Search

PyMilo is an open-source Python package that addresses the limitations of existing Machine Learning (ML) model storage formats by providing a transparent, reliable, and safe method for exporting and deploying trained models. Current formats, such as pickle and other binary formats, have significant problems, such as reliability, safety, and transparency issues. In contrast, PyMilo serializes ML models in a transparent non-executable format, enabling straightforward and safe model exchange, while also facilitating the deserialization and deployment of exported models in production environments. This package aims to provide a seamless, end-to-end solution for the exportation and importation of pre-trained ML models, which simplifies the model development and deployment pipeline., Comment: 7 pages, 5 figures, 2 tables, 3 code blocks

Long sessions of computer use introduce physical and mental health risks, particularly for programmers and intensive computer users. Breathing exercises can improve focus, reduce stress, and overall well-being. However, existing tools for such practices are often app-based, requiring users to leave their workspace. In this technical report, we introduce Nafas, a command-line interface (CLI) application designed specifically for computer users, enabling them to perform breathing exercises directly within the terminal. Nafas offers structured breathing programs with various levels tailored to the needs of busy developers and other intensive computer users., Comment: Link to repository: https://github.com/sepandhaghighi/nafas

Fair graph clustering is crucial for ensuring equitable representation and treatment of diverse communities in network analysis. Traditional methods often ignore disparities among social, economic, and demographic groups, perpetuating biased outcomes and reinforcing inequalities. This study introduces fair graph clustering within the framework of the disparate impact doctrine, treating it as a joint optimization problem integrating clustering quality and fairness constraints. Given the NP-hard nature of this problem, we employ a semidefinite relaxation approach to approximate the underlying optimization problem. For up to medium-sized graphs, we utilize a singular value decomposition-based algorithm, while for larger graphs, we propose a novel algorithm based on the alternative direction method of multipliers. Unlike existing methods, our formulation allows for tuning the trade-off between clustering quality and fairness. Experimental results on graphs generated from the standard stochastic block model demonstrate the superiority of our approach in achieving an optimal accuracy-fairness trade-off compared to state-of-the-art methods.

The objective of this study was to develop an automated pipeline that enhances thyroid disease classification using thyroid scintigraphy images, aiming to decrease assessment time and increase diagnostic accuracy. Anterior thyroid scintigraphy images from 2,643 patients were collected and categorized into diffuse goiter (DG), multinodal goiter (MNG), and thyroiditis (TH) based on clinical reports, and then segmented by an expert. A ResUNet model was trained to perform auto-segmentation. Radiomic features were extracted from both physician (scenario 1) and ResUNet segmentations (scenario 2), followed by omitting highly correlated features using Spearman's correlation, and feature selection using Recursive Feature Elimination (RFE) with XGBoost as the core. All models were trained under leave-one-center-out cross-validation (LOCOCV) scheme, where nine instances of algorithms were iteratively trained and validated on data from eight centers and tested on the ninth for both scenarios separately. Segmentation performance was assessed using the Dice similarity coefficient (DSC), while classification performance was assessed using metrics, such as precision, recall, F1-score, accuracy, area under the Receiver Operating Characteristic (ROC AUC), and area under the precision-recall curve (PRC AUC). ResUNet achieved DSC values of 0.84$\pm$0.03, 0.71$\pm$0.06, and 0.86$\pm$0.02 for MNG, TH, and DG, respectively. Classification in scenario 1 achieved an accuracy of 0.76$\pm$0.04 and a ROC AUC of 0.92$\pm$0.02 while in scenario 2, classification yielded an accuracy of 0.74$\pm$0.05 and a ROC AUC of 0.90$\pm$0.02. The automated pipeline demonstrated comparable performance to physician segmentations on several classification metrics across different classes, effectively reducing assessment time while maintaining high diagnostic accuracy. Code available at: https://github.com/ahxmeds/thyroidiomics.git., Comment: 7 pages, 4 figures, 2 tables

Recent satellite observations have revealed significant anisotropy in the cosmic microwave background (CMB) radiation, a phenomenon that had previously been detected but received limited attention due to its subtlety. With the advent of more precise measurements from satellites, the extent of this anisotropy has become increasingly apparent. This paper examines the CMB radiation by reviewing past research on the causes of CMB anisotropy and presents a new model to explain the observed temperature anisotropy and the anisotropy in the correlation function between temperature and E-mode polarization in the CMB radiation. The proposed model is based on a modified-generalized Compton scattering approach incorporating Loop Quantum Gravity (LQG). We begin by describing the generalized Compton scattering and then discuss the CMB radiation in the context of processes occurring at the last scattering surface. Our findings are derived from the latest observational data from the Planck satellite (2018). In our model, besides the parameters available in the Planck data for the standard model ($\Lambda$CDM), we introduce two novel parameters: $\delta_{L}$, the density of cosmic electrons, and $M^2$, a parameter related to the modified-generalized Compton scattering effects. The results indicate that, based on the 2018 Planck data, small values were obtained for $\delta_{L}$ and $M^{2}$, $\delta_{L}=1.63\pm0.08(10^{-13})$ and $M^2=2.28\pm0.34(10^{-4})$, showing no significant deviation from the standard model. Moreover, increasing the values of $\delta_{L}$ and $M^{2}$ leads to an increase in the range of fluctuations in the CMB temperature anisotropy power spectrum and the correlation function between temperature and E-mode polarization for multipoles $l<500$ until the first peak., Comment: 15 pages, 3 figures. Minor revisions

The present study addresses the challenge of enhancing computational efficiency without compromising accuracy in numerical simulations of vacuum gas dynamics using the direct simulation Monte Carlo (DSMC) method. A technique termed "fixed particle per cell (FPPC)" was employed, which enforces a fixed number of simulator particles across all computational cells. The proposed technique eliminates the need for real-time adjustment of particle weights during simulation, reducing calculation time. Using the SPARTA solver, simulations of rarefied gas flow in a micromixer and rarefied supersonic airflow around a cylinder were conducted to validate the proposed technique. Results demonstrate that applying the FPPC technique effectively reduces computational costs while yielding results comparable to conventional DSMC implementations. Additionally, the application of local grid refinement coupled with the FPPC technique was investigated. The results show that integrating local grid refinement with the FPPC technique enables accurate prediction of flow behaviour in regions with significant gradients. These findings highlight the efficacy of the proposed technique in improving the accuracy and efficiency of numerical simulations of complex vacuum gas dynamics at a reduced computational cost.

Calibration in recommender systems is an important performance criterion that ensures consistency between the distribution of user preference categories and that of recommendations generated by the system. Standard methods for mitigating miscalibration typically assume that user preference profiles are static, and they measure calibration relative to the full history of user's interactions, including possibly outdated and stale preference categories. We conjecture that this approach can lead to recommendations that, while appearing calibrated, in fact, distort users' true preferences. In this paper, we conduct a preliminary investigation of recommendation calibration at a more granular level, taking into account evolving user preferences. By analyzing differently sized training time windows from the most recent interactions to the oldest, we identify the most relevant segment of user's preferences that optimizes the calibration metric. We perform an exploratory analysis with datasets from different domains with distinctive user-interaction characteristics. We demonstrate how the evolving nature of user preferences affects recommendation calibration, and how this effect is manifested differently depending on the characteristics of the data in a given domain. Datasets, codes, and more detailed experimental results are available at: https://github.com/nicolelin13/DynamicCalibrationUMAP., Comment: 8 pages, 4 figures, accepted as LBR paper at UMAP '24 -- ACM Conference on User Modeling, Adaptation and Personalization 2024

There is a need for open-source libraries in emission tomography that (i) use modern and popular backend code to encourage community contributions and (ii) offer support for the multitude of reconstruction techniques available in recent literature, such as those that employ artificial intelligence. The purpose of this research was to create and evaluate a GPU-accelerated, open-source, and user-friendly image reconstruction library, designed to serve as a central platform for the development, validation, and deployment of various tomographic reconstruction algorithms. PyTomography was developed using Python and inherits the GPU-accelerated functionality of PyTorch and parallelproj for fast computations. Its flexible and modular design decouples system matrices, likelihoods, and reconstruction algorithms, simplifying the process of integrating new imaging modalities using various python tools. Example use cases demonstrate the software capabilities in parallel hole SPECT and listmode PET imaging. Overall, we have developed and publicly share PyTomography, a highly optimized and user-friendly software for medical image reconstruction, with a class hierarchy that fosters the development of novel imaging applications., Comment: 28 pages, 7 figures

Americans travel 7 to 9 miles on average for shopping and recreational activities, which is far longer than the 15-minute (walking) city advocated by ecologically-oriented urban planners. This paper provides a comprehensive analysis of local trip behavior in US cities using GPS data on individual trips from 40 million mobile devices. We define local usage as the share of trips made within 15-minutes walking distance from home, and find that the median US city resident makes only 12% of their daily trips within such a short distance. We find that differences in access to local services can explain eighty percent of the variation in 15-minute usage across metropolitan areas and 74 percent of the variation in usage within metropolitan areas. Differences in historic zoning permissiveness within New York suggest a causal link between access and usage, and that less restrictive zoning rules, such as permitting more mixed-use development, would lead to shorter travel times. Finally, we document a strong correlation between local usage and experienced segregation for poorer, but not richer, urbanites, which suggests that 15-minute cities may also exacerbate the social isolation of marginalized communities.

The rise of large language models (LLMs) has transformed numerous natural language processing (NLP) tasks, yet their performance in low and mid-resource languages, such as Farsi, still lags behind resource-rich languages like English. To address this gap, we introduce naab, the largest publicly available, cleaned, and ready-to-use Farsi textual corpus. naab consists of 130GB of data, comprising over 250 million paragraphs and 15 billion words. Named after the Farsi word NAAB (meaning "pure" or "high-grade"), this corpus is openly accessible via Hugging Face, offering researchers a valuable resource for Farsi NLP tasks. In addition to naab, we provide naab-raw, an unprocessed version of the dataset, along with a pre-processing toolkit that allows users to clean their custom corpora. These resources empower NLP researchers and practitioners, particularly those focusing on low-resource languages, to improve the performance of LLMs in their respective domains and bridge the gap between resource-rich and resource-poor languages.

Many models of dark energy have been proposed to describe the universe since the beginning of the Big Bang. In this study, we present a new model of agegraphic dark energy ($NADE$) based on the three generalized uncertainty principles $KMM$ (Kempf, Mangan, Mann), Nouicer and $GUP^{*}$ ( higher orders generalized uncertainty principle).Using the obtained relations from three of types of $GUP$, in the form of three scenarios(Emergent,Intermediate,Logamediate), we consider three different eras of the universe evolution. Also we describe the evolution and expansion of the universe in each subsection. We will plot the obtained relations in these models for better comparatione., Comment: 23 pages, 28 figures, Accepted for publication in IJGMMP