Search

We consider log-correlated random fields $X$ and the associated multiplicative chaos measures $\mu_{\gamma,X}$. Our results reconstruct the underlying field $X$ from the multiplicative chaos measure $\nu_{\gamma,X}$. The new feature of our results is that we allow the dimension $d$ to be arbitrary and cover also the critical case $\gamma=\sqrt{2d}$. In the sub-critical regime $\gamma<\sqrt{2d}$, we allow the fields to be mildly non-Gaussian, that is, the field has the decomposition $X=G+H$ with a log-correlated Gaussian field $G$ and a H\"older-continuos (not necessarily Gaussian) field $H$., Comment: 39 pages, 1 figure

Non-prehensile object transportation offers a way to enhance robotic performance in object manipulation tasks, especially with unstable objects. Effective trajectory planning requires simultaneous consideration of robot motion constraints and object stability. Here, we introduce a physical model for object stability and propose a novel trajectory planning approach for non-prehensile transportation along arbitrary straight lines in 3D space. Validation with a 7-DoF Franka Panda robot confirms improved transportation speed via tray rotation integration while ensuring object stability and robot motion constraints., Comment: Accepted to the European Robotic Forum (ERF) 2024

Cardinality estimation is crucial for enabling high query performance in relational databases. Recently learned cardinality estimation models have been proposed to improve accuracy but there is no systematic benchmark or datasets which allows researchers to evaluate the progress made by new learned approaches and even systematically develop new learned approaches. In this paper, we are releasing a benchmark, containing thousands of queries over 20 distinct real-world databases for learned cardinality estimation. In contrast to other initial benchmarks, our benchmark is much more diverse and can be used for training and testing learned models systematically. Using this benchmark, we explored whether learned cardinality estimation can be transferred to an unseen dataset in a zero-shot manner. We trained GNN-based and transformer-based models to study the problem in three setups: 1-) instance-based, 2-) zero-shot, and 3-) fine-tuned. Our results show that while we get promising results for zero-shot cardinality estimation on simple single table queries; as soon as we add joins, the accuracy drops. However, we show that with fine-tuning, we can still utilize pre-trained models for cardinality estimation, significantly reducing training overheads compared to instance specific models. We are open sourcing our scripts to collect statistics, generate queries and training datasets to foster more extensive research, also from the ML community on the important problem of cardinality estimation and in particular improve on recent directions such as pre-trained cardinality estimation.

Prosthetic limb abandonment remains an unsolved challenge as amputees consistently reject their devices. Current prosthetic designs often fail to balance human-like perfomance with acceptable device weight, highlighting the need for optimised designs tailored to modern tasks. This study aims to provide a comprehensive dataset of joint kinematics and kinetics essential for performing activities of daily living (ADL), thereby informing the design of more functional and user-friendly prosthetic devices. Functionally required Ranges of Motion (ROM), velocities, and torques for the Glenohumeral (rotation), elbow, Radioulnar, and wrist joints were computed using motion capture data from 12 subjects performing 24 ADLs. Our approach included the computation of joint torques for varying mass and inertia properties of the upper limb, while torques induced by the manipulation of experimental objects were considered by their interaction wrench with the subjects hand. Joint torques pertaining to individual ADL scaled linearly with limb and object mass and mass distribution, permitting their generalisation to not explicitly simulated limb and object dynamics with linear regressors (LRM), exhibiting coefficients of determination R = 0.99 pm 0.01. Exemplifying an application of data-driven prosthesis design, we optimise wrist axes orientations for two serial and two differential joint configurations. Optimised axes reduced peak power requirements, between 22 to 38 percent compared to anatomical configurations, by exploiting high torque correlations between Ulnar deviation and wrist flexion/extension joints. This study offers critical insights into the functional requirements of upper limb prostheses, providing a valuable foundation for data-driven prosthetic design that addresses key user concerns and enhances device adoption., Comment: Accepted at IROS 2024

Despite recent advancements in torque-controlled tactile robots, integrating them into manufacturing settings remains challenging, particularly in complex environments. Simplifying robotic skill programming for non-experts is crucial for increasing robot deployment in manufacturing. This work proposes an innovative approach, Vision-Augmented Unified Force-Impedance Control (VA-UFIC), aimed at intuitive visuo-tactile exploration of unknown 3D curvatures. VA-UFIC stands out by seamlessly integrating vision and tactile data, enabling the exploration of diverse contact shapes in three dimensions, including point contacts, flat contacts with concave and convex curvatures, and scenarios involving contact loss. A pivotal component of our method is a robust online contact alignment monitoring system that considers tactile error, local surface curvature, and orientation, facilitating adaptive adjustments of robot stiffness and force regulation during exploration. We introduce virtual energy tanks within the control framework to ensure safety and stability, effectively addressing inherent safety concerns in visuo-tactile exploration. Evaluation using a Franka Emika research robot demonstrates the efficacy of VA-UFIC in exploring unknown 3D curvatures while adhering to arbitrarily defined force-motion policies. By seamlessly integrating vision and tactile sensing, VA-UFIC offers a promising avenue for intuitive exploration of complex environments, with potential applications spanning manufacturing, inspection, and beyond., Comment: 8 pages, 3 figures, accepted by IROS 2024

Ca II K observations of the Sun have a great potential for probing the Sun's magnetism and activity, as well as for reconstructing solar irradiance. The Kodaikanal Solar Observatory (KoSO) in India, houses one of the most prominent Ca II K archives, spanning from 1904 to 2007, obtained under the same experimental conditions over a century, a feat very few other sites have achieved. However, the KoSO Ca II K archive suffers from several inconsistencies (e.g., missing/incorrect timestamps of observations and orientation of some images) which have limited the use of the archive. This study is a step towards bringing the KoSO archive to its full potential. We did this by developing an automatic method to orient the images more accurately than in previous studies. Furthermore, we included more data than in earlier studies (considering images that could not previously be analyzed by other techniques as well as 2845 newly digitized images), while also accounting for mistakes in the observational date/time. These images were accurately processed to identify plage regions along with their locations, enabling us to construct the butterfly diagram of plage areas from the entire KoSO Ca II K archive covering 1904-2007. Our butterfly diagram shows significantly fewer data gaps compared to earlier versions due to the larger set of data used in this study. Moreover, our butterfly diagram is consistent with Sp\"orer's law for sunspots, validating our automatic image orientation method. Additionally, we found that the mean latitude of plage areas calculated over the entire period is 20.5%+/-2.0 higher than that of sunspots, irrespective of the phase or the strength of the solar cycle. We also studied the North-South asymmetry showing that the northern hemisphere dominated plage areas during solar cycles 19 and 20, while the southern hemisphere dominated during solar cycles 21--23., Comment: 15 pages, 9 figures, Under Review in Solar Physics

This study addresses the absence of an identification framework to quantify a comprehensive dynamic model of human and anthropomorphic tendon-driven fingers, which is necessary to investigate the physiological properties of human fingers and improve the control of robotic hands. First, a generalized dynamic model was formulated, which takes into account the inherent properties of such a mechanical system. This includes rigid-body dynamics, coupling matrix, joint viscoelasticity, and tendon friction. Then, we propose a methodology comprising a series of experiments, for step-wise identification and validation of this dynamic model. Moreover, an experimental setup was designed and constructed that features actuation modules and peripheral sensors to facilitate the identification process. To verify the proposed methodology, a 3D-printed robotic finger based on the index finger design of the Dexmart hand was developed, and the proposed experiments were executed to identify and validate its dynamic model. This study could be extended to explore the identification of cadaver hands, aiming for a consistent dataset from a single cadaver specimen to improve the development of musculoskeletal hand models., Comment: 8 pages, 9 figures

Robotic manipulation is essential for modernizing factories and automating industrial tasks like polishing, which require advanced tactile abilities. These robots must be easily set up, safely work with humans, learn tasks autonomously, and transfer skills to similar tasks. Addressing these needs, we introduce the tactile-morph skill framework, which integrates unified force-impedance control with data-driven learning. Our system adjusts robot movements and force application based on estimated energy levels for the desired trajectory and force profile, ensuring safety by stopping if energy allocated for the control runs out. Using a Temporal Convolutional Network, we estimate the energy distribution for a given motion and force profile, enabling skill transfer across different tasks and surfaces. Our approach maintains stability and performance even on unfamiliar geometries with similar friction characteristics, demonstrating improved accuracy, zero-shot transferable performance, and enhanced safety in real-world scenarios. This framework promises to enhance robotic capabilities in industrial settings, making intelligent robots more accessible and valuable., Comment: 15 pages, 7 figures,updated footnote

Recent studies show that large language models (LLMs) struggle with technical standards in telecommunications. We propose a fine-tuned retrieval-augmented generation (RAG) system based on the Phi-2 small language model (SLM) to serve as an oracle for communication networks. Our developed system leverages forward-looking semantic chunking to adaptively determine parsing breakpoints based on embedding similarity, enabling effective processing of diverse document formats. To handle the challenge of multiple similar contexts in technical standards, we employ a re-ranking algorithm to prioritize the most relevant retrieved chunks. Recognizing the limitations of Phi-2's small context window, we implement a recent technique, namely SelfExtend, to expand the context window during inference, which not only boosts the performance but also can accommodate a wider range of user queries and design requirements from customers to specialized technicians. For fine-tuning, we utilize the low-rank adaptation (LoRA) technique to enhance computational efficiency during training and enable effective fine-tuning on small datasets. Our comprehensive experiments demonstrate substantial improvements over existing question-answering approaches in the telecom domain, achieving performance that exceeds larger language models such as GPT-4 (which is about 880 times larger in size). This work presents a novel approach to leveraging SLMs for communication networks, offering a balance of efficiency and performance. This work can serve as a foundation towards agentic language models for networks., Comment: submitted to Proc. IEEE Globecom

Using the optimal sampling model, we synthesized the embedded clusters of ATLASGAL clumps with HII regions (HII-clumps). The 0.1 Myr isochrone was used to estimate the bolometric luminosity of each star in an embedded cluster, we also added the accretion luminosity of each star in the embeded cluster. The total bolometric luminosity of synthetic embedded clusters can well fit the observed bolometric luminosity of HII-clumps. More realistically, we considered the age spread in the young star and protostar populations in embedded clusters of HII-clumps by modeling both constant and time-varying star formation histories (SFHs). According to the age distribution of the stellar population, we distributed the appropriate isochrones to each star, and sorted out the fraction of stellar objects that are still protostars (Class 0 and Class I phases) to properly add their accretion luminosities. Compared to a constant SFH, burst-like and time-dependent SFHs can better fit the observational data. We found that as long as 20\% of the stars within the embedded cluster are still accreting, the contribution of accretion luminosity will be significant to the total bolometric luminosity of low-mass HII-clumps with mass log$_{10}$(M$_{\rm cl}$/M$_{\odot}$) $<$ 2.8. Variations in the accretion rate, the SFE and the initial mass function (IMF) and more physical processes like the external heating from HII regions and the flaring from pre-main sequence (PMS) stars and protostars need to be investigated to further explain the excess luminosity of low-mass HII-clumps., Comment: 7 pages, 10 figures, Accepted for publication

Requirements Engineering (RE) plays a pivotal role in software development, encompassing tasks such as requirements elicitation, analysis, specification, and change management. Despite its critical importance, RE faces challenges including communication complexities, early-stage uncertainties, and accurate resource estimation. This study empirically investigates the effectiveness of utilizing Large Language Models (LLMs) to automate requirements analysis tasks. We implemented a multi-agent system that deploys AI models as agents to generate user stories from initial requirements, assess and improve their quality, and prioritize them using a selected technique. In our implementation, we deployed four models, namely GPT-3.5, GPT-4 Omni, LLaMA3-70, and Mixtral-8B, and conducted experiments to analyze requirements on four real-world projects. We evaluated the results by analyzing the semantic similarity and API performance of different models, as well as their effectiveness and efficiency in requirements analysis, gathering users' feedback on their experiences. Preliminary results indicate notable variations in task completion among the models. Mixtral-8B provided the quickest responses, while GPT-3.5 performed exceptionally well when processing complex user stories with a higher similarity score, demonstrating its capability in deriving accurate user stories from project descriptions. Feedback and suggestions from the four project members further corroborate the effectiveness of LLMs in improving and streamlining RE phases.

Supply optimization is a complex and challenging task in the magazine retail industry because of the fixed inventory assumption, irregular sales patterns, and varying product and point-of-sale characteristics. We introduce AthenIA, an industrialized magazine supply optimization solution that plans the supply for over 20,000 points of sale in France. We modularize the supply planning process into a four-step pipeline: demand sensing, optimization, business rules, and operating. The core of the solution is a novel group conformalized quantile regression method that integrates domain expert insights, coupled with a supply optimization technique that balances the costs of out-of-stock against the costs of over-supply. AthenIA has proven to be a valuable tool for magazine publishers, particularly in the context of evolving economic and ecological challenges.

Voice signals originating from the respiratory tract are utilized as valuable acoustic biomarkers for the diagnosis and assessment of respiratory diseases. Among the employed acoustic features, Mel Frequency Cepstral Coefficients (MFCC) is widely used for automatic analysis, with MFCC extraction commonly relying on default parameters. However, no comprehensive study has systematically investigated the impact of MFCC extraction parameters on respiratory disease diagnosis. In this study, we address this gap by examining the effects of key parameters, namely the number of coefficients, frame length, and hop length between frames, on respiratory condition examination. Our investigation uses four datasets: the Cambridge COVID-19 Sound database, the Coswara dataset, the Saarbrucken Voice Disorders (SVD) database, and a TACTICAS dataset. The Support Vector Machine (SVM) is employed as the classifier, given its widespread adoption and efficacy. Our findings indicate that the accuracy of MFCC decreases as hop length increases, and the optimal number of coefficients is observed to be approximately 30. The performance of MFCC varies with frame length across the datasets: for the COVID-19 datasets (Cambridge COVID-19 Sound database and Coswara dataset), performance declines with longer frame lengths, while for the SVD dataset, performance improves with increasing frame length (from 50 ms to 500 ms). Furthermore, we investigate the optimized combination of these parameters and observe substantial enhancements in accuracy. Compared to the worst combination, the SVM model achieves an accuracy of 81.1%, 80.6%, and 71.7%, with improvements of 19.6%, 16.10%, and 14.90% for the Cambridge COVID-19 Sound database, the Coswara dataset, and the SVD dataset respectively.

This study addresses the critical need for diverse and comprehensive data focused on human arm joint torques while performing activities of daily living (ADL). Previous studies have often overlooked the influence of objects on joint torques during ADL, resulting in limited datasets for analysis. To address this gap, we propose an Object Augmentation Algorithm (OAA) capable of augmenting existing marker-based databases with virtual object motions and object-induced joint torque estimations. The OAA consists of five phases: (1) computing hand coordinate systems from optical markers, (2) characterising object movements with virtual markers, (3) calculating object motions through inverse kinematics (IK), (4) determining the wrench necessary for prescribed object motion using inverse dynamics (ID), and (5) computing joint torques resulting from object manipulation. The algorithm's accuracy is validated through trajectory tracking and torque analysis on a 7+4 degree of freedom (DoF) robotic hand-arm system, manipulating three unique objects. The results show that the OAA can accurately and precisely estimate 6 DoF object motion and object-induced joint torques. Correlations between computed and measured quantities were > 0.99 for object trajectories and > 0.93 for joint torques. The OAA was further shown to be robust to variations in the number and placement of input markers, which are expected between databases. Differences between repeated experiments were minor but significant (p < 0.05). The algorithm expands the scope of available data and facilitates more comprehensive analyses of human-object interaction dynamics., Comment: An open source implementation of the described algorithm is available at https://github.com/ChristopherHerneth/ObjectAugmentationAlgorithm/tree/main. Accompanying video material may be found here https://youtu.be/8oz-awvyNRA. The article was accepted at IROS 2024

In the context of relativistic heavy-ion collisions, we explore the stochastic and dissipative relaxational dynamics of a non-conserved order parameter in a $\lambda\varphi^4$ interaction. The cutoff of the theory is provided by the lattice spacing chosen for our numerical simulations. As a consequence, observables become dependent on that scale. We consider a possible first-order phase transition and an evolution close to a critical point. We demonstrate that using a lattice counterterm restores the expected behavior of the mean, variance and kurtosis: the mean and the variance become lattice spacing independent, and we recover the correct expectation value of the mean, the growth of the variance with the correlation length and the expected minimum in the kurtosis. Our findings hold true in equilibrium and during the dynamical relaxation, and therefore mark an important step towards a fully fluctuating fluid dynamical setup.

Safety for physical human-robot interaction (pHRI) is a major concern for all application domains. While current standardization for industrial robot applications provide safety constraints that address the onset of pain in blunt impacts, these impact thresholds are difficult to use on edged or pointed impactors. The most severe injuries occur in constrained contact scenarios, where crushing is possible. Nevertheless, situations potentially resulting in constrained contact only occur in certain areas of a workspace and design or organisational approaches can be used to avoid them. What remains are risks to the human physical integrity caused by unconstrained accidental contacts, which are difficult to avoid while maintaining robot motion efficiency. Nevertheless, the probability and severity of injuries occurring with edged or pointed impacting objects in unconstrained collisions is hardly researched. In this paper, we propose an experimental setup and procedure using two pendulums modeling human hands and arms and robots to understand the injury potential of unconstrained collisions of human hands with edged objects. Pig feet are used as ex vivo surrogate samples - as these closely resemble the physiological characteristics of human hands - to create an initial injury database on the severity of injuries caused by unconstrained edged or pointed impacts. For the effective mass range of typical lightweight robots, the data obtained show low probabilities of injuries such as skin cuts or bone/tendon injuries in unconstrained collisions when the velocity is reduced to < 0.5 m/s. The proposed experimental setups and procedures should be complemented by sufficient human modeling and will eventually lead to a complete understanding of the biomechanical injury potential in pHRI., Comment: \c{opyright} 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 works

We study the possibility of accommodating both early and late-time tensions using a novel reinforcement learning technique. By applying this technique, we aim to optimize the evolution of the Hubble parameter from recombination to the present epoch, addressing both tensions simultaneously. To maximize the goodness of fit, our learning technique achieves a fit that surpasses even the $\Lambda$CDM model. Our results demonstrate a tendency to weaken both early and late time tensions in a completely model-independent manner., Comment: 17 pages, 4 figures

Recent research has seen notable progress in the development of linkage-based artificial hands. While previous designs have focused on adaptive grasping, dexterity and biomimetic artificial skin, only a few systems have proposed a lightweight, accessible solution integrating tactile sensing with a compliant linkage-based mechanism. This paper introduces OPENGRASP LITE, an open-source, highly integrated, tactile, and lightweight artificial hand. Leveraging compliant linkage systems and MEMS barometer-based tactile sensing, it offers versatile grasping capabilities with six degrees of actuation. By providing tactile sensors and enabling soft grasping, it serves as an accessible platform for further research in tactile artificial hands., Comment: Accepted at IEEE/RSJ International Conference on Intelligent Robots and Systems, 14-18 October 2024

Trauma significantly impacts global health, accounting for over 5 million deaths annually, which is comparable to mortality rates from diseases such as tuberculosis, AIDS, and malaria. In Iran, the financial repercussions of road traffic accidents represent approximately 2% of the nation's Gross National Product each year. Bleeding is the leading cause of mortality in trauma patients within the first 24 hours following an injury, making rapid diagnosis and assessment of severity crucial. Trauma patients require comprehensive scans of all organs, generating a large volume of data. Evaluating CT images for the entire body is time-consuming and requires significant expertise, underscoring the need for efficient time management in diagnosis. Efficient diagnostic processes can significantly reduce treatment costs and decrease the likelihood of secondary complications. In this context, the development of a reliable Decision Support System (DSS) for trauma triage, particularly focused on the abdominal area, is vital. This paper presents a novel method for detecting liver bleeding and lacerations using CT scans, utilising the GAN Pix2Pix translation model. The effectiveness of the method is quantified by Dice score metrics, with the model achieving an accuracy of 97% for liver bleeding and 93% for liver laceration detection. These results represent a notable improvement over current state-of-the-art technologies. The system's design integrates seamlessly with existing medical imaging technologies, making it a practical addition to emergency medical services. This research underscores the potential of advanced image translation models like GAN Pix2Pix in improving the precision and speed of medical diagnostics in critical care scenarios.

The industrial point of view towards integrated sensing and communication (ISAC), the preference is to leverage existing resources and fifth-generation (5G) infrastructure to minimize deployment costs and complexity. In this context, we explore the utilization of current 5G new radio (NR) signals aligned with 3rd generation partnership project (3GPP) standards. Positioning reference signals (PRS) for sensing and physical downlink shared channel (PDSCH) for communication have been chosen to form an ISAC framework. However, PRS-based sensing suffers from Doppler ambiguity when the Doppler frequency shift is severe. To address this challenge, we introduce a novel method within the ISAC system that leverages the demodulation reference signal (DMRS) present in PDSCH to eliminate Doppler ambiguity. Furthermore, we formulate a resource allocation problem between PRS and PDSCH to achieve a Pareto optimal point between communication and sensing without Doppler ambiguity. Through simulations and analysis, we demonstrate the effectiveness of our proposed method on joint DMRS-PRS exploitation in mitigating Doppler ambiguity and the efficiency of the resource allocation scheme in achieving Pareto optimality for ISAC within a 5G NR framework., Comment: 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 works

From the industrial standpoint on integrated sensing and communication (ISAC), the preference lies in augmenting existing infrastructure with sensing services while minimizing network changes and leveraging available resources. This paper investigates the potential of utilizing the existing infrastructure of fifth-generation (5G) new radio (NR) signals as defined by the 3rd generation partnership project (3GPP), particularly focusing on pilot signals for sensing within the ISAC framework. We propose to take advantage of the existing positioning reference signal (PRS) for sensing and the physical downlink shared channel (PDSCH) for communication, both readily available in 5G NR. However, the use of PRS for sensing poses challenges, leading to the appearance of ghost targets. To overcome this obstacle, we propose two innovative approaches for different PRS comb sizes within the ISAC framework, leveraging the demodulation reference signal (DMRS) within PDSCH to eliminate ghost targets. Subsequently, we formulate a resource allocation problem between PRS and PDSCH and determine the Pareto optimal point between communication and sensing without ghost targets. Through comprehensive simulation and analysis, we demonstrate that the joint exploitation of DMRS and PRS offers a promising solution for ghost target removal, while effective time and frequency resource allocation enables the achievement of Pareto optimality in ISAC., Comment: 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 works

Recent advancements in propagation-based phase-contrast imaging, such as hierarchical imaging, have enabled the visualization of internal structures in large biological specimens and material samples. However, wavefront marker-based techniques, which provide quantitative electron density information, face challenges when imaging larger objects due to stringent beam stability requirements and potential structural changes in objects during longer measurements. Extending the fields-of-view of these methods is crucial for obtaining comparable quantitative results across beamlines and adapting to the smaller beam profiles of fourth-generation synchrotron sources. We introduce a novel technique combining an adapted eigenflat optimization with deformable image registration to address the challenges and enable quantitative high-resolution scans of centimeter-sized objects with micrometre resolution. We demonstrate the potential of the method by obtaining an electron density map of a rat brain sample 15 mm in diameter using speckle-based imaging, despite the limited horizontal field-of-view of 6 mm of the beamline (PETRA III, P05, operated by Hereon at DESY). This showcases the ability of the technique to significantly widen the range of application of wavefront marker-based techniques in both biological and materials science research., Comment: *The authors contributed equally to this work

A drawing robot avatar is a robotic system that allows for telepresence-based drawing, enabling users to remotely control a robotic arm and create drawings in real-time from a remote location. The proposed control framework aims to improve bimanual robot telepresence quality by reducing the user workload and required prior knowledge through the automation of secondary or auxiliary tasks. The introduced novel method calculates the near-optimal Cartesian end-effector pose in terms of visual feedback quality for the attached eye-to-hand camera with motion constraints in consideration. The effectiveness is demonstrated by conducting user studies of drawing reference shapes using the implemented robot avatar compared to stationary and teleoperated camera pose conditions. Our results demonstrate that the proposed control framework offers improved visual feedback quality and drawing performance., Comment: Accepted to ICRA 2024

We used the dendrogram algorithm to decompose the surface density distributions of stars into hierarchical structures. These structures were tied to the multiscale structures of star clusters. A similar power-law for the mass-size relation of star clusters measured at different scales suggests a self-similar structure of star clusters. We used the minimum spanning tree method to measure the separations between clusters and gas clumps in each massive star-forming region. The separations between clusters, between clumps, and between clusters and clumps were comparable, which indicates that the evolution from clump to embedded cluster proceeds in isolation and locally, and does not affect the surrounding objects significantly. By comparing the mass functions of the ATLASGAL clumps and the identified embedded clusters, we confirm that a constant star formation efficiency of $\approx$ 0.33 can be a typical value for the ATLASGAL clumps., Comment: 6 pages, 8 figures, Accepted for publication in A&A

Many systems occurring in real-world applications, such as controlling the motions of robots or modeling the spread of diseases, are switched impulsive systems. To ensure that the system state stays in a safe region (e.g., to avoid collisions with obstacles), barrier functions are widely utilized. As the system dimension increases, deriving suitable barrier functions becomes extremely complex. Fortunately, many systems consist of multiple subsystems, such as different areas where the disease occurs. In this work, we present sufficient conditions for interconnected switched impulsive systems to maintain safety by constructing local barrier functions for the individual subsystems instead of a global one, allowing for much easier and more efficient derivation. To validate our results, we numerically demonstrate its effectiveness using an epidemiological model., Comment: Accepted for publication in the proceedings of the IEEE 63rd Conference on Decision and Control

Recent advancements in natural language processing (NLP) have led to automation in various domains. However, clinical NLP often relies on benchmark datasets that may not reflect real-world scenarios accurately. Automatic ICD coding, a vital NLP task, typically uses outdated and imbalanced datasets like MIMIC-III, with existing methods yielding micro-averaged F1 scores between 0.4 and 0.7 due to many false positives. Our research introduces an enhanced approach to ICD coding that improves F1 scores by using chapter-based named entities and attentional models. This method categorizes discharge summaries into ICD-9 Chapters and develops attentional models with chapter-specific data, eliminating the need to consider external data for code identification. For categorization, we use Chapter-IV to de-bias and influence key entities and weights without neural networks, creating accurate thresholds and providing interpretability for human validation. Post-validation, we develop attentional models for three frequent and three non-frequent codes from Chapter-IV using Bidirectional-Gated Recurrent Units (GRUs) with Attention and Transformer with Multi-head Attention architectures. The average Micro-F1 scores of 0.79 and 0.81 from these models demonstrate significant performance improvements in ICD coding., Comment: 10 Pages

In this paper, we review in detail different mechanisms of generation of large primordial fluctuations and their implications for the production of primordial black holes (PBHs) and scalar-induced secondary gravity waves (SIGW), with the ultimate aim of understanding the impact of loop correction on quantum correlations and the power spectrum. To accomplish the goal, we provide a concise, comprehensive, but in depth review of conceptual and technical details of the standard model of the universe, namely, causal structure and inflation, quantization of primordial perturbations and field theoretic techniques such as "in-in" formalism needed for the estimation of loop correction to the power spectrum. We discuss at length the severe constraints (no-go) on PBH production in single-field inflation imposed by appropriately renormalized quantum loop corrections, computed while maintaining the validity of the perturbation framework and assuming sufficient inflation to address the causality problem. Thereafter, we discuss in detail the efforts to circumvent the no-go result in Galileon inflation, multiple sharp transition (MST)-induced inflation, and stochastic single field inflation using an effective field theoretic (EFT) framework applicable to a variety of models. We provide a thorough analysis of the Dynamical Renormalization Group (DRG) resummation approach, adiabatic and late-time renormalization schemes, and their use in producing solar and sub-solar mass PBHs. Additionally, we give a summary of how scalar-induced gravitational waves (SIGWs) are produced in MST setups and Galileon inflation.Finally, the PBH overproduction issue is thoroughly discussed., Comment: 322 pages, 80 figures, 7 tables, Invited Physics Reports review, Dedicated to the memory of Alexei A. Starobinsky, Criticism and comments are most welcome

Business users dedicate significant amounts of time to repetitive tasks within enterprise digital platforms, highlighting a critical need for automation. Despite advancements in low-code tools for UI automation, their complexity remains a significant barrier to adoption among non-technical business users. However, recent advancements in large language models (LLMs) have created new opportunities to overcome this barrier by offering more powerful, yet simpler and more human-centric programming environments. This paper presents IDA (Intelligent Digital Apprentice), a novel no-code Web UI automation tool designed specifically to empower business users with no technical background. IDA incorporates human-centric design principles, including guided programming by demonstration, semantic programming model, and teacher-student learning metaphor which is tailored to the skill set of business users. By leveraging LLMs, IDA overcomes some of the key technical barriers that have traditionally limited the possibility of no-code solutions. We have developed a prototype of IDA and conducted a user study involving real world business users and enterprise applications. The promising results indicate that users could effectively utilize IDA to create automation. The qualitative feedback indicates that IDA is perceived as user-friendly and trustworthy. This study contributes to unlocking the potential of AI assistants to enhance the productivity of business users through no-code user interface automation.

The diagnosis of bronchiectasis requires measuring abnormal bronchial dilation. It is confirmed using a chest CT scan, where the key feature is an increased broncho-arterial ratio (BAR) (>0.8 in children), often with bronchial wall thickening. Image processing methods facilitate quicker interpretation and detailed evaluations by lobes and segments. Challenges like inclined nature, oblique orientation, and partial volume effect make it difficult to obtain accurate measurements in the upper and middle lobes using the same algorithms. Therefore, accurate detection and measurement of airway and artery regions for BAR and wall thickness in each lobe require different image processing/machine learning methods. We propose methods for: 1. Separating the right lower lobe (RLL) region from full-length CT scans using the tracheal bifurcation (Carina) point as a central marker; 2. Locating the inner diameter of airways and outer diameter of arteries for BAR measurement; and 3. Measuring airway wall thickness (WT) by identifying the outer and inner diameters of airway boundaries. Analysis of 13 HRCT scans with varying thicknesses (0.67mm, 1mm, 2mm) shows the tracheal bifurcation frame can be detected accurately, with a deviation of +/- 2 frames in some cases. A Windows app was developed for measuring inner airway diameter, artery diameter, BAR, and wall thickness, allowing users to draw boundaries around visible BA pairs in the RLL region. Measurements of 10 BA pairs revealed accurate results comparable to those of a human reader, with deviations of +/- 0.10-0.15mm. Additional studies and validation are needed to consolidate inter- and intra-rater variability and enhance the methods., Comment: 14 pages

We present an analysis method to search for exotic low-mass field (ELF) bursts generated during large energy astrophysical events such as supernovae, binary black hole or binary neutron star mergers, and fast radio bursts using the Global Network of Optical Magnetometers for Exotic physics searches (GNOME). In our model, the associated gravitational waves or electromagnetic signals herald the arrival of the ELF burst that interacts via coupling to the spin of fermions in the magnetometers. This enables GNOME to serve as a tool for multi-messenger astronomy. The algorithm employs a model-agnostic excess-power method to identify network-wide candidate events to be subjected to a model-dependent generalized likelihood-ratio test to determine their statistical significance. We perform the first search with this technique on GNOME data coincident with the binary black hole merger S200311bg detected by LIGO/Virgo on the 11th of March 2020 and find no significant events. We place the first lab-based limits on combinations of ELF production and coupling parameters.

The rapid rise of air pollution events necessitates accurate, real-time monitoring for informed mitigation strategies. Data Assimilation (DA) methods provide promising solutions, but their effectiveness hinges heavily on optimal measurement locations. This paper presents a novel approach for air quality mapping where autonomous drones, guided by a collaborative multi-agent reinforcement learning (MARL) framework, act as airborne detectives. Ditching the limitations of static sensor networks, the drones engage in a synergistic interaction, adapting their flight paths in real time to gather optimal data for Data Assimilation (DA). Our approach employs a tailored reward function with dynamic credit assignment, enabling drones to prioritize informative measurements without requiring unavailable ground truth data, making it practical for real-world deployments. Extensive experiments using a real-world dataset demonstrate that our solution achieves significantly improved pollution estimates, even with limited drone resources or limited prior knowledge of the pollution plume. Beyond air quality, this solution unlocks possibilities for tackling diverse environmental challenges like wildfire detection and management through scalable and autonomous drone cooperation., Comment: 8 pages, 4 figures

Intrinsically elastic robots surpass their rigid counterparts in a range of different characteristics. By temporarily storing potential energy and subsequently converting it to kinetic energy, elastic robots are capable of highly dynamic motions even with limited motor power. However, the time-dependency of this energy storage and release mechanism remains one of the major challenges in controlling elastic robots. A possible remedy is the introduction of locking elements (i.e. clutches and brakes) in the drive train. This gives rise to a new class of robots, so-called clutched-elastic robots (CER), with which it is possible to precisely control the energy-transfer timing. A prevalent challenge in the realm of CERs is the automatic discovery of clutch sequences. Due to complexity, many methods still rely on pre-defined modes. In this paper, we introduce a novel contact-implicit scheme designed to optimize both control input and clutch sequence simultaneously. A penalty in the objective function ensures the prevention of unnecessary clutch transitions. We empirically demonstrate the effectiveness of our proposed method on a double pendulum equipped with two of our newly proposed clutch-based Bi-Stiffness Actuators (BSA)., Comment: Accepted to the 2024 IEEE International Conference on Robotics and Automation (ICRA 2024). The first two authors contributed equally to this work. A cited paper, "Posa M, Cantu C, and Tedrake R (2014)" has a corrigendum (https://doi.org/10.1177/0278364914533878) referencing earlier work by Dr. Kerim Yunt

We aim to test the reliability of determining the line-of-sight magnetic field from a 3D MHD simulation of a unipolar region. In contrast to earlier similar studies, we consider the full solar disk, i.e. considering the full centre-to-limb variation, as well as regions with different averaged field strengths. We synthesised Stokes profiles from MURaM MHD simulations of unipolar regions with varying mean vertical magnetic flux densities, ranging from quiet Sun to active region plage. We did this for a comprehensive range of heliocentric angles: from $\mu=1$ to $\mu=0.15$, and for two commonly used photospheric spectral lines: Fe I $6173.3$ and Fe I $5250.2${\AA}. The line-of-sight magnetic field was derived with a Milne-Eddington Inversion as well as with other commonly used methods. The inferred spatially averaged $\langle B_{LOS}\rangle$ is always lower than that present in the MHD simulations, with the exception of $\mu\approx 1$ and sufficiently high spatial resolution. It is also generally inconsistent with a linear dependence on $\mu$. Above $\mu=0.5$ the spatial resolution greatly impacts the retrieved line-of-sight magnetic field. For $\mu\leq0.5$ the retrieved $B_{LOS}$ is nearly independent of resolution, but is always lower than expected from the simulation. These trends persist regardless of the mean vertical magnetic field in the MHD simulations and are independent of the $B_{LOS}$ retrieval method. For $\mu\leq0.5$, a larger $\langle B_{LOS}\rangle$ is inferred for the $5250.2${\AA} spectral line than $6173.3${\AA}, but the converse is true at higher $\mu$. The results found here raise some doubts of the reliability of determining the radial field by dividing the line-of-sight field by $\mu$ and are of considerable importance for deducing the total magnetic flux of the Sun. They may also contribute to the resolution of the open flux problem., Comment: Submitted to A&A

In computer science, transforming spherical coordinates into Cartesian coordinates is an important mathematical operation. The CORDIC (Coordinate Rotation Digital Computer) iterative algorithm can perform this operation, as well as trigonometric functions and vector rotations, using only simple arithmetic operations like addition, subtraction, and bit-shifting. This research paper presents hardware architecture for a 3-D CORDIC processor using Quartus II 7.1 ALTERA software, which enables easy modifications and design changes due to its regularity and simplicity. The proposed 3-D CORDIC model is evaluated by comparing the calculated results with the simulated results to determine its accuracy. The results were satisfaction and the proposed model could be suitable for numerous real-time applications., Comment: 9 pages, 10 figures, 5 tables, and 21 References. https://www.ijisae.org/index.php/IJISAE/article/view/6302

OpenDiLoCo is an open-source implementation and replication of the Distributed Low-Communication (DiLoCo) training method for large language models. We provide a reproducible implementation of the DiLoCo experiments, offering it within a scalable, decentralized training framework using the Hivemind library. We demonstrate its effectiveness by training a model across two continents and three countries, while maintaining 90-95% compute utilization. Additionally, we conduct ablations studies focusing on the algorithm's compute efficiency, scalability in the number of workers and show that its gradients can be all-reduced using FP16 without any performance degradation. Furthermore, we scale OpenDiLoCo to 3x the size of the original work, demonstrating its effectiveness for billion parameter models.

In the era of 6G, developing and managing software requires cutting-edge software engineering (SE) theories and practices tailored for such complexity across a vast number of connected edge devices. Our project aims to lead the development of sustainable methods and energy-efficient orchestration models specifically for edge environments, enhancing architectural support driven by AI for contemporary edge-to-cloud continuum computing. This initiative seeks to position Finland at the forefront of the 6G landscape, focusing on sophisticated edge orchestration and robust software architectures to optimize the performance and scalability of edge networks. Collaborating with leading Finnish universities and companies, the project emphasizes deep industry-academia collaboration and international expertise to address critical challenges in edge orchestration and software architecture, aiming to drive significant advancements in software productivity and market impact.

The emergence of large language models (LLMs) has transformed research and practice in a wide range of domains. Within the computing education research (CER) domain, LLMs have received plenty of attention especially in the context of learning programming. Much of the work on LLMs in CER has however focused on applying and evaluating proprietary models. In this article, we evaluate the efficiency of open-source LLMs in generating high-quality feedback for programming assignments, and in judging the quality of the programming feedback, contrasting the results against proprietary models. Our evaluations on a dataset of students' submissions to Python introductory programming exercises suggest that the state-of-the-art open-source LLMs (Meta's Llama3) are almost on-par with proprietary models (GPT-4o) in both the generation and assessment of programming feedback. We further demonstrate the efficiency of smaller LLMs in the tasks, and highlight that there are a wide range of LLMs that are accessible even for free for educators and practitioners.

In this paper, we extend the concept of Lie superalgebras to a more generalized framework called Super-Lie superalgebras. In addition, they seem to be exploring various supergeneralizations of other algebraic structures, such as Super-associative, left (right) Super-Leibniz, and Super-left(right)-symmetric superalgebras, then we give some examples and related fundamental results. The notion of Rota-Baxter operators with any parity on the Super-Lie superalgebras is given. Moreover, we study a representations of Super-Lie superalgebras and its associate dual representations. The notion of derivations of Super-Lie superalgebras is introduced thus we show that the converse of a bijective derivation defines a Rota-Baxter operator. Finally, we give a generalization of the Super-Lie superalgebras and some other structures in the ternary case which we supported this with some examples and interesting results.

We study the out-of-equilibrium production of non-minimally coupled self-interacting scalar dark matter during reheating using classical lattice simulations. The outcomes of the classical simulations are in qualitative agreement with the previous results obtained using the quantum 2PI approach in the Hartree truncation. In particular, the novel non-linear resonance found in the 2PI Hartee study is present also in the classical lattice simulations and can dominate the final dark matter yield. For the parameters considered, the difference in final value of the scalar two-point function between the two approaches is a factor of O(1)., Comment: 16 pages, 7 figures. Comments welcome

Morphodynamic descriptions of fluid deformable surfaces are relevant for a range of biological and soft matter phenomena, spanning materials that can be passive or active, as well as ordered or topological. However, a principled, geometric formulation of the correct hydrodynamic equations has remained opaque, with objective rates proving a central, contentious issue. We argue that this is due to a conflation of several important notions that must be disambiguated when describing fluid deformable surfaces. These are the Eulerian and Lagrangian perspectives on fluid motion, and three different types of gauge freedom: in the ambient space; in the parameterisation of the surface, and; in the choice of frame field on the surface. We clarify these ideas, and show that objective rates in fluid deformable surfaces are time derivatives that are invariant under the first of these gauge freedoms, and which also preserve the structure of the ambient metric. The latter condition reduces a potentially infinite number of possible objective rates to only two: the material derivative and the Jaumann rate. The material derivative is invariant under the Galilean group, and therefore applies to velocities, whose rate captures the conservation of momentum. The Jaumann derivative is invariant under all time-dependent isometries, and therefore applies to local order parameters, or symmetry-broken variables, such as the nematic $Q$-tensor. We provide examples of material and Jaumann rates in two different frame fields that are pertinent to the current applications of the fluid mechanics of deformable surfaces., Comment: 27 pages, 4 figures

Skin cancer is a major concern to public health, accounting for one-third of the reported cancers. If not detected early, the cancer has the potential for severe consequences. Recognizing the critical need for effective skin cancer classification, we address the limitations of existing models, which are often too large to deploy in areas with limited computational resources. In response, we present a knowledge distillation based approach for creating a lightweight yet high-performing classifier. The proposed solution involves fusing three models, namely ResNet152V2, ConvNeXtBase, and ViT Base, to create an effective teacher model. The teacher model is then employed to guide a lightweight student model of size 2.03 MB. This student model is further compressed to 469.77 KB using 16-bit quantization, enabling smooth incorporation into edge devices. With six-stage image preprocessing, data augmentation, and a rigorous ablation study, the model achieves an impressive accuracy of 98.75% on the HAM10000 dataset and 98.94% on the Kaggle dataset in classifying benign and malignant skin cancers. With its high accuracy and compact size, our model appears to be a potential choice for accurate skin cancer classification, particularly in resource-constrained settings.

Purpose: To develop a 3D distortion-free reduced-FOV diffusion-prepared GRE sequence and demonstrate its in-vivo application for diffusion imaging of the spinal cord in healthy volunteers. Methods: A 3D multi-shot reduced-FOV diffusion-prepared GRE (RFOV-DP-GRE) acquisition is achieved using a slice-selective tip-down pulse in the phase encoding direction in the diffusion preparation, combined with magnitude stabilisers. The efficacy of the developed reduced FOV approach and accuracy of ADC estimates were evaluated in a phantom. In addition, 5 healthy volunteers were enrolled and scanned at 3T using the proposed sequence and a standard spin echo diffusion-weighted single-shot EPI sequence (DW-SS-EPI) for spinal cord imaging. Image quality, perceived SNR and image distortion were assessed by two expert readers and quantitative measurements of apparent SNR were performed. Results: The phantom scan demonstrates the efficacy of the proposed reduced FOV approach. Consistent ADC estimates were measured with RFOV-DP-GRE when compared with DW-SS-EPI. In-vivo, RFOV-DP-GRE demonstrated improved image quality and reduced perceived distortion, while maintaining perceived SNR compared to DW-SS-EPI. Conclusion: 3D Distortion-free diffusion-prepared imaging can be achieved using the proposed sequence, Comment: 16 pages, 4 figures, submitted to Magnetic Resonance in Medicine

We introduce a general framework for many-body force field models, the Completely Multipolar Model (CMM), that utilizes multipolar electrical moments modulated by exponential decay of electron density as a common functional form for all piecewise terms of an energy decomposition analysis of intermolecular interactions. With this common functional form the CMM model establishes well-formulated damped tensors that reach the correct asymptotes at both long- and short-range while formally ensuring no short-range catastrophes. The CMM describes the separable EDA terms of dispersion, exchange polarization, and Pauli repulsion with short-ranged anisotropy, polarization as intramolecular charge fluctuations and induced dipoles, while charge transfer describes explicit movement of charge between molecules, and naturally describes many-body charge transfer by coupling into the polarization equations. We also utilize a new one-body potential that accounts for intramolecular polarization by including an electric field-dependent correction to the Morse potential to ensure that the CMM reproduces all physically relevant monomer properties including the dipole moment, molecular polarizability, and dipole and polarizability derivatives. The quality of the CMM is illustrated through agreement of individual terms of the EDA and excellent extrapolation to energies and geometries of an extensive validation set of water cluster data.

Tree-based ensemble methods such as random forests, gradient-boosted trees, and Bayesianadditive regression trees have been successfully used for regression problems in many applicationsand research studies. In this paper, we study ensemble versions of probabilisticregression trees that provide smooth approximations of the objective function by assigningeach observation to each region with respect to a probability distribution. We prove thatthe ensemble versions of probabilistic regression trees considered are consistent, and experimentallystudy their bias-variance trade-off and compare them with the state-of-the-art interms of performance prediction.

Dimuon production is in many global parton distribution function analyses calculated by assuming that it is proportional to inclusive charm production. As this assumption breaks down at next-to-leading order in the perturbative expansion, we present a direct calculation of dimuon production that does not require an external acceptance correction. Our calculation utilizes semi-inclusive deep inelastic scattering and a decay function fitted to experimental data. We find our calculation to be in good agreement with available experimental data. Here we also demonstrate that the acceptance correction depends on the used parton distribution and perturbative order., Comment: To appear in the proceedings of the 31st International Workshop on Deep Inelastic Scattering (DIS2024), 8-12 April 2024, Grenoble, France

ESA's PLATO mission aims the detection and characterization of terrestrial planets around solar-type stars as well as the study of host star properties. The noise-to-signal ratio (NSR) is the main performance parameter of the PLATO instrument, which consists of 24 Normal Cameras and 2 Fast Cameras. In order to justify, verify and breakdown NSR-relevant requirements the software simulator PINE was developed. PINE models the signal pathway from a target star to the digital output of a camera based on physical models and considers the major noise contributors. In this paper, the simulator's coarse mode is introduced which allows fast performance analyses on instrument level. The added value of PINE is illustrated by exemplary applications., Comment: 17 pages, 8 figures, 3 tables

Programming skills are typically developed through completing various hands-on exercises. Such programming problems can be contextualized to students' interests and cultural backgrounds. Prior research in educational psychology has demonstrated that context personalization of exercises stimulates learners' situational interests and positively affects their engagement. However, creating a varied and comprehensive set of programming exercises for students to practice on is a time-consuming and laborious task for computer science educators. Previous studies have shown that large language models can generate conceptually and contextually relevant programming exercises. Thus, they offer a possibility to automatically produce personalized programming problems to fit students' interests and needs. This article reports on a user study conducted in an elective introductory programming course that included contextually personalized programming exercises created with GPT-4. The quality of the exercises was evaluated by both the students and the authors. Additionally, this work investigated student attitudes towards the created exercises and their engagement with the system. The results demonstrate that the quality of exercises generated with GPT-4 was generally high. What is more, the course participants found them engaging and useful. This suggests that AI-generated programming problems can be a worthwhile addition to introductory programming courses, as they provide students with a practically unlimited pool of practice material tailored to their personal interests and educational needs., Comment: 19 pages, 12 figures. Accepted for publication at ICER 2024

Large Language Models (LLMs) are widely used in Software Engineering (SE) for various tasks, including generating code, designing and documenting software, adding code comments, reviewing code, and writing test scripts. However, creating test scripts or automating test cases demands test suite documentation that comprehensively covers functional requirements. Such documentation must enable thorough testing within a constrained scope and timeframe, particularly as requirements and user demands evolve. This article centers on generating user requirements as epics and high-level user stories and crafting test case scenarios based on these stories. It introduces a web-based software tool that employs an LLM-based agent and prompt engineering to automate the generation of test case scenarios against user requirements., Comment: 6 pages, 2 figures, and 1 table

Large language models are redefining software engineering by implementing AI-powered techniques throughout the whole software development process, including requirement gathering, software architecture, code generation, testing, and deployment. However, it is still difficult to develop a cohesive platform that consistently produces the best outcomes across all stages. The objective of this study is to develop a unified platform that utilizes multiple artificial intelligence agents to automate the process of transforming user requirements into well-organized deliverables. These deliverables include user stories, prioritization, and UML sequence diagrams, along with the modular approach to APIs, unit tests, and end-to-end tests. Additionally, the platform will organize tasks, perform security and compliance, and suggest design patterns and improvements for non-functional requirements. We allow users to control and manage each phase according to their preferences. In addition, the platform provides security and compliance checks following European standards and proposes design optimizations. We use multiple models, such as GPT-3.5, GPT-4, and Llama3 to enable to generation of modular code as per user choice. The research also highlights the limitations and future research discussions to overall improve the software development life cycle. The source code for our uniform platform is hosted on GitHub, enabling additional experimentation and supporting both research and practical uses. \end

This paper proposes a short-range FMCW radar-based facial authentication and out-of-distribution (OOD) detection framework. Our pipeline jointly estimates the correct classes for the in-distribution (ID) samples and detects the OOD samples to prevent their inaccurate prediction. Our reconstruction-based architecture consists of a main convolutional block with one encoder and multi-decoder configuration, and intermediate linear encoder-decoder parts. Together, these elements form an accurate human face classifier and a robust OOD detector. For our dataset, gathered using a 60 GHz short-range FMCW radar, our network achieves an average classification accuracy of 98.07% in identifying in-distribution human faces. As an OOD detector, it achieves an average Area Under the Receiver Operating Characteristic (AUROC) curve of 98.50% and an average False Positive Rate at 95% True Positive Rate (FPR95) of 6.20%. Also, our extensive experiments show that the proposed approach outperforms previous OOD detectors in terms of common OOD detection metrics., Comment: Accepted at ICIP 2024