Search

Perimetric measurements provide insight into a patient's peripheral vision and day-to-day functioning and are the main outcome measure for identifying progression of visual damage from glaucoma. However, visual field data can be noisy, exhibiting high variance, especially with increasing damage. In this study, we demonstrate the utility of self-supervised deep learning in denoising visual field data from over 4000 patients to enhance its signal-to-noise ratio and its ability to detect true glaucoma progression. We deployed both a variational autoencoder (VAE) and a masked autoencoder to determine which self-supervised model best smooths the visual field data while reconstructing salient features that are less noisy and more predictive of worsening disease. Our results indicate that including a categorical p-value at every visual field location improves the smoothing of visual field data. Masked autoencoders led to cleaner denoised data than previous methods, such as variational autoencoders. A 4.7% increase in detection of progressing eyes with pointwise linear regression (PLR) was observed. The masked and variational autoencoders' smoothed data predicted glaucoma progression 2.3 months earlier when p-values were included compared to when they were not. The faster prediction of time to progression (TTP) and the higher percentage progression detected support our hypothesis that masking out visual field elements during training while including p-values at each location would improve the task of detection of visual field progression. Our study has clinically relevant implications regarding masking when training neural networks to denoise visual field data, resulting in earlier and more accurate detection of glaucoma progression. This denoising model can be integrated into future models for visual field analysis to enhance detection of glaucoma progression., Comment: 10 pages

There is a lack of benchmarks for evaluating large language models (LLMs) in long-form medical question answering (QA). Most existing medical QA evaluation benchmarks focus on automatic metrics and multiple-choice questions. While valuable, these benchmarks fail to fully capture or assess the complexities of real-world clinical applications where LLMs are being deployed. Furthermore, existing studies on evaluating long-form answer generation in medical QA are primarily closed-source, lacking access to human medical expert annotations, which makes it difficult to reproduce results and enhance existing baselines. In this work, we introduce a new publicly available benchmark featuring real-world consumer medical questions with long-form answer evaluations annotated by medical doctors. We performed pairwise comparisons of responses from various open and closed-source medical and general-purpose LLMs based on criteria such as correctness, helpfulness, harmfulness, and bias. Additionally, we performed a comprehensive LLM-as-a-judge analysis to study the alignment between human judgments and LLMs. Our preliminary results highlight the strong potential of open LLMs in medical QA compared to leading closed models. Code & Data: https://github.com/lavita-ai/medical-eval-sphere, Comment: AIM-FM: Advancements in Medical Foundation Models Workshop, 38th Conference on Neural Information Processing Systems (NeurIPS 2024)

The rise of Industry 5.0 has introduced new demands for manufacturing companies, requiring a shift in how production schedules are managed to address human centered, environmental, and economic goals comprehensively. The flexible job shop scheduling problem (FJSSP), which involves processing operations on various capable machines, accurately reflects the complexities of modern manufacturing settings. This paper investigates the FJSSP involving reconfigurable machine tools with configuration dependent setup times, while integrating human aspects like worker assignments, moving time, and rest periods, as well as minimizing total energy consumption. A mixed-integer programming (MIP) model is developed to simultaneously optimize these objectives. The model determines the assignment of operations to machines, workers, and configurations while sequencing operations, scheduling worker movements, and respecting rest periods, and minimizing overall energy consumption. Given the NPhard nature of the FJSSP with worker assignments and reconfigurable tools, a memetic algorithm (MA) is proposed. This metaheuristic evolutionary algorithm features a three layer chromosome encoding method, specialized crossover and mutation strategies, and neighborhood search mechanisms to enhance solution quality and diversity. Comparisons of MA with MIP and genetic algorithms (GA) on benchmark instances demonstrate the MA efficiency and effectiveness, particularly for larger problem instances where MIP becomes impractical. This research paves the way for sustainable and resilient production schedules tailored for the factory of the future under the Industry 5.0 paradigm. The work bridges a crucial gap in current literature by integrating worker and environmental impact into the FJSSP with reconfigurable machine models., Comment: IFIP International Conference on Advances in Production Management Systems (APMS 2024)

Iterative human engagement is a common and effective means of leveraging the advanced language processing power of large language models (LLMs). Using well-structured prompts in a conversational manner, human users can effectively influence an LLM to develop more thoughtful and accurate responses. Motivated by this insight, we propose the Iteration of Thought (IoT) framework for enhancing LLM responses by generating "thought"-provoking prompts vis a vis an input query and the current iteration of an LLM's response. Unlike static or semi-static approaches, e.g. Chain of Thought (CoT) or Tree of Thoughts (ToT), IoT adapts its reasoning path dynamically, based on evolving context, and without generating alternate explorative thoughts which are ultimately discarded. The three components of the IoT framework are (1) an Inner Dialogue Agent (IDA) responsible for generating instructive, context-specific prompts; (2) an LLM Agent (LLMA) that processes these prompts to refine its responses; and (3) an iterative prompting loop that implements a conversation between the former two components. We introduce two variants of our framework: Autonomous Iteration of Thought (AIoT), where an LLM decides when to stop iterating, and Guided Iteration of Thought (GIoT), which always forces a fixed number iterations. We investigate the performance of IoT across various datasets, spanning complex reasoning tasks from the GPQA dataset, explorative problem-solving in Game of 24, puzzle solving in Mini Crosswords, and multi-hop question answering from the HotpotQA dataset. Our results show that IoT represents a viable paradigm for autonomous response refinement in LLMs, showcasing significant improvements over CoT and thereby enabling more adaptive and efficient reasoning systems that minimize human intervention.

In the Internet of Things (IoT) networks, the Routing Protocol forLow-power and Lossy Networks (RPL) is a widely adopted standard due toits efficiency in managing resource-constrained and energy-limited nodes.However, persistent challenges such as high energy consumption, unstablelinks, and suboptimal routing continue to hinder network performance,affecting both the longevity of the network and the reliability of datatransmission. This paper proposes an enhanced RPL routing mechanismby integrating the Tabu Search optimization algorithm to address theseissues. The proposed approach focuses on optimizing the parent and childselection process in the RPL protocol, leveraging a composite cost func-tion that incorporates key parameters including Residual Energy, Trans-mission Energy, Distance to Sink, Hop Count, Expected TransmissionCount (ETX), and Link Stability Rate. Through extensive simulations,we demonstrate that our method significantly improves link stability, re-duces energy consumption, and enhances the packet delivery ratio, leadingto a more efficient and longer-lasting IoT network. The findings suggestthat Tabu Search can effectively balance the trade-offs inherent in IoTrouting, providing a practical solution for improving the overall perfor-mance of RPL-based networks., Comment: 20 Pages

This study introduces a novel methodology for fault detection and cause identification within the Tennessee Eastman Process (TEP) by integrating a Bidirectional Long Short-Term Memory (BiLSTM) neural network with an Integrated Attention Mechanism (IAM). The IAM combines the strengths of scaled dot product attention, residual attention, and dynamic attention to capture intricate patterns and dependencies crucial for TEP fault detection. Initially, the attention mechanism extracts important features from the input data, enhancing the model's interpretability and relevance. The BiLSTM network processes these features bidirectionally to capture long-range dependencies, and the IAM further refines the output, leading to improved fault detection results. Simulation results demonstrate the efficacy of this approach, showcasing superior performance in accuracy, false alarm rate, and misclassification rate compared to existing methods. This methodology provides a robust and interpretable solution for fault detection and diagnosis in the TEP, highlighting its potential for industrial applications.

The $\alpha$-Bernstein operators were initially introduced in the paper by Chen, X., Tan, J., Liu, Z., Xie, J. (2017) titled "Approximation of Functions by a New Family of Generalized Bernstein Operators" (Journal of Mathematical Analysis and Applications, 450(1), 244-261). Since their introduction, these operators have served as a source of inspiration for numerous research endeavors. In this study, we propose a novel technique, founded on a recursive relation, for constructing Bernstein-like bases. A special case of this new representation yields a novel portrayal of Chen's operators. This innovative representation enables the discovery of additional properties of $\alpha$-Bernstein operators and facilitates alternative and more straightforward proofs for certain theorems.

Gathering data and identifying events in various traffic situations remains an essential challenge for the systematic evaluation of a perception system's performance. Analyzing large-scale, typically unstructured, multi-modal, time series data obtained from video, radar, and LiDAR is computationally demanding, particularly when meta-information or annotations are missing. We compare Optical Flow (OF) and Deep Learning (DL) to feed computationally efficient event detection via space-filling curves on video data from a forward-facing, in-vehicle camera. Our first approach leverages unexpected disturbances in the OF field from vehicle surroundings; the second approach is a DL model trained on human visual attention to predict a driver's gaze to spot potential event locations. We feed these results to a space-filling curve to reduce dimensionality and achieve computationally efficient event retrieval. We systematically evaluate our concept by obtaining characteristic patterns for both approaches from a large-scale virtual dataset (SMIRK) and applied our findings to the Zenseact Open Dataset (ZOD), a large multi-modal, real-world dataset, collected over two years in 14 different European countries. Our results yield that the OF approach excels in specificity and reduces false positives, while the DL approach demonstrates superior sensitivity. Both approaches offer comparable processing speed, making them suitable for real-time applications., Comment: 27th IEEE International Conference on Intelligent Transportation Systems (IEEE ITSC 2024)

In this study the effects of Joule heating parameter on entropy generation and heat transfer in MHD flow inside a channel is investigated by means of Physics-Informed Neural Networks (PINNs) in form of a parametric analysis in addition to exploring the solution to the ill-posed problem. All of the governing equations are reformulated in terms of first order derivatives and the dimensionless form of the governing equations has been employed to further lessen the number of parameters and achieve better compatibility with loss function terms. Dimensionless groups such as Reynolds number, Prandtl number, Hartmann number and Joule heating parameter have been designated as the input for the neural network in order to perform the parametric study. Besides achieving high accuracy for case of parameters confined in the predefined ranges, the generalization ability of the method is depicted by solving the problem for the cases where the dimensionless parameters were outside of the assumed ranges. Moreover, the ability of handling Neumann boundary conditions is also investigated in the present study despite being neglected prevalently in the literature concerning PINNs. The effects of Joule heating parameter on entropy generation are researched using a parametric approach utilizing PINNs which is another novel aspect of the article at hand. As a concluding remark, an ill-posed problem is also defined such that the Joule heating parameter is included in a learning process and the method has been able to determine Joule heating parameter as a parameter of interest alongside other learnable parameters of the neural network such as weights and biases.

The current standard model of cosmology successfully describes a variety of measurements, but the nature of its main ingredients, dark matter and dark energy, remains unknown. Euclid is a medium-class mission in the Cosmic Vision 2015-2025 programme of the European Space Agency (ESA) that will provide high-resolution optical imaging, as well as near-infrared imaging and spectroscopy, over about 14,000 deg^2 of extragalactic sky. In addition to accurate weak lensing and clustering measurements that probe structure formation over half of the age of the Universe, its primary probes for cosmology, these exquisite data will enable a wide range of science. This paper provides a high-level overview of the mission, summarising the survey characteristics, the various data-processing steps, and data products. We also highlight the main science objectives and expected performance., Comment: Accepted for publication in the A&A special issue`Euclid on Sky'

We build an emulator based on the polynomial chaos expansion (PCE) technique to efficiently model the non-linear effects associated with the clustering of the $k$-essence dark energy in the effective field theory (EFT) framework. These effects can be described through a modification of Poisson's equation, denoted by the function $\mu(k,z)$, which in general depends on wavenumber $k$ and redshift $z$. To emulate this function, we perform $200$ high-resolution $N$-body simulations sampled from a seven-dimensional parameter space with the Latin hypercube method. These simulations are executed using the $\texttt{k-evolution}$ code on a fixed mesh, containing $1200^3$ dark matter particles within a box size of $400~\text{Mpc}/ h$. The emulation process has been carried out within $\texttt{UQLab}$, a $\texttt{MATLAB}$-based software specifically dedicated to emulation and uncertainty quantification tasks. Apart from its role in emulation, the PCE method also facilitates the measurement of Sobol indices, enabling us to assess the relative impact of each cosmological parameter on the $\mu$ function. Our results show that the PCE-based emulator efficiently and accurately reflects the behavior of the $k$-essence dark energy for the cosmological parameter space defined by $w_0 c_s^2 \text{CDM} +\sum m_{\nu}$. Compared against actual simulations, the emulator achieves sub-percent accuracy up to the wavenumber $k \approx 9.4 ~h \text{Mpc}^{-1} $ for redshifts $z \leq 3$. Our emulator provides an efficient and reliable tool for Markov chain Monte Carlo (MCMC) analysis, and its capability to closely mimic the properties of the $k$-essence dark energy makes it a crucial component in Bayesian parameter estimations. The code is publicly available at https://github.com/anourizo/k-emulator ., Comment: 21 pages, 16 figures, 4 tables

This study aims on proposing a new structure for constructing Bernstein-like bases. The structure uses an auxiliary function and a shape parameter to construct a new family of bases from any family of blending functions. The new family of bases inherit almost all algebraic and geometric properties of the initial blending functions. The corresponding curves have the freedom to travel from the curve constructed from the initial blending functions to the line segment joining the first and last control points. The new bases have the monotonicity preservation property and the shape of the curve could be adjusted by changing the parameter.

After studying null geodesics in the equatorial plane in NUT spacetime, we show that there are unstable photon rings in this plane. Next we transform the metric of this plane to the isotropic coordinates and introduce its equivalent index of refraction. Using the analog gravity ideas we assign this index of refraction to a metamaterial analog of this plane, and by ray-tracing simulation find its photon rings. Furthermore, we employ wave optics to solve Maxwell's equations numerically for electromagnetic waves within an inhomogeneous medium characterized by the same index of refraction. Further we investigate the optical behavior of this medium in response to the radiation from an electric dipole., Comment: 22 pages, 5 figures

A novel methodology is developed to extract accurate skeletal reaction models for nuclear combustion. Local sensitivities of isotope mass fractions with respect to reaction rates are modeled based on the forced optimally time-dependent (f-OTD) scheme. These sensitivities are then analyzed temporally to generate skeletal models. The methodology is demonstrated by conducting skeletal reduction of constant density and temperature burning of carbon and oxygen relevant to SNe Ia. The 495-isotopes Torch model is chosen as the detailed reaction network. A map of maximum production of $^{56}\text{Ni}$ in SNe Ia is produced for different temperatures, densities, and proton to neutron ratios. The f-OTD simulations and the sensitivity analyses are then performed with initial conditions from this map. A series of skeletal models are derived and their performances are assessed by comparison against currently existing skeletal models. Previous models have been constructed intuitively by assuming the dominance of $\alpha$-chain reactions. The comparison of the newly generated skeletal models against previous models is based on the predicted energy release and $^{44}\text{Ti}$ and $^{56}\text{Ni}$ abundances by each model. The consequences of $\mathtt{y}_e \neq 0.5$ in the initial composition are also explored where $\mathtt{y}_e$ is the electron fraction. The simulated results show that $^{56}\text{Ni}$ production decreases by decreasing $\mathtt{y}_e$ as expected, and that the $^{43}\text{Sc}$ is a key isotope in proton and neutron channels toward $^{56}\text{Ni}$ production. It is shown that an f-OTD skeletal model with 150 isotopes can accurately predict the $^{56}\text{Ni}$ abundance in SNe Ia for $\mathtt{y}_e \lesssim 0.5$ initial conditions.

In this study, fluid flow inside of an obstructed channel under the influence of magnetic field has been analyzed using physics informed neural networks(PINNs). Governing equations have been utilized in low-order form and the solution has been obtained in dimensionless form. Geometric and physics-related dimensionless parameters have been used as input variables of the neural network in the learning process. The radius and longitudinal position of the obstruction have also been involved in the learning process and the problem has been solved parametrically. In the successive sections of the study, inverse problem has been a matter of interest, particularly in form of obtaining the Hartmann number using the proposed method. The results have indicated that the employed method determined the Hartmann number with great accuracy and entailed proper results. In this study a thorough exploration of effects of physical and geometric parameters on the magnetically influenced flow through a duct has been carried out. The accuracy of the results obtained from the solving method proposed have been compared to results generated by common methods used in computational fluid mechanics. The parametric solution of the problem can serve as a powerful tool in optimization problems. The method was also applicable to cases where the parameters were outside of defined range, indicating it's generalization capabilities.

Interpreting and understanding the predictions made by deep learning models poses a formidable challenge due to their inherently opaque nature. Many previous efforts aimed at explaining these predictions rely on input features, specifically, the words within NLP models. However, such explanations are often less informative due to the discrete nature of these words and their lack of contextual verbosity. To address this limitation, we introduce the Latent Concept Attribution method (LACOAT), which generates explanations for predictions based on latent concepts. Our foundational intuition is that a word can exhibit multiple facets, contingent upon the context in which it is used. Therefore, given a word in context, the latent space derived from our training process reflects a specific facet of that word. LACOAT functions by mapping the representations of salient input words into the training latent space, allowing it to provide latent context-based explanations of the prediction., Comment: Accepted by EMNLP 2024 Main Conference

Evaluating Large Language Models (LLMs) is challenging due to their generative nature, necessitating precise evaluation methodologies. Additionally, non-English LLM evaluation lags behind English, resulting in the absence or weakness of LLMs for many languages. In response to this necessity, we introduce Khayyam Challenge (also known as PersianMMLU), a meticulously curated collection comprising 20,192 four-choice questions sourced from 38 diverse tasks extracted from Persian examinations, spanning a wide spectrum of subjects, complexities, and ages. The primary objective of the Khayyam Challenge is to facilitate the rigorous evaluation of LLMs that support the Persian language. Distinctive features of the Khayyam Challenge are (i) its comprehensive coverage of various topics, including literary comprehension, mathematics, sciences, logic, intelligence testing, etc., aimed at assessing different facets of LLMs such as language comprehension, reasoning, and information retrieval across various educational stages, from lower primary school to upper secondary school (ii) its inclusion of rich metadata such as human response rates, difficulty levels, and descriptive answers (iii) its utilization of new data to avoid data contamination issues prevalent in existing frameworks (iv) its use of original, non-translated data tailored for Persian speakers, ensuring the framework is free from translation challenges and errors while encompassing cultural nuances (v) its inherent scalability for future data updates and evaluations without requiring special human effort. Previous works lacked an evaluation framework that combined all of these features into a single comprehensive benchmark. Furthermore, we evaluate a wide range of existing LLMs that support the Persian language, with statistical analyses and interpretations of their outputs.

Changes and updates in the requirement artifacts, which can be frequent in the automotive domain, are a challenge for SafetyOps. Large Language Models (LLMs), with their impressive natural language understanding and generating capabilities, can play a key role in automatically refining and decomposing requirements after each update. In this study, we propose a prototype of a pipeline of prompts and LLMs that receives an item definition and outputs solutions in the form of safety requirements. This pipeline also performs a review of the requirement dataset and identifies redundant or contradictory requirements. We first identified the necessary characteristics for performing HARA and then defined tests to assess an LLM's capability in meeting these criteria. We used design science with multiple iterations and let experts from different companies evaluate each cycle quantitatively and qualitatively. Finally, the prototype was implemented at a case company and the responsible team evaluated its efficiency., Comment: Accepted in 32nd IEEE International Requirements Engineering 2024 conference, Iceland

Many drugs used therapeutically or recreationally induce tolerance: the effect of the substance decreases with repeated use. This phenomenon may reduce the efficacy of the substance unless dosage is increased beyond what is healthy for the individual. Restoring the effect of the substance can often be obtained by taking a break from consumption. We propose designing dosing schedules that maximize the desired effect of the substance with a given total consumption, while factoring in the effect of tolerance. We provide a simple mathematical model of response to consumption and tolerance that can be fit from data on substance administration and response. Using this model with given parameters, we determine optimal consumption schedules to maximize a given objective. We illustrate with the example of caffeine, where we provide a schedule of consumption for a user who values the effects of caffeine on all days but needs extra alertness on some days of the week., Comment: 18 pages, 3 figures, 2 tables

DevOps is a necessity in many industries, including the development of Autonomous Vehicles. In those settings, there are iterative activities that reduce the speed of SafetyOps cycles. One of these activities is "Hazard Analysis & Risk Assessment" (HARA), which is an essential step to start the safety requirements specification. As a potential approach to increase the speed of this step in SafetyOps, we have delved into the capabilities of Large Language Models (LLMs). Our objective is to systematically assess their potential for application in the field of safety engineering. To that end, we propose a framework to support a higher degree of automation of HARA with LLMs. Despite our endeavors to automate as much of the process as possible, expert review remains crucial to ensure the validity and correctness of the analysis results, with necessary modifications made accordingly., Comment: Accepted in CAIN 2024, 6 pages, 1 figure

Safety analysis is used to identify hazards and build knowledge during the design phase of safety-relevant functions. This is especially true for complex AI-enabled and software intensive systems such as Autonomous Drive (AD). System-Theoretic Process Analysis (STPA) is a novel method applied in safety-related fields like defense and aerospace, which is also becoming popular in the automotive industry. However, STPA assumes prerequisites that are not fully valid in the automotive system engineering with distributed system development and multi-abstraction design levels. This would inhibit software developers from using STPA to analyze their software as part of a bigger system, resulting in a lack of traceability. This can be seen as a maintainability challenge in continuous development and deployment (DevOps). In this paper, STPA's different guidelines for the automotive industry, e.g. J31887/ISO21448/STPA handbook, are firstly compared to assess their applicability to the distributed development of complex AI-enabled systems like AD. Further, an approach to overcome the challenges of using STPA in a multi-level design context is proposed. By conducting an interview study with automotive industry experts for the development of AD, the challenges are validated and the effectiveness of the proposed approach is evaluated., Comment: Accepted at SEAA. 8 pages, 2 figures

Using continuous development, deployment, and monitoring (CDDM) to understand and improve applications in a customer's context is widely used for non-safety applications such as smartphone apps or web applications to enable rapid and innovative feature improvements. Having demonstrated its potential in such domains, it may have the potential to also improve the software development for automotive functions as some OEMs described on a high level in their financial company communiqus. However, the application of a CDDM strategy also faces challenges from a process adherence and documentation perspective as required by safety-related products such as autonomous driving systems (ADS) and guided by industry standards such as ISO-26262 and ISO21448. There are publications on CDDM in safety-relevant contexts that focus on safety-critical functions on a rather generic level and thus, not specifically ADS or automotive, or that are concentrating only on software and hence, missing out the particular context of an automotive OEM: Well-established legacy processes and the need of their adaptations, and aspects originating from the role of being a system integrator for software/software, hardware/hardware, and hardware/software. In this paper, particular challenges from the automotive domain to better adopt CDDM are identified and discussed to shed light on research gaps to enhance CDDM, especially for the software development of safe ADS. The challenges are identified from today's industrial well-established ways of working by conducting interviews with domain experts and complemented by a literature study., Comment: Proceedings of 2022 48th Euromicro Conference on Software Engineering and Advanced Applications (SEAA), Gran Canaria, Spain, 2022, pp. 358-365. 8 pages, 2 figures