suite is released as open source software with this work at https://github.com/FZJ-JSC/jubench., Comment: To be published in Proceedings of The International Conference for High Performance Computing Networking, Storage, and Analysis (SC '24) (2024)

To solve ever more complex problems, Deep Neural Networks are scaled to billions of parameters, leading to huge computational costs. An effective approach to reduce computational requirements and increase efficiency is to prune unnecessary components of these often over-parameterized networks. Previous work has shown that attribution methods from the field of eXplainable AI serve as effective means to extract and prune the least relevant network components in a few-shot fashion. We extend the current state by proposing to explicitly optimize hyperparameters of attribution methods for the task of pruning, and further include transformer-based networks in our analysis. Our approach yields higher model compression rates of large transformer- and convolutional architectures (VGG, ResNet, ViT) compared to previous works, while still attaining high performance on ImageNet classification tasks. Here, our experiments indicate that transformers have a higher degree of over-parameterization compared to convolutional neural networks. Code is available at https://github.com/erfanhatefi/Pruning-by-eXplaining-in-PyTorch., Comment: Accepted as a workshop paper at ECCV 2024, 26 pages (11 pages manuscript, 3 pages references, 12 pages appendix)