Search

Pulmonary embolism (PE) is a leading cause of preventable in-hospital mortality. Advances in diagnosis, risk stratification, and prevention can improve outcomes. There are few large publicly available datasets that contain PE labels for research. Using the MIMIC-IV database, we extracted all available radiology reports of computed tomography pulmonary angiography (CTPA) scans and two physicians manually labeled the results as PE positive (acute PE) or PE negative. We then applied a previously finetuned Bio_ClinicalBERT transformer language model, VTE-BERT, to extract labels automatically. We verified VTE-BERT's reliability by measuring its performance against manual adjudication. We also compared the performance of VTE-BERT to diagnosis codes. We found that VTE-BERT has a sensitivity of 92.4% and positive predictive value (PPV) of 87.8% on all 19,942 patients with CTPA radiology reports from the emergency room and/or hospital admission. In contrast, diagnosis codes have a sensitivity of 95.4% and PPV of 83.8% on the subset of 11,990 hospitalized patients with discharge diagnosis codes. We successfully add nearly 20,000 labels to CTPAs in a publicly available dataset and demonstrate the external validity of a semi-supervised language model in accelerating hematologic research.

Continuous arterial blood pressure (ABP) monitoring is invasive but essential for hemodynamic monitoring. Recent techniques have reconstructed ABP non-invasively using pulsatile signals but produced inaccurate systolic and diastolic blood pressure (SBP and DBP) values and were sensitive to individual variability. ArterialNet integrates generalized pulsatile-to-ABP signal translation and personalized feature extraction using hybrid loss functions and regularization. We validated ArterialNet using the MIMIC-III dataset and achieved a root mean square error (RMSE) of 5.41 mmHg, with at least a 58% lower standard deviation. ArterialNet reconstructed ABP with an RMSE of 7.99 mmHg in remote health scenarios. ArterialNet achieved superior performance in ABP reconstruction and SBP and DBP estimations, with significantly reduced subject variance, demonstrating its potential in remote health settings. We also ablated ArterialNet architecture to investigate the contributions of each component and evaluated its translational impact and robustness by conducting a series of ablations on data quality and availability.

The present paper investigated automatic melody construction for Persian lyrics as an input. It was assumed that there is a phonological correlation between the lyric syllables and the melody in a song. A seq2seq neural network was developed to investigate this assumption, trained on parallel syllable and note sequences in Persian songs to suggest a pleasant melody for a new sequence of syllables. More than 100 pieces of Persian music were collected and converted from the printed version to the digital format due to the lack of a dataset on Persian digital music. Finally, 14 new lyrics were given to the model as input, and the suggested melodies were performed and recorded by music experts to evaluate the trained model. The evaluation was conducted using an audio questionnaire, which more than 170 persons answered. According to the answers about the pleasantness of melody, the system outputs scored an average of 3.005 from 5, while the human-made melodies for the same lyrics obtained an average score of 4.078.

Initiating a quest to unravel the complexities of musical aesthetics through the lens of information dynamics, our study delves into the realm of musical sequence modeling, drawing a parallel between the sequential structured nature of music and natural language. Despite the prevalence of neural network models in MIR, the modeling of symbolic music events as applied to music cognition and music neuroscience has largely relied on statistical models. In this "proof of concept" paper we posit the superiority of neural network models over statistical models for predicting musical events. Specifically, we compare LSTM, Transformer, and GPT models against a widely-used markov model to predict a chord event following a sequence of chords. Utilizing chord sequences from the McGill Billboard dataset, we trained each model to predict the next chord from a given sequence of chords. We found that neural models significantly outperformed statistical ones in our study. Specifically, the LSTM with attention model led with an accuracy of 0.329, followed by Transformer models at 0.321, GPT at 0.301, and standard LSTM at 0.191. Variable Order Markov and Markov trailed behind with accuracies of 0.277 and 0.140, respectively. Encouraged by these results, we extended our investigation to multidimensional modeling, employing a many-to-one LSTM, LSTM with attention, Transformer, and GPT predictors. These models were trained on both chord and melody lines as two-dimensional data using the CoCoPops Billboard dataset, achieving an accuracy of 0.083, 0.312, 0.271, and 0.120, respectively, in predicting the next chord., Comment: Presented in Society for Music Perception and Cognition 2024 Conference at the Banff Centre for Arts and Creativity

The use of foundation models in climate science has recently gained significant attention. However, a critical issue remains: the lack of a comprehensive evaluation framework capable of assessing the quality and scientific validity of model outputs. To address this issue, we develop ClimaGen (Climate QA Generator), an automated algorithmic framework that generates question-answer pairs from graduate textbooks with climate scientists in the loop. As a result, we present ClimaQA-Gold, an expert-annotated benchmark dataset alongside ClimaQA-Silver, a large-scale, comprehensive synthetic QA dataset for climate science. Finally, we develop evaluation strategies and compare different Large Language Models (LLMs) on our benchmarks. Our results offer novel insights into various approaches used to enhance climate foundation models.

Responsible AI (RAI) has emerged as a major focus across industry, policymaking, and academia, aiming to mitigate the risks and maximize the benefits of AI, both on an organizational and societal level. This study explores the global state of RAI through one of the most extensive surveys to date on the topic, surveying 1000 organizations across 20 industries and 19 geographical regions. We define a conceptual RAI maturity model for organizations to map how well they implement organizational and operational RAI measures. Based on this model, the survey assesses the adoption of system-level measures to mitigate identified risks related to, for example, discrimination, reliability, or privacy, and also covers key organizational processes pertaining to governance, risk management, and monitoring and control. The study highlights the expanding AI risk landscape, emphasizing the need for comprehensive risk mitigation strategies. The findings also reveal significant strides towards RAI maturity, but we also identify gaps in RAI implementation that could lead to increased (public) risks from AI systems. This research offers a structured approach to assess and improve RAI practices globally and underscores the critical need for bridging the gap between RAI planning and execution to ensure AI advancement aligns with human welfare and societal benefits.

This study employs Natural Language Processing (NLP) to analyze the intricate linguistic and emotional dimensions within the plays of Bernard-Marie Kolt\`es, a central figure in contemporary French theatre. By integrating advanced computational techniques, we dissect Kolt\`es' narrative style, revealing the subtle interplay between language and emotion across his dramatic oeuvre. Our findings highlight how Kolt\`es crafts his narratives, enriching our understanding of his thematic explorations and contributing to the broader field of digital humanities in literary analysis.

Exploring the depths of Samuel Beckett's "Not I" through advanced natural language processing techniques, this research uncovers the intricate linguistic structures that underpin the text. By analyzing word frequency, detecting emotional sentiments with a BERT-based model, and examining repetitive motifs, we unveil how Beckett's minimalist yet complex language reflects the protagonist's fragmented psyche. Our results demonstrate that recurring themes of time, memory, and existential angst are artfully woven through recursive linguistic patterns and rhythmic repetition. This innovative approach not only deepens our understanding of Beckett's stylistic contributions but also highlights his unique role in modern literature, where language transcends simple communication to explore profound existential questions.

This work introduces a new neural model which follows the transport equation by design. A physical problem, the Taylor-Green vortex, defined on a bi-periodic domain, is used as a benchmark to evaluate the performance of both the standard physics-informed neural network and our model (transport-embedded neural network). Results exhibit that while the standard physics-informed neural network fails to predict the solution accurately and merely returns the initial condition for the entire time span, our model successfully captures the temporal changes in the physics, particularly for high Reynolds numbers of the flow. Additionally, the ability of our model to prevent false minima can pave the way for addressing multiphysics problems, which are more prone to false minima, and help them accurately predict complex physics.

Language typology databases enhance multi-lingual Natural Language Processing (NLP) by improving model adaptability to diverse linguistic structures. The widely-used lang2vec toolkit integrates several such databases, but its coverage remains limited at 28.9\%. Previous work on automatically increasing coverage predicts missing values based on features from other languages or focuses on single features, we propose to use textual data for better-informed feature prediction. To this end, we introduce a multi-lingual Part-of-Speech (POS) tagger, achieving over 70\% accuracy across 1,749 languages, and experiment with external statistical features and a variety of machine learning algorithms. We also introduce a more realistic evaluation setup, focusing on likely to be missing typology features, and show that our approach outperforms previous work in both setups., Comment: 9 pages, 11 figures

Large Language Models (LLMs), with their increasing depth and number of parameters, have demonstrated outstanding performance across a variety of natural language processing tasks. However, this growth in scale leads to increased computational demands, particularly during inference and fine-tuning. To address these challenges, we introduce EchoAtt, a novel framework aimed at optimizing transformer-based models by analyzing and leveraging the similarity of attention patterns across layers. Our analysis reveals that many inner layers in LLMs, especially larger ones, exhibit highly similar attention matrices. By exploiting this similarity, EchoAtt enables the sharing of attention matrices in less critical layers, significantly reducing computational requirements without compromising performance. We incorporate this approach within a knowledge distillation setup, where a pre-trained teacher model guides the training of a smaller student model. The student model selectively shares attention matrices in layers with high similarity while inheriting key parameters from the teacher. Our best results with TinyLLaMA-1.1B demonstrate that EchoAtt improves inference speed by 15\%, training speed by 25\%, and reduces the number of parameters by approximately 4\%, all while improving zero-shot performance. These findings highlight the potential of attention matrix sharing to enhance the efficiency of LLMs, making them more practical for real-time and resource-limited applications.

We introduce a novel category of set functions called Extended Deep Submodular functions (EDSFs), which are neural network-representable. EDSFs serve as an extension of Deep Submodular Functions (DSFs), inheriting crucial properties from DSFs while addressing innate limitations. It is known that DSFs can represent a limiting subset of submodular functions. In contrast, through an analysis of polymatroid properties, we establish that EDSFs possess the capability to represent all monotone submodular functions, a notable enhancement compared to DSFs. Furthermore, our findings demonstrate that EDSFs can represent any monotone set function, indicating the family of EDSFs is equivalent to the family of all monotone set functions. Additionally, we prove that EDSFs maintain the concavity inherent in DSFs when the components of the input vector are non-negative real numbers-an essential feature in certain combinatorial optimization problems. Through extensive experiments, we illustrate that EDSFs exhibit significantly lower empirical generalization error than DSFs in the learning of coverage functions. This suggests that EDSFs present a promising advancement in the representation and learning of set functions with improved generalization capabilities.

The world of Machine Learning (ML) has witnessed rapid changes in terms of new models and ways to process users data. The majority of work that has been done is focused on Deep Learning (DL) based approaches. However, with the emergence of new algorithms such as the Tsetlin Machine (TM) algorithm, there is growing interest in exploring alternative approaches that may offer unique advantages in certain domains or applications. One of these domains is Federated Learning (FL), in which users privacy is of utmost importance. Due to its novelty, FL has seen a surge in the incorporation of personalization techniques to enhance model accuracy while maintaining user privacy under personalized conditions. In this work, we propose a novel approach called TPFL: Tsetlin-Personalized Federated Learning, in which models are grouped into clusters based on their confidence towards a specific class. In this way, clustering can benefit from two key advantages. Firstly, clients share only what they are confident about, resulting in the elimination of wrongful weight aggregation among clients whose data for a specific class may have not been enough during the training. This phenomenon is prevalent when the data are non-Independent and Identically Distributed (non-IID). Secondly, by sharing only weights towards a specific class, communication cost is substantially reduced, making TPLF efficient in terms of both accuracy and communication cost. The TPFL results were compared with 6 other baseline methods; namely FedAvg, FedProx, FLIS DC, FLIS HC, IFCA and FedTM. The results demonstrated that TPFL performance better than baseline methods with 98.94% accuracy on MNIST, 98.52% accuracy on FashionMNIST and 91.16% accuracy on FEMNIST dataset.

Nonreciprocal thermal emitters that break Kirchhoff's law of thermal radiation promise exciting applications for thermal and energy applications. The design of the bandwidth and angular range of the nonreciprocal effect, which directly affects the performance of nonreciprocal emitters, typically relies on physical intuition. In this study, we present a general numerical approach to maximize the nonreciprocal effect. We choose doped magneto-optic materials and magnetic Weyl semimetal materials as model materials and focus on pattern-free multilayer structures. The optimization randomly starts from a less effective structure and incrementally improves the broadband nonreciprocity through the combination of Bayesian optimization and reparameterization. Optimization results show that the proposed approach can discover structures that can achieve broadband nonreciprocal emission at wavelengths from 5 to 40 micrometers using only a fewer layers, significantly outperforming current state-of-the-art designs based on intuition in terms of both performance and simplicity.

This paper describes Auriga's @Work team and their robot, developed at Shahid Beheshti University Faculty of Electrical Engineering's Robotics and Intelligent Automation Lab for RoboCup 2024 competitions. The robot is designed for industrial tasks, optimizing efficiency in repetitive or hazardous environments. It features a 4-wheel Mecanum system for omnidirectional movement and a 5-degree-of-freedom manipulator arm with a 3D-printed gripper for object handling and navigation. The electronics include custom boards with ESP32 microcontrollers and an Nvidia Jetson Nano for real-time control. Key software components include Hector SLAM for mapping, A* path planning, and YOLO for object detection, supported by integrated sensors for enhanced navigation and collision avoidance.

Brain is one the most complex organs in the human body. Due to its complexity, classification of brain tumors still poses a significant challenge, making brain tumors a particularly serious medical issue. Techniques such as Machine Learning (ML) coupled with Magnetic Resonance Imaging (MRI) have paved the way for doctors and medical institutions to classify different types of tumors. However, these techniques suffer from limitations that violate patients privacy. Federated Learning (FL) has recently been introduced to solve such an issue, but the FL itself suffers from limitations like communication costs and dependencies on model architecture, forcing all models to have identical architectures. In this paper, we propose FedBrain-Distill, an approach that leverages Knowledge Distillation (KD) in an FL setting that maintains the users privacy and ensures the independence of FL clients in terms of model architecture. FedBrain-Distill uses an ensemble of teachers that distill their knowledge to a simple student model. The evaluation of FedBrain-Distill demonstrated high-accuracy results for both Independent and Identically Distributed (IID) and non-IID data with substantial low communication costs on the real-world Figshare brain tumor dataset. It is worth mentioning that we used Dirichlet distribution to partition the data into IID and non-IID data. All the implementation details are accessible through our Github repository.

The Master Stability Function is a robust and useful tool for determining the conditions of synchronization stability in a network of coupled systems. While a comprehensive classification exists in the case in which the nodes are chaotic dynamical systems, its application to periodic systems has been less explored. By studying several well-known periodic systems, we establish a comprehensive framework to understand and classify their properties of synchronizability. This allows us to define five distinct classes of synchronization stability, including some that are unique to periodic systems. Specifically, in periodic systems, the Master Stability Function vanishes at the origin, and it can therefore display behavioral classes that are not achievable in chaotic systems, where it starts, instead, at a strictly positive value. Moreover, our results challenge the widely-held belief that periodic systems are easily put in a stable synchronous state, showing, instead, the common occurrence of a lower threshold for synchronization stability., Comment: 8 pages, 6 figures, plus supplementary material with 5 pages and 6 figures

Software Defined Networks (SDN) face many security challenges today. A great deal of research has been done within the field of Intrusion Detection Systems (IDS) in these networks. Yet, numerous approaches still rely on deep learning algorithms. These algorithms suffer from complexity in implementation, high processing power and high memory consumption. In addition to security issues, firstly, the number of datasets that are based on SDN protocols are very small. Secondly, the ones that are available encompass numerous attacks in the network and do not focus on a single attack. For this reason, to introduce an SDN-based IDS with a focus on Distributed Denial of Service (DDoS) attacks, it is necessary to generate a DDoS-oriented dataset whose features can train a high-quality IDS. In this work, in order to address two important challenges in SDNs, initially, we generate three DDoS attack datasets based on three common and different network topologies. In the second step, using the Convolutional Tsetlin Machine (CTM), we introduce a lightweight IDS for DDoS attack dubbed CTMBIDS. The lightweight nature of the CTMBIDS stems from its low memory consumption and also its interpretability compared to the existing complex deep learning models. The low usage of system resources for the CTMBIDS makes it an ideal choice for an optimal software that consumes the SDN controllers least amount of memory. Also, in order to ascertain the quality of the generated datasets, we compare the CTMBIDS empirical results with the DDoS attacks of the KDDCup99 benchmark dataset as well. Since the main focus of this work is on a lightweight IDS, the results show the CTMBIDS performs much more efficiently than deep learning based approaches. Furthermore, the results also show in most datasets, the proposed method has relatively equal or better accuracy and also consumes much less memory than the existing methods.

We analyze the coherence dynamics of a central spin coupled to a spin chain with a time-dependent noisy magnetic field, focusing on how noise influences the system's decoherence. Our results show that decoherency due to the nonequilibrium critical dynamics of the environment is amplified in the presence of uncorrelated and correlated Gaussian noise. We demonstrate that decoherence factor consistently signals the critical points, and exhibits exponential scaling with the system size, the square of noise intensity, and the noise correlation time at the critical points. We find that strong coupling between the qubit and the environment allows partial revivals of coherence, which diminish with increasing noise intensity or decreasing noise correlation time. In contrast, weak coupling leads to monotonic enhanced decoherence. The numerical results illustrate that, the revivals decay and scale exponentially with noise intensity. Moreover, the revivals increase and indicate linear or power law scaling with noise correlation time depends on how the correlated noise is fast or slow. Additionally, we explore the non-Markovianity of the dynamics, finding that it decays in the presence of noise but increases as the noise correlation time grows. Our findings have potential applications in the noise spectroscopy of external signals.

The emergence of new and disruptive technologies makes the economy and labor market more unstable. To overcome this kind of uncertainty and to make the labor market more comprehensible, we must employ labor market intelligence techniques, which are predominantly based on data analysis. Companies use job posting sites to advertise their job vacancies, known as online job vacancies (OJVs). LinkedIn is one of the most utilized websites for matching the supply and demand sides of the labor market; companies post their job vacancies on their job pages, and LinkedIn recommends these jobs to job seekers who are likely to be interested. However, with the vast number of online job vacancies, it becomes challenging to discern overarching trends in the labor market. In this paper, we propose a data mining-based approach for job classification in the modern online labor market. We employed structural topic modeling as our methodology and used the NASDAQ-100 indexed companies' online job vacancies on LinkedIn as the input data. We discover that among all 13 job categories, Marketing, Branding, and Sales; Software Engineering; Hardware Engineering; Industrial Engineering; and Project Management are the most frequently posted job classifications. This study aims to provide a clearer understanding of job market trends, enabling stakeholders to make informed decisions in a rapidly evolving employment landscape., Comment: 17 pages, 4 figures, 1 table. Presented at the International Conference on Optimization and Data Science in Industrial Engineering (ODSIE 2023)

Explainable Artificial Intelligence (XAI) plays a crucial role in fostering transparency and trust in AI systems, where traditional XAI approaches typically offer one level of abstraction for explanations, often in the form of heatmaps highlighting single or multiple input features. However, we ask whether abstract reasoning or problem-solving strategies of a model may also be relevant, as these align more closely with how humans approach solutions to problems. We propose a framework, called Symbolic XAI, that attributes relevance to symbolic queries expressing logical relationships between input features, thereby capturing the abstract reasoning behind a model's predictions. The methodology is built upon a simple yet general multi-order decomposition of model predictions. This decomposition can be specified using higher-order propagation-based relevance methods, such as GNN-LRP, or perturbation-based explanation methods commonly used in XAI. The effectiveness of our framework is demonstrated in the domains of natural language processing (NLP), vision, and quantum chemistry (QC), where abstract symbolic domain knowledge is abundant and of significant interest to users. The Symbolic XAI framework provides an understanding of the model's decision-making process that is both flexible for customization by the user and human-readable through logical formulas.

We show that magnetic reconnection and topology-change can be understood, and distinguished, in terms of trajectories of Alfv\'enic wave-packets ${\bf x}(t)$ moving along the magnetic field ${\bf B(x}, t)$ with Alfv\'en velocity $\dot{\bf x}(t)={\bf V}_A({\bf x},t)$, i.e. adopting a Lagrangian formalism for virtual particles. A considerable simplification is attained, in fact, by directly employing elementary concepts from hydrodynamic turbulence without appealing to the fictitious and complicated notion of magnetic field lines moving through plasma. In incompressible flows, Alfv\'enic trajectories correspond to the dynamical system $\dot{\bf x}(t)={\bf B}$, where $\bf B$ solves the induction equation, with phase space $(\bf x,B)$. Metric topology of this phase space, at any time $t$, captures the intuitive notion that nearby wave-packets should remain nearby at a slightly different time $t\pm \delta t$, unless topology changes e.g., by dissipation. In fact, continuity conditions for magnetic field allow rapid but continuous divergence of these trajectories, i.e., reconnection, but not discontinuous divergence which would change magnetic topology. Thus topology can change only due to time-reversal symmetry breaking e.g., by dissipation or turbulence. In laminar and even chaotic flows, the separation of Alfv\'enic trajectories at all times remains proportional to their initial separation, i.e., slow reconnection, and topology changes by dissipation with a rate proportional to resistivity. In turbulence, trajectories diverge super-linearly with time independent of their initial separation, i.e., fast reconnection, and magnetic topology changes by turbulent diffusion with a rate independent of small-scale plasma effects. Our results strongly support the Lazarian-Vishniac model of stochastic reconnection and its reformulation by Eyink in terms of stochastic flux-freezing.

Advancing the capabilities of earthquake nowcasting, the real-time forecasting of seismic activities remains a crucial and enduring objective aimed at reducing casualties. This multifaceted challenge has recently gained attention within the deep learning domain, facilitated by the availability of extensive, long-term earthquake datasets. Despite significant advancements, existing literature on earthquake nowcasting lacks comprehensive evaluations of pre-trained foundation models and modern deep learning architectures. These architectures, such as transformers or graph neural networks, uniquely focus on different aspects of data, including spatial relationships, temporal patterns, and multi-scale dependencies. This paper addresses the mentioned gap by analyzing different architectures and introducing two innovation approaches called MultiFoundationQuake and GNNCoder. We formulate earthquake nowcasting as a time series forecasting problem for the next 14 days within 0.1-degree spatial bins in Southern California, spanning from 1986 to 2024. Earthquake time series is forecasted as a function of logarithm energy released by quakes. Our comprehensive evaluation employs several key performance metrics, notably Nash-Sutcliffe Efficiency and Mean Squared Error, over time in each spatial region. The results demonstrate that our introduced models outperform other custom architectures by effectively capturing temporal-spatial relationships inherent in seismic data. The performance of existing foundation models varies significantly based on the pre-training datasets, emphasizing the need for careful dataset selection. However, we introduce a new general approach termed MultiFoundationPattern that combines a bespoke pattern with foundation model results handled as auxiliary streams. In the earthquake case, the resultant MultiFoundationQuake model achieves the best overall performance., Comment: 22 pages, 8 figures, 2 tables

Novelty detection is a critical task for deploying machine learning models in the open world. A crucial property of novelty detection methods is universality, which can be interpreted as generalization across various distributions of training or test data. More precisely, for novelty detection, distribution shifts may occur in the training set or the test set. Shifts in the training set refer to cases where we train a novelty detector on a new dataset and expect strong transferability. Conversely, distribution shifts in the test set indicate the methods' performance when the trained model encounters a shifted test sample. We experimentally show that existing methods falter in maintaining universality, which stems from their rigid inductive biases. Motivated by this, we aim for more generalized techniques that have more adaptable inductive biases. In this context, we leverage the fact that contrastive learning provides an efficient framework to easily switch and adapt to new inductive biases through the proper choice of augmentations in forming the negative pairs. We propose a novel probabilistic auto-negative pair generation method AutoAugOOD, along with contrastive learning, to yield a universal novelty detector method. Our experiments demonstrate the superiority of our method under different distribution shifts in various image benchmark datasets. Notably, our method emerges universality in the lens of adaptability to different setups of novelty detection, including one-class, unlabeled multi-class, and labeled multi-class settings. Code: https://github.com/mojtaba-nafez/UNODE, Comment: 16 pages, 5 figures, conference

We investigate some interesting solutions in the DSR theories. These solutions have important features in optics and mechanics. We use these similarities for a better understanding of these theories. We know that, the vacuum in the DSR has an effective refractive index which depends on the frequency of the light. We find this modified refractive index which leads us to a modified Electrodynamics with some new interesting aspects, for example near the Planck energy the electric field can be stronger or weaker than the usual case. Also, we will find a new modified Lorentz transformations in the first order of the Planck length which are very similar to the usual Lorentz transformations., Comment: 6 pages

In recent years, talking head generation has become a focal point for researchers. Considerable effort is being made to refine lip-sync motion, capture expressive facial expressions, generate natural head poses, and achieve high video quality. However, no single model has yet achieved equivalence across all these metrics. This paper aims to animate a 3D face using Jamba, a hybrid Transformers-Mamba model. Mamba, a pioneering Structured State Space Model (SSM) architecture, was designed to address the constraints of the conventional Transformer architecture. Nevertheless, it has several drawbacks. Jamba merges the advantages of both Transformer and Mamba approaches, providing a holistic solution. Based on the foundational Jamba block, we present JambaTalk to enhance motion variety and speed through multimodal integration. Extensive experiments reveal that our method achieves performance comparable or superior to state-of-the-art models., Comment: 12 pages with 3 figures

Claim verification can be a challenging task. In this paper, we present a method to enhance the robustness and reasoning capabilities of automated claim verification through the extraction of short facts from evidence. Our novel approach, FactDetect, leverages Large Language Models (LLMs) to generate concise factual statements from evidence and label these facts based on their semantic relevance to the claim and evidence. The generated facts are then combined with the claim and evidence. To train a lightweight supervised model, we incorporate a fact-detection task into the claim verification process as a multitasking approach to improve both performance and explainability. We also show that augmenting FactDetect in the claim verification prompt enhances performance in zero-shot claim verification using LLMs. Our method demonstrates competitive results in the supervised claim verification model by 15% on the F1 score when evaluated for challenging scientific claim verification datasets. We also demonstrate that FactDetect can be augmented with claim and evidence for zero-shot prompting (AugFactDetect) in LLMs for verdict prediction. We show that AugFactDetect outperforms the baseline with statistical significance on three challenging scientific claim verification datasets with an average of 17.3% performance gain compared to the best performing baselines.

Polar regions are covered by sea ice, which can be seen as a thin solid elastic sheet with heterogeneous mechanical properties. The dynamics of deformation of a floating solid sheet are primarly governed by gravity, water density, and the flexural modulus, which depends on its mechanical properties, namely the thickness, the Young's Modulus and the Poisson ratio. Non-invasive methods from seismology can retrieve these three parameters from sheet deformation dynamics. In this article, we developed another method to extract locally the flexural modulus of a floating thin elastic sheet from the spatio-temporal deformations of the sheet. We perform laboratory experiment to test the accuracy and the robustness of this method on silicon membranes of controlled mechanical properties. Using patches of different thicknesses and shapes, we eventually draw maps of sheet thickness, with a sub-wavelength spatial resolution.

Automatic spelling correction stands as a pivotal challenge within the ambit of natural language processing (NLP), demanding nuanced solutions. Traditional spelling correction techniques are typically only capable of detecting and correcting non-word errors, such as typos and misspellings. However, context-sensitive errors, also known as real-word errors, are more challenging to detect because they are valid words that are used incorrectly in a given context. The Persian language, characterized by its rich morphology and complex syntax, presents formidable challenges to automatic spelling correction systems. Furthermore, the limited availability of Persian language resources makes it difficult to train effective spelling correction models. This paper introduces a cutting-edge approach for precise and efficient real-word error correction in Persian text. Our methodology adopts a structured, multi-tiered approach, employing semantic analysis, feature selection, and advanced classifiers to enhance error detection and correction efficacy. The innovative architecture discovers and stores semantic similarities between words and phrases in Persian text. The classifiers accurately identify real-word errors, while the semantic ranking algorithm determines the most probable corrections for real-word errors, taking into account specific spelling correction and context properties such as context, semantic similarity, and edit-distance measures. Evaluations have demonstrated that our proposed method surpasses previous Persian real-word error correction models. Our method achieves an impressive F-measure of 96.6% in the detection phase and an accuracy of 99.1% in the correction phase. These results clearly indicate that our approach is a highly promising solution for automatic real-word error correction in Persian text., Comment: Neural Comput & Applic (2024)

This research introduces a state-of-the-art Persian spelling correction system that seamlessly integrates deep learning techniques with phonetic analysis, significantly enhancing the accuracy and efficiency of natural language processing (NLP) for Persian. Utilizing a fine-tuned language representation model, our methodology effectively combines deep contextual analysis with phonetic insights, adeptly correcting both non-word and real-word spelling errors. This strategy proves particularly effective in tackling the unique complexities of Persian spelling, including its elaborate morphology and the challenge of homophony. A thorough evaluation on a wide-ranging dataset confirms our system's superior performance compared to existing methods, with impressive F1-Scores of 0.890 for detecting real-word errors and 0.905 for correcting them. Additionally, the system demonstrates a strong capability in non-word error correction, achieving an F1-Score of 0.891. These results illustrate the significant benefits of incorporating phonetic insights into deep learning models for spelling correction. Our contributions not only advance Persian language processing by providing a versatile solution for a variety of NLP applications but also pave the way for future research in the field, emphasizing the critical role of phonetic analysis in developing effective spelling correction system.

The nonequilibrium dynamics of long-range pairing Kitaev model with noiseless/noisy linear time dependent chemical potential, is investigated in the frame work of dynamical quantum phase transitions (DQPTs). We have shown for the ramp crosses a single quantum critical point, while the short-range pairing Kitaev model displays a single critical time scale, the long-range pairing induces a region with three DQPTs time scales. We have found that the region with three DQPTs time scales shrinks in the presence of the noise. In addition, we have uncovered for a quench crossess two critical points, the critical sweep velocity above which the DQPTs disappear, enhances by the long-range pairing exponent while decreases in the presence of the noise. On the basis of numerical simulations, we have shown that noise diminishes the long-range pairing inductions., Comment: 11 pages, 6 figures. arXiv admin note: substantial text overlap with arXiv:2310.15101

In this paper, we propose and investigate the concept of $k$-coalitions in graphs, where $k\ge 1$ is an integer. A $k$-coalition refers to a pair of disjoint vertex sets that jointly constitute a $k$-dominating set of the graph, meaning that every vertex not in the set has at least $k$ neighbors in the set. We define a $k$-coalition partition of a graph as a vertex partition in which each set is either a $k$-dominating set with exactly $k$ members or forms a $k$-coalition with another set in the partition. The maximum number of sets in a $k$-coalition partition is called the $k$-coalition number of the graph represented by $C_k(G)$. We present fundamental findings regarding the properties of $k$-coalitions and their connections with other graph parameters. We obtain the exact values of $2$-coalition number of some specific graphs and also study graphs with large $2$-coalition number., Comment: 13 pages, 1 figure

Micro-mobility transport vehicles such as e-scooters are joining current sidewalk users and affect the safety and comfort of pedestrians as primary sidewalk users. The lack of agreed-upon metrics to quantify people's discomfort hinders shared public space safety research. We introduce perceived Time To Collision (TTC) as a potential metric of user discomfort performing controlled experiments using an e-scooter and a pedestrian moving in a hallway. The results strongly correlate the participant's reported discomfort and the perceived TTC. Therefore, TTC is a potential metric for public space users' discomfort. Since the metric only uses relative velocity and position information, it is a viable candidate for neighboring people's discomfort estimation in advanced driver assistance systems for e-scooters and PMVs. Our ongoing research extends the results to mobile robots., Comment: 6 pages, 7 figures, 1 table, IFAC 2023

Today, electric scooter is a trendy personal mobility vehicle. The rising demand and opportunities attract ride-share services. A common problem of such services is abandoned e-scooters. An autonomous e-scooter capable of moving to the charging station is a solution. This paper focuses on maintaining balance for these riderless e-scooters. The paper presents a nonlinear model for an e-scooter moving with simultaneously varying speed and steering. A PD and a feedback-linearized PD controller stabilize the model. The stability analysis shows that the controllers are ultimately bounded even with parameter uncertainties and measurement inaccuracy. Simulations on a realistic e-scooter with a general demanding path to follow verify the ultimate boundedness of the controllers. In addition, the feedback-linearized PD controller outperforms the PD controller because it has narrower ultimate bounds. Future work focuses on experiments using a self-balancing mechanism installed on an e-scooter., Comment: 7 pages, 4 figures, 1 table, In ACC2024

It is thought that nature already exploits quantum mechanical properties to increase the efficiency of solar energy harvesting devices. So, the operation of these devices can be enhanced by clever design of a nanoscopic, quantum mechanical system where the quantum coherence plays a crucial role in this process. In this investigation, we develop a donor-acceptor two-level trap dipole model converging the key role of quantum coherence and aggregation effects along with different initial states. Our analysis reveals that quenching unwanted emissions is achievable by preparing the system in specific initial state under the effect of optimal spatial aggregation. Interestingly it is observed that characterizing aggregation-induced properties and quantum effects of bandgap engineering can increase the power enhancement up to 35.87% compared with classical counterparts. This encouraging trend suggests a promising novel design aspect of nature-mimicking photovoltaic devices., Comment: 18 pages, 5 figures

Accurate classification of mode choice datasets is crucial for transportation planning and decision-making processes. However, conventional classification models often struggle to adequately capture the nuanced patterns of minority classes within these datasets, leading to sub-optimal accuracy. In response to this challenge, we present Ensemble Synthesizer (ENSY) which leverages probability distribution for data augmentation, a novel data model tailored specifically for enhancing classification accuracy in mode choice datasets. In our study, ENSY demonstrates remarkable efficacy by nearly quadrupling the F1 score of minority classes and improving overall classification accuracy by nearly 3%. To assess its performance comprehensively, we compare ENSY against various augmentation techniques including Random Oversampling, SMOTE-NC, and CTGAN. Through experimentation, ENSY consistently outperforms these methods across various scenarios, underscoring its robustness and effectiveness

We show that quantum circuit complexity for the unitary time evolution operator of any time-independent Hamiltonian is bounded by linear growth at early times, independent of any choices of the fundamental gates or cost metric. Deviations from linear early-time growth arise from the commutation algebra of the gates and are manifestly negative for any circuit, decreasing the linear growth rate and leading to a bound on the growth rate of complexity of a circuit at early times. We illustrate this general result by applying it to qubit and harmonic oscillator systems, including the coupled and anharmonic oscillator. By discretizing free and interacting scalar field theories on a lattice, we are also able to extract the early-time behavior and dependence on the lattice spacing of complexity of these field theories in the continuum limit, demonstrating how this approach applies to systems that have been previously difficult to study using existing techniques for quantum circuit complexity., Comment: 32 pages, Version published in JHEP

We investigate the application of active inference in developing energy-efficient control agents for manufacturing systems. Active inference, rooted in neuroscience, provides a unified probabilistic framework integrating perception, learning, and action, with inherent uncertainty quantification elements. Our study explores deep active inference, an emerging field that combines deep learning with the active inference decision-making framework. Leveraging a deep active inference agent, we focus on controlling parallel and identical machine workstations to enhance energy efficiency. We address challenges posed by the problem's stochastic nature and delayed policy response by introducing tailored enhancements to existing agent architectures. Specifically, we introduce multi-step transition and hybrid horizon methods to mitigate the need for complex planning. Our experimental results demonstrate the effectiveness of these enhancements and highlight the potential of the active inference-based approach.

Recent sequence modeling approaches using selective state space sequence models, referred to as Mamba models, have seen a surge of interest. These models allow efficient processing of long sequences in linear time and are rapidly being adopted in a wide range of applications such as language modeling, demonstrating promising performance. To foster their reliable use in real-world scenarios, it is crucial to augment their transparency. Our work bridges this critical gap by bringing explainability, particularly Layer-wise Relevance Propagation (LRP), to the Mamba architecture. Guided by the axiom of relevance conservation, we identify specific components in the Mamba architecture, which cause unfaithful explanations. To remedy this issue, we propose MambaLRP, a novel algorithm within the LRP framework, which ensures a more stable and reliable relevance propagation through these components. Our proposed method is theoretically sound and excels in achieving state-of-the-art explanation performance across a diverse range of models and datasets. Moreover, MambaLRP facilitates a deeper inspection of Mamba architectures, uncovering various biases and evaluating their significance. It also enables the analysis of previous speculations regarding the long-range capabilities of Mamba models.

In order to overcome the challenges caused by flash memories and also to protect against errors related to reading information stored in DNA molecules in the shotgun sequencing method, the rank modulation is proposed. In the rank modulation framework, codewords are permutations. In this paper, we study the largest size $P(n, d)$ of permutation codes of length $n$, i.e., subsets of the set $S_n$ of all permutations on $\{1,\ldots, n\}$ with the minimum distance at least $d\in\{1,\ldots ,\binom{n}{2}\}$ under the Kendall $\tau$-metric. By presenting an algorithm and some theorems, we managed to improve the known lower and upper bounds for $P(n,d)$. In particular, we show that $P(n,d)=4$ for all $n\geq 6$ and $\frac{3}{5}\binom{n}{2}< d \leq \frac{2}{3} \binom{n}{2}$. Additionally, we prove that for any prime number $n$ and integer $r\leq \frac{n}{6}$, $ P(n,3)\leq (n-1)!-\dfrac{n-6r}{\sqrt{n^2-8rn+20r^2}}\sqrt{\dfrac{(n-1)!}{n(n-r)!}}. $ This result greatly improves the upper bound of $P(n,3)$ for all primes $n\geq 37$., Comment: 15 pages

We study the \k{appa}-Poincare and the Magueijo-Smolin (MS) DSR in the context of the relative locality theory. This theory assigns connection, torsion and curvature to momentum space of every modified theory beyond special relativity. We obtain these quantities for the \k{appa}-Poincare and the MS DSR in all order of the Planck length, at the every point of the momentum space. The connection for the \k{appa}-Poincare theory and the MS DSR can be non-zero. The torsion for the \k{appa}-Poincare theory can also be non-zero, but it is zero for the MS DSR. The curvature for the \k{appa}-Poincare theory and the MS DSR are zero. We will find that the non-zero torsion and curvature of the momentum space implies a non-commutative spactime which is tangent to this momentum space. Also, we show that the torsion for every Abelian DSR theory is zero at the origin of the momentum space. At the end, we will discus dual spacetime transformations for the \k{appa}-Poincare theory and MS-DSR., Comment: 17 pages. arXiv admin note: text overlap with arXiv:2404.08553

This research employs Gaussian Process Regression (GPR) with an ensemble kernel, integrating Exponential Squared, Revised Mat\'ern, and Rational Quadratic kernels to analyze pharmaceutical sales data. Bayesian optimization was used to identify optimal kernel weights: 0.76 for Exponential Squared, 0.21 for Revised Mat\'ern, and 0.13 for Rational Quadratic. The ensemble kernel demonstrated superior performance in predictive accuracy, achieving an \( R^2 \) score near 1.0, and significantly lower values in Mean Squared Error (MSE), Mean Absolute Error (MAE), and Root Mean Squared Error (RMSE). These findings highlight the efficacy of ensemble kernels in GPR for predictive analytics in complex pharmaceutical sales datasets., Comment: 6 pages, 5 figures

This paper presents a novel approach to improving autonomous vehicle control in environments lacking clear road markings by integrating a diffusion-based motion predictor within an Active Inference Framework (AIF). Using a simulated parking lot environment as a parallel to unmarked roads, we develop and test our model to predict and guide vehicle movements effectively. The diffusion-based motion predictor forecasts vehicle actions by leveraging probabilistic dynamics, while AIF aids in decision-making under uncertainty. Unlike traditional methods such as Model Predictive Control (MPC) and Reinforcement Learning (RL), our approach reduces computational demands and requires less extensive training, enhancing navigation safety and efficiency. Our results demonstrate the model's capability to navigate complex scenarios, marking significant progress in autonomous driving technology.