Search

Variational techniques have long been at the heart of atomic, solid-state, and many-body physics. They have recently extended to quantum and classical machine learning, providing a basis for representing quantum states via neural networks. These methods generally aim to minimize the energy of a given ans\"atz, though open questions remain about the expressivity of quantum and classical variational ans\"atze. The connection between variational techniques and quantum computing, through variational quantum algorithms, offers opportunities to explore the quantum complexity of classical methods. We demonstrate how the concept of non-stabilizerness, or magic, can create a bridge between quantum information and variational techniques and we show that energy accuracy is a necessary but not always sufficient condition for accuracy in non-stabilizerness. Through systematic benchmarking of neural network quantum states, matrix product states, and variational quantum methods, we show that while classical techniques are more accurate in non-stabilizerness, not accounting for the symmetries of the system can have a severe impact on this accuracy. Our findings form a basis for a universal expressivity characterization of both quantum and classical variational methods., Comment: 11 pages, 7 figures. Data and code available at https://gitlab.com/QMAI/papers/quantumresourcesml

In the field of pharmacokinetics and pharmacodynamics (PKPD) modeling, which plays a pivotal role in the drug development process, traditional models frequently encounter difficulties in fully encapsulating the complexities of drug absorption, distribution, and their impact on targets. Although multi-compartment models are frequently utilized to elucidate intricate drug dynamics, they can also be overly complex. To generalize modeling while maintaining simplicity, we propose an innovative approach that enhances PK and integrated PK-PD modeling by incorporating fractional calculus or time-varying parameter(s), combined with constant or piecewise constant parameters. These approaches effectively model anomalous diffusion, thereby capturing drug trapping and escape rates in heterogeneous tissues, which is a prevalent phenomenon in drug dynamics. Furthermore, this method provides insight into the dynamics of drug in cancer in multi-dose administrations. Our methodology employs a Physics-Informed Neural Network (PINN) and fractional Physics-Informed Neural Networks (fPINNs), integrating ordinary differential equations (ODEs) with integer/fractional derivative order from compartmental modeling with neural networks. This integration optimizes parameter estimation for variables that are time-variant, constant, piecewise constant, or related to the fractional derivative order. The results demonstrate that this methodology offers a robust framework that not only markedly enhances the model's depiction of drug absorption rates and distributed delayed responses but also unlocks different drug-effect dynamics, providing new insights into absorption rates, anomalous diffusion, drug resistance, peristance and pharmacokinetic tolerance, all within a system of just two (fractional) ODEs with explainable results.

The continuous flow of data collected by Internet of Things (IoT) devices, has revolutionised our ability to understand and interact with the world across various applications. However, this data must be prepared and transformed into event data before analysis can begin. In this paper, we shed light on the potential of leveraging Large Language Models (LLMs) in event abstraction and integration. Our approach aims to create event records from raw sensor readings and merge the logs from multiple IoT sources into a single event log suitable for further Process Mining applications. We demonstrate the capabilities of LLMs in event abstraction considering a case study for IoT application in elderly care and longitudinal health monitoring. The results, showing on average an accuracy of 90% in detecting high-level activities. These results highlight LLMs' promising potential in addressing event abstraction and integration challenges, effectively bridging the existing gap., Comment: 12 pages

Physics-informed machine learning (PIML) has emerged as a promising alternative to classical methods for predicting dynamical systems, offering faster and more generalizable solutions. However, existing models, including recurrent neural networks (RNNs), transformers, and neural operators, face challenges such as long-time integration, long-range dependencies, chaotic dynamics, and extrapolation, to name a few. To this end, this paper introduces state-space models implemented in Mamba for accurate and efficient dynamical system operator learning. Mamba addresses the limitations of existing architectures by dynamically capturing long-range dependencies and enhancing computational efficiency through reparameterization techniques. To extensively test Mamba and compare against another 11 baselines, we introduce several strict extrapolation testbeds that go beyond the standard interpolation benchmarks. We demonstrate Mamba's superior performance in both interpolation and challenging extrapolation tasks. Mamba consistently ranks among the top models while maintaining the lowest computational cost and exceptional extrapolation capabilities. Moreover, we demonstrate the good performance of Mamba for a real-world application in quantitative systems pharmacology for assessing the efficacy of drugs in tumor growth under limited data scenarios. Taken together, our findings highlight Mamba's potential as a powerful tool for advancing scientific machine learning in dynamical systems modeling. (The code will be available at https://github.com/zheyuanhu01/State_Space_Model_Neural_Operator upon acceptance.), Comment: 34 pages

In this paper, we review the new method Physics-Informed Neural Networks (PINNs) that has become the main pillar in scientific machine learning, we present recent practical extensions, and provide a specific example in data-driven discovery of governing differential equations., Comment: Frontiers of Science Awards 2024

In this study we construct a data-driven model describing Lithium plating in a battery cell, which is a key process contributing to degradation of such cells. Starting from the fundamental Doyle-Fuller-Newman (DFN) model, we use asymptotic reduction and spatial averaging techniques to derive a simplified representation to track the temporal evolution of two key concentrations in the system, namely, the total intercalated Lithium on the negative electrode particles and total plated Lithium. This model depends on an a priori unknown constitutive relations of the cell as a function of thestate variables. An optimal form of this constitutive relation is then deduced from experimental measurements of the time dependent concentrations of different Lithium phases acquired through Nuclear Magnetic Resonance spectroscopy. This is done by solving an inverse problem in which this constitutive relation is found subject to minimum assumptions as a minimizer of a suitable constrained optimization problem where the discrepancy between the model predictions and experimental data is minimized. This optimization problem is solved using a state-of-the-art adjoint-based technique. In contrast to some of the earlier approaches to modelling Lithium plating, the proposed model is able to predict non-trivial evolution of the concentrations in the relaxation regime when no current isapplied to the cell. When equipped with an optimal constitutive relation, the model provides accurate predictions of the time evolution of both intercalated and plated Lithium across a wide range of charging/discharging rates. It can therefore serve as a useful tool for prediction and control of degradation mechanism in battery cells., Comment: 63 pages, 14 figures

This paper considers an unsourced random access (URA) set-up equipped with a passive reconfigurable intelligent surface (RIS), where a massive number of unidentified users (only a small fraction of them being active at any given time) are connected to the base station (BS). We introduce a slotted coding scheme for which each active user chooses a slot at random for transmitting its signal, consisting of a pilot part and a randomly spread polar codeword. The proposed decoder operates in two phases. In the first phase, called the RIS configuration phase, the BS detects the transmitted pilots. The detected pilots are then utilized to estimate the corresponding users' channel state information, using which the BS suitably selects RIS phase shift employing the proposed RIS design algorithms. The proposed channel estimator offers the capability to obtain the channel coefficients of the users whose pilots interfere with each other without prior access to the list of transmitted pilots or the number of active users. In the second phase, called the data phase, transmitted messages of active users are decoded. Moreover, we establish an approximate achievability bound for the RIS-based URA scheme, providing a valuable benchmark. Computer simulations show that the proposed scheme outperforms the state-of-the-art for RIS-aided URA.

Residential outdoor water use in North America accounts for nearly 9 billion gallons daily, with approximately 50\% of this water wasted due to over-watering, particularly in lawns and gardens. This inefficiency highlights the need for smart, data-driven irrigation systems. Traditional approaches to reducing water wastage have focused on centralized data collection and processing, but such methods can raise privacy concerns and may not account for the diverse environmental conditions across different regions. In this paper, we propose a federated learning-based approach to optimize water usage in residential and agricultural settings. By integrating moisture sensors and actuators with a distributed network of edge devices, our system allows each user to locally train a model on their specific environmental data while sharing only model updates with a central server. This preserves user privacy and enables the creation of a global model that can adapt to varying conditions. Our implementation leverages low-cost hardware, including an Arduino Uno microcontroller and soil moisture sensors, to demonstrate how federated learning can be applied to reduce water wastage while maintaining efficient crop production. The proposed system not only addresses the need for water conservation but also provides a scalable, privacy-preserving solution adaptable to diverse environments.

Medication nonadherence significantly reduces the effectiveness of therapies, yet it remains prevalent among patients. Nonadherence has been linked to adverse outcomes, including increased risks of mortality and hospitalization. Although various methods exist to help patients track medication schedules, such as the Intelligent Drug Administration System (IDAS) and Smart Blister, these tools often face challenges that hinder their commercial viability. Building on the principles of dosage measurement and information communication in IoT, we introduce the Smart Pill Case a smart health adherence tool that leverages RFID-based data recording and NFC-based data extraction. This system incorporates a load cell for precise dosage measurement and features an Android app to monitor medication intake, offer suggestions, and issue warnings. To enhance the effectiveness and personalization of the Smart Pill Case, we propose integrating federated learning into the system. Federated learning allows the Smart Pill Case to learn from medication adherence patterns across multiple users without compromising individual privacy. By training machine learning models on decentralized data collected from various Smart Pill Cases, the system can continuously improve its recommendations and warnings, adapting to the diverse needs and behaviors of users. This approach not only enhances the tools ability to support medication adherence but also ensures that sensitive user data remains secure and private.

Markerless motion capture offers several benefits over traditional marker-based systems by eliminating the need for physical markers, which are prone to misplacement and artifacts. Utilizing computer vision and deep learning algorithms, markerless systems can directly detect human body landmarks, reducing manual processing and errors associated with marker placement. These systems are adaptable, able to track user-defined features, and practical for real-world applications using consumer-grade devices such as smartphone cameras. This study compares the performance of OpenCap, a markerless motion capture system, with traditional marker-based systems in assessing cycling biomechanics. Ten healthy adults participated in experiments to capture sagittal hip, knee, and ankle kinematics and dynamics using both methods. OpenCap used videos from smartphones and integrated computer vision and musculoskeletal simulations to estimate 3D kinematics. Results showed high agreement between the two systems, with no significant differences in kinematic and kinetic measurements for the hip, knee, and ankle. The correlation coefficients exceeded 0.98, indicating very strong consistency. Errors were minimal, with kinematic errors under 4 degrees and kinetic errors below 5 Nm. This study concludes that OpenCap is a viable alternative to marker-based motion capture, offering comparable precision without extensive setup for hip (flexion/extension), knee (flexion/extension), and ankle (dorsiflexion/plantarflexion) joints. Future work should aim to enhance the accuracy of ankle joint measurements and extend analyses to 3D kinematics and kinetics for comprehensive biomechanical assessments.

The rise of computer vision applications in the real world puts the security of the deep neural networks at risk. Recent works demonstrate that convolutional neural networks are susceptible to adversarial examples - where the input images look similar to the natural images but are classified incorrectly by the model. To provide a rebuttal to this problem, we propose a new method to build robust deep neural networks against adversarial attacks by reformulating the saddle point optimization problem in \cite{madry2017towards}. Our proposed method offers significant resistance and a concrete security guarantee against multiple adversaries. The goal of this paper is to act as a stepping stone for a new variation of deep learning models which would lead towards fully robust deep learning models.

We use data from the ALMA Evolutionary Study of High Mass Protocluster Formation in the Galaxy (ALMAGAL) survey to study 100 ALMAGAL regions at $\sim$ 1 arsecond resolution located between $\sim$ 2 and 6 kpc distance. Using ALMAGAL $\sim$ 1.3mm line and continuum data we estimate flow rates onto individual cores. We focus specifically on flow rates along filamentary structures associated with these cores. Our primary analysis is centered around position velocity cuts in H$_2$CO (3$_{0,3}$ - 2$_{0,2}$) which allow us to measure the velocity fields, surrounding these cores. Combining this work with column density estimates we derive the flow rates along the extended filamentary structures associated with cores in these regions. We select a sample of 100 ALMAGAL regions covering four evolutionary stages from quiescent to protostellar, Young Stellar Objects (YSOs), and HII regions (25 each). Using dendrogram and line analysis, we identify a final sample of 182 cores in 87 regions. In this paper, we present 728 flow rates for our sample (4 per core), analysed in the context of evolutionary stage, distance from the core, and core mass. On average, for the whole sample, we derive flow rates on the order of $\sim$10$^{-4}$ M$_{sun}$yr$^{-1}$ with estimated uncertainties of $\pm$50%. We see increasing differences in the values among evolutionary stages, most notably between the less evolved (quiescent/protostellar) and more evolved (YSO/HII region) sources. We also see an increasing trend as we move further away from the centre of these cores. We also find a clear relationship between the flow rates and core masses $\sim$M$^{2/3}$ which is in line with the result expected from the tidal-lobe accretion mechanism. Overall, we see increasing trends in the relationships between the flow rate and the three investigated parameters; evolutionary stage, distance from the core, and core mass., Comment: 11 pages, 11 figures, accepted for publication in A&A

The emergence of quantum technologies has brought much attention to the characterization of quantum resources as well as the classical simulatability of quantum processes. Quantum resources, as quantified by non-stabilizerness, have in one theoretical approach been linked to a family of entropic, monotonic functions. In this work, we demonstrate both analytically and numerically a simple relationship between non-stabilizerness and information scrambling using the fluctuations of an entropy-based quantifier. Specifically, we find that the non-stabilizerness generated by a random quantum circuit is proportional to fluctuations of mutual information. Furthermore, we explore the role of non-stabilizerness in measurement-induced entanglement phase transitions. We find that the fluctuations of mutual information decrease with increasing non-stabilizerness yielding potentially easier identification of the transition point. Our work establishes a key connection between quantum resource theory, information scrambling and measurement-induced entanglement phase transitions., Comment: 13 pages, 7 figures, code https://gitlab.com/QMAI/papers/mutualfluctuations

The emergence of learned indexes has caused a paradigm shift in our perception of indexing by considering indexes as predictive models that estimate keys' positions within a data set, resulting in notable improvements in key search efficiency and index size reduction; however, a significant challenge inherent in learned index modeling is its constrained support for update operations, necessitated by the requirement for a fixed distribution of records. Previous studies have proposed various approaches to address this issue with the drawback of high overhead due to multiple model retraining. In this paper, we present UpLIF, an adaptive self-tuning learned index that adjusts the model to accommodate incoming updates, predicts the distribution of updates for performance improvement, and optimizes its index structure using reinforcement learning. We also introduce the concept of balanced model adjustment, which determines the model's inherent properties (i.e. bias and variance), enabling the integration of these factors into the existing index model without the need for retraining with new data. Our comprehensive experiments show that the system surpasses state-of-the-art indexing solutions (both traditional and ML-based), achieving an increase in throughput of up to 3.12 times with 1000 times less memory usage., Comment: 20 pages, ACM IDEAS 2024

Since the dawn of scanning probe microscopy (SPM), tapping or intermittent contact mode has been one of the most widely used imaging modes. Manual optimization of tapping mode not only takes a lot of instrument and operator time, but also often leads to frequent probe and sample damage, poor image quality and reproducibility issues for new types of samples or inexperienced users. Despite wide use, optimization of tapping mode imaging is an extremely hard problem, ill-suited to either classical control methods or machine learning. Here we introduce a reward-driven workflow to automate the optimization of SPM in the tapping mode. The reward function is defined based on multiple channels with physical and empirical knowledge of good scans encoded, representing a sample-agnostic measure of image quality and imitating the decision-making logic employed by human operators. This automated workflow gives optimal scanning parameters for different probes and samples and gives high-quality SPM images consistently in the attractive mode. This study broadens the application and accessibility of SPM and opens the door for fully automated SPM., Comment: 20 pages, 6 figures

Quantification of tissue parameters using MRI is emerging as a powerful tool in clinical diagnosis and research studies. The need for multiple long scans with different acquisition parameters prohibits quantitative MRI from reaching widespread adoption in routine clinical and research exams. Accelerated parameter mapping techniques leverage parallel imaging, signal modelling and deep learning to offer more practical quantitative MRI acquisitions. However, the achievable acceleration and the quality of maps are often limited. Joint MAPLE is a recent state-of-the-art multi-parametric and scan-specific parameter mapping technique with promising performance at high acceleration rates. It synergistically combines parallel imaging, model-based and machine learning approaches for joint mapping of T1, T2*, proton density and the field inhomogeneity. However, Joint MAPLE suffers from prohibitively long reconstruction time to estimate the maps from a multi-echo, multi-flip angle (MEMFA) dataset at high resolution in a scan-specific manner. In this work, we propose a faster version of Joint MAPLE which retains the mapping performance of the original version. Coil compression, random slice selection, parameter-specific learning rates and transfer learning are synergistically combined in the proposed framework. It speeds-up the reconstruction time up to 700 times than the original version and processes a whole-brain MEMFA dataset in 21 minutes on average, which originally requires ~260 hours for Joint MAPLE. The mapping performance of the proposed framework is ~2-fold better than the standard and the state-of-the-art evaluated reconstruction techniques on average in terms of the root mean squared error.

Purpose: Artificial intelligence (AI) techniques have been extensively utilized for diagnosing and prognosis of several diseases in recent years. This study identifies, appraises and synthesizes published studies on the use of AI for the prognosis of COVID-19. Method: Electronic search was performed using Medline, Google Scholar, Scopus, Embase, Cochrane and ProQuest. Studies that examined machine learning or deep learning methods to determine the prognosis of COVID-19 using CT or chest X-ray images were included. Polled sensitivity, specificity area under the curve and diagnostic odds ratio were calculated. Result: A total of 36 articles were included; various prognosis-related issues, including disease severity, mechanical ventilation or admission to the intensive care unit and mortality, were investigated. Several AI models and architectures were employed, such as the Siamense model, support vector machine, Random Forest , eXtreme Gradient Boosting, and convolutional neural networks. The models achieved 71%, 88% and 67% sensitivity for mortality, severity assessment and need for ventilation, respectively. The specificity of 69%, 89% and 89% were reported for the aforementioned variables. Conclusion: Based on the included articles, machine learning and deep learning methods used for the prognosis of COVID-19 patients using radiomic features from CT or CXR images can help clinicians manage patients and allocate resources more effectively. These studies also demonstrate that combining patient demographic, clinical data, laboratory tests and radiomic features improves model performances.

We introduce a family of symmetric convex bodies called generalized ellipsoids of degree $d$ (GE-$d$s), with ellipsoids corresponding to the case of $d=0$. Generalized ellipsoids (GEs) retain many geometric, algebraic, and algorithmic properties of ellipsoids. We show that the conditions that the parameters of a GE must satisfy can be checked in strongly polynomial time, and that one can search for GEs of a given degree by solving a semidefinite program whose size grows only linearly with dimension. We give an example of a GE which does not have a second-order cone representation, but show that every GE has a semidefinite representation whose size depends linearly on both its dimension and degree. In terms of expressiveness, we prove that for any integer $m\geq 2$, every symmetric full-dimensional polytope with $2m$ facets and every intersection of $m$ co-centered ellipsoids can be represented exactly as a GE-$d$ with $d \leq 2m-3$. Using this result, we show that every symmetric convex body can be approximated arbitrarily well by a GE-$d$ and we quantify the quality of the approximation as a function of the degree $d$. Finally, we present applications of GEs to several areas, such as time-varying portfolio optimization, stability analysis of switched linear systems, robust-to-dynamics optimization, and robust polynomial regression.

Cloud key-value (KV) stores provide businesses with a cost-effective and adaptive alternative to traditional on-premise data management solutions. KV stores frequently consist of heterogeneous clusters, characterized by varying hardware specifications of the deployment nodes, with each node potentially running a distinct version of the KV store software. This heterogeneity is accompanied by the diverse metadata that they need to manage. In this study, we introduce MetaHive, a cache-optimized approach to managing metadata in heterogeneous KV store clusters. MetaHive disaggregates the original data from its associated metadata to promote independence between them, while maintaining their interconnection during usage. This makes the metadata opaque from the downstream processes and the other KV stores in the cluster. MetaHive also ensures that the KV and metadata entries are stored in the vicinity of each other in memory and storage. This allows MetaHive to optimally utilize the caching mechanism without extra storage read overhead for metadata retrieval. We deploy MetaHive to ensure data integrity in RocksDB and demonstrate its rapid data validation with minimal effect on performance., Comment: Cloud Databases

A pivotal attribute of 5G networks is their capability to cater to diverse application requirements. This is achieved by creating logically isolated virtual networks, or slices, with distinct service level agreements (SLAs) tailored to specific use cases. However, efficiently allocating resources to maintain slice SLA is challenging due to varying traffic and QoS requirements. Traditional peak traffic-based resource allocation leads to over-provisioning, as actual traffic rarely peaks. Additionally, the complex relationship between resource allocation and QoS in end-to-end slices spanning different network segments makes conventional optimization techniques impractical. Existing approaches in this domain use network models or simulations and various optimization methods but struggle with optimality, tractability, and generalizability across different slice types. In this paper, we propose MicroOpt, a novel framework that leverages a differentiable neural network-based slice model with gradient descent for resource optimization and Lagrangian decomposition for QoS constraint satisfaction. We evaluate MicroOpt against two state-of-the-art approaches using an open-source 5G testbed with real-world traffic traces. Our results demonstrate up to 21.9% improvement in resource allocation compared to these approaches across various scenarios, including different QoS thresholds and dynamic slice traffic., Comment: 12 pages, 10 figures

Fine-grained understanding of objects, attributes, and relationships between objects is crucial for visual-language models (VLMs). Existing benchmarks primarily focus on evaluating VLMs' capability to distinguish between two very similar \textit{captions} given an image. In this paper, we introduce a new, challenging benchmark termed \textbf{Vis}ual \textbf{Min}imal-Change Understanding (VisMin), which requires models to predict the correct image-caption match given two images and two captions. The image pair and caption pair contain minimal changes, i.e., only one aspect changes at a time from among the following: \textit{object}, \textit{attribute}, \textit{count}, and \textit{spatial relation}. These changes test the models' understanding of objects, attributes (such as color, material, shape), counts, and spatial relationships between objects. We built an automatic framework using large language models and diffusion models, followed by a rigorous 4-step verification process by human annotators. Empirical experiments reveal that current VLMs exhibit notable deficiencies in understanding spatial relationships and counting abilities. We also generate a large-scale training dataset to finetune CLIP and Idefics2, showing significant improvements in fine-grained understanding across benchmarks and in CLIP's general image-text alignment. We release all resources, including the benchmark, training data, and finetuned model checkpoints, at \url{https://vismin.net/}., Comment: Project URL at https://vismin.net/

Energy dissipation, typically considered an undesirable process, has recently been shown to be harnessed as a resource to optimize the performance of a quantum battery. Following this perspective, we introduce a novel technique of charging in which coherent charger-battery interaction is replaced by a dissipative interaction via an engineered shared reservoir. We demonstrate that exploiting collective effects of the engineered shared reservoir allows for extra optimization giving rise to optimal redistribution of energy, which leads to a significant enhancement in the efficiency of the charging process. The article unveils the intricacies of built-in detuning within the context of a shared environment, offering a deeper understanding of the charging mechanisms involved. These findings apply naturally to quantum circuit battery architectures, suggesting the feasibility of efficient energy storage in these systems. Moreover, the super-optimal charging offers a practical justification for charger-battery configurations.

We investigate the chemical history of interstellar OCS and SO2 by deriving a statistically-significant sample of gas-phase column densities towards massive protostars and comparing to observations of gas and ices towards other sources spanning from dark clouds to comets. We analyze a subset of 26 line-rich massive protostars observed by ALMA as part of the ALMAGAL survey. Column densities are derived for OCS and SO2 from their rare isotopologues O13CS and 34SO2 towards the compact gas around the hot core. We find that gas-phase column density ratios of OCS and SO2 with respect to methanol remain fairly constant as a function of luminosity between low- and high-mass sources, despite their very different physical conditions. The derived gaseous OCS and SO2 abundances relative to CH3OH are overall similar to protostellar ice values, with a significantly larger scatter for SO2 than for OCS. Cometary and dark-cloud ice values agree well with protostellar gas-phase ratios for OCS, whereas higher abundances of SO2 are generally seen in comets compared to the other sources. Gaseous SO2/OCS ratios are consistent with ices toward dark clouds, protostars, and comets, albeit with some scatter. The constant gas-phase column density ratios throughout low and high-mass sources indicate an early stage formation before intense environmental differentiation begins. Icy protostellar values are similar to the gas phase medians, compatible with an icy origin of these species followed by thermal sublimation. The larger spread in SO2 compared to OCS ratios w.r.t. CH3OH is likely due to a more water-rich chemical environment associated with the former, as opposed to a CO-rich origin of the latter. Post-sublimation gas-phase processing of SO2 can also contribute to the large spread. Comparisons to ices in dark clouds and comets point to a significant inheritance of OCS from earlier to later evolutionary stages., Comment: Accepted for publication in Astronomy and Astrophysics on July 17th 2024

In many applied optimization settings, parameters that define the constraints may not guarantee the best possible solution, and superior solutions might exist that are infeasible for the given parameter values. Removing such constraints, re-optimizing, and evaluating the new solution may be insufficient, as the optimizer's preferences in selecting the existing solutions might be lost. To address this issue, we present an inverse optimization-based model that takes an observed solution as input and aims to improve upon it by projecting onto desired hyperplanes or expanding the feasible set while balancing the distance to the observed decision to preserve the optimizer's preferences. We demonstrate the applicability of the model in the context of radiation therapy treatment planning, an essential component of cancer treatment. Radiation therapy treatment planning is typically guided by expert-driven guidelines that define the optimization problem but remain mostly general. Our model provides an automated framework that learns new plans from available plans based on given clinical criteria, optimizing the desired effect without compromising the remaining constraints. The proposed approach is applied to a cohort of four prostate cancer patients, and the results demonstrate improvements in dose-volume histograms while maintaining comparable target coverage to clinically acceptable plans. By optimizing the parameters of the treatment planning problem and exploring the Pareto frontier, our methodology uncovers previously unattainable solutions that enhance organ-at-risk sparing without sacrificing target coverage. The framework's ability to handle multiple organs-at-risk and various dose-volume constraints highlights its flexibility and potential for application to diverse radiation therapy treatment planning scenarios.

We study the problem of online binary classification in settings where strategic agents can modify their observable features to receive a positive classification. We model the set of feasible manipulations by a directed graph over the feature space, and assume the learner only observes the manipulated features instead of the original ones. We introduce the Strategic Littlestone Dimension, a new combinatorial measure that captures the joint complexity of the hypothesis class and the manipulation graph. We demonstrate that it characterizes the instance-optimal mistake bounds for deterministic learning algorithms in the realizable setting. We also achieve improved regret in the agnostic setting by a refined agnostic-to-realizable reduction that accounts for the additional challenge of not observing agents' original features. Finally, we relax the assumption that the learner knows the manipulation graph, instead assuming their knowledge is captured by a family of graphs. We derive regret bounds in both the realizable setting where all agents manipulate according to the same graph within the graph family, and the agnostic setting where the manipulation graphs are chosen adversarially and not consistently modeled by a single graph in the family.

For skew Brownian motion with two-valued drift, adopting a perturbation approach we find expressions of its potential densities. As applications, we recover its transition density and study its long-time asymptotic behaviors. We also compare with previous results on transition densities for skew Brownian motions. We propose two approaches for generating quasi-random samples by approximating the cumulative distribution function and discussing their risk measurement application., Comment: 26 pages, 3 figures, 2 tables

Collective remote attestation (CRA) is a security service that aims to efficiently identify compromised (often low-powered) devices in a (heterogeneous) network. The last few years have seen an extensive growth in CRA protocol proposals, showing a variety of designs guided by different network topologies, hardware assumptions and other functional requirements. However, they differ in their trust assumptions, adversary models and role descriptions making it difficult to uniformly assess their security guarantees. In this paper we present Catt, a unifying framework for CRA protocols that enables them to be compared systematically, based on a comprehensive study of 40 CRA protocols and their adversary models. Catt characterises the roles that devices can take and based on these we develop a novel set of security properties for CRA protocols. We then classify the security aims of all the studied protocols. We illustrate the applicability of our security properties by encoding them in the tamarin prover and verifying the SIMPLE+ protocol against them.

Simulation studies, such as finite element (FE) modeling, offer insights into knee joint biomechanics, which may not be achieved through experimental methods without direct involvement of patients. While generic FE models have been used to predict tissue biomechanics, they overlook variations in population-specific geometry, loading, and material properties. In contrast, subject-specific models account for these factors, delivering enhanced predictive precision but requiring significant effort and time for development. This study aimed to facilitate subject-specific knee joint FE modeling by integrating an automated cartilage segmentation algorithm using a 3D Swin UNETR. This algorithm provided initial segmentation of knee cartilage, followed by automated geometry filtering to refine surface roughness and continuity. In addition to the standard metrics of image segmentation performance, such as Dice similarity coefficient (DSC) and Hausdorff distance, the method's effectiveness was also assessed in FE simulation. Nine pairs of knee cartilage FE models, using manual and automated segmentation methods, were developed to compare the predicted stress and strain responses during gait. The automated segmentation achieved high Dice similarity coefficients of 89.4% for femoral and 85.1% for tibial cartilage, with a Hausdorff distance of 2.3 mm between the automated and manual segmentation. Mechanical results including maximum principal stress and strain, fluid pressure, fibril strain, and contact area showed no significant differences between the manual and automated FE models. These findings demonstrate the effectiveness of the proposed automated segmentation method in creating accurate knee joint FE models., Comment: arXiv admin note: substantial text overlap with arXiv:2312.00169

This paper introduces a pioneering English-Azerbaijani (Arabic Script) parallel corpus, designed to bridge the technological gap in language learning and machine translation (MT) for under-resourced languages. Consisting of 548,000 parallel sentences and approximately 9 million words per language, this dataset is derived from diverse sources such as news articles and holy texts, aiming to enhance natural language processing (NLP) applications and language education technology. This corpus marks a significant step forward in the realm of linguistic resources, particularly for Turkic languages, which have lagged in the neural machine translation (NMT) revolution. By presenting the first comprehensive case study for the English-Azerbaijani (Arabic Script) language pair, this work underscores the transformative potential of NMT in low-resource contexts. The development and utilization of this corpus not only facilitate the advancement of machine translation systems tailored for specific linguistic needs but also promote inclusive language learning through technology. The findings demonstrate the corpus's effectiveness in training deep learning MT systems and underscore its role as an essential asset for researchers and educators aiming to foster bilingual education and multilingual communication. This research covers the way for future explorations into NMT applications for languages lacking substantial digital resources, thereby enhancing global language education frameworks. The Python package of our code is available at https://pypi.org/project/chevir-kartalol/, and we also have a website accessible at https://translate.kartalol.com/., Comment: This paper is accepted and published at NeTTT 2024 Conf

Artificial Intelligence (AI) is increasingly employed to enhance assistive technologies, yet it can fail in various ways. We conducted a systematic literature review of research into AI-based assistive technology for persons with visual impairments. Our study shows that most proposed technologies with a testable prototype have not been evaluated in a human study with members of the sight-loss community. Furthermore, many studies did not consider or report failure cases or possible risks. These findings highlight the importance of inclusive system evaluations and the necessity of standardizing methods for presenting and analyzing failure cases and threats when developing AI-based assistive technologies.

In this paper, we present a unique $\text {2D}$ high resolution, compact, low-cost, low-weight, and highly accurate millimeter wave imagery system capable of operating in all weather conditions. We describe millimeter wave imaging process in detail and present several novel signal processing methods with their applications. To create the array, we utilize the Synthetic Aperture Radar (SAR) concept. The imagery system presented in this paper, can strongly compete with Lidar systems as the resolution limit is at the same level. Furthermore, in contrast to the Lidar systems, our imagery system can operate in heavy rain and dense fog and produce high quality images. Finally, we utilize our wide-band custom-made Frequency Modulated Continuous Wave (FMCW) radar, which operates at W-band with $\text {33 GHz}$ bandwidth, for data collection and present the results.

Consider a compact metric space $X$, and let $\mathcal{F}=\{f_1,\,f_2,\ldots,\, f_k\}$ be a set of contracting and continuous self maps on $X$. Let $\Sigma$ be a sub-shift on $k$ symbols, and let $\Sigma_k$ be the full shift. Define $\mathcal{L}_n(\Sigma)$ as the set of words of length $n$ in $\Sigma$. For $u=u_1\cdots u_n\in \mathcal{L}_n(\Sigma)$, set $f_u:=f_{u_n}\circ\cdots \circ f_{u_1}$ and $H^n(\cdot):=\cup_{u \in \mathcal{L}_{n}(\Sigma_k)} f_{u}(\cdot)$. When $\Sigma=\Sigma_k$, $H^n(\cdot)$ is the $n$th iteration of the Hutchinson's operator, and there exists a compact set $S= \lim_{n \rightarrow \infty} H^n(A)$ for any compact $A\subseteq X$ with $H^n(S)=S$ (self-similarity criteria) for $n\in\N$. For arbitrary $\Sigma$, the above limit exists; but it is not necessarily true that $H^n(S)=S$. Sufficient conditions on $\Sigma$ are provided to have $H^n(S)=S$ for all or some $n\in\N$, and then the dynamics of $S$ under the admissible iterations of $f_i$'s defined by $\Sigma$ are investigated., Comment: 23 pages, 1 figure

It is well known that massless Goldstone bosons have not yet been observed. In the Goldstone boson model, after the spontaneous symmetry breaking under $U(1)$, two coupled nonlinear equations are obtained for which we present the exact solitonic solutions. These solutions completely localize the energy density of the model and show the existence of two boson fields, one massive and the other massless. Also, it is seen that the solitonic waves are modulated and the massless wave rides on the massive wave. Finally, we calculate the charge density of the model, which again confirms the neutrality of these boson fields. Since massive bosons can be observed in the laboratory, these solitonic waves may be useful in tracking and detecting Goldstone bosons., Comment: 9 pages, 3 figures. Accepted in International Journal of Modern Physics A

Adding visual cues to audio-based speech separation can improve separation performance. This paper introduces AV-CrossNet, an audiovisual (AV) system for speech enhancement, target speaker extraction, and multi-talker speaker separation. AV-CrossNet is extended from the CrossNet architecture, which is a recently proposed network that performs complex spectral mapping for speech separation by leveraging global attention and positional encoding. To effectively utilize visual cues, the proposed system incorporates pre-extracted visual embeddings and employs a visual encoder comprising temporal convolutional layers. Audio and visual features are fused in an early fusion layer before feeding to AV-CrossNet blocks. We evaluate AV-CrossNet on multiple datasets, including LRS, VoxCeleb, and COG-MHEAR challenge. Evaluation results demonstrate that AV-CrossNet advances the state-of-the-art performance in all audiovisual tasks, even on untrained and mismatched datasets., Comment: 10 pages, 4 Figures, and 4 Tables

As brain-computer interfacing (BCI) systems transition from assistive technology to more diverse applications, their speed, reliability, and user experience become increasingly important. Dynamic stopping methods enhance BCI system speed by deciding at any moment whether to output a result or wait for more information. Such approach leverages trial variance, allowing good trials to be detected earlier, thereby speeding up the process without significantly compromising accuracy. Existing dynamic stopping algorithms typically optimize measures such as symbols per minute (SPM) and information transfer rate (ITR). However, these metrics may not accurately reflect system performance for specific applications or user types. Moreover, many methods depend on arbitrary thresholds or parameters that require extensive training data. We propose a model-based approach that takes advantage of the analytical knowledge that we have about the underlying classification model. By using a risk minimisation approach, our model allows precise control over the types of errors and the balance between precision and speed. This adaptability makes it ideal for customizing BCI systems to meet the diverse needs of various applications. We validate our proposed method on a publicly available dataset, comparing it with established static and dynamic stopping methods. Our results demonstrate that our approach offers a broad range of accuracy-speed trade-offs and achieves higher precision than baseline stopping methods.

Artificial intelligence has dramatically reshaped our interaction with digital technologies, ushering in an era where advancements in AI algorithms and Large Language Models (LLMs) have natural language processing (NLP) systems like ChatGPT. This study delves into the impact of cutting-edge LLMs, notably OpenAI's ChatGPT, on medical diagnostics, with a keen focus on the dental sector. Leveraging publicly accessible datasets, these models augment the diagnostic capabilities of medical professionals, streamline communication between patients and healthcare providers, and enhance the efficiency of clinical procedures. The advent of ChatGPT-4 is poised to make substantial inroads into dental practices, especially in the realm of oral surgery. This paper sheds light on the current landscape and explores potential future research directions in the burgeoning field of LLMs, offering valuable insights for both practitioners and developers. Furthermore, it critically assesses the broad implications and challenges within various sectors, including academia and healthcare, thus mapping out an overview of AI's role in transforming dental diagnostics for enhanced patient care.

A major challenge in defending against adversarial attacks is the enormous space of possible attacks that even a simple adversary might perform. To address this, prior work has proposed a variety of defenses that effectively reduce the size of this space. These include randomized smoothing methods that add noise to the input to take away some of the adversary's impact. Another approach is input discretization which limits the adversary's possible number of actions. Motivated by these two approaches, we introduce a new notion of adversarial loss which we call distributional adversarial loss, to unify these two forms of effectively weakening an adversary. In this notion, we assume for each original example, the allowed adversarial perturbation set is a family of distributions (e.g., induced by a smoothing procedure), and the adversarial loss over each example is the maximum loss over all the associated distributions. The goal is to minimize the overall adversarial loss. We show generalization guarantees for our notion of adversarial loss in terms of the VC-dimension of the hypothesis class and the size of the set of allowed adversarial distributions associated with each input. We also investigate the role of randomness in achieving robustness against adversarial attacks in the methods described above. We show a general derandomization technique that preserves the extent of a randomized classifier's robustness against adversarial attacks. We corroborate the procedure experimentally via derandomizing the Random Projection Filters framework of \cite{dong2023adversarial}. Our procedure also improves the robustness of the model against various adversarial attacks.

This paper presents a comparative study of sampling methods within the FedHome framework, designed for personalized in-home health monitoring. FedHome leverages federated learning (FL) and generative convolutional autoencoders (GCAE) to train models on decentralized edge devices while prioritizing data privacy. A notable challenge in this domain is the class imbalance in health data, where critical events such as falls are underrepresented, adversely affecting model performance. To address this, the research evaluates six oversampling techniques using Stratified K-fold cross-validation: SMOTE, Borderline-SMOTE, Random OverSampler, SMOTE-Tomek, SVM-SMOTE, and SMOTE-ENN. These methods are tested on FedHome's public implementation over 200 training rounds with and without stratified K-fold cross-validation. The findings indicate that SMOTE-ENN achieves the most consistent test accuracy, with a standard deviation range of 0.0167-0.0176, demonstrating stable performance compared to other samplers. In contrast, SMOTE and SVM-SMOTE exhibit higher variability in performance, as reflected by their wider standard deviation ranges of 0.0157-0.0180 and 0.0155-0.0180, respectively. Similarly, the Random OverSampler method shows a significant deviation range of 0.0155-0.0176. SMOTE-Tomek, with a deviation range of 0.0160-0.0175, also shows greater stability but not as much as SMOTE-ENN. This finding highlights the potential of SMOTE-ENN to enhance the reliability and accuracy of personalized health monitoring systems within the FedHome framework., Comment: 11 Figures

Motor Imagery (MI) is gaining traction in both rehabilitation and sports settings, but its immediate influence on human postural control is not yet clearly understood. The focus of this study is to examine the effects of MI on the dynamics of the Center of Pressure (COP), a crucial metric for evaluating postural stability. In the experiment, thirty healthy young adults participated in four different scenarios: normal standing with both open and closed eyes, and kinesthetic motor imagery focused on mediolateral (ML) and anteroposterior (AP) sway movements. A mathematical model was developed to characterize the nonlinear dynamics of the COP and to assess the impact of MI on these dynamics. Our results show a statistically significant increase (p-value<0.05) in variables such as COP path length and Long-Range Correlation (LRC) during MI compared to the closed-eye and normal standing conditions. These observations align well with psycho-neuromuscular theory, which suggests that imagining a specific movement activates neural pathways, consequently affecting postural control. This study presents compelling evidence that motor imagery not only has a quantifiable impact on COP dynamics but also that changes in the Center of Pressure (COP) are directionally consistent with the imagined movements. This finding holds significant implications for the field of rehabilitation science, suggesting that motor imagery could be strategically utilized to induce targeted postural adjustments. Nonetheless, additional research is required to fully understand the complex mechanisms that underlie this relationship and to corroborate these results across a more diverse set of populations.

The way organs are positioned and moved in the workplace can cause pain and physical harm. Therefore, ergonomists use ergonomic risk assessments based on visual observation of the workplace, or review pictures and videos taken in the workplace. Sometimes the workers in the photos are not in perfect condition. Some parts of the workers' bodies may not be in the camera's field of view, could be obscured by objects, or by self-occlusion, this is the main problem in 2D human posture recognition. It is difficult to predict the position of body parts when they are not visible in the image, and geometric mathematical methods are not entirely suitable for this purpose. Therefore, we created a dataset with artificial images of a 3D human model, specifically for painful postures, and real human photos from different viewpoints. Each image we captured was based on a predefined joint angle for each 3D model or human model. We created various images, including images where some body parts are not visible. Nevertheless, the joint angle is estimated beforehand, so we could study the case by converting the input images into the sequence of joint connections between predefined body parts and extracting the desired joint angle with a convolutional neural network. In the end, we obtained root mean square error (RMSE) of 12.89 and mean absolute error (MAE) of 4.7 on the test dataset.

This paper introduces the Bi-linear consensus Alternating Direction Method of Multipliers (Bi-cADMM), aimed at solving large-scale regularized Sparse Machine Learning (SML) problems defined over a network of computational nodes. Mathematically, these are stated as minimization problems with convex local loss functions over a global decision vector, subject to an explicit $\ell_0$ norm constraint to enforce the desired sparsity. The considered SML problem generalizes different sparse regression and classification models, such as sparse linear and logistic regression, sparse softmax regression, and sparse support vector machines. Bi-cADMM leverages a bi-linear consensus reformulation of the original non-convex SML problem and a hierarchical decomposition strategy that divides the problem into smaller sub-problems amenable to parallel computing. In Bi-cADMM, this decomposition strategy is based on a two-phase approach. Initially, it performs a sample decomposition of the data and distributes local datasets across computational nodes. Subsequently, a delayed feature decomposition of the data is conducted on Graphics Processing Units (GPUs) available to each node. This methodology allows Bi-cADMM to undertake computationally intensive data-centric computations on GPUs, while CPUs handle more cost-effective computations. The proposed algorithm is implemented within an open-source Python package called Parallel Sparse Fitting Toolbox (PsFiT), which is publicly available. Finally, computational experiments demonstrate the efficiency and scalability of our algorithm through numerical benchmarks across various SML problems featuring distributed datasets.

With the increasing availability of diverse data types, particularly images and time series data from medical experiments, there is a growing demand for techniques designed to combine various modalities of data effectively. Our motivation comes from the important areas of predicting mortality and phenotyping where using different modalities of data could significantly improve our ability to predict. To tackle this challenge, we introduce a new method that uses two separate encoders, one for each type of data, allowing the model to understand complex patterns in both visual and time-based information. Apart from the technical challenges, our goal is to make the predictive model more robust in noisy conditions and perform better than current methods. We also deal with imbalanced datasets and use an uncertainty loss function, yielding improved results while simultaneously providing a principled means of modeling uncertainty. Additionally, we include attention mechanisms to fuse different modalities, allowing the model to focus on what's important for each task. We tested our approach using the comprehensive multimodal MIMIC dataset, combining MIMIC-IV and MIMIC-CXR datasets. Our experiments show that our method is effective in improving multimodal deep learning for clinical applications. The code will be made available online.

Estimating the Bone Age of children is very important for diagnosing growth defects, and related diseases, and estimating the final height that children reach after maturity. For this reason, it is widely used in different countries. Traditional methods for estimating bone age are performed by comparing atlas images and radiographic images of the left hand, which is time-consuming and error-prone. To estimate bone age using deep neural network models, a lot of research has been done, our effort has been to improve the accuracy and speed of this process by using the introduced approach. After creating and analyzing our initial model, we focused on preprocessing and made the inputs smaller, and increased their quality. we selected small regions of hand radiographs and estimated the age of the bone only according to these regions. by doing this we improved bone age estimation accuracy even further than what was achieved in related works, without increasing the required computational resource. We reached a Mean Absolute Error (MAE) of 3.90 months in the range of 0-20 years and an MAE of 3.84 months in the range of 1-18 years on the RSNA test set.

In the field of brain-computer interfaces (BCIs), the potential for leveraging deep learning techniques for representing electroencephalogram (EEG) signals has gained substantial interest. This review synthesizes empirical findings from a collection of articles using deep representation learning techniques for BCI decoding, to provide a comprehensive analysis of the current state-of-the-art. Each article was scrutinized based on three criteria: (1) the deep representation learning technique employed, (2) the underlying motivation for its utilization, and (3) the approaches adopted for characterizing the learned representations. Among the 81 articles finally reviewed in depth, our analysis reveals a predominance of 31 articles using autoencoders. We identified 13 studies employing self-supervised learning (SSL) techniques, among which ten were published in 2022 or later, attesting to the relative youth of the field. However, at the time being, none of these have led to standard foundation models that are picked up by the BCI community. Likewise, only a few studies have introspected their learned representations. We observed that the motivation in most studies for using representation learning techniques is for solving transfer learning tasks, but we also found more specific motivations such as to learn robustness or invariances, as an algorithmic bridge, or finally to uncover the structure of the data. Given the potential of foundation models to effectively tackle these challenges, we advocate for a continued dedication to the advancement of foundation models specifically designed for EEG signal decoding by using SSL techniques. We also underline the imperative of establishing specialized benchmarks and datasets to facilitate the development and continuous improvement of such foundation models., Comment: Submitted to: Journal of Neural Engineering (JNE)

We study joint optimization of service placement, request routing, and CPU sizing in a cooperative MEC system. The problem is considered from the perspective of the service provider (SP), which delivers heterogeneous MEC-enabled delay-sensitive services, and needs to pay for the used resources to the mobile network operators and the cloud provider, while earning revenue from the served requests. We formulate the problem of maximizing the SP's total profit subject to the computation, storage, and communication constraints of each edge node and end-to-end delay requirements of the services as a mixed-integer non-convex optimization problem, and prove it to be NP-hard. To tackle the challenges in solving the problem, we first introduce a design trade-off parameter for different delay requirements of each service, which maintains flexibility in prioritizing them, and transform the original optimization problem by the new delay constraints. Then, by exploiting a hidden convexity, we reformulate the delay constraints into an equivalent form. Next, to handle the challenge of the complicating (integer) variables, using primal decomposition, we decompose the problem into an equivalent form of master and inner sub-problems over the mixed and real variables, respectively. We then employ a cutting-plane approach for building up adequate representations of the extremal value of the inner problem as a function of the complicating variables and the set of values of the complicating variables for which the inner problem is feasible. Finally, we propose a solution strategy based on generalized Benders decomposition and prove its convergence to the optimal solution within a limited number of iterations. Extensive simulation results demonstrate that the proposed scheme significantly outperforms the existing mechanisms in terms of the SP's profit, cache hit ratio, running time, and end-to-end delay.

The proliferation of 5G technology presents an unprecedented challenge in managing the energy consumption of densely deployed network infrastructures, particularly Base Stations (BSs), which account for the majority of power usage in mobile networks. The O-RAN architecture, with its emphasis on open and intelligent design, offers a promising framework to address the Energy Efficiency (EE) demands of modern telecommunication systems. This paper introduces two xApps designed for the O-RAN architecture to optimize power savings without compromising the Quality of Service (QoS). Utilizing a commercial RAN Intelligent Controller (RIC) simulator, we demonstrate the effectiveness of our proposed xApps through extensive simulations that reflect real-world operational conditions. Our results show a significant reduction in power consumption, achieving up to 50% power savings with a minimal number of User Equipments (UEs), by intelligently managing the operational state of Radio Cards (RCs), particularly through switching between active and sleep modes based on network resource block usage conditions., Comment: 6 pages, 4 figures

Deep Reinforcement Learning (DRL) emerges as a prime solution for Unmanned Aerial Vehicle (UAV) trajectory planning, offering proficiency in navigating high-dimensional spaces, adaptability to dynamic environments, and making sequential decisions based on real-time feedback. Despite these advantages, the use of DRL for UAV trajectory planning requires significant retraining when the UAV is confronted with a new environment, resulting in wasted resources and time. Therefore, it is essential to develop techniques that can reduce the overhead of retraining DRL models, enabling them to adapt to constantly changing environments. This paper presents a novel method to reduce the need for extensive retraining using a double deep Q network (DDQN) model as a pretrained base, which is subsequently adapted to different urban environments through Continuous Transfer Learning (CTL). Our method involves transferring the learned model weights and adapting the learning parameters, including the learning and exploration rates, to suit each new environment specific characteristics. The effectiveness of our approach is validated in three scenarios, each with different levels of similarity. CTL significantly improves learning speed and success rates compared to DDQN models initiated from scratch. For similar environments, Transfer Learning (TL) improved stability, accelerated convergence by 65%, and facilitated 35% faster adaptation in dissimilar settings., Comment: 6 pages

Accretion bursts from low-mass young stellar objects (YSOs) are known for many decades. In recent years, the first accretion bursts of massive YSOs (MYSOs) have been observed. These phases of intense protostellar growth are of particular importance for studying massive star formation. Bursts of MYSOs are accompanied by flares of Class II methanol masers (hereafter masers), caused by an increase in exciting mid-infrared (MIR) emission. The G323.46$-$0.08 (hereafter G323) event extends the small sample of known MYSO bursts. Maser observations of the MYSO G323 show evidence of a flare, which was presumed to be caused by an accretion burst. This should be verified with IR data. We used time-dependent radiative transfer (TDRT) to characterize the heating and cooling timescales for eruptive MYSOs and to infer the main burst parameters. The G323 accretion burst is confirmed. It reached its peak in late 2013/early 2014 with a Ks-band increase of 2.5mag. TDRT indicates that the duration of the thermal afterglow in the far-infrared (FIR) can exceed the burst duration by years. The latter was proved by SOFIA observations, which indicate a flux increase of $(14.2\pm4.6)$% at $70\, \rm \mu m$ and $(8.5\pm6.1)$% at $160\, \mu$m in 2022 (2 years after the burst end). A one-sided light echo emerged that was propagating into the interstellar medium. The G323 burst is probably the most energetic MYSO burst observed so far. Within $8.4 \rm \, yrs$, an energy of $(0.9\pm_{0.8}^{2.5}) \times 10^{47}\,\rm erg$ was released. The short timescale points to the accretion of a compact body, while the burst energy corresponds to an accumulated mass of at least $(7\pm_{6}^{20})\,M_{Jup}$ and possibly even more if the protostar is bloated. In this case, the accretion event might have triggered protostellar pulsations, which give rise to the observed maser periodicity.

In this article, we focus on the critical tasks of plant protection in arable farms, addressing a modern challenge in agriculture: integrating ecological considerations into the operational strategy of precision weeding robots like \bbot. This article presents the recent advancements in weed management algorithms and the real-world performance of \bbot\ at the University of Bonn's Klein-Altendorf campus. We present a novel Rolling-view observation model for the BonnBot-Is weed monitoring section which leads to an average absolute weeding performance enhancement of $3.4\%$. Furthermore, for the first time, we show how precision weeding robots could consider bio-diversity-aware concerns in challenging weeding scenarios. We carried out comprehensive weeding experiments in sugar-beet fields, covering both weed-only and mixed crop-weed situations, and introduced a new dataset compatible with precision weeding. Our real-field experiments revealed that our weeding approach is capable of handling diverse weed distributions, with a minimal loss of only $11.66\%$ attributable to intervention planning and $14.7\%$ to vision system limitations highlighting required improvements of the vision system.