Search

This paper compares machine learning approaches with different input data formats for the classification of acoustic emission (AE) signals. AE signals are a promising monitoring technique in many structural health monitoring applications. Machine learning has been demonstrated as an effective data analysis method, classifying different AE signals according to the damage mechanism they represent. These classifications can be performed based on the entire AE waveform or specific features that have been extracted from it. However, it is currently unknown which of these approaches is preferred. With the goal of model deployment on resource-constrained embedded Internet of Things (IoT) systems, this work evaluates and compares both approaches in terms of classification accuracy, memory requirement, processing time, and energy consumption. To accomplish this, features are extracted and carefully selected, neural network models are designed and optimized for each input data scenario, and the models are deployed on a low-power IoT node. The comparative analysis reveals that all models can achieve high classification accuracies of over 99\%, but that embedded feature extraction is computationally expensive. Consequently, models utilizing the raw AE signal as input have the fastest processing speed and thus the lowest energy consumption, which comes at the cost of a larger memory requirement., Comment: Conference Presentations (Accepted) at IEEE 10th World Forum on Internet of Things. "https://wfiot2024.iot.ieee.org/program/technical-paper-program"

Mining 4.0 leverages advancements in automation, digitalization, and interconnected technologies from Industry 4.0 to address the unique challenges of the mining sector, enhancing efficiency, safety, and sustainability. Conveyor belts are crucial in mining operations by enabling the continuous and efficient movement of bulk materials over long distances, which directly impacts productivity. While detecting anomalies in specific conveyor belt components, such as idlers, pulleys, and belt surfaces, has been widely studied, identifying the root causes of these failures remains critical due to factors like changing production conditions and operator errors. Continuous monitoring of mining conveyor belt work cycles for anomaly detection is still at an early stage and requires robust solutions. This study proposes two distinctive pattern recognition approaches for real-time anomaly detection in the operational cycles of mining conveyor belts, combining feature extraction, threshold-based cycle detection, and tiny machine-learning classification. Both approaches outperformed a state-of-the-art technique on two datasets for duty cycle classification in terms of F1-scores. The first approach, with 97.3% and 80.2% for normal and abnormal cycles, respectively, reaches the highest performance in the first dataset while the second approach excels on the second dataset, scoring 91.3% and 67.9%. Implemented on two low-power microcontrollers, the methods demonstrated efficient, real-time operation with energy consumption of 13.3 and 20.6 ${\mu}$J during inference. These results offer valuable insights for detecting mechanical failure sources, supporting targeted preventive maintenance, and optimizing production cycles., Comment: Preprint submitted to IEEE Transactions on Instrumentation and Measurement

Resilient divertor features connected to open chaotic edge structures in the Helically Symmetric Experiment (HSX) are investigated. For the first time, an expanded vessel wall was considered that would give space for implementation of a physical divertor target structure. The analysis was done for four different magnetic configurations with very different chaotic plasma edges. A resilient plasma wall interaction pattern was identified across all configurations. This manifests as qualitatively very similar footprint behavior across the different plasma equilibria. Overall, the resilient field lines of interest with high connection length $L_C$ lie within a helical band along the wall for all configurations. This resiliency can be used to identify the best location of a divertor. The details of the magnetic footprint's resilient helical band is subject to specific field line structures which are linked to the penetration depth of field lines into the plasma and directly influence the heat and particle flux patterns. The differences arising from these details are characterized by introducing a new metric, the minimum radial connection $\text{min}(\delta_N)$ of a field line from the last closed flux surface. The relationship, namely the deviation from a scaling law, between $\text{min}(\delta_N)$ and $L_C$ of the field lines in the plasma edge field line behavior suggests that the field lines are associated with structures such as resonant islands, cantori, and turnstiles. This helps determine the relevant magnetic flux channels based on the radial location of these chaotic edge structures and the divertor target footprint. These details will need to be taken into account for resilient divertor design., Comment: 18 pages, 10 figures

We establish a general spectral gap theorem for actions of products of groups which may replace Kazhdan's property (T) in various situations. As a main application, we prove that a confined subgroup of an irreducible lattice in a higher rank semisimple Lie group is of finite index. This significantly strengthens the classical normal subgroup theorem of Margulis and removes the property (T) assumption from the recent counterpart result of Fraczyk and Gelander. We further show that any confined discrete subgroup of a higher rank semisimple Lie group satisfying a certain irreducibility condition is an irreducible lattice. This implies a variant of the Stuck-Zimmer conjecture under a strong irreducibility assumption of the action.

The Workflows Community Summit gathered 111 participants from 18 countries to discuss emerging trends and challenges in scientific workflows, focusing on six key areas: time-sensitive workflows, AI-HPC convergence, multi-facility workflows, heterogeneous HPC environments, user experience, and FAIR computational workflows. The integration of AI and exascale computing has revolutionized scientific workflows, enabling higher-fidelity models and complex, time-sensitive processes, while introducing challenges in managing heterogeneous environments and multi-facility data dependencies. The rise of large language models is driving computational demands to zettaflop scales, necessitating modular, adaptable systems and cloud-service models to optimize resource utilization and ensure reproducibility. Multi-facility workflows present challenges in data movement, curation, and overcoming institutional silos, while diverse hardware architectures require integrating workflow considerations into early system design and developing standardized resource management tools. The summit emphasized improving user experience in workflow systems and ensuring FAIR workflows to enhance collaboration and accelerate scientific discovery. Key recommendations include developing standardized metrics for time-sensitive workflows, creating frameworks for cloud-HPC integration, implementing distributed-by-design workflow modeling, establishing multi-facility authentication protocols, and accelerating AI integration in HPC workflow management. The summit also called for comprehensive workflow benchmarks, workflow-specific UX principles, and a FAIR workflow maturity model, highlighting the need for continued collaboration in addressing the complex challenges posed by the convergence of AI, HPC, and multi-facility research environments.

The spatial sensitivity of an ultrasound transducer, which strongly influences its suitability for different applications, depends on the shape of the transducer surface. Accurate simulation of these spatial effects is important for transducer characterization and design, and for system response modelling in imaging applications. In optoacoustic imaging, broadband transducers are used to capitalize on the rich frequency content of the signals, but their usage makes highly accurate simulations with general wave equation solvers prohibitively memory- and time-intensive. Therefore, specialized tools for simulating the isolated spatial focusing properties described by the spatial impulse response (SIR) have been developed. However, the challenging numerics of the SIR and the necessity to convolve the SIR with the wave shape generated by the optoacoustic absorber to simulate the system response lead to numerical inaccuracies of SIR-based methods. In addition, the approximation error of these methods cannot be controlled a priori. To circumvent the problems associated with the explicit calculation of SIR, we propose directly computing the convolution of the required wave shape with the SIR, which we call the spatial pulse response (SPR). We demonstrate that by utilizing an h-adaptive cubature algorithm, SPR can be computed with significantly higher accuracy than an SIR-based reference method, and the approximation error can be controlled with a tolerance parameter. In addition, the integration of accurate SPR simulations into model-based optoacoustic image reconstruction is shown to improve image contrast and reduce noise artifacts. Precise system characterization and simulation leads to improved imaging performance, ultimately increasing the value of optoacoustic imaging systems for clinical applications.

The increasing accuracy reports of metric monocular depth estimation models lead to a growing interest from the automotive domain. Current model evaluations do not provide deeper insights into the models' performance, also in relation to safety-critical or unseen classes. Within this paper, we present a novel approach for the evaluation of depth estimation models. Our proposed metric leverages three components, a class-wise component, an edge and corner image feature component, and a global consistency retaining component. Classes are further weighted on their distance in the scene and on criticality for automotive applications. In the evaluation, we present the benefits of our metric through comparison to classical metrics, class-wise analytics, and the retrieval of critical situations. The results show that our metric provides deeper insights into model results while fulfilling safety-critical requirements. We release the code and weights on the following repository: https://github.com/leisemann/ca_mmde, Comment: Accepted at the European Conference on Computer Vision (ECCV) 2024 Workshop on Out Of Distribution Generalization in Computer Vision

Indonesian and Western gamelan ensembles are investigated with respect to performance differences. Thereby, the often exotistic history of this music in the West might be reflected in contemporary tonal system, articulation, or large-scale form differences. Analyzing recordings of four Western and five Indonesian orchestras with respect to tonal systems and timbre features and using self-organizing Kohonen map (SOM) as a machine learning algorithm, a clear clustering between Indonesian and Western ensembles appears using certain psychoacoustic features. These point to a reduced articulation and large-scale form variability of Western ensembles compared to Indonesian ones. The SOM also clusters the ensembles with respect to their tonal systems, but no clusters between Indonesian and Western ensembles can be found in this respect. Therefore, a clear analogy between lower articulatory variability and large-scale form variation and a more exostistic, mediative and calm performance expectation and reception of gamelan in the West therefore appears., Comment: 5 figures, 4 tables

Scientific workflow management systems enable the reproducible execution of data analysis pipelines on cluster infrastructures managed by resource managers such as Kubernetes, Slurm, or HTCondor. These resource managers require resource estimates for each workflow task to be executed on one of the cluster nodes. However, task resource consumption varies significantly between different tasks and for the same task with different inputs. Furthermore, resource consumption also fluctuates during a task's execution. As a result, manually configuring static memory allocations is error-prone, often leading users to overestimate memory usage to avoid costly failures from under-provisioning, which results in significant memory wastage. We propose KS+, a method that predicts a task's memory consumption over time depending on its inputs. For this, KS+ dynamically segments the task execution and predicts the memory required for each segment. Our experimental evaluation shows an average reduction in memory wastage of 38% compared to the best-performing state-of-the-art baseline for two real-world workflows from the popular nf-core repository., Comment: Paper accepted in 2024 IEEE ReWorDS, eScience

In the field of Image Quality Assessment (IQA), the adversarial robustness of the metrics poses a critical concern. This paper presents a comprehensive benchmarking study of various defense mechanisms in response to the rise in adversarial attacks on IQA. We systematically evaluate 25 defense strategies, including adversarial purification, adversarial training, and certified robustness methods. We applied 14 adversarial attack algorithms of various types in both non-adaptive and adaptive settings and tested these defenses against them. We analyze the differences between defenses and their applicability to IQA tasks, considering that they should preserve IQA scores and image quality. The proposed benchmark aims to guide future developments and accepts submissions of new methods, with the latest results available online: https://videoprocessing.ai/benchmarks/iqa-defenses.html.

Scientific workflows are used to analyze large amounts of data. These workflows comprise numerous tasks, many of which are executed repeatedly, running the same custom program on different inputs. Users specify resource allocations for each task, which must be sufficient for all inputs to prevent task failures. As a result, task memory allocations tend to be overly conservative, wasting precious cluster resources, limiting overall parallelism, and increasing workflow makespan. In this paper, we first benchmark a state-of-the-art method on four real-life workflows from the nf-core workflow repository. This analysis reveals that certain assumptions underlying current prediction methods, which typically were evaluated only on simulated workflows, cannot generally be confirmed for real workflows and executions. We then present Ponder, a new online task-sizing strategy that considers and chooses between different methods to cater to different memory demand patterns. We implemented Ponder for Nextflow and made the code publicly available. In an experimental evaluation that also considers the impact of memory predictions on scheduling, Ponder improves Memory Allocation Quality on average by 71.0% and makespan by 21.8% in comparison to a state-of-the-art method. Moreover, Ponder produces 93.8% fewer task failures.

Let M be a closed Riemannian manifold with Kazhdan fundamental group. It is well known that the Cheeger inequality yields a uniform waist inequality in codimension one for the finite covers of M. We show that the finite covers of M also satisfy a uniform waist inequality in codimension two., Comment: updated introduction; 14 pages

As the amount of available data continues to grow in fields as diverse as bioinformatics, physics, and remote sensing, the importance of scientific workflows in the design and implementation of reproducible data analysis pipelines increases. When developing workflows, resource requirements must be defined for each type of task in the workflow. Typically, task types vary widely in their computational demands because they are simply wrappers for arbitrary black-box analysis tools. Furthermore, the resource consumption for the same task type can vary considerably as well due to different inputs. Since underestimating memory resources leads to bottlenecks and task failures, workflow developers tend to overestimate memory resources. However, overprovisioning of memory wastes resources and limits cluster throughput. Addressing this problem, we propose Sizey, a novel online memory prediction method for workflow tasks. During workflow execution, Sizey simultaneously trains multiple machine learning models and then dynamically selects the best model for each workflow task. To evaluate the quality of the model, we introduce a novel resource allocation quality (RAQ) score based on memory prediction accuracy and efficiency. Sizey's prediction models are retrained and re-evaluated online during workflow execution, continuously incorporating metrics from completed tasks. Our evaluation with a prototype implementation of Sizey uses metrics from six real-world scientific workflows from the popular nf-core framework and shows a median reduction in memory waste over time of 24.68% compared to the respective best-performing state-of-the-art baseline., Comment: Paper accepted in 2024 IEEE International Conference on Cluster Computing (CLUSTER)

While text-to-image diffusion models have been shown to achieve state-of-the-art results in image synthesis, they have yet to prove their effectiveness in downstream applications. Previous work has proposed to generate data for image classifier training given limited real data access. However, these methods struggle to generate in-distribution images or depict fine-grained features, thereby hindering the generalization of classification models trained on synthetic datasets. We propose DataDream, a framework for synthesizing classification datasets that more faithfully represents the real data distribution when guided by few-shot examples of the target classes. DataDream fine-tunes LoRA weights for the image generation model on the few real images before generating the training data using the adapted model. We then fine-tune LoRA weights for CLIP using the synthetic data to improve downstream image classification over previous approaches on a large variety of datasets. We demonstrate the efficacy of DataDream through extensive experiments, surpassing state-of-the-art classification accuracy with few-shot data across 7 out of 10 datasets, while being competitive on the other 3. Additionally, we provide insights into the impact of various factors, such as the number of real-shot and generated images as well as the fine-tuning compute on model performance. The code is available at https://github.com/ExplainableML/DataDream., Comment: Accepted to ECCV 2024

Large Language Models (LLMs) have the potential to revolutionize the Sixth Generation (6G) communication networks. However, current mainstream LLMs generally lack the specialized knowledge in telecom domain. In this paper, for the first time, we propose a pipeline to adapt any general purpose LLMs to a telecom-specific LLMs. We collect and build telecom-specific pre-train dataset, instruction dataset, preference dataset to perform continual pre-training, instruct tuning and alignment tuning respectively. Besides, due to the lack of widely accepted evaluation benchmarks in telecom domain, we extend existing evaluation benchmarks and proposed three new benchmarks, namely, Telecom Math Modeling, Telecom Open QnA and Telecom Code Tasks. These new benchmarks provide a holistic evaluation of the capabilities of LLMs including math modeling, Open-Ended question answering, code generation, infilling, summarization and analysis in telecom domain. Our fine-tuned LLM TelecomGPT outperforms state of the art (SOTA) LLMs including GPT-4, Llama-3 and Mistral in Telecom Math Modeling benchmark significantly and achieve comparable performance in various evaluation benchmarks such as TeleQnA, 3GPP technical documents classification, telecom code summary and generation and infilling., Comment: arXiv admin note: text overlap with arXiv:1303.2654 by other authors

Integrated sensing and communication (ISAC) has emerged as a promising technology to facilitate high-rate communications and super-resolution sensing, particularly operating in the millimeter wave (mmWave) band. However, the vulnerability of mmWave signals to blockages severely impairs ISAC capabilities and coverage. To tackle this, an efficient and low-cost solution is to deploy distributed reconfigurable intelligent surfaces (RISs) to construct virtual links between the base stations (BSs) and users in a controllable fashion. In this paper, we investigate the generalized RIS-assisted mmWave ISAC networks considering the blockage effect, and examine the beneficial impact of RISs on the coverage rate utilizing stochastic geometry. Specifically, taking into account the coupling effect of ISAC dual functions within the same network topology, we derive the conditional coverage probability of ISAC performance for two association cases, based on the proposed beam pattern model and user association policies. Then, the marginal coverage rate is calculated by combining these two cases through the distance-dependent thinning method. Simulation results verify the accuracy of derived theoretical formulations and provide valuable guidelines for the practical network deployment. Specifically, our results indicate the superiority of the RIS deployment with the density of 40 km${}^{-2}$ BSs, and that the joint coverage rate of ISAC performance exhibits potential growth from $67.1\%$ to $92.2\%$ with the deployment of RISs.

In this paper we argue that Neuro-Symbolic AI (NeSy-AI) should be applied for patient monitoring. In this context, we introduce patient monitoring as a special case of Human Activity Recognition and derive concrete requirements for this application area. We then present a process architecture and discuss why NeSy-AI should be applied for patient monitoring. To further support our argumentation, we show how NeSy-AI can help to overcome certain technical challenges that arise from this application area., Comment: Accepted at PharML@ECMLPKDD23

Topological materials provide a platform that utilizes the geometric characteristics of structured materials to control the flow of waves, enabling unidirectional and protected transmission that is immune to defects or impurities. The topologically designed photonic materials can carry quantum states and electromagnetic energy, benefiting nanolasers or quantum photonic systems. This article reviews recent advances in the topological applications of photonic materials for radiative heat transfer, especially in the near field. When the separation distance between media is considerably smaller than the thermal wavelength, the heat transfer exhibits super-Planckian behavior that surpasses Planck's blackbody predictions. Near-field thermal radiation in subwavelength systems supporting surface modes has various applications, including nanoscale thermal management and energy conversion. Photonic materials and structures that support topological surface states show immense potential for enhancing or suppressing near-field thermal radiation. We present various topological effects, such as periodic and quasi-periodic nanoparticle arrays, Dirac and Weyl semimetal-based materials, structures with broken global symmetries, and other topological insulators, on near-field heat transfer. Also, the possibility of realizing near-field thermal radiation in such topological materials for alternative thermal management and heat flux guiding in nano-scale systems is discussed based on the existing technology.

This paper describes how to propagate wavefields for arbitrary numbers of traditional time steps in a single step, called a superstep. We show how to construct operators that accomplish this task for finite-difference time domain schemes, including temporal first-order schemes in isotropic, anisotropic and elastic media, as well as temporal second-order schemes for acoustic media. This task is achieved by implementing a computational tradeoff differing from traditional single step wavefield propagators by precomputing propagator matrices for each model location for k timesteps (a superstep) and using these propagator matrices to advance the wavefield k time steps at once. This tradeoff separates the physics of the propagator matrix computation from the computer science of wavefield propagation and allows each discipline to provide their optimal modular solutions.

In 1996, Gersten proved that finitely presented subgroups of a word hyperbolic group of integral cohomological dimension 2 are hyperbolic. We use isoperimetric inequalities over arbitrary rings to extend this result to any ring. In particular, we study the discrete isoperimetric function and show that its linearity is equivalent to hyperbolicity, which is also equivalent to it being subquadratic. We further use these ideas to obtain conditions for subgroups of higher rank hyperbolic groups to be again higher rank hyperbolic of the same rank. The appendix discusses the equivalence between isoperimetric inequalities and coning inequalities in the simplicial setting and the general setting, leading to combinatorial definitions of higher rank hyperbolicity in the setting of simplicial complexes and allowing us to give elementary definitions of higher rank hyperbolic groups., Comment: 27 pages

Millimeter-wave (mmWave) multiple-input multiple-output (MIMO) communication with the advanced beamforming technologies is a key enabler to meet the growing demands of future mobile communication. However, the dynamic nature of cellular channels in large-scale urban mmWave MIMO communication scenarios brings substantial challenges, particularly in terms of complexity and robustness. To address these issues, we propose a robust gradient-based liquid neural network (GLNN) framework that utilizes ordinary differential equation-based liquid neurons to solve the beamforming problem. Specifically, our proposed GLNN framework takes gradients of the optimization objective function as inputs to extract the high-order channel feature information, and then introduces a residual connection to mitigate the training burden. Furthermore, we use the manifold learning technique to compress the search space of the beamforming problem. These designs enable the GLNN to effectively maintain low complexity while ensuring strong robustness to noisy and highly dynamic channels. Extensive simulation results demonstrate that the GLNN can achieve 4.15% higher spectral efficiency than that of typical iterative algorithms, and reduce the time consumption to only 1.61% that of conventional methods., Comment: Accepted by IEEE Wireless Communications Letters

This paper outlines our submission to the MEDIQA2024 Multilingual and Multimodal Medical Answer Generation (M3G) shared task. We report results for two standalone solutions under the English category of the task, the first involving two consecutive API calls to the Claude 3 Opus API and the second involving training an image-disease label joint embedding in the style of CLIP for image classification. These two solutions scored 1st and 2nd place respectively on the competition leaderboard, substantially outperforming the next best solution. Additionally, we discuss insights gained from post-competition experiments. While the performance of these two solutions have significant room for improvement due to the difficulty of the shared task and the challenging nature of medical visual question answering in general, we identify the multi-stage LLM approach and the CLIP image classification approach as promising avenues for further investigation.

A nonlinear-dynamical algorithm for city planning is proposed as an Impulse Pattern Formulation (IPF) for predicting relevant parameters like health, artistic freedom, or financial developments of different social or political stakeholders over the cause of a planning process. The IPF has already shown high predictive precision at low computational cost in musical instrument simulations, brain dynamics, and human-human interactions. The social and political IPF consists of three basic equations of system state developments, self-adaptation of stakeholders, two adaptive interactions, and external impact terms suitable for respective planning situations. Typical scenarios of stakeholder interactions and developments are modeled by adjusting a set of system parameters. These include stakeholder reaction to external input, enhanced system stability through self-adaptation, stakeholder convergence due to adaptive interaction, as well as complex dynamics in terms of fixed stakeholder impacts. A workflow for implementing the algorithm in real city planning scenarios is outlined. This workflow includes machine learning of a suitable set of parameters suggesting best-practice planning to aim at the desired development of the planning process and its output.