Search

Enterprise Resource Planning (ERP) consultants play a vital role in customizing systems to meet specific business needs by processing large amounts of data and adapting functionalities. However, the process is resource-intensive, time-consuming, and requires continuous adjustments as business demands evolve. This research introduces a Self-Adaptive ERP Framework that automates customization using enterprise process models and system usage analysis. It leverages Artificial Intelligence (AI) & Natural Language Processing (NLP) for Petri nets to transform business processes into adaptable models, addressing both structural and functional matching. The framework, built using Design Science Research (DSR) and a Systematic Literature Review (SLR), reduces reliance on manual adjustments, improving ERP customization efficiency and accuracy while minimizing the need for consultants.

Neural Radiance Fields (NeRF) revolutionized novel view synthesis in recent years by offering a new volumetric representation, which is compact and provides high-quality image rendering. However, the methods to edit those radiance fields developed slower than the many improvements to other aspects of NeRF. With the recent development of alternative radiance field-based representations inspired by NeRF as well as the worldwide rise in popularity of text-to-image models, many new opportunities and strategies have emerged to provide radiance field editing. In this paper, we deliver a comprehensive survey of the different editing methods present in the literature for NeRF and other similar radiance field representations. We propose a new taxonomy for classifying existing works based on their editing methodologies, review pioneering models, reflect on current and potential new applications of radiance field editing, and compare state-of-the-art approaches in terms of editing options and performance.

Process mining has grown popular today given their ability to provide managers with insights into the actual business process as executed by employees. Process mining depends on event logs found in process aware information systems to model business processes. This has raised the need to develop event log standards given that event logs are the entry point to any process mining project. One of the main challenges of event logs and process mining in general as was mentioned by the IEEE task force on process mining deals with the finding, merging and cleaning event data.This resulted in having multiple event log standards with different features. This paper attempts to propose a new unified standard for event logs that enriches the results of process mining without the need to tailor event logs for each process mining project.

A question if a polynomially bounded operator is similar to a contraction was posed by Halmos and was answered in the negative by Pisier. His counterexample is an operator of infinite multiplicity, while all its restrictions on invariant subspaces of finite multiplicity are similar to contractions. In the paper, cyclic polynomially bounded operators which are not similar to contractions and are quasisimilar to $C_0$-contractions or to isometries are constructed. The construction is based on a perturbation of the sequence of finite dimensional operators which is uniformly polynomially bounded, but is not uniformly completely polynomially bounded, constructed by Pisier.

We propose a GPU accelerated proximal message passing algorithm for solving contingency-constrained DC optimal power flow problems (OPF). We consider a highly general formulation of OPF that uses a sparse device-node model and supports a broad range of devices and constraints, e.g., energy storage and ramping limits. Our algorithm is a variant of the alternating direction method multipliers (ADMM) that does not require solving any linear systems and only consists of sparse incidence matrix multiplies and vectorized scalar operations. We develop a pure PyTorch implementation of our algorithm that runs entirely on the GPU. The implementation is also end-to-end differentiable, i.e., all updates are automatic differentiation compatible. We demonstrate the performance of our method using test cases of varying network sizes and time horizons. Relative to a CPU-based commercial optimizer, our implementation achieves well over 100x speedups on large test cases, solving problems with over 500 million variables in under a minute on a single GPU.

Large scale grid expansion planning studies are essential to rapidly and efficiently decarbonizing the electricity sector. These studies help policy makers and grid participants understand which renewable generation, storage, and transmission assets should be built and where they will be most cost effective or have the highest emissions impact. However, these studies are often either too computationally expensive to run repeatedly or too coarsely modeled to give actionable decision information. In this study, we present an implicit gradient descent algorithm to solve expansion planning studies at scale, i.e., problems with many scenarios and large network models. Our algorithm is also interactive: given a base plan, planners can modify assumptions and data then quickly receive an updated plan. This allows the planner to study expansion outcomes for a wide variety of technology cost, weather, and electrification assumptions. We demonstrate the scalability of our tool, solving a case with over a hundred million variables. Then, we show that using warm starts can speed up subsequent runs by as much as 100x. We highlight how this can be used to quickly conduct storage cost uncertainty analysis.

This paper presents DENSER, an efficient and effective approach leveraging 3D Gaussian splatting (3DGS) for the reconstruction of dynamic urban environments. While several methods for photorealistic scene representations, both implicitly using neural radiance fields (NeRF) and explicitly using 3DGS have shown promising results in scene reconstruction of relatively complex dynamic scenes, modeling the dynamic appearance of foreground objects tend to be challenging, limiting the applicability of these methods to capture subtleties and details of the scenes, especially far dynamic objects. To this end, we propose DENSER, a framework that significantly enhances the representation of dynamic objects and accurately models the appearance of dynamic objects in the driving scene. Instead of directly using Spherical Harmonics (SH) to model the appearance of dynamic objects, we introduce and integrate a new method aiming at dynamically estimating SH bases using wavelets, resulting in better representation of dynamic objects appearance in both space and time. Besides object appearance, DENSER enhances object shape representation through densification of its point cloud across multiple scene frames, resulting in faster convergence of model training. Extensive evaluations on KITTI dataset show that the proposed approach significantly outperforms state-of-the-art methods by a wide margin. Source codes and models will be uploaded to this repository https://github.com/sntubix/denser

Marginal emissions rates -- the sensitivity of carbon emissions to electricity demand -- are important for evaluating the impact of emissions mitigation measures. Like locational marginal prices, locational marginal emissions rates (LMEs) can vary geographically, even between nearby locations, and may be coupled across time periods because of, for example, storage and ramping constraints. This temporal coupling makes computing LMEs computationally expensive for large electricity networks with high storage and renewable penetrations. Recent work demonstrates that decentralized algorithms can mitigate this problem by decoupling timesteps during differentiation. Unfortunately, we show these potential speedups are negated by the sparse structure inherent in power systems problems. We address these limitations by introducing a parallel, reverse-mode decentralized differentiation scheme that never explicitly instantiates the solution map Jacobian. We show both theoretically and empirically that parallelization is necessary to achieve non-trivial speedups when computing grid emissions sensitivities. Numerical results on a 500 node system indicate that our method can achieve greater than 10x speedups over centralized and serial decentralized approaches.

We present spectroscopic observations of Nova Cas 2020(V1391 Cas) obtained using the Russian Turkish Telescope during different stages of its 2020 outburst. We followed the spectral evolution of the nova until it entered the nebular phase. The expansion velocity of the ejecta reached $\sim$780 $\mathrm{km\,s^{-1}}$. The fluxes of the neutral [O I] lines at wavelengths 6300, 6364, and 5577 $\r{A}$ were used to calculate the electron temperature and the mass of neutral oxygen in the ejecta. We found average values $T_e = 4890\,K$ ,$M_{OI} = 2.54 \times 10^{-5}\, M_{\odot}$ which are consistent with the values calculated for other novae. We modeled the nova's ejected envelope 515 days after its discovery and found that the log elemental abundances by number relative to Hydrogen of the envelope are He = -0.7, C = -5.5, O = -2.5, N = -2.0 and Ne = -4.0.

Model training requires significantly more memory, compared with inference. Parameter efficient fine-tuning (PEFT) methods provide a means of adapting large models to downstream tasks using less memory. However, existing methods such as adapters, prompt tuning or low-rank adaptation (LoRA) either introduce latency overhead at inference time or achieve subpar downstream performance compared with full fine-tuning. In this work we propose Random Subspace Adaptation (ROSA), a method that outperforms previous PEFT methods by a significant margin, while maintaining a zero latency overhead during inference time. In contrast to previous methods, ROSA is able to adapt subspaces of arbitrarily large dimension, better approximating full-finetuning. We demonstrate both theoretically and experimentally that this makes ROSA strictly more expressive than LoRA, without consuming additional memory during runtime. As PEFT methods are especially useful in the natural language processing domain, where models operate on scales that make full fine-tuning very expensive, we evaluate ROSA in two common NLP scenarios: natural language generation (NLG) and natural language understanding (NLU) with GPT-2 and RoBERTa, respectively. We show that on almost every GLUE task ROSA outperforms LoRA by a significant margin, while also outperforming LoRA on NLG tasks. Our code is available at https://github.com/rosa-paper/rosa

This paper solves the open problem of characterizing the performance of quantum illumination (QI) with discrete variable states. By devising a novel quantum measurement approach along with meticulous analysis, our investigation demonstrates that, in the limit as $M \rightarrow \infty$, the maximally entangled $M$ mode Bell state achieves optimal performance, matching the two-mode squeezed vacuum in a high-noise regime and exceeding it in low-noise. This result challenges the dominance of continuous variable states in photonic sensing applications and extends the novelty of QI to regimes where no quantum advantage was believed to exist. A closer analysis reveals that this advantage stems from retained entanglement in the transmitted Bell state, a paradigm-shifting discovery since interaction with the environment in optical systems is believed to break entanglement. The complete mathematical analysis of this work provides granular insights into the interaction between photonic systems and environmental noise, motivating further research into discrete variable quantum sensing., Comment: Supplementary material available upon request. Please contact the authors via email

Second-order Recurrent Neural Networks (2RNNs) extend RNNs by leveraging second-order interactions for sequence modelling. These models are provably more expressive than their first-order counterparts and have connections to well-studied models from formal language theory. However, their large parameter tensor makes computations intractable. To circumvent this issue, one approach known as MIRNN consists in limiting the type of interactions used by the model. Another is to leverage tensor decomposition to diminish the parameter count. In this work, we study the model resulting from parameterizing 2RNNs using the CP decomposition, which we call CPRNN. Intuitively, the rank of the decomposition should reduce expressivity. We analyze how rank and hidden size affect model capacity and show the relationships between RNNs, 2RNNs, MIRNNs, and CPRNNs based on these parameters. We support these results empirically with experiments on the Penn Treebank dataset which demonstrate that, with a fixed parameter budget, CPRNNs outperforms RNNs, 2RNNs, and MIRNNs with the right choice of rank and hidden size., Comment: Accepted at ICML 2024. Camera ready version

A criterion on the similarity of a (bounded, linear) operator $T$ on a (complex, separable) Hilbert space $\mathcal H$ in terms of shift-type invariant subspaces of $T$ to a contraction of class $C_{\cdot 0}$ with finite unequal defects is given. Namely, $T$ is similar to such a contraction if and only if the minimal quantity of (closed) invariant subspaces $\mathcal M$ of $T$ such that the restriction $T|_{\mathcal M}$ of $T$ on $\mathcal M$ is similar to the simple unilateral shift, whose linear span is $\mathcal H$, is finite. A sufficient condition for the similarity of an absolutely continuous polynomially bounded operator $T$ to a contraction of class $C_{\cdot 0}$ with finite equal defects is given. Namely, $T$ is similar to such a contraction if the (spectral) multiplicity of $T$ is finite and $B(T)=\mathbb O$, where $B$ is a finite product of Blaschke products with simple zeros satisfying the Carleson interpolating condition (a Carleson--Newman product).

In the realm of quantum information, entanglement stands as a cornerstone phenomenon. It underpins a vast array of quantum information processes, offering significant potential for advancements in quantum computing, communication, and sensing. This paper introduces a novel multi-photon entangled state, which generalizes the maximally entangled single-photon state and exhibits remarkable resilience to signal attenuation in photonic applications. We demonstrate the novelty of the proposed state through a simplified target detection model and illustrate its superior performance over traditional single-photon protocols, attributed to its higher entanglement level and enhanced noise suppression capabilities. Our findings suggest that the proposed multi-photon state holds significant promise for enhancing the efficiency and reliability of photonic applications subject to loss. This work lays the groundwork for future exploration into the practical applications of multi-photon entangled states in quantum technologies, potentially revolutionizing our approach to quantum sensing and beyond, Comment: QuIK'24 Workshop - IEEE ISIT conference

The COVID-19 pandemic and the implementation of social distancing policies have rapidly changed people's visiting patterns, as reflected in mobility data that tracks mobility traffic using location trackers on cell phones. However, the frequency and duration of concurrent occupancy at specific locations govern the transmission rather than the number of customers visiting. Therefore, understanding how people interact in different locations is crucial to target policies, inform contact tracing, and prevention strategies. This study proposes an efficient way to reduce the spread of the virus among on-campus university students by developing a self-developed Google History Location Extractor and Indicator software based on real-world human mobility data. The platform enables policymakers and researchers to explore the possibility of future developments in the epidemic's spread and simulate the outcomes of human mobility and epidemic state under different epidemic control policies. It offers functions for determining potential contacts, assessing individual infection risks, and evaluating the effectiveness of on-campus policies. The proposed multi-functional platform facilitates the screening process by more accurately targeting potential virus carriers and aids in making informed decisions on epidemic control policies, ultimately contributing to preventing and managing future outbreaks., Comment: 8 pages

This paper introduces RoboCar, an open-source research platform for autonomous driving developed at the University of Luxembourg. RoboCar provides a modular, cost-effective framework for the development of experimental Autonomous Driving Systems (ADS), utilizing the 2018 KIA Soul EV. The platform integrates a robust hardware and software architecture that aligns with the vehicle's existing systems, minimizing the need for extensive modifications. It supports various autonomous driving functions and has undergone real-world testing on public roads in Luxembourg City. This paper outlines the platform's architecture, integration challenges, and initial test results, offering insights into its application in advancing autonomous driving research. RoboCar is available to anyone at https://github.com/sntubix/robocar and is released under an open-source MIT license.