Search

Bengali is the seventh most spoken language on earth, yet considered a low-resource language in the field of natural language processing (NLP). Question answering over unstructured text is a challenging NLP task as it requires understanding both question and passage. Very few researchers attempted to perform question answering over Bengali (natively pronounced as Bangla) text. Typically, existing approaches construct the dataset by directly translating them from English to Bengali, which produces noisy and improper sentence structures. Furthermore, they lack topics and terminologies related to the Bengali language and people. This paper introduces BanglaQuAD, a Bengali question answering dataset, containing 30,808 question-answer pairs constructed from Bengali Wikipedia articles by native speakers. Additionally, we propose an annotation tool that facilitates question-answering dataset construction on a local machine. A qualitative analysis demonstrates the quality of our proposed dataset., Comment: Accepted into LREC-COLING 2024, Turin, Italy

The majority of medical images, especially those that resemble cells, have similar characteristics. These images, which occur in a variety of shapes, often show abnormalities in the organ or cell region. The convolution operation possesses a restricted capability to extract visual patterns across several spatial regions of an image. The involution process, which is the inverse operation of convolution, complements this inherent lack of spatial information extraction present in convolutions. In this study, we investigate how applying a single layer of involution prior to a convolutional neural network (CNN) architecture can significantly improve classification and segmentation performance, with a comparatively negligible amount of weight parameters. The study additionally shows how excessive use of involution layers might result in inaccurate predictions in a particular type of medical image. According to our findings from experiments, the strategy of adding only a single involution layer before a CNN-based model outperforms most of the previous works., Comment: 13 pages, 5 figures, 4 tables, preprint submitted to an Elsevier journal

Context: The advent of Large Language Model-driven tools like ChatGPT offers software engineers an interactive alternative to community question-answering (CQA) platforms like Stack Overflow. While Stack Overflow provides benefits from the accumulated crowd-sourced knowledge, it often suffers from unpleasant comments, reactions, and long waiting times. Objective: In this study, we assess the efficacy of ChatGPT in providing solutions to software engineering questions by analyzing its performance specifically against human solutions. Method: We empirically analyze 2564 Python and JavaScript questions from StackOverflow that were asked between January 2022 and December 2022. We parse the questions and answers from Stack Overflow, then collect the answers to the same questions from ChatGPT through API, and employ four textual and four cognitive metrics to compare the answers generated by ChatGPT with the accepted answers provided by human subject matter experts to find out the potential reasons for which future knowledge seekers may prefer ChatGPT over CQA platforms. We also measure the accuracy of the answers provided by ChatGPT. We also measure user interaction on StackOverflow over the past two years using three metrics to determine how ChatGPT affects it. Results: Our analysis indicates that ChatGPT's responses are 66% shorter and share 35% more words with the questions, showing a 25% increase in positive sentiment compared to human responses. ChatGPT's answers' accuracy rate is between 71 to 75%, with a variation in response characteristics between JavaScript and Python. Additionally, our findings suggest a recent 38% decrease in comment interactions on Stack Overflow, indicating a shift in community engagement patterns. A supplementary survey with 14 Python and JavaScript professionals validated these findings.

This paper introduces a Machine Learning-Driven website Platform and Browser Extension designed to quickly enhance online security by providing real-time risk scoring and fraud detection for website legitimacy verification and consumer protection. The platform works seamlessly in the background to analyze website behavior, network traffic, and user interactions, offering immediate feedback and alerts when potential threats are detected. By integrating this system into a user-friendly browser extension, the platform empowers individuals to navigate the web safely, reducing the risk of engaging with fraudulent websites. Its real-time functionality is crucial in e-commerce and everyday browsing, where quick, actionable insights can prevent financial losses, identity theft, and exposure to malicious sites. This paper explores how this solution offers a practical, fast-acting tool for enhancing online consumer protection, underscoring its potential to play a critical role in safeguarding users and maintaining trust in digital transactions. The platform's focus on speed and efficiency makes it an essential asset for preventing fraud in today's increasingly digital world., Comment: Journal of Multidisciplinary Engineering Science and Technology (JMEST) 2024

Quasi-phase matching (QPM) is a technique extensively utilized in nonlinear optics for enhancing the efficiency and stability of frequency conversion processes. However, the conventional QPM relies on periodically poled ferroelectric crystals, which are limited in availability. The 3R phase of molybdenum disulfide (3R-MoS2), a transition metal dichalcogenide (TMDc) with the broken inversion symmetry, stands out as a promising candidate for QPM, enabling efficient nonlinear process. Here, we experimentally demonstrate the QPM at nanoscale, utilizing van der Waals stacking of 3R-MoS2 layers with specific orientation to realize second harmonic generation (SHG) enhancement beyond the non QPM limit. We have also demonstrated enhanced spontaneous parametric down-conversion (SPDC) via QPM of 3R-MoS2 homo-structure, enabling more efficient generation of entangled photon pairs. The tunable capacity of 3R-MoS2 van der Waals stacking provides a platform for tuning phase-matching condition. This technique opens interesting possibilities for potential applications in nonlinear process and quantum technology.

Bayesian Kernel Machine Regression (BKMR) has emerged as a powerful tool to detect negative health effects from exposure to complex multi-pollutant mixtures. However, its performance is degraded when data deviate from normality. In this comprehensive simulation analysis, we show that BKMR's power and test size vary under different distributions and covariance matrix structures. Our results demonstrate specifically that BKMR's robustness is influenced by the response's coefficient of variation (CV), resulting in reduced accuracy to detect true effects when data are skewed. Test sizes become uncontrolled (> 0.05) as CV values increase, leading to inflated false detection rates. However, we find that BKMR effectively utilizes off-diagonal covariance information corresponding to predictor interdependencies, increasing statistical power and accuracy. To achieve reliable and accurate results, we advocate for scrutiny of data skewness and covariance before applying BKMR, particularly when used to predict cognitive decline from blood/urine heavy metal concentrations in environmental health contexts., Comment: This article is submitted to the Journal of Statistical Computation and Simulation and currently under review

The rare three body decay of a Higgs boson to a lepton-anti lepton pair and a photon has begun to attract attention, after the first evidence for the $H\to Z\gamma$ at CMS and ATLAS, which is a sub process of $H \to \ell^+ \ell^- \gamma$ . To investigate some important features of this process, we suggest that the polarized forward-backward and the photon polarization asymmetries could be useful to probe its important properties, such as the behavior of Yukawa coupling, resonance, and non-resonance contributions. Our analysis introduces a comprehensive framework to evaluate the aforementioned polarization-dependent observables. By analyzing the polarization effects of the final-state photon and lepton separately on forward-backward asymmetries, we demonstrate that loop-induced contributions play a significant role to investigate these asymmetries. Unlike the unpolarized case, where the interference effects of resonance and non-resonance effects are minimal, we show that polarization dependent observables offer a powerful tool to analyze these features of this decay mode. Furthermore, these observables can provide a handy tool for probing possible signatures of physics beyond the SM.

Mixture experiments often involve process variables, such as different chemical reactors in a laboratory or varying mixing speeds in a production line. Organizing the runs in orthogonal blocks allows the mixture model to be fitted independently of the process effects, ensuring clearer insights into the role of each mixture component. Current literature on mixture designs in orthogonal blocks ignores the order of addition of mixture components in mixture blends. This paper considers the order of addition of components in mixture and mixture-amount experiments, using the variable total amount taken into orthogonal blocks. The response depends on both the mixture proportions or the amounts of the components and the order of their addition. Mixture designs in orthogonal blocks are constructed to enable the estimation of mixture or component-amount model parameters and the order-of-addition effects. The G-efficiency criterion is used to assess how well the design supports precise and unbiased estimation of the model parameters. The fraction of the Design Space plot is used to provide a visual assessment of the prediction capabilities of a design across the entire design space., Comment: 15, 1

As online fraud becomes more sophisticated and pervasive, traditional fraud detection methods are struggling to keep pace with the evolving tactics employed by fraudsters. This paper explores the transformative role of machine learning in addressing these challenges by offering more advanced, scalable, and adaptable solutions for fraud detection and prevention. By analyzing key models such as Random Forest, Neural Networks, and Gradient Boosting, this paper highlights the strengths of machine learning in processing vast datasets, identifying intricate fraud patterns, and providing real-time predictions that enable a proactive approach to fraud prevention. Unlike rule-based systems that react after fraud has occurred, machine learning models continuously learn from new data, adapting to emerging fraud schemes and reducing false positives, which ultimately minimizes financial losses. This research emphasizes the potential of machine learning to revolutionize fraud detection frameworks by making them more dynamic, efficient, and capable of handling the growing complexity of fraud across various industries. Future developments in machine learning, including deep learning and hybrid models, are expected to further enhance the predictive accuracy and applicability of these systems, ensuring that organizations remain resilient in the face of new and emerging fraud tactics., Comment: World Journal of Advanced Research and Reviews (2024)

Nematic quantum fluids appear in strongly interacting systems and break the rotational symmetry of the crystallographic lattice. In metals, this is connected to a well-known instability of the Fermi liquid-the Pomeranchuk instability. Using scanning tunneling microscopy, we identified this instability in a highly unusual setting: on the surface of an elemental topological metal, arsenic. By directly visualizing the Fermi surface of the surface state via scanning tunneling spectroscopy and photoemission spectroscopy, we find that the Fermi surface gets deformed and becomes elliptical at the energies where the nematic state is present. Known instances of nematic instability typically need van-Hove singularities or multi-orbital physics as drivers. In contrast, the surface states of arsenic are essentially indistinguishable from well-confined isotropic Rashba bands near the Fermi level, rendering our finding the first realization of Pomeranchuk instability of the topological surface state.

This letter introduces a novel analytical approach to calculating phase-space integrals, crucial for precision in particle physics. We develop a method to compute angular components using multifold Mellin-Barnes integrals, yielding results in terms of Goncharov polylogarithms for integrals involving three denominators. Our results include expressions for massless momenta up to $\cal{O}(\epsilon^2)$ and for one massive momentum up to $\cal{O}(\epsilon)$. Additionally, we derive recursion relations that reduce integrals with higher powers of denominators to simpler ones. We detail how to combine the angular part with the radial one which requires a careful handling of singularities., Comment: 6 pages

Zero Trust Architecture (ZTA) represents a transformative approach to modern cybersecurity, directly addressing the shortcomings of traditional perimeter-based security models. With the rise of cloud computing, remote work, and increasingly sophisticated cyber threats, perimeter defenses have proven ineffective at mitigating risks, particularly those involving insider threats and lateral movement within networks. ZTA shifts the security paradigm by assuming that no user, device, or system can be trusted by default, requiring continuous verification and the enforcement of least privilege access for all entities. This paper explores the key components of ZTA, such as identity and access management (IAM), micro-segmentation, continuous monitoring, and behavioral analytics, and evaluates their effectiveness in reducing vulnerabilities across diverse sectors, including finance, healthcare, and technology. Through case studies and industry reports, the advantages of ZTA in mitigating insider threats and minimizing attack surfaces are discussed. Additionally, the paper addresses the challenges faced during ZTA implementation, such as scalability, integration complexity, and costs, while providing best practices for overcoming these obstacles. Lastly, future research directions focusing on emerging technologies like AI, machine learning, blockchain, and their integration into ZTA are examined to enhance its capabilities further., Comment: 21 pages, 4 figures, focusing on Zero Trust Architecture (ZTA) implementation and its impact on mitigating insider threats and reducing vulnerabilities. Case studies from sectors like finance and healthcare are included

The X-ray column density (NHX) of gamma-ray bursts (GRBs) can probe the local environment of their progenitors over a wide redshift range. Previous work has suggested an increasing trend as a function of redshift. The relevance of the current analysis relies on investigating the selection bias method, such as the effect of the X-ray spectrum in high-redshift GRBs, which complicates the measurement of small NHX, have yet to be fully evaluated or discussed elsewhere. In this work, we evaluated these effects through simulations to define appropriate observational limits in the NHX versus redshift plane. We then applied a one-sided nonparametric method developed by Efron and Petrosian. Within the framework of this method, we investigated the redshift dependence of NHX and the local distribution function. Our results show that the evolution of NHX with redshift firmly exists with a significance of more than four sigma and follows a power law of $(1+z)^{1.39 (+0.22, -0.27)}$. Based on these analyses and previous studies, the GRB progenitor mass varies but is more massive in the high redshift environment and has a higher gas column density. This suggests that part of the luminosity evolution of GRBs, which has been widely reported, may be due to the evolution of the progenitor's mass. Using the same method, we demonstrate that optically dark GRBs show a consistent evolution as $(1+z)^{1.15(+0.67, -0.83)}$. By applying the Kolmogorov-Smirnov (KS) test, it is shown that optically dark GRBs have statistically identical flux and photon index distributions compared to normal GRBs, but the NHX is systematically larger. This result suggests that the darkness of some GRB populations is not due to an intrinsic mechanism, but that a higher density surrounds them.

Growing exploitation of Machine Learning (ML) in safety-critical applications necessitates rigorous safety analysis. Hardware reliability assessment is a major concern with respect to measuring the level of safety. Quantifying the reliability of emerging ML models, including Deep Neural Networks (DNNs), is highly complex due to their enormous size in terms of the number of parameters and computations. Conventionally, Fault Injection (FI) is applied to perform a reliability measurement. However, performing FI on modern-day DNNs is prohibitively time-consuming if an acceptable confidence level is to be achieved. In order to speed up FI for large DNNs, statistical FI has been proposed. However, the run-time for the large DNN models is still considerably long. In this work, we introduce DeepVigor+, a scalable, fast and accurate semi-analytical method as an efficient alternative for reliability measurement in DNNs. DeepVigor+ implements a fault propagation analysis model and attempts to acquire Vulnerability Factors (VFs) as reliability metrics in an optimal way. The results indicate that DeepVigor+ obtains VFs for DNN models with an error less than 1\% and 14.9 up to 26.9 times fewer simulations than the best-known state-of-the-art statistical FI enabling an accurate reliability analysis for emerging DNNs within a few minutes., Comment: 14 pages, 9 figures, 8 tables, 16 equations. The source code is accessible via: https://github.com/mhahmadilivany/DeepVigor

Due to the involvement of multiple intermediaries without trusted parties, lack of proper regulations, and a complicated supply chain, ad impression discrepancy affects online advertising. This issue causes up to $82 billion annual revenue loss for honest parties. The loss can be significantly reduced with a precise and trusted decentralized mechanism. This paper presents AdChain, a decentralized, distributed, and verifiable solution that detects and minimizes online advertisement impression discrepancies. AdChain establishes trust by employing multiple independent agents to receive and record log-level data, along with a consensus protocol to validate each ad data. AdChain is scalable, efficient, and compatible with the current infrastructure. Our experimental evaluation, using over half a million ad data points, identifies system parameters that achieve 98% accuracy, reducing the ad discrepancy rate from 20% to 2%. Our cost analysis shows that active nodes on AdChain can generate profits comparable to miners on major blockchain networks like Bitcoin., Comment: Being published at MARBLE 2024 (The 5th International Conference on Mathematical Research for Blockchain Economy)

Efficient vectorization of hand-drawn cadastral maps, such as Mouza maps in Bangladesh, poses a significant challenge due to their complex structures. Current manual digitization methods are time-consuming and labor-intensive. Our study proposes a semi-automated approach to streamline the digitization process, saving both time and human resources. Our methodology focuses on separating the plot boundaries and plot identifiers and applying our digitization methodology to convert both of them into vectorized format. To accomplish full vectorization, Convolutional Neural Network (CNN) models are utilized for pre-processing and plot number detection along with our smoothing algorithms based on the diversity of vector maps. The CNN models are trained with our own labeled dataset, generated from the maps, and smoothing algorithms are introduced from the various observations of the map's vector formats. Further human intervention remains essential for precision. We have evaluated our methods on several maps and provided both quantitative and qualitative results with user study. The result demonstrates that our methodology outperforms the existing map digitization processes significantly., Comment: 13 pages including reference, 14 figures, 4 tables

This paper presents an experience report on the development of Retrieval Augmented Generation (RAG) systems using PDF documents as the primary data source. The RAG architecture combines generative capabilities of Large Language Models (LLMs) with the precision of information retrieval. This approach has the potential to redefine how we interact with and augment both structured and unstructured knowledge in generative models to enhance transparency, accuracy, and contextuality of responses. The paper details the end-to-end pipeline, from data collection, preprocessing, to retrieval indexing and response generation, highlighting technical challenges and practical solutions. We aim to offer insights to researchers and practitioners developing similar systems using two distinct approaches: OpenAI's Assistant API with GPT Series and Llama's open-source models. The practical implications of this research lie in enhancing the reliability of generative AI systems in various sectors where domain-specific knowledge and real-time information retrieval is important. The Python code used in this work is also available at: https://github.com/GPT-Laboratory/RAG-LLM-Development-Guidebook-from-PDFs., Comment: 36 pages, 8 figures, 2 tables, and python code snippets

Reliable facial expression learning (FEL) involves the effective learning of distinctive facial expression characteristics for more reliable, unbiased and accurate predictions in real-life settings. However, current systems struggle with FEL tasks because of the variance in people's facial expressions due to their unique facial structures, movements, tones, and demographics. Biased and imbalanced datasets compound this challenge, leading to wrong and biased prediction labels. To tackle these, we introduce GReFEL, leveraging Vision Transformers and a facial geometry-aware anchor-based reliability balancing module to combat imbalanced data distributions, bias, and uncertainty in facial expression learning. Integrating local and global data with anchors that learn different facial data points and structural features, our approach adjusts biased and mislabeled emotions caused by intra-class disparity, inter-class similarity, and scale sensitivity, resulting in comprehensive, accurate, and reliable facial expression predictions. Our model outperforms current state-of-the-art methodologies, as demonstrated by extensive experiments on various datasets., Comment: ACCV 2024. Extended version of ARBEx (arXiv:2305.01486)

We introduce a novel approach to derive compressibility corrections for Reynolds-averaged Navier-Stokes (RANS) models. Using this approach, we derive variable-property corrections for wall-bounded flows that are consistent with the semi-local velocity transformation in the inner layer and the Van Driest velocity transformation in the outer layer. We also propose modifying the eddy viscosity to account for changes in the near-wall damping of turbulent shear stress caused by intrinsic compressibility effects. Furthermore, we address some important aspects related to the modeling of the energy equation, primarily focusing on the turbulent Prandtl number and the modeling of the source terms. Compared to the existing state-of-the-art compressibility corrections, the present corrections, combined with accurate modeling of the energy equation, lead to a significant improvement in the results for a wide range of turbulent boundary layers and channel flows. The proposed corrections have the potential to enhance modeling across a range of applications, involving low-speed flows with strong heat transfer, fluids at supercritical pressures, and supersonic and hypersonic flows., Comment: 20 pages, 4 figures

Magnetic reconnection often initiates abruptly and then rapidly progresses to a nonlinear quasi-steady state. While satellites frequently detect reconnection events, ascertaining whether the system has achieved steady-state or is still evolving in time remains challenging. Here, we propose that the relatively rapid opening of reconnection separatrices within the electron diffusion region (EDR) serves as an indicator of the growth phase of reconnection. The opening of the separatrices is produced by electron flows diverging away from the neutral line downstream of the X-line and flowing around a dipolarization front. This flow pattern leads to characteristic spatial structures in pressure-strain interaction that could be a useful indicator for the growth phase of a reconnection event. We employ two-dimensional particle-in-cell numerical simulations of anti-parallel magnetic reconnection to validate this prediction. We find that the signature discussed here, alongside traditional reconnection indicators, can serve as a marker of the growth phase. This signature is potentially accessible using multi-spacecraft single-point measurements, such as with NASA's Magnetospheric Multiscale (MMS) satellites in Earth's magnetotail. Applications to other settings where reconnection occurs are also discussed., Comment: Submitted to JGR: Space Physics

In this article, we develop a predator-prey model with Allee effect and prey group defense. The model has three equilibrium points i.e. the trivial point, the predator extinction point, and the coexistence point. All equilibrium points are locally asymptotically stable under certain conditions. The Allee effect in this model influences the stability of the equilibrium point. If the Allee effect is weak, then the trivial equilibrium point is unstable. Meanwhile, if the Allee effect is strong, then the trivial equilibrium point is locally asymptotically stable. Those mean that a strong Allee effect can lead to the extinction of both populations. Moreover, under weak Allee condition, forward bifurcation and Hopf bifurcation occur at the predator extinction equilibrium point. Meanwhile, a strong Allee effect may induce bistability at both the trivial equilibrium point and the predator extinction equilibrium point. Those mean that prey can survive without the presence of predators, but a strong Allee effect can lead to prey extinction if the population size is very small. To support our analytical findings, we perform some numerical simulations in the final section., Comment: 12 pages, 6 figures, The International Symposium on Biomathematics (Symomath), 10-12 July 2024, Depok, Indonesia

Large Language Models (LLMs) are trained on massive amounts of data, enabling their application across diverse domains and tasks. Despite their remarkable performance, most LLMs are developed and evaluated primarily in English. Recently, a few multi-lingual LLMs have emerged, but their performance in low-resource languages, especially the most spoken languages in South Asia, is less explored. To address this gap, in this study, we evaluate LLMs such as GPT-4, Llama 2, and Gemini to analyze their effectiveness in English compared to other low-resource languages from South Asia (e.g., Bangla, Hindi, and Urdu). Specifically, we utilized zero-shot prompting and five different prompt settings to extensively investigate the effectiveness of the LLMs in cross-lingual translated prompts. The findings of the study suggest that GPT-4 outperformed Llama 2 and Gemini in all five prompt settings and across all languages. Moreover, all three LLMs performed better for English language prompts than other low-resource language prompts. This study extensively investigates LLMs in low-resource language contexts to highlight the improvements required in LLMs and language-specific resources to develop more generally purposed NLP applications.

Healthcare industries face challenges when experiencing rare diseases due to limited samples. Artificial Intelligence (AI) communities overcome this situation to create synthetic data which is an ethical and privacy issue in the medical domain. This research introduces the CAT-U-Net framework as a new approach to overcome these limitations, which enhances feature extraction from medical images without the need for large datasets. The proposed framework adds an extra concatenation layer with downsampling parts, thereby improving its ability to learn from limited data while maintaining patient privacy. To validate, the proposed framework's robustness, different medical conditioning datasets were utilized including COVID-19, brain tumors, and wrist fractures. The framework achieved nearly 98% reconstruction accuracy, with a Dice coefficient close to 0.946. The proposed CAT-U-Net has the potential to make a big difference in medical image diagnostics in settings with limited data., Comment: 7 pages, 7 figures

The objective of this work is to develop an AI foundation model for physical signals that can generalize across diverse phenomena, domains, applications, and sensing apparatuses. We propose a phenomenological approach and framework for creating and validating such AI foundation models. Based on this framework, we developed and trained a model on 0.59 billion samples of cross-modal sensor measurements, ranging from electrical current to fluid flow to optical sensors. Notably, no prior knowledge of physical laws or inductive biases were introduced into the model. Through several real-world experiments, we demonstrate that a single foundation model could effectively encode and predict physical behaviors, such as mechanical motion and thermodynamics, including phenomena not seen in training. The model also scales across physical processes of varying complexity, from tracking the trajectory of a simple spring-mass system to forecasting large electrical grid dynamics. This work highlights the potential of building a unified AI foundation model for diverse physical world processes.

Healthcare technology has advanced with the development of an IoT-based real-time monitoring system for post-operative heart disease patients. This system integrates advanced sensor technologies with cloud-connected platforms to continuously track vital signs, enabling more effective post-operative care. The system employs the HW-827 Heart Rate Sensor and DS18B20 Temperature Sensor, integrated with an ESP32 for wireless connectivity, to collect real-time data. Data was collected from 20 participants in each of the following categories: healthy individuals, pre-operative heart disease patients, and post-operative heart disease patients. The results revealed distinct physiological variations across the groups. Healthy individuals maintained stable temperatures (mean 36.3{\deg}C), while post-operative patients exhibited slightly elevated temperatures (mean 36.6{\deg}C). Heart rate analysis indicated higher rates in pre-operative (mean 87.8 bpm) and post-operative patients (mean 82.0 bpm) compared to healthy individuals (mean 72.4 bpm). ECG analysis showed elevated readings in pre-operative patients (mean 0.16 mV) compared to healthy individuals (mean 0.10 mV) and post-operative patients (mean 0.12 mV). Statistical analyses, including ANOVA tests, confirmed significant differences among the groups in terms of temperature (F(2, 12) = 4.57, p < 0.05), heart rate (F(2, 12) = 5.91, p < 0.01), and ECG readings (F(2, 12) = 3.24, p < 0.05). This study demonstrates the potential of IoT technologies in enhancing post-operative care through continuous monitoring and data-driven insights. It emphasizes the role of real-time patient data in improving personalized healthcare management., Comment: 17 Pages, 7 figures, 7 Tables, Journal

The geopolitical division between the indigenous Chakma population and mainstream Bangladesh creates a significant cultural and linguistic gap, as the Chakma community, mostly residing in the hill tracts of Bangladesh, maintains distinct cultural traditions and language. Developing a Machine Translation (MT) model or Chakma to Bangla could play a crucial role in alleviating this cultural-linguistic divide. Thus, we have worked on MT between CCP-BN(Chakma-Bangla) by introducing a novel dataset of 15,021 parallel samples and 42,783 monolingual samples of the Chakma Language. Moreover, we introduce a small set for Benchmarking containing 600 parallel samples between Chakma, Bangla, and English. We ran traditional and state-of-the-art models in NLP on the training set, where fine-tuning BanglaT5 with back-translation using transliteration of Chakma achieved the highest BLEU score of 17.8 and 4.41 in CCP-BN and BN-CCP respectively on the Benchmark Dataset. As far as we know, this is the first-ever work on MT for the Chakma Language. Hopefully, this research will help to bridge the gap in linguistic resources and contribute to preserving endangered languages. Our dataset link and codes will be published soon., Comment: to be submitted in ACL findings 2025

Media companies witnessed a significant transformation with the rise of the internet, bigdata, machine learning (ML) and AI. Recent emergence of large language models (LLM) have added another aspect to this transformation. Researchers believe that with the help of these technologies, investigative digital journalism will enter a new era. Using a smart set of data gathering and analysis tools, journalists will be able to create data driven contents and insights in unprecedented ways. In this paper, we introduce a versatile and autonomous investigative journalism tool, called {\em SociaLens}, for identifying and extracting query specific data from online sources, responding to probing queries and drawing conclusions entailed by large volumes of data using ML analytics fully autonomously. We envision its use in investigative journalism, law enforcement and social policy planning. The proposed system capitalizes on the integration of ML technology with LLMs and advanced bigdata search techniques. We illustrate the functionality of SociaLens using a focused case study on rape incidents in a developing country and demonstrate that journalists can gain nuanced insights without requiring coding expertise they might lack. SociaLens is designed as a ChatBot that is capable of contextual conversation, find and collect data relevant to queries, initiate ML tasks to respond to queries, generate textual and visual reports, all fully autonomously within the ChatBot environment.

To adapt to real-world dynamics, intelligent systems need to assimilate new knowledge without catastrophic forgetting, where learning new tasks leads to a degradation in performance on old tasks. To address this, continual learning concept is proposed for enabling autonomous systems to acquire new knowledge and dynamically adapt to changing environments. Specifically, energy-efficient continual learning is needed to ensure the functionality of autonomous systems under tight compute and memory resource budgets (i.e., so-called autonomous embedded systems). Neuromorphic computing, with brain-inspired Spiking Neural Networks (SNNs), offers inherent advantages for enabling low-power/energy continual learning in autonomous embedded systems. In this paper, we comprehensively discuss the foundations and methods for enabling continual learning in neural networks, then analyze the state-of-the-art works considering SNNs. Afterward, comparative analyses of existing methods are conducted while considering crucial design factors, such as network complexity, memory, latency, and power/energy efficiency. We also explore the practical applications that can benefit from SNN-based continual learning and open challenges in real-world scenarios. In this manner, our survey provides valuable insights into the recent advancements of SNN-based continual learning for real-world application use-cases., Comment: This work has been submitted to the IEEE Access for possible publication

The FCC's National Broadband Map aspires to provide an unprecedented view into broadband availability in the US. However, this map, which also determines eligibility for public grant funding, relies on self-reported data from service providers that in turn have incentives to strategically misrepresent their coverage. In this paper, we develop an approach for automatically identifying these low-quality service claims in the National Broadband Map. To do this, we develop a novel dataset of broadband availability consisting of 750k observations from more than 900 US ISPs, derived from a combination of regulatory data and crowdsourced speed tests. Using this dataset, we develop a model to classify the accuracy of service provider regulatory filings and achieve AUCs over 0.98 for unseen examples. Our approach provides an effective technique to enable policymakers, civil society, and the public to identify portions of the National Broadband Map that are likely to have integrity challenges., Comment: 17 pages

Fine-tuning has become a popular approach to adapting large foundational models to specific tasks. As the size of models and datasets grows, parameter-efficient fine-tuning techniques are increasingly important. One of the most widely used methods is Low-Rank Adaptation (LoRA), with adaptation update expressed as the product of two low-rank matrices. While LoRA was shown to possess strong performance in fine-tuning, it often under-performs when compared to full-parameter fine-tuning (FPFT). Although many variants of LoRA have been extensively studied empirically, their theoretical optimization analysis is heavily under-explored. The starting point of our work is a demonstration that LoRA and its two extensions, Asymmetric LoRA and Chain of LoRA, indeed encounter convergence issues. To address these issues, we propose Randomized Asymmetric Chain of LoRA (RAC-LoRA) -- a general optimization framework that rigorously analyzes the convergence rates of LoRA-based methods. Our approach inherits the empirical benefits of LoRA-style heuristics, but introduces several small but important algorithmic modifications which turn it into a provably convergent method. Our framework serves as a bridge between FPFT and low-rank adaptation. We provide provable guarantees of convergence to the same solution as FPFT, along with the rate of convergence. Additionally, we present a convergence analysis for smooth, non-convex loss functions, covering gradient descent, stochastic gradient descent, and federated learning settings. Our theoretical findings are supported by experimental results., Comment: 36 pages, 4 figures, 2 algorithms

Generative modeling of discrete data underlies important applications spanning text-based agents like ChatGPT to the design of the very building blocks of life in protein sequences. However, application domains need to exert control over the generated data by steering the generative process - typically via RLHF - to satisfy a specified property, reward, or affinity metric. In this paper, we study the problem of steering Masked Diffusion Models (MDMs), a recent class of discrete diffusion models that offer a compelling alternative to traditional autoregressive models. We introduce Discrete Denoising Posterior Prediction (DDPP), a novel framework that casts the task of steering pre-trained MDMs as a problem of probabilistic inference by learning to sample from a target Bayesian posterior. Our DDPP framework leads to a family of three novel objectives that are all simulation-free, and thus scalable while applying to general non-differentiable reward functions. Empirically, we instantiate DDPP by steering MDMs to perform class-conditional pixel-level image modeling, RLHF-based alignment of MDMs using text-based rewards, and finetuning protein language models to generate more diverse secondary structures and shorter proteins. We substantiate our designs via wet-lab validation, where we observe transient expression of reward-optimized protein sequences.

Applying deep learning (DL) for annotating surgical instruments in robot-assisted minimally invasive surgeries (MIS) represents a significant advancement in surgical technology. This systematic review examines 48 studies that and advanced DL methods and architectures. These sophisticated DL models have shown notable improvements in the precision and efficiency of detecting and segmenting surgical tools. The enhanced capabilities of these models support various clinical applications, including real-time intraoperative guidance, comprehensive postoperative evaluations, and objective assessments of surgical skills. By accurately identifying and segmenting surgical instruments in video data, DL models provide detailed feedback to surgeons, thereby improving surgical outcomes and reducing complication risks. Furthermore, the application of DL in surgical education is transformative. The review underscores the significant impact of DL on improving the accuracy of skill assessments and the overall quality of surgical training programs. However, implementing DL in surgical tool detection and segmentation faces challenges, such as the need for large, accurately annotated datasets to train these models effectively. The manual annotation process is labor-intensive and time-consuming, posing a significant bottleneck. Future research should focus on automating the detection and segmentation process and enhancing the robustness of DL models against environmental variations. Expanding the application of DL models across various surgical specialties will be essential to fully realize this technology's potential. Integrating DL with other emerging technologies, such as augmented reality (AR), also offers promising opportunities to further enhance the precision and efficacy of surgical procedures., Comment: 57 pages, 9 figures, Accepted for publication in Artificial Intelligence Reviews journal

This paper, for the first time, presents a low-complexity peak-power-assisted data-aided channel estimation (DACE) scheme for both single-input single-output (SISO) and multiple-input multiple-output orthogonal frequency division multiplexing (MIMO-OFDM) wireless systems. In OFDM, high peak-power levels occur when the subcarriers align in phase and constructively interfere with each other. The research proposes a peak-power-assisted channel estimation scheme that accurately selects peak-power carriers at the transmitter of an OFDM system and uses them as reliable carriers for the DACE scheme. By incorporating these reliable carriers with known pilot symbols as additional pilot signals, channel estimation accuracy significantly improves in MIMO-OFDM systems. This eliminates the need to determine reliable data symbols at the receiver, thereby significantly reducing the computational complexity of the system. However, high peak-powers are considered a major drawback in OFDM. In this work, we incorporate a companding technique to mitigate this issue and provide sufficient margin for the DACE scheme. The performance of the proposed DACE scheme is evaluated using both least square (LS) and linear minimum mean square error (LMMSE) channel estimators. In this regard, the proposed technique not only improves channel estimation accuracy but also enhances the spectral efficiency of the wireless system. It outperforms traditional channel estimators in terms of system mean square error (MSE) and bit-error-rate (BER) performance. It also reduces the pilot overhead by 50$\%$ compared to traditional channel estimators and provides bandwidth optimization for MIMO-OFDM systems. This makes it a promising solution for improving the performance and efficiency of wireless communication systems., Comment: This paper is submitted to arXiv as a preprint because it has not yet been published in a journal

We study extreme events in a finite-size 2D Abelian sandpile model, specifically focusing on avalanche area and size. Employing the approach of Block Maxima, the study numerically reveals that the rescaled distributions for the largest avalanche size and area converge into the Gumbel and Weibull family of Generalized Extreme Value (GEV) distributions respectively. Numerically, we propose scaling functions for extreme avalanche activities that connect the activities on different length scales. With the help of data collapse, we estimate the precise values of these scaling exponents. The scaling function provides an understanding of the intricate dynamics within the sandpile model, shedding light on the relationship between system size and extreme event characteristics. The findings presented in this paper give valuable insights into the extreme behaviour of the Abelian sandpile model and offer a framework to understand the statistical properties of extreme events in complex systems., Comment: 7 pages, 4 figures

We propose RelitLRM, a Large Reconstruction Model (LRM) for generating high-quality Gaussian splatting representations of 3D objects under novel illuminations from sparse (4-8) posed images captured under unknown static lighting. Unlike prior inverse rendering methods requiring dense captures and slow optimization, often causing artifacts like incorrect highlights or shadow baking, RelitLRM adopts a feed-forward transformer-based model with a novel combination of a geometry reconstructor and a relightable appearance generator based on diffusion. The model is trained end-to-end on synthetic multi-view renderings of objects under varying known illuminations. This architecture design enables to effectively decompose geometry and appearance, resolve the ambiguity between material and lighting, and capture the multi-modal distribution of shadows and specularity in the relit appearance. We show our sparse-view feed-forward RelitLRM offers competitive relighting results to state-of-the-art dense-view optimization-based baselines while being significantly faster. Our project page is available at: https://relit-lrm.github.io/., Comment: webpage: https://relit-lrm.github.io/

In a mixture experiment, we study the behavior and properties of $m$ mixture components, where the primary focus is on the proportions of the components that make up the mixture rather than the total amount. Mixture-amount experiments are specialized types of mixture experiments where both the proportions of the components in the mixture and the total amount of the mixture are of interest. Such experiments consider the total amount of the mixture as a variable. In this paper, we consider an Order-of-Addition (OofA) mixture-amount experiment in which the response depends on both the mixture amounts of components and their order of addition. Full Mixture OofA designs are constructed to maintain orthogonality between the mixture-amount model terms and the effects of the order of addition. These designs enable the estimation of mixture-component model parameters and the order-of-addition effects. The G-efficiency criterion assesses how well the design supports precise and unbiased estimation of the model parameters. The Fraction of Design Space (FDS) plot is used to provide a visual assessment of the prediction capabilities of a design across the entire design space., Comment: 12 pages figures 2 tables 5

Peer review is the quality assessment of a manuscript by one or more peer experts. Papers are submitted by the authors to scientific venues, and these papers must be reviewed by peers or other authors. The meta-reviewers then gather the peer reviews, assess them, and create a meta-review and decision for each manuscript. As the number of papers submitted to these venues has grown in recent years, it becomes increasingly challenging for meta-reviewers to collect these peer evaluations on time while still maintaining the quality that is the primary goal of meta-review creation. In this paper, we address two peer review aggregation challenges a meta-reviewer faces: paper acceptance decision-making and meta-review generation. Firstly, we propose to automate the process of acceptance decision prediction by applying traditional machine learning algorithms. We use pre-trained word embedding techniques BERT to process the reviews written in natural language text. For the meta-review generation, we propose a transfer learning model based on the T5 model. Experimental results show that BERT is more effective than the other word embedding techniques, and the recommendation score is an important feature for the acceptance decision prediction. In addition, we figure out that fine-tuned T5 outperforms other inference models. Our proposed system takes peer reviews and other relevant features as input to produce a meta-review and make a judgment on whether or not the paper should be accepted. In addition, experimental results show that the acceptance decision prediction system of our task outperforms the existing models, and the meta-review generation task shows significantly improved scores compared to the existing models. For the statistical test, we utilize the Wilcoxon signed-rank test to assess whether there is a statistically significant improvement between paired observations.

Despite the strong prediction power of deep learning models, their interpretability remains an important concern. Disentanglement models increase interpretability by decomposing the latent space into interpretable subspaces. In this paper, we propose the first disentanglement method for pathology images. We focus on the task of detecting tumor-infiltrating lymphocytes (TIL). We propose different ideas including cascading disentanglement, novel architecture, and reconstruction branches. We achieve superior performance on complex pathology images, thus improving the interpretability and even generalization power of TIL detection deep learning models. Our codes are available at https://github.com/Shauqi/SS-cVAE.

Gradient descent computed by backpropagation (BP) is a widely used learning method for training artificial neural networks but has several limitations: it is computationally demanding, requires frequent manual tuning of the network architecture, and is prone to catastrophic forgetting when learning incrementally. To address these issues, we introduce a brain-mimetic developmental spiking neural network (BDNN) that mimics the postnatal development of neural circuits. We validate its performance through a neuromorphic tactile system capable of learning to recognize objects through grasping. Unlike traditional BP-based methods, BDNN exhibits strong knowledge transfer, supporting efficient incremental learning of new tactile information. It requires no hyperparameter tuning and dynamically adapts to incoming data. Moreover, compared to the BP-based counterpart, it achieves classification accuracy on par with BP while learning over ten times faster in ideal conditions and up to two or three orders of magnitude faster in practical settings. These features make BDNN well-suited for fast data processing on edge devices., Comment: 24 pages, 8 figures, 2 tables

Recommender systems are designed to suggest items based on user preferences, helping users navigate the vast amount of information available on the internet. Given the overwhelming content, outlier detection has emerged as a key research area in recommender systems. It involves identifying unusual or suspicious patterns in user behavior. However, existing studies in this field face several challenges, including the limited universality of algorithms, difficulties in selecting users, and a lack of optimization. In this paper, we propose an approach that addresses these challenges by employing various clustering algorithms. Specifically, we utilize a user-user matrix-based clustering technique to detect outliers. By constructing a user-user matrix, we can identify suspicious users in the system. Both local and global outliers are detected to ensure comprehensive analysis. Our experimental results demonstrate that this approach significantly improves the accuracy of outlier detection in recommender systems., Comment: 6 pages, 5 figures

We study the evolution equation for magnetic energy density for a non-relativistic magnetized plasma in the (Lagrangian) reference frame comoving with the electron bulk velocity. Analyzing the terms that arise due to the ideal electric field, namely perpendicular electron compression and magnetic field line bending, we recast them to reveal a quantity with a functional form analogous to the often-studied pressure-strain interaction term that describes one piece of internal energy density evolution of the species in a plasma, except with the species pressure tensor replaced by the magnetic stress tensor. We dub it the "magnetic stress-strain interaction." We discuss decompositions of the magnetic stress-strain interaction analogous to those used for pressure-strain interaction. These analogies facilitate the interpretation of the evolution of the various forms of energy in magnetized plasmas, and should be useful for a wide array of applications including magnetic reconnection, turbulence, collisionless shocks, and wave-particle interactions. We display and analyze all the terms that can change magnetic energy density in the Lagrangian reference frame using a particle-in-cell simulation of magnetic reconnection., Comment: Submitted to Physics of Plasmas

Fire hazards are extremely dangerous, particularly in sectors such as the transportation industry, where political unrest increases the likelihood of their occurrence. By employing IP cameras to facilitate the setup of fire detection systems on transport vehicles, losses from fire events may be prevented proactively. However, the development of lightweight fire detection models is required due to the computational constraints of the embedded systems within these cameras. We introduce FireLite, a low-parameter convolutional neural network (CNN) designed for quick fire detection in contexts with limited resources, in response to this difficulty. With an accuracy of 98.77\%, our model -- which has just 34,978 trainable parameters achieves remarkable performance numbers. It also shows a validation loss of 8.74 and peaks at 98.77 for precision, recall, and F1-score measures. Because of its precision and efficiency, FireLite is a promising solution for fire detection in resource-constrained environments.

Here we review scanning tunneling microscopy research on the surface determination for various types of kagome materials, including 11-type (CoSn, FeSn, FeGe), 32-type (Fe3Sn2), 13-type (Mn3Sn), 135-type (AV3Sb5, A = K, Rb, Cs), 166-type (TbMn6Sn6, YMn6Sn6 and ScV6Sn6), and 322-type (Co3Sn2S2 and Ni3In2Se2). We first demonstrate that the measured step height between different surfaces typically deviates from the expected value of +-0.4~0.8A, which is owing to the tunneling convolution effect with electronic states and becomes a serious issue for Co3Sn2S2 where the expected Sn-S interlayer distance is 0.6A. Hence, we put forward a general methodology for surface determination as atomic step geometry imaging, which is fundamental but also experimentally challenging to locate the step and to image with atomic precision. We discuss how this method can be used to resolve the surface termination puzzle in Co3Sn2S2. This method provides a natural explanation for the existence of adatoms and vacancies, and beyond using unknown impurity states, we propose and use designer layer-selective substitutional chemical markers to confirm the validity of this method. Finally, we apply this method to determine the surface of a new kagome material Ni3In2Se2, as a cousin of Co3Sn2S2, and we image the underlying kagome geometry on the determined Se surface above the kagome layer, which directly visualizes the p-d hybridization physics. We emphasize that this general method does not rely on theory, but the determined surface identity can provide guidelines for first-principles calculations with adjustable parameters on the surface-dependent local density of states and quasi-particle interference patterns.

Accurate real-time prediction of formation pressure and kick detection is crucial for drilling operations, as it can significantly improve decision-making and the cost-effectiveness of the process. Data-driven models have gained popularity for automating drilling operations by predicting formation pressure and detecting kicks. However, the current literature does not make supporting datasets publicly available to advance research in the field of drilling rigs, thus impeding technological progress in this domain. This paper introduces two new datasets to support researchers in developing intelligent algorithms to enhance oil/gas well drilling research. The datasets include data samples for formation pressure prediction and kick detection with 28 drilling variables and more than 2000 data samples. Principal component regression is employed to forecast formation pressure, while principal component analysis is utilized to identify kicks for the dataset's technical validation. Notably, the R2 and Residual Predictive Deviation scores for principal component regression are 0.78 and 0.922, respectively.

3D Gaussian Splatting (3DGS) has shown its impressive power in novel view synthesis. However, creating relightable 3D assets, especially for objects with ill-defined shapes (e.g., fur), is still a challenging task. For these scenes, the decomposition between the light, geometry, and material is more ambiguous, as neither the surface constraints nor the analytical shading model hold. To address this issue, we propose RNG, a novel representation of relightable neural Gaussians, enabling the relighting of objects with both hard surfaces or fluffy boundaries. We avoid any assumptions in the shading model but maintain feature vectors, which can be further decoded by an MLP into colors, in each Gaussian point. Following prior work, we utilize a point light to reduce the ambiguity and introduce a shadow-aware condition to the network. We additionally propose a depth refinement network to help the shadow computation under the 3DGS framework, leading to better shadow effects under point lights. Furthermore, to avoid the blurriness brought by the alpha-blending in 3DGS, we design a hybrid forward-deferred optimization strategy. As a result, we achieve about $20\times$ faster in training and about $600\times$ faster in rendering than prior work based on neural radiance fields, with $60$ frames per second on an RTX4090.

In this paper, we propose a Newton method for unconstrained set optimization problems to find its weakly minimal solutions with respect to lower set-less ordering. The objective function of the problem under consideration is given by finitely many strongly convex twice continuously differentiable vector-valued functions. At first, with the help of a family of vector optimization problems and the Gerstewitz scalarizing function, we identify a necessary optimality condition for weakly minimal solutions of the considered problem. In the proposed Newton method, we derive a sequence of iterative points that exhibits local convergence to a point which satisfies the derived necessary optimality condition for weakly minimal points. To find this sequence of iterates, we formulate a family of vector optimization problems with the help of a partition set concept. Then, we find a descent direction for this obtained family of vector optimization problems to progress from the current iterate to the next iterate. As the chosen vector optimization problem differed across the iterates, the proposed Newton method for set optimization problems is not a straight extension of that for vector optimization problems. A step-wise algorithm of the entire process is provided. The well-definedness and convergence of the proposed method are analyzed. To establish the convergence of the proposed algorithm under some regularity condition of the stationary points, we derive three key relations: a condition of nonstationarity, the boundedness of the norm of Newton direction, and the existence of step length that satisfies the Armijo condition. We obtain the local superlinear convergence of the proposed method under uniform continuity of the Hessian and local quadratic convergence under Lipschitz continuity of the Hessian.

Recommendation system is such a platform that helps people to easily find out the things they need within a few seconds. It is implemented based on the preferences of similar users or items. In this digital era, the internet has provided us with huge opportunities to use a lot of open resources for our own needs. But there are too many resources on the internet from which finding the precise one is a difficult job. Recommendation system has made this easier for people. Research-paper recommendation system is a system that is developed for people with common research interests using a collaborative filtering recommender system. In this paper, coauthor, keyword, reference, and common citation similarities are calculated using Jaccard Similarity to find the final similarity and to find the top-n similar users. Based on the test of top-n similar users of the target user research paper recommendations have been made. Finally, the accuracy of our recommendation system has been calculated. An impressive result has been found using our proposed system., Comment: 5 pages, 4 figures